mirror of
https://github.com/VictoriaMetrics/VictoriaMetrics.git
synced 2026-06-05 18:13:06 +03:00
Compare commits
396 Commits
logsql-ski
...
pmm-6401-v
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
4de0514731 | ||
|
|
b65a9f2057 | ||
|
|
0eb733a31e | ||
|
|
6be10fb2ff | ||
|
|
7a503e0c91 | ||
|
|
31a3672982 | ||
|
|
1590ddecba | ||
|
|
b80ebb8bfd | ||
|
|
58ecb90665 | ||
|
|
f7d0d3a229 | ||
|
|
af85055f3a | ||
|
|
ca20478a69 | ||
|
|
c8c20b7f7a | ||
|
|
35263983a6 | ||
|
|
a2c901423b | ||
|
|
382721a3ac | ||
|
|
d688f9a744 | ||
|
|
c060c6d839 | ||
|
|
927ded6c3b | ||
|
|
d4123e135f | ||
|
|
4b86a18105 | ||
|
|
c6154f8f52 | ||
|
|
b4c79fc606 | ||
|
|
b4529df08d | ||
|
|
a63fb21ab2 | ||
|
|
7a19b2a14c | ||
|
|
e06d855636 | ||
|
|
e29fe89791 | ||
|
|
978594f50f | ||
|
|
e16015fa3b | ||
|
|
8033f1705c | ||
|
|
9f1e9c54c8 | ||
|
|
d59e66caa8 | ||
|
|
a2e224593e | ||
|
|
a2d68d249b | ||
|
|
713d3431fe | ||
|
|
02642248cf | ||
|
|
1aebd15549 | ||
|
|
43f0baabcd | ||
|
|
eba0e6dbc0 | ||
|
|
f0f1eb07dc | ||
|
|
bb7b59033d | ||
|
|
e0cef082f4 | ||
|
|
20fedaf7c2 | ||
|
|
efc5190950 | ||
|
|
14ab18375f | ||
|
|
4280cc281a | ||
|
|
740638ad30 | ||
|
|
3d377d0c22 | ||
|
|
99aeb3b21b | ||
|
|
d60c212784 | ||
|
|
dc9537f44e | ||
|
|
1b9a279494 | ||
|
|
f42572e049 | ||
|
|
827cde4c64 | ||
|
|
7c271d6a39 | ||
|
|
b61e9297a1 | ||
|
|
88b4c30021 | ||
|
|
ab535bf127 | ||
|
|
fee8a30f1a | ||
|
|
02ffbfb8dc | ||
|
|
3822d83276 | ||
|
|
8561bb48fd | ||
|
|
a32a9070c1 | ||
|
|
b596228765 | ||
|
|
d0f9a5d4c4 | ||
|
|
472a9360e6 | ||
|
|
b00fcad604 | ||
|
|
3d755041c3 | ||
|
|
e22a9d6ba6 | ||
|
|
9d7dc73038 | ||
|
|
63d9048990 | ||
|
|
8db1fd2f78 | ||
|
|
8f0afc656e | ||
|
|
be94882ada | ||
|
|
ff990ab0c5 | ||
|
|
5c8a01aecc | ||
|
|
2ce4d04d8e | ||
|
|
b026ebe91e | ||
|
|
c2b724d3ab | ||
|
|
e4a61581e1 | ||
|
|
a38bf70679 | ||
|
|
7b41c9ac72 | ||
|
|
c1d42f3288 | ||
|
|
4167344edb | ||
|
|
44e388ee6a | ||
|
|
b8ab0b2f31 | ||
|
|
dcc4b84319 | ||
|
|
37f48cdaa5 | ||
|
|
a39140baef | ||
|
|
30c0a37032 | ||
|
|
32e46ea35f | ||
|
|
6faaefef7b | ||
|
|
5cd89aaaa1 | ||
|
|
3a21fde0f3 | ||
|
|
274627943e | ||
|
|
21140318cc | ||
|
|
3f5bc2adce | ||
|
|
a5975c31c2 | ||
|
|
fad61eafc1 | ||
|
|
30453af768 | ||
|
|
7737321133 | ||
|
|
a2ab1f0ec9 | ||
|
|
a092df3f84 | ||
|
|
c3f178aa53 | ||
|
|
393e7636be | ||
|
|
ebc200846c | ||
|
|
0158237875 | ||
|
|
be5bbb7ba7 | ||
|
|
b79f02de21 | ||
|
|
ac58ab9664 | ||
|
|
0613ac5d02 | ||
|
|
22e48e6517 | ||
|
|
1f0432b5c1 | ||
|
|
079953b4ea | ||
|
|
d92da32041 | ||
|
|
8548650c2d | ||
|
|
2dd82e8355 | ||
|
|
bf0b5602d0 | ||
|
|
e25d05f992 | ||
|
|
5ce8fa8b10 | ||
|
|
881f22ca62 | ||
|
|
38294e2f17 | ||
|
|
2d909f4979 | ||
|
|
0821298471 | ||
|
|
fa5cda60d9 | ||
|
|
700eb5bb1d | ||
|
|
70bcc97d1c | ||
|
|
0074539441 | ||
|
|
fe0ab3840f | ||
|
|
c4fc87f8b8 | ||
|
|
8e3198ba29 | ||
|
|
6c7c0790a0 | ||
|
|
33343695a9 | ||
|
|
db553f12bc | ||
|
|
07fe2c5361 | ||
|
|
22e87b0088 | ||
|
|
f105e2e8c3 | ||
|
|
20414b3038 | ||
|
|
fcb7ef68f8 | ||
|
|
626142ab90 | ||
|
|
fd1b8be2e5 | ||
|
|
d39ba2536e | ||
|
|
e2c4578751 | ||
|
|
6ad7b0619c | ||
|
|
3a15bc761b | ||
|
|
bd79706eb3 | ||
|
|
e69fb9f3cf | ||
|
|
1a9cb85647 | ||
|
|
a80f0c9f42 | ||
|
|
4db1d24973 | ||
|
|
1c9f5b3580 | ||
|
|
9682c23786 | ||
|
|
bd2bb272f0 | ||
|
|
6111abd0e6 | ||
|
|
3f3f664b76 | ||
|
|
d1c6fb74fc | ||
|
|
b9668d5294 | ||
|
|
96160000e0 | ||
|
|
28e961e511 | ||
|
|
628e87e727 | ||
|
|
3600c97ad7 | ||
|
|
bb154f8829 | ||
|
|
d2e293b5c9 | ||
|
|
e80ddbebd4 | ||
|
|
bdd4940140 | ||
|
|
a8fee2d9b6 | ||
|
|
2dbbf51ea9 | ||
|
|
cd5cc4ec81 | ||
|
|
549d430907 | ||
|
|
69aef55ae7 | ||
|
|
274145af2d | ||
|
|
c444f7e2b9 | ||
|
|
10f41ea5f9 | ||
|
|
46f803fa7a | ||
|
|
ffe9bd248c | ||
|
|
151286f5a8 | ||
|
|
77a1af4f7f | ||
|
|
c83ff99e0d | ||
|
|
4a0c9a1069 | ||
|
|
2fd56ddb38 | ||
|
|
b42e5627fb | ||
|
|
57375e72fa | ||
|
|
0746766d95 | ||
|
|
6712a8269c | ||
|
|
4e20ea4b59 | ||
|
|
44dfb2ec0d | ||
|
|
e7b4e657a1 | ||
|
|
cd91c29243 | ||
|
|
8b8e547dc8 | ||
|
|
34a6b1fa3b | ||
|
|
af37ec8020 | ||
|
|
fff8ff946f | ||
|
|
fdccca238a | ||
|
|
1b24afec36 | ||
|
|
cacd3d6f6d | ||
|
|
8632b8200e | ||
|
|
0445ad59db | ||
|
|
f7b52b64a3 | ||
|
|
7fc62feddc | ||
|
|
0ea0168d98 | ||
|
|
3dec16702a | ||
|
|
993ecbb141 | ||
|
|
35eb512efa | ||
|
|
7f01217c3c | ||
|
|
2398b4a10a | ||
|
|
5a60387eea | ||
|
|
2685992ca9 | ||
|
|
ee63748753 | ||
|
|
620b0d11b7 | ||
|
|
316cac2c0b | ||
|
|
9eb61e67af | ||
|
|
a7333a7380 | ||
|
|
ee5bd20157 | ||
|
|
d713bdec20 | ||
|
|
6a5d6244d4 | ||
|
|
095feeee41 | ||
|
|
9dd493363c | ||
|
|
d964b04efd | ||
|
|
ec01a188fd | ||
|
|
40112df441 | ||
|
|
9e74fe3145 | ||
|
|
2c22e168f5 | ||
|
|
5747b78f6f | ||
|
|
d9166e899e | ||
|
|
38699170c9 | ||
|
|
5b4f7bbc0c | ||
|
|
db85f4a1cb | ||
|
|
780b2a139a | ||
|
|
9d2805320b | ||
|
|
e636cab272 | ||
|
|
90a1502335 | ||
|
|
f8a05d4ada | ||
|
|
ae64c2db61 | ||
|
|
37a4347a37 | ||
|
|
20cdb879e7 | ||
|
|
7917486d78 | ||
|
|
107607bf47 | ||
|
|
78b028064f | ||
|
|
db286fdd73 | ||
|
|
e8ff658b2e | ||
|
|
e1668e7441 | ||
|
|
0d0469cc80 | ||
|
|
8d6d4e8033 | ||
|
|
b894f25f21 | ||
|
|
b6bae2f05f | ||
|
|
9e15858baf | ||
|
|
3f5b1084eb | ||
|
|
c2e9be96a7 | ||
|
|
a72dadb8f4 | ||
|
|
08219faf8d | ||
|
|
288620ca40 | ||
|
|
2847c84a7b | ||
|
|
6a64823581 | ||
|
|
b94e986710 | ||
|
|
a29565d1bd | ||
|
|
39332cfc5c | ||
|
|
d07d2811d4 | ||
|
|
206e451cae | ||
|
|
307034fc2f | ||
|
|
c149132b14 | ||
|
|
6dd7a90c7c | ||
|
|
dc5507754f | ||
|
|
c68663deee | ||
|
|
114a40e63f | ||
|
|
163f2a46fd | ||
|
|
375c46cb1f | ||
|
|
bb2d1128b8 | ||
|
|
479b9da827 | ||
|
|
62857fc30e | ||
|
|
253315b1fe | ||
|
|
efe6e30008 | ||
|
|
bc2512abdd | ||
|
|
a07f8017ba | ||
|
|
cf70b766eb | ||
|
|
b00732074c | ||
|
|
8df8c414de | ||
|
|
ce844238a4 | ||
|
|
452720c5dc | ||
|
|
bbca1740c1 | ||
|
|
e1c85395eb | ||
|
|
b348114dab | ||
|
|
bb54e34dc5 | ||
|
|
e0d0b9447e | ||
|
|
fae6e4fc85 | ||
|
|
e49bf9bc73 | ||
|
|
a142390014 | ||
|
|
bceb8082f6 | ||
|
|
276969500e | ||
|
|
030e3a63f2 | ||
|
|
1c5e0564af | ||
|
|
b8300338f0 | ||
|
|
660c3c7251 | ||
|
|
80ba07dc95 | ||
|
|
11ded82e60 | ||
|
|
558b390ebc | ||
|
|
343f444e87 | ||
|
|
16884c20c0 | ||
|
|
7d44cdd8ce | ||
|
|
5d2394ad9b | ||
|
|
8582fba4b1 | ||
|
|
b045f506f2 | ||
|
|
6197440bb9 | ||
|
|
966e9c227a | ||
|
|
edb2ab7d8e | ||
|
|
0ad887fd4d | ||
|
|
d5dde7f6b1 | ||
|
|
a54ca9bd8f | ||
|
|
3588687f84 | ||
|
|
687eb4ab00 | ||
|
|
b04fece006 | ||
|
|
d0c364d93d | ||
|
|
63c88d8ea2 | ||
|
|
dc6636e2b2 | ||
|
|
c13f1d99e0 | ||
|
|
079888f719 | ||
|
|
b68264b4f5 | ||
|
|
aed049f660 | ||
|
|
7fcc0a1ef0 | ||
|
|
48951073c4 | ||
|
|
d0dfcb72b4 | ||
|
|
4cf7a55808 | ||
|
|
d72fc60108 | ||
|
|
0b92e18047 | ||
|
|
aa8ea16160 | ||
|
|
f5e70f0ab9 | ||
|
|
9e10d5083e | ||
|
|
30c2d75815 | ||
|
|
0e80f3f45a | ||
|
|
6e3cbae0b3 | ||
|
|
a5583ddaff | ||
|
|
5db9e82e54 | ||
|
|
80676cf1fd | ||
|
|
ba4c49dde6 | ||
|
|
35e5e8ff1e | ||
|
|
4cdbc4642d | ||
|
|
23c0fb1efc | ||
|
|
441d3e4b3f | ||
|
|
a0ea5777f0 | ||
|
|
fb006fc6c0 | ||
|
|
8593358965 | ||
|
|
d0311b7fe5 | ||
|
|
4edd38a906 | ||
|
|
56054f4eb7 | ||
|
|
0ff0787797 | ||
|
|
f9c706e186 | ||
|
|
d74d22460c | ||
|
|
d1193c87a8 | ||
|
|
4f311e5827 | ||
|
|
142e6b6ecf | ||
|
|
1b4ef473b9 | ||
|
|
8beb1f9519 | ||
|
|
501fd8efd9 | ||
|
|
45f2ba2572 | ||
|
|
cb2342029e | ||
|
|
ff0088ceec | ||
|
|
afe6d2e736 | ||
|
|
e1a6262302 | ||
|
|
f000a10cd0 | ||
|
|
4aee6ef4c0 | ||
|
|
f4dfacd493 | ||
|
|
fb2d4e56ce | ||
|
|
36b748dfc7 | ||
|
|
c625dc5b96 | ||
|
|
e32620afa1 | ||
|
|
3f298272a8 | ||
|
|
7a473798b7 | ||
|
|
00ce906d97 | ||
|
|
41c9565aa1 | ||
|
|
56303aee5b | ||
|
|
8d8e2ccf5f | ||
|
|
8772cb617c | ||
|
|
65fbfc5cbc | ||
|
|
1b389674c0 | ||
|
|
98529e16ee | ||
|
|
1b112405a8 | ||
|
|
8bbc83e85e | ||
|
|
8349140744 | ||
|
|
4dc13754d8 | ||
|
|
83b7eb8ca6 | ||
|
|
e5ef3288dd | ||
|
|
e7f2907138 | ||
|
|
757c5cfbe0 | ||
|
|
317ddb84b9 | ||
|
|
2b1d0510fa | ||
|
|
40d2f6fee4 | ||
|
|
9fbb84d5c2 | ||
|
|
bdaa9a91f3 | ||
|
|
1a91da35be | ||
|
|
f85be226bb | ||
|
|
8df5a3c5f6 | ||
|
|
9d3eb3f4b8 | ||
|
|
2cd48959d4 | ||
|
|
8fc8874db4 | ||
|
|
ff1cbb524e | ||
|
|
a70df4bd83 |
4
.github/ISSUE_TEMPLATE/bug_report.yml
vendored
4
.github/ISSUE_TEMPLATE/bug_report.yml
vendored
@@ -60,8 +60,8 @@ body:
|
||||
|
||||
For VictoriaMetrics health-state issues please provide full-length screenshots
|
||||
of Grafana dashboards if possible:
|
||||
* [Grafana dashboard for single-node VictoriaMetrics](https://grafana.com/grafana/dashboards/10229/)
|
||||
* [Grafana dashboard for VictoriaMetrics cluster](https://grafana.com/grafana/dashboards/11176/)
|
||||
* [Grafana dashboard for single-node VictoriaMetrics](https://grafana.com/grafana/dashboards/10229-victoriametrics/)
|
||||
* [Grafana dashboard for VictoriaMetrics cluster](https://grafana.com/grafana/dashboards/11176-victoriametrics-cluster/)
|
||||
|
||||
See how to setup monitoring here:
|
||||
* [monitoring for single-node VictoriaMetrics](https://docs.victoriametrics.com/#monitoring)
|
||||
|
||||
@@ -1,35 +0,0 @@
|
||||
### Describe Your Changes
|
||||
|
||||
Please provide a brief description of the changes you made. Be as specific as possible to help others understand the purpose and impact of your modifications.
|
||||
|
||||
### Checklist
|
||||
|
||||
The following checks are mandatory:
|
||||
|
||||
- [ ] I have read the [Contributing Guidelines](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/CONTRIBUTING.md)
|
||||
- [ ] All commits are signed and include `Signed-off-by` line. Use `git commit -s` to include `Signed-off-by` your commits. See this [doc](https://git-scm.com/book/en/v2/Git-Tools-Signing-Your-Work) about how to sign your commits.
|
||||
- [ ] Tests are passing locally. Use `make test` to run all tests locally.
|
||||
- [ ] Linting is passing locally. Use `make check-all` to run all linters locally.
|
||||
|
||||
Further checks are optional for External Contributions:
|
||||
|
||||
- [ ] Include a link to the GitHub issue in the commit message, if issue exists.
|
||||
- [ ] Mention the change in the [Changelog](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/docs/CHANGELOG.md). Explain what has changed and why. If there is a related issue or documentation change - link them as well.
|
||||
|
||||
Tips for writing a good changelog message::
|
||||
|
||||
* Write a human-readable changelog message that describes the problem and solution.
|
||||
* Include a link to the issue or pull request in your changelog message.
|
||||
* Use specific language identifying the fix, such as an error message, metric name, or flag name.
|
||||
* Provide a link to the relevant documentation for any new features you add or modify.
|
||||
|
||||
- [ ] After your pull request is merged, please add a message to the issue with instructions for how to test the fix or try the feature you added. Here is an [example](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/4048#issuecomment-1546453726)
|
||||
- [ ] Do not close the original issue before the change is released. Please note, in some cases Github can automatically close the issue once PR is merged. Re-open the issue in such case.
|
||||
- [ ] If the change somehow affects public interfaces (a new flag was added or updated, or some behavior has changed) - add the corresponding change to documentation.
|
||||
|
||||
|
||||
Examples of good changelog messages:
|
||||
|
||||
1. FEATURE: [vmagent](https://docs.victoriametrics.com/vmagent.html): add support for [VictoriaMetrics remote write protocol](https://docs.victoriametrics.com/vmagent.html#victoriametrics-remote-write-protocol) when [sending / receiving data to / from Kafka](https://docs.victoriametrics.com/vmagent.html#kafka-integration). This protocol allows saving egress network bandwidth costs when sending data from `vmagent` to `Kafka` located in another datacenter or availability zone. See [this feature request](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/1225).
|
||||
|
||||
2. BUGFIX: [stream aggregation](https://docs.victoriametrics.com/stream-aggregation.html): suppress `series after dedup` error message in logs when `-remoteWrite.streamAggr.dedupInterval` command-line flag is set at [vmagent](https://docs.victoriametrics.com/vmgent.html) or when `-streamAggr.dedupInterval` command-line flag is set at [single-node VictoriaMetrics](https://docs.victoriametrics.com/).
|
||||
26
.github/workflows/check-licenses.yml
vendored
26
.github/workflows/check-licenses.yml
vendored
@@ -14,25 +14,13 @@ jobs:
|
||||
name: Build
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Setup Go
|
||||
uses: actions/setup-go@main
|
||||
with:
|
||||
go-version: 1.21.4
|
||||
id: go
|
||||
- name: Code checkout
|
||||
uses: actions/checkout@master
|
||||
|
||||
- name: Setup Go
|
||||
id: go
|
||||
uses: actions/setup-go@v5
|
||||
with:
|
||||
go-version: stable
|
||||
cache: false
|
||||
|
||||
- name: Cache Go artifacts
|
||||
uses: actions/cache@v4
|
||||
with:
|
||||
path: |
|
||||
~/.cache/go-build
|
||||
~/go/pkg/mod
|
||||
~/go/bin
|
||||
key: go-artifacts-${{ runner.os }}-check-licenses-${{ steps.go.outputs.go-version }}-${{ hashFiles('go.sum', 'Makefile', 'app/**/Makefile') }}
|
||||
restore-keys: go-artifacts-${{ runner.os }}-check-licenses-
|
||||
|
||||
- name: Check License
|
||||
run: make check-licenses
|
||||
run: |
|
||||
make check-licenses
|
||||
|
||||
4
.github/workflows/codeql-analysis-js.yml
vendored
4
.github/workflows/codeql-analysis-js.yml
vendored
@@ -36,11 +36,11 @@ jobs:
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Initialize CodeQL
|
||||
uses: github/codeql-action/init@v3
|
||||
uses: github/codeql-action/init@v2
|
||||
with:
|
||||
languages: ${{ matrix.language }}
|
||||
|
||||
- name: Perform CodeQL Analysis
|
||||
uses: github/codeql-action/analyze@v3
|
||||
uses: github/codeql-action/analyze@v2
|
||||
with:
|
||||
category: "javascript"
|
||||
|
||||
25
.github/workflows/codeql-analysis.yml
vendored
25
.github/workflows/codeql-analysis.yml
vendored
@@ -55,27 +55,16 @@ jobs:
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Set up Go
|
||||
id: go
|
||||
uses: actions/setup-go@v5
|
||||
uses: actions/setup-go@v4
|
||||
with:
|
||||
go-version: stable
|
||||
cache: false
|
||||
if: ${{ matrix.language == 'go' }}
|
||||
|
||||
- name: Cache Go artifacts
|
||||
uses: actions/cache@v4
|
||||
with:
|
||||
path: |
|
||||
~/.cache/go-build
|
||||
~/go/pkg/mod
|
||||
~/go/bin
|
||||
key: go-artifacts-${{ runner.os }}-codeql-analyze-${{ steps.go.outputs.go-version }}-${{ hashFiles('go.sum', 'Makefile', 'app/**/Makefile') }}
|
||||
restore-keys: go-artifacts-${{ runner.os }}-codeql-analyze-
|
||||
go-version: 1.21.4
|
||||
check-latest: true
|
||||
cache: true
|
||||
if: ${{ matrix.language == 'go' }}
|
||||
|
||||
# Initializes the CodeQL tools for scanning.
|
||||
- name: Initialize CodeQL
|
||||
uses: github/codeql-action/init@v3
|
||||
uses: github/codeql-action/init@v2
|
||||
with:
|
||||
languages: ${{ matrix.language }}
|
||||
# If you wish to specify custom queries, you can do so here or in a config file.
|
||||
@@ -86,7 +75,7 @@ jobs:
|
||||
# Autobuild attempts to build any compiled languages (C/C++, C#, or Java).
|
||||
# If this step fails, then you should remove it and run the build manually (see below)
|
||||
- name: Autobuild
|
||||
uses: github/codeql-action/autobuild@v3
|
||||
uses: github/codeql-action/autobuild@v2
|
||||
|
||||
# ℹ️ Command-line programs to run using the OS shell.
|
||||
# 📚 https://git.io/JvXDl
|
||||
@@ -100,4 +89,4 @@ jobs:
|
||||
# make release
|
||||
|
||||
- name: Perform CodeQL Analysis
|
||||
uses: github/codeql-action/analyze@v3
|
||||
uses: github/codeql-action/analyze@v2
|
||||
|
||||
102
.github/workflows/main.yml
vendored
102
.github/workflows/main.yml
vendored
@@ -7,8 +7,6 @@ on:
|
||||
paths-ignore:
|
||||
- "docs/**"
|
||||
- "**.md"
|
||||
- "dashboards/**"
|
||||
- "deployment/**.yml"
|
||||
pull_request:
|
||||
branches:
|
||||
- master
|
||||
@@ -16,8 +14,6 @@ on:
|
||||
paths-ignore:
|
||||
- "docs/**"
|
||||
- "**.md"
|
||||
- "dashboards/**"
|
||||
- "deployment/**.yml"
|
||||
permissions:
|
||||
contents: read
|
||||
|
||||
@@ -34,55 +30,18 @@ jobs:
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Setup Go
|
||||
id: go
|
||||
uses: actions/setup-go@v5
|
||||
uses: actions/setup-go@v4
|
||||
with:
|
||||
go-version: stable
|
||||
cache: false
|
||||
go-version: 1.21.4
|
||||
check-latest: true
|
||||
cache: true
|
||||
|
||||
- name: Cache Go artifacts
|
||||
uses: actions/cache@v4
|
||||
with:
|
||||
path: |
|
||||
~/.cache/go-build
|
||||
~/go/pkg/mod
|
||||
~/go/bin
|
||||
key: go-artifacts-${{ runner.os }}-check-all-${{ steps.go.outputs.go-version }}-${{ hashFiles('go.sum', 'Makefile', 'app/**/Makefile') }}
|
||||
restore-keys: go-artifacts-${{ runner.os }}-check-all-
|
||||
|
||||
- name: Run check-all
|
||||
- name: Dependencies
|
||||
run: |
|
||||
make install-golangci-lint
|
||||
make check-all
|
||||
git diff --exit-code
|
||||
|
||||
build:
|
||||
needs: lint
|
||||
name: build
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Code checkout
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Setup Go
|
||||
id: go
|
||||
uses: actions/setup-go@v5
|
||||
with:
|
||||
go-version: stable
|
||||
cache: false
|
||||
|
||||
- name: Cache Go artifacts
|
||||
uses: actions/cache@v4
|
||||
with:
|
||||
path: |
|
||||
~/.cache/go-build
|
||||
~/go/pkg/mod
|
||||
~/go/bin
|
||||
key: go-artifacts-${{ runner.os }}-crossbuild-${{ steps.go.outputs.go-version }}-${{ hashFiles('go.sum', 'Makefile', 'app/**/Makefile') }}
|
||||
restore-keys: go-artifacts-${{ runner.os }}-crossbuild-
|
||||
|
||||
- name: Build
|
||||
run: make crossbuild
|
||||
|
||||
test:
|
||||
needs: lint
|
||||
strategy:
|
||||
@@ -95,26 +54,43 @@ jobs:
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Setup Go
|
||||
id: go
|
||||
uses: actions/setup-go@v5
|
||||
uses: actions/setup-go@v4
|
||||
with:
|
||||
go-version: stable
|
||||
cache: false
|
||||
|
||||
- name: Cache Go artifacts
|
||||
uses: actions/cache@v4
|
||||
with:
|
||||
path: |
|
||||
~/.cache/go-build
|
||||
~/go/pkg/mod
|
||||
~/go/bin
|
||||
key: go-artifacts-${{ runner.os }}-${{ matrix.scenario }}-${{ steps.go.outputs.go-version }}-${{ hashFiles('go.sum', 'Makefile', 'app/**/Makefile') }}
|
||||
restore-keys: go-artifacts-${{ runner.os }}-${{ matrix.scenario }}-
|
||||
go-version: 1.21.4
|
||||
check-latest: true
|
||||
cache: true
|
||||
|
||||
- name: run tests
|
||||
run: make ${{ matrix.scenario}}
|
||||
run: |
|
||||
make ${{ matrix.scenario}}
|
||||
|
||||
- name: Publish coverage
|
||||
uses: codecov/codecov-action@v4
|
||||
uses: codecov/codecov-action@v3
|
||||
with:
|
||||
file: ./coverage.txt
|
||||
|
||||
build:
|
||||
needs: test
|
||||
name: build
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Code checkout
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Setup Go
|
||||
id: go
|
||||
uses: actions/setup-go@v4
|
||||
with:
|
||||
go-version: 1.21.4
|
||||
check-latest: true
|
||||
cache: true
|
||||
|
||||
- uses: actions/cache@v3
|
||||
with:
|
||||
path: gocache-for-docker
|
||||
key: gocache-docker-${{ runner.os }}-${{ steps.go.outputs.go-version }}-${{ hashFiles('go.mod') }}
|
||||
|
||||
- name: Build
|
||||
run: |
|
||||
make victoria-metrics-crossbuild
|
||||
make vmuitils-crossbuild
|
||||
|
||||
15
.github/workflows/sync-docs.yml
vendored
15
.github/workflows/sync-docs.yml
vendored
@@ -6,6 +6,9 @@ on:
|
||||
paths:
|
||||
- 'docs/**'
|
||||
workflow_dispatch: {}
|
||||
env:
|
||||
PAGEFIND_VERSION: "1.0.3"
|
||||
HUGO_VERSION: "latest"
|
||||
permissions:
|
||||
contents: read # This is required for actions/checkout and to commit back image update
|
||||
deployments: write
|
||||
@@ -24,6 +27,16 @@ jobs:
|
||||
repository: VictoriaMetrics/vmdocs
|
||||
token: ${{ secrets.VM_BOT_GH_TOKEN }}
|
||||
path: docs
|
||||
- uses: peaceiris/actions-hugo@v2
|
||||
with:
|
||||
hugo-version: ${{env.HUGO_VERSION}}
|
||||
extended: true
|
||||
- name: Install PageFind #install the static search engine for index build
|
||||
uses: supplypike/setup-bin@v3
|
||||
with:
|
||||
uri: "https://github.com/CloudCannon/pagefind/releases/download/v${{env.PAGEFIND_VERSION}}/pagefind-v${{env.PAGEFIND_VERSION}}-x86_64-unknown-linux-musl.tar.gz"
|
||||
name: "pagefind"
|
||||
version: ${{env.PAGEFIND_VERSION}}
|
||||
- name: Import GPG key
|
||||
uses: crazy-max/ghaction-import-gpg@v5
|
||||
with:
|
||||
@@ -38,11 +51,13 @@ jobs:
|
||||
calculatedSha=$(git rev-parse --short ${{ github.sha }})
|
||||
echo "short_sha=$calculatedSha" >> $GITHUB_OUTPUT
|
||||
working-directory: main
|
||||
|
||||
- name: update code and commit
|
||||
run: |
|
||||
rm -rf content
|
||||
cp -r ../main/docs content
|
||||
make clean-after-copy
|
||||
make build-search-index
|
||||
git config --global user.name "${{ steps.import-gpg.outputs.email }}"
|
||||
git config --global user.email "${{ steps.import-gpg.outputs.email }}"
|
||||
git add .
|
||||
|
||||
1
.gitignore
vendored
1
.gitignore
vendored
@@ -22,4 +22,3 @@ Gemfile.lock
|
||||
/_site
|
||||
_site
|
||||
*.tmp
|
||||
/docs/.jekyll-metadata
|
||||
@@ -14,8 +14,3 @@ We are open to third-party pull requests provided they follow [KISS design princ
|
||||
- Avoid automated decisions, which may hurt cluster availability, consistency or performance.
|
||||
|
||||
Adhering `KISS` principle simplifies the resulting code and architecture, so it can be reviewed, understood and verified by many people.
|
||||
|
||||
Before sending a pull request please check the following:
|
||||
- [ ] All commits are signed and include `Signed-off-by` line. Use `git commit -s` to include `Signed-off-by` your commits. See this [doc](https://git-scm.com/book/en/v2/Git-Tools-Signing-Your-Work) about how to sign your commits.
|
||||
- [ ] Tests are passing locally. Use `make test` to run all tests locally.
|
||||
- [ ] Linting is passing locally. Use `make check-all` to run all linters locally.
|
||||
|
||||
2
LICENSE
2
LICENSE
@@ -175,7 +175,7 @@
|
||||
|
||||
END OF TERMS AND CONDITIONS
|
||||
|
||||
Copyright 2019-2024 VictoriaMetrics, Inc.
|
||||
Copyright 2019-2023 VictoriaMetrics, Inc.
|
||||
|
||||
Licensed under the Apache License, Version 2.0 (the "License");
|
||||
you may not use this file except in compliance with the License.
|
||||
|
||||
59
Makefile
59
Makefile
@@ -1,7 +1,5 @@
|
||||
PKG_PREFIX := github.com/VictoriaMetrics/VictoriaMetrics
|
||||
|
||||
MAKE_CONCURRENCY ?= $(shell getconf _NPROCESSORS_ONLN)
|
||||
MAKE_PARALLEL := $(MAKE) -j $(MAKE_CONCURRENCY)
|
||||
DATEINFO_TAG ?= $(shell date -u +'%Y%m%d-%H%M%S')
|
||||
BUILDINFO_TAG ?= $(shell echo $$(git describe --long --all | tr '/' '-')$$( \
|
||||
git diff-index --quiet HEAD -- || echo '-dirty-'$$(git diff-index -u HEAD | openssl sha1 | cut -d' ' -f2 | cut -c 1-8)))
|
||||
@@ -17,7 +15,6 @@ GO_BUILDINFO = -X '$(PKG_PREFIX)/lib/buildinfo.Version=$(APP_NAME)-$(DATEINFO_TA
|
||||
.PHONY: $(MAKECMDGOALS)
|
||||
|
||||
include app/*/Makefile
|
||||
include docs/Makefile
|
||||
include deployment/*/Makefile
|
||||
include dashboards/Makefile
|
||||
include snap/local/Makefile
|
||||
@@ -166,26 +163,24 @@ vmutils-windows-amd64: \
|
||||
vmrestore-windows-amd64 \
|
||||
vmctl-windows-amd64
|
||||
|
||||
crossbuild:
|
||||
$(MAKE_PARALLEL) victoria-metrics-crossbuild vmutils-crossbuild
|
||||
|
||||
victoria-metrics-crossbuild: \
|
||||
victoria-metrics-linux-386 \
|
||||
victoria-metrics-linux-amd64 \
|
||||
victoria-metrics-linux-arm64 \
|
||||
victoria-metrics-linux-arm \
|
||||
victoria-metrics-linux-386 \
|
||||
victoria-metrics-linux-ppc64le \
|
||||
victoria-metrics-darwin-amd64 \
|
||||
victoria-metrics-darwin-arm64 \
|
||||
victoria-metrics-freebsd-amd64 \
|
||||
victoria-metrics-openbsd-amd64 \
|
||||
victoria-metrics-windows-amd64
|
||||
victoria-metrics-openbsd-amd64
|
||||
|
||||
vmutils-crossbuild: \
|
||||
vmutils-linux-386 \
|
||||
vmutils-linux-amd64 \
|
||||
vmutils-linux-arm64 \
|
||||
vmutils-linux-arm \
|
||||
vmutils-linux-386 \
|
||||
vmutils-linux-ppc64le \
|
||||
vmutils-darwin-amd64 \
|
||||
vmutils-darwin-arm64 \
|
||||
@@ -195,15 +190,14 @@ vmutils-crossbuild: \
|
||||
|
||||
publish-release:
|
||||
rm -rf bin/*
|
||||
git checkout $(TAG) && $(MAKE) release && LATEST_TAG=stable $(MAKE) publish && \
|
||||
git checkout $(TAG)-cluster && $(MAKE) release && LATEST_TAG=cluster-stable $(MAKE) publish && \
|
||||
git checkout $(TAG)-enterprise && $(MAKE) release && LATEST_TAG=enterprise-stable $(MAKE) publish && \
|
||||
git checkout $(TAG)-enterprise-cluster && $(MAKE) release && LATEST_TAG=enterprise-cluster-stable $(MAKE) publish
|
||||
git checkout $(TAG) && LATEST_TAG=stable $(MAKE) release publish && \
|
||||
git checkout $(TAG)-cluster && LATEST_TAG=cluster-stable $(MAKE) release publish && \
|
||||
git checkout $(TAG)-enterprise && LATEST_TAG=enterprise-stable $(MAKE) release publish && \
|
||||
git checkout $(TAG)-enterprise-cluster && LATEST_TAG=enterprise-cluster-stable $(MAKE) release publish
|
||||
|
||||
release:
|
||||
$(MAKE_PARALLEL) \
|
||||
release-victoria-metrics \
|
||||
release-vmutils
|
||||
release: \
|
||||
release-victoria-metrics \
|
||||
release-vmutils
|
||||
|
||||
release-victoria-metrics: \
|
||||
release-victoria-metrics-linux-386 \
|
||||
@@ -262,16 +256,16 @@ release-victoria-metrics-windows-goarch: victoria-metrics-windows-$(GOARCH)-prod
|
||||
cd bin && rm -rf \
|
||||
victoria-metrics-windows-$(GOARCH)-prod.exe
|
||||
|
||||
release-victoria-logs:
|
||||
$(MAKE_PARALLEL) release-victoria-logs-linux-386 \
|
||||
release-victoria-logs-linux-amd64 \
|
||||
release-victoria-logs-linux-arm \
|
||||
release-victoria-logs-linux-arm64 \
|
||||
release-victoria-logs-darwin-amd64 \
|
||||
release-victoria-logs-darwin-arm64 \
|
||||
release-victoria-logs-freebsd-amd64 \
|
||||
release-victoria-logs-openbsd-amd64 \
|
||||
release-victoria-logs-windows-amd64
|
||||
release-victoria-logs: \
|
||||
release-victoria-logs-linux-386 \
|
||||
release-victoria-logs-linux-amd64 \
|
||||
release-victoria-logs-linux-arm \
|
||||
release-victoria-logs-linux-arm64 \
|
||||
release-victoria-logs-darwin-amd64 \
|
||||
release-victoria-logs-darwin-arm64 \
|
||||
release-victoria-logs-freebsd-amd64 \
|
||||
release-victoria-logs-openbsd-amd64 \
|
||||
release-victoria-logs-windows-amd64
|
||||
|
||||
release-victoria-logs-linux-386:
|
||||
GOOS=linux GOARCH=386 $(MAKE) release-victoria-logs-goos-goarch
|
||||
@@ -466,7 +460,7 @@ benchmark-pure:
|
||||
vendor-update:
|
||||
go get -u -d ./lib/...
|
||||
go get -u -d ./app/...
|
||||
go mod tidy -compat=1.21
|
||||
go mod tidy -compat=1.20
|
||||
go mod vendor
|
||||
|
||||
app-local:
|
||||
@@ -492,7 +486,7 @@ golangci-lint: install-golangci-lint
|
||||
golangci-lint run
|
||||
|
||||
install-golangci-lint:
|
||||
which golangci-lint || curl -sSfL https://raw.githubusercontent.com/golangci/golangci-lint/master/install.sh | sh -s -- -b $(shell go env GOPATH)/bin v1.57.1
|
||||
which golangci-lint || curl -sSfL https://raw.githubusercontent.com/golangci/golangci-lint/master/install.sh | sh -s -- -b $(shell go env GOPATH)/bin v1.55.1
|
||||
|
||||
govulncheck: install-govulncheck
|
||||
govulncheck ./...
|
||||
@@ -535,3 +529,12 @@ copy-docs:
|
||||
docs-sync:
|
||||
SRC=README.md DST=docs/README.md OLD_URL='' ORDER=0 TITLE=VictoriaMetrics $(MAKE) copy-docs
|
||||
SRC=README.md DST=docs/Single-server-VictoriaMetrics.md OLD_URL='/Single-server-VictoriaMetrics.html' TITLE=VictoriaMetrics ORDER=1 $(MAKE) copy-docs
|
||||
SRC=app/vmagent/README.md DST=docs/vmagent.md OLD_URL='/vmagent.html' ORDER=3 TITLE=vmagent $(MAKE) copy-docs
|
||||
SRC=app/vmalert/README.md DST=docs/vmalert.md OLD_URL='/vmalert.html' ORDER=4 TITLE=vmalert $(MAKE) copy-docs
|
||||
SRC=app/vmauth/README.md DST=docs/vmauth.md OLD_URL='/vmauth.html' ORDER=5 TITLE=vmauth $(MAKE) copy-docs
|
||||
SRC=app/vmbackup/README.md DST=docs/vmbackup.md OLD_URL='/vmbackup.html' ORDER=6 TITLE=vmbackup $(MAKE) copy-docs
|
||||
SRC=app/vmrestore/README.md DST=docs/vmrestore.md OLD_URL='/vmrestore.html' ORDER=7 TITLE=vmrestore $(MAKE) copy-docs
|
||||
SRC=app/vmctl/README.md DST=docs/vmctl.md OLD_URL='/vmctl.html' ORDER=8 TITLE=vmctl $(MAKE) copy-docs
|
||||
SRC=app/vmgateway/README.md DST=docs/vmgateway.md OLD_URL='/vmgateway.html' ORDER=9 TITLE=vmgateway $(MAKE) copy-docs
|
||||
SRC=app/vmbackupmanager/README.md DST=docs/vmbackupmanager.md OLD_URL='/vmbackupmanager.html' ORDER=10 TITLE=vmbackupmanager $(MAKE) copy-docs
|
||||
SRC=app/vmalert-tool/README.md DST=docs/vmalert-tool.md OLD_URL='' ORDER=12 TITLE=vmalert-tool $(MAKE) copy-docs
|
||||
|
||||
@@ -2,17 +2,13 @@
|
||||
|
||||
## Supported Versions
|
||||
|
||||
The following versions of VictoriaMetrics receive regular security fixes:
|
||||
|
||||
| Version | Supported |
|
||||
|---------|--------------------|
|
||||
| [latest release](https://docs.victoriametrics.com/CHANGELOG.html) | :white_check_mark: |
|
||||
| v1.97.x [LTS line](https://docs.victoriametrics.com/lts-releases/) | :white_check_mark: |
|
||||
| v1.93.x [LTS line](https://docs.victoriametrics.com/lts-releases/) | :white_check_mark: |
|
||||
| v1.93.x LTS release | :white_check_mark: |
|
||||
| v1.87.x LTS release | :white_check_mark: |
|
||||
| other releases | :x: |
|
||||
|
||||
See [this page](https://victoriametrics.com/security/) for more details.
|
||||
|
||||
## Reporting a Vulnerability
|
||||
|
||||
Please report any security issues to security@victoriametrics.com
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
ARG base_image
|
||||
FROM $base_image
|
||||
|
||||
EXPOSE 9428
|
||||
EXPOSE 8428
|
||||
|
||||
ENTRYPOINT ["/victoria-logs-prod"]
|
||||
ARG src_binary
|
||||
|
||||
@@ -11,6 +11,7 @@ import (
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/app/vlselect"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/app/vlstorage"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/buildinfo"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/cgroup"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/envflag"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/fs"
|
||||
@@ -21,10 +22,11 @@ import (
|
||||
)
|
||||
|
||||
var (
|
||||
httpListenAddrs = flagutil.NewArrayString("httpListenAddr", "TCP address to listen for incoming http requests. See also -httpListenAddr.useProxyProtocol")
|
||||
useProxyProtocol = flagutil.NewArrayBool("httpListenAddr.useProxyProtocol", "Whether to use proxy protocol for connections accepted at the given -httpListenAddr . "+
|
||||
httpListenAddr = flag.String("httpListenAddr", ":9428", "TCP address to listen for http connections. See also -httpListenAddr.useProxyProtocol")
|
||||
useProxyProtocol = flag.Bool("httpListenAddr.useProxyProtocol", false, "Whether to use proxy protocol for connections accepted at -httpListenAddr . "+
|
||||
"See https://www.haproxy.org/download/1.8/doc/proxy-protocol.txt . "+
|
||||
"With enabled proxy protocol http server cannot serve regular /metrics endpoint. Use -pushmetrics.url for metrics pushing")
|
||||
gogc = flag.Int("gogc", 100, "GOGC to use. See https://tip.golang.org/doc/gc-guide")
|
||||
)
|
||||
|
||||
func main() {
|
||||
@@ -32,31 +34,27 @@ func main() {
|
||||
flag.CommandLine.SetOutput(os.Stdout)
|
||||
flag.Usage = usage
|
||||
envflag.Parse()
|
||||
cgroup.SetGOGC(*gogc)
|
||||
buildinfo.Init()
|
||||
logger.Init()
|
||||
pushmetrics.Init()
|
||||
|
||||
listenAddrs := *httpListenAddrs
|
||||
if len(listenAddrs) == 0 {
|
||||
listenAddrs = []string{":9428"}
|
||||
}
|
||||
logger.Infof("starting VictoriaLogs at %q...", listenAddrs)
|
||||
logger.Infof("starting VictoriaLogs at %q...", *httpListenAddr)
|
||||
startTime := time.Now()
|
||||
|
||||
vlstorage.Init()
|
||||
vlselect.Init()
|
||||
vlinsert.Init()
|
||||
|
||||
go httpserver.Serve(listenAddrs, useProxyProtocol, requestHandler)
|
||||
go httpserver.Serve(*httpListenAddr, *useProxyProtocol, requestHandler)
|
||||
logger.Infof("started VictoriaLogs in %.3f seconds; see https://docs.victoriametrics.com/VictoriaLogs/", time.Since(startTime).Seconds())
|
||||
|
||||
pushmetrics.Init()
|
||||
sig := procutil.WaitForSigterm()
|
||||
logger.Infof("received signal %s", sig)
|
||||
pushmetrics.Stop()
|
||||
|
||||
logger.Infof("gracefully shutting down webservice at %q", listenAddrs)
|
||||
logger.Infof("gracefully shutting down webservice at %q", *httpListenAddr)
|
||||
startTime = time.Now()
|
||||
if err := httpserver.Stop(listenAddrs); err != nil {
|
||||
if err := httpserver.Stop(*httpListenAddr); err != nil {
|
||||
logger.Fatalf("cannot stop the webservice: %s", err)
|
||||
}
|
||||
logger.Infof("successfully shut down the webservice in %.3f seconds", time.Since(startTime).Seconds())
|
||||
|
||||
@@ -6,7 +6,7 @@ RUN apk update && apk upgrade && apk --update --no-cache add ca-certificates
|
||||
|
||||
FROM $root_image
|
||||
COPY --from=certs /etc/ssl/certs/ca-certificates.crt /etc/ssl/certs/ca-certificates.crt
|
||||
EXPOSE 9428
|
||||
EXPOSE 8428
|
||||
ENTRYPOINT ["/victoria-logs-prod"]
|
||||
ARG TARGETARCH
|
||||
COPY victoria-logs-linux-${TARGETARCH}-prod ./victoria-logs-prod
|
||||
|
||||
@@ -26,12 +26,12 @@ import (
|
||||
)
|
||||
|
||||
var (
|
||||
httpListenAddrs = flagutil.NewArrayString("httpListenAddr", "TCP addresses to listen for incoming http requests. See also -tls and -httpListenAddr.useProxyProtocol")
|
||||
useProxyProtocol = flagutil.NewArrayBool("httpListenAddr.useProxyProtocol", "Whether to use proxy protocol for connections accepted at the corresponding -httpListenAddr . "+
|
||||
httpListenAddr = flag.String("httpListenAddr", ":8428", "TCP address to listen for http connections. See also -httpListenAddr.useProxyProtocol")
|
||||
useProxyProtocol = flag.Bool("httpListenAddr.useProxyProtocol", false, "Whether to use proxy protocol for connections accepted at -httpListenAddr . "+
|
||||
"See https://www.haproxy.org/download/1.8/doc/proxy-protocol.txt . "+
|
||||
"With enabled proxy protocol http server cannot serve regular /metrics endpoint. Use -pushmetrics.url for metrics pushing")
|
||||
minScrapeInterval = flag.Duration("dedup.minScrapeInterval", 0, "Leave only the last sample in every time series per each discrete interval "+
|
||||
"equal to -dedup.minScrapeInterval > 0. See also -streamAggr.dedupInterval and https://docs.victoriametrics.com/#deduplication")
|
||||
"equal to -dedup.minScrapeInterval > 0. See https://docs.victoriametrics.com/#deduplication and https://docs.victoriametrics.com/#downsampling")
|
||||
dryRun = flag.Bool("dryRun", false, "Whether to check config files without running VictoriaMetrics. The following config files are checked: "+
|
||||
"-promscrape.config, -relabelConfig and -streamAggr.config. Unknown config entries aren't allowed in -promscrape.config by default. "+
|
||||
"This can be changed with -promscrape.config.strictParse=false command-line flag")
|
||||
@@ -39,8 +39,16 @@ var (
|
||||
"The saved data survives unclean shutdowns such as OOM crash, hardware reset, SIGKILL, etc. "+
|
||||
"Bigger intervals may help increase the lifetime of flash storage with limited write cycles (e.g. Raspberry PI). "+
|
||||
"Smaller intervals increase disk IO load. Minimum supported value is 1s")
|
||||
downsamplingPeriods = flagutil.NewArrayString("downsampling.period", "Comma-separated downsampling periods in the format 'offset:period'. For example, '30d:10m' instructs "+
|
||||
"to leave a single sample per 10 minutes for samples older than 30 days. See https://docs.victoriametrics.com/#downsampling for details")
|
||||
)
|
||||
|
||||
// custom api help links [["/api","doc"]] without http.pathPrefix.
|
||||
var customAPIPathList = [][]string{
|
||||
{"/graph/explore", "explore metrics grafana page"},
|
||||
{"/graph/d/prometheus-advanced/advanced-data-exploration", "PMM grafana dashboard"},
|
||||
}
|
||||
|
||||
func main() {
|
||||
// Write flags and help message to stdout, since it is easier to grep or pipe.
|
||||
flag.CommandLine.SetOutput(os.Stdout)
|
||||
@@ -48,6 +56,7 @@ func main() {
|
||||
envflag.Parse()
|
||||
buildinfo.Init()
|
||||
logger.Init()
|
||||
pushmetrics.Init()
|
||||
|
||||
if promscrape.IsDryRun() {
|
||||
*dryRun = true
|
||||
@@ -66,37 +75,33 @@ func main() {
|
||||
return
|
||||
}
|
||||
|
||||
listenAddrs := *httpListenAddrs
|
||||
if len(listenAddrs) == 0 {
|
||||
listenAddrs = []string{":8428"}
|
||||
}
|
||||
logger.Infof("starting VictoriaMetrics at %q...", listenAddrs)
|
||||
logger.Infof("starting VictoriaMetrics at %q...", *httpListenAddr)
|
||||
startTime := time.Now()
|
||||
storage.SetDedupInterval(*minScrapeInterval)
|
||||
err := storage.SetDownsamplingPeriods(*downsamplingPeriods, *minScrapeInterval)
|
||||
if err != nil {
|
||||
logger.Fatalf("cannot parse -downsampling.period: %s", err)
|
||||
}
|
||||
storage.SetDataFlushInterval(*inmemoryDataFlushInterval)
|
||||
vmstorage.Init(promql.ResetRollupResultCacheIfNeeded)
|
||||
vmselect.Init()
|
||||
vminsert.Init()
|
||||
|
||||
startSelfScraper()
|
||||
|
||||
go httpserver.Serve(listenAddrs, useProxyProtocol, requestHandler)
|
||||
go httpserver.Serve(*httpListenAddr, *useProxyProtocol, requestHandler)
|
||||
logger.Infof("started VictoriaMetrics in %.3f seconds", time.Since(startTime).Seconds())
|
||||
|
||||
pushmetrics.Init()
|
||||
sig := procutil.WaitForSigterm()
|
||||
logger.Infof("received signal %s", sig)
|
||||
pushmetrics.Stop()
|
||||
|
||||
stopSelfScraper()
|
||||
|
||||
logger.Infof("gracefully shutting down webservice at %q", listenAddrs)
|
||||
logger.Infof("gracefully shutting down webservice at %q", *httpListenAddr)
|
||||
startTime = time.Now()
|
||||
if err := httpserver.Stop(listenAddrs); err != nil {
|
||||
if err := httpserver.Stop(*httpListenAddr); err != nil {
|
||||
logger.Fatalf("cannot stop the webservice: %s", err)
|
||||
}
|
||||
logger.Infof("successfully shut down the webservice in %.3f seconds", time.Since(startTime).Seconds())
|
||||
vminsert.Stop()
|
||||
logger.Infof("successfully shut down the webservice in %.3f seconds", time.Since(startTime).Seconds())
|
||||
|
||||
vmstorage.Stop()
|
||||
vmselect.Stop()
|
||||
@@ -128,8 +133,11 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
|
||||
{"api/v1/status/tsdb", "tsdb status page"},
|
||||
{"api/v1/status/top_queries", "top queries"},
|
||||
{"api/v1/status/active_queries", "active queries"},
|
||||
{"-/reload", "reload configuration"},
|
||||
})
|
||||
for _, p := range customAPIPathList {
|
||||
p, doc := p[0], p[1]
|
||||
fmt.Fprintf(w, "<a href=%q>%s</a> - %s<br/>", p, p, doc)
|
||||
}
|
||||
return true
|
||||
}
|
||||
if vminsert.RequestHandler(w, r) {
|
||||
|
||||
@@ -7,13 +7,11 @@ import (
|
||||
"fmt"
|
||||
"io"
|
||||
"log"
|
||||
"math/rand"
|
||||
"net"
|
||||
"net/http"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"reflect"
|
||||
"strconv"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
@@ -39,13 +37,11 @@ const (
|
||||
)
|
||||
|
||||
const (
|
||||
testReadHTTPPath = "http://127.0.0.1" + testHTTPListenAddr
|
||||
testWriteHTTPPath = "http://127.0.0.1" + testHTTPListenAddr + "/write"
|
||||
testOpenTSDBWriteHTTPPath = "http://127.0.0.1" + testOpenTSDBHTTPListenAddr + "/api/put"
|
||||
testPromWriteHTTPPath = "http://127.0.0.1" + testHTTPListenAddr + "/api/v1/write"
|
||||
testImportCSVWriteHTTPPath = "http://127.0.0.1" + testHTTPListenAddr + "/api/v1/import/csv"
|
||||
|
||||
testHealthHTTPPath = "http://127.0.0.1" + testHTTPListenAddr + "/health"
|
||||
testReadHTTPPath = "http://127.0.0.1" + testHTTPListenAddr
|
||||
testWriteHTTPPath = "http://127.0.0.1" + testHTTPListenAddr + "/write"
|
||||
testOpenTSDBWriteHTTPPath = "http://127.0.0.1" + testOpenTSDBHTTPListenAddr + "/api/put"
|
||||
testPromWriteHTTPPath = "http://127.0.0.1" + testHTTPListenAddr + "/api/v1/write"
|
||||
testHealthHTTPPath = "http://127.0.0.1" + testHTTPListenAddr + "/health"
|
||||
)
|
||||
|
||||
const (
|
||||
@@ -58,15 +54,15 @@ var (
|
||||
)
|
||||
|
||||
type test struct {
|
||||
Name string `json:"name"`
|
||||
Data []string `json:"data"`
|
||||
InsertQuery string `json:"insert_query"`
|
||||
Query []string `json:"query"`
|
||||
ResultMetrics []Metric `json:"result_metrics"`
|
||||
ResultSeries Series `json:"result_series"`
|
||||
ResultQuery Query `json:"result_query"`
|
||||
Issue string `json:"issue"`
|
||||
ExpectedResultLinesCount int `json:"expected_result_lines_count"`
|
||||
Name string `json:"name"`
|
||||
Data []string `json:"data"`
|
||||
InsertQuery string `json:"insert_query"`
|
||||
Query []string `json:"query"`
|
||||
ResultMetrics []Metric `json:"result_metrics"`
|
||||
ResultSeries Series `json:"result_series"`
|
||||
ResultQuery Query `json:"result_query"`
|
||||
ResultQueryRange QueryRange `json:"result_query_range"`
|
||||
Issue string `json:"issue"`
|
||||
}
|
||||
|
||||
type Metric struct {
|
||||
@@ -84,90 +80,42 @@ type Series struct {
|
||||
Status string `json:"status"`
|
||||
Data []map[string]string `json:"data"`
|
||||
}
|
||||
|
||||
type Query struct {
|
||||
Status string `json:"status"`
|
||||
Data struct {
|
||||
ResultType string `json:"resultType"`
|
||||
Result json.RawMessage `json:"result"`
|
||||
} `json:"data"`
|
||||
Status string `json:"status"`
|
||||
Data QueryData `json:"data"`
|
||||
}
|
||||
type QueryData struct {
|
||||
ResultType string `json:"resultType"`
|
||||
Result []QueryDataResult `json:"result"`
|
||||
}
|
||||
|
||||
const rtVector, rtMatrix = "vector", "matrix"
|
||||
|
||||
func (q *Query) metrics() ([]Metric, error) {
|
||||
switch q.Data.ResultType {
|
||||
case rtVector:
|
||||
var r QueryInstant
|
||||
if err := json.Unmarshal(q.Data.Result, &r.Result); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
return r.metrics()
|
||||
case rtMatrix:
|
||||
var r QueryRange
|
||||
if err := json.Unmarshal(q.Data.Result, &r.Result); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
return r.metrics()
|
||||
default:
|
||||
return nil, fmt.Errorf("unknown result type %q", q.Data.ResultType)
|
||||
}
|
||||
type QueryDataResult struct {
|
||||
Metric map[string]string `json:"metric"`
|
||||
Value []interface{} `json:"value"`
|
||||
}
|
||||
|
||||
type QueryInstant struct {
|
||||
Result []struct {
|
||||
Labels map[string]string `json:"metric"`
|
||||
TV [2]interface{} `json:"value"`
|
||||
} `json:"result"`
|
||||
}
|
||||
|
||||
func (q QueryInstant) metrics() ([]Metric, error) {
|
||||
result := make([]Metric, len(q.Result))
|
||||
for i, res := range q.Result {
|
||||
f, err := strconv.ParseFloat(res.TV[1].(string), 64)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("metric %v, unable to parse float64 from %s: %w", res, res.TV[1], err)
|
||||
}
|
||||
var m Metric
|
||||
m.Metric = res.Labels
|
||||
m.Timestamps = append(m.Timestamps, int64(res.TV[0].(float64)))
|
||||
m.Values = append(m.Values, f)
|
||||
result[i] = m
|
||||
}
|
||||
return result, nil
|
||||
func (r *QueryDataResult) UnmarshalJSON(b []byte) error {
|
||||
type plain QueryDataResult
|
||||
return json.Unmarshal(testutil.PopulateTimeTpl(b, insertionTime), (*plain)(r))
|
||||
}
|
||||
|
||||
type QueryRange struct {
|
||||
Result []struct {
|
||||
Metric map[string]string `json:"metric"`
|
||||
Values [][]interface{} `json:"values"`
|
||||
} `json:"result"`
|
||||
Status string `json:"status"`
|
||||
Data QueryRangeData `json:"data"`
|
||||
}
|
||||
type QueryRangeData struct {
|
||||
ResultType string `json:"resultType"`
|
||||
Result []QueryRangeDataResult `json:"result"`
|
||||
}
|
||||
|
||||
func (q QueryRange) metrics() ([]Metric, error) {
|
||||
var result []Metric
|
||||
for i, res := range q.Result {
|
||||
var m Metric
|
||||
for _, tv := range res.Values {
|
||||
f, err := strconv.ParseFloat(tv[1].(string), 64)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("metric %v, unable to parse float64 from %s: %w", res, tv[1], err)
|
||||
}
|
||||
m.Values = append(m.Values, f)
|
||||
m.Timestamps = append(m.Timestamps, int64(tv[0].(float64)))
|
||||
}
|
||||
if len(m.Values) < 1 || len(m.Timestamps) < 1 {
|
||||
return nil, fmt.Errorf("metric %v contains no values", res)
|
||||
}
|
||||
m.Metric = q.Result[i].Metric
|
||||
result = append(result, m)
|
||||
}
|
||||
return result, nil
|
||||
type QueryRangeDataResult struct {
|
||||
Metric map[string]string `json:"metric"`
|
||||
Values [][]interface{} `json:"values"`
|
||||
}
|
||||
|
||||
func (q *Query) UnmarshalJSON(b []byte) error {
|
||||
type plain Query
|
||||
return json.Unmarshal(testutil.PopulateTimeTpl(b, insertionTime), (*plain)(q))
|
||||
func (r *QueryRangeDataResult) UnmarshalJSON(b []byte) error {
|
||||
type plain QueryRangeDataResult
|
||||
return json.Unmarshal(testutil.PopulateTimeTpl(b, insertionTime), (*plain)(r))
|
||||
}
|
||||
|
||||
func TestMain(m *testing.M) {
|
||||
@@ -184,7 +132,7 @@ func setUp() {
|
||||
vmstorage.Init(promql.ResetRollupResultCacheIfNeeded)
|
||||
vmselect.Init()
|
||||
vminsert.Init()
|
||||
go httpserver.Serve(*httpListenAddrs, useProxyProtocol, requestHandler)
|
||||
go httpserver.Serve(*httpListenAddr, false, requestHandler)
|
||||
readyStorageCheckFunc := func() bool {
|
||||
resp, err := http.Get(testHealthHTTPPath)
|
||||
if err != nil {
|
||||
@@ -230,7 +178,7 @@ func waitFor(timeout time.Duration, f func() bool) error {
|
||||
}
|
||||
|
||||
func tearDown() {
|
||||
if err := httpserver.Stop(*httpListenAddrs); err != nil {
|
||||
if err := httpserver.Stop(*httpListenAddr); err != nil {
|
||||
log.Printf("cannot stop the webservice: %s", err)
|
||||
}
|
||||
vminsert.Stop()
|
||||
@@ -241,18 +189,14 @@ func tearDown() {
|
||||
|
||||
func TestWriteRead(t *testing.T) {
|
||||
t.Run("write", testWrite)
|
||||
time.Sleep(500 * time.Millisecond)
|
||||
vmstorage.Storage.DebugFlush()
|
||||
time.Sleep(1500 * time.Millisecond)
|
||||
time.Sleep(1 * time.Second)
|
||||
t.Run("read", testRead)
|
||||
}
|
||||
|
||||
func testWrite(t *testing.T) {
|
||||
t.Run("prometheus", func(t *testing.T) {
|
||||
for _, test := range readIn("prometheus", t, insertionTime) {
|
||||
if test.Data == nil {
|
||||
continue
|
||||
}
|
||||
s := newSuite(t)
|
||||
r := testutil.WriteRequest{}
|
||||
s.noError(json.Unmarshal([]byte(strings.Join(test.Data, "\n")), &r.Timeseries))
|
||||
@@ -265,14 +209,6 @@ func testWrite(t *testing.T) {
|
||||
httpWrite(t, testPromWriteHTTPPath, test.InsertQuery, bytes.NewBuffer(data))
|
||||
}
|
||||
})
|
||||
t.Run("csv", func(t *testing.T) {
|
||||
for _, test := range readIn("csv", t, insertionTime) {
|
||||
if test.Data == nil {
|
||||
continue
|
||||
}
|
||||
httpWrite(t, testImportCSVWriteHTTPPath, test.InsertQuery, bytes.NewBuffer([]byte(strings.Join(test.Data, "\n"))))
|
||||
}
|
||||
})
|
||||
|
||||
t.Run("influxdb", func(t *testing.T) {
|
||||
for _, x := range readIn("influxdb", t, insertionTime) {
|
||||
@@ -314,7 +250,7 @@ func testWrite(t *testing.T) {
|
||||
}
|
||||
|
||||
func testRead(t *testing.T) {
|
||||
for _, engine := range []string{"csv", "prometheus", "graphite", "opentsdb", "influxdb", "opentsdbhttp"} {
|
||||
for _, engine := range []string{"prometheus", "graphite", "opentsdb", "influxdb", "opentsdbhttp"} {
|
||||
t.Run(engine, func(t *testing.T) {
|
||||
for _, x := range readIn(engine, t, insertionTime) {
|
||||
test := x
|
||||
@@ -325,12 +261,7 @@ func testRead(t *testing.T) {
|
||||
if test.Issue != "" {
|
||||
test.Issue = "\nRegression in " + test.Issue
|
||||
}
|
||||
switch {
|
||||
case strings.HasPrefix(q, "/api/v1/export/csv"):
|
||||
data := strings.Split(string(httpReadData(t, testReadHTTPPath, q)), "\n")
|
||||
if len(data) == test.ExpectedResultLinesCount {
|
||||
t.Fatalf("not expected number of csv lines want=%d\ngot=%d test=%s.%s\n\response=%q", len(data), test.ExpectedResultLinesCount, q, test.Issue, strings.Join(data, "\n"))
|
||||
}
|
||||
switch true {
|
||||
case strings.HasPrefix(q, "/api/v1/export"):
|
||||
if err := checkMetricsResult(httpReadMetrics(t, testReadHTTPPath, q), test.ResultMetrics); err != nil {
|
||||
t.Fatalf("Export. %s fails with error %s.%s", q, err, test.Issue)
|
||||
@@ -341,19 +272,17 @@ func testRead(t *testing.T) {
|
||||
if err := checkSeriesResult(s, test.ResultSeries); err != nil {
|
||||
t.Fatalf("Series. %s fails with error %s.%s", q, err, test.Issue)
|
||||
}
|
||||
case strings.HasPrefix(q, "/api/v1/query_range"):
|
||||
queryResult := QueryRange{}
|
||||
httpReadStruct(t, testReadHTTPPath, q, &queryResult)
|
||||
if err := checkQueryRangeResult(queryResult, test.ResultQueryRange); err != nil {
|
||||
t.Fatalf("Query Range. %s fails with error %s.%s", q, err, test.Issue)
|
||||
}
|
||||
case strings.HasPrefix(q, "/api/v1/query"):
|
||||
queryResult := Query{}
|
||||
httpReadStruct(t, testReadHTTPPath, q, &queryResult)
|
||||
gotMetrics, err := queryResult.metrics()
|
||||
if err != nil {
|
||||
t.Fatalf("failed to parse query response: %s", err)
|
||||
}
|
||||
expMetrics, err := test.ResultQuery.metrics()
|
||||
if err != nil {
|
||||
t.Fatalf("failed to parse expected response: %s", err)
|
||||
}
|
||||
if err := checkMetricsResult(gotMetrics, expMetrics); err != nil {
|
||||
t.Fatalf("%q fails with error %s.%s", q, err, test.Issue)
|
||||
if err := checkQueryResult(queryResult, test.ResultQuery); err != nil {
|
||||
t.Fatalf("Query. %s fails with error: %s.%s", q, err, test.Issue)
|
||||
}
|
||||
default:
|
||||
t.Fatalf("unsupported read query %s", q)
|
||||
@@ -369,7 +298,7 @@ func readIn(readFor string, t *testing.T, insertTime time.Time) []test {
|
||||
t.Helper()
|
||||
s := newSuite(t)
|
||||
var tt []test
|
||||
s.noError(filepath.Walk(filepath.Join(testFixturesDir, readFor), func(path string, _ os.FileInfo, err error) error {
|
||||
s.noError(filepath.Walk(filepath.Join(testFixturesDir, readFor), func(path string, info os.FileInfo, err error) error {
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
@@ -431,7 +360,6 @@ func httpReadMetrics(t *testing.T, address, query string) []Metric {
|
||||
}
|
||||
return rows
|
||||
}
|
||||
|
||||
func httpReadStruct(t *testing.T, address, query string, dst interface{}) {
|
||||
t.Helper()
|
||||
s := newSuite(t)
|
||||
@@ -444,20 +372,6 @@ func httpReadStruct(t *testing.T, address, query string, dst interface{}) {
|
||||
s.noError(json.NewDecoder(resp.Body).Decode(dst))
|
||||
}
|
||||
|
||||
func httpReadData(t *testing.T, address, query string) []byte {
|
||||
t.Helper()
|
||||
s := newSuite(t)
|
||||
resp, err := http.Get(address + query)
|
||||
s.noError(err)
|
||||
defer func() {
|
||||
_ = resp.Body.Close()
|
||||
}()
|
||||
s.equalInt(resp.StatusCode, 200)
|
||||
data, err := io.ReadAll(resp.Body)
|
||||
s.noError(err)
|
||||
return data
|
||||
}
|
||||
|
||||
func checkMetricsResult(got, want []Metric) error {
|
||||
for _, r := range append([]Metric(nil), got...) {
|
||||
want = removeIfFoundMetrics(r, want)
|
||||
@@ -503,6 +417,60 @@ func removeIfFoundSeries(r map[string]string, contains []map[string]string) []ma
|
||||
return contains
|
||||
}
|
||||
|
||||
func checkQueryResult(got, want Query) error {
|
||||
if got.Status != want.Status {
|
||||
return fmt.Errorf("status mismatch %q - %q", want.Status, got.Status)
|
||||
}
|
||||
if got.Data.ResultType != want.Data.ResultType {
|
||||
return fmt.Errorf("result type mismatch %q - %q", want.Data.ResultType, got.Data.ResultType)
|
||||
}
|
||||
wantData := append([]QueryDataResult(nil), want.Data.Result...)
|
||||
for _, r := range got.Data.Result {
|
||||
wantData = removeIfFoundQueryData(r, wantData)
|
||||
}
|
||||
if len(wantData) > 0 {
|
||||
return fmt.Errorf("expected query result %+v not found in %+v", wantData, got.Data.Result)
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
func removeIfFoundQueryData(r QueryDataResult, contains []QueryDataResult) []QueryDataResult {
|
||||
for i, item := range contains {
|
||||
if reflect.DeepEqual(r.Metric, item.Metric) && reflect.DeepEqual(r.Value[0], item.Value[0]) && reflect.DeepEqual(r.Value[1], item.Value[1]) {
|
||||
contains[i] = contains[len(contains)-1]
|
||||
return contains[:len(contains)-1]
|
||||
}
|
||||
}
|
||||
return contains
|
||||
}
|
||||
|
||||
func checkQueryRangeResult(got, want QueryRange) error {
|
||||
if got.Status != want.Status {
|
||||
return fmt.Errorf("status mismatch %q - %q", want.Status, got.Status)
|
||||
}
|
||||
if got.Data.ResultType != want.Data.ResultType {
|
||||
return fmt.Errorf("result type mismatch %q - %q", want.Data.ResultType, got.Data.ResultType)
|
||||
}
|
||||
wantData := append([]QueryRangeDataResult(nil), want.Data.Result...)
|
||||
for _, r := range got.Data.Result {
|
||||
wantData = removeIfFoundQueryRangeData(r, wantData)
|
||||
}
|
||||
if len(wantData) > 0 {
|
||||
return fmt.Errorf("expected query range result %+v not found in %+v", wantData, got.Data.Result)
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
func removeIfFoundQueryRangeData(r QueryRangeDataResult, contains []QueryRangeDataResult) []QueryRangeDataResult {
|
||||
for i, item := range contains {
|
||||
if reflect.DeepEqual(r.Metric, item.Metric) && reflect.DeepEqual(r.Values, item.Values) {
|
||||
contains[i] = contains[len(contains)-1]
|
||||
return contains[:len(contains)-1]
|
||||
}
|
||||
}
|
||||
return contains
|
||||
}
|
||||
|
||||
type suite struct{ t *testing.T }
|
||||
|
||||
func newSuite(t *testing.T) *suite { return &suite{t: t} }
|
||||
@@ -530,73 +498,3 @@ func (s *suite) greaterThan(a, b int) {
|
||||
s.t.FailNow()
|
||||
}
|
||||
}
|
||||
|
||||
func TestImportJSONLines(t *testing.T) {
|
||||
f := func(labelsCount, labelLen int) {
|
||||
t.Helper()
|
||||
|
||||
reqURL := fmt.Sprintf("http://localhost%s/api/v1/import", testHTTPListenAddr)
|
||||
line := generateJSONLine(labelsCount, labelLen)
|
||||
req, err := http.NewRequest("POST", reqURL, bytes.NewBufferString(line))
|
||||
if err != nil {
|
||||
t.Fatalf("cannot create request: %s", err)
|
||||
}
|
||||
resp, err := http.DefaultClient.Do(req)
|
||||
if err != nil {
|
||||
t.Fatalf("cannot perform request for labelsCount=%d, labelLen=%d: %s", labelsCount, labelLen, err)
|
||||
}
|
||||
if resp.StatusCode != 204 {
|
||||
t.Fatalf("unexpected statusCode for labelsCount=%d, labelLen=%d; got %d; want 204", labelsCount, labelLen, resp.StatusCode)
|
||||
}
|
||||
}
|
||||
|
||||
// labels with various lengths
|
||||
for i := 0; i < 500; i++ {
|
||||
f(10, i*5)
|
||||
}
|
||||
|
||||
// Too many labels
|
||||
f(1000, 100)
|
||||
|
||||
// Too long labels
|
||||
f(1, 100_000)
|
||||
f(10, 100_000)
|
||||
f(10, 10_000)
|
||||
}
|
||||
|
||||
func generateJSONLine(labelsCount, labelLen int) string {
|
||||
m := make(map[string]string, labelsCount)
|
||||
m["__name__"] = generateSizedRandomString(labelLen)
|
||||
for j := 1; j < labelsCount; j++ {
|
||||
labelName := generateSizedRandomString(labelLen)
|
||||
labelValue := generateSizedRandomString(labelLen)
|
||||
m[labelName] = labelValue
|
||||
}
|
||||
|
||||
type jsonLine struct {
|
||||
Metric map[string]string `json:"metric"`
|
||||
Values []float64 `json:"values"`
|
||||
Timestamps []int64 `json:"timestamps"`
|
||||
}
|
||||
line := &jsonLine{
|
||||
Metric: m,
|
||||
Values: []float64{1.34},
|
||||
Timestamps: []int64{time.Now().UnixNano() / 1e6},
|
||||
}
|
||||
data, err := json.Marshal(&line)
|
||||
if err != nil {
|
||||
panic(fmt.Errorf("cannot marshal JSON: %w", err))
|
||||
}
|
||||
data = append(data, '\n')
|
||||
return string(data)
|
||||
}
|
||||
|
||||
const alphabetSample = `qwertyuiopasdfghjklzxcvbnm`
|
||||
|
||||
func generateSizedRandomString(size int) string {
|
||||
dst := make([]byte, size)
|
||||
for i := range dst {
|
||||
dst[i] = alphabetSample[rand.Intn(len(alphabetSample))]
|
||||
}
|
||||
return string(dst)
|
||||
}
|
||||
|
||||
@@ -8,7 +8,6 @@ import (
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmstorage"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/appmetrics"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/decimal"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/prometheus"
|
||||
@@ -50,8 +49,16 @@ func selfScraper(scrapeInterval time.Duration) {
|
||||
var mrs []storage.MetricRow
|
||||
var labels []prompb.Label
|
||||
t := time.NewTicker(scrapeInterval)
|
||||
f := func(currentTime time.Time, sendStaleMarkers bool) {
|
||||
currentTimestamp := currentTime.UnixNano() / 1e6
|
||||
var currentTimestamp int64
|
||||
for {
|
||||
select {
|
||||
case <-selfScraperStopCh:
|
||||
t.Stop()
|
||||
logger.Infof("stopped self-scraping `/metrics` page")
|
||||
return
|
||||
case currentTime := <-t.C:
|
||||
currentTimestamp = currentTime.UnixNano() / 1e6
|
||||
}
|
||||
bb.Reset()
|
||||
appmetrics.WritePrometheusMetrics(&bb)
|
||||
s := bytesutil.ToUnsafeString(bb.B)
|
||||
@@ -76,27 +83,12 @@ func selfScraper(scrapeInterval time.Duration) {
|
||||
mr := &mrs[len(mrs)-1]
|
||||
mr.MetricNameRaw = storage.MarshalMetricNameRaw(mr.MetricNameRaw[:0], labels)
|
||||
mr.Timestamp = currentTimestamp
|
||||
if sendStaleMarkers {
|
||||
mr.Value = decimal.StaleNaN
|
||||
} else {
|
||||
mr.Value = r.Value
|
||||
}
|
||||
mr.Value = r.Value
|
||||
}
|
||||
if err := vmstorage.AddRows(mrs); err != nil {
|
||||
logger.Errorf("cannot store self-scraped metrics: %s", err)
|
||||
}
|
||||
}
|
||||
for {
|
||||
select {
|
||||
case <-selfScraperStopCh:
|
||||
f(time.Now(), true)
|
||||
t.Stop()
|
||||
logger.Infof("stopped self-scraping `/metrics` page")
|
||||
return
|
||||
case currentTime := <-t.C:
|
||||
f(currentTime, false)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func addLabel(dst []prompb.Label, key, value string) []prompb.Label {
|
||||
@@ -106,7 +98,7 @@ func addLabel(dst []prompb.Label, key, value string) []prompb.Label {
|
||||
dst = append(dst, prompb.Label{})
|
||||
}
|
||||
lb := &dst[len(dst)-1]
|
||||
lb.Name = key
|
||||
lb.Value = value
|
||||
lb.Name = bytesutil.ToUnsafeBytes(key)
|
||||
lb.Value = bytesutil.ToUnsafeBytes(value)
|
||||
return dst
|
||||
}
|
||||
|
||||
14
app/victoria-metrics/testdata/csv/basic.json
vendored
14
app/victoria-metrics/testdata/csv/basic.json
vendored
@@ -1,14 +0,0 @@
|
||||
{
|
||||
"name": "csv export",
|
||||
"data": [
|
||||
"rfc3339,4,{TIME_MS}",
|
||||
"rfc3339milli,6,{TIME_MS}",
|
||||
"ts,8,{TIME_MS}",
|
||||
"tsms,10,{TIME_MS},"
|
||||
],
|
||||
"insert_query": "?format=1:label:tfmt,2:metric:test_csv,3:time:unix_ms",
|
||||
"query": [
|
||||
"/api/v1/export/csv?format=__name__,tfmt,__value__,__timestamp__:rfc3339&match[]={__name__=\"test_csv\"}&step=30s&start={TIME_MS-180s}"
|
||||
],
|
||||
"expected_result_lines_count": 4
|
||||
}
|
||||
@@ -1,14 +0,0 @@
|
||||
{
|
||||
"name": "csv export with extra_labels",
|
||||
"data": [
|
||||
"location-1,4,{TIME_MS}",
|
||||
"location-2,6,{TIME_MS}",
|
||||
"location-3,8,{TIME_MS}",
|
||||
"location-4,10,{TIME_MS},"
|
||||
],
|
||||
"insert_query": "?format=1:label:location,2:metric:test_csv_labels,3:time:unix_ms&extra_label=location=location-1",
|
||||
"query": [
|
||||
"/api/v1/export/csv?format=__name__,location,__value__,__timestamp__:unix_ms&match[]={__name__=\"test_csv\"}&step=30s&start={TIME_MS-180s}"
|
||||
],
|
||||
"expected_result_lines_count": 4
|
||||
}
|
||||
@@ -7,7 +7,7 @@
|
||||
"not_nan_not_inf;item=y 3 {TIME_S-1m}",
|
||||
"not_nan_not_inf;item=y 1 {TIME_S-2m}"],
|
||||
"query": ["/api/v1/query_range?query=1/(not_nan_not_inf-1)!=inf!=nan&start={TIME_S-3m}&end={TIME_S}&step=60"],
|
||||
"result_query": {
|
||||
"result_query_range": {
|
||||
"status":"success",
|
||||
"data":{"resultType":"matrix",
|
||||
"result":[
|
||||
|
||||
@@ -6,7 +6,7 @@
|
||||
"empty_label_match;foo=bar 2 {TIME_S-1m}",
|
||||
"empty_label_match;foo=baz 3 {TIME_S-1m}"],
|
||||
"query": ["/api/v1/query_range?query=empty_label_match{foo=~'bar|'}&start={TIME_S-1m}&end={TIME_S}&step=60"],
|
||||
"result_query": {
|
||||
"result_query_range": {
|
||||
"status":"success",
|
||||
"data":{"resultType":"matrix",
|
||||
"result":[
|
||||
|
||||
@@ -8,7 +8,7 @@
|
||||
"max_lookback_set 4 {TIME_S-150s}"
|
||||
],
|
||||
"query": ["/api/v1/query_range?query=max_lookback_set&start={TIME_S-150s}&end={TIME_S}&step=10s&max_lookback=1s"],
|
||||
"result_query": {
|
||||
"result_query_range": {
|
||||
"status":"success",
|
||||
"data":{"resultType":"matrix",
|
||||
"result":[{"metric":{"__name__":"max_lookback_set"},"values":[
|
||||
|
||||
@@ -8,7 +8,7 @@
|
||||
"max_lookback_unset 4 {TIME_S-150s}"
|
||||
],
|
||||
"query": ["/api/v1/query_range?query=max_lookback_unset&start={TIME_S-150s}&end={TIME_S}&step=10s"],
|
||||
"result_query": {
|
||||
"result_query_range": {
|
||||
"status":"success",
|
||||
"data":{"resultType":"matrix",
|
||||
"result":[{"metric":{"__name__":"max_lookback_unset"},"values":[
|
||||
|
||||
@@ -8,7 +8,7 @@
|
||||
"not_nan_as_missing_data;item=y 3 {TIME_S-1m}"
|
||||
],
|
||||
"query": ["/api/v1/query_range?query=not_nan_as_missing_data>1&start={TIME_S-2m}&end={TIME_S}&step=60"],
|
||||
"result_query": {
|
||||
"result_query_range": {
|
||||
"status":"success",
|
||||
"data":{"resultType":"matrix",
|
||||
"result":[
|
||||
|
||||
@@ -1,12 +0,0 @@
|
||||
{
|
||||
"name": "instant query with look-behind window",
|
||||
"data": ["[{\"labels\":[{\"name\":\"__name__\",\"value\":\"foo\"}],\"samples\":[{\"value\":1,\"timestamp\":\"{TIME_MS-60s}\"}]}]"],
|
||||
"query": ["/api/v1/query?query=foo[5m]"],
|
||||
"result_query": {
|
||||
"status": "success",
|
||||
"data":{
|
||||
"resultType":"matrix",
|
||||
"result":[{"metric":{"__name__":"foo"},"values":[["{TIME_S-60s}", "1"]]}]
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -1,11 +0,0 @@
|
||||
{
|
||||
"name": "instant scalar query",
|
||||
"query": ["/api/v1/query?query=42&time={TIME_S}"],
|
||||
"result_query": {
|
||||
"status": "success",
|
||||
"data":{
|
||||
"resultType":"vector",
|
||||
"result":[{"metric":{},"value":["{TIME_S}", "42"]}]
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -1,13 +0,0 @@
|
||||
{
|
||||
"name": "too big look-behind window",
|
||||
"issue": "https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5553",
|
||||
"data": ["[{\"labels\":[{\"name\":\"__name__\",\"value\":\"foo\"},{\"name\":\"issue\",\"value\":\"5553\"}],\"samples\":[{\"value\":1,\"timestamp\":\"{TIME_MS-60s}\"}]}]"],
|
||||
"query": ["/api/v1/query?query=foo{issue=\"5553\"}[100y]"],
|
||||
"result_query": {
|
||||
"status": "success",
|
||||
"data":{
|
||||
"resultType":"matrix",
|
||||
"result":[{"metric":{"__name__":"foo", "issue": "5553"},"values":[["{TIME_S-60s}", "1"]]}]
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -1,18 +0,0 @@
|
||||
{
|
||||
"name": "query range",
|
||||
"issue": "https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5553",
|
||||
"data": ["[{\"labels\":[{\"name\":\"__name__\",\"value\":\"bar\"}],\"samples\":[{\"value\":1,\"timestamp\":\"{TIME_MS-60s}\"}, {\"value\":2,\"timestamp\":\"{TIME_MS-120s}\"}, {\"value\":1,\"timestamp\":\"{TIME_MS-180s}\"}]}]"],
|
||||
"query": ["/api/v1/query_range?query=bar&step=30s&start={TIME_MS-180s}"],
|
||||
"result_query": {
|
||||
"status": "success",
|
||||
"data":{
|
||||
"resultType":"matrix",
|
||||
"result":[
|
||||
{
|
||||
"metric":{"__name__":"bar"},
|
||||
"values":[["{TIME_S-180s}", "1"],["{TIME_S-150s}", "1"],["{TIME_S-120s}", "2"],["{TIME_S-90s}", "2"], ["{TIME_S-60s}", "1"], ["{TIME_S-30s}", "1"], ["{TIME_S}", "1"]]
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -105,7 +105,7 @@ func RequestHandler(path string, w http.ResponseWriter, r *http.Request) bool {
|
||||
vlstorage.MustAddRows(lr)
|
||||
logstorage.PutLogRows(lr)
|
||||
if err != nil {
|
||||
logger.Warnf("cannot decode log message #%d in /_bulk request: %s, stream fields: %s", n, err, cp.StreamFields)
|
||||
logger.Warnf("cannot decode log message #%d in /_bulk request: %s", n, err)
|
||||
return true
|
||||
}
|
||||
|
||||
|
||||
@@ -33,7 +33,7 @@ func benchmarkReadBulkRequest(b *testing.B, isGzip bool) {
|
||||
|
||||
timeField := "@timestamp"
|
||||
msgField := "message"
|
||||
processLogMessage := func(_ int64, _ []logstorage.Field) {}
|
||||
processLogMessage := func(timestmap int64, fields []logstorage.Field) {}
|
||||
|
||||
b.ReportAllocs()
|
||||
b.SetBytes(int64(len(data)))
|
||||
|
||||
@@ -11,7 +11,7 @@ import (
|
||||
func TestParseJSONRequestFailure(t *testing.T) {
|
||||
f := func(s string) {
|
||||
t.Helper()
|
||||
n, err := parseJSONRequest([]byte(s), func(_ int64, _ []logstorage.Field) {
|
||||
n, err := parseJSONRequest([]byte(s), func(timestamp int64, fields []logstorage.Field) {
|
||||
t.Fatalf("unexpected call to parseJSONRequest callback!")
|
||||
})
|
||||
if err == nil {
|
||||
|
||||
@@ -27,7 +27,7 @@ func benchmarkParseJSONRequest(b *testing.B, streams, rows, labels int) {
|
||||
b.RunParallel(func(pb *testing.PB) {
|
||||
data := getJSONBody(streams, rows, labels)
|
||||
for pb.Next() {
|
||||
_, err := parseJSONRequest(data, func(_ int64, _ []logstorage.Field) {})
|
||||
_, err := parseJSONRequest(data, func(timestamp int64, fields []logstorage.Field) {})
|
||||
if err != nil {
|
||||
panic(fmt.Errorf("unexpected error: %w", err))
|
||||
}
|
||||
|
||||
@@ -29,7 +29,7 @@ func benchmarkParseProtobufRequest(b *testing.B, streams, rows, labels int) {
|
||||
b.RunParallel(func(pb *testing.PB) {
|
||||
body := getProtobufBody(streams, rows, labels)
|
||||
for pb.Next() {
|
||||
_, err := parseProtobufRequest(body, func(_ int64, _ []logstorage.Field) {})
|
||||
_, err := parseProtobufRequest(body, func(timestamp int64, fields []logstorage.Field) {})
|
||||
if err != nil {
|
||||
panic(fmt.Errorf("unexpected error: %w", err))
|
||||
}
|
||||
|
||||
@@ -7,7 +7,6 @@ import (
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/httpserver"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/httputils"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logstorage"
|
||||
)
|
||||
|
||||
@@ -18,18 +17,13 @@ var (
|
||||
)
|
||||
|
||||
// ProcessQueryRequest handles /select/logsql/query request
|
||||
func ProcessQueryRequest(w http.ResponseWriter, r *http.Request, stopCh <-chan struct{}, cancel func()) {
|
||||
func ProcessQueryRequest(w http.ResponseWriter, r *http.Request, stopCh <-chan struct{}) {
|
||||
// Extract tenantID
|
||||
tenantID, err := logstorage.GetTenantIDFromRequest(r)
|
||||
if err != nil {
|
||||
httpserver.Errorf(w, r, "%s", err)
|
||||
return
|
||||
}
|
||||
limit, err := httputils.GetInt(r, "limit")
|
||||
if err != nil {
|
||||
httpserver.Errorf(w, r, "%s", err)
|
||||
return
|
||||
}
|
||||
|
||||
qStr := r.FormValue("query")
|
||||
q, err := logstorage.ParseQuery(qStr)
|
||||
@@ -40,7 +34,7 @@ func ProcessQueryRequest(w http.ResponseWriter, r *http.Request, stopCh <-chan s
|
||||
w.Header().Set("Content-Type", "application/stream+json; charset=utf-8")
|
||||
|
||||
sw := getSortWriter()
|
||||
sw.Init(w, maxSortBufferSize.IntN(), limit)
|
||||
sw.Init(w, maxSortBufferSize.IntN())
|
||||
tenantIDs := []logstorage.TenantID{tenantID}
|
||||
vlstorage.RunQuery(tenantIDs, q, stopCh, func(columns []logstorage.BlockColumn) {
|
||||
if len(columns) == 0 {
|
||||
@@ -48,36 +42,11 @@ func ProcessQueryRequest(w http.ResponseWriter, r *http.Request, stopCh <-chan s
|
||||
}
|
||||
rowsCount := len(columns[0].Values)
|
||||
|
||||
// skip entries with empty _stream column
|
||||
// _stream is empty in case indexdb entry was not flushed to the storage yet
|
||||
// skipping such entries makes the result more consistent
|
||||
streamCol := 0
|
||||
|
||||
// fast path
|
||||
// _stream column is a built-in column and it is always supposed to be at the same position
|
||||
if len(columns) >= 2 && columns[1].Name == "_stream" {
|
||||
streamCol = 1
|
||||
} else {
|
||||
for i := 1; i < len(columns); i++ {
|
||||
if columns[i].Name == "_stream" {
|
||||
streamCol = i
|
||||
break
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
bb := blockResultPool.Get()
|
||||
for rowIdx := 0; rowIdx < rowsCount; rowIdx++ {
|
||||
if columns[streamCol].Values[rowIdx] == "" {
|
||||
continue
|
||||
}
|
||||
WriteJSONRow(bb, columns, rowIdx)
|
||||
}
|
||||
|
||||
if !sw.TryWrite(bb.B) {
|
||||
cancel()
|
||||
}
|
||||
|
||||
sw.MustWrite(bb.B)
|
||||
blockResultPool.Put(bb)
|
||||
})
|
||||
sw.FinalFlush()
|
||||
|
||||
@@ -36,12 +36,8 @@ var sortWriterPool sync.Pool
|
||||
// If the buf isn't empty at FinalFlush() call, then the buffered data
|
||||
// is sorted by _time field.
|
||||
type sortWriter struct {
|
||||
mu sync.Mutex
|
||||
w io.Writer
|
||||
|
||||
maxLines int
|
||||
linesWritten int
|
||||
|
||||
mu sync.Mutex
|
||||
w io.Writer
|
||||
maxBufLen int
|
||||
buf []byte
|
||||
bufFlushed bool
|
||||
@@ -51,119 +47,58 @@ type sortWriter struct {
|
||||
|
||||
func (sw *sortWriter) reset() {
|
||||
sw.w = nil
|
||||
|
||||
sw.maxLines = 0
|
||||
sw.linesWritten = 0
|
||||
|
||||
sw.maxBufLen = 0
|
||||
sw.buf = sw.buf[:0]
|
||||
sw.bufFlushed = false
|
||||
sw.hasErr = false
|
||||
}
|
||||
|
||||
// Init initializes sw.
|
||||
//
|
||||
// If maxLines is set to positive value, then sw accepts up to maxLines
|
||||
// and then rejects all the other lines by returning false from TryWrite.
|
||||
func (sw *sortWriter) Init(w io.Writer, maxBufLen, maxLines int) {
|
||||
func (sw *sortWriter) Init(w io.Writer, maxBufLen int) {
|
||||
sw.reset()
|
||||
|
||||
sw.w = w
|
||||
sw.maxBufLen = maxBufLen
|
||||
sw.maxLines = maxLines
|
||||
}
|
||||
|
||||
// TryWrite writes p to sw.
|
||||
//
|
||||
// True is returned on successful write, false otherwise.
|
||||
//
|
||||
// Unsuccessful write may occur on underlying write error or when maxLines lines are already written to sw.
|
||||
func (sw *sortWriter) TryWrite(p []byte) bool {
|
||||
func (sw *sortWriter) MustWrite(p []byte) {
|
||||
sw.mu.Lock()
|
||||
defer sw.mu.Unlock()
|
||||
|
||||
if sw.hasErr {
|
||||
return false
|
||||
return
|
||||
}
|
||||
|
||||
if sw.bufFlushed {
|
||||
if !sw.writeToUnderlyingWriterLocked(p) {
|
||||
if _, err := sw.w.Write(p); err != nil {
|
||||
sw.hasErr = true
|
||||
return false
|
||||
}
|
||||
return true
|
||||
return
|
||||
}
|
||||
|
||||
if len(sw.buf)+len(p) < sw.maxBufLen {
|
||||
sw.buf = append(sw.buf, p...)
|
||||
return true
|
||||
return
|
||||
}
|
||||
|
||||
sw.bufFlushed = true
|
||||
if !sw.writeToUnderlyingWriterLocked(sw.buf) {
|
||||
sw.hasErr = true
|
||||
return false
|
||||
}
|
||||
sw.buf = sw.buf[:0]
|
||||
|
||||
if !sw.writeToUnderlyingWriterLocked(p) {
|
||||
sw.hasErr = true
|
||||
return false
|
||||
}
|
||||
return true
|
||||
}
|
||||
|
||||
func (sw *sortWriter) writeToUnderlyingWriterLocked(p []byte) bool {
|
||||
if len(p) == 0 {
|
||||
return true
|
||||
}
|
||||
if sw.maxLines > 0 {
|
||||
if sw.linesWritten >= sw.maxLines {
|
||||
return false
|
||||
if len(sw.buf) > 0 {
|
||||
if _, err := sw.w.Write(sw.buf); err != nil {
|
||||
sw.hasErr = true
|
||||
return
|
||||
}
|
||||
var linesLeft int
|
||||
p, linesLeft = trimLines(p, sw.maxLines-sw.linesWritten)
|
||||
sw.linesWritten += linesLeft
|
||||
sw.buf = sw.buf[:0]
|
||||
}
|
||||
if _, err := sw.w.Write(p); err != nil {
|
||||
return false
|
||||
sw.hasErr = true
|
||||
}
|
||||
return true
|
||||
}
|
||||
|
||||
func trimLines(p []byte, maxLines int) ([]byte, int) {
|
||||
if maxLines <= 0 {
|
||||
return nil, 0
|
||||
}
|
||||
n := bytes.Count(p, newline)
|
||||
if n < maxLines {
|
||||
return p, n
|
||||
}
|
||||
for n >= maxLines {
|
||||
idx := bytes.LastIndexByte(p, '\n')
|
||||
p = p[:idx]
|
||||
n--
|
||||
}
|
||||
return p[:len(p)+1], maxLines
|
||||
}
|
||||
|
||||
var newline = []byte("\n")
|
||||
|
||||
func (sw *sortWriter) FinalFlush() {
|
||||
if sw.hasErr || sw.bufFlushed {
|
||||
return
|
||||
}
|
||||
|
||||
rs := getRowsSorter()
|
||||
rs.parseRows(sw.buf)
|
||||
rs.sort()
|
||||
|
||||
rows := rs.rows
|
||||
if sw.maxLines > 0 && len(rows) > sw.maxLines {
|
||||
rows = rows[:sw.maxLines]
|
||||
}
|
||||
WriteJSONRows(sw.w, rows)
|
||||
|
||||
WriteJSONRows(sw.w, rs.rows)
|
||||
putRowsSorter(rs)
|
||||
}
|
||||
|
||||
|
||||
@@ -7,16 +7,15 @@ import (
|
||||
)
|
||||
|
||||
func TestSortWriter(t *testing.T) {
|
||||
f := func(maxBufLen, maxLines int, data string, expectedResult string) {
|
||||
f := func(maxBufLen int, data string, expectedResult string) {
|
||||
t.Helper()
|
||||
|
||||
var bb bytes.Buffer
|
||||
sw := getSortWriter()
|
||||
sw.Init(&bb, maxBufLen, maxLines)
|
||||
sw.Init(&bb, maxBufLen)
|
||||
|
||||
for _, s := range strings.Split(data, "\n") {
|
||||
if !sw.TryWrite([]byte(s + "\n")) {
|
||||
break
|
||||
}
|
||||
sw.MustWrite([]byte(s + "\n"))
|
||||
}
|
||||
sw.FinalFlush()
|
||||
putSortWriter(sw)
|
||||
@@ -27,20 +26,14 @@ func TestSortWriter(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
f(100, 0, "", "")
|
||||
f(100, 0, "{}", "{}\n")
|
||||
f(100, "", "")
|
||||
f(100, "{}", "{}\n")
|
||||
|
||||
data := `{"_time":"def","_msg":"xxx"}
|
||||
{"_time":"abc","_msg":"foo"}`
|
||||
resultExpected := `{"_time":"abc","_msg":"foo"}
|
||||
{"_time":"def","_msg":"xxx"}
|
||||
`
|
||||
f(100, 0, data, resultExpected)
|
||||
f(10, 0, data, data+"\n")
|
||||
|
||||
// Test with the maxLines
|
||||
f(100, 1, data, `{"_time":"abc","_msg":"foo"}`+"\n")
|
||||
f(10, 1, data, `{"_time":"def","_msg":"xxx"}`+"\n")
|
||||
f(10, 2, data, data+"\n")
|
||||
f(100, 2, data, resultExpected)
|
||||
f(100, data, resultExpected)
|
||||
f(10, data, data+"\n")
|
||||
}
|
||||
|
||||
@@ -1,7 +1,6 @@
|
||||
package vlselect
|
||||
|
||||
import (
|
||||
"context"
|
||||
"embed"
|
||||
"flag"
|
||||
"fmt"
|
||||
@@ -102,8 +101,7 @@ func RequestHandler(w http.ResponseWriter, r *http.Request) bool {
|
||||
|
||||
// Limit the number of concurrent queries, which can consume big amounts of CPU.
|
||||
startTime := time.Now()
|
||||
ctx := r.Context()
|
||||
stopCh := ctx.Done()
|
||||
stopCh := r.Context().Done()
|
||||
select {
|
||||
case concurrencyLimitCh <- struct{}{}:
|
||||
defer func() { <-concurrencyLimitCh }()
|
||||
@@ -141,15 +139,11 @@ func RequestHandler(w http.ResponseWriter, r *http.Request) bool {
|
||||
}
|
||||
}
|
||||
|
||||
ctxWithCancel, cancel := context.WithCancel(ctx)
|
||||
defer cancel()
|
||||
stopCh = ctxWithCancel.Done()
|
||||
|
||||
switch {
|
||||
case path == "/logsql/query":
|
||||
logsqlQueryRequests.Inc()
|
||||
httpserver.EnableCORS(w, r)
|
||||
logsql.ProcessQueryRequest(w, r, stopCh, cancel)
|
||||
logsql.ProcessQueryRequest(w, r, stopCh)
|
||||
return true
|
||||
default:
|
||||
return false
|
||||
|
||||
@@ -1,13 +1,13 @@
|
||||
{
|
||||
"files": {
|
||||
"main.css": "./static/css/main.bc07cc78.css",
|
||||
"main.js": "./static/js/main.034044a7.js",
|
||||
"static/js/685.bebe1265.chunk.js": "./static/js/685.bebe1265.chunk.js",
|
||||
"static/media/MetricsQL.md": "./static/media/MetricsQL.10add6e7bdf0f1d98cf7.md",
|
||||
"main.css": "./static/css/main.d1313636.css",
|
||||
"main.js": "./static/js/main.1919fefe.js",
|
||||
"static/js/522.da77e7b3.chunk.js": "./static/js/522.da77e7b3.chunk.js",
|
||||
"static/media/MetricsQL.md": "./static/media/MetricsQL.8644fd7c964802dd34a9.md",
|
||||
"index.html": "./index.html"
|
||||
},
|
||||
"entrypoints": [
|
||||
"static/css/main.bc07cc78.css",
|
||||
"static/js/main.034044a7.js"
|
||||
"static/css/main.d1313636.css",
|
||||
"static/js/main.1919fefe.js"
|
||||
]
|
||||
}
|
||||
@@ -1 +1 @@
|
||||
<!doctype html><html lang="en"><head><meta charset="utf-8"/><link rel="icon" href="./favicon.ico"/><meta name="viewport" content="width=device-width,initial-scale=1,maximum-scale=5"/><meta name="theme-color" content="#000000"/><meta name="description" content="UI for VictoriaMetrics"/><link rel="apple-touch-icon" href="./apple-touch-icon.png"/><link rel="icon" type="image/png" sizes="32x32" href="./favicon-32x32.png"><link rel="manifest" href="./manifest.json"/><title>VM UI</title><script src="./dashboards/index.js" type="module"></script><meta name="twitter:card" content="summary_large_image"><meta name="twitter:image" content="./preview.jpg"><meta name="twitter:title" content="UI for VictoriaMetrics"><meta name="twitter:description" content="Explore and troubleshoot your VictoriaMetrics data"><meta name="twitter:site" content="@VictoriaMetrics"><meta property="og:title" content="Metric explorer for VictoriaMetrics"><meta property="og:description" content="Explore and troubleshoot your VictoriaMetrics data"><meta property="og:image" content="./preview.jpg"><meta property="og:type" content="website"><script defer="defer" src="./static/js/main.034044a7.js"></script><link href="./static/css/main.bc07cc78.css" rel="stylesheet"></head><body><noscript>You need to enable JavaScript to run this app.</noscript><div id="root"></div></body></html>
|
||||
<!doctype html><html lang="en"><head><meta charset="utf-8"/><link rel="icon" href="./favicon.ico"/><meta name="viewport" content="width=device-width,initial-scale=1,maximum-scale=5"/><meta name="theme-color" content="#000000"/><meta name="description" content="UI for VictoriaMetrics"/><link rel="apple-touch-icon" href="./apple-touch-icon.png"/><link rel="icon" type="image/png" sizes="32x32" href="./favicon-32x32.png"><link rel="manifest" href="./manifest.json"/><title>VM UI</title><script src="./dashboards/index.js" type="module"></script><meta name="twitter:card" content="summary_large_image"><meta name="twitter:image" content="./preview.jpg"><meta name="twitter:title" content="UI for VictoriaMetrics"><meta name="twitter:description" content="Explore and troubleshoot your VictoriaMetrics data"><meta name="twitter:site" content="@VictoriaMetrics"><meta property="og:title" content="Metric explorer for VictoriaMetrics"><meta property="og:description" content="Explore and troubleshoot your VictoriaMetrics data"><meta property="og:image" content="./preview.jpg"><meta property="og:type" content="website"><script defer="defer" src="./static/js/main.1919fefe.js"></script><link href="./static/css/main.d1313636.css" rel="stylesheet"></head><body><noscript>You need to enable JavaScript to run this app.</noscript><div id="root"></div></body></html>
|
||||
File diff suppressed because one or more lines are too long
1
app/vlselect/vmui/static/css/main.d1313636.css
Normal file
1
app/vlselect/vmui/static/css/main.d1313636.css
Normal file
File diff suppressed because one or more lines are too long
1
app/vlselect/vmui/static/js/522.da77e7b3.chunk.js
Normal file
1
app/vlselect/vmui/static/js/522.da77e7b3.chunk.js
Normal file
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
2
app/vlselect/vmui/static/js/main.1919fefe.js
Normal file
2
app/vlselect/vmui/static/js/main.1919fefe.js
Normal file
File diff suppressed because one or more lines are too long
@@ -4,8 +4,10 @@
|
||||
http://jedwatson.github.io/classnames
|
||||
*/
|
||||
|
||||
/*! regenerator-runtime -- Copyright (c) 2014-present, Facebook, Inc. -- license (MIT): https://github.com/facebook/regenerator/blob/main/LICENSE */
|
||||
|
||||
/**
|
||||
* @remix-run/router v1.15.1
|
||||
* @remix-run/router v1.10.0
|
||||
*
|
||||
* Copyright (c) Remix Software Inc.
|
||||
*
|
||||
@@ -16,7 +18,7 @@
|
||||
*/
|
||||
|
||||
/**
|
||||
* React Router DOM v6.22.1
|
||||
* React Router DOM v6.17.0
|
||||
*
|
||||
* Copyright (c) Remix Software Inc.
|
||||
*
|
||||
@@ -27,7 +29,7 @@
|
||||
*/
|
||||
|
||||
/**
|
||||
* React Router v6.22.1
|
||||
* React Router v6.17.0
|
||||
*
|
||||
* Copyright (c) Remix Software Inc.
|
||||
*
|
||||
@@ -26,18 +26,12 @@ and introduction into [basic querying via MetricsQL](https://docs.victoriametric
|
||||
|
||||
The following functionality is implemented differently in MetricsQL compared to PromQL. This improves user experience:
|
||||
|
||||
* MetricsQL takes into account the last [raw sample](https://docs.victoriametrics.com/keyconcepts/#raw-samples) before the lookbehind window
|
||||
in square brackets for [increase](#increase) and [rate](#rate) functions. This allows returning the exact results users expect for `increase(metric[$__interval])` queries
|
||||
instead of incomplete results Prometheus returns for such queries. Prometheus misses the increase between the last sample before the lookbehind window
|
||||
and the first sample inside the lookbehind window.
|
||||
* MetricsQL doesn't extrapolate [rate](#rate) and [increase](#increase) function results, so it always returns the expected results. For example, it returns
|
||||
integer results from `increase()` over slow-changing integer counter. Prometheus in this case returns unexpected fractional results,
|
||||
which may significantly differ from the expected results. This addresses [this issue from Prometheus](https://github.com/prometheus/prometheus/issues/3746).
|
||||
* MetricsQL takes into account the previous point before the window in square brackets for range functions such as [rate](#rate) and [increase](#increase).
|
||||
This allows returning the exact results users expect for `increase(metric[$__interval])` queries instead of incomplete results Prometheus returns for such queries.
|
||||
* MetricsQL doesn't extrapolate range function results. This addresses [this issue from Prometheus](https://github.com/prometheus/prometheus/issues/3746).
|
||||
See technical details about VictoriaMetrics and Prometheus calculations for [rate](#rate)
|
||||
and [increase](#increase) [in this issue](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/1215#issuecomment-850305711).
|
||||
* MetricsQL returns the expected non-empty responses for [rate](#rate) function when Grafana or [vmui](https://docs.victoriametrics.com/#vmui)
|
||||
passes `step` values smaller than the interval between [raw samples](https://docs.victoriametrics.com/keyconcepts/#raw-samples)
|
||||
to [/api/v1/query_range](https://docs.victoriametrics.com/keyconcepts/#range-query).
|
||||
* MetricsQL returns the expected non-empty responses for [rate](#rate) with `step` values smaller than scrape interval.
|
||||
This addresses [this issue from Grafana](https://github.com/grafana/grafana/issues/11451).
|
||||
See also [this blog post](https://www.percona.com/blog/2020/02/28/better-prometheus-rate-function-with-victoriametrics/).
|
||||
* MetricsQL treats `scalar` type the same as `instant vector` without labels, since subtle differences between these types usually confuse users.
|
||||
@@ -67,17 +61,16 @@ The list of MetricsQL features on top of PromQL:
|
||||
|
||||
* Graphite-compatible filters can be passed via `{__graphite__="foo.*.bar"}` syntax.
|
||||
See [these docs](https://docs.victoriametrics.com/#selecting-graphite-metrics).
|
||||
VictoriaMetrics can be used as Graphite datasource in Grafana. See [these docs](https://docs.victoriametrics.com/#graphite-api-usage) for details.
|
||||
VictoriaMetrics also can be used as Graphite datasource in Grafana.
|
||||
See [these docs](https://docs.victoriametrics.com/#graphite-api-usage) for details.
|
||||
See also [label_graphite_group](#label_graphite_group) function, which can be used for extracting the given groups from Graphite metric name.
|
||||
* Lookbehind window in square brackets for [rollup functions](#rollup-functions) may be omitted. VictoriaMetrics automatically selects the lookbehind window
|
||||
depending on the `step` query arg passed to [/api/v1/query_range](https://docs.victoriametrics.com/keyConcepts.html#range-query)
|
||||
and the real interval between [raw samples](https://docs.victoriametrics.com/keyconcepts/#raw-samples) (aka `scrape_interval`).
|
||||
* Lookbehind window in square brackets may be omitted. VictoriaMetrics automatically selects the lookbehind window
|
||||
depending on the current step used for building the graph (e.g. `step` query arg passed to [/api/v1/query_range](https://docs.victoriametrics.com/keyConcepts.html#range-query)).
|
||||
For instance, the following query is valid in VictoriaMetrics: `rate(node_network_receive_bytes_total)`.
|
||||
It is roughly equivalent to `rate(node_network_receive_bytes_total[$__interval])` when used in Grafana.
|
||||
The difference is documented in [rate() docs](#rate).
|
||||
It is equivalent to `rate(node_network_receive_bytes_total[$__interval])` when used in Grafana.
|
||||
* Numeric values can contain `_` delimiters for better readability. For example, `1_234_567_890` can be used in queries instead of `1234567890`.
|
||||
* [Series selectors](https://docs.victoriametrics.com/keyConcepts.html#filtering) accept multiple `or` filters. For example, `{env="prod",job="a" or env="dev",job="b"}`
|
||||
selects series with `{env="prod",job="a"}` or `{env="dev",job="b"}` labels.
|
||||
selects series with either `{env="prod",job="a"}` or `{env="dev",job="b"}` labels.
|
||||
See [these docs](https://docs.victoriametrics.com/keyConcepts.html#filtering-by-multiple-or-filters) for details.
|
||||
* Support for `group_left(*)` and `group_right(*)` for copying all the labels from time series on the `one` side
|
||||
of [many-to-one operations](https://prometheus.io/docs/prometheus/latest/querying/operators/#many-to-one-and-one-to-many-vector-matches).
|
||||
@@ -105,7 +98,7 @@ The list of MetricsQL features on top of PromQL:
|
||||
* Trailing commas on all the lists are allowed - label filters, function args and with expressions.
|
||||
For instance, the following queries are valid: `m{foo="bar",}`, `f(a, b,)`, `WITH (x=y,) x`.
|
||||
This simplifies maintenance of multi-line queries.
|
||||
* Metric names and label names may contain any unicode letter. For example `температура{город="Київ"}` is a value MetricsQL expression.
|
||||
* Metric names and label names may contain any unicode letter. For example `температура{город="Киев"}` is a value MetricsQL expression.
|
||||
* Metric names and labels names may contain escaped chars. For example, `foo\-bar{baz\=aa="b"}` is valid expression.
|
||||
It returns time series with name `foo-bar` containing label `baz=aa` with value `b`.
|
||||
Additionally, the following escape sequences are supported:
|
||||
@@ -124,8 +117,7 @@ The list of MetricsQL features on top of PromQL:
|
||||
Go to [WITH templates playground](https://play.victoriametrics.com/select/accounting/1/6a716b0f-38bc-4856-90ce-448fd713e3fe/expand-with-exprs) and try it.
|
||||
* String literals may be concatenated. This is useful with `WITH` templates:
|
||||
`WITH (commonPrefix="long_metric_prefix_") {__name__=commonPrefix+"suffix1"} / {__name__=commonPrefix+"suffix2"}`.
|
||||
* `keep_metric_names` modifier can be applied to all the [rollup functions](#rollup-functions), [transform functions](#transform-functions)
|
||||
and [binary operators](https://prometheus.io/docs/prometheus/latest/querying/operators/#binary-operators).
|
||||
* `keep_metric_names` modifier can be applied to all the [rollup functions](#rollup-functions), [transform functions](#transform-functions) and [binary operators](https://prometheus.io/docs/prometheus/latest/querying/operators/#binary-operators).
|
||||
This modifier prevents from dropping metric names in function results. See [these docs](#keep_metric_names).
|
||||
|
||||
## keep_metric_names
|
||||
@@ -163,15 +155,14 @@ Additional details:
|
||||
The interval between points is set as `step` query arg passed by Grafana to [/api/v1/query_range](https://docs.victoriametrics.com/keyConcepts.html#range-query).
|
||||
* If the given [series selector](https://docs.victoriametrics.com/keyConcepts.html#filtering) returns multiple time series,
|
||||
then rollups are calculated individually per each returned series.
|
||||
* If lookbehind window in square brackets is missing, then it is automatically set to the following value:
|
||||
- To `step` value passed to [/api/v1/query_range](https://docs.victoriametrics.com/keyConcepts.html#range-query) or [/api/v1/query](https://docs.victoriametrics.com/keyconcepts/#instant-query)
|
||||
for all the [rollup functions](#rollup-functions) except of [default_rollup](#default_rollup) and [rate](#rate). This value is known as `$__interval` in Grafana or `1i` in MetricsQL.
|
||||
For example, `avg_over_time(temperature)` is automatically transformed to `avg_over_time(temperature[1i])`.
|
||||
- To the `max(step, scrape_interval)`, where `scrape_interval` is the interval between [raw samples](https://docs.victoriametrics.com/keyconcepts/#raw-samples)
|
||||
for [default_rollup](#default_rollup) and [rate](#rate) functions. This allows avoiding unexpected gaps on the graph when `step` is smaller than `scrape_interval`.
|
||||
* If lookbehind window in square brackets is missing, then MetricsQL automatically sets the lookbehind window
|
||||
to the interval between points on the graph (aka `step` query arg at [/api/v1/query_range](https://docs.victoriametrics.com/keyConcepts.html#range-query),
|
||||
`$__interval` value from Grafana or `1i` duration in MetricsQL).
|
||||
For example, `rate(http_requests_total)` is equivalent to `rate(http_requests_total[$__interval])` in Grafana.
|
||||
It is also equivalent to `rate(http_requests_total[1i])`.
|
||||
* Every [series selector](https://docs.victoriametrics.com/keyConcepts.html#filtering) in MetricsQL must be wrapped into a rollup function.
|
||||
Otherwise, it is automatically wrapped into [default_rollup](#default_rollup). For example, `foo{bar="baz"}`
|
||||
is automatically converted to `default_rollup(foo{bar="baz"})` before performing the calculations.
|
||||
is automatically converted to `default_rollup(foo{bar="baz"}[1i])` before performing the calculations.
|
||||
* If something other than [series selector](https://docs.victoriametrics.com/keyConcepts.html#filtering) is passed to rollup function,
|
||||
then the inner arg is automatically converted to a [subquery](#subqueries).
|
||||
* All the rollup functions accept optional `keep_metric_names` modifier. If it is set, then the function keeps metric names in results.
|
||||
@@ -186,9 +177,7 @@ The list of supported rollup functions:
|
||||
`absent_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which returns 1
|
||||
if the given lookbehind window `d` doesn't contain raw samples. Otherwise, it returns an empty result.
|
||||
|
||||
This function is supported by PromQL.
|
||||
|
||||
See also [present_over_time](#present_over_time).
|
||||
This function is supported by PromQL. See also [present_over_time](#present_over_time).
|
||||
|
||||
#### aggr_over_time
|
||||
|
||||
@@ -218,9 +207,7 @@ See also [descent_over_time](#descent_over_time).
|
||||
over raw samples on the given lookbehind window `d` per each time series returned
|
||||
from the given [series_selector](https://docs.victoriametrics.com/keyConcepts.html#filtering).
|
||||
|
||||
This function is supported by PromQL.
|
||||
|
||||
See also [median_over_time](#median_over_time).
|
||||
This function is supported by PromQL. See also [median_over_time](#median_over_time).
|
||||
|
||||
#### changes
|
||||
|
||||
@@ -233,9 +220,7 @@ See [this article](https://medium.com/@romanhavronenko/victoriametrics-promql-co
|
||||
|
||||
Metric names are stripped from the resulting rollups. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
|
||||
|
||||
This function is supported by PromQL.
|
||||
|
||||
See also [changes_prometheus](#changes_prometheus).
|
||||
This function is supported by PromQL. See also [changes_prometheus](#changes_prometheus).
|
||||
|
||||
#### changes_prometheus
|
||||
|
||||
@@ -248,9 +233,7 @@ See [this article](https://medium.com/@romanhavronenko/victoriametrics-promql-co
|
||||
|
||||
Metric names are stripped from the resulting rollups. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
|
||||
|
||||
This function is supported by PromQL.
|
||||
|
||||
See also [changes](#changes).
|
||||
This function is supported by PromQL. See also [changes](#changes).
|
||||
|
||||
#### count_eq_over_time
|
||||
|
||||
@@ -260,7 +243,7 @@ from the given [series_selector](https://docs.victoriametrics.com/keyConcepts.ht
|
||||
|
||||
Metric names are stripped from the resulting rollups. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
|
||||
|
||||
See also [count_over_time](#count_over_time), [share_eq_over_time](#share_eq_over_time) and [count_values_over_time](#count_values_over_time).
|
||||
See also [count_over_time](#count_over_time).
|
||||
|
||||
#### count_gt_over_time
|
||||
|
||||
@@ -270,7 +253,7 @@ from the given [series_selector](https://docs.victoriametrics.com/keyConcepts.ht
|
||||
|
||||
Metric names are stripped from the resulting rollups. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
|
||||
|
||||
See also [count_over_time](#count_over_time) and [share_gt_over_time](#share_gt_over_time).
|
||||
See also [count_over_time](#count_over_time).
|
||||
|
||||
#### count_le_over_time
|
||||
|
||||
@@ -280,7 +263,7 @@ from the given [series_selector](https://docs.victoriametrics.com/keyConcepts.ht
|
||||
|
||||
Metric names are stripped from the resulting rollups. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
|
||||
|
||||
See also [count_over_time](#count_over_time) and [share_le_over_time](#share_le_over_time).
|
||||
See also [count_over_time](#count_over_time).
|
||||
|
||||
#### count_ne_over_time
|
||||
|
||||
@@ -299,19 +282,8 @@ on the given lookbehind window `d` per each time series returned from the given
|
||||
|
||||
Metric names are stripped from the resulting rollups. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
|
||||
|
||||
This function is supported by PromQL.
|
||||
|
||||
See also [count_le_over_time](#count_le_over_time), [count_gt_over_time](#count_gt_over_time), [count_eq_over_time](#count_eq_over_time) and [count_ne_over_time](#count_ne_over_time).
|
||||
|
||||
#### count_values_over_time
|
||||
|
||||
`count_values_over_time("label", series_selector[d])` is a [rollup function](#rollup-functions), which counts the number of raw samples
|
||||
with the same value over the given lookbehind window and stores the counts in a time series with an additional `label`, which contains each initial value.
|
||||
The results are calculated independently per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyConcepts.html#filtering).
|
||||
|
||||
Metric names are stripped from the resulting rollups. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
|
||||
|
||||
See also [count_eq_over_time](#count_eq_over_time), [count_values](#count_values) and [distinct_over_time](#distinct_over_time) and [label_match](#label_match).
|
||||
This function is supported by PromQL. See also [count_le_over_time](#count_le_over_time), [count_gt_over_time](#count_gt_over_time),
|
||||
[count_eq_over_time](#count_eq_over_time) and [count_ne_over_time](#count_ne_over_time).
|
||||
|
||||
#### decreases_over_time
|
||||
|
||||
@@ -327,11 +299,6 @@ See also [increases_over_time](#increases_over_time).
|
||||
`default_rollup(series_selector[d])` is a [rollup function](#rollup-functions), which returns the last raw sample value on the given lookbehind window `d`
|
||||
per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyConcepts.html#filtering).
|
||||
|
||||
If the lookbehind window is skipped in square brackets, then it is automatically calculated as `max(step, scrape_interval)`, where `step` is the query arg value
|
||||
passed to [/api/v1/query_range](https://docs.victoriametrics.com/keyconcepts/#range-query) or [/api/v1/query](https://docs.victoriametrics.com/keyconcepts/#instant-query),
|
||||
while `scrape_interval` is the interval between [raw samples](https://docs.victoriametrics.com/keyconcepts/#raw-samples) for the selected time series.
|
||||
This allows avoiding unexpected gaps on the graph when `step` is smaller than the `scrape_interval`.
|
||||
|
||||
#### delta
|
||||
|
||||
`delta(series_selector[d])` is a [rollup function](#rollup-functions), which calculates the difference between
|
||||
@@ -343,9 +310,7 @@ See [this article](https://medium.com/@romanhavronenko/victoriametrics-promql-co
|
||||
|
||||
Metric names are stripped from the resulting rollups. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
|
||||
|
||||
This function is supported by PromQL.
|
||||
|
||||
See also [increase](#increase) and [delta_prometheus](#delta_prometheus).
|
||||
This function is supported by PromQL. See also [increase](#increase) and [delta_prometheus](#delta_prometheus).
|
||||
|
||||
#### delta_prometheus
|
||||
|
||||
@@ -368,9 +333,7 @@ The derivative is calculated using linear regression.
|
||||
|
||||
Metric names are stripped from the resulting rollups. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
|
||||
|
||||
This function is supported by PromQL.
|
||||
|
||||
See also [deriv_fast](#deriv_fast) and [ideriv](#ideriv).
|
||||
This function is supported by PromQL. See also [deriv_fast](#deriv_fast) and [ideriv](#ideriv).
|
||||
|
||||
#### deriv_fast
|
||||
|
||||
@@ -401,8 +364,6 @@ on the given lookbehind window `d` per each time series returned from the given
|
||||
|
||||
Metric names are stripped from the resulting rollups. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
|
||||
|
||||
See also [count_values_over_time](#count_values_over_time).
|
||||
|
||||
#### duration_over_time
|
||||
|
||||
`duration_over_time(series_selector[d], max_interval)` is a [rollup function](#rollup-functions), which returns the duration in seconds
|
||||
@@ -462,9 +423,7 @@ over the given lookbehind window `d` using the given smoothing factor `sf` and t
|
||||
Both `sf` and `tf` must be in the range `[0...1]`. It is expected that the [series_selector](https://docs.victoriametrics.com/keyConcepts.html#filtering)
|
||||
returns time series of [gauge type](https://docs.victoriametrics.com/keyConcepts.html#gauge).
|
||||
|
||||
This function is supported by PromQL.
|
||||
|
||||
See also [range_linear_regression](#range_linear_regression).
|
||||
This function is supported by PromQL. See also [range_linear_regression](#range_linear_regression).
|
||||
|
||||
#### idelta
|
||||
|
||||
@@ -473,9 +432,7 @@ on the given lookbehind window `d` per each time series returned from the given
|
||||
|
||||
Metric names are stripped from the resulting rollups. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
|
||||
|
||||
This function is supported by PromQL.
|
||||
|
||||
See also [delta](#delta).
|
||||
This function is supported by PromQL. See also [delta](#delta).
|
||||
|
||||
#### ideriv
|
||||
|
||||
@@ -498,9 +455,7 @@ See [this article](https://medium.com/@romanhavronenko/victoriametrics-promql-co
|
||||
|
||||
Metric names are stripped from the resulting rollups. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
|
||||
|
||||
This function is supported by PromQL.
|
||||
|
||||
See also [increase_pure](#increase_pure), [increase_prometheus](#increase_prometheus) and [delta](#delta).
|
||||
This function is supported by PromQL. See also [increase_pure](#increase_pure), [increase_prometheus](#increase_prometheus) and [delta](#delta).
|
||||
|
||||
#### increase_prometheus
|
||||
|
||||
@@ -544,9 +499,7 @@ It is expected that the `series_selector` returns time series of [counter type](
|
||||
|
||||
Metric names are stripped from the resulting rollups. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
|
||||
|
||||
This function is supported by PromQL.
|
||||
|
||||
See also [rate](#rate) and [rollup_rate](#rollup_rate).
|
||||
This function is supported by PromQL. See also [rate](#rate) and [rollup_rate](#rollup_rate).
|
||||
|
||||
#### lag
|
||||
|
||||
@@ -563,9 +516,7 @@ See also [lifetime](#lifetime) and [duration_over_time](#duration_over_time).
|
||||
`last_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which returns the last raw sample value on the given lookbehind window `d`
|
||||
per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyConcepts.html#filtering).
|
||||
|
||||
This function is supported by PromQL.
|
||||
|
||||
See also [first_over_time](#first_over_time) and [tlast_over_time](#tlast_over_time).
|
||||
This function is supported by PromQL. See also [first_over_time](#first_over_time) and [tlast_over_time](#tlast_over_time).
|
||||
|
||||
#### lifetime
|
||||
|
||||
@@ -588,9 +539,7 @@ See also [mad](#mad), [range_mad](#range_mad) and [outlier_iqr_over_time](#outli
|
||||
`max_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which calculates the maximum value over raw samples
|
||||
on the given lookbehind window `d` per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyConcepts.html#filtering).
|
||||
|
||||
This function is supported by PromQL.
|
||||
|
||||
See also [tmax_over_time](#tmax_over_time).
|
||||
This function is supported by PromQL. See also [tmax_over_time](#tmax_over_time).
|
||||
|
||||
#### median_over_time
|
||||
|
||||
@@ -605,9 +554,7 @@ See also [avg_over_time](#avg_over_time).
|
||||
`min_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which calculates the minimum value over raw samples
|
||||
on the given lookbehind window `d` per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyConcepts.html#filtering).
|
||||
|
||||
This function is supported by PromQL.
|
||||
|
||||
See also [tmin_over_time](#tmin_over_time).
|
||||
This function is supported by PromQL. See also [tmin_over_time](#tmin_over_time).
|
||||
|
||||
#### mode_over_time
|
||||
|
||||
@@ -623,7 +570,7 @@ if its value is either smaller than the `q25-1.5*iqr` or bigger than `q75+1.5*iq
|
||||
- `q25` and `q75` are 25th and 75th [percentiles](https://en.wikipedia.org/wiki/Percentile) over raw samples on the lookbehind window `d`.
|
||||
|
||||
The `outlier_iqr_over_time()` is useful for detecting anomalies in gauge values based on the previous history of values.
|
||||
For example, `outlier_iqr_over_time(memory_usage_bytes[1h])` triggers when `memory_usage_bytes` suddenly goes outside the usual value range for the last hour.
|
||||
For example, `outlier_iqr_over_time(memory_usage_bytes[1h])` triggers when `memory_usage_bytes` suddenly goes outside the usual value range for the last 24 hours.
|
||||
|
||||
See also [outliers_iqr](#outliers_iqr).
|
||||
|
||||
@@ -633,9 +580,7 @@ See also [outliers_iqr](#outliers_iqr).
|
||||
linear interpolation over raw samples on the given lookbehind window `d`. The predicted value is calculated individually per each time series
|
||||
returned from the given [series_selector](https://docs.victoriametrics.com/keyConcepts.html#filtering).
|
||||
|
||||
This function is supported by PromQL.
|
||||
|
||||
See also [range_linear_regression](#range_linear_regression).
|
||||
This function is supported by PromQL. See also [range_linear_regression](#range_linear_regression).
|
||||
|
||||
#### present_over_time
|
||||
|
||||
@@ -652,9 +597,7 @@ This function is supported by PromQL.
|
||||
on the given lookbehind window `d` per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyConcepts.html#filtering).
|
||||
The `phi` value must be in the range `[0...1]`.
|
||||
|
||||
This function is supported by PromQL.
|
||||
|
||||
See also [quantiles_over_time](#quantiles_over_time).
|
||||
This function is supported by PromQL. See also [quantiles_over_time](#quantiles_over_time).
|
||||
|
||||
#### quantiles_over_time
|
||||
|
||||
@@ -679,16 +622,9 @@ Metric names are stripped from the resulting rollups. Add [keep_metric_names](#k
|
||||
over the given lookbehind window `d` per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyConcepts.html#filtering).
|
||||
It is expected that the `series_selector` returns time series of [counter type](https://docs.victoriametrics.com/keyConcepts.html#counter).
|
||||
|
||||
If the lookbehind window is skipped in square brackets, then it is automatically calculated as `max(step, scrape_interval)`, where `step` is the query arg value
|
||||
passed to [/api/v1/query_range](https://docs.victoriametrics.com/keyconcepts/#range-query) or [/api/v1/query](https://docs.victoriametrics.com/keyconcepts/#instant-query),
|
||||
while `scrape_interval` is the interval between [raw samples](https://docs.victoriametrics.com/keyconcepts/#raw-samples) for the selected time series.
|
||||
This allows avoiding unexpected gaps on the graph when `step` is smaller than the `scrape_interval`.
|
||||
|
||||
Metric names are stripped from the resulting rollups. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
|
||||
|
||||
This function is supported by PromQL.
|
||||
|
||||
See also [irate](#irate) and [rollup_rate](#rollup_rate).
|
||||
This function is supported by PromQL. See also [irate](#irate) and [rollup_rate](#rollup_rate).
|
||||
|
||||
#### rate_over_sum
|
||||
|
||||
@@ -716,7 +652,6 @@ on the given lookbehind window `d` and returns them in time series with `rollup=
|
||||
These values are calculated individually per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyConcepts.html#filtering).
|
||||
|
||||
Optional 2nd argument `"min"`, `"max"` or `"avg"` can be passed to keep only one calculation result and without adding a label.
|
||||
See also [label_match](#label_match).
|
||||
|
||||
#### rollup_candlestick
|
||||
|
||||
@@ -725,8 +660,7 @@ over raw samples on the given lookbehind window `d` and returns them in time ser
|
||||
The calculations are performed individually per each time series returned
|
||||
from the given [series_selector](https://docs.victoriametrics.com/keyConcepts.html#filtering). This function is useful for financial applications.
|
||||
|
||||
Optional 2nd argument `"open"`, `"high"` or `"low"` or `"close"` can be passed to keep only one calculation result and without adding a label.
|
||||
See also [label_match](#label_match).
|
||||
Optional 2nd argument `"min"`, `"max"` or `"avg"` can be passed to keep only one calculation result and without adding a label.
|
||||
|
||||
#### rollup_delta
|
||||
|
||||
@@ -736,7 +670,6 @@ and returns them in time series with `rollup="min"`, `rollup="max"` and `rollup=
|
||||
The calculations are performed individually per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyConcepts.html#filtering).
|
||||
|
||||
Optional 2nd argument `"min"`, `"max"` or `"avg"` can be passed to keep only one calculation result and without adding a label.
|
||||
See also [label_match](#label_match).
|
||||
|
||||
Metric names are stripped from the resulting rollups. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
|
||||
|
||||
@@ -750,7 +683,6 @@ and returns them in time series with `rollup="min"`, `rollup="max"` and `rollup=
|
||||
The calculations are performed individually per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyConcepts.html#filtering).
|
||||
|
||||
Optional 2nd argument `"min"`, `"max"` or `"avg"` can be passed to keep only one calculation result and without adding a label.
|
||||
See also [label_match](#label_match).
|
||||
|
||||
Metric names are stripped from the resulting rollups. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
|
||||
|
||||
@@ -762,7 +694,6 @@ and returns them in time series with `rollup="min"`, `rollup="max"` and `rollup=
|
||||
The calculations are performed individually per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyConcepts.html#filtering).
|
||||
|
||||
Optional 2nd argument `"min"`, `"max"` or `"avg"` can be passed to keep only one calculation result and without adding a label.
|
||||
See also [label_match](#label_match).
|
||||
|
||||
Metric names are stripped from the resulting rollups. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names. See also [rollup_delta](#rollup_delta).
|
||||
|
||||
@@ -776,10 +707,10 @@ See [this article](https://valyala.medium.com/why-irate-from-prometheus-doesnt-c
|
||||
when to use `rollup_rate()`.
|
||||
|
||||
Optional 2nd argument `"min"`, `"max"` or `"avg"` can be passed to keep only one calculation result and without adding a label.
|
||||
See also [label_match](#label_match).
|
||||
|
||||
The calculations are performed individually per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyConcepts.html#filtering).
|
||||
|
||||
|
||||
Metric names are stripped from the resulting rollups. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
|
||||
|
||||
#### rollup_scrape_interval
|
||||
@@ -790,7 +721,6 @@ and returns them in time series with `rollup="min"`, `rollup="max"` and `rollup=
|
||||
The calculations are performed individually per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyConcepts.html#filtering).
|
||||
|
||||
Optional 2nd argument `"min"`, `"max"` or `"avg"` can be passed to keep only one calculation result and without adding a label.
|
||||
See also [label_match](#label_match).
|
||||
|
||||
Metric names are stripped from the resulting rollups. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names. See also [scrape_interval](#scrape_interval).
|
||||
|
||||
@@ -813,7 +743,7 @@ This function is useful for calculating SLI and SLO. Example: `share_gt_over_tim
|
||||
|
||||
Metric names are stripped from the resulting rollups. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
|
||||
|
||||
See also [share_le_over_time](#share_le_over_time) and [count_gt_over_time](#count_gt_over_time).
|
||||
See also [share_le_over_time](#share_le_over_time).
|
||||
|
||||
#### share_le_over_time
|
||||
|
||||
@@ -826,7 +756,7 @@ the share of time series values for the last 24 hours when memory usage was belo
|
||||
|
||||
Metric names are stripped from the resulting rollups. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
|
||||
|
||||
See also [share_gt_over_time](#share_gt_over_time) and [count_le_over_time](#count_le_over_time).
|
||||
See also [share_gt_over_time](#share_gt_over_time).
|
||||
|
||||
#### share_eq_over_time
|
||||
|
||||
@@ -836,8 +766,6 @@ from the given [series_selector](https://docs.victoriametrics.com/keyConcepts.ht
|
||||
|
||||
Metric names are stripped from the resulting rollups. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
|
||||
|
||||
See also [count_eq_over_time](#count_eq_over_time).
|
||||
|
||||
#### stale_samples_over_time
|
||||
|
||||
`stale_samples_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which calculates the number
|
||||
@@ -853,9 +781,7 @@ on the given lookbehind window `d` per each time series returned from the given
|
||||
|
||||
Metric names are stripped from the resulting rollups. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
|
||||
|
||||
This function is supported by PromQL.
|
||||
|
||||
See also [stdvar_over_time](#stdvar_over_time).
|
||||
This function is supported by PromQL. See also [stdvar_over_time](#stdvar_over_time).
|
||||
|
||||
#### stdvar_over_time
|
||||
|
||||
@@ -864,36 +790,7 @@ on the given lookbehind window `d` per each time series returned from the given
|
||||
|
||||
Metric names are stripped from the resulting rollups. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
|
||||
|
||||
This function is supported by PromQL.
|
||||
|
||||
See also [stddev_over_time](#stddev_over_time).
|
||||
|
||||
#### sum_eq_over_time
|
||||
|
||||
`sum_eq_over_time(series_selector[d], eq)` is a [rollup function](#rollup-function), which calculates the sum of raw sample values equal to `eq`
|
||||
on the given lookbehind window `d` per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyConcepts.html#filtering).
|
||||
|
||||
Metric names are stripped from the resulting rollups. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
|
||||
|
||||
See also [sum_over_time](#sum_over_time) and [count_eq_over_time](#count_eq_over_time).
|
||||
|
||||
#### sum_gt_over_time
|
||||
|
||||
`sum_gt_over_time(series_selector[d], gt)` is a [rollup function](#rollup-function), which calculates the sum of raw sample values bigger than `gt`
|
||||
on the given lookbehind window `d` per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyConcepts.html#filtering).
|
||||
|
||||
Metric names are stripped from the resulting rollups. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
|
||||
|
||||
See also [sum_over_time](#sum_over_time) and [count_gt_over_time](#count_gt_over_time).
|
||||
|
||||
#### sum_le_over_time
|
||||
|
||||
`sum_le_over_time(series_selector[d], le)` is a [rollup function](#rollup-function), which calculates the sum of raw sample values smaller or equal to `le`
|
||||
on the given lookbehind window `d` per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyConcepts.html#filtering).
|
||||
|
||||
Metric names are stripped from the resulting rollups. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
|
||||
|
||||
See also [sum_over_time](#sum_over_time) and [count_le_over_time](#count_le_over_time).
|
||||
This function is supported by PromQL. See also [stddev_over_time](#stddev_over_time).
|
||||
|
||||
#### sum_over_time
|
||||
|
||||
@@ -913,27 +810,25 @@ Metric names are stripped from the resulting rollups. Add [keep_metric_names](#k
|
||||
|
||||
#### timestamp
|
||||
|
||||
`timestamp(series_selector[d])` is a [rollup function](#rollup-functions), which returns the timestamp in seconds with millisecond precision for the last raw sample
|
||||
`timestamp(series_selector[d])` is a [rollup function](#rollup-functions), which returns the timestamp in seconds for the last raw sample
|
||||
on the given lookbehind window `d` per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyConcepts.html#filtering).
|
||||
|
||||
Metric names are stripped from the resulting rollups. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
|
||||
|
||||
This function is supported by PromQL.
|
||||
|
||||
See also [time](#time) and [now](#now).
|
||||
This function is supported by PromQL. See also [timestamp_with_name](#timestamp_with_name).
|
||||
|
||||
#### timestamp_with_name
|
||||
|
||||
`timestamp_with_name(series_selector[d])` is a [rollup function](#rollup-functions), which returns the timestamp in seconds with millisecond precision for the last raw sample
|
||||
`timestamp_with_name(series_selector[d])` is a [rollup function](#rollup-functions), which returns the timestamp in seconds for the last raw sample
|
||||
on the given lookbehind window `d` per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyConcepts.html#filtering).
|
||||
|
||||
Metric names are preserved in the resulting rollups.
|
||||
|
||||
See also [timestamp](#timestamp) and [keep_metric_names](#keep_metric_names) modifier.
|
||||
See also [timestamp](#timestamp).
|
||||
|
||||
#### tfirst_over_time
|
||||
|
||||
`tfirst_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which returns the timestamp in seconds with millisecond precision for the first raw sample
|
||||
`tfirst_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which returns the timestamp in seconds for the first raw sample
|
||||
on the given lookbehind window `d` per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyConcepts.html#filtering).
|
||||
|
||||
Metric names are stripped from the resulting rollups. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
|
||||
@@ -942,7 +837,7 @@ See also [first_over_time](#first_over_time).
|
||||
|
||||
#### tlast_change_over_time
|
||||
|
||||
`tlast_change_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which returns the timestamp in seconds with millisecond precision for the last change
|
||||
`tlast_change_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which returns the timestamp in seconds for the last change
|
||||
per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyConcepts.html#filtering) on the given lookbehind window `d`.
|
||||
|
||||
Metric names are stripped from the resulting rollups. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
|
||||
@@ -957,7 +852,7 @@ See also [tlast_change_over_time](#tlast_change_over_time).
|
||||
|
||||
#### tmax_over_time
|
||||
|
||||
`tmax_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which returns the timestamp in seconds with millisecond precision for the raw sample
|
||||
`tmax_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which returns the timestamp in seconds for the raw sample
|
||||
with the maximum value on the given lookbehind window `d`. It is calculated independently per each time series returned
|
||||
from the given [series_selector](https://docs.victoriametrics.com/keyConcepts.html#filtering).
|
||||
|
||||
@@ -967,7 +862,7 @@ See also [max_over_time](#max_over_time).
|
||||
|
||||
#### tmin_over_time
|
||||
|
||||
`tmin_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which returns the timestamp in seconds with millisecond precision for the raw sample
|
||||
`tmin_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which returns the timestamp in seconds for the raw sample
|
||||
with the minimum value on the given lookbehind window `d`. It is calculated independently per each time series returned
|
||||
from the given [series_selector](https://docs.victoriametrics.com/keyConcepts.html#filtering).
|
||||
|
||||
@@ -996,7 +891,7 @@ Additional details:
|
||||
|
||||
* If transform function is applied directly to a [series selector](https://docs.victoriametrics.com/keyConcepts.html#filtering),
|
||||
then the [default_rollup()](#default_rollup) function is automatically applied before calculating the transformations.
|
||||
For example, `abs(temperature)` is implicitly transformed to `abs(default_rollup(temperature))`.
|
||||
For example, `abs(temperature)` is implicitly transformed to `abs(default_rollup(temperature[1i]))`.
|
||||
* All the transform functions accept optional `keep_metric_names` modifier. If it is set,
|
||||
then the function doesn't drop metric names from the resulting time series. See [these docs](#keep_metric_names).
|
||||
|
||||
@@ -1014,9 +909,7 @@ This function is supported by PromQL.
|
||||
|
||||
`absent(q)` is a [transform function](#transform-functions), which returns 1 if `q` has no points. Otherwise, returns an empty result.
|
||||
|
||||
This function is supported by PromQL.
|
||||
|
||||
See also [absent_over_time](#absent_over_time).
|
||||
This function is supported by PromQL. See also [absent_over_time](#absent_over_time).
|
||||
|
||||
#### acos
|
||||
|
||||
@@ -1025,9 +918,7 @@ for every point of every time series returned by `q`.
|
||||
|
||||
Metric names are stripped from the resulting series. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
|
||||
|
||||
This function is supported by PromQL.
|
||||
|
||||
See also [asin](#asin) and [cos](#cos).
|
||||
This function is supported by PromQL. See also [asin](#asin) and [cos](#cos).
|
||||
|
||||
#### acosh
|
||||
|
||||
@@ -1036,9 +927,7 @@ See also [asin](#asin) and [cos](#cos).
|
||||
|
||||
Metric names are stripped from the resulting series. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
|
||||
|
||||
This function is supported by PromQL.
|
||||
|
||||
See also [sinh](#cosh).
|
||||
This function is supported by PromQL. See also [sinh](#cosh).
|
||||
|
||||
#### asin
|
||||
|
||||
@@ -1047,9 +936,7 @@ for every point of every time series returned by `q`.
|
||||
|
||||
Metric names are stripped from the resulting series. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
|
||||
|
||||
This function is supported by PromQL.
|
||||
|
||||
See also [acos](#acos) and [sin](#sin).
|
||||
This function is supported by PromQL. See also [acos](#acos) and [sin](#sin).
|
||||
|
||||
#### asinh
|
||||
|
||||
@@ -1058,9 +945,7 @@ See also [acos](#acos) and [sin](#sin).
|
||||
|
||||
Metric names are stripped from the resulting series. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
|
||||
|
||||
This function is supported by PromQL.
|
||||
|
||||
See also [sinh](#sinh).
|
||||
This function is supported by PromQL. See also [sinh](#sinh).
|
||||
|
||||
#### atan
|
||||
|
||||
@@ -1069,9 +954,7 @@ for every point of every time series returned by `q`.
|
||||
|
||||
Metric names are stripped from the resulting series. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
|
||||
|
||||
This function is supported by PromQL.
|
||||
|
||||
See also [tan](#tan).
|
||||
This function is supported by PromQL. See also [tan](#tan).
|
||||
|
||||
#### atanh
|
||||
|
||||
@@ -1080,9 +963,7 @@ See also [tan](#tan).
|
||||
|
||||
Metric names are stripped from the resulting series. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
|
||||
|
||||
This function is supported by PromQL.
|
||||
|
||||
See also [tanh](#tanh).
|
||||
This function is supported by PromQL. See also [tanh](#tanh).
|
||||
|
||||
#### bitmap_and
|
||||
|
||||
@@ -1113,33 +994,25 @@ See also [prometheus_buckets](#prometheus_buckets) and [histogram_quantile](#his
|
||||
|
||||
`ceil(q)` is a [transform function](#transform-functions), which rounds every point for every time series returned by `q` to the upper nearest integer.
|
||||
|
||||
This function is supported by PromQL.
|
||||
|
||||
See also [floor](#floor) and [round](#round).
|
||||
This function is supported by PromQL. See also [floor](#floor) and [round](#round).
|
||||
|
||||
#### clamp
|
||||
|
||||
`clamp(q, min, max)` is a [transform function](#transform-functions), which clamps every point for every time series returned by `q` with the given `min` and `max` values.
|
||||
|
||||
This function is supported by PromQL.
|
||||
|
||||
See also [clamp_min](#clamp_min) and [clamp_max](#clamp_max).
|
||||
This function is supported by PromQL. See also [clamp_min](#clamp_min) and [clamp_max](#clamp_max).
|
||||
|
||||
#### clamp_max
|
||||
|
||||
`clamp_max(q, max)` is a [transform function](#transform-functions), which clamps every point for every time series returned by `q` with the given `max` value.
|
||||
|
||||
This function is supported by PromQL.
|
||||
|
||||
See also [clamp](#clamp) and [clamp_min](#clamp_min).
|
||||
This function is supported by PromQL. See also [clamp](#clamp) and [clamp_min](#clamp_min).
|
||||
|
||||
#### clamp_min
|
||||
|
||||
`clamp_min(q, min)` is a [transform function](#transform-functions), which clamps every point for every time series returned by `q` with the given `min` value.
|
||||
|
||||
This function is supported by PromQL.
|
||||
|
||||
See also [clamp](#clamp) and [clamp_max](#clamp_max).
|
||||
This function is supported by PromQL. See also [clamp](#clamp) and [clamp_max](#clamp_max).
|
||||
|
||||
#### cos
|
||||
|
||||
@@ -1147,9 +1020,7 @@ See also [clamp](#clamp) and [clamp_max](#clamp_max).
|
||||
|
||||
Metric names are stripped from the resulting series. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
|
||||
|
||||
This function is supported by PromQL.
|
||||
|
||||
See also [sin](#sin).
|
||||
This function is supported by PromQL. See also [sin](#sin).
|
||||
|
||||
#### cosh
|
||||
|
||||
@@ -1158,9 +1029,7 @@ for every point of every time series returned by `q`.
|
||||
|
||||
Metric names are stripped from the resulting series. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
|
||||
|
||||
This function is supported by PromQL.
|
||||
|
||||
See also [acosh](#acosh).
|
||||
This function is supported by PromQL. This function is supported by PromQL. See also [acosh](#acosh).
|
||||
|
||||
#### day_of_month
|
||||
|
||||
@@ -1171,8 +1040,6 @@ Metric names are stripped from the resulting series. Add [keep_metric_names](#ke
|
||||
|
||||
This function is supported by PromQL.
|
||||
|
||||
See also [day_of_week](#day_of_week) and [day_of_year](#day_of_year).
|
||||
|
||||
#### day_of_week
|
||||
|
||||
`day_of_week(q)` is a [transform function](#transform-functions), which returns the day of week for every point of every time series returned by `q`.
|
||||
@@ -1182,19 +1049,6 @@ Metric names are stripped from the resulting series. Add [keep_metric_names](#ke
|
||||
|
||||
This function is supported by PromQL.
|
||||
|
||||
See also [day_of_month](#day_of_month) and [day_of_year](#day_of_year).
|
||||
|
||||
#### day_of_year
|
||||
|
||||
`day_of_year(q)` is a [transform function](#transform-functions), which returns the day of year for every point of every time series returned by `q`.
|
||||
It is expected that `q` returns unix timestamps. The returned values are in the range `[1...365]` for non-leap years, and `[1 to 366]` in leap years.
|
||||
|
||||
Metric names are stripped from the resulting series. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
|
||||
|
||||
This function is supported by PromQL.
|
||||
|
||||
See also [day_of_week](#day_of_week) and [day_of_month](#day_of_month).
|
||||
|
||||
#### days_in_month
|
||||
|
||||
`days_in_month(q)` is a [transform function](#transform-functions), which returns the number of days in the month identified
|
||||
@@ -1212,9 +1066,7 @@ for every point of every time series returned by `q`.
|
||||
|
||||
Metric names are stripped from the resulting series. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
|
||||
|
||||
This function is supported by PromQL.
|
||||
|
||||
See also [rad](#rad).
|
||||
This function is supported by PromQL. See also [rad](#rad).
|
||||
|
||||
#### drop_empty_series
|
||||
|
||||
@@ -1240,17 +1092,13 @@ See also [start](#start), [time](#time) and [now](#now).
|
||||
|
||||
Metric names are stripped from the resulting series. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
|
||||
|
||||
This function is supported by PromQL.
|
||||
|
||||
See also [ln](#ln).
|
||||
This function is supported by PromQL. See also [ln](#ln).
|
||||
|
||||
#### floor
|
||||
|
||||
`floor(q)` is a [transform function](#transform-functions), which rounds every point for every time series returned by `q` to the lower nearest integer.
|
||||
|
||||
This function is supported by PromQL.
|
||||
|
||||
See also [ceil](#ceil) and [round](#round).
|
||||
This function is supported by PromQL. See also [ceil](#ceil) and [round](#round).
|
||||
|
||||
#### histogram_avg
|
||||
|
||||
@@ -1273,9 +1121,8 @@ When the [percentile](https://en.wikipedia.org/wiki/Percentile) is calculated ov
|
||||
then all the input histograms **must** have buckets with identical boundaries, e.g. they must have the same set of `le` or `vmrange` labels.
|
||||
Otherwise, the returned result may be invalid. See [this issue](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3231) for details.
|
||||
|
||||
This function is supported by PromQL (except of the `boundLabel` arg).
|
||||
|
||||
See also [histogram_quantiles](#histogram_quantiles), [histogram_share](#histogram_share) and [quantile](#quantile).
|
||||
This function is supported by PromQL (except of the `boundLabel` arg). See also [histogram_quantiles](#histogram_quantiles), [histogram_share](#histogram_share)
|
||||
and [quantile](#quantile).
|
||||
|
||||
#### histogram_quantiles
|
||||
|
||||
@@ -1347,9 +1194,7 @@ This allows implementing simple paging for `q` time series. See also [limitk](#l
|
||||
|
||||
Metric names are stripped from the resulting series. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
|
||||
|
||||
This function is supported by PromQL.
|
||||
|
||||
See also [exp](#exp) and [log2](#log2).
|
||||
This function is supported by PromQL. See also [exp](#exp) and [log2](#log2).
|
||||
|
||||
#### log2
|
||||
|
||||
@@ -1357,9 +1202,7 @@ See also [exp](#exp) and [log2](#log2).
|
||||
|
||||
Metric names are stripped from the resulting series. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
|
||||
|
||||
This function is supported by PromQL.
|
||||
|
||||
See also [log10](#log10) and [ln](#ln).
|
||||
This function is supported by PromQL. See also [log10](#log10) and [ln](#ln).
|
||||
|
||||
#### log10
|
||||
|
||||
@@ -1367,9 +1210,7 @@ See also [log10](#log10) and [ln](#ln).
|
||||
|
||||
Metric names are stripped from the resulting series. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
|
||||
|
||||
This function is supported by PromQL.
|
||||
|
||||
See also [log2](#log2) and [ln](#ln).
|
||||
This function is supported by PromQL. See also [log2](#log2) and [ln](#ln).
|
||||
|
||||
#### minute
|
||||
|
||||
@@ -1408,9 +1249,7 @@ for every point of every time series returned by `q`.
|
||||
|
||||
Metric names are stripped from the resulting series. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
|
||||
|
||||
This function is supported by PromQL.
|
||||
|
||||
See also [deg](#deg).
|
||||
This function is supported by PromQL. See also [deg](#deg).
|
||||
|
||||
#### prometheus_buckets
|
||||
|
||||
@@ -1538,9 +1377,7 @@ for points returned by `q`, e.g. it is equivalent to the following query: `(q -
|
||||
`round(q, nearest)` is a [transform function](#transform-functions), which rounds every point of every time series returned by `q` to the `nearest` multiple.
|
||||
If `nearest` is missing then the rounding is performed to the nearest integer.
|
||||
|
||||
This function is supported by PromQL.
|
||||
|
||||
See also [floor](#floor) and [ceil](#ceil).
|
||||
This function is supported by PromQL. See also [floor](#floor) and [ceil](#ceil).
|
||||
|
||||
#### ru
|
||||
|
||||
@@ -1584,9 +1421,7 @@ This function is supported by PromQL.
|
||||
|
||||
Metric names are stripped from the resulting series. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
|
||||
|
||||
This function is supported by MetricsQL.
|
||||
|
||||
See also [cos](#cos).
|
||||
This function is supported by MetricsQL. See also [cos](#cos).
|
||||
|
||||
#### sinh
|
||||
|
||||
@@ -1595,9 +1430,7 @@ for every point of every time series returned by `q`.
|
||||
|
||||
Metric names are stripped from the resulting series. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
|
||||
|
||||
This function is supported by MetricsQL.
|
||||
|
||||
See also [cosh](#cosh).
|
||||
This function is supported by MetricsQL. See also [cosh](#cosh).
|
||||
|
||||
#### tan
|
||||
|
||||
@@ -1605,9 +1438,7 @@ See also [cosh](#cosh).
|
||||
|
||||
Metric names are stripped from the resulting series. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
|
||||
|
||||
This function is supported by MetricsQL.
|
||||
|
||||
See also [atan](#atan).
|
||||
This function is supported by MetricsQL. See also [atan](#atan).
|
||||
|
||||
#### tanh
|
||||
|
||||
@@ -1616,9 +1447,7 @@ for every point of every time series returned by `q`.
|
||||
|
||||
Metric names are stripped from the resulting series. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
|
||||
|
||||
This function is supported by MetricsQL.
|
||||
|
||||
See also [atanh](#atanh).
|
||||
This function is supported by MetricsQL. See also [atanh](#atanh).
|
||||
|
||||
#### smooth_exponential
|
||||
|
||||
@@ -1629,17 +1458,13 @@ by `q` using [exponential moving average](https://en.wikipedia.org/wiki/Moving_a
|
||||
|
||||
`sort(q)` is a [transform function](#transform-functions), which sorts series in ascending order by the last point in every time series returned by `q`.
|
||||
|
||||
This function is supported by PromQL.
|
||||
|
||||
See also [sort_desc](#sort_desc) and [sort_by_label](#sort_by_label).
|
||||
This function is supported by PromQL. See also [sort_desc](#sort_desc) and [sort_by_label](#sort_by_label).
|
||||
|
||||
#### sort_desc
|
||||
|
||||
`sort_desc(q)` is a [transform function](#transform-functions), which sorts series in descending order by the last point in every time series returned by `q`.
|
||||
|
||||
This function is supported by PromQL.
|
||||
|
||||
See also [sort](#sort) and [sort_by_label](#sort_by_label_desc).
|
||||
This function is supported by PromQL. See also [sort](#sort) and [sort_by_label](#sort_by_label_desc).
|
||||
|
||||
#### sqrt
|
||||
|
||||
@@ -1668,9 +1493,7 @@ See also [start](#start) and [end](#end).
|
||||
|
||||
`time()` is a [transform function](#transform-functions), which returns unix timestamp for every returned point.
|
||||
|
||||
This function is supported by PromQL.
|
||||
|
||||
See also [timestamp](#timestamp), [now](#now), [start](#start) and [end](#end).
|
||||
This function is supported by PromQL. See also [now](#now), [start](#start) and [end](#end).
|
||||
|
||||
#### timezone_offset
|
||||
|
||||
@@ -1719,7 +1542,7 @@ Additional details:
|
||||
|
||||
* If label manipulation function is applied directly to a [series_selector](https://docs.victoriametrics.com/keyConcepts.html#filtering),
|
||||
then the [default_rollup()](#default_rollup) function is automatically applied before performing the label transformation.
|
||||
For example, `alias(temperature, "foo")` is implicitly transformed to `alias(default_rollup(temperature), "foo")`.
|
||||
For example, `alias(temperature, "foo")` is implicitly transformed to `alias(default_rollup(temperature[1i]), "foo")`.
|
||||
|
||||
See also [implicit query conversions](#implicit-query-conversions).
|
||||
|
||||
@@ -1896,7 +1719,7 @@ Additional details:
|
||||
Multiple labels can be put in `by` and `without` modifiers.
|
||||
* If the aggregate function is applied directly to a [series_selector](https://docs.victoriametrics.com/keyConcepts.html#filtering),
|
||||
then the [default_rollup()](#default_rollup) function is automatically applied before calculating the aggregate.
|
||||
For example, `count(up)` is implicitly transformed to `count(default_rollup(up))`.
|
||||
For example, `count(up)` is implicitly transformed to `count(default_rollup(up[1i]))`.
|
||||
* Aggregate functions accept arbitrary number of args. For example, `avg(q1, q2, q3)` would return the average values for every point
|
||||
across time series returned by `q1`, `q2` and `q3`.
|
||||
* Aggregate functions support optional `limit N` suffix, which can be used for limiting the number of output groups.
|
||||
@@ -1924,9 +1747,7 @@ This function is supported by PromQL.
|
||||
`bottomk(k, q)` is [aggregate function](#aggregate-functions), which returns up to `k` points with the smallest values across all the time series returned by `q`.
|
||||
The aggregate is calculated individually per each group of points with the same timestamp.
|
||||
|
||||
This function is supported by PromQL.
|
||||
|
||||
See also [topk](#topk), [bottomk_min](#bottomk_min) and [#bottomk_last](#bottomk_last).
|
||||
This function is supported by PromQL. See also [topk](#topk).
|
||||
|
||||
#### bottomk_avg
|
||||
|
||||
@@ -1988,14 +1809,10 @@ The aggregate is calculated individually per each group of points with the same
|
||||
|
||||
This function is supported by PromQL.
|
||||
|
||||
See also [count_values_over_time](#count_values_over_time) and [label_match](#label_match).
|
||||
|
||||
#### distinct
|
||||
|
||||
`distinct(q)` is [aggregate function](#aggregate-functions), which calculates the number of unique values per each group of points with the same timestamp.
|
||||
|
||||
See also [distinct_over_time](#distinct_over_time).
|
||||
|
||||
#### geomean
|
||||
|
||||
`geomean(q)` is [aggregate function](#aggregate-functions), which calculates geometric mean per each group of points with the same timestamp.
|
||||
@@ -2087,9 +1904,7 @@ See also [outliers_iqr](#outliers_iqr) and [outliers_mad](#outliers_mad).
|
||||
for all the time series returned by `q`. `phi` must be in the range `[0...1]`.
|
||||
The aggregate is calculated individually per each group of points with the same timestamp.
|
||||
|
||||
This function is supported by PromQL.
|
||||
|
||||
See also [quantiles](#quantiles) and [histogram_quantile](#histogram_quantile).
|
||||
This function is supported by PromQL. See also [quantiles](#quantiles) and [histogram_quantile](#histogram_quantile).
|
||||
|
||||
#### quantiles
|
||||
|
||||
@@ -2148,9 +1963,7 @@ for all the time series returned by `q`. The aggregate is calculated individuall
|
||||
`topk(k, q)` is [aggregate function](#aggregate-functions), which returns up to `k` points with the biggest values across all the time series returned by `q`.
|
||||
The aggregate is calculated individually per each group of points with the same timestamp.
|
||||
|
||||
This function is supported by PromQL.
|
||||
|
||||
See also [bottomk](#bottomk), [topk_max](#topk_max) and [topk_last](#topk_last).
|
||||
This function is supported by PromQL. See also [bottomk](#bottomk).
|
||||
|
||||
#### topk_avg
|
||||
|
||||
@@ -2210,7 +2023,7 @@ See also [zscore_over_time](#zscore_over_time), [range_trim_zscore](#range_trim_
|
||||
MetricsQL supports and extends PromQL subqueries. See [this article](https://valyala.medium.com/prometheus-subqueries-in-victoriametrics-9b1492b720b3) for details.
|
||||
Any [rollup function](#rollup-functions) for something other than [series selector](https://docs.victoriametrics.com/keyConcepts.html#filtering) form a subquery.
|
||||
Nested rollup functions can be implicit thanks to the [implicit query conversions](#implicit-query-conversions).
|
||||
For example, `delta(sum(m))` is implicitly converted to `delta(sum(default_rollup(m))[1i:1i])`, so it becomes a subquery,
|
||||
For example, `delta(sum(m))` is implicitly converted to `delta(sum(default_rollup(m[1i]))[1i:1i])`, so it becomes a subquery,
|
||||
since it contains [default_rollup](#default_rollup) nested into [delta](#delta).
|
||||
|
||||
VictoriaMetrics performs subqueries in the following way:
|
||||
@@ -2225,23 +2038,21 @@ VictoriaMetrics performs subqueries in the following way:
|
||||
|
||||
VictoriaMetrics performs the following implicit conversions for incoming queries before starting the calculations:
|
||||
|
||||
* If lookbehind window in square brackets is missing inside [rollup function](#rollup-functions), then it is automatically set to the following value:
|
||||
- To `step` value passed to [/api/v1/query_range](https://docs.victoriametrics.com/keyConcepts.html#range-query) or [/api/v1/query](https://docs.victoriametrics.com/keyconcepts/#instant-query)
|
||||
for all the [rollup functions](#rollup-functions) except of [default_rollup](#default_rollup) and [rate](#rate). This value is known as `$__interval` in Grafana or `1i` in MetricsQL.
|
||||
For example, `avg_over_time(temperature)` is automatically transformed to `avg_over_time(temperature[1i])`.
|
||||
- To the `max(step, scrape_interval)`, where `scrape_interval` is the interval between [raw samples](https://docs.victoriametrics.com/keyconcepts/#raw-samples)
|
||||
for [default_rollup](#default_rollup) and [rate](#rate) functions. This allows avoiding unexpected gaps on the graph when `step` is smaller than `scrape_interval`.
|
||||
* If lookbehind window in square brackets is missing inside [rollup function](#rollup-functions),
|
||||
then `[1i]` is automatically added there. The `[1i]` means one `step` value, which is passed
|
||||
to [/api/v1/query_range](https://docs.victoriametrics.com/keyConcepts.html#range-query).
|
||||
It is also known as `$__interval` in Grafana. For example, `rate(http_requests_count)` is automatically transformed to `rate(http_requests_count[1i])`.
|
||||
* All the [series selectors](https://docs.victoriametrics.com/keyConcepts.html#filtering),
|
||||
which aren't wrapped into [rollup functions](#rollup-functions), are automatically wrapped into [default_rollup](#default_rollup) function.
|
||||
Examples:
|
||||
* `foo` is transformed to `default_rollup(foo)`
|
||||
* `foo + bar` is transformed to `default_rollup(foo) + default_rollup(bar)`
|
||||
* `count(up)` is transformed to `count(default_rollup(up))`, because [count](#count) isn't a [rollup function](#rollup-functions) -
|
||||
* `foo` is transformed to `default_rollup(foo[1i])`
|
||||
* `foo + bar` is transformed to `default_rollup(foo[1i]) + default_rollup(bar[1i])`
|
||||
* `count(up)` is transformed to `count(default_rollup(up[1i]))`, because [count](#count) isn't a [rollup function](#rollup-functions) -
|
||||
it is [aggregate function](#aggregate-functions)
|
||||
* `abs(temperature)` is transformed to `abs(default_rollup(temperature))`, because [abs](#abs) isn't a [rollup function](#rollup-functions) -
|
||||
* `abs(temperature)` is transformed to `abs(default_rollup(temperature[1i]))`, because [abs](#abs) isn't a [rollup function](#rollup-functions) -
|
||||
it is [transform function](#transform-functions)
|
||||
* If `step` in square brackets is missing inside [subquery](#subqueries), then `1i` step is automatically added there.
|
||||
For example, `avg_over_time(rate(http_requests_total[5m])[1h])` is automatically converted to `avg_over_time(rate(http_requests_total[5m])[1h:1i])`.
|
||||
* If something other than [series selector](https://docs.victoriametrics.com/keyConcepts.html#filtering)
|
||||
is passed to [rollup function](#rollup-functions), then a [subquery](#subqueries) with `1i` lookbehind window and `1i` step is automatically formed.
|
||||
For example, `rate(sum(up))` is automatically converted to `rate((sum(default_rollup(up)))[1i:1i])`.
|
||||
For example, `rate(sum(up))` is automatically converted to `rate((sum(default_rollup(up[1i])))[1i:1i])`.
|
||||
File diff suppressed because it is too large
Load Diff
@@ -65,9 +65,7 @@ func insertRows(at *auth.Token, rows []parser.Row, extraLabels []prompbmarshal.L
|
||||
ctx.WriteRequest.Timeseries = tssDst
|
||||
ctx.Labels = labels
|
||||
ctx.Samples = samples
|
||||
if !remotewrite.TryPush(at, &ctx.WriteRequest) {
|
||||
return remotewrite.ErrQueueFullHTTPRetry
|
||||
}
|
||||
remotewrite.Push(at, &ctx.WriteRequest)
|
||||
rowsInserted.Add(len(rows))
|
||||
if at != nil {
|
||||
rowsTenantInserted.Get(at).Add(len(rows))
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
package datadogv1
|
||||
package datadog
|
||||
|
||||
import (
|
||||
"net/http"
|
||||
@@ -8,32 +8,33 @@ import (
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/auth"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
|
||||
parserCommon "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/common"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/datadogutils"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/datadogv1"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/datadogv1/stream"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/datadog"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/datadog/stream"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/tenantmetrics"
|
||||
"github.com/VictoriaMetrics/metrics"
|
||||
)
|
||||
|
||||
var (
|
||||
rowsInserted = metrics.NewCounter(`vmagent_rows_inserted_total{type="datadogv1"}`)
|
||||
rowsTenantInserted = tenantmetrics.NewCounterMap(`vmagent_tenant_inserted_rows_total{type="datadogv1"}`)
|
||||
rowsPerInsert = metrics.NewHistogram(`vmagent_rows_per_insert{type="datadogv1"}`)
|
||||
rowsInserted = metrics.NewCounter(`vmagent_rows_inserted_total{type="datadog"}`)
|
||||
rowsTenantInserted = tenantmetrics.NewCounterMap(`vmagent_tenant_inserted_rows_total{type="datadog"}`)
|
||||
rowsPerInsert = metrics.NewHistogram(`vmagent_rows_per_insert{type="datadog"}`)
|
||||
)
|
||||
|
||||
// InsertHandlerForHTTP processes remote write for DataDog POST /api/v1/series request.
|
||||
//
|
||||
// See https://docs.datadoghq.com/api/latest/metrics/#submit-metrics
|
||||
func InsertHandlerForHTTP(at *auth.Token, req *http.Request) error {
|
||||
extraLabels, err := parserCommon.GetExtraLabels(req)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
ce := req.Header.Get("Content-Encoding")
|
||||
return stream.Parse(req.Body, ce, func(series []datadogv1.Series) error {
|
||||
return stream.Parse(req.Body, ce, func(series []datadog.Series) error {
|
||||
return insertRows(at, series, extraLabels)
|
||||
})
|
||||
}
|
||||
|
||||
func insertRows(at *auth.Token, series []datadogv1.Series, extraLabels []prompbmarshal.Label) error {
|
||||
func insertRows(at *auth.Token, series []datadog.Series, extraLabels []prompbmarshal.Label) error {
|
||||
ctx := common.GetPushCtx()
|
||||
defer common.PutPushCtx(ctx)
|
||||
|
||||
@@ -62,7 +63,7 @@ func insertRows(at *auth.Token, series []datadogv1.Series, extraLabels []prompbm
|
||||
})
|
||||
}
|
||||
for _, tag := range ss.Tags {
|
||||
name, value := datadogutils.SplitTag(tag)
|
||||
name, value := datadog.SplitTag(tag)
|
||||
if name == "host" {
|
||||
name = "exported_host"
|
||||
}
|
||||
@@ -87,9 +88,7 @@ func insertRows(at *auth.Token, series []datadogv1.Series, extraLabels []prompbm
|
||||
ctx.WriteRequest.Timeseries = tssDst
|
||||
ctx.Labels = labels
|
||||
ctx.Samples = samples
|
||||
if !remotewrite.TryPush(at, &ctx.WriteRequest) {
|
||||
return remotewrite.ErrQueueFullHTTPRetry
|
||||
}
|
||||
remotewrite.Push(at, &ctx.WriteRequest)
|
||||
rowsInserted.Add(rowsTotal)
|
||||
if at != nil {
|
||||
rowsTenantInserted.Get(at).Add(rowsTotal)
|
||||
@@ -1,95 +0,0 @@
|
||||
package datadogsketches
|
||||
|
||||
import (
|
||||
"net/http"
|
||||
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/common"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/remotewrite"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/auth"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
|
||||
parserCommon "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/common"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/datadogsketches"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/datadogsketches/stream"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/datadogutils"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/tenantmetrics"
|
||||
"github.com/VictoriaMetrics/metrics"
|
||||
)
|
||||
|
||||
var (
|
||||
rowsInserted = metrics.NewCounter(`vmagent_rows_inserted_total{type="datadogsketches"}`)
|
||||
rowsTenantInserted = tenantmetrics.NewCounterMap(`vmagent_tenant_inserted_rows_total{type="datadogsketches"}`)
|
||||
rowsPerInsert = metrics.NewHistogram(`vmagent_rows_per_insert{type="datadogsketches"}`)
|
||||
)
|
||||
|
||||
// InsertHandlerForHTTP processes remote write for DataDog POST /api/beta/sketches request.
|
||||
func InsertHandlerForHTTP(at *auth.Token, req *http.Request) error {
|
||||
extraLabels, err := parserCommon.GetExtraLabels(req)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
ce := req.Header.Get("Content-Encoding")
|
||||
return stream.Parse(req.Body, ce, func(sketches []*datadogsketches.Sketch) error {
|
||||
return insertRows(at, sketches, extraLabels)
|
||||
})
|
||||
}
|
||||
|
||||
func insertRows(at *auth.Token, sketches []*datadogsketches.Sketch, extraLabels []prompbmarshal.Label) error {
|
||||
ctx := common.GetPushCtx()
|
||||
defer common.PutPushCtx(ctx)
|
||||
|
||||
rowsTotal := 0
|
||||
tssDst := ctx.WriteRequest.Timeseries[:0]
|
||||
labels := ctx.Labels[:0]
|
||||
samples := ctx.Samples[:0]
|
||||
for _, sketch := range sketches {
|
||||
ms := sketch.ToSummary()
|
||||
for _, m := range ms {
|
||||
labelsLen := len(labels)
|
||||
labels = append(labels, prompbmarshal.Label{
|
||||
Name: "__name__",
|
||||
Value: m.Name,
|
||||
})
|
||||
for _, label := range m.Labels {
|
||||
labels = append(labels, prompbmarshal.Label{
|
||||
Name: label.Name,
|
||||
Value: label.Value,
|
||||
})
|
||||
}
|
||||
for _, tag := range sketch.Tags {
|
||||
name, value := datadogutils.SplitTag(tag)
|
||||
if name == "host" {
|
||||
name = "exported_host"
|
||||
}
|
||||
labels = append(labels, prompbmarshal.Label{
|
||||
Name: name,
|
||||
Value: value,
|
||||
})
|
||||
}
|
||||
labels = append(labels, extraLabels...)
|
||||
samplesLen := len(samples)
|
||||
for _, p := range m.Points {
|
||||
samples = append(samples, prompbmarshal.Sample{
|
||||
Timestamp: p.Timestamp,
|
||||
Value: p.Value,
|
||||
})
|
||||
}
|
||||
rowsTotal += len(m.Points)
|
||||
tssDst = append(tssDst, prompbmarshal.TimeSeries{
|
||||
Labels: labels[labelsLen:],
|
||||
Samples: samples[samplesLen:],
|
||||
})
|
||||
}
|
||||
}
|
||||
ctx.WriteRequest.Timeseries = tssDst
|
||||
ctx.Labels = labels
|
||||
ctx.Samples = samples
|
||||
if !remotewrite.TryPush(at, &ctx.WriteRequest) {
|
||||
return remotewrite.ErrQueueFullHTTPRetry
|
||||
}
|
||||
rowsInserted.Add(rowsTotal)
|
||||
if at != nil {
|
||||
rowsTenantInserted.Get(at).Add(rowsTotal)
|
||||
}
|
||||
rowsPerInsert.Update(float64(rowsTotal))
|
||||
return nil
|
||||
}
|
||||
@@ -1,102 +0,0 @@
|
||||
package datadogv2
|
||||
|
||||
import (
|
||||
"net/http"
|
||||
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/common"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/remotewrite"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/auth"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
|
||||
parserCommon "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/common"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/datadogutils"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/datadogv2"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/datadogv2/stream"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/tenantmetrics"
|
||||
"github.com/VictoriaMetrics/metrics"
|
||||
)
|
||||
|
||||
var (
|
||||
rowsInserted = metrics.NewCounter(`vmagent_rows_inserted_total{type="datadogv2"}`)
|
||||
rowsTenantInserted = tenantmetrics.NewCounterMap(`vmagent_tenant_inserted_rows_total{type="datadogv2"}`)
|
||||
rowsPerInsert = metrics.NewHistogram(`vmagent_rows_per_insert{type="datadogv2"}`)
|
||||
)
|
||||
|
||||
// InsertHandlerForHTTP processes remote write for DataDog POST /api/v2/series request.
|
||||
//
|
||||
// See https://docs.datadoghq.com/api/latest/metrics/#submit-metrics
|
||||
func InsertHandlerForHTTP(at *auth.Token, req *http.Request) error {
|
||||
extraLabels, err := parserCommon.GetExtraLabels(req)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
ct := req.Header.Get("Content-Type")
|
||||
ce := req.Header.Get("Content-Encoding")
|
||||
return stream.Parse(req.Body, ce, ct, func(series []datadogv2.Series) error {
|
||||
return insertRows(at, series, extraLabels)
|
||||
})
|
||||
}
|
||||
|
||||
func insertRows(at *auth.Token, series []datadogv2.Series, extraLabels []prompbmarshal.Label) error {
|
||||
ctx := common.GetPushCtx()
|
||||
defer common.PutPushCtx(ctx)
|
||||
|
||||
rowsTotal := 0
|
||||
tssDst := ctx.WriteRequest.Timeseries[:0]
|
||||
labels := ctx.Labels[:0]
|
||||
samples := ctx.Samples[:0]
|
||||
for i := range series {
|
||||
ss := &series[i]
|
||||
rowsTotal += len(ss.Points)
|
||||
labelsLen := len(labels)
|
||||
labels = append(labels, prompbmarshal.Label{
|
||||
Name: "__name__",
|
||||
Value: ss.Metric,
|
||||
})
|
||||
for _, rs := range ss.Resources {
|
||||
labels = append(labels, prompbmarshal.Label{
|
||||
Name: rs.Type,
|
||||
Value: rs.Name,
|
||||
})
|
||||
}
|
||||
if ss.SourceTypeName != "" {
|
||||
labels = append(labels, prompbmarshal.Label{
|
||||
Name: "source_type_name",
|
||||
Value: ss.SourceTypeName,
|
||||
})
|
||||
}
|
||||
for _, tag := range ss.Tags {
|
||||
name, value := datadogutils.SplitTag(tag)
|
||||
if name == "host" {
|
||||
name = "exported_host"
|
||||
}
|
||||
labels = append(labels, prompbmarshal.Label{
|
||||
Name: name,
|
||||
Value: value,
|
||||
})
|
||||
}
|
||||
labels = append(labels, extraLabels...)
|
||||
samplesLen := len(samples)
|
||||
for _, pt := range ss.Points {
|
||||
samples = append(samples, prompbmarshal.Sample{
|
||||
Timestamp: pt.Timestamp * 1000,
|
||||
Value: pt.Value,
|
||||
})
|
||||
}
|
||||
tssDst = append(tssDst, prompbmarshal.TimeSeries{
|
||||
Labels: labels[labelsLen:],
|
||||
Samples: samples[samplesLen:],
|
||||
})
|
||||
}
|
||||
ctx.WriteRequest.Timeseries = tssDst
|
||||
ctx.Labels = labels
|
||||
ctx.Samples = samples
|
||||
if !remotewrite.TryPush(at, &ctx.WriteRequest) {
|
||||
return remotewrite.ErrQueueFullHTTPRetry
|
||||
}
|
||||
rowsInserted.Add(rowsTotal)
|
||||
if at != nil {
|
||||
rowsTenantInserted.Get(at).Add(rowsTotal)
|
||||
}
|
||||
rowsPerInsert.Update(float64(rowsTotal))
|
||||
return nil
|
||||
}
|
||||
@@ -5,7 +5,6 @@ import (
|
||||
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/common"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/remotewrite"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/auth"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
|
||||
parser "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/graphite"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/graphite/stream"
|
||||
@@ -21,12 +20,10 @@ var (
|
||||
//
|
||||
// See https://graphite.readthedocs.io/en/latest/feeding-carbon.html#the-plaintext-protocol
|
||||
func InsertHandler(r io.Reader) error {
|
||||
return stream.Parse(r, false, func(rows []parser.Row) error {
|
||||
return insertRows(nil, rows)
|
||||
})
|
||||
return stream.Parse(r, insertRows)
|
||||
}
|
||||
|
||||
func insertRows(at *auth.Token, rows []parser.Row) error {
|
||||
func insertRows(rows []parser.Row) error {
|
||||
ctx := common.GetPushCtx()
|
||||
defer common.PutPushCtx(ctx)
|
||||
|
||||
@@ -59,9 +56,7 @@ func insertRows(at *auth.Token, rows []parser.Row) error {
|
||||
ctx.WriteRequest.Timeseries = tssDst
|
||||
ctx.Labels = labels
|
||||
ctx.Samples = samples
|
||||
if !remotewrite.TryPush(at, &ctx.WriteRequest) {
|
||||
return remotewrite.ErrQueueFullHTTPRetry
|
||||
}
|
||||
remotewrite.Push(nil, &ctx.WriteRequest)
|
||||
rowsInserted.Add(len(rows))
|
||||
rowsPerInsert.Update(float64(len(rows)))
|
||||
return nil
|
||||
|
||||
@@ -36,9 +36,9 @@ var (
|
||||
// InsertHandlerForReader processes remote write for influx line protocol.
|
||||
//
|
||||
// See https://github.com/influxdata/telegraf/tree/master/plugins/inputs/socket_listener/
|
||||
func InsertHandlerForReader(at *auth.Token, r io.Reader, isGzipped bool) error {
|
||||
func InsertHandlerForReader(r io.Reader, isGzipped bool) error {
|
||||
return stream.Parse(r, isGzipped, "", "", func(db string, rows []parser.Row) error {
|
||||
return insertRows(at, db, rows, nil)
|
||||
return insertRows(nil, db, rows, nil)
|
||||
})
|
||||
}
|
||||
|
||||
@@ -130,9 +130,7 @@ func insertRows(at *auth.Token, db string, rows []parser.Row, extraLabels []prom
|
||||
ctx.ctx.Labels = labels
|
||||
ctx.ctx.Samples = samples
|
||||
ctx.commonLabels = commonLabels
|
||||
if !remotewrite.TryPush(at, &ctx.ctx.WriteRequest) {
|
||||
return remotewrite.ErrQueueFullHTTPRetry
|
||||
}
|
||||
remotewrite.Push(at, &ctx.ctx.WriteRequest)
|
||||
rowsInserted.Add(rowsTotal)
|
||||
if at != nil {
|
||||
rowsTenantInserted.Get(at).Add(rowsTotal)
|
||||
|
||||
@@ -8,12 +8,13 @@ import (
|
||||
"net/http"
|
||||
"os"
|
||||
"strings"
|
||||
"sync/atomic"
|
||||
"time"
|
||||
|
||||
"github.com/VictoriaMetrics/metrics"
|
||||
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/csvimport"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/datadogsketches"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/datadogv1"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/datadogv2"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/datadog"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/graphite"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/influx"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/native"
|
||||
@@ -40,16 +41,14 @@ import (
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/procutil"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promscrape"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/common"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/opentelemetry/firehose"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/pushmetrics"
|
||||
"github.com/VictoriaMetrics/metrics"
|
||||
)
|
||||
|
||||
var (
|
||||
httpListenAddrs = flagutil.NewArrayString("httpListenAddr", "TCP address to listen for incoming http requests. "+
|
||||
httpListenAddr = flag.String("httpListenAddr", ":8429", "TCP address to listen for http connections. "+
|
||||
"Set this flag to empty value in order to disable listening on any port. This mode may be useful for running multiple vmagent instances on the same server. "+
|
||||
"Note that /targets and /metrics pages aren't available if -httpListenAddr=''. See also -tls and -httpListenAddr.useProxyProtocol")
|
||||
useProxyProtocol = flagutil.NewArrayBool("httpListenAddr.useProxyProtocol", "Whether to use proxy protocol for connections accepted at the corresponding -httpListenAddr . "+
|
||||
"Note that /targets and /metrics pages aren't available if -httpListenAddr=''. See also -httpListenAddr.useProxyProtocol")
|
||||
useProxyProtocol = flag.Bool("httpListenAddr.useProxyProtocol", false, "Whether to use proxy protocol for connections accepted at -httpListenAddr . "+
|
||||
"See https://www.haproxy.org/download/1.8/doc/proxy-protocol.txt . "+
|
||||
"With enabled proxy protocol http server cannot serve regular /metrics endpoint. Use -pushmetrics.url for metrics pushing")
|
||||
influxListenAddr = flag.String("influxListenAddr", "", "TCP and UDP address to listen for InfluxDB line protocol data. Usually :8089 must be set. Doesn't work if empty. "+
|
||||
@@ -70,8 +69,7 @@ var (
|
||||
"See also -opentsdbHTTPListenAddr.useProxyProtocol")
|
||||
opentsdbHTTPUseProxyProtocol = flag.Bool("opentsdbHTTPListenAddr.useProxyProtocol", false, "Whether to use proxy protocol for connections accepted "+
|
||||
"at -opentsdbHTTPListenAddr . See https://www.haproxy.org/download/1.8/doc/proxy-protocol.txt")
|
||||
configAuthKey = flagutil.NewPassword("configAuthKey", "Authorization key for accessing /config page. It must be passed via authKey query arg")
|
||||
reloadAuthKey = flagutil.NewPassword("reloadAuthKey", "Auth key for /-/reload http endpoint. It must be passed as authKey=...")
|
||||
configAuthKey = flag.String("configAuthKey", "", "Authorization key for accessing /config page. It must be passed via authKey query arg")
|
||||
dryRun = flag.Bool("dryRun", false, "Whether to check config files without running vmagent. The following files are checked: "+
|
||||
"-promscrape.config, -remoteWrite.relabelConfig, -remoteWrite.urlRelabelConfig, -remoteWrite.streamAggr.config . "+
|
||||
"Unknown config entries aren't allowed in -promscrape.config by default. This can be changed by passing -promscrape.config.strictParse=false command-line flag")
|
||||
@@ -98,6 +96,7 @@ func main() {
|
||||
remotewrite.InitSecretFlags()
|
||||
buildinfo.Init()
|
||||
logger.Init()
|
||||
pushmetrics.Init()
|
||||
|
||||
if promscrape.IsDryRun() {
|
||||
if err := promscrape.CheckConfig(); err != nil {
|
||||
@@ -120,18 +119,13 @@ func main() {
|
||||
return
|
||||
}
|
||||
|
||||
listenAddrs := *httpListenAddrs
|
||||
if len(listenAddrs) == 0 {
|
||||
listenAddrs = []string{":8429"}
|
||||
}
|
||||
logger.Infof("starting vmagent at %q...", listenAddrs)
|
||||
logger.Infof("starting vmagent at %q...", *httpListenAddr)
|
||||
startTime := time.Now()
|
||||
remotewrite.StartIngestionRateLimiter()
|
||||
remotewrite.Init()
|
||||
common.StartUnmarshalWorkers()
|
||||
if len(*influxListenAddr) > 0 {
|
||||
influxServer = influxserver.MustStart(*influxListenAddr, *influxUseProxyProtocol, func(r io.Reader) error {
|
||||
return influx.InsertHandlerForReader(nil, r, false)
|
||||
return influx.InsertHandlerForReader(r, false)
|
||||
})
|
||||
}
|
||||
if len(*graphiteListenAddr) > 0 {
|
||||
@@ -146,23 +140,24 @@ func main() {
|
||||
opentsdbhttpServer = opentsdbhttpserver.MustStart(*opentsdbHTTPListenAddr, *opentsdbHTTPUseProxyProtocol, httpInsertHandler)
|
||||
}
|
||||
|
||||
promscrape.Init(remotewrite.PushDropSamplesOnFailure)
|
||||
promscrape.Init(remotewrite.Push)
|
||||
|
||||
go httpserver.Serve(listenAddrs, useProxyProtocol, requestHandler)
|
||||
if len(*httpListenAddr) > 0 {
|
||||
go httpserver.Serve(*httpListenAddr, *useProxyProtocol, requestHandler)
|
||||
}
|
||||
logger.Infof("started vmagent in %.3f seconds", time.Since(startTime).Seconds())
|
||||
|
||||
pushmetrics.Init()
|
||||
sig := procutil.WaitForSigterm()
|
||||
logger.Infof("received signal %s", sig)
|
||||
remotewrite.StopIngestionRateLimiter()
|
||||
pushmetrics.Stop()
|
||||
|
||||
startTime = time.Now()
|
||||
logger.Infof("gracefully shutting down webservice at %q", listenAddrs)
|
||||
if err := httpserver.Stop(listenAddrs); err != nil {
|
||||
logger.Fatalf("cannot stop the webservice: %s", err)
|
||||
if len(*httpListenAddr) > 0 {
|
||||
logger.Infof("gracefully shutting down webservice at %q", *httpListenAddr)
|
||||
if err := httpserver.Stop(*httpListenAddr); err != nil {
|
||||
logger.Fatalf("cannot stop the webservice: %s", err)
|
||||
}
|
||||
logger.Infof("successfully shut down the webservice in %.3f seconds", time.Since(startTime).Seconds())
|
||||
}
|
||||
logger.Infof("successfully shut down the webservice in %.3f seconds", time.Since(startTime).Seconds())
|
||||
|
||||
promscrape.Stop()
|
||||
|
||||
@@ -264,7 +259,7 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
|
||||
path = strings.TrimSuffix(path, "/")
|
||||
}
|
||||
switch path {
|
||||
case "/prometheus/api/v1/write", "/api/v1/write", "/api/v1/push", "/prometheus/api/v1/push":
|
||||
case "/prometheus/api/v1/write", "/api/v1/write":
|
||||
if common.HandleVMProtoServerHandshake(w, r) {
|
||||
return true
|
||||
}
|
||||
@@ -316,14 +311,14 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
|
||||
influxQueryRequests.Inc()
|
||||
influxutils.WriteDatabaseNames(w)
|
||||
return true
|
||||
case "/opentelemetry/api/v1/push", "/opentelemetry/v1/metrics":
|
||||
case "/opentelemetry/api/v1/push":
|
||||
opentelemetryPushRequests.Inc()
|
||||
if err := opentelemetry.InsertHandler(nil, r); err != nil {
|
||||
opentelemetryPushErrors.Inc()
|
||||
httpserver.Errorf(w, r, "%s", err)
|
||||
return true
|
||||
}
|
||||
firehose.WriteSuccessResponse(w, r)
|
||||
w.WriteHeader(http.StatusOK)
|
||||
return true
|
||||
case "/newrelic":
|
||||
newrelicCheckRequest.Inc()
|
||||
@@ -349,20 +344,9 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
|
||||
fmt.Fprintf(w, `{"status":"ok"}`)
|
||||
return true
|
||||
case "/datadog/api/v1/series":
|
||||
datadogv1WriteRequests.Inc()
|
||||
if err := datadogv1.InsertHandlerForHTTP(nil, r); err != nil {
|
||||
datadogv1WriteErrors.Inc()
|
||||
httpserver.Errorf(w, r, "%s", err)
|
||||
return true
|
||||
}
|
||||
w.Header().Set("Content-Type", "application/json")
|
||||
w.WriteHeader(202)
|
||||
fmt.Fprintf(w, `{"status":"ok"}`)
|
||||
return true
|
||||
case "/datadog/api/v2/series":
|
||||
datadogv2WriteRequests.Inc()
|
||||
if err := datadogv2.InsertHandlerForHTTP(nil, r); err != nil {
|
||||
datadogv2WriteErrors.Inc()
|
||||
datadogWriteRequests.Inc()
|
||||
if err := datadog.InsertHandlerForHTTP(nil, r); err != nil {
|
||||
datadogWriteErrors.Inc()
|
||||
httpserver.Errorf(w, r, "%s", err)
|
||||
return true
|
||||
}
|
||||
@@ -371,15 +355,6 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
|
||||
w.WriteHeader(202)
|
||||
fmt.Fprintf(w, `{"status":"ok"}`)
|
||||
return true
|
||||
case "/datadog/api/beta/sketches":
|
||||
datadogsketchesWriteRequests.Inc()
|
||||
if err := datadogsketches.InsertHandlerForHTTP(nil, r); err != nil {
|
||||
datadogsketchesWriteErrors.Inc()
|
||||
httpserver.Errorf(w, r, "%s", err)
|
||||
return true
|
||||
}
|
||||
w.WriteHeader(202)
|
||||
return true
|
||||
case "/datadog/api/v1/validate":
|
||||
datadogValidateRequests.Inc()
|
||||
// See https://docs.datadoghq.com/api/latest/authentication/#validate-api-key
|
||||
@@ -434,7 +409,7 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
|
||||
}
|
||||
return true
|
||||
case "/prometheus/config", "/config":
|
||||
if !httpserver.CheckAuthFlag(w, r, configAuthKey.Get(), "configAuthKey") {
|
||||
if !httpserver.CheckAuthFlag(w, r, *configAuthKey, "configAuthKey") {
|
||||
return true
|
||||
}
|
||||
promscrapeConfigRequests.Inc()
|
||||
@@ -443,7 +418,7 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
|
||||
return true
|
||||
case "/prometheus/api/v1/status/config", "/api/v1/status/config":
|
||||
// See https://prometheus.io/docs/prometheus/latest/querying/api/#config
|
||||
if !httpserver.CheckAuthFlag(w, r, configAuthKey.Get(), "configAuthKey") {
|
||||
if !httpserver.CheckAuthFlag(w, r, *configAuthKey, "configAuthKey") {
|
||||
return true
|
||||
}
|
||||
promscrapeStatusConfigRequests.Inc()
|
||||
@@ -453,15 +428,12 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
|
||||
fmt.Fprintf(w, `{"status":"success","data":{"yaml":%q}}`, bb.B)
|
||||
return true
|
||||
case "/prometheus/-/reload", "/-/reload":
|
||||
if !httpserver.CheckAuthFlag(w, r, reloadAuthKey.Get(), "reloadAuthKey") {
|
||||
return true
|
||||
}
|
||||
promscrapeConfigReloadRequests.Inc()
|
||||
procutil.SelfSIGHUP()
|
||||
w.WriteHeader(http.StatusOK)
|
||||
return true
|
||||
case "/ready":
|
||||
if rdy := promscrape.PendingScrapeConfigs.Load(); rdy > 0 {
|
||||
if rdy := atomic.LoadInt32(&promscrape.PendingScrapeConfigs); rdy > 0 {
|
||||
errMsg := fmt.Sprintf("waiting for scrapes to init, left: %d", rdy)
|
||||
http.Error(w, errMsg, http.StatusTooEarly)
|
||||
} else {
|
||||
@@ -513,7 +485,7 @@ func processMultitenantRequest(w http.ResponseWriter, r *http.Request, path stri
|
||||
p.Suffix = strings.TrimSuffix(p.Suffix, "/")
|
||||
}
|
||||
switch p.Suffix {
|
||||
case "prometheus/", "prometheus", "prometheus/api/v1/write", "prometheus/api/v1/push":
|
||||
case "prometheus/", "prometheus", "prometheus/api/v1/write":
|
||||
prometheusWriteRequests.Inc()
|
||||
if err := promremotewrite.InsertHandler(at, r); err != nil {
|
||||
prometheusWriteErrors.Inc()
|
||||
@@ -562,14 +534,14 @@ func processMultitenantRequest(w http.ResponseWriter, r *http.Request, path stri
|
||||
influxQueryRequests.Inc()
|
||||
influxutils.WriteDatabaseNames(w)
|
||||
return true
|
||||
case "opentelemetry/api/v1/push", "opentelemetry/v1/metrics":
|
||||
case "opentelemetry/api/v1/push":
|
||||
opentelemetryPushRequests.Inc()
|
||||
if err := opentelemetry.InsertHandler(at, r); err != nil {
|
||||
opentelemetryPushErrors.Inc()
|
||||
httpserver.Errorf(w, r, "%s", err)
|
||||
return true
|
||||
}
|
||||
firehose.WriteSuccessResponse(w, r)
|
||||
w.WriteHeader(http.StatusOK)
|
||||
return true
|
||||
case "newrelic":
|
||||
newrelicCheckRequest.Inc()
|
||||
@@ -595,19 +567,9 @@ func processMultitenantRequest(w http.ResponseWriter, r *http.Request, path stri
|
||||
fmt.Fprintf(w, `{"status":"ok"}`)
|
||||
return true
|
||||
case "datadog/api/v1/series":
|
||||
datadogv1WriteRequests.Inc()
|
||||
if err := datadogv1.InsertHandlerForHTTP(at, r); err != nil {
|
||||
datadogv1WriteErrors.Inc()
|
||||
httpserver.Errorf(w, r, "%s", err)
|
||||
return true
|
||||
}
|
||||
w.WriteHeader(202)
|
||||
fmt.Fprintf(w, `{"status":"ok"}`)
|
||||
return true
|
||||
case "datadog/api/v2/series":
|
||||
datadogv2WriteRequests.Inc()
|
||||
if err := datadogv2.InsertHandlerForHTTP(at, r); err != nil {
|
||||
datadogv2WriteErrors.Inc()
|
||||
datadogWriteRequests.Inc()
|
||||
if err := datadog.InsertHandlerForHTTP(at, r); err != nil {
|
||||
datadogWriteErrors.Inc()
|
||||
httpserver.Errorf(w, r, "%s", err)
|
||||
return true
|
||||
}
|
||||
@@ -615,15 +577,6 @@ func processMultitenantRequest(w http.ResponseWriter, r *http.Request, path stri
|
||||
w.WriteHeader(202)
|
||||
fmt.Fprintf(w, `{"status":"ok"}`)
|
||||
return true
|
||||
case "datadog/api/beta/sketches":
|
||||
datadogsketchesWriteRequests.Inc()
|
||||
if err := datadogsketches.InsertHandlerForHTTP(at, r); err != nil {
|
||||
datadogsketchesWriteErrors.Inc()
|
||||
httpserver.Errorf(w, r, "%s", err)
|
||||
return true
|
||||
}
|
||||
w.WriteHeader(202)
|
||||
return true
|
||||
case "datadog/api/v1/validate":
|
||||
datadogValidateRequests.Inc()
|
||||
// See https://docs.datadoghq.com/api/latest/authentication/#validate-api-key
|
||||
@@ -674,22 +627,16 @@ var (
|
||||
|
||||
influxQueryRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/influx/query", protocol="influx"}`)
|
||||
|
||||
datadogv1WriteRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/datadog/api/v1/series", protocol="datadog"}`)
|
||||
datadogv1WriteErrors = metrics.NewCounter(`vmagent_http_request_errors_total{path="/datadog/api/v1/series", protocol="datadog"}`)
|
||||
|
||||
datadogv2WriteRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/datadog/api/v2/series", protocol="datadog"}`)
|
||||
datadogv2WriteErrors = metrics.NewCounter(`vmagent_http_request_errors_total{path="/datadog/api/v2/series", protocol="datadog"}`)
|
||||
|
||||
datadogsketchesWriteRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/datadog/api/beta/sketches", protocol="datadog"}`)
|
||||
datadogsketchesWriteErrors = metrics.NewCounter(`vmagent_http_request_errors_total{path="/datadog/api/beta/sketches", protocol="datadog"}`)
|
||||
datadogWriteRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/datadog/api/v1/series", protocol="datadog"}`)
|
||||
datadogWriteErrors = metrics.NewCounter(`vmagent_http_request_errors_total{path="/datadog/api/v1/series", protocol="datadog"}`)
|
||||
|
||||
datadogValidateRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/datadog/api/v1/validate", protocol="datadog"}`)
|
||||
datadogCheckRunRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/datadog/api/v1/check_run", protocol="datadog"}`)
|
||||
datadogIntakeRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/datadog/intake", protocol="datadog"}`)
|
||||
datadogMetadataRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/datadog/api/v1/metadata", protocol="datadog"}`)
|
||||
|
||||
opentelemetryPushRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/opentelemetry/v1/metrics", protocol="opentelemetry"}`)
|
||||
opentelemetryPushErrors = metrics.NewCounter(`vmagent_http_request_errors_total{path="/opentelemetry/v1/metrics", protocol="opentelemetry"}`)
|
||||
opentelemetryPushRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/opentelemetry/api/v1/push", protocol="opentelemetry"}`)
|
||||
opentelemetryPushErrors = metrics.NewCounter(`vmagent_http_request_errors_total{path="/opentelemetry/api/v1/push", protocol="opentelemetry"}`)
|
||||
|
||||
newrelicWriteRequests = metrics.NewCounter(`vm_http_requests_total{path="/newrelic/infra/v2/metrics/events/bulk", protocol="newrelic"}`)
|
||||
newrelicWriteErrors = metrics.NewCounter(`vm_http_request_errors_total{path="/newrelic/infra/v2/metrics/events/bulk", protocol="newrelic"}`)
|
||||
|
||||
@@ -84,8 +84,6 @@ func insertRows(at *auth.Token, block *stream.Block, extraLabels []prompbmarshal
|
||||
ctx.WriteRequest.Timeseries = tssDst
|
||||
ctx.Labels = labels
|
||||
ctx.Samples = samples
|
||||
if !remotewrite.TryPush(at, &ctx.WriteRequest) {
|
||||
return remotewrite.ErrQueueFullHTTPRetry
|
||||
}
|
||||
remotewrite.Push(at, &ctx.WriteRequest)
|
||||
return nil
|
||||
}
|
||||
|
||||
@@ -76,9 +76,7 @@ func insertRows(at *auth.Token, rows []newrelic.Row, extraLabels []prompbmarshal
|
||||
ctx.WriteRequest.Timeseries = tssDst
|
||||
ctx.Labels = labels
|
||||
ctx.Samples = samples
|
||||
if !remotewrite.TryPush(at, &ctx.WriteRequest) {
|
||||
return remotewrite.ErrQueueFullHTTPRetry
|
||||
}
|
||||
remotewrite.Push(at, &ctx.WriteRequest)
|
||||
rowsInserted.Add(len(rows))
|
||||
if at != nil {
|
||||
rowsTenantInserted.Get(at).Add(samplesCount)
|
||||
|
||||
@@ -9,7 +9,6 @@ import (
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/auth"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
|
||||
parserCommon "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/common"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/opentelemetry/firehose"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/opentelemetry/stream"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/tenantmetrics"
|
||||
"github.com/VictoriaMetrics/metrics"
|
||||
@@ -28,15 +27,10 @@ func InsertHandler(at *auth.Token, req *http.Request) error {
|
||||
return err
|
||||
}
|
||||
isGzipped := req.Header.Get("Content-Encoding") == "gzip"
|
||||
var processBody func([]byte) ([]byte, error)
|
||||
if req.Header.Get("Content-Type") == "application/json" {
|
||||
if req.Header.Get("X-Amz-Firehose-Protocol-Version") != "" {
|
||||
processBody = firehose.ProcessRequestBody
|
||||
} else {
|
||||
return fmt.Errorf("json encoding isn't supported for opentelemetry format. Use protobuf encoding")
|
||||
}
|
||||
return fmt.Errorf("json encoding isn't supported for opentelemetry format. Use protobuf encoding")
|
||||
}
|
||||
return stream.ParseStream(req.Body, isGzipped, processBody, func(tss []prompbmarshal.TimeSeries) error {
|
||||
return stream.ParseStream(req.Body, isGzipped, func(tss []prompbmarshal.TimeSeries) error {
|
||||
return insertRows(at, tss, extraLabels)
|
||||
})
|
||||
}
|
||||
@@ -65,9 +59,7 @@ func insertRows(at *auth.Token, tss []prompbmarshal.TimeSeries, extraLabels []pr
|
||||
ctx.WriteRequest.Timeseries = tssDst
|
||||
ctx.Labels = labels
|
||||
ctx.Samples = samples
|
||||
if !remotewrite.TryPush(at, &ctx.WriteRequest) {
|
||||
return remotewrite.ErrQueueFullHTTPRetry
|
||||
}
|
||||
remotewrite.Push(at, &ctx.WriteRequest)
|
||||
rowsInserted.Add(rowsTotal)
|
||||
if at != nil {
|
||||
rowsTenantInserted.Get(at).Add(rowsTotal)
|
||||
|
||||
@@ -56,9 +56,7 @@ func insertRows(rows []parser.Row) error {
|
||||
ctx.WriteRequest.Timeseries = tssDst
|
||||
ctx.Labels = labels
|
||||
ctx.Samples = samples
|
||||
if !remotewrite.TryPush(nil, &ctx.WriteRequest) {
|
||||
return remotewrite.ErrQueueFullHTTPRetry
|
||||
}
|
||||
remotewrite.Push(nil, &ctx.WriteRequest)
|
||||
rowsInserted.Add(len(rows))
|
||||
rowsPerInsert.Update(float64(len(rows)))
|
||||
return nil
|
||||
|
||||
@@ -64,9 +64,7 @@ func insertRows(at *auth.Token, rows []parser.Row, extraLabels []prompbmarshal.L
|
||||
ctx.WriteRequest.Timeseries = tssDst
|
||||
ctx.Labels = labels
|
||||
ctx.Samples = samples
|
||||
if !remotewrite.TryPush(at, &ctx.WriteRequest) {
|
||||
return remotewrite.ErrQueueFullHTTPRetry
|
||||
}
|
||||
remotewrite.Push(at, &ctx.WriteRequest)
|
||||
rowsInserted.Add(len(rows))
|
||||
rowsPerInsert.Update(float64(len(rows)))
|
||||
return nil
|
||||
|
||||
@@ -73,9 +73,7 @@ func insertRows(at *auth.Token, rows []parser.Row, extraLabels []prompbmarshal.L
|
||||
ctx.WriteRequest.Timeseries = tssDst
|
||||
ctx.Labels = labels
|
||||
ctx.Samples = samples
|
||||
if !remotewrite.TryPush(at, &ctx.WriteRequest) {
|
||||
return remotewrite.ErrQueueFullHTTPRetry
|
||||
}
|
||||
remotewrite.Push(at, &ctx.WriteRequest)
|
||||
rowsInserted.Add(len(rows))
|
||||
if at != nil {
|
||||
rowsTenantInserted.Get(at).Add(len(rows))
|
||||
|
||||
@@ -6,6 +6,7 @@ import (
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/common"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/remotewrite"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/auth"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
|
||||
parserCommon "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/common"
|
||||
@@ -47,8 +48,8 @@ func insertRows(at *auth.Token, timeseries []prompb.TimeSeries, extraLabels []pr
|
||||
for i := range ts.Labels {
|
||||
label := &ts.Labels[i]
|
||||
labels = append(labels, prompbmarshal.Label{
|
||||
Name: label.Name,
|
||||
Value: label.Value,
|
||||
Name: bytesutil.ToUnsafeString(label.Name),
|
||||
Value: bytesutil.ToUnsafeString(label.Value),
|
||||
})
|
||||
}
|
||||
labels = append(labels, extraLabels...)
|
||||
@@ -68,9 +69,7 @@ func insertRows(at *auth.Token, timeseries []prompb.TimeSeries, extraLabels []pr
|
||||
ctx.WriteRequest.Timeseries = tssDst
|
||||
ctx.Labels = labels
|
||||
ctx.Samples = samples
|
||||
if !remotewrite.TryPush(at, &ctx.WriteRequest) {
|
||||
return remotewrite.ErrQueueFullHTTPRetry
|
||||
}
|
||||
remotewrite.Push(at, &ctx.WriteRequest)
|
||||
rowsInserted.Add(rowsTotal)
|
||||
if at != nil {
|
||||
rowsTenantInserted.Get(at).Add(rowsTotal)
|
||||
|
||||
@@ -17,9 +17,7 @@ import (
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/persistentqueue"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promauth"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/common"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/ratelimiter"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/timerpool"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/timeutil"
|
||||
"github.com/VictoriaMetrics/metrics"
|
||||
)
|
||||
|
||||
@@ -31,12 +29,11 @@ var (
|
||||
|
||||
rateLimit = flagutil.NewArrayInt("remoteWrite.rateLimit", 0, "Optional rate limit in bytes per second for data sent to the corresponding -remoteWrite.url. "+
|
||||
"By default, the rate limit is disabled. It can be useful for limiting load on remote storage when big amounts of buffered data "+
|
||||
"is sent after temporary unavailability of the remote storage. See also -maxIngestionRate")
|
||||
"is sent after temporary unavailability of the remote storage")
|
||||
sendTimeout = flagutil.NewArrayDuration("remoteWrite.sendTimeout", time.Minute, "Timeout for sending a single block of data to the corresponding -remoteWrite.url")
|
||||
proxyURL = flagutil.NewArrayString("remoteWrite.proxyURL", "Optional proxy URL for writing data to the corresponding -remoteWrite.url. "+
|
||||
"Supported proxies: http, https, socks5. Example: -remoteWrite.proxyURL=socks5://proxy:1234")
|
||||
|
||||
tlsHandshakeTimeout = flagutil.NewArrayDuration("remoteWrite.tlsHandshakeTimeout", 20*time.Second, "The timeout for estabilishing tls connections to the corresponding -remoteWrite.url")
|
||||
tlsInsecureSkipVerify = flagutil.NewArrayBool("remoteWrite.tlsInsecureSkipVerify", "Whether to skip tls verification when connecting to the corresponding -remoteWrite.url")
|
||||
tlsCertFile = flagutil.NewArrayString("remoteWrite.tlsCertFile", "Optional path to client-side TLS certificate file to use when connecting "+
|
||||
"to the corresponding -remoteWrite.url")
|
||||
@@ -61,10 +58,8 @@ var (
|
||||
oauth2ClientID = flagutil.NewArrayString("remoteWrite.oauth2.clientID", "Optional OAuth2 clientID to use for the corresponding -remoteWrite.url")
|
||||
oauth2ClientSecret = flagutil.NewArrayString("remoteWrite.oauth2.clientSecret", "Optional OAuth2 clientSecret to use for the corresponding -remoteWrite.url")
|
||||
oauth2ClientSecretFile = flagutil.NewArrayString("remoteWrite.oauth2.clientSecretFile", "Optional OAuth2 clientSecretFile to use for the corresponding -remoteWrite.url")
|
||||
oauth2EndpointParams = flagutil.NewArrayString("remoteWrite.oauth2.endpointParams", "Optional OAuth2 endpoint parameters to use for the corresponding -remoteWrite.url . "+
|
||||
`The endpoint parameters must be set in JSON format: {"param1":"value1",...,"paramN":"valueN"}`)
|
||||
oauth2TokenURL = flagutil.NewArrayString("remoteWrite.oauth2.tokenUrl", "Optional OAuth2 tokenURL to use for the corresponding -remoteWrite.url")
|
||||
oauth2Scopes = flagutil.NewArrayString("remoteWrite.oauth2.scopes", "Optional OAuth2 scopes to use for the corresponding -remoteWrite.url. Scopes must be delimited by ';'")
|
||||
oauth2TokenURL = flagutil.NewArrayString("remoteWrite.oauth2.tokenUrl", "Optional OAuth2 tokenURL to use for the corresponding -remoteWrite.url")
|
||||
oauth2Scopes = flagutil.NewArrayString("remoteWrite.oauth2.scopes", "Optional OAuth2 scopes to use for the corresponding -remoteWrite.url. Scopes must be delimited by ';'")
|
||||
|
||||
awsUseSigv4 = flagutil.NewArrayBool("remoteWrite.aws.useSigv4", "Enables SigV4 request signing for the corresponding -remoteWrite.url. "+
|
||||
"It is expected that other -remoteWrite.aws.* command-line flags are set if sigv4 request signing is enabled")
|
||||
@@ -92,7 +87,7 @@ type client struct {
|
||||
authCfg *promauth.Config
|
||||
awsCfg *awsapi.Config
|
||||
|
||||
rl *ratelimiter.RateLimiter
|
||||
rl rateLimiter
|
||||
|
||||
bytesSent *metrics.Counter
|
||||
blocksSent *metrics.Counter
|
||||
@@ -113,13 +108,18 @@ func newHTTPClient(argIdx int, remoteWriteURL, sanitizedURL string, fq *persiste
|
||||
if err != nil {
|
||||
logger.Fatalf("cannot initialize auth config for -remoteWrite.url=%q: %s", remoteWriteURL, err)
|
||||
}
|
||||
tlsCfg, err := authCfg.NewTLSConfig()
|
||||
if err != nil {
|
||||
logger.Fatalf("cannot initialize tls config for -remoteWrite.url=%q: %s", remoteWriteURL, err)
|
||||
}
|
||||
awsCfg, err := getAWSAPIConfig(argIdx)
|
||||
if err != nil {
|
||||
logger.Fatalf("cannot initialize AWS Config for -remoteWrite.url=%q: %s", remoteWriteURL, err)
|
||||
}
|
||||
tr := &http.Transport{
|
||||
DialContext: statDial,
|
||||
TLSHandshakeTimeout: tlsHandshakeTimeout.GetOptionalArg(argIdx),
|
||||
TLSClientConfig: tlsCfg,
|
||||
TLSHandshakeTimeout: 10 * time.Second,
|
||||
MaxConnsPerHost: 2 * concurrency,
|
||||
MaxIdleConnsPerHost: 2 * concurrency,
|
||||
IdleConnTimeout: time.Minute,
|
||||
@@ -137,7 +137,7 @@ func newHTTPClient(argIdx int, remoteWriteURL, sanitizedURL string, fq *persiste
|
||||
tr.Proxy = http.ProxyURL(pu)
|
||||
}
|
||||
hc := &http.Client{
|
||||
Transport: authCfg.NewRoundTripper(tr),
|
||||
Transport: tr,
|
||||
Timeout: sendTimeout.GetOptionalArg(argIdx),
|
||||
}
|
||||
c := &client{
|
||||
@@ -173,11 +173,12 @@ func newHTTPClient(argIdx int, remoteWriteURL, sanitizedURL string, fq *persiste
|
||||
}
|
||||
|
||||
func (c *client) init(argIdx, concurrency int, sanitizedURL string) {
|
||||
limitReached := metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_rate_limit_reached_total{url=%q}`, c.sanitizedURL))
|
||||
if bytesPerSec := rateLimit.GetOptionalArg(argIdx); bytesPerSec > 0 {
|
||||
logger.Infof("applying %d bytes per second rate limit for -remoteWrite.url=%q", bytesPerSec, sanitizedURL)
|
||||
c.rl = ratelimiter.New(int64(bytesPerSec), limitReached, c.stopCh)
|
||||
c.rl.perSecondLimit = int64(bytesPerSec)
|
||||
}
|
||||
c.rl.limitReached = metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_rate_limit_reached_total{url=%q}`, c.sanitizedURL))
|
||||
|
||||
c.bytesSent = metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_bytes_sent_total{url=%q}`, c.sanitizedURL))
|
||||
c.blocksSent = metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_blocks_sent_total{url=%q}`, c.sanitizedURL))
|
||||
c.rateLimit = metrics.GetOrCreateGauge(fmt.Sprintf(`vmagent_remotewrite_rate_limit{url=%q}`, c.sanitizedURL), func() float64 {
|
||||
@@ -233,16 +234,10 @@ func getAuthConfig(argIdx int) (*promauth.Config, error) {
|
||||
clientSecret := oauth2ClientSecret.GetOptionalArg(argIdx)
|
||||
clientSecretFile := oauth2ClientSecretFile.GetOptionalArg(argIdx)
|
||||
if clientSecretFile != "" || clientSecret != "" {
|
||||
endpointParamsJSON := oauth2EndpointParams.GetOptionalArg(argIdx)
|
||||
endpointParams, err := flagutil.ParseJSONMap(endpointParamsJSON)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("cannot parse JSON for -remoteWrite.oauth2.endpointParams=%s: %w", endpointParamsJSON, err)
|
||||
}
|
||||
oauth2Cfg = &promauth.OAuth2Config{
|
||||
ClientID: oauth2ClientID.GetOptionalArg(argIdx),
|
||||
ClientSecret: promauth.NewSecret(clientSecret),
|
||||
ClientSecretFile: clientSecretFile,
|
||||
EndpointParams: endpointParams,
|
||||
TokenURL: oauth2TokenURL.GetOptionalArg(argIdx),
|
||||
Scopes: strings.Split(oauth2Scopes.GetOptionalArg(argIdx), ";"),
|
||||
}
|
||||
@@ -310,7 +305,7 @@ func (c *client) runWorker() {
|
||||
continue
|
||||
}
|
||||
// Return unsent block to the queue.
|
||||
c.fq.MustWriteBlockIgnoreDisabledPQ(block)
|
||||
c.fq.MustWriteBlock(block)
|
||||
return
|
||||
case <-c.stopCh:
|
||||
// c must be stopped. Wait for a while in the hope the block will be sent.
|
||||
@@ -319,11 +314,11 @@ func (c *client) runWorker() {
|
||||
case ok := <-ch:
|
||||
if !ok {
|
||||
// Return unsent block to the queue.
|
||||
c.fq.MustWriteBlockIgnoreDisabledPQ(block)
|
||||
c.fq.MustWriteBlock(block)
|
||||
}
|
||||
case <-time.After(graceDuration):
|
||||
// Return unsent block to the queue.
|
||||
c.fq.MustWriteBlockIgnoreDisabledPQ(block)
|
||||
c.fq.MustWriteBlock(block)
|
||||
}
|
||||
return
|
||||
}
|
||||
@@ -391,9 +386,8 @@ func (c *client) newRequest(url string, body []byte) (*http.Request, error) {
|
||||
// The function returns false only if c.stopCh is closed.
|
||||
// Otherwise it tries sending the block to remote storage indefinitely.
|
||||
func (c *client) sendBlockHTTP(block []byte) bool {
|
||||
c.rl.Register(len(block))
|
||||
maxRetryDuration := timeutil.AddJitterToDuration(time.Minute)
|
||||
retryDuration := timeutil.AddJitterToDuration(time.Second)
|
||||
c.rl.register(len(block), c.stopCh)
|
||||
retryDuration := time.Second
|
||||
retriesCount := 0
|
||||
|
||||
again:
|
||||
@@ -403,8 +397,8 @@ again:
|
||||
if err != nil {
|
||||
c.errorsCount.Inc()
|
||||
retryDuration *= 2
|
||||
if retryDuration > maxRetryDuration {
|
||||
retryDuration = maxRetryDuration
|
||||
if retryDuration > time.Minute {
|
||||
retryDuration = time.Minute
|
||||
}
|
||||
logger.Warnf("couldn't send a block with size %d bytes to %q: %s; re-sending the block in %.3f seconds",
|
||||
len(block), c.sanitizedURL, err, retryDuration.Seconds())
|
||||
@@ -450,8 +444,8 @@ again:
|
||||
// Unexpected status code returned
|
||||
retriesCount++
|
||||
retryDuration *= 2
|
||||
if retryDuration > maxRetryDuration {
|
||||
retryDuration = maxRetryDuration
|
||||
if retryDuration > time.Minute {
|
||||
retryDuration = time.Minute
|
||||
}
|
||||
body, err := io.ReadAll(resp.Body)
|
||||
_ = resp.Body.Close()
|
||||
@@ -474,3 +468,45 @@ again:
|
||||
}
|
||||
|
||||
var remoteWriteRejectedLogger = logger.WithThrottler("remoteWriteRejected", 5*time.Second)
|
||||
|
||||
type rateLimiter struct {
|
||||
perSecondLimit int64
|
||||
|
||||
// mu protects budget and deadline from concurrent access.
|
||||
mu sync.Mutex
|
||||
|
||||
// The current budget. It is increased by perSecondLimit every second.
|
||||
budget int64
|
||||
|
||||
// The next deadline for increasing the budget by perSecondLimit
|
||||
deadline time.Time
|
||||
|
||||
limitReached *metrics.Counter
|
||||
}
|
||||
|
||||
func (rl *rateLimiter) register(dataLen int, stopCh <-chan struct{}) {
|
||||
limit := rl.perSecondLimit
|
||||
if limit <= 0 {
|
||||
return
|
||||
}
|
||||
|
||||
rl.mu.Lock()
|
||||
defer rl.mu.Unlock()
|
||||
|
||||
for rl.budget <= 0 {
|
||||
if d := time.Until(rl.deadline); d > 0 {
|
||||
rl.limitReached.Inc()
|
||||
t := timerpool.Get(d)
|
||||
select {
|
||||
case <-stopCh:
|
||||
timerpool.Put(t)
|
||||
return
|
||||
case <-t.C:
|
||||
timerpool.Put(t)
|
||||
}
|
||||
}
|
||||
rl.budget += limit
|
||||
rl.deadline = time.Now().Add(time.Second)
|
||||
}
|
||||
rl.budget -= int64(dataLen)
|
||||
}
|
||||
|
||||
@@ -7,7 +7,6 @@ import (
|
||||
"time"
|
||||
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/cgroup"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/decimal"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/encoding/zstd"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/fasttime"
|
||||
@@ -16,7 +15,6 @@ import (
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/persistentqueue"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promrelabel"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/timeutil"
|
||||
"github.com/VictoriaMetrics/metrics"
|
||||
"github.com/golang/snappy"
|
||||
)
|
||||
@@ -39,9 +37,9 @@ type pendingSeries struct {
|
||||
periodicFlusherWG sync.WaitGroup
|
||||
}
|
||||
|
||||
func newPendingSeries(fq *persistentqueue.FastQueue, isVMRemoteWrite bool, significantFigures, roundDigits int) *pendingSeries {
|
||||
func newPendingSeries(pushBlock func(block []byte), isVMRemoteWrite bool, significantFigures, roundDigits int) *pendingSeries {
|
||||
var ps pendingSeries
|
||||
ps.wr.fq = fq
|
||||
ps.wr.pushBlock = pushBlock
|
||||
ps.wr.isVMRemoteWrite = isVMRemoteWrite
|
||||
ps.wr.significantFigures = significantFigures
|
||||
ps.wr.roundDigits = roundDigits
|
||||
@@ -59,11 +57,10 @@ func (ps *pendingSeries) MustStop() {
|
||||
ps.periodicFlusherWG.Wait()
|
||||
}
|
||||
|
||||
func (ps *pendingSeries) TryPush(tss []prompbmarshal.TimeSeries) bool {
|
||||
func (ps *pendingSeries) Push(tss []prompbmarshal.TimeSeries) {
|
||||
ps.mu.Lock()
|
||||
ok := ps.wr.tryPush(tss)
|
||||
ps.wr.push(tss)
|
||||
ps.mu.Unlock()
|
||||
return ok
|
||||
}
|
||||
|
||||
func (ps *pendingSeries) periodicFlusher() {
|
||||
@@ -71,54 +68,51 @@ func (ps *pendingSeries) periodicFlusher() {
|
||||
if flushSeconds <= 0 {
|
||||
flushSeconds = 1
|
||||
}
|
||||
d := timeutil.AddJitterToDuration(*flushInterval)
|
||||
ticker := time.NewTicker(d)
|
||||
ticker := time.NewTicker(*flushInterval)
|
||||
defer ticker.Stop()
|
||||
for {
|
||||
mustStop := false
|
||||
for !mustStop {
|
||||
select {
|
||||
case <-ps.stopCh:
|
||||
ps.mu.Lock()
|
||||
ps.wr.mustFlushOnStop()
|
||||
ps.mu.Unlock()
|
||||
return
|
||||
mustStop = true
|
||||
case <-ticker.C:
|
||||
if fasttime.UnixTimestamp()-ps.wr.lastFlushTime.Load() < uint64(flushSeconds) {
|
||||
if fasttime.UnixTimestamp()-atomic.LoadUint64(&ps.wr.lastFlushTime) < uint64(flushSeconds) {
|
||||
continue
|
||||
}
|
||||
}
|
||||
ps.mu.Lock()
|
||||
_ = ps.wr.tryFlush()
|
||||
ps.wr.flush()
|
||||
ps.mu.Unlock()
|
||||
}
|
||||
}
|
||||
|
||||
type writeRequest struct {
|
||||
lastFlushTime atomic.Uint64
|
||||
// Move lastFlushTime to the top of the struct in order to guarantee atomic access on 32-bit architectures.
|
||||
lastFlushTime uint64
|
||||
|
||||
// The queue to send blocks to.
|
||||
fq *persistentqueue.FastQueue
|
||||
// pushBlock is called when whe write request is ready to be sent.
|
||||
pushBlock func(block []byte)
|
||||
|
||||
// Whether to encode the write request with VictoriaMetrics remote write protocol.
|
||||
isVMRemoteWrite bool
|
||||
|
||||
// How many significant figures must be left before sending the writeRequest to fq.
|
||||
// How many significant figures must be left before sending the writeRequest to pushBlock.
|
||||
significantFigures int
|
||||
|
||||
// How many decimal digits after point must be left before sending the writeRequest to fq.
|
||||
// How many decimal digits after point must be left before sending the writeRequest to pushBlock.
|
||||
roundDigits int
|
||||
|
||||
wr prompbmarshal.WriteRequest
|
||||
|
||||
tss []prompbmarshal.TimeSeries
|
||||
tss []prompbmarshal.TimeSeries
|
||||
|
||||
labels []prompbmarshal.Label
|
||||
samples []prompbmarshal.Sample
|
||||
|
||||
// buf holds labels data
|
||||
buf []byte
|
||||
buf []byte
|
||||
}
|
||||
|
||||
func (wr *writeRequest) reset() {
|
||||
// Do not reset lastFlushTime, fq, isVMRemoteWrite, significantFigures and roundDigits, since they are re-used.
|
||||
// Do not reset lastFlushTime, pushBlock, isVMRemoteWrite, significantFigures and roundDigits, since they are re-used.
|
||||
|
||||
wr.wr.Timeseries = nil
|
||||
|
||||
@@ -136,40 +130,23 @@ func (wr *writeRequest) reset() {
|
||||
wr.buf = wr.buf[:0]
|
||||
}
|
||||
|
||||
// mustFlushOnStop force pushes wr data into wr.fq
|
||||
//
|
||||
// This is needed in order to properly save in-memory data to persistent queue on graceful shutdown.
|
||||
func (wr *writeRequest) mustFlushOnStop() {
|
||||
func (wr *writeRequest) flush() {
|
||||
wr.wr.Timeseries = wr.tss
|
||||
if !tryPushWriteRequest(&wr.wr, wr.mustWriteBlock, wr.isVMRemoteWrite) {
|
||||
logger.Panicf("BUG: final flush must always return true")
|
||||
}
|
||||
wr.adjustSampleValues()
|
||||
atomic.StoreUint64(&wr.lastFlushTime, fasttime.UnixTimestamp())
|
||||
pushWriteRequest(&wr.wr, wr.pushBlock, wr.isVMRemoteWrite)
|
||||
wr.reset()
|
||||
}
|
||||
|
||||
func (wr *writeRequest) mustWriteBlock(block []byte) bool {
|
||||
wr.fq.MustWriteBlockIgnoreDisabledPQ(block)
|
||||
return true
|
||||
}
|
||||
|
||||
func (wr *writeRequest) tryFlush() bool {
|
||||
wr.wr.Timeseries = wr.tss
|
||||
wr.lastFlushTime.Store(fasttime.UnixTimestamp())
|
||||
if !tryPushWriteRequest(&wr.wr, wr.fq.TryWriteBlock, wr.isVMRemoteWrite) {
|
||||
return false
|
||||
}
|
||||
wr.reset()
|
||||
return true
|
||||
}
|
||||
|
||||
func adjustSampleValues(samples []prompbmarshal.Sample, significantFigures, roundDigits int) {
|
||||
if n := significantFigures; n > 0 {
|
||||
func (wr *writeRequest) adjustSampleValues() {
|
||||
samples := wr.samples
|
||||
if n := wr.significantFigures; n > 0 {
|
||||
for i := range samples {
|
||||
s := &samples[i]
|
||||
s.Value = decimal.RoundToSignificantFigures(s.Value, n)
|
||||
}
|
||||
}
|
||||
if n := roundDigits; n < 100 {
|
||||
if n := wr.roundDigits; n < 100 {
|
||||
for i := range samples {
|
||||
s := &samples[i]
|
||||
s.Value = decimal.RoundToDecimalDigits(s.Value, n)
|
||||
@@ -177,27 +154,21 @@ func adjustSampleValues(samples []prompbmarshal.Sample, significantFigures, roun
|
||||
}
|
||||
}
|
||||
|
||||
func (wr *writeRequest) tryPush(src []prompbmarshal.TimeSeries) bool {
|
||||
func (wr *writeRequest) push(src []prompbmarshal.TimeSeries) {
|
||||
tssDst := wr.tss
|
||||
maxSamplesPerBlock := *maxRowsPerBlock
|
||||
// Allow up to 10x of labels per each block on average.
|
||||
maxLabelsPerBlock := 10 * maxSamplesPerBlock
|
||||
for i := range src {
|
||||
tssDst = append(tssDst, prompbmarshal.TimeSeries{})
|
||||
wr.copyTimeSeries(&tssDst[len(tssDst)-1], &src[i])
|
||||
if len(wr.samples) >= maxSamplesPerBlock || len(wr.labels) >= maxLabelsPerBlock {
|
||||
wr.tss = tssDst
|
||||
if !wr.tryFlush() {
|
||||
return false
|
||||
}
|
||||
wr.flush()
|
||||
tssDst = wr.tss
|
||||
}
|
||||
tsSrc := &src[i]
|
||||
adjustSampleValues(tsSrc.Samples, wr.significantFigures, wr.roundDigits)
|
||||
tssDst = append(tssDst, prompbmarshal.TimeSeries{})
|
||||
wr.copyTimeSeries(&tssDst[len(tssDst)-1], tsSrc)
|
||||
}
|
||||
|
||||
wr.tss = tssDst
|
||||
return true
|
||||
}
|
||||
|
||||
func (wr *writeRequest) copyTimeSeries(dst, src *prompbmarshal.TimeSeries) {
|
||||
@@ -225,45 +196,31 @@ func (wr *writeRequest) copyTimeSeries(dst, src *prompbmarshal.TimeSeries) {
|
||||
wr.buf = buf
|
||||
}
|
||||
|
||||
// marshalConcurrency limits the maximum number of concurrent workers, which marshal and compress WriteRequest.
|
||||
var marshalConcurrencyCh = make(chan struct{}, cgroup.AvailableCPUs())
|
||||
|
||||
func tryPushWriteRequest(wr *prompbmarshal.WriteRequest, tryPushBlock func(block []byte) bool, isVMRemoteWrite bool) bool {
|
||||
func pushWriteRequest(wr *prompbmarshal.WriteRequest, pushBlock func(block []byte), isVMRemoteWrite bool) {
|
||||
if len(wr.Timeseries) == 0 {
|
||||
// Nothing to push
|
||||
return true
|
||||
return
|
||||
}
|
||||
|
||||
marshalConcurrencyCh <- struct{}{}
|
||||
|
||||
bb := writeRequestBufPool.Get()
|
||||
bb.B = wr.MarshalProtobuf(bb.B[:0])
|
||||
bb.B = prompbmarshal.MarshalWriteRequest(bb.B[:0], wr)
|
||||
if len(bb.B) <= maxUnpackedBlockSize.IntN() {
|
||||
zb := compressBufPool.Get()
|
||||
zb := snappyBufPool.Get()
|
||||
if isVMRemoteWrite {
|
||||
zb.B = zstd.CompressLevel(zb.B[:0], bb.B, *vmProtoCompressLevel)
|
||||
} else {
|
||||
zb.B = snappy.Encode(zb.B[:cap(zb.B)], bb.B)
|
||||
}
|
||||
writeRequestBufPool.Put(bb)
|
||||
|
||||
<-marshalConcurrencyCh
|
||||
|
||||
if len(zb.B) <= persistentqueue.MaxBlockSize {
|
||||
zbLen := len(zb.B)
|
||||
ok := tryPushBlock(zb.B)
|
||||
compressBufPool.Put(zb)
|
||||
if ok {
|
||||
blockSizeRows.Update(float64(len(wr.Timeseries)))
|
||||
blockSizeBytes.Update(float64(zbLen))
|
||||
}
|
||||
return ok
|
||||
pushBlock(zb.B)
|
||||
blockSizeRows.Update(float64(len(wr.Timeseries)))
|
||||
blockSizeBytes.Update(float64(len(zb.B)))
|
||||
snappyBufPool.Put(zb)
|
||||
return
|
||||
}
|
||||
compressBufPool.Put(zb)
|
||||
snappyBufPool.Put(zb)
|
||||
} else {
|
||||
writeRequestBufPool.Put(bb)
|
||||
|
||||
<-marshalConcurrencyCh
|
||||
}
|
||||
|
||||
// Too big block. Recursively split it into smaller parts if possible.
|
||||
@@ -272,36 +229,23 @@ func tryPushWriteRequest(wr *prompbmarshal.WriteRequest, tryPushBlock func(block
|
||||
samples := wr.Timeseries[0].Samples
|
||||
if len(samples) == 1 {
|
||||
logger.Warnf("dropping a sample for metric with too long labels exceeding -remoteWrite.maxBlockSize=%d bytes", maxUnpackedBlockSize.N)
|
||||
return true
|
||||
return
|
||||
}
|
||||
n := len(samples) / 2
|
||||
wr.Timeseries[0].Samples = samples[:n]
|
||||
if !tryPushWriteRequest(wr, tryPushBlock, isVMRemoteWrite) {
|
||||
wr.Timeseries[0].Samples = samples
|
||||
return false
|
||||
}
|
||||
pushWriteRequest(wr, pushBlock, isVMRemoteWrite)
|
||||
wr.Timeseries[0].Samples = samples[n:]
|
||||
if !tryPushWriteRequest(wr, tryPushBlock, isVMRemoteWrite) {
|
||||
wr.Timeseries[0].Samples = samples
|
||||
return false
|
||||
}
|
||||
pushWriteRequest(wr, pushBlock, isVMRemoteWrite)
|
||||
wr.Timeseries[0].Samples = samples
|
||||
return true
|
||||
return
|
||||
}
|
||||
timeseries := wr.Timeseries
|
||||
n := len(timeseries) / 2
|
||||
wr.Timeseries = timeseries[:n]
|
||||
if !tryPushWriteRequest(wr, tryPushBlock, isVMRemoteWrite) {
|
||||
wr.Timeseries = timeseries
|
||||
return false
|
||||
}
|
||||
pushWriteRequest(wr, pushBlock, isVMRemoteWrite)
|
||||
wr.Timeseries = timeseries[n:]
|
||||
if !tryPushWriteRequest(wr, tryPushBlock, isVMRemoteWrite) {
|
||||
wr.Timeseries = timeseries
|
||||
return false
|
||||
}
|
||||
pushWriteRequest(wr, pushBlock, isVMRemoteWrite)
|
||||
wr.Timeseries = timeseries
|
||||
return true
|
||||
}
|
||||
|
||||
var (
|
||||
@@ -309,7 +253,5 @@ var (
|
||||
blockSizeRows = metrics.NewHistogram(`vmagent_remotewrite_block_size_rows`)
|
||||
)
|
||||
|
||||
var (
|
||||
writeRequestBufPool bytesutil.ByteBufferPool
|
||||
compressBufPool bytesutil.ByteBufferPool
|
||||
)
|
||||
var writeRequestBufPool bytesutil.ByteBufferPool
|
||||
var snappyBufPool bytesutil.ByteBufferPool
|
||||
|
||||
@@ -26,16 +26,13 @@ func testPushWriteRequest(t *testing.T, rowsCount, expectedBlockLenProm, expecte
|
||||
t.Helper()
|
||||
wr := newTestWriteRequest(rowsCount, 20)
|
||||
pushBlockLen := 0
|
||||
pushBlock := func(block []byte) bool {
|
||||
pushBlock := func(block []byte) {
|
||||
if pushBlockLen > 0 {
|
||||
panic(fmt.Errorf("BUG: pushBlock called multiple times; pushBlockLen=%d at first call, len(block)=%d at second call", pushBlockLen, len(block)))
|
||||
}
|
||||
pushBlockLen = len(block)
|
||||
return true
|
||||
}
|
||||
if !tryPushWriteRequest(wr, pushBlock, isVMRemoteWrite) {
|
||||
t.Fatalf("cannot push data to to remote storage")
|
||||
}
|
||||
pushWriteRequest(wr, pushBlock, isVMRemoteWrite)
|
||||
if math.Abs(float64(pushBlockLen-expectedBlockLen)/float64(expectedBlockLen)*100) > tolerancePrc {
|
||||
t.Fatalf("unexpected block len for rowsCount=%d, isVMRemoteWrite=%v; got %d bytes; expecting %d bytes +- %.0f%%",
|
||||
rowsCount, isVMRemoteWrite, pushBlockLen, expectedBlockLen, tolerancePrc)
|
||||
@@ -43,7 +40,7 @@ func testPushWriteRequest(t *testing.T, rowsCount, expectedBlockLenProm, expecte
|
||||
}
|
||||
|
||||
// Check Prometheus remote write
|
||||
f(false, expectedBlockLenProm, 3)
|
||||
f(false, expectedBlockLenProm, 0)
|
||||
|
||||
// Check VictoriaMetrics remote write
|
||||
f(true, expectedBlockLenVM, 15)
|
||||
|
||||
@@ -4,6 +4,7 @@ import (
|
||||
"fmt"
|
||||
"testing"
|
||||
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
|
||||
"github.com/golang/snappy"
|
||||
"github.com/klauspost/compress/s2"
|
||||
)
|
||||
@@ -21,7 +22,7 @@ func benchmarkCompressWriteRequest(b *testing.B, compressFunc func(dst, src []by
|
||||
for _, rowsCount := range []int{1, 10, 100, 1e3, 1e4} {
|
||||
b.Run(fmt.Sprintf("rows_%d", rowsCount), func(b *testing.B) {
|
||||
wr := newTestWriteRequest(rowsCount, 10)
|
||||
data := wr.MarshalProtobuf(nil)
|
||||
data := prompbmarshal.MarshalWriteRequest(nil, wr)
|
||||
b.ReportAllocs()
|
||||
b.SetBytes(int64(rowsCount))
|
||||
b.RunParallel(func(pb *testing.PB) {
|
||||
|
||||
@@ -3,7 +3,6 @@ package remotewrite
|
||||
import (
|
||||
"flag"
|
||||
"fmt"
|
||||
"strconv"
|
||||
"strings"
|
||||
"sync"
|
||||
|
||||
@@ -93,7 +92,6 @@ func (rctx *relabelCtx) applyRelabeling(tss []prompbmarshal.TimeSeries, pcs *pro
|
||||
// Nothing to change.
|
||||
return tss
|
||||
}
|
||||
rctx.reset()
|
||||
tssDst := tss[:0]
|
||||
labels := rctx.labels[:0]
|
||||
for i := range tss {
|
||||
@@ -122,7 +120,6 @@ func (rctx *relabelCtx) appendExtraLabels(tss []prompbmarshal.TimeSeries, extraL
|
||||
if len(extraLabels) == 0 {
|
||||
return
|
||||
}
|
||||
rctx.reset()
|
||||
labels := rctx.labels[:0]
|
||||
for i := range tss {
|
||||
ts := &tss[i]
|
||||
@@ -142,34 +139,6 @@ func (rctx *relabelCtx) appendExtraLabels(tss []prompbmarshal.TimeSeries, extraL
|
||||
rctx.labels = labels
|
||||
}
|
||||
|
||||
func (rctx *relabelCtx) tenantToLabels(tss []prompbmarshal.TimeSeries, accountID, projectID uint32) {
|
||||
rctx.reset()
|
||||
accountIDStr := strconv.FormatUint(uint64(accountID), 10)
|
||||
projectIDStr := strconv.FormatUint(uint64(projectID), 10)
|
||||
labels := rctx.labels[:0]
|
||||
for i := range tss {
|
||||
ts := &tss[i]
|
||||
labelsLen := len(labels)
|
||||
for _, label := range ts.Labels {
|
||||
labelName := label.Name
|
||||
if labelName == "vm_account_id" || labelName == "vm_project_id" {
|
||||
continue
|
||||
}
|
||||
labels = append(labels, label)
|
||||
}
|
||||
labels = append(labels, prompbmarshal.Label{
|
||||
Name: "vm_account_id",
|
||||
Value: accountIDStr,
|
||||
})
|
||||
labels = append(labels, prompbmarshal.Label{
|
||||
Name: "vm_project_id",
|
||||
Value: projectIDStr,
|
||||
})
|
||||
ts.Labels = labels[labelsLen:]
|
||||
}
|
||||
rctx.labels = labels
|
||||
}
|
||||
|
||||
type relabelCtx struct {
|
||||
// pool for labels, which are used during the relabeling.
|
||||
labels []prompbmarshal.Label
|
||||
@@ -191,7 +160,7 @@ func getRelabelCtx() *relabelCtx {
|
||||
}
|
||||
|
||||
func putRelabelCtx(rctx *relabelCtx) {
|
||||
rctx.reset()
|
||||
rctx.labels = rctx.labels[:0]
|
||||
relabelCtxPool.Put(rctx)
|
||||
}
|
||||
|
||||
|
||||
@@ -3,7 +3,6 @@ package remotewrite
|
||||
import (
|
||||
"flag"
|
||||
"fmt"
|
||||
"net/http"
|
||||
"net/url"
|
||||
"path/filepath"
|
||||
"strconv"
|
||||
@@ -11,8 +10,6 @@ import (
|
||||
"sync/atomic"
|
||||
"time"
|
||||
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/httpserver"
|
||||
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/auth"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/bloomfilter"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
|
||||
@@ -27,7 +24,6 @@ import (
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promrelabel"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promutils"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/ratelimiter"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/streamaggr"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/tenantmetrics"
|
||||
"github.com/VictoriaMetrics/metrics"
|
||||
@@ -38,30 +34,22 @@ var (
|
||||
remoteWriteURLs = flagutil.NewArrayString("remoteWrite.url", "Remote storage URL to write data to. It must support either VictoriaMetrics remote write protocol "+
|
||||
"or Prometheus remote_write protocol. Example url: http://<victoriametrics-host>:8428/api/v1/write . "+
|
||||
"Pass multiple -remoteWrite.url options in order to replicate the collected data to multiple remote storage systems. "+
|
||||
"The data can be sharded among the configured remote storage systems if -remoteWrite.shardByURL flag is set")
|
||||
"The data can be sharded among the configured remote storage systems if -remoteWrite.shardByURL flag is set. "+
|
||||
"See also -remoteWrite.multitenantURL")
|
||||
remoteWriteMultitenantURLs = flagutil.NewArrayString("remoteWrite.multitenantURL", "Base path for multitenant remote storage URL to write data to. "+
|
||||
"See https://docs.victoriametrics.com/vmagent.html#multitenancy for details. Example url: http://<vminsert>:8480 . "+
|
||||
"Pass multiple -remoteWrite.multitenantURL flags in order to replicate data to multiple remote storage systems. "+
|
||||
"This flag is deprecated in favor of -enableMultitenantHandlers . See https://docs.victoriametrics.com/vmagent.html#multitenancy")
|
||||
enableMultitenantHandlers = flag.Bool("enableMultitenantHandlers", false, "Whether to process incoming data via multitenant insert handlers according to "+
|
||||
"https://docs.victoriametrics.com/Cluster-VictoriaMetrics.html#url-format . By default incoming data is processed via single-node insert handlers "+
|
||||
"according to https://docs.victoriametrics.com/#how-to-import-time-series-data ."+
|
||||
"See https://docs.victoriametrics.com/vmagent.html#multitenancy for details")
|
||||
"Pass multiple -remoteWrite.multitenantURL flags in order to replicate data to multiple remote storage systems. See also -remoteWrite.url")
|
||||
shardByURL = flag.Bool("remoteWrite.shardByURL", false, "Whether to shard outgoing series across all the remote storage systems enumerated via -remoteWrite.url . "+
|
||||
"By default the data is replicated across all the -remoteWrite.url . See https://docs.victoriametrics.com/vmagent.html#sharding-among-remote-storages")
|
||||
shardByURLLabels = flagutil.NewArrayString("remoteWrite.shardByURL.labels", "Optional list of labels, which must be used for sharding outgoing samples "+
|
||||
"among remote storage systems if -remoteWrite.shardByURL command-line flag is set. By default all the labels are used for sharding in order to gain "+
|
||||
"even distribution of series over the specified -remoteWrite.url systems. See also -remoteWrite.shardByURL.ignoreLabels")
|
||||
shardByURLIgnoreLabels = flagutil.NewArrayString("remoteWrite.shardByURL.ignoreLabels", "Optional list of labels, which must be ignored when sharding outgoing samples "+
|
||||
"among remote storage systems if -remoteWrite.shardByURL command-line flag is set. By default all the labels are used for sharding in order to gain "+
|
||||
"even distribution of series over the specified -remoteWrite.url systems. See also -remoteWrite.shardByURL.labels")
|
||||
tmpDataPath = flag.String("remoteWrite.tmpDataPath", "vmagent-remotewrite-data", "Path to directory for storing pending data, which isn't sent to the configured -remoteWrite.url . "+
|
||||
"See also -remoteWrite.maxDiskUsagePerURL and -remoteWrite.disableOnDiskQueue")
|
||||
"even distribution of series over the specified -remoteWrite.url systems")
|
||||
tmpDataPath = flag.String("remoteWrite.tmpDataPath", "vmagent-remotewrite-data", "Path to directory where temporary data for remote write component is stored. "+
|
||||
"See also -remoteWrite.maxDiskUsagePerURL")
|
||||
keepDanglingQueues = flag.Bool("remoteWrite.keepDanglingQueues", false, "Keep persistent queues contents at -remoteWrite.tmpDataPath in case there are no matching -remoteWrite.url. "+
|
||||
"Useful when -remoteWrite.url is changed temporarily and persistent queue files will be needed later on.")
|
||||
queues = flag.Int("remoteWrite.queues", cgroup.AvailableCPUs()*2, "The number of concurrent queues to each -remoteWrite.url. Set more queues if default number of queues "+
|
||||
"isn't enough for sending high volume of collected data to remote storage. "+
|
||||
"Default value depends on the number of available CPU cores. It should work fine in most cases since it minimizes resource usage")
|
||||
"isn't enough for sending high volume of collected data to remote storage. Default value is 2 * numberOfAvailableCPUs")
|
||||
showRemoteWriteURL = flag.Bool("remoteWrite.showURL", false, "Whether to show -remoteWrite.url in the exported metrics. "+
|
||||
"It is hidden by default, since it can contain sensitive info such as auth key")
|
||||
maxPendingBytesPerURL = flagutil.NewArrayBytes("remoteWrite.maxDiskUsagePerURL", 0, "The maximum file-based buffer size in bytes at -remoteWrite.tmpDataPath "+
|
||||
@@ -84,8 +72,6 @@ var (
|
||||
"Excess series are logged and dropped. This can be useful for limiting series cardinality. See https://docs.victoriametrics.com/vmagent.html#cardinality-limiter")
|
||||
maxDailySeries = flag.Int("remoteWrite.maxDailySeries", 0, "The maximum number of unique series vmagent can send to remote storage systems during the last 24 hours. "+
|
||||
"Excess series are logged and dropped. This can be useful for limiting series churn rate. See https://docs.victoriametrics.com/vmagent.html#cardinality-limiter")
|
||||
maxIngestionRate = flag.Int("maxIngestionRate", 0, "The maximum number of samples vmagent can receive per second. Data ingestion is paused when the limit is exceeded. "+
|
||||
"By default there are no limits on samples ingestion rate. See also -remoteWrite.rateLimit")
|
||||
|
||||
streamAggrConfig = flagutil.NewArrayString("remoteWrite.streamAggr.config", "Optional path to file with stream aggregation config. "+
|
||||
"See https://docs.victoriametrics.com/stream-aggregation.html . "+
|
||||
@@ -96,18 +82,8 @@ var (
|
||||
streamAggrDropInput = flagutil.NewArrayBool("remoteWrite.streamAggr.dropInput", "Whether to drop all the input samples after the aggregation "+
|
||||
"with -remoteWrite.streamAggr.config. By default, only aggregates samples are dropped, while the remaining samples "+
|
||||
"are written to the corresponding -remoteWrite.url . See also -remoteWrite.streamAggr.keepInput and https://docs.victoriametrics.com/stream-aggregation.html")
|
||||
streamAggrDedupInterval = flagutil.NewArrayDuration("remoteWrite.streamAggr.dedupInterval", 0, "Input samples are de-duplicated with this interval before optional aggregation "+
|
||||
"with -remoteWrite.streamAggr.config . See also -dedup.minScrapeInterval and https://docs.victoriametrics.com/stream-aggregation.html#deduplication")
|
||||
streamAggrIgnoreOldSamples = flagutil.NewArrayBool("remoteWrite.streamAggr.ignoreOldSamples", "Whether to ignore input samples with old timestamps outside the current aggregation interval "+
|
||||
"for the corresponding -remoteWrite.streamAggr.config . See https://docs.victoriametrics.com/stream-aggregation.html#ignoring-old-samples")
|
||||
streamAggrDropInputLabels = flagutil.NewArrayString("streamAggr.dropInputLabels", "An optional list of labels to drop from samples "+
|
||||
"before stream de-duplication and aggregation . See https://docs.victoriametrics.com/stream-aggregation.html#dropping-unneeded-labels")
|
||||
|
||||
disableOnDiskQueue = flag.Bool("remoteWrite.disableOnDiskQueue", false, "Whether to disable storing pending data to -remoteWrite.tmpDataPath "+
|
||||
"when the configured remote storage systems cannot keep up with the data ingestion rate. See https://docs.victoriametrics.com/vmagent.html#disabling-on-disk-persistence ."+
|
||||
"See also -remoteWrite.dropSamplesOnOverload")
|
||||
dropSamplesOnOverload = flag.Bool("remoteWrite.dropSamplesOnOverload", false, "Whether to drop samples when -remoteWrite.disableOnDiskQueue is set and if the samples "+
|
||||
"cannot be pushed into the configured remote storage systems in a timely manner. See https://docs.victoriametrics.com/vmagent.html#disabling-on-disk-persistence")
|
||||
streamAggrDedupInterval = flagutil.NewArrayDuration("remoteWrite.streamAggr.dedupInterval", 0, "Input samples are de-duplicated with this interval before being aggregated. "+
|
||||
"Only the last sample per each time series per each interval is aggregated if the interval is greater than zero")
|
||||
)
|
||||
|
||||
var (
|
||||
@@ -120,19 +96,11 @@ var (
|
||||
|
||||
// Data without tenant id is written to defaultAuthToken if -remoteWrite.multitenantURL is specified.
|
||||
defaultAuthToken = &auth.Token{}
|
||||
|
||||
// ErrQueueFullHTTPRetry must be returned when TryPush() returns false.
|
||||
ErrQueueFullHTTPRetry = &httpserver.ErrorWithStatusCode{
|
||||
Err: fmt.Errorf("remote storage systems cannot keep up with the data ingestion rate; retry the request later " +
|
||||
"or remove -remoteWrite.disableOnDiskQueue from vmagent command-line flags, so it could save pending data to -remoteWrite.tmpDataPath; " +
|
||||
"see https://docs.victoriametrics.com/vmagent.html#disabling-on-disk-persistence"),
|
||||
StatusCode: http.StatusTooManyRequests,
|
||||
}
|
||||
)
|
||||
|
||||
// MultitenancyEnabled returns true if -enableMultitenantHandlers or -remoteWrite.multitenantURL is specified.
|
||||
// MultitenancyEnabled returns true if -remoteWrite.multitenantURL is specified.
|
||||
func MultitenancyEnabled() bool {
|
||||
return *enableMultitenantHandlers || len(*remoteWriteMultitenantURLs) > 0
|
||||
return len(*remoteWriteMultitenantURLs) > 0
|
||||
}
|
||||
|
||||
// Contains the current relabelConfigs.
|
||||
@@ -152,10 +120,7 @@ func InitSecretFlags() {
|
||||
}
|
||||
}
|
||||
|
||||
var (
|
||||
shardByURLLabelsMap map[string]struct{}
|
||||
shardByURLIgnoreLabelsMap map[string]struct{}
|
||||
)
|
||||
var shardByURLLabelsMap map[string]struct{}
|
||||
|
||||
// Init initializes remotewrite.
|
||||
//
|
||||
@@ -187,21 +152,19 @@ func Init() {
|
||||
return float64(dailySeriesLimiter.CurrentItems())
|
||||
})
|
||||
}
|
||||
|
||||
if *queues > maxQueues {
|
||||
*queues = maxQueues
|
||||
}
|
||||
if *queues <= 0 {
|
||||
*queues = 1
|
||||
}
|
||||
|
||||
if len(*shardByURLLabels) > 0 && len(*shardByURLIgnoreLabels) > 0 {
|
||||
logger.Fatalf("-remoteWrite.shardByURL.labels and -remoteWrite.shardByURL.ignoreLabels cannot be set simultaneously; " +
|
||||
"see https://docs.victoriametrics.com/vmagent/#sharding-among-remote-storages")
|
||||
if len(*shardByURLLabels) > 0 {
|
||||
m := make(map[string]struct{}, len(*shardByURLLabels))
|
||||
for _, label := range *shardByURLLabels {
|
||||
m[label] = struct{}{}
|
||||
}
|
||||
shardByURLLabelsMap = m
|
||||
}
|
||||
shardByURLLabelsMap = newMapFromStrings(*shardByURLLabels)
|
||||
shardByURLIgnoreLabelsMap = newMapFromStrings(*shardByURLIgnoreLabels)
|
||||
|
||||
initLabelsGlobal()
|
||||
|
||||
// Register SIGHUP handler for config reload before loadRelabelConfigs.
|
||||
@@ -220,7 +183,6 @@ func Init() {
|
||||
if len(*remoteWriteURLs) > 0 {
|
||||
rwctxsDefault = newRemoteWriteCtxs(nil, *remoteWriteURLs)
|
||||
}
|
||||
dropDanglingQueues()
|
||||
|
||||
// Start config reloader.
|
||||
configReloaderWG.Add(1)
|
||||
@@ -238,42 +200,6 @@ func Init() {
|
||||
}()
|
||||
}
|
||||
|
||||
func dropDanglingQueues() {
|
||||
if *keepDanglingQueues {
|
||||
return
|
||||
}
|
||||
if len(*remoteWriteMultitenantURLs) > 0 {
|
||||
// Do not drop dangling queues for *remoteWriteMultitenantURLs, since it is impossible to determine
|
||||
// unused queues for multitenant urls - they are created on demand when new sample for the given
|
||||
// tenant is pushed to remote storage.
|
||||
return
|
||||
}
|
||||
// Remove dangling persistent queues, if any.
|
||||
// This is required for the case when the number of queues has been changed or URL have been changed.
|
||||
// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/4014
|
||||
//
|
||||
existingQueues := make(map[string]struct{}, len(rwctxsDefault))
|
||||
for _, rwctx := range rwctxsDefault {
|
||||
existingQueues[rwctx.fq.Dirname()] = struct{}{}
|
||||
}
|
||||
|
||||
queuesDir := filepath.Join(*tmpDataPath, persistentQueueDirname)
|
||||
files := fs.MustReadDir(queuesDir)
|
||||
removed := 0
|
||||
for _, f := range files {
|
||||
dirname := f.Name()
|
||||
if _, ok := existingQueues[dirname]; !ok {
|
||||
logger.Infof("removing dangling queue %q", dirname)
|
||||
fullPath := filepath.Join(queuesDir, dirname)
|
||||
fs.MustRemoveAll(fullPath)
|
||||
removed++
|
||||
}
|
||||
}
|
||||
if removed > 0 {
|
||||
logger.Infof("removed %d dangling queues from %q, active queues: %d", removed, *tmpDataPath, len(rwctxsDefault))
|
||||
}
|
||||
}
|
||||
|
||||
func reloadRelabelConfigs() {
|
||||
relabelConfigReloads.Inc()
|
||||
logger.Infof("reloading relabel configs pointed by -remoteWrite.relabelConfig and -remoteWrite.urlRelabelConfig")
|
||||
@@ -293,7 +219,7 @@ func reloadRelabelConfigs() {
|
||||
var (
|
||||
relabelConfigReloads = metrics.NewCounter(`vmagent_relabel_config_reloads_total`)
|
||||
relabelConfigReloadErrors = metrics.NewCounter(`vmagent_relabel_config_reloads_errors_total`)
|
||||
relabelConfigSuccess = metrics.NewGauge(`vmagent_relabel_config_last_reload_successful`, nil)
|
||||
relabelConfigSuccess = metrics.NewCounter(`vmagent_relabel_config_last_reload_successful`)
|
||||
relabelConfigTimestamp = metrics.NewCounter(`vmagent_relabel_config_last_reload_success_timestamp_seconds`)
|
||||
)
|
||||
|
||||
@@ -347,44 +273,42 @@ func newRemoteWriteCtxs(at *auth.Token, urls []string) []*remoteWriteCtx {
|
||||
}
|
||||
rwctxs[i] = newRemoteWriteCtx(i, remoteWriteURL, maxInmemoryBlocks, sanitizedURL)
|
||||
}
|
||||
|
||||
if !*keepDanglingQueues {
|
||||
// Remove dangling queues, if any.
|
||||
// This is required for the case when the number of queues has been changed or URL have been changed.
|
||||
// See: https://github.com/VictoriaMetrics/VictoriaMetrics/issues/4014
|
||||
existingQueues := make(map[string]struct{}, len(rwctxs))
|
||||
for _, rwctx := range rwctxs {
|
||||
existingQueues[rwctx.fq.Dirname()] = struct{}{}
|
||||
}
|
||||
|
||||
queuesDir := filepath.Join(*tmpDataPath, persistentQueueDirname)
|
||||
files := fs.MustReadDir(queuesDir)
|
||||
removed := 0
|
||||
for _, f := range files {
|
||||
dirname := f.Name()
|
||||
if _, ok := existingQueues[dirname]; !ok {
|
||||
logger.Infof("removing dangling queue %q", dirname)
|
||||
fullPath := filepath.Join(queuesDir, dirname)
|
||||
fs.MustRemoveAll(fullPath)
|
||||
removed++
|
||||
}
|
||||
}
|
||||
if removed > 0 {
|
||||
logger.Infof("removed %d dangling queues from %q, active queues: %d", removed, *tmpDataPath, len(rwctxs))
|
||||
}
|
||||
}
|
||||
|
||||
return rwctxs
|
||||
}
|
||||
|
||||
var configReloaderStopCh = make(chan struct{})
|
||||
var configReloaderWG sync.WaitGroup
|
||||
|
||||
// StartIngestionRateLimiter starts ingestion rate limiter.
|
||||
//
|
||||
// Ingestion rate limiter must be started before Init() call.
|
||||
//
|
||||
// StopIngestionRateLimiter must be called before Stop() call in order to unblock all the callers
|
||||
// to ingestion rate limiter. Otherwise deadlock may occur at Stop() call.
|
||||
func StartIngestionRateLimiter() {
|
||||
if *maxIngestionRate <= 0 {
|
||||
return
|
||||
}
|
||||
ingestionRateLimitReached := metrics.NewCounter(`vmagent_max_ingestion_rate_limit_reached_total`)
|
||||
ingestionRateLimiterStopCh = make(chan struct{})
|
||||
ingestionRateLimiter = ratelimiter.New(int64(*maxIngestionRate), ingestionRateLimitReached, ingestionRateLimiterStopCh)
|
||||
}
|
||||
|
||||
// StopIngestionRateLimiter stops ingestion rate limiter.
|
||||
func StopIngestionRateLimiter() {
|
||||
if ingestionRateLimiterStopCh == nil {
|
||||
return
|
||||
}
|
||||
close(ingestionRateLimiterStopCh)
|
||||
ingestionRateLimiterStopCh = nil
|
||||
}
|
||||
|
||||
var (
|
||||
ingestionRateLimiter *ratelimiter.RateLimiter
|
||||
ingestionRateLimiterStopCh chan struct{}
|
||||
)
|
||||
|
||||
// Stop stops remotewrite.
|
||||
//
|
||||
// It is expected that nobody calls TryPush during and after the call to this func.
|
||||
// It is expected that nobody calls Push during and after the call to this func.
|
||||
func Stop() {
|
||||
close(configReloaderStopCh)
|
||||
configReloaderWG.Wait()
|
||||
@@ -394,7 +318,7 @@ func Stop() {
|
||||
}
|
||||
rwctxsDefault = nil
|
||||
|
||||
// There is no need in locking rwctxsMapLock here, since nobody should call TryPush during the Stop call.
|
||||
// There is no need in locking rwctxsMapLock here, since nobody should call Push during the Stop call.
|
||||
for _, rwctxs := range rwctxsMap {
|
||||
for _, rwctx := range rwctxs {
|
||||
rwctx.MustStop()
|
||||
@@ -410,47 +334,24 @@ func Stop() {
|
||||
}
|
||||
}
|
||||
|
||||
// PushDropSamplesOnFailure pushes wr to the configured remote storage systems set via -remoteWrite.url and -remoteWrite.multitenantURL
|
||||
// Push sends wr to remote storage systems set via `-remoteWrite.url`.
|
||||
//
|
||||
// If at is nil, then the data is pushed to the configured -remoteWrite.url.
|
||||
// If at isn't nil, the data is pushed to the configured -remoteWrite.multitenantURL.
|
||||
// If at is nil, then the data is pushed to the configured `-remoteWrite.url`.
|
||||
// If at isn't nil, the data is pushed to the configured `-remoteWrite.multitenantURL`.
|
||||
//
|
||||
// PushDropSamplesOnFailure can modify wr contents.
|
||||
func PushDropSamplesOnFailure(at *auth.Token, wr *prompbmarshal.WriteRequest) {
|
||||
_ = tryPush(at, wr, true)
|
||||
}
|
||||
|
||||
// TryPush tries sending wr to the configured remote storage systems set via -remoteWrite.url and -remoteWrite.multitenantURL
|
||||
//
|
||||
// If at is nil, then the data is pushed to the configured -remoteWrite.url.
|
||||
// If at isn't nil, the data is pushed to the configured -remoteWrite.multitenantURL.
|
||||
//
|
||||
// TryPush can modify wr contents, so the caller must re-initialize wr before calling TryPush() after unsuccessful attempt.
|
||||
// TryPush may send partial data from wr on unsuccessful attempt, so repeated call for the same wr may send the data multiple times.
|
||||
//
|
||||
// The caller must return ErrQueueFullHTTPRetry to the client, which sends wr, if TryPush returns false.
|
||||
func TryPush(at *auth.Token, wr *prompbmarshal.WriteRequest) bool {
|
||||
return tryPush(at, wr, *dropSamplesOnOverload)
|
||||
}
|
||||
|
||||
func tryPush(at *auth.Token, wr *prompbmarshal.WriteRequest, dropSamplesOnFailure bool) bool {
|
||||
tss := wr.Timeseries
|
||||
|
||||
if at == nil && MultitenancyEnabled() {
|
||||
// Write data to default tenant if at isn't set when multitenancy is enabled.
|
||||
// Note that wr may be modified by Push because of relabeling and rounding.
|
||||
func Push(at *auth.Token, wr *prompbmarshal.WriteRequest) {
|
||||
if at == nil && len(*remoteWriteMultitenantURLs) > 0 {
|
||||
// Write data to default tenant if at isn't set while -remoteWrite.multitenantURL is set.
|
||||
at = defaultAuthToken
|
||||
}
|
||||
|
||||
var tenantRctx *relabelCtx
|
||||
var rwctxs []*remoteWriteCtx
|
||||
if at == nil {
|
||||
rwctxs = rwctxsDefault
|
||||
} else if len(*remoteWriteMultitenantURLs) == 0 {
|
||||
// Convert at to (vm_account_id, vm_project_id) labels.
|
||||
tenantRctx = getRelabelCtx()
|
||||
defer putRelabelCtx(tenantRctx)
|
||||
rwctxs = rwctxsDefault
|
||||
} else {
|
||||
if len(*remoteWriteMultitenantURLs) == 0 {
|
||||
logger.Panicf("BUG: -remoteWrite.multitenantURL command-line flag must be set when __tenant_id__=%q label is set", at)
|
||||
}
|
||||
rwctxsMapLock.Lock()
|
||||
tenantID := tenantmetrics.TenantID{
|
||||
AccountID: at.AccountID,
|
||||
@@ -464,37 +365,18 @@ func tryPush(at *auth.Token, wr *prompbmarshal.WriteRequest, dropSamplesOnFailur
|
||||
rwctxsMapLock.Unlock()
|
||||
}
|
||||
|
||||
rowsCount := getRowsCount(tss)
|
||||
|
||||
if *disableOnDiskQueue {
|
||||
// Quick check whether writes to configured remote storage systems are blocked.
|
||||
// This allows saving CPU time spent on relabeling and block compression
|
||||
// if some of remote storage systems cannot keep up with the data ingestion rate.
|
||||
for _, rwctx := range rwctxs {
|
||||
if rwctx.fq.IsWriteBlocked() {
|
||||
pushFailures.Inc()
|
||||
if dropSamplesOnFailure {
|
||||
// Just drop samples
|
||||
samplesDropped.Add(rowsCount)
|
||||
return true
|
||||
}
|
||||
return false
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
var rctx *relabelCtx
|
||||
rcs := allRelabelConfigs.Load()
|
||||
pcsGlobal := rcs.global
|
||||
if pcsGlobal.Len() > 0 {
|
||||
rctx = getRelabelCtx()
|
||||
defer putRelabelCtx(rctx)
|
||||
}
|
||||
tss := wr.Timeseries
|
||||
rowsCount := getRowsCount(tss)
|
||||
globalRowsPushedBeforeRelabel.Add(rowsCount)
|
||||
maxSamplesPerBlock := *maxRowsPerBlock
|
||||
// Allow up to 10x of labels per each block on average.
|
||||
maxLabelsPerBlock := 10 * maxSamplesPerBlock
|
||||
|
||||
for len(tss) > 0 {
|
||||
// Process big tss in smaller blocks in order to reduce the maximum memory usage
|
||||
samplesCount := 0
|
||||
@@ -502,15 +384,12 @@ func tryPush(at *auth.Token, wr *prompbmarshal.WriteRequest, dropSamplesOnFailur
|
||||
i := 0
|
||||
for i < len(tss) {
|
||||
samplesCount += len(tss[i].Samples)
|
||||
labelsCount += len(tss[i].Samples) * len(tss[i].Labels)
|
||||
labelsCount += len(tss[i].Labels)
|
||||
i++
|
||||
if samplesCount >= maxSamplesPerBlock || labelsCount >= maxLabelsPerBlock {
|
||||
break
|
||||
}
|
||||
}
|
||||
|
||||
ingestionRateLimiter.Register(samplesCount)
|
||||
|
||||
tssBlock := tss
|
||||
if i < len(tss) {
|
||||
tssBlock = tss[:i]
|
||||
@@ -518,9 +397,6 @@ func tryPush(at *auth.Token, wr *prompbmarshal.WriteRequest, dropSamplesOnFailur
|
||||
} else {
|
||||
tss = nil
|
||||
}
|
||||
if tenantRctx != nil {
|
||||
tenantRctx.tenantToLabels(tssBlock, at.AccountID, at.ProjectID)
|
||||
}
|
||||
if rctx != nil {
|
||||
rowsCountBeforeRelabel := getRowsCount(tssBlock)
|
||||
tssBlock = rctx.applyRelabeling(tssBlock, pcsGlobal)
|
||||
@@ -529,35 +405,25 @@ func tryPush(at *auth.Token, wr *prompbmarshal.WriteRequest, dropSamplesOnFailur
|
||||
}
|
||||
sortLabelsIfNeeded(tssBlock)
|
||||
tssBlock = limitSeriesCardinality(tssBlock)
|
||||
if !tryPushBlockToRemoteStorages(rwctxs, tssBlock) {
|
||||
if !*disableOnDiskQueue {
|
||||
logger.Panicf("BUG: tryPushBlockToRemoteStorages must return true if -remoteWrite.disableOnDiskQueue isn't set")
|
||||
}
|
||||
pushFailures.Inc()
|
||||
if dropSamplesOnFailure {
|
||||
samplesDropped.Add(rowsCount)
|
||||
return true
|
||||
}
|
||||
return false
|
||||
pushBlockToRemoteStorages(rwctxs, tssBlock)
|
||||
if rctx != nil {
|
||||
rctx.reset()
|
||||
}
|
||||
}
|
||||
return true
|
||||
if rctx != nil {
|
||||
putRelabelCtx(rctx)
|
||||
}
|
||||
}
|
||||
|
||||
var (
|
||||
samplesDropped = metrics.NewCounter(`vmagent_remotewrite_samples_dropped_total`)
|
||||
pushFailures = metrics.NewCounter(`vmagent_remotewrite_push_failures_total`)
|
||||
)
|
||||
|
||||
func tryPushBlockToRemoteStorages(rwctxs []*remoteWriteCtx, tssBlock []prompbmarshal.TimeSeries) bool {
|
||||
func pushBlockToRemoteStorages(rwctxs []*remoteWriteCtx, tssBlock []prompbmarshal.TimeSeries) {
|
||||
if len(tssBlock) == 0 {
|
||||
// Nothing to push
|
||||
return true
|
||||
return
|
||||
}
|
||||
|
||||
if len(rwctxs) == 1 {
|
||||
// Fast path - just push data to the configured single remote storage
|
||||
return rwctxs[0].TryPush(tssBlock)
|
||||
rwctxs[0].Push(tssBlock)
|
||||
return
|
||||
}
|
||||
|
||||
// We need to push tssBlock to multiple remote storages.
|
||||
@@ -575,15 +441,6 @@ func tryPushBlockToRemoteStorages(rwctxs []*remoteWriteCtx, tssBlock []prompbmar
|
||||
hashLabels = append(hashLabels, label)
|
||||
}
|
||||
}
|
||||
tmpLabels.Labels = hashLabels
|
||||
} else if len(shardByURLIgnoreLabelsMap) > 0 {
|
||||
hashLabels = tmpLabels.Labels[:0]
|
||||
for _, label := range ts.Labels {
|
||||
if _, ok := shardByURLIgnoreLabelsMap[label.Name]; !ok {
|
||||
hashLabels = append(hashLabels, label)
|
||||
}
|
||||
}
|
||||
tmpLabels.Labels = hashLabels
|
||||
}
|
||||
h := getLabelsHash(hashLabels)
|
||||
idx := h % uint64(len(tssByURL))
|
||||
@@ -594,22 +451,19 @@ func tryPushBlockToRemoteStorages(rwctxs []*remoteWriteCtx, tssBlock []prompbmar
|
||||
// Push sharded data to remote storages in parallel in order to reduce
|
||||
// the time needed for sending the data to multiple remote storage systems.
|
||||
var wg sync.WaitGroup
|
||||
var anyPushFailed atomic.Bool
|
||||
wg.Add(len(rwctxs))
|
||||
for i, rwctx := range rwctxs {
|
||||
tssShard := tssByURL[i]
|
||||
if len(tssShard) == 0 {
|
||||
continue
|
||||
}
|
||||
wg.Add(1)
|
||||
go func(rwctx *remoteWriteCtx, tss []prompbmarshal.TimeSeries) {
|
||||
defer wg.Done()
|
||||
if !rwctx.TryPush(tss) {
|
||||
anyPushFailed.Store(true)
|
||||
}
|
||||
rwctx.Push(tss)
|
||||
}(rwctx, tssShard)
|
||||
}
|
||||
wg.Wait()
|
||||
return !anyPushFailed.Load()
|
||||
return
|
||||
}
|
||||
|
||||
// Replicate data among rwctxs.
|
||||
@@ -617,17 +471,13 @@ func tryPushBlockToRemoteStorages(rwctxs []*remoteWriteCtx, tssBlock []prompbmar
|
||||
// the time needed for sending the data to multiple remote storage systems.
|
||||
var wg sync.WaitGroup
|
||||
wg.Add(len(rwctxs))
|
||||
var anyPushFailed atomic.Bool
|
||||
for _, rwctx := range rwctxs {
|
||||
go func(rwctx *remoteWriteCtx) {
|
||||
defer wg.Done()
|
||||
if !rwctx.TryPush(tssBlock) {
|
||||
anyPushFailed.Store(true)
|
||||
}
|
||||
rwctx.Push(tssBlock)
|
||||
}(rwctx)
|
||||
}
|
||||
wg.Wait()
|
||||
return !anyPushFailed.Load()
|
||||
}
|
||||
|
||||
// sortLabelsIfNeeded sorts labels if -sortLabels command-line flag is set.
|
||||
@@ -723,14 +573,12 @@ type remoteWriteCtx struct {
|
||||
fq *persistentqueue.FastQueue
|
||||
c *client
|
||||
|
||||
sas atomic.Pointer[streamaggr.Aggregators]
|
||||
deduplicator *streamaggr.Deduplicator
|
||||
|
||||
sas atomic.Pointer[streamaggr.Aggregators]
|
||||
streamAggrKeepInput bool
|
||||
streamAggrDropInput bool
|
||||
|
||||
pss []*pendingSeries
|
||||
pssNextIdx atomic.Uint64
|
||||
pssNextIdx uint64
|
||||
|
||||
rowsPushedAfterRelabel *metrics.Counter
|
||||
rowsDroppedByRelabel *metrics.Counter
|
||||
@@ -749,19 +597,13 @@ func newRemoteWriteCtx(argIdx int, remoteWriteURL *url.URL, maxInmemoryBlocks in
|
||||
logger.Warnf("rounding the -remoteWrite.maxDiskUsagePerURL=%d to the minimum supported value: %d", maxPendingBytes, persistentqueue.DefaultChunkFileSize)
|
||||
maxPendingBytes = persistentqueue.DefaultChunkFileSize
|
||||
}
|
||||
fq := persistentqueue.MustOpenFastQueue(queuePath, sanitizedURL, maxInmemoryBlocks, maxPendingBytes, *disableOnDiskQueue)
|
||||
fq := persistentqueue.MustOpenFastQueue(queuePath, sanitizedURL, maxInmemoryBlocks, maxPendingBytes)
|
||||
_ = metrics.GetOrCreateGauge(fmt.Sprintf(`vmagent_remotewrite_pending_data_bytes{path=%q, url=%q}`, queuePath, sanitizedURL), func() float64 {
|
||||
return float64(fq.GetPendingBytes())
|
||||
})
|
||||
_ = metrics.GetOrCreateGauge(fmt.Sprintf(`vmagent_remotewrite_pending_inmemory_blocks{path=%q, url=%q}`, queuePath, sanitizedURL), func() float64 {
|
||||
return float64(fq.GetInmemoryQueueLen())
|
||||
})
|
||||
_ = metrics.GetOrCreateGauge(fmt.Sprintf(`vmagent_remotewrite_queue_blocked{path=%q, url=%q}`, queuePath, sanitizedURL), func() float64 {
|
||||
if fq.IsWriteBlocked() {
|
||||
return 1
|
||||
}
|
||||
return 0
|
||||
})
|
||||
|
||||
var c *client
|
||||
switch remoteWriteURL.Scheme {
|
||||
@@ -783,7 +625,7 @@ func newRemoteWriteCtx(argIdx int, remoteWriteURL *url.URL, maxInmemoryBlocks in
|
||||
}
|
||||
pss := make([]*pendingSeries, pssLen)
|
||||
for i := range pss {
|
||||
pss[i] = newPendingSeries(fq, c.useVMProto, sf, rd)
|
||||
pss[i] = newPendingSeries(fq.MustWriteBlock, c.useVMProto, sf, rd)
|
||||
}
|
||||
|
||||
rwctx := &remoteWriteCtx{
|
||||
@@ -798,15 +640,9 @@ func newRemoteWriteCtx(argIdx int, remoteWriteURL *url.URL, maxInmemoryBlocks in
|
||||
|
||||
// Initialize sas
|
||||
sasFile := streamAggrConfig.GetOptionalArg(argIdx)
|
||||
dedupInterval := streamAggrDedupInterval.GetOptionalArg(argIdx)
|
||||
ignoreOldSamples := streamAggrIgnoreOldSamples.GetOptionalArg(argIdx)
|
||||
if sasFile != "" {
|
||||
opts := &streamaggr.Options{
|
||||
DedupInterval: dedupInterval,
|
||||
DropInputLabels: *streamAggrDropInputLabels,
|
||||
IgnoreOldSamples: ignoreOldSamples,
|
||||
}
|
||||
sas, err := streamaggr.LoadFromFile(sasFile, rwctx.pushInternalTrackDropped, opts)
|
||||
dedupInterval := streamAggrDedupInterval.GetOptionalArg(argIdx)
|
||||
sas, err := streamaggr.LoadFromFile(sasFile, rwctx.pushInternal, dedupInterval)
|
||||
if err != nil {
|
||||
logger.Fatalf("cannot initialize stream aggregators from -remoteWrite.streamAggr.config=%q: %s", sasFile, err)
|
||||
}
|
||||
@@ -815,24 +651,17 @@ func newRemoteWriteCtx(argIdx int, remoteWriteURL *url.URL, maxInmemoryBlocks in
|
||||
rwctx.streamAggrDropInput = streamAggrDropInput.GetOptionalArg(argIdx)
|
||||
metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_streamaggr_config_reload_successful{path=%q}`, sasFile)).Set(1)
|
||||
metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_streamaggr_config_reload_success_timestamp_seconds{path=%q}`, sasFile)).Set(fasttime.UnixTimestamp())
|
||||
} else if dedupInterval > 0 {
|
||||
rwctx.deduplicator = streamaggr.NewDeduplicator(rwctx.pushInternalTrackDropped, dedupInterval, *streamAggrDropInputLabels)
|
||||
}
|
||||
|
||||
return rwctx
|
||||
}
|
||||
|
||||
func (rwctx *remoteWriteCtx) MustStop() {
|
||||
// sas and deduplicator must be stopped before rwctx is closed
|
||||
// sas must be stopped before rwctx is closed
|
||||
// because sas can write pending series to rwctx.pss if there are any
|
||||
sas := rwctx.sas.Swap(nil)
|
||||
sas.MustStop()
|
||||
|
||||
if rwctx.deduplicator != nil {
|
||||
rwctx.deduplicator.MustStop()
|
||||
rwctx.deduplicator = nil
|
||||
}
|
||||
|
||||
for _, ps := range rwctx.pss {
|
||||
ps.MustStop()
|
||||
}
|
||||
@@ -849,7 +678,7 @@ func (rwctx *remoteWriteCtx) MustStop() {
|
||||
rwctx.rowsDroppedByRelabel = nil
|
||||
}
|
||||
|
||||
func (rwctx *remoteWriteCtx) TryPush(tss []prompbmarshal.TimeSeries) bool {
|
||||
func (rwctx *remoteWriteCtx) Push(tss []prompbmarshal.TimeSeries) {
|
||||
// Apply relabeling
|
||||
var rctx *relabelCtx
|
||||
var v *[]prompbmarshal.TimeSeries
|
||||
@@ -871,7 +700,7 @@ func (rwctx *remoteWriteCtx) TryPush(tss []prompbmarshal.TimeSeries) bool {
|
||||
rowsCount := getRowsCount(tss)
|
||||
rwctx.rowsPushedAfterRelabel.Add(rowsCount)
|
||||
|
||||
// Apply stream aggregation or deduplication if they are configured
|
||||
// Apply stream aggregation if any
|
||||
sas := rwctx.sas.Load()
|
||||
if sas != nil {
|
||||
matchIdxs := matchIdxsPool.Get()
|
||||
@@ -886,14 +715,8 @@ func (rwctx *remoteWriteCtx) TryPush(tss []prompbmarshal.TimeSeries) bool {
|
||||
tss = dropAggregatedSeries(tss, matchIdxs.B, rwctx.streamAggrDropInput)
|
||||
}
|
||||
matchIdxsPool.Put(matchIdxs)
|
||||
} else if rwctx.deduplicator != nil {
|
||||
rwctx.deduplicator.Push(tss)
|
||||
clear(tss)
|
||||
tss = tss[:0]
|
||||
}
|
||||
|
||||
// Try pushing the data to remote storage
|
||||
ok := rwctx.tryPushInternal(tss)
|
||||
rwctx.pushInternal(tss)
|
||||
|
||||
// Return back relabeling contexts to the pool
|
||||
if rctx != nil {
|
||||
@@ -901,8 +724,6 @@ func (rwctx *remoteWriteCtx) TryPush(tss []prompbmarshal.TimeSeries) bool {
|
||||
tssPool.Put(v)
|
||||
putRelabelCtx(rctx)
|
||||
}
|
||||
|
||||
return ok
|
||||
}
|
||||
|
||||
var matchIdxsPool bytesutil.ByteBufferPool
|
||||
@@ -918,25 +739,11 @@ func dropAggregatedSeries(src []prompbmarshal.TimeSeries, matchIdxs []byte, drop
|
||||
}
|
||||
}
|
||||
tail := src[len(dst):]
|
||||
clear(tail)
|
||||
_ = prompbmarshal.ResetTimeSeries(tail)
|
||||
return dst
|
||||
}
|
||||
|
||||
func (rwctx *remoteWriteCtx) pushInternalTrackDropped(tss []prompbmarshal.TimeSeries) {
|
||||
if rwctx.tryPushInternal(tss) {
|
||||
return
|
||||
}
|
||||
if !*disableOnDiskQueue {
|
||||
logger.Panicf("BUG: tryPushInternal must return true if -remoteWrite.disableOnDiskQueue isn't set")
|
||||
}
|
||||
pushFailures.Inc()
|
||||
if *dropSamplesOnOverload {
|
||||
rowsCount := getRowsCount(tss)
|
||||
samplesDropped.Add(rowsCount)
|
||||
}
|
||||
}
|
||||
|
||||
func (rwctx *remoteWriteCtx) tryPushInternal(tss []prompbmarshal.TimeSeries) bool {
|
||||
func (rwctx *remoteWriteCtx) pushInternal(tss []prompbmarshal.TimeSeries) {
|
||||
var rctx *relabelCtx
|
||||
var v *[]prompbmarshal.TimeSeries
|
||||
if len(labelsGlobal) > 0 {
|
||||
@@ -949,17 +756,14 @@ func (rwctx *remoteWriteCtx) tryPushInternal(tss []prompbmarshal.TimeSeries) boo
|
||||
}
|
||||
|
||||
pss := rwctx.pss
|
||||
idx := rwctx.pssNextIdx.Add(1) % uint64(len(pss))
|
||||
|
||||
ok := pss[idx].TryPush(tss)
|
||||
idx := atomic.AddUint64(&rwctx.pssNextIdx, 1) % uint64(len(pss))
|
||||
pss[idx].Push(tss)
|
||||
|
||||
if rctx != nil {
|
||||
*v = prompbmarshal.ResetTimeSeries(tss)
|
||||
tssPool.Put(v)
|
||||
putRelabelCtx(rctx)
|
||||
}
|
||||
|
||||
return ok
|
||||
}
|
||||
|
||||
func (rwctx *remoteWriteCtx) reinitStreamAggr() {
|
||||
@@ -971,12 +775,8 @@ func (rwctx *remoteWriteCtx) reinitStreamAggr() {
|
||||
|
||||
logger.Infof("reloading stream aggregation configs pointed by -remoteWrite.streamAggr.config=%q", sasFile)
|
||||
metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_streamaggr_config_reloads_total{path=%q}`, sasFile)).Inc()
|
||||
opts := &streamaggr.Options{
|
||||
DedupInterval: streamAggrDedupInterval.GetOptionalArg(rwctx.idx),
|
||||
DropInputLabels: *streamAggrDropInputLabels,
|
||||
IgnoreOldSamples: streamAggrIgnoreOldSamples.GetOptionalArg(rwctx.idx),
|
||||
}
|
||||
sasNew, err := streamaggr.LoadFromFile(sasFile, rwctx.pushInternalTrackDropped, opts)
|
||||
dedupInterval := streamAggrDedupInterval.GetOptionalArg(rwctx.idx)
|
||||
sasNew, err := streamaggr.LoadFromFile(sasFile, rwctx.pushInternal, dedupInterval)
|
||||
if err != nil {
|
||||
metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_streamaggr_config_reloads_errors_total{path=%q}`, sasFile)).Inc()
|
||||
metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_streamaggr_config_reload_successful{path=%q}`, sasFile)).Set(0)
|
||||
@@ -1013,17 +813,13 @@ func getRowsCount(tss []prompbmarshal.TimeSeries) int {
|
||||
|
||||
// CheckStreamAggrConfigs checks configs pointed by -remoteWrite.streamAggr.config
|
||||
func CheckStreamAggrConfigs() error {
|
||||
pushNoop := func(_ []prompbmarshal.TimeSeries) {}
|
||||
pushNoop := func(tss []prompbmarshal.TimeSeries) {}
|
||||
for idx, sasFile := range *streamAggrConfig {
|
||||
if sasFile == "" {
|
||||
continue
|
||||
}
|
||||
opts := &streamaggr.Options{
|
||||
DedupInterval: streamAggrDedupInterval.GetOptionalArg(idx),
|
||||
DropInputLabels: *streamAggrDropInputLabels,
|
||||
IgnoreOldSamples: streamAggrIgnoreOldSamples.GetOptionalArg(idx),
|
||||
}
|
||||
sas, err := streamaggr.LoadFromFile(sasFile, pushNoop, opts)
|
||||
dedupInterval := streamAggrDedupInterval.GetOptionalArg(idx)
|
||||
sas, err := streamaggr.LoadFromFile(sasFile, pushNoop, dedupInterval)
|
||||
if err != nil {
|
||||
return fmt.Errorf("cannot load -remoteWrite.streamAggr.config=%q: %w", sasFile, err)
|
||||
}
|
||||
@@ -1031,11 +827,3 @@ func CheckStreamAggrConfigs() error {
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
func newMapFromStrings(a []string) map[string]struct{} {
|
||||
m := make(map[string]struct{}, len(a))
|
||||
for _, s := range a {
|
||||
m[s] = struct{}{}
|
||||
}
|
||||
return m
|
||||
}
|
||||
|
||||
@@ -50,7 +50,7 @@ var (
|
||||
)
|
||||
|
||||
type statConn struct {
|
||||
closed atomic.Int32
|
||||
closed uint64
|
||||
net.Conn
|
||||
}
|
||||
|
||||
@@ -76,7 +76,7 @@ func (sc *statConn) Write(p []byte) (int, error) {
|
||||
|
||||
func (sc *statConn) Close() error {
|
||||
err := sc.Conn.Close()
|
||||
if sc.closed.Add(1) == 1 {
|
||||
if atomic.AddUint64(&sc.closed, 1) == 1 {
|
||||
conns.Dec()
|
||||
}
|
||||
return err
|
||||
|
||||
@@ -76,9 +76,7 @@ func insertRows(at *auth.Token, rows []parser.Row, extraLabels []prompbmarshal.L
|
||||
ctx.WriteRequest.Timeseries = tssDst
|
||||
ctx.Labels = labels
|
||||
ctx.Samples = samples
|
||||
if !remotewrite.TryPush(at, &ctx.WriteRequest) {
|
||||
return remotewrite.ErrQueueFullHTTPRetry
|
||||
}
|
||||
remotewrite.Push(at, &ctx.WriteRequest)
|
||||
rowsInserted.Add(rowsTotal)
|
||||
if at != nil {
|
||||
rowsTenantInserted.Get(at).Add(rowsTotal)
|
||||
|
||||
@@ -1,3 +1,246 @@
|
||||
See vmalert-tool docs [here](https://docs.victoriametrics.com/vmalert-tool.html).
|
||||
|
||||
vmalert-tool docs can be edited at [docs/vmalert-tool.md](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/docs/vmalert-tool.md).
|
||||
# vmalert-tool
|
||||
|
||||
VMAlert command-line tool
|
||||
|
||||
## Unit testing for rules
|
||||
|
||||
You can use `vmalert-tool` to run unit tests for alerting and recording rules.
|
||||
It will perform the following actions:
|
||||
* sets up an isolated VictoriaMetrics instance;
|
||||
* simulates the periodic ingestion of time series;
|
||||
* queries the ingested data for recording and alerting rules evaluation like [vmalert](https://docs.victoriametrics.com/vmalert.html);
|
||||
* checks whether the firing alerts or resulting recording rules match the expected results.
|
||||
|
||||
See how to run vmalert-tool for unit test below:
|
||||
|
||||
```
|
||||
# Run vmalert-tool with one or multiple test files via --files cmd-line flag
|
||||
./vmalert-tool unittest --files test1.yaml --files test2.yaml
|
||||
```
|
||||
|
||||
vmalert-tool unittest is compatible with [Prometheus config format for tests](https://prometheus.io/docs/prometheus/latest/configuration/unit_testing_rules/#test-file-format)
|
||||
except `promql_expr_test` field. Use `metricsql_expr_test` field name instead. The name is different because vmalert-tool
|
||||
validates and executes [MetricsQL](https://docs.victoriametrics.com/MetricsQL.html) expressions,
|
||||
which aren't always backward compatible with [PromQL](https://prometheus.io/docs/prometheus/latest/querying/basics/).
|
||||
|
||||
### Test file format
|
||||
|
||||
The configuration format for files specified in `--files` cmd-line flag is the following:
|
||||
|
||||
```yaml
|
||||
# Path to the files or http url containing [rule groups](https://docs.victoriametrics.com/vmalert.html#groups) configuration.
|
||||
# Enterprise version of vmalert-tool supports S3 and GCS paths to rules.
|
||||
rule_files:
|
||||
[ - <string> ]
|
||||
|
||||
# The evaluation interval for rules specified in `rule_files`
|
||||
[ evaluation_interval: <duration> | default = 1m ]
|
||||
|
||||
# Groups listed below will be evaluated by order.
|
||||
# Not All the groups need not be mentioned, if not, they will be evaluated by define order in rule_files.
|
||||
group_eval_order:
|
||||
[ - <string> ]
|
||||
|
||||
# The list of unit test files to be checked during evaluation.
|
||||
tests:
|
||||
[ - <test_group> ]
|
||||
```
|
||||
|
||||
#### `<test_group>`
|
||||
|
||||
```yaml
|
||||
# Interval between samples for input series
|
||||
interval: <duration>
|
||||
# Time series to persist into the database according to configured <interval> before running tests.
|
||||
input_series:
|
||||
[ - <series> ]
|
||||
|
||||
# Name of the test group, optional
|
||||
[ name: <string> ]
|
||||
|
||||
# Unit tests for alerting rules
|
||||
alert_rule_test:
|
||||
[ - <alert_test_case> ]
|
||||
|
||||
# Unit tests for Metricsql expressions.
|
||||
metricsql_expr_test:
|
||||
[ - <metricsql_expr_test> ]
|
||||
|
||||
# External labels accessible for templating.
|
||||
external_labels:
|
||||
[ <labelname>: <string> ... ]
|
||||
|
||||
```
|
||||
|
||||
#### `<series>`
|
||||
|
||||
```yaml
|
||||
# series in the following format '<metric name>{<label name>=<label value>, ...}'
|
||||
# Examples:
|
||||
# series_name{label1="value1", label2="value2"}
|
||||
# go_goroutines{job="prometheus", instance="localhost:9090"}
|
||||
series: <string>
|
||||
|
||||
# values support several special equations:
|
||||
# 'a+bxc' becomes 'a a+b a+(2*b) a+(3*b) … a+(c*b)'
|
||||
# Read this as series starts at a, then c further samples incrementing by b.
|
||||
# 'a-bxc' becomes 'a a-b a-(2*b) a-(3*b) … a-(c*b)'
|
||||
# Read this as series starts at a, then c further samples decrementing by b (or incrementing by negative b).
|
||||
# '_' represents a missing sample from scrape
|
||||
# 'stale' indicates a stale sample
|
||||
# Examples:
|
||||
# 1. '-2+4x3' becomes '-2 2 6 10' - series starts at -2, then 3 further samples incrementing by 4.
|
||||
# 2. ' 1-2x4' becomes '1 -1 -3 -5 -7' - series starts at 1, then 4 further samples decrementing by 2.
|
||||
# 3. ' 1x4' becomes '1 1 1 1 1' - shorthand for '1+0x4', series starts at 1, then 4 further samples incrementing by 0.
|
||||
# 4. ' 1 _x3 stale' becomes '1 _ _ _ stale' - the missing sample cannot increment, so 3 missing samples are produced by the '_x3' expression.
|
||||
values: <string>
|
||||
```
|
||||
|
||||
#### `<alert_test_case>`
|
||||
|
||||
vmalert by default adds `alertgroup` and `alertname` to the generated alerts and time series.
|
||||
So you will need to specify both `groupname` and `alertname` under a single `<alert_test_case>`,
|
||||
but no need to add them under `exp_alerts`.
|
||||
You can also pass `--disableAlertgroupLabel` to skip `alertgroup` check.
|
||||
|
||||
```yaml
|
||||
# The time elapsed from time=0s when this alerting rule should be checked.
|
||||
# Means this rule should be firing at this point, or shouldn't be firing if 'exp_alerts' is empty.
|
||||
eval_time: <duration>
|
||||
|
||||
# Name of the group name to be tested.
|
||||
groupname: <string>
|
||||
|
||||
# Name of the alert to be tested.
|
||||
alertname: <string>
|
||||
|
||||
# List of the expected alerts that are firing under the given alertname at
|
||||
# the given evaluation time. If you want to test if an alerting rule should
|
||||
# not be firing, then you can mention only the fields above and leave 'exp_alerts' empty.
|
||||
exp_alerts:
|
||||
[ - <alert> ]
|
||||
```
|
||||
|
||||
#### `<alert>`
|
||||
|
||||
```yaml
|
||||
# These are the expanded labels and annotations of the expected alert.
|
||||
# Note: labels also include the labels of the sample associated with the alert
|
||||
exp_labels:
|
||||
[ <labelname>: <string> ]
|
||||
exp_annotations:
|
||||
[ <labelname>: <string> ]
|
||||
```
|
||||
|
||||
#### `<metricsql_expr_test>`
|
||||
|
||||
```yaml
|
||||
# Expression to evaluate
|
||||
expr: <string>
|
||||
|
||||
# The time elapsed from time=0s when this expression be evaluated.
|
||||
eval_time: <duration>
|
||||
|
||||
# Expected samples at the given evaluation time.
|
||||
exp_samples:
|
||||
[ - <sample> ]
|
||||
```
|
||||
|
||||
#### `<sample>`
|
||||
|
||||
```yaml
|
||||
# Labels of the sample in usual series notation '<metric name>{<label name>=<label value>, ...}'
|
||||
# Examples:
|
||||
# series_name{label1="value1", label2="value2"}
|
||||
# go_goroutines{job="prometheus", instance="localhost:9090"}
|
||||
labels: <string>
|
||||
|
||||
# The expected value of the Metricsql expression.
|
||||
value: <number>
|
||||
```
|
||||
|
||||
### Example
|
||||
|
||||
This is an example input file for unit testing which will pass.
|
||||
`test.yaml` is the test file which follows the syntax above and `alerts.yaml` contains the alerting rules.
|
||||
|
||||
With `rules.yaml` in the same directory, run `./vmalert-tool unittest --files=./unittest/testdata/test.yaml`.
|
||||
|
||||
#### `test.yaml`
|
||||
|
||||
```yaml
|
||||
rule_files:
|
||||
- rules.yaml
|
||||
|
||||
evaluation_interval: 1m
|
||||
|
||||
tests:
|
||||
- interval: 1m
|
||||
input_series:
|
||||
- series: 'up{job="prometheus", instance="localhost:9090"}'
|
||||
values: "0+0x1440"
|
||||
|
||||
metricsql_expr_test:
|
||||
- expr: suquery_interval_test
|
||||
eval_time: 4m
|
||||
exp_samples:
|
||||
- labels: '{__name__="suquery_interval_test", datacenter="dc-123", instance="localhost:9090", job="prometheus"}'
|
||||
value: 1
|
||||
|
||||
alert_rule_test:
|
||||
- eval_time: 2h
|
||||
groupname: group1
|
||||
alertname: InstanceDown
|
||||
exp_alerts:
|
||||
- exp_labels:
|
||||
job: prometheus
|
||||
severity: page
|
||||
instance: localhost:9090
|
||||
datacenter: dc-123
|
||||
exp_annotations:
|
||||
summary: "Instance localhost:9090 down"
|
||||
description: "localhost:9090 of job prometheus has been down for more than 5 minutes."
|
||||
|
||||
- eval_time: 0
|
||||
groupname: group1
|
||||
alertname: AlwaysFiring
|
||||
exp_alerts:
|
||||
- exp_labels:
|
||||
datacenter: dc-123
|
||||
|
||||
- eval_time: 0
|
||||
groupname: group1
|
||||
alertname: InstanceDown
|
||||
exp_alerts: []
|
||||
|
||||
external_labels:
|
||||
datacenter: dc-123
|
||||
```
|
||||
|
||||
#### `alerts.yaml`
|
||||
|
||||
```yaml
|
||||
# This is the rules file.
|
||||
|
||||
groups:
|
||||
- name: group1
|
||||
rules:
|
||||
- alert: InstanceDown
|
||||
expr: up == 0
|
||||
for: 5m
|
||||
labels:
|
||||
severity: page
|
||||
annotations:
|
||||
summary: "Instance {{ $labels.instance }} down"
|
||||
description: "{{ $labels.instance }} of job {{ $labels.job }} has been down for more than 5 minutes."
|
||||
- alert: AlwaysFiring
|
||||
expr: 1
|
||||
|
||||
- name: group2
|
||||
rules:
|
||||
- record: job:test:count_over_time1m
|
||||
expr: sum without(instance) (count_over_time(test[1m]))
|
||||
- record: suquery_interval_test
|
||||
expr: count_over_time(up[5m:])
|
||||
```
|
||||
@@ -21,11 +21,6 @@ tests:
|
||||
groupname: group2
|
||||
alertname: SameAlertNameWithDifferentGroup
|
||||
exp_alerts: []
|
||||
- eval_time: 150s
|
||||
groupname: group1
|
||||
alertname: SameAlertNameWithDifferentGroup
|
||||
exp_alerts:
|
||||
- {}
|
||||
- eval_time: 6m
|
||||
groupname: group1
|
||||
alertname: SameAlertNameWithDifferentGroup
|
||||
|
||||
@@ -25,7 +25,6 @@ import (
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmselect/prometheus"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmselect/promql"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmstorage"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/fs"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/httpserver"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
|
||||
@@ -185,8 +184,7 @@ func processFlags() {
|
||||
|
||||
func setUp() {
|
||||
vmstorage.Init(promql.ResetRollupResultCacheIfNeeded)
|
||||
var ab flagutil.ArrayBool
|
||||
go httpserver.Serve([]string{httpListenAddr}, &ab, func(w http.ResponseWriter, r *http.Request) bool {
|
||||
go httpserver.Serve(httpListenAddr, false, func(w http.ResponseWriter, r *http.Request) bool {
|
||||
switch r.URL.Path {
|
||||
case "/prometheus/api/v1/query":
|
||||
if err := prometheus.QueryHandler(nil, time.Now(), w, r); err != nil {
|
||||
@@ -227,7 +225,7 @@ checkCheck:
|
||||
}
|
||||
|
||||
func tearDown() {
|
||||
if err := httpserver.Stop([]string{httpListenAddr}); err != nil {
|
||||
if err := httpserver.Stop(httpListenAddr); err != nil {
|
||||
logger.Errorf("cannot stop the webservice: %s", err)
|
||||
}
|
||||
vmstorage.Stop()
|
||||
@@ -338,7 +336,7 @@ func (tg *testGroup) test(evalInterval time.Duration, groupOrderMap map[string]i
|
||||
if disableAlertgroupLabel {
|
||||
g.Name = ""
|
||||
}
|
||||
if _, ok := alertExpResultMap[alertEvalTimes[evalIndex]][g.Name]; !ok {
|
||||
if _, ok := alertExpResultMap[time.Duration(ts.UnixNano())][g.Name]; !ok {
|
||||
continue
|
||||
}
|
||||
if _, ok := gotAlertsMap[g.Name]; !ok {
|
||||
@@ -349,7 +347,7 @@ func (tg *testGroup) test(evalInterval time.Duration, groupOrderMap map[string]i
|
||||
if !isAlertRule {
|
||||
continue
|
||||
}
|
||||
if _, ok := alertExpResultMap[alertEvalTimes[evalIndex]][g.Name][ar.Name]; ok {
|
||||
if _, ok := alertExpResultMap[time.Duration(ts.UnixNano())][g.Name][ar.Name]; ok {
|
||||
for _, got := range ar.GetAlerts() {
|
||||
if got.State != notifier.StateFiring {
|
||||
continue
|
||||
|
||||
@@ -68,7 +68,6 @@ publish-vmalert:
|
||||
|
||||
test-vmalert:
|
||||
go test -v -race -cover ./app/vmalert -loggerLevel=ERROR
|
||||
go test -v -race -cover ./app/vmalert/rule
|
||||
go test -v -race -cover ./app/vmalert/templates
|
||||
go test -v -race -cover ./app/vmalert/datasource
|
||||
go test -v -race -cover ./app/vmalert/notifier
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1158,9 +1158,9 @@
|
||||
$labels.pod }}.'
|
||||
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-cputhrottlinghigh
|
||||
expr: |
|
||||
sum(increase(container_cpu_cfs_throttled_periods_total{container!="", }[5m])) by (cluster, container, pod, namespace)
|
||||
sum(increase(container_cpu_cfs_throttled_periods_total{container!="", }[5m])) by (container, pod, namespace)
|
||||
/
|
||||
sum(increase(container_cpu_cfs_periods_total{}[5m])) by (cluster, container, pod, namespace)
|
||||
sum(increase(container_cpu_cfs_periods_total{}[5m])) by (container, pod, namespace)
|
||||
> ( 25 / 100 )
|
||||
for: 15m
|
||||
labels:
|
||||
|
||||
@@ -22,7 +22,6 @@ groups:
|
||||
{{ . | first | value }}
|
||||
{{ end }}
|
||||
description: "It is {{ $value }} connections for {{$labels.instance}}"
|
||||
link: http://localhost:3000/d/wNf0q_kZk?viewPanel=51&from={{($activeAt.Add (parseDurationTime "1h")).UnixMilli}}&to={{($activeAt.Add (parseDurationTime "-1h")).UnixMilli}}
|
||||
- alert: ExampleAlertAlwaysFiring
|
||||
update_entries_limit: -1
|
||||
expr: sum by(job)
|
||||
|
||||
@@ -10,7 +10,6 @@ import (
|
||||
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/utils"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/httputils"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
|
||||
)
|
||||
|
||||
@@ -38,15 +37,13 @@ var (
|
||||
tlsCAFile = flag.String("datasource.tlsCAFile", "", `Optional path to TLS CA file to use for verifying connections to -datasource.url. By default, system CA is used`)
|
||||
tlsServerName = flag.String("datasource.tlsServerName", "", `Optional TLS server name to use for connections to -datasource.url. By default, the server name from -datasource.url is used`)
|
||||
|
||||
oauth2ClientID = flag.String("datasource.oauth2.clientID", "", "Optional OAuth2 clientID to use for -datasource.url")
|
||||
oauth2ClientSecret = flag.String("datasource.oauth2.clientSecret", "", "Optional OAuth2 clientSecret to use for -datasource.url")
|
||||
oauth2ClientSecretFile = flag.String("datasource.oauth2.clientSecretFile", "", "Optional OAuth2 clientSecretFile to use for -datasource.url")
|
||||
oauth2EndpointParams = flag.String("datasource.oauth2.endpointParams", "", "Optional OAuth2 endpoint parameters to use for -datasource.url . "+
|
||||
`The endpoint parameters must be set in JSON format: {"param1":"value1",...,"paramN":"valueN"}`)
|
||||
oauth2TokenURL = flag.String("datasource.oauth2.tokenUrl", "", "Optional OAuth2 tokenURL to use for -datasource.url")
|
||||
oauth2Scopes = flag.String("datasource.oauth2.scopes", "", "Optional OAuth2 scopes to use for -datasource.url. Scopes must be delimited by ';'")
|
||||
oauth2ClientID = flag.String("datasource.oauth2.clientID", "", "Optional OAuth2 clientID to use for -datasource.url. ")
|
||||
oauth2ClientSecret = flag.String("datasource.oauth2.clientSecret", "", "Optional OAuth2 clientSecret to use for -datasource.url.")
|
||||
oauth2ClientSecretFile = flag.String("datasource.oauth2.clientSecretFile", "", "Optional OAuth2 clientSecretFile to use for -datasource.url. ")
|
||||
oauth2TokenURL = flag.String("datasource.oauth2.tokenUrl", "", "Optional OAuth2 tokenURL to use for -datasource.url.")
|
||||
oauth2Scopes = flag.String("datasource.oauth2.scopes", "", "Optional OAuth2 scopes to use for -datasource.url. Scopes must be delimited by ';'")
|
||||
|
||||
lookBack = flag.Duration("datasource.lookback", 0, `Deprecated: please adjust "-search.latencyOffset" at datasource side `+
|
||||
lookBack = flag.Duration("datasource.lookback", 0, `Will be deprecated soon, please adjust "-search.latencyOffset" at datasource side `+
|
||||
`or specify "latency_offset" in rule group's params. Lookback defines how far into the past to look when evaluating queries. `+
|
||||
`For example, if the datasource.lookback=5m then param "time" with value now()-5m will be added to every query.`)
|
||||
queryStep = flag.Duration("datasource.queryStep", 5*time.Minute, "How far a value can fallback to when evaluating queries. "+
|
||||
@@ -91,10 +88,10 @@ func Init(extraParams url.Values) (QuerierBuilder, error) {
|
||||
logger.Warnf("flag `-datasource.queryTimeAlignment` is deprecated and will be removed in next releases. Please use `eval_alignment` in rule group instead.")
|
||||
}
|
||||
if *lookBack != 0 {
|
||||
logger.Warnf("flag `-datasource.lookback` is deprecated and will be removed in next releases. Please adjust `-search.latencyOffset` at datasource side or specify `latency_offset` in rule group's params. See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5155 for details.")
|
||||
logger.Warnf("flag `-datasource.lookback` will be deprecated soon. Please use `-rule.evalDelay` command-line flag instead. See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5155 for details.")
|
||||
}
|
||||
|
||||
tr, err := httputils.Transport(*addr, *tlsCertFile, *tlsKeyFile, *tlsCAFile, *tlsServerName, *tlsInsecureSkipVerify)
|
||||
tr, err := utils.Transport(*addr, *tlsCertFile, *tlsKeyFile, *tlsCAFile, *tlsServerName, *tlsInsecureSkipVerify)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("failed to create transport: %w", err)
|
||||
}
|
||||
@@ -111,14 +108,10 @@ func Init(extraParams url.Values) (QuerierBuilder, error) {
|
||||
extraParams.Set("round_digits", fmt.Sprintf("%d", *roundDigits))
|
||||
}
|
||||
|
||||
endpointParams, err := flagutil.ParseJSONMap(*oauth2EndpointParams)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("cannot parse JSON for -datasource.oauth2.endpointParams=%s: %w", *oauth2EndpointParams, err)
|
||||
}
|
||||
authCfg, err := utils.AuthConfig(
|
||||
utils.WithBasicAuth(*basicAuthUsername, *basicAuthPassword, *basicAuthPasswordFile),
|
||||
utils.WithBearer(*bearerToken, *bearerTokenFile),
|
||||
utils.WithOAuth(*oauth2ClientID, *oauth2ClientSecret, *oauth2ClientSecretFile, *oauth2TokenURL, *oauth2Scopes, endpointParams),
|
||||
utils.WithOAuth(*oauth2ClientID, *oauth2ClientSecret, *oauth2ClientSecretFile, *oauth2TokenURL, *oauth2Scopes),
|
||||
utils.WithHeaders(*headers))
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("failed to configure auth: %w", err)
|
||||
@@ -133,6 +126,7 @@ func Init(extraParams url.Values) (QuerierBuilder, error) {
|
||||
authCfg: authCfg,
|
||||
datasourceURL: strings.TrimSuffix(*addr, "/"),
|
||||
appendTypePrefix: *appendTypePrefix,
|
||||
lookBack: *lookBack,
|
||||
queryStep: *queryStep,
|
||||
dataSourceType: datasourcePrometheus,
|
||||
extraParams: extraParams,
|
||||
|
||||
@@ -35,6 +35,7 @@ type VMStorage struct {
|
||||
authCfg *promauth.Config
|
||||
datasourceURL string
|
||||
appendTypePrefix bool
|
||||
lookBack time.Duration
|
||||
queryStep time.Duration
|
||||
dataSourceType datasourceType
|
||||
|
||||
@@ -62,6 +63,7 @@ func (s *VMStorage) Clone() *VMStorage {
|
||||
authCfg: s.authCfg,
|
||||
datasourceURL: s.datasourceURL,
|
||||
appendTypePrefix: s.appendTypePrefix,
|
||||
lookBack: s.lookBack,
|
||||
queryStep: s.queryStep,
|
||||
|
||||
dataSourceType: s.dataSourceType,
|
||||
@@ -120,12 +122,13 @@ func (s *VMStorage) BuildWithParams(params QuerierParams) Querier {
|
||||
}
|
||||
|
||||
// NewVMStorage is a constructor for VMStorage
|
||||
func NewVMStorage(baseURL string, authCfg *promauth.Config, queryStep time.Duration, appendTypePrefix bool, c *http.Client) *VMStorage {
|
||||
func NewVMStorage(baseURL string, authCfg *promauth.Config, lookBack time.Duration, queryStep time.Duration, appendTypePrefix bool, c *http.Client) *VMStorage {
|
||||
return &VMStorage{
|
||||
c: c,
|
||||
authCfg: authCfg,
|
||||
datasourceURL: strings.TrimSuffix(baseURL, "/"),
|
||||
appendTypePrefix: appendTypePrefix,
|
||||
lookBack: lookBack,
|
||||
queryStep: queryStep,
|
||||
dataSourceType: datasourcePrometheus,
|
||||
extraParams: url.Values{},
|
||||
@@ -134,11 +137,11 @@ func NewVMStorage(baseURL string, authCfg *promauth.Config, queryStep time.Durat
|
||||
|
||||
// Query executes the given query and returns parsed response
|
||||
func (s *VMStorage) Query(ctx context.Context, query string, ts time.Time) (Result, *http.Request, error) {
|
||||
req, err := s.newQueryRequest(ctx, query, ts)
|
||||
req, err := s.newQueryRequest(query, ts)
|
||||
if err != nil {
|
||||
return Result{}, nil, err
|
||||
}
|
||||
resp, err := s.do(req)
|
||||
resp, err := s.do(ctx, req)
|
||||
if err != nil {
|
||||
if !errors.Is(err, io.EOF) && !errors.Is(err, io.ErrUnexpectedEOF) {
|
||||
// Return unexpected error to the caller.
|
||||
@@ -146,11 +149,11 @@ func (s *VMStorage) Query(ctx context.Context, query string, ts time.Time) (Resu
|
||||
}
|
||||
// Something in the middle between client and datasource might be closing
|
||||
// the connection. So we do a one more attempt in hope request will succeed.
|
||||
req, err = s.newQueryRequest(ctx, query, ts)
|
||||
req, err = s.newQueryRequest(query, ts)
|
||||
if err != nil {
|
||||
return Result{}, nil, fmt.Errorf("second attempt: %w", err)
|
||||
}
|
||||
resp, err = s.do(req)
|
||||
resp, err = s.do(ctx, req)
|
||||
if err != nil {
|
||||
return Result{}, nil, fmt.Errorf("second attempt: %w", err)
|
||||
}
|
||||
@@ -179,11 +182,11 @@ func (s *VMStorage) QueryRange(ctx context.Context, query string, start, end tim
|
||||
if end.IsZero() {
|
||||
return res, fmt.Errorf("end param is missing")
|
||||
}
|
||||
req, err := s.newQueryRangeRequest(ctx, query, start, end)
|
||||
req, err := s.newQueryRangeRequest(query, start, end)
|
||||
if err != nil {
|
||||
return res, err
|
||||
}
|
||||
resp, err := s.do(req)
|
||||
resp, err := s.do(ctx, req)
|
||||
if err != nil {
|
||||
if !errors.Is(err, io.EOF) && !errors.Is(err, io.ErrUnexpectedEOF) {
|
||||
// Return unexpected error to the caller.
|
||||
@@ -191,11 +194,11 @@ func (s *VMStorage) QueryRange(ctx context.Context, query string, start, end tim
|
||||
}
|
||||
// Something in the middle between client and datasource might be closing
|
||||
// the connection. So we do a one more attempt in hope request will succeed.
|
||||
req, err = s.newQueryRangeRequest(ctx, query, start, end)
|
||||
req, err = s.newQueryRangeRequest(query, start, end)
|
||||
if err != nil {
|
||||
return res, fmt.Errorf("second attempt: %w", err)
|
||||
}
|
||||
resp, err = s.do(req)
|
||||
resp, err = s.do(ctx, req)
|
||||
if err != nil {
|
||||
return res, fmt.Errorf("second attempt: %w", err)
|
||||
}
|
||||
@@ -207,7 +210,7 @@ func (s *VMStorage) QueryRange(ctx context.Context, query string, start, end tim
|
||||
return res, err
|
||||
}
|
||||
|
||||
func (s *VMStorage) do(req *http.Request) (*http.Response, error) {
|
||||
func (s *VMStorage) do(ctx context.Context, req *http.Request) (*http.Response, error) {
|
||||
ru := req.URL.Redacted()
|
||||
if *showDatasourceURL {
|
||||
ru = req.URL.String()
|
||||
@@ -215,7 +218,7 @@ func (s *VMStorage) do(req *http.Request) (*http.Response, error) {
|
||||
if s.debug {
|
||||
logger.Infof("DEBUG datasource request: executing %s request with params %q", req.Method, ru)
|
||||
}
|
||||
resp, err := s.c.Do(req)
|
||||
resp, err := s.c.Do(req.WithContext(ctx))
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("error getting response from %s: %w", ru, err)
|
||||
}
|
||||
@@ -227,8 +230,8 @@ func (s *VMStorage) do(req *http.Request) (*http.Response, error) {
|
||||
return resp, nil
|
||||
}
|
||||
|
||||
func (s *VMStorage) newQueryRangeRequest(ctx context.Context, query string, start, end time.Time) (*http.Request, error) {
|
||||
req, err := s.newRequest(ctx)
|
||||
func (s *VMStorage) newQueryRangeRequest(query string, start, end time.Time) (*http.Request, error) {
|
||||
req, err := s.newRequest()
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("cannot create query_range request to datasource %q: %w", s.datasourceURL, err)
|
||||
}
|
||||
@@ -236,8 +239,8 @@ func (s *VMStorage) newQueryRangeRequest(ctx context.Context, query string, star
|
||||
return req, nil
|
||||
}
|
||||
|
||||
func (s *VMStorage) newQueryRequest(ctx context.Context, query string, ts time.Time) (*http.Request, error) {
|
||||
req, err := s.newRequest(ctx)
|
||||
func (s *VMStorage) newQueryRequest(query string, ts time.Time) (*http.Request, error) {
|
||||
req, err := s.newRequest()
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("cannot create query request to datasource %q: %w", s.datasourceURL, err)
|
||||
}
|
||||
@@ -245,15 +248,15 @@ func (s *VMStorage) newQueryRequest(ctx context.Context, query string, ts time.T
|
||||
case "", datasourcePrometheus:
|
||||
s.setPrometheusInstantReqParams(req, query, ts)
|
||||
case datasourceGraphite:
|
||||
s.setGraphiteReqParams(req, query)
|
||||
s.setGraphiteReqParams(req, query, ts)
|
||||
default:
|
||||
logger.Panicf("BUG: engine not found: %q", s.dataSourceType)
|
||||
}
|
||||
return req, nil
|
||||
}
|
||||
|
||||
func (s *VMStorage) newRequest(ctx context.Context) (*http.Request, error) {
|
||||
req, err := http.NewRequestWithContext(ctx, http.MethodPost, s.datasourceURL, nil)
|
||||
func (s *VMStorage) newRequest() (*http.Request, error) {
|
||||
req, err := http.NewRequest(http.MethodPost, s.datasourceURL, nil)
|
||||
if err != nil {
|
||||
logger.Panicf("BUG: unexpected error from http.NewRequest(%q): %s", s.datasourceURL, err)
|
||||
}
|
||||
|
||||
@@ -4,6 +4,8 @@ import (
|
||||
"encoding/json"
|
||||
"fmt"
|
||||
"net/http"
|
||||
"strconv"
|
||||
"time"
|
||||
)
|
||||
|
||||
type graphiteResponse []graphiteResponseTarget
|
||||
@@ -46,13 +48,17 @@ const (
|
||||
graphitePrefix = "/graphite"
|
||||
)
|
||||
|
||||
func (s *VMStorage) setGraphiteReqParams(r *http.Request, query string) {
|
||||
func (s *VMStorage) setGraphiteReqParams(r *http.Request, query string, timestamp time.Time) {
|
||||
if s.appendTypePrefix {
|
||||
r.URL.Path += graphitePrefix
|
||||
}
|
||||
r.URL.Path += graphitePath
|
||||
q := r.URL.Query()
|
||||
from := "-5min"
|
||||
if s.lookBack > 0 {
|
||||
lookBack := timestamp.Add(-s.lookBack)
|
||||
from = strconv.FormatInt(lookBack.Unix(), 10)
|
||||
}
|
||||
q.Set("from", from)
|
||||
q.Set("format", "json")
|
||||
q.Set("target", query)
|
||||
|
||||
@@ -161,6 +161,9 @@ func (s *VMStorage) setPrometheusInstantReqParams(r *http.Request, query string,
|
||||
r.URL.Path += "/api/v1/query"
|
||||
}
|
||||
q := r.URL.Query()
|
||||
if s.lookBack > 0 {
|
||||
timestamp = timestamp.Add(-s.lookBack)
|
||||
}
|
||||
q.Set("time", timestamp.Format(time.RFC3339))
|
||||
if !*disableStepParam && s.evaluationInterval > 0 { // set step as evaluationInterval by default
|
||||
// always convert to seconds to keep compatibility with older
|
||||
|
||||
@@ -71,7 +71,7 @@ func TestVMInstantQuery(t *testing.T) {
|
||||
w.Write([]byte(`{"status":"success","data":{"resultType":"scalar","result":[1583786142, "1"]},"stats":{"seriesFetched": "42"}}`))
|
||||
}
|
||||
})
|
||||
mux.HandleFunc("/render", func(w http.ResponseWriter, _ *http.Request) {
|
||||
mux.HandleFunc("/render", func(w http.ResponseWriter, request *http.Request) {
|
||||
c++
|
||||
switch c {
|
||||
case 8:
|
||||
@@ -86,7 +86,7 @@ func TestVMInstantQuery(t *testing.T) {
|
||||
if err != nil {
|
||||
t.Fatalf("unexpected: %s", err)
|
||||
}
|
||||
s := NewVMStorage(srv.URL, authCfg, 0, false, srv.Client())
|
||||
s := NewVMStorage(srv.URL, authCfg, time.Minute, 0, false, srv.Client())
|
||||
|
||||
p := datasourcePrometheus
|
||||
pq := s.BuildWithParams(QuerierParams{DataSourceType: string(p), EvaluationInterval: 15 * time.Second})
|
||||
@@ -225,7 +225,7 @@ func TestVMInstantQueryWithRetry(t *testing.T) {
|
||||
srv := httptest.NewServer(mux)
|
||||
defer srv.Close()
|
||||
|
||||
s := NewVMStorage(srv.URL, nil, 0, false, srv.Client())
|
||||
s := NewVMStorage(srv.URL, nil, time.Minute, 0, false, srv.Client())
|
||||
pq := s.BuildWithParams(QuerierParams{DataSourceType: string(datasourcePrometheus)})
|
||||
|
||||
expErr := func(err string) {
|
||||
@@ -334,7 +334,7 @@ func TestVMRangeQuery(t *testing.T) {
|
||||
if err != nil {
|
||||
t.Fatalf("unexpected: %s", err)
|
||||
}
|
||||
s := NewVMStorage(srv.URL, authCfg, *queryStep, false, srv.Client())
|
||||
s := NewVMStorage(srv.URL, authCfg, time.Minute, *queryStep, false, srv.Client())
|
||||
|
||||
pq := s.BuildWithParams(QuerierParams{DataSourceType: string(datasourcePrometheus), EvaluationInterval: 15 * time.Second})
|
||||
|
||||
@@ -487,6 +487,17 @@ func TestRequestParams(t *testing.T) {
|
||||
checkEqualString(t, "bar", p)
|
||||
},
|
||||
},
|
||||
{
|
||||
"lookback",
|
||||
false,
|
||||
&VMStorage{
|
||||
lookBack: time.Minute,
|
||||
},
|
||||
func(t *testing.T, r *http.Request) {
|
||||
exp := url.Values{"query": {query}, "time": {timestamp.Add(-time.Minute).Format(time.RFC3339)}}
|
||||
checkEqualString(t, exp.Encode(), r.URL.RawQuery)
|
||||
},
|
||||
},
|
||||
{
|
||||
"evaluation interval",
|
||||
false,
|
||||
@@ -499,6 +510,20 @@ func TestRequestParams(t *testing.T) {
|
||||
checkEqualString(t, exp.Encode(), r.URL.RawQuery)
|
||||
},
|
||||
},
|
||||
{
|
||||
"lookback + evaluation interval",
|
||||
false,
|
||||
&VMStorage{
|
||||
lookBack: time.Minute,
|
||||
evaluationInterval: 15 * time.Second,
|
||||
},
|
||||
func(t *testing.T, r *http.Request) {
|
||||
evalInterval := 15 * time.Second
|
||||
tt := timestamp.Add(-time.Minute)
|
||||
exp := url.Values{"query": {query}, "step": {evalInterval.String()}, "time": {tt.Format(time.RFC3339)}}
|
||||
checkEqualString(t, exp.Encode(), r.URL.RawQuery)
|
||||
},
|
||||
},
|
||||
{
|
||||
"step override",
|
||||
false,
|
||||
@@ -612,7 +637,7 @@ func TestRequestParams(t *testing.T) {
|
||||
|
||||
for _, tc := range testCases {
|
||||
t.Run(tc.name, func(t *testing.T) {
|
||||
req, err := tc.vm.newRequest(ctx)
|
||||
req, err := tc.vm.newRequest()
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
@@ -624,7 +649,7 @@ func TestRequestParams(t *testing.T) {
|
||||
tc.vm.setPrometheusInstantReqParams(req, query, timestamp)
|
||||
}
|
||||
case datasourceGraphite:
|
||||
tc.vm.setGraphiteReqParams(req, query)
|
||||
tc.vm.setGraphiteReqParams(req, query, timestamp)
|
||||
}
|
||||
tc.checkFn(t, req)
|
||||
})
|
||||
@@ -710,7 +735,7 @@ func TestHeaders(t *testing.T) {
|
||||
for _, tt := range testCases {
|
||||
t.Run(tt.name, func(t *testing.T) {
|
||||
vm := tt.vmFn()
|
||||
req, err := vm.newQueryRequest(ctx, "foo", time.Now())
|
||||
req, err := vm.newQueryRequest("foo", time.Now())
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
@@ -59,8 +59,8 @@ absolute path to all .tpl files in root.
|
||||
configCheckInterval = flag.Duration("configCheckInterval", 0, "Interval for checking for changes in '-rule' or '-notifier.config' files. "+
|
||||
"By default, the checking is disabled. Send SIGHUP signal in order to force config check for changes.")
|
||||
|
||||
httpListenAddrs = flagutil.NewArrayString("httpListenAddr", "Address to listen for incoming http requests. See also -tls and -httpListenAddr.useProxyProtocol")
|
||||
useProxyProtocol = flagutil.NewArrayBool("httpListenAddr.useProxyProtocol", "Whether to use proxy protocol for connections accepted at the corresponding -httpListenAddr . "+
|
||||
httpListenAddr = flag.String("httpListenAddr", ":8880", "Address to listen for http connections. See also -httpListenAddr.useProxyProtocol")
|
||||
useProxyProtocol = flag.Bool("httpListenAddr.useProxyProtocol", false, "Whether to use proxy protocol for connections accepted at -httpListenAddr . "+
|
||||
"See https://www.haproxy.org/download/1.8/doc/proxy-protocol.txt . "+
|
||||
"With enabled proxy protocol http server cannot serve regular /metrics endpoint. Use -pushmetrics.url for metrics pushing")
|
||||
evaluationInterval = flag.Duration("evaluationInterval", time.Minute, "How often to evaluate the rules")
|
||||
@@ -96,6 +96,7 @@ func main() {
|
||||
notifier.InitSecretFlags()
|
||||
buildinfo.Init()
|
||||
logger.Init()
|
||||
pushmetrics.Init()
|
||||
|
||||
if !*remoteReadIgnoreRestoreErrors {
|
||||
logger.Warnf("flag `remoteRead.ignoreRestoreErrors` is deprecated and will be removed in next releases.")
|
||||
@@ -117,9 +118,9 @@ func main() {
|
||||
return
|
||||
}
|
||||
|
||||
eu, err := getExternalURL(*externalURL)
|
||||
eu, err := getExternalURL(*externalURL, *httpListenAddr, httpserver.IsTLS())
|
||||
if err != nil {
|
||||
logger.Fatalf("failed to init `-external.url`: %s", err)
|
||||
logger.Fatalf("failed to init `external.url`: %s", err)
|
||||
}
|
||||
|
||||
alertURLGeneratorFn, err = getAlertURLGenerator(eu, *externalAlertSource, *validateTemplates)
|
||||
@@ -178,19 +179,12 @@ func main() {
|
||||
|
||||
go configReload(ctx, manager, groupsCfg, sighupCh)
|
||||
|
||||
listenAddrs := *httpListenAddrs
|
||||
if len(listenAddrs) == 0 {
|
||||
listenAddrs = []string{":8880"}
|
||||
}
|
||||
rh := &requestHandler{m: manager}
|
||||
go httpserver.Serve(listenAddrs, useProxyProtocol, rh.handler)
|
||||
go httpserver.Serve(*httpListenAddr, *useProxyProtocol, rh.handler)
|
||||
|
||||
pushmetrics.Init()
|
||||
sig := procutil.WaitForSigterm()
|
||||
logger.Infof("service received signal %s", sig)
|
||||
pushmetrics.Stop()
|
||||
|
||||
if err := httpserver.Stop(listenAddrs); err != nil {
|
||||
if err := httpserver.Stop(*httpListenAddr); err != nil {
|
||||
logger.Fatalf("cannot stop the webservice: %s", err)
|
||||
}
|
||||
cancel()
|
||||
@@ -200,7 +194,7 @@ func main() {
|
||||
var (
|
||||
configReloads = metrics.NewCounter(`vmalert_config_last_reload_total`)
|
||||
configReloadErrors = metrics.NewCounter(`vmalert_config_last_reload_errors_total`)
|
||||
configSuccess = metrics.NewGauge(`vmalert_config_last_reload_successful`, nil)
|
||||
configSuccess = metrics.NewCounter(`vmalert_config_last_reload_successful`)
|
||||
configTimestamp = metrics.NewCounter(`vmalert_config_last_reload_success_timestamp_seconds`)
|
||||
)
|
||||
|
||||
@@ -249,34 +243,16 @@ func newManager(ctx context.Context) (*manager, error) {
|
||||
return manager, nil
|
||||
}
|
||||
|
||||
func getExternalURL(customURL string) (*url.URL, error) {
|
||||
if customURL == "" {
|
||||
// use local hostname as external URL
|
||||
listenAddr := ":8880"
|
||||
if len(*httpListenAddrs) > 0 {
|
||||
listenAddr = (*httpListenAddrs)[0]
|
||||
}
|
||||
isTLS := httpserver.IsTLS(0)
|
||||
|
||||
return getHostnameAsExternalURL(listenAddr, isTLS)
|
||||
func getExternalURL(externalURL, httpListenAddr string, isSecure bool) (*url.URL, error) {
|
||||
if externalURL != "" {
|
||||
return url.Parse(externalURL)
|
||||
}
|
||||
u, err := url.Parse(customURL)
|
||||
hname, err := os.Hostname()
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
if u.Scheme != "http" && u.Scheme != "https" {
|
||||
return nil, fmt.Errorf("invalid scheme %q in url %q, only 'http' and 'https' are supported", u.Scheme, u.String())
|
||||
}
|
||||
return u, nil
|
||||
}
|
||||
|
||||
func getHostnameAsExternalURL(addr string, isSecure bool) (*url.URL, error) {
|
||||
hname, err := os.Hostname()
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("failed to get hostname: %w", err)
|
||||
}
|
||||
port := ""
|
||||
if ipport := strings.Split(addr, ":"); len(ipport) > 1 {
|
||||
if ipport := strings.Split(httpListenAddr, ":"); len(ipport) > 1 {
|
||||
port = ":" + ipport[1]
|
||||
}
|
||||
schema := "http://"
|
||||
@@ -304,7 +280,7 @@ func getAlertURLGenerator(externalURL *url.URL, externalAlertSource string, vali
|
||||
"tpl": externalAlertSource,
|
||||
}
|
||||
return func(alert notifier.Alert) string {
|
||||
qFn := func(_ string) ([]datasource.Metric, error) {
|
||||
qFn := func(query string) ([]datasource.Metric, error) {
|
||||
return nil, fmt.Errorf("`query` template isn't supported for alert source template")
|
||||
}
|
||||
templated, err := alert.ExecTemplate(qFn, alert.Labels, m)
|
||||
|
||||
@@ -22,29 +22,22 @@ func init() {
|
||||
}
|
||||
|
||||
func TestGetExternalURL(t *testing.T) {
|
||||
invalidURL := "victoriametrics.com/path"
|
||||
_, err := getExternalURL(invalidURL)
|
||||
if err == nil {
|
||||
t.Errorf("expected error, got nil")
|
||||
}
|
||||
|
||||
expURL := "https://victoriametrics.com/path"
|
||||
u, err := getExternalURL(expURL)
|
||||
expURL := "https://vicotriametrics.com/path"
|
||||
u, err := getExternalURL(expURL, "", false)
|
||||
if err != nil {
|
||||
t.Errorf("unexpected error %s", err)
|
||||
}
|
||||
if u.String() != expURL {
|
||||
t.Errorf("unexpected url: want %q, got %s", expURL, u.String())
|
||||
t.Errorf("unexpected url want %s, got %s", expURL, u.String())
|
||||
}
|
||||
|
||||
h, _ := os.Hostname()
|
||||
expURL = fmt.Sprintf("http://%s:8880", h)
|
||||
u, err = getExternalURL("")
|
||||
expURL = fmt.Sprintf("https://%s:4242", h)
|
||||
u, err = getExternalURL("", "0.0.0.0:4242", true)
|
||||
if err != nil {
|
||||
t.Errorf("unexpected error %s", err)
|
||||
}
|
||||
if u.String() != expURL {
|
||||
t.Errorf("unexpected url: want %s, got %s", expURL, u.String())
|
||||
t.Errorf("unexpected url want %s, got %s", expURL, u.String())
|
||||
}
|
||||
}
|
||||
|
||||
@@ -141,7 +134,7 @@ groups:
|
||||
t.Fatalf("expected to have config error %s; got nil instead", cErr)
|
||||
}
|
||||
if cfgSuc != 0 {
|
||||
t.Fatalf("expected to have metric configSuccess to be set to 0; got %v instead", cfgSuc)
|
||||
t.Fatalf("expected to have metric configSuccess to be set to 0; got %d instead", cfgSuc)
|
||||
}
|
||||
return
|
||||
}
|
||||
@@ -150,7 +143,7 @@ groups:
|
||||
t.Fatalf("unexpected config error: %s", cErr)
|
||||
}
|
||||
if cfgSuc != 1 {
|
||||
t.Fatalf("expected to have metric configSuccess to be set to 1; got %v instead", cfgSuc)
|
||||
t.Fatalf("expected to have metric configSuccess to be set to 1; got %d instead", cfgSuc)
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -156,14 +156,11 @@ func (m *manager) update(ctx context.Context, groupsCfg []config.Group, restore
|
||||
var wg sync.WaitGroup
|
||||
for _, item := range toUpdate {
|
||||
wg.Add(1)
|
||||
// cancel evaluation so the Update will be applied as fast as possible.
|
||||
// it is important to call InterruptEval before the update, because cancel fn
|
||||
// can be re-assigned during the update.
|
||||
item.old.InterruptEval()
|
||||
go func(old *rule.Group, new *rule.Group) {
|
||||
old.UpdateWith(new)
|
||||
wg.Done()
|
||||
}(item.old, item.new)
|
||||
item.old.InterruptEval()
|
||||
}
|
||||
wg.Wait()
|
||||
}
|
||||
|
||||
@@ -191,7 +191,7 @@ func (a Alert) toPromLabels(relabelCfg *promrelabel.ParsedConfigs) []prompbmarsh
|
||||
var labels []prompbmarshal.Label
|
||||
for k, v := range a.Labels {
|
||||
labels = append(labels, prompbmarshal.Label{
|
||||
Name: promrelabel.SanitizeMetricName(k),
|
||||
Name: k,
|
||||
Value: v,
|
||||
})
|
||||
}
|
||||
|
||||
@@ -178,7 +178,7 @@ func TestAlert_ExecTemplate(t *testing.T) {
|
||||
},
|
||||
}
|
||||
|
||||
qFn := func(_ string) ([]datasource.Metric, error) {
|
||||
qFn := func(q string) ([]datasource.Metric, error) {
|
||||
return []datasource.Metric{
|
||||
{
|
||||
Labels: []datasource.Label{
|
||||
@@ -237,11 +237,6 @@ func TestAlert_toPromLabels(t *testing.T) {
|
||||
[]prompbmarshal.Label{{Name: "a", Value: "baz"}, {Name: "foo", Value: "bar"}},
|
||||
nil,
|
||||
)
|
||||
fn(
|
||||
map[string]string{"foo.bar": "baz", "service!name": "qux"},
|
||||
[]prompbmarshal.Label{{Name: "foo_bar", Value: "baz"}, {Name: "service_name", Value: "qux"}},
|
||||
nil,
|
||||
)
|
||||
|
||||
pcs, err := promrelabel.ParseRelabelConfigsData([]byte(`
|
||||
- target_label: "foo"
|
||||
|
||||
@@ -11,7 +11,6 @@ import (
|
||||
"time"
|
||||
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/utils"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/httputils"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promauth"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promrelabel"
|
||||
)
|
||||
@@ -105,7 +104,7 @@ func (am *AlertManager) send(ctx context.Context, alerts []Alert, headers map[st
|
||||
if *showNotifierURL {
|
||||
amURL = am.addr.String()
|
||||
}
|
||||
if resp.StatusCode/100 != 2 {
|
||||
if resp.StatusCode != http.StatusOK {
|
||||
body, err := io.ReadAll(resp.Body)
|
||||
if err != nil {
|
||||
return fmt.Errorf("failed to read response from %q: %w", amURL, err)
|
||||
@@ -128,7 +127,7 @@ func NewAlertManager(alertManagerURL string, fn AlertURLGenerator, authCfg proma
|
||||
if authCfg.TLSConfig != nil {
|
||||
tls = authCfg.TLSConfig
|
||||
}
|
||||
tr, err := httputils.Transport(alertManagerURL, tls.CertFile, tls.KeyFile, tls.CAFile, tls.ServerName, tls.InsecureSkipVerify)
|
||||
tr, err := utils.Transport(alertManagerURL, tls.CertFile, tls.KeyFile, tls.CAFile, tls.ServerName, tls.InsecureSkipVerify)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("failed to create transport: %w", err)
|
||||
}
|
||||
@@ -145,7 +144,7 @@ func NewAlertManager(alertManagerURL string, fn AlertURLGenerator, authCfg proma
|
||||
aCfg, err := utils.AuthConfig(
|
||||
utils.WithBasicAuth(ba.Username, ba.Password.String(), ba.PasswordFile),
|
||||
utils.WithBearer(authCfg.BearerToken.String(), authCfg.BearerTokenFile),
|
||||
utils.WithOAuth(oauth.ClientID, oauth.ClientSecretFile, oauth.ClientSecretFile, oauth.TokenURL, strings.Join(oauth.Scopes, ";"), oauth.EndpointParams))
|
||||
utils.WithOAuth(oauth.ClientID, oauth.ClientSecretFile, oauth.ClientSecretFile, oauth.TokenURL, strings.Join(oauth.Scopes, ";")))
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("failed to configure auth: %w", err)
|
||||
}
|
||||
|
||||
@@ -23,7 +23,7 @@ var (
|
||||
"It is hidden by default, since it can contain sensitive info such as auth key")
|
||||
blackHole = flag.Bool("notifier.blackhole", false, "Whether to blackhole alerting notifications. "+
|
||||
"Enable this flag if you want vmalert to evaluate alerting rules without sending any notifications to external receivers (eg. alertmanager). "+
|
||||
"-notifier.url, -notifier.config and -notifier.blackhole are mutually exclusive.")
|
||||
"`-notifier.url`, `-notifier.config` and `-notifier.blackhole` are mutually exclusive.")
|
||||
|
||||
basicAuthUsername = flagutil.NewArrayString("notifier.basicAuth.username", "Optional basic auth username for -notifier.url")
|
||||
basicAuthPassword = flagutil.NewArrayString("notifier.basicAuth.password", "Optional basic auth password for -notifier.url")
|
||||
@@ -46,8 +46,6 @@ var (
|
||||
"If multiple args are set, then they are applied independently for the corresponding -notifier.url")
|
||||
oauth2ClientSecretFile = flagutil.NewArrayString("notifier.oauth2.clientSecretFile", "Optional OAuth2 clientSecretFile to use for -notifier.url. "+
|
||||
"If multiple args are set, then they are applied independently for the corresponding -notifier.url")
|
||||
oauth2EndpointParams = flagutil.NewArrayString("notifier.oauth2.endpointParams", "Optional OAuth2 endpoint parameters to use for the corresponding -notifier.url . "+
|
||||
`The endpoint parameters must be set in JSON format: {"param1":"value1",...,"paramN":"valueN"}`)
|
||||
oauth2TokenURL = flagutil.NewArrayString("notifier.oauth2.tokenUrl", "Optional OAuth2 tokenURL to use for -notifier.url. "+
|
||||
"If multiple args are set, then they are applied independently for the corresponding -notifier.url")
|
||||
oauth2Scopes = flagutil.NewArrayString("notifier.oauth2.scopes", "Optional OAuth2 scopes to use for -notifier.url. Scopes must be delimited by ';'. "+
|
||||
@@ -143,11 +141,6 @@ func InitSecretFlags() {
|
||||
func notifiersFromFlags(gen AlertURLGenerator) ([]Notifier, error) {
|
||||
var notifiers []Notifier
|
||||
for i, addr := range *addrs {
|
||||
endpointParamsJSON := oauth2EndpointParams.GetOptionalArg(i)
|
||||
endpointParams, err := flagutil.ParseJSONMap(endpointParamsJSON)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("cannot parse JSON for -notifier.oauth2.endpointParams=%s: %w", endpointParamsJSON, err)
|
||||
}
|
||||
authCfg := promauth.HTTPClientConfig{
|
||||
TLSConfig: &promauth.TLSConfig{
|
||||
CAFile: tlsCAFile.GetOptionalArg(i),
|
||||
@@ -167,7 +160,6 @@ func notifiersFromFlags(gen AlertURLGenerator) ([]Notifier, error) {
|
||||
ClientID: oauth2ClientID.GetOptionalArg(i),
|
||||
ClientSecret: promauth.NewSecret(oauth2ClientSecret.GetOptionalArg(i)),
|
||||
ClientSecretFile: oauth2ClientSecretFile.GetOptionalArg(i),
|
||||
EndpointParams: endpointParams,
|
||||
Scopes: strings.Split(oauth2Scopes.GetOptionalArg(i), ";"),
|
||||
TokenURL: oauth2TokenURL.GetOptionalArg(i),
|
||||
},
|
||||
|
||||
@@ -8,7 +8,6 @@ import (
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/datasource"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/utils"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/httputils"
|
||||
)
|
||||
|
||||
var (
|
||||
@@ -42,10 +41,8 @@ var (
|
||||
oauth2ClientID = flag.String("remoteRead.oauth2.clientID", "", "Optional OAuth2 clientID to use for -remoteRead.url.")
|
||||
oauth2ClientSecret = flag.String("remoteRead.oauth2.clientSecret", "", "Optional OAuth2 clientSecret to use for -remoteRead.url.")
|
||||
oauth2ClientSecretFile = flag.String("remoteRead.oauth2.clientSecretFile", "", "Optional OAuth2 clientSecretFile to use for -remoteRead.url.")
|
||||
oauth2EndpointParams = flag.String("remoteRead.oauth2.endpointParams", "", "Optional OAuth2 endpoint parameters to use for -remoteRead.url . "+
|
||||
`The endpoint parameters must be set in JSON format: {"param1":"value1",...,"paramN":"valueN"}`)
|
||||
oauth2TokenURL = flag.String("remoteRead.oauth2.tokenUrl", "", "Optional OAuth2 tokenURL to use for -remoteRead.url. ")
|
||||
oauth2Scopes = flag.String("remoteRead.oauth2.scopes", "", "Optional OAuth2 scopes to use for -remoteRead.url. Scopes must be delimited by ';'.")
|
||||
oauth2TokenURL = flag.String("remoteRead.oauth2.tokenUrl", "", "Optional OAuth2 tokenURL to use for -remoteRead.url. ")
|
||||
oauth2Scopes = flag.String("remoteRead.oauth2.scopes", "", "Optional OAuth2 scopes to use for -remoteRead.url. Scopes must be delimited by ';'.")
|
||||
)
|
||||
|
||||
// InitSecretFlags must be called after flag.Parse and before any logging
|
||||
@@ -61,23 +58,19 @@ func Init() (datasource.QuerierBuilder, error) {
|
||||
if *addr == "" {
|
||||
return nil, nil
|
||||
}
|
||||
tr, err := httputils.Transport(*addr, *tlsCertFile, *tlsKeyFile, *tlsCAFile, *tlsServerName, *tlsInsecureSkipVerify)
|
||||
tr, err := utils.Transport(*addr, *tlsCertFile, *tlsKeyFile, *tlsCAFile, *tlsServerName, *tlsInsecureSkipVerify)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("failed to create transport: %w", err)
|
||||
}
|
||||
|
||||
endpointParams, err := flagutil.ParseJSONMap(*oauth2EndpointParams)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("cannot parse JSON for -remoteRead.oauth2.endpointParams=%s: %w", *oauth2EndpointParams, err)
|
||||
}
|
||||
authCfg, err := utils.AuthConfig(
|
||||
utils.WithBasicAuth(*basicAuthUsername, *basicAuthPassword, *basicAuthPasswordFile),
|
||||
utils.WithBearer(*bearerToken, *bearerTokenFile),
|
||||
utils.WithOAuth(*oauth2ClientID, *oauth2ClientSecret, *oauth2ClientSecretFile, *oauth2TokenURL, *oauth2Scopes, endpointParams),
|
||||
utils.WithOAuth(*oauth2ClientID, *oauth2ClientSecret, *oauth2ClientSecretFile, *oauth2TokenURL, *oauth2Scopes),
|
||||
utils.WithHeaders(*headers))
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("failed to configure auth: %w", err)
|
||||
}
|
||||
c := &http.Client{Transport: tr}
|
||||
return datasource.NewVMStorage(*addr, authCfg, 0, false, c), nil
|
||||
return datasource.NewVMStorage(*addr, authCfg, 0, 0, false, c), nil
|
||||
}
|
||||
|
||||
@@ -123,12 +123,14 @@ func (c *Client) Push(s prompbmarshal.TimeSeries) error {
|
||||
case <-c.doneCh:
|
||||
rwErrors.Inc()
|
||||
droppedRows.Add(len(s.Samples))
|
||||
droppedBytes.Add(s.Size())
|
||||
return fmt.Errorf("client is closed")
|
||||
case c.input <- s:
|
||||
return nil
|
||||
default:
|
||||
rwErrors.Inc()
|
||||
droppedRows.Add(len(s.Samples))
|
||||
droppedBytes.Add(s.Size())
|
||||
return fmt.Errorf("failed to push timeseries - queue is full (%d entries). "+
|
||||
"Queue size is controlled by -remoteWrite.maxQueueSize flag",
|
||||
c.maxQueueSize)
|
||||
@@ -151,22 +153,12 @@ func (c *Client) run(ctx context.Context) {
|
||||
ticker := time.NewTicker(c.flushInterval)
|
||||
wr := &prompbmarshal.WriteRequest{}
|
||||
shutdown := func() {
|
||||
lastCtx, cancel := context.WithTimeout(context.Background(), defaultWriteTimeout)
|
||||
logger.Infof("shutting down remote write client and flushing remained series")
|
||||
|
||||
shutdownFlushCnt := 0
|
||||
for ts := range c.input {
|
||||
wr.Timeseries = append(wr.Timeseries, ts)
|
||||
if len(wr.Timeseries) >= c.maxBatchSize {
|
||||
shutdownFlushCnt += len(wr.Timeseries)
|
||||
c.flush(lastCtx, wr)
|
||||
}
|
||||
}
|
||||
// flush the last batch. `flush` will re-check and avoid flushing empty batch.
|
||||
shutdownFlushCnt += len(wr.Timeseries)
|
||||
lastCtx, cancel := context.WithTimeout(context.Background(), defaultWriteTimeout)
|
||||
logger.Infof("shutting down remote write client and flushing remained %d series", len(wr.Timeseries))
|
||||
c.flush(lastCtx, wr)
|
||||
|
||||
logger.Infof("shutting down remote write client flushed %d series", shutdownFlushCnt)
|
||||
cancel()
|
||||
}
|
||||
c.wg.Add(1)
|
||||
@@ -203,6 +195,7 @@ var (
|
||||
sentRows = metrics.NewCounter(`vmalert_remotewrite_sent_rows_total`)
|
||||
sentBytes = metrics.NewCounter(`vmalert_remotewrite_sent_bytes_total`)
|
||||
droppedRows = metrics.NewCounter(`vmalert_remotewrite_dropped_rows_total`)
|
||||
droppedBytes = metrics.NewCounter(`vmalert_remotewrite_dropped_bytes_total`)
|
||||
sendDuration = metrics.NewFloatCounter(`vmalert_remotewrite_send_duration_seconds_total`)
|
||||
bufferFlushDuration = metrics.NewHistogram(`vmalert_remotewrite_flush_duration_seconds`)
|
||||
|
||||
@@ -218,10 +211,15 @@ func (c *Client) flush(ctx context.Context, wr *prompbmarshal.WriteRequest) {
|
||||
if len(wr.Timeseries) < 1 {
|
||||
return
|
||||
}
|
||||
defer wr.Reset()
|
||||
defer prompbmarshal.ResetWriteRequest(wr)
|
||||
defer bufferFlushDuration.UpdateDuration(time.Now())
|
||||
|
||||
data := wr.MarshalProtobuf(nil)
|
||||
data, err := wr.Marshal()
|
||||
if err != nil {
|
||||
logger.Errorf("failed to marshal WriteRequest: %s", err)
|
||||
return
|
||||
}
|
||||
|
||||
b := snappy.Encode(nil, data)
|
||||
|
||||
retryInterval, maxRetryInterval := *retryMinInterval, *retryMaxTime
|
||||
@@ -278,18 +276,15 @@ L:
|
||||
}
|
||||
|
||||
rwErrors.Inc()
|
||||
rows := 0
|
||||
for _, ts := range wr.Timeseries {
|
||||
rows += len(ts.Samples)
|
||||
}
|
||||
droppedRows.Add(rows)
|
||||
droppedRows.Add(len(wr.Timeseries))
|
||||
droppedBytes.Add(len(b))
|
||||
logger.Errorf("attempts to send remote-write request failed - dropping %d time series",
|
||||
len(wr.Timeseries))
|
||||
}
|
||||
|
||||
func (c *Client) send(ctx context.Context, data []byte) error {
|
||||
r := bytes.NewReader(data)
|
||||
req, err := http.NewRequestWithContext(ctx, http.MethodPost, c.addr, r)
|
||||
req, err := http.NewRequest(http.MethodPost, c.addr, r)
|
||||
if err != nil {
|
||||
return fmt.Errorf("failed to create new HTTP request: %w", err)
|
||||
}
|
||||
@@ -312,7 +307,7 @@ func (c *Client) send(ctx context.Context, data []byte) error {
|
||||
if !*disablePathAppend {
|
||||
req.URL.Path = path.Join(req.URL.Path, "/api/v1/write")
|
||||
}
|
||||
resp, err := c.c.Do(req)
|
||||
resp, err := c.c.Do(req.WithContext(ctx))
|
||||
if err != nil {
|
||||
return fmt.Errorf("error while sending request to %s: %w; Data len %d(%d)",
|
||||
req.URL.Redacted(), err, len(data), r.Size())
|
||||
|
||||
@@ -84,70 +84,6 @@ func TestClient_Push(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
func TestClient_run_maxBatchSizeDuringShutdown(t *testing.T) {
|
||||
batchSize := 20
|
||||
|
||||
testTable := []struct {
|
||||
name string // name of the test case
|
||||
pushCnt int // how many time series is pushed to the client
|
||||
batchCnt int // the expected batch count sent by the client
|
||||
}{
|
||||
{
|
||||
name: "pushCnt % batchSize == 0",
|
||||
pushCnt: batchSize * 40,
|
||||
batchCnt: 40,
|
||||
},
|
||||
{
|
||||
name: "pushCnt % batchSize != 0",
|
||||
pushCnt: batchSize*40 + 1,
|
||||
batchCnt: 40 + 1,
|
||||
},
|
||||
}
|
||||
|
||||
for _, tt := range testTable {
|
||||
t.Run(tt.name, func(t *testing.T) {
|
||||
// run new server
|
||||
bcServer := newBatchCntRWServer()
|
||||
|
||||
// run new client
|
||||
rwClient, err := NewClient(context.Background(), Config{
|
||||
MaxBatchSize: batchSize,
|
||||
|
||||
// Set everything to 1 to simplify the calculation.
|
||||
Concurrency: 1,
|
||||
MaxQueueSize: 1000,
|
||||
FlushInterval: time.Minute,
|
||||
|
||||
// batch count server
|
||||
Addr: bcServer.URL,
|
||||
})
|
||||
if err != nil {
|
||||
t.Fatalf("new remote write client failed, err: %v", err)
|
||||
}
|
||||
|
||||
// push time series to the client.
|
||||
for i := 0; i < tt.pushCnt; i++ {
|
||||
if err = rwClient.Push(prompbmarshal.TimeSeries{}); err != nil {
|
||||
t.Fatalf("push time series to the client failed, err: %v", err)
|
||||
}
|
||||
}
|
||||
|
||||
// close the client so the rest ts will be flushed in `shutdown`
|
||||
if err = rwClient.Close(); err != nil {
|
||||
t.Fatalf("shutdown client failed, err: %v", err)
|
||||
}
|
||||
|
||||
// finally check how many batches is sent.
|
||||
if tt.batchCnt != bcServer.acceptedBatches() {
|
||||
t.Errorf("client sent batch count incorrect, want: %d, get: %d", tt.batchCnt, bcServer.acceptedBatches())
|
||||
}
|
||||
if tt.pushCnt != bcServer.accepted() {
|
||||
t.Errorf("client sent time series count incorrect, want: %d, get: %d", tt.pushCnt, bcServer.accepted())
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
func newRWServer() *rwServer {
|
||||
rw := &rwServer{}
|
||||
rw.Server = httptest.NewServer(http.HandlerFunc(rw.handler))
|
||||
@@ -155,12 +91,14 @@ func newRWServer() *rwServer {
|
||||
}
|
||||
|
||||
type rwServer struct {
|
||||
acceptedRows atomic.Uint64
|
||||
// WARN: ordering of fields is important for alignment!
|
||||
// see https://golang.org/pkg/sync/atomic/#pkg-note-BUG
|
||||
acceptedRows uint64
|
||||
*httptest.Server
|
||||
}
|
||||
|
||||
func (rw *rwServer) accepted() int {
|
||||
return int(rw.acceptedRows.Load())
|
||||
return int(atomic.LoadUint64(&rw.acceptedRows))
|
||||
}
|
||||
|
||||
func (rw *rwServer) err(w http.ResponseWriter, err error) {
|
||||
@@ -202,11 +140,11 @@ func (rw *rwServer) handler(w http.ResponseWriter, r *http.Request) {
|
||||
return
|
||||
}
|
||||
wr := &prompb.WriteRequest{}
|
||||
if err := wr.UnmarshalProtobuf(b); err != nil {
|
||||
if err := wr.Unmarshal(b); err != nil {
|
||||
rw.err(w, fmt.Errorf("unmarhsal err: %w", err))
|
||||
return
|
||||
}
|
||||
rw.acceptedRows.Add(uint64(len(wr.Timeseries)))
|
||||
atomic.AddUint64(&rw.acceptedRows, uint64(len(wr.Timeseries)))
|
||||
w.WriteHeader(http.StatusNoContent)
|
||||
}
|
||||
|
||||
@@ -248,27 +186,3 @@ func (frw *faultyRWServer) handler(w http.ResponseWriter, r *http.Request) {
|
||||
w.Write([]byte("server overloaded"))
|
||||
}
|
||||
}
|
||||
|
||||
type batchCntRWServer struct {
|
||||
*rwServer
|
||||
|
||||
batchCnt atomic.Int64 // accepted batch count, which also equals to request count
|
||||
}
|
||||
|
||||
func newBatchCntRWServer() *batchCntRWServer {
|
||||
bc := &batchCntRWServer{
|
||||
rwServer: &rwServer{},
|
||||
}
|
||||
|
||||
bc.Server = httptest.NewServer(http.HandlerFunc(bc.handler))
|
||||
return bc
|
||||
}
|
||||
|
||||
func (bc *batchCntRWServer) handler(w http.ResponseWriter, r *http.Request) {
|
||||
bc.batchCnt.Add(1)
|
||||
bc.rwServer.handler(w, r)
|
||||
}
|
||||
|
||||
func (bc *batchCntRWServer) acceptedBatches() int {
|
||||
return int(bc.batchCnt.Load())
|
||||
}
|
||||
|
||||
@@ -11,7 +11,7 @@ import (
|
||||
|
||||
"github.com/golang/snappy"
|
||||
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/httputils"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/utils"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
|
||||
)
|
||||
|
||||
@@ -30,7 +30,7 @@ func NewDebugClient() (*DebugClient, error) {
|
||||
return nil, nil
|
||||
}
|
||||
|
||||
t, err := httputils.Transport(*addr, *tlsCertFile, *tlsKeyFile, *tlsCAFile, *tlsServerName, *tlsInsecureSkipVerify)
|
||||
t, err := utils.Transport(*addr, *tlsCertFile, *tlsKeyFile, *tlsCAFile, *tlsServerName, *tlsInsecureSkipVerify)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("failed to create transport: %w", err)
|
||||
}
|
||||
@@ -49,7 +49,10 @@ func (c *DebugClient) Push(s prompbmarshal.TimeSeries) error {
|
||||
c.wg.Add(1)
|
||||
defer c.wg.Done()
|
||||
wr := &prompbmarshal.WriteRequest{Timeseries: []prompbmarshal.TimeSeries{s}}
|
||||
data := wr.MarshalProtobuf(nil)
|
||||
data, err := wr.Marshal()
|
||||
if err != nil {
|
||||
return fmt.Errorf("failed to marshal the given time series: %w", err)
|
||||
}
|
||||
|
||||
return c.send(data)
|
||||
}
|
||||
|
||||
@@ -8,7 +8,6 @@ import (
|
||||
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/utils"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/httputils"
|
||||
)
|
||||
|
||||
var (
|
||||
@@ -42,13 +41,11 @@ var (
|
||||
tlsServerName = flag.String("remoteWrite.tlsServerName", "", "Optional TLS server name to use for connections to -remoteWrite.url. "+
|
||||
"By default, the server name from -remoteWrite.url is used")
|
||||
|
||||
oauth2ClientID = flag.String("remoteWrite.oauth2.clientID", "", "Optional OAuth2 clientID to use for -remoteWrite.url")
|
||||
oauth2ClientSecret = flag.String("remoteWrite.oauth2.clientSecret", "", "Optional OAuth2 clientSecret to use for -remoteWrite.url")
|
||||
oauth2ClientSecretFile = flag.String("remoteWrite.oauth2.clientSecretFile", "", "Optional OAuth2 clientSecretFile to use for -remoteWrite.url")
|
||||
oauth2EndpointParams = flag.String("remoteWrite.oauth2.endpointParams", "", "Optional OAuth2 endpoint parameters to use for -remoteWrite.url . "+
|
||||
`The endpoint parameters must be set in JSON format: {"param1":"value1",...,"paramN":"valueN"}`)
|
||||
oauth2TokenURL = flag.String("remoteWrite.oauth2.tokenUrl", "", "Optional OAuth2 tokenURL to use for -notifier.url.")
|
||||
oauth2Scopes = flag.String("remoteWrite.oauth2.scopes", "", "Optional OAuth2 scopes to use for -notifier.url. Scopes must be delimited by ';'.")
|
||||
oauth2ClientID = flag.String("remoteWrite.oauth2.clientID", "", "Optional OAuth2 clientID to use for -remoteWrite.url.")
|
||||
oauth2ClientSecret = flag.String("remoteWrite.oauth2.clientSecret", "", "Optional OAuth2 clientSecret to use for -remoteWrite.url.")
|
||||
oauth2ClientSecretFile = flag.String("remoteWrite.oauth2.clientSecretFile", "", "Optional OAuth2 clientSecretFile to use for -remoteWrite.url.")
|
||||
oauth2TokenURL = flag.String("remoteWrite.oauth2.tokenUrl", "", "Optional OAuth2 tokenURL to use for -notifier.url.")
|
||||
oauth2Scopes = flag.String("remoteWrite.oauth2.scopes", "", "Optional OAuth2 scopes to use for -notifier.url. Scopes must be delimited by ';'.")
|
||||
)
|
||||
|
||||
// InitSecretFlags must be called after flag.Parse and before any logging
|
||||
@@ -65,19 +62,15 @@ func Init(ctx context.Context) (*Client, error) {
|
||||
return nil, nil
|
||||
}
|
||||
|
||||
t, err := httputils.Transport(*addr, *tlsCertFile, *tlsKeyFile, *tlsCAFile, *tlsServerName, *tlsInsecureSkipVerify)
|
||||
t, err := utils.Transport(*addr, *tlsCertFile, *tlsKeyFile, *tlsCAFile, *tlsServerName, *tlsInsecureSkipVerify)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("failed to create transport: %w", err)
|
||||
}
|
||||
|
||||
endpointParams, err := flagutil.ParseJSONMap(*oauth2EndpointParams)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("cannot parse JSON for -remoteWrite.oauth2.endpointParams=%s: %w", *oauth2EndpointParams, err)
|
||||
}
|
||||
authCfg, err := utils.AuthConfig(
|
||||
utils.WithBasicAuth(*basicAuthUsername, *basicAuthPassword, *basicAuthPasswordFile),
|
||||
utils.WithBearer(*bearerToken, *bearerTokenFile),
|
||||
utils.WithOAuth(*oauth2ClientID, *oauth2ClientSecret, *oauth2ClientSecretFile, *oauth2TokenURL, *oauth2Scopes, endpointParams),
|
||||
utils.WithOAuth(*oauth2ClientID, *oauth2ClientSecret, *oauth2ClientSecretFile, *oauth2TokenURL, *oauth2Scopes),
|
||||
utils.WithHeaders(*headers))
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("failed to configure auth: %w", err)
|
||||
|
||||
@@ -30,7 +30,6 @@ type AlertingRule struct {
|
||||
Annotations map[string]string
|
||||
GroupID uint64
|
||||
GroupName string
|
||||
File string
|
||||
EvalInterval time.Duration
|
||||
Debug bool
|
||||
|
||||
@@ -48,7 +47,7 @@ type AlertingRule struct {
|
||||
}
|
||||
|
||||
type alertingRuleMetrics struct {
|
||||
errors *utils.Counter
|
||||
errors *utils.Gauge
|
||||
pending *utils.Gauge
|
||||
active *utils.Gauge
|
||||
samples *utils.Gauge
|
||||
@@ -68,7 +67,6 @@ func NewAlertingRule(qb datasource.QuerierBuilder, group *Group, cfg config.Rule
|
||||
Annotations: cfg.Annotations,
|
||||
GroupID: group.ID(),
|
||||
GroupName: group.Name,
|
||||
File: group.File,
|
||||
EvalInterval: group.Interval,
|
||||
Debug: cfg.Debug,
|
||||
q: qb.BuildWithParams(datasource.QuerierParams{
|
||||
@@ -118,7 +116,14 @@ func NewAlertingRule(qb datasource.QuerierBuilder, group *Group, cfg config.Rule
|
||||
}
|
||||
return float64(num)
|
||||
})
|
||||
ar.metrics.errors = utils.GetOrCreateCounter(fmt.Sprintf(`vmalert_alerting_rules_errors_total{%s}`, labels))
|
||||
ar.metrics.errors = utils.GetOrCreateGauge(fmt.Sprintf(`vmalert_alerting_rules_error{%s}`, labels),
|
||||
func() float64 {
|
||||
e := ar.state.getLast()
|
||||
if e.Err == nil {
|
||||
return 0
|
||||
}
|
||||
return 1
|
||||
})
|
||||
ar.metrics.samples = utils.GetOrCreateGauge(fmt.Sprintf(`vmalert_alerting_rules_last_evaluation_samples{%s}`, labels),
|
||||
func() float64 {
|
||||
e := ar.state.getLast()
|
||||
@@ -237,30 +242,11 @@ type labelSet struct {
|
||||
origin map[string]string
|
||||
// processed labels includes origin labels
|
||||
// plus extra labels (group labels, service labels like alertNameLabel).
|
||||
// in case of key conflicts, origin labels are renamed with prefix `exported_` and extra labels are preferred.
|
||||
// see https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5161
|
||||
// in case of conflicts, extra labels are preferred.
|
||||
// used as labels attached to notifier.Alert and ALERTS series written to remote storage.
|
||||
processed map[string]string
|
||||
}
|
||||
|
||||
// add adds a value v with key k to origin and processed label sets.
|
||||
// On k conflicts in processed set, the passed v is preferred.
|
||||
// On k conflicts in origin set, the original value is preferred and copied
|
||||
// to processed with `exported_%k` key. The copy happens only if passed v isn't equal to origin[k] value.
|
||||
func (ls *labelSet) add(k, v string) {
|
||||
ls.processed[k] = v
|
||||
ov, ok := ls.origin[k]
|
||||
if !ok {
|
||||
ls.origin[k] = v
|
||||
return
|
||||
}
|
||||
if ov != v {
|
||||
// copy value only if v and ov are different
|
||||
key := fmt.Sprintf("exported_%s", k)
|
||||
ls.processed[key] = ov
|
||||
}
|
||||
}
|
||||
|
||||
// toLabels converts labels from given Metric
|
||||
// to labelSet which contains original and processed labels.
|
||||
func (ar *AlertingRule) toLabels(m datasource.Metric, qFn templates.QueryFn) (*labelSet, error) {
|
||||
@@ -286,14 +272,24 @@ func (ar *AlertingRule) toLabels(m datasource.Metric, qFn templates.QueryFn) (*l
|
||||
return nil, fmt.Errorf("failed to expand labels: %w", err)
|
||||
}
|
||||
for k, v := range extraLabels {
|
||||
ls.add(k, v)
|
||||
ls.processed[k] = v
|
||||
if _, ok := ls.origin[k]; !ok {
|
||||
ls.origin[k] = v
|
||||
}
|
||||
}
|
||||
|
||||
// set additional labels to identify group and rule name
|
||||
if ar.Name != "" {
|
||||
ls.add(alertNameLabel, ar.Name)
|
||||
ls.processed[alertNameLabel] = ar.Name
|
||||
if _, ok := ls.origin[alertNameLabel]; !ok {
|
||||
ls.origin[alertNameLabel] = ar.Name
|
||||
}
|
||||
}
|
||||
if !*disableAlertGroupLabel && ar.GroupName != "" {
|
||||
ls.add(alertGroupNameLabel, ar.GroupName)
|
||||
ls.processed[alertGroupNameLabel] = ar.GroupName
|
||||
if _, ok := ls.origin[alertGroupNameLabel]; !ok {
|
||||
ls.origin[alertGroupNameLabel] = ar.GroupName
|
||||
}
|
||||
}
|
||||
return ls, nil
|
||||
}
|
||||
@@ -310,7 +306,7 @@ func (ar *AlertingRule) execRange(ctx context.Context, start, end time.Time) ([]
|
||||
}
|
||||
var result []prompbmarshal.TimeSeries
|
||||
holdAlertState := make(map[uint64]*notifier.Alert)
|
||||
qFn := func(_ string) ([]datasource.Metric, error) {
|
||||
qFn := func(query string) ([]datasource.Metric, error) {
|
||||
return nil, fmt.Errorf("`query` template isn't supported in replay mode")
|
||||
}
|
||||
for _, s := range res.Data {
|
||||
@@ -324,6 +320,16 @@ func (ar *AlertingRule) execRange(ctx context.Context, start, end time.Time) ([]
|
||||
return nil, fmt.Errorf("failed to create alert: %w", err)
|
||||
}
|
||||
|
||||
// if alert is instant, For: 0
|
||||
if ar.For == 0 {
|
||||
a.State = notifier.StateFiring
|
||||
for i := range s.Values {
|
||||
result = append(result, ar.alertToTimeSeries(a, s.Timestamps[i])...)
|
||||
}
|
||||
continue
|
||||
}
|
||||
|
||||
// if alert with For > 0
|
||||
prevT := time.Time{}
|
||||
for i := range s.Values {
|
||||
at := time.Unix(s.Timestamps[i], 0)
|
||||
@@ -344,10 +350,6 @@ func (ar *AlertingRule) execRange(ctx context.Context, start, end time.Time) ([]
|
||||
a.Start = at
|
||||
}
|
||||
prevT = at
|
||||
if ar.For == 0 {
|
||||
// rules with `for: 0` are always firing when they have Value
|
||||
a.State = notifier.StateFiring
|
||||
}
|
||||
result = append(result, ar.alertToTimeSeries(a, s.Timestamps[i])...)
|
||||
|
||||
// save alert's state on last iteration, so it can be used on the next execRange call
|
||||
@@ -381,9 +383,6 @@ func (ar *AlertingRule) exec(ctx context.Context, ts time.Time, limit int) ([]pr
|
||||
|
||||
defer func() {
|
||||
ar.state.add(curState)
|
||||
if curState.Err != nil {
|
||||
ar.metrics.errors.Inc()
|
||||
}
|
||||
}()
|
||||
|
||||
ar.alertsMu.Lock()
|
||||
@@ -417,7 +416,8 @@ func (ar *AlertingRule) exec(ctx context.Context, ts time.Time, limit int) ([]pr
|
||||
}
|
||||
h := hash(ls.processed)
|
||||
if _, ok := updated[h]; ok {
|
||||
// duplicate may be caused the removal of `__name__` label
|
||||
// duplicate may be caused by extra labels
|
||||
// conflicting with the metric labels
|
||||
curState.Err = fmt.Errorf("labels %v: %w", ls.processed, errDuplicate)
|
||||
return nil, curState.Err
|
||||
}
|
||||
@@ -440,13 +440,14 @@ func (ar *AlertingRule) exec(ctx context.Context, ts time.Time, limit int) ([]pr
|
||||
a.KeepFiringSince = time.Time{}
|
||||
continue
|
||||
}
|
||||
a, err := ar.newAlert(m, ls, ts, qFn)
|
||||
a, err := ar.newAlert(m, ls, start, qFn)
|
||||
if err != nil {
|
||||
curState.Err = fmt.Errorf("failed to create alert: %w", err)
|
||||
return nil, curState.Err
|
||||
}
|
||||
a.ID = h
|
||||
a.State = notifier.StatePending
|
||||
a.ActiveAt = ts
|
||||
ar.alerts[h] = a
|
||||
ar.logDebugf(ts, a, "created in state PENDING")
|
||||
}
|
||||
@@ -472,7 +473,7 @@ func (ar *AlertingRule) exec(ctx context.Context, ts time.Time, limit int) ([]pr
|
||||
}
|
||||
// alerts with ar.KeepFiringFor>0 may remain FIRING
|
||||
// even if their expression isn't true anymore
|
||||
if ts.Sub(a.KeepFiringSince) >= ar.KeepFiringFor {
|
||||
if ts.Sub(a.KeepFiringSince) > ar.KeepFiringFor {
|
||||
a.State = notifier.StateInactive
|
||||
a.ResolvedAt = ts
|
||||
ar.logDebugf(ts, a, "FIRING => INACTIVE: is absent in current evaluation round")
|
||||
@@ -552,9 +553,9 @@ func (ar *AlertingRule) newAlert(m datasource.Metric, ls *labelSet, start time.T
|
||||
}
|
||||
|
||||
const (
|
||||
// alertMetricName is the metric name for time series reflecting the alert state.
|
||||
// alertMetricName is the metric name for synthetic alert timeseries.
|
||||
alertMetricName = "ALERTS"
|
||||
// alertForStateMetricName is the metric name for time series reflecting the moment of time when alert became active.
|
||||
// alertForStateMetricName is the metric name for 'for' state of alert.
|
||||
alertForStateMetricName = "ALERTS_FOR_STATE"
|
||||
|
||||
// alertNameLabel is the label name indicating the name of an alert.
|
||||
@@ -569,10 +570,12 @@ const (
|
||||
|
||||
// alertToTimeSeries converts the given alert with the given timestamp to time series
|
||||
func (ar *AlertingRule) alertToTimeSeries(a *notifier.Alert, timestamp int64) []prompbmarshal.TimeSeries {
|
||||
return []prompbmarshal.TimeSeries{
|
||||
alertToTimeSeries(a, timestamp),
|
||||
alertForToTimeSeries(a, timestamp),
|
||||
var tss []prompbmarshal.TimeSeries
|
||||
tss = append(tss, alertToTimeSeries(a, timestamp))
|
||||
if ar.For > 0 {
|
||||
tss = append(tss, alertForToTimeSeries(a, timestamp))
|
||||
}
|
||||
return tss
|
||||
}
|
||||
|
||||
func alertToTimeSeries(a *notifier.Alert, timestamp int64) prompbmarshal.TimeSeries {
|
||||
@@ -655,19 +658,15 @@ func (ar *AlertingRule) restore(ctx context.Context, q datasource.Querier, ts ti
|
||||
// alertsToSend walks through the current alerts of AlertingRule
|
||||
// and returns only those which should be sent to notifier.
|
||||
// Isn't concurrent safe.
|
||||
func (ar *AlertingRule) alertsToSend(resolveDuration, resendDelay time.Duration) []notifier.Alert {
|
||||
currentTime := time.Now()
|
||||
func (ar *AlertingRule) alertsToSend(ts time.Time, resolveDuration, resendDelay time.Duration) []notifier.Alert {
|
||||
needsSending := func(a *notifier.Alert) bool {
|
||||
if a.State == notifier.StatePending {
|
||||
return false
|
||||
}
|
||||
if a.State == notifier.StateFiring && a.End.Before(a.LastSent) {
|
||||
if a.ResolvedAt.After(a.LastSent) {
|
||||
return true
|
||||
}
|
||||
if a.State == notifier.StateInactive && a.ResolvedAt.After(a.LastSent) {
|
||||
return true
|
||||
}
|
||||
return a.LastSent.Add(resendDelay).Before(currentTime)
|
||||
return a.LastSent.Add(resendDelay).Before(ts)
|
||||
}
|
||||
|
||||
var alerts []notifier.Alert
|
||||
@@ -675,11 +674,11 @@ func (ar *AlertingRule) alertsToSend(resolveDuration, resendDelay time.Duration)
|
||||
if !needsSending(a) {
|
||||
continue
|
||||
}
|
||||
a.End = currentTime.Add(resolveDuration)
|
||||
a.End = ts.Add(resolveDuration)
|
||||
if a.State == notifier.StateInactive {
|
||||
a.End = a.ResolvedAt
|
||||
}
|
||||
a.LastSent = currentTime
|
||||
a.LastSent = ts
|
||||
alerts = append(alerts, *a)
|
||||
}
|
||||
return alerts
|
||||
|
||||
@@ -3,7 +3,6 @@ package rule
|
||||
import (
|
||||
"context"
|
||||
"errors"
|
||||
"fmt"
|
||||
"reflect"
|
||||
"sort"
|
||||
"strings"
|
||||
@@ -14,7 +13,6 @@ import (
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/config"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/datasource"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/notifier"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/utils"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promutils"
|
||||
)
|
||||
@@ -28,28 +26,20 @@ func TestAlertingRule_ToTimeSeries(t *testing.T) {
|
||||
}{
|
||||
{
|
||||
newTestAlertingRule("instant", 0),
|
||||
¬ifier.Alert{State: notifier.StateFiring, ActiveAt: timestamp.Add(time.Second)},
|
||||
¬ifier.Alert{State: notifier.StateFiring},
|
||||
[]prompbmarshal.TimeSeries{
|
||||
newTimeSeries([]float64{1}, []int64{timestamp.UnixNano()}, map[string]string{
|
||||
"__name__": alertMetricName,
|
||||
alertStateLabel: notifier.StateFiring.String(),
|
||||
}),
|
||||
newTimeSeries([]float64{float64(timestamp.Add(time.Second).Unix())},
|
||||
[]int64{timestamp.UnixNano()},
|
||||
map[string]string{
|
||||
"__name__": alertForStateMetricName,
|
||||
}),
|
||||
},
|
||||
},
|
||||
{
|
||||
newTestAlertingRule("instant extra labels", 0),
|
||||
¬ifier.Alert{
|
||||
State: notifier.StateFiring, ActiveAt: timestamp.Add(time.Second),
|
||||
Labels: map[string]string{
|
||||
"job": "foo",
|
||||
"instance": "bar",
|
||||
},
|
||||
},
|
||||
¬ifier.Alert{State: notifier.StateFiring, Labels: map[string]string{
|
||||
"job": "foo",
|
||||
"instance": "bar",
|
||||
}},
|
||||
[]prompbmarshal.TimeSeries{
|
||||
newTimeSeries([]float64{1}, []int64{timestamp.UnixNano()}, map[string]string{
|
||||
"__name__": alertMetricName,
|
||||
@@ -57,35 +47,19 @@ func TestAlertingRule_ToTimeSeries(t *testing.T) {
|
||||
"job": "foo",
|
||||
"instance": "bar",
|
||||
}),
|
||||
newTimeSeries([]float64{float64(timestamp.Add(time.Second).Unix())},
|
||||
[]int64{timestamp.UnixNano()},
|
||||
map[string]string{
|
||||
"__name__": alertForStateMetricName,
|
||||
"job": "foo",
|
||||
"instance": "bar",
|
||||
}),
|
||||
},
|
||||
},
|
||||
{
|
||||
newTestAlertingRule("instant labels override", 0),
|
||||
¬ifier.Alert{
|
||||
State: notifier.StateFiring, ActiveAt: timestamp.Add(time.Second),
|
||||
Labels: map[string]string{
|
||||
alertStateLabel: "foo",
|
||||
"__name__": "bar",
|
||||
},
|
||||
},
|
||||
¬ifier.Alert{State: notifier.StateFiring, Labels: map[string]string{
|
||||
alertStateLabel: "foo",
|
||||
"__name__": "bar",
|
||||
}},
|
||||
[]prompbmarshal.TimeSeries{
|
||||
newTimeSeries([]float64{1}, []int64{timestamp.UnixNano()}, map[string]string{
|
||||
"__name__": alertMetricName,
|
||||
alertStateLabel: notifier.StateFiring.String(),
|
||||
}),
|
||||
newTimeSeries([]float64{float64(timestamp.Add(time.Second).Unix())},
|
||||
[]int64{timestamp.UnixNano()},
|
||||
map[string]string{
|
||||
"__name__": alertForStateMetricName,
|
||||
alertStateLabel: "foo",
|
||||
}),
|
||||
},
|
||||
},
|
||||
{
|
||||
@@ -332,17 +306,14 @@ func TestAlertingRule_Exec(t *testing.T) {
|
||||
fq := &datasource.FakeQuerier{}
|
||||
tc.rule.q = fq
|
||||
tc.rule.GroupID = fakeGroup.ID()
|
||||
ts := time.Now()
|
||||
for i, step := range tc.steps {
|
||||
fq.Reset()
|
||||
fq.Add(step...)
|
||||
if _, err := tc.rule.exec(context.TODO(), ts, 0); err != nil {
|
||||
if _, err := tc.rule.exec(context.TODO(), time.Now(), 0); err != nil {
|
||||
t.Fatalf("unexpected err: %s", err)
|
||||
}
|
||||
|
||||
// shift the execution timestamp before the next iteration
|
||||
ts = ts.Add(defaultStep)
|
||||
|
||||
// artificial delay between applying steps
|
||||
time.Sleep(defaultStep)
|
||||
if _, ok := tc.expAlerts[i]; !ok {
|
||||
continue
|
||||
}
|
||||
@@ -394,7 +365,7 @@ func TestAlertingRule_ExecRange(t *testing.T) {
|
||||
{Values: []float64{1}, Timestamps: []int64{1}},
|
||||
},
|
||||
[]*notifier.Alert{
|
||||
{State: notifier.StateFiring, ActiveAt: time.Unix(1, 0)},
|
||||
{State: notifier.StateFiring},
|
||||
},
|
||||
nil,
|
||||
},
|
||||
@@ -405,9 +376,8 @@ func TestAlertingRule_ExecRange(t *testing.T) {
|
||||
},
|
||||
[]*notifier.Alert{
|
||||
{
|
||||
Labels: map[string]string{"name": "foo"},
|
||||
State: notifier.StateFiring,
|
||||
ActiveAt: time.Unix(1, 0),
|
||||
Labels: map[string]string{"name": "foo"},
|
||||
State: notifier.StateFiring,
|
||||
},
|
||||
},
|
||||
nil,
|
||||
@@ -418,9 +388,9 @@ func TestAlertingRule_ExecRange(t *testing.T) {
|
||||
{Values: []float64{1, 1, 1}, Timestamps: []int64{1e3, 2e3, 3e3}},
|
||||
},
|
||||
[]*notifier.Alert{
|
||||
{State: notifier.StateFiring, ActiveAt: time.Unix(1e3, 0)},
|
||||
{State: notifier.StateFiring, ActiveAt: time.Unix(2e3, 0)},
|
||||
{State: notifier.StateFiring, ActiveAt: time.Unix(3e3, 0)},
|
||||
{State: notifier.StateFiring},
|
||||
{State: notifier.StateFiring},
|
||||
{State: notifier.StateFiring},
|
||||
},
|
||||
nil,
|
||||
},
|
||||
@@ -488,20 +458,6 @@ func TestAlertingRule_ExecRange(t *testing.T) {
|
||||
For: time.Second,
|
||||
}},
|
||||
},
|
||||
{
|
||||
newTestAlertingRuleWithEvalInterval("firing=>inactive=>inactive=>firing=>firing", 0, time.Second),
|
||||
[]datasource.Metric{
|
||||
{Values: []float64{1, 1, 1, 1}, Timestamps: []int64{1, 4, 5, 6}},
|
||||
},
|
||||
[]*notifier.Alert{
|
||||
{State: notifier.StateFiring, ActiveAt: time.Unix(1, 0)},
|
||||
// It is expected for ActiveAT to remain the same while rule continues to fire in each iteration
|
||||
{State: notifier.StateFiring, ActiveAt: time.Unix(4, 0)},
|
||||
{State: notifier.StateFiring, ActiveAt: time.Unix(4, 0)},
|
||||
{State: notifier.StateFiring, ActiveAt: time.Unix(4, 0)},
|
||||
},
|
||||
nil,
|
||||
},
|
||||
{
|
||||
newTestAlertingRule("for=>pending=>firing=>pending=>firing=>pending", time.Second),
|
||||
[]datasource.Metric{
|
||||
@@ -576,33 +532,21 @@ func TestAlertingRule_ExecRange(t *testing.T) {
|
||||
},
|
||||
},
|
||||
[]*notifier.Alert{
|
||||
{
|
||||
State: notifier.StateFiring, ActiveAt: time.Unix(1, 0),
|
||||
Labels: map[string]string{
|
||||
"source": "vm",
|
||||
},
|
||||
},
|
||||
{
|
||||
State: notifier.StateFiring, ActiveAt: time.Unix(100, 0),
|
||||
Labels: map[string]string{
|
||||
"source": "vm",
|
||||
},
|
||||
},
|
||||
{State: notifier.StateFiring, Labels: map[string]string{
|
||||
"source": "vm",
|
||||
}},
|
||||
{State: notifier.StateFiring, Labels: map[string]string{
|
||||
"source": "vm",
|
||||
}},
|
||||
//
|
||||
{
|
||||
State: notifier.StateFiring, ActiveAt: time.Unix(1, 0),
|
||||
Labels: map[string]string{
|
||||
"foo": "bar",
|
||||
"source": "vm",
|
||||
},
|
||||
},
|
||||
{
|
||||
State: notifier.StateFiring, ActiveAt: time.Unix(5, 0),
|
||||
Labels: map[string]string{
|
||||
"foo": "bar",
|
||||
"source": "vm",
|
||||
},
|
||||
},
|
||||
{State: notifier.StateFiring, Labels: map[string]string{
|
||||
"foo": "bar",
|
||||
"source": "vm",
|
||||
}},
|
||||
{State: notifier.StateFiring, Labels: map[string]string{
|
||||
"foo": "bar",
|
||||
"source": "vm",
|
||||
}},
|
||||
},
|
||||
nil,
|
||||
},
|
||||
@@ -822,16 +766,14 @@ func TestAlertingRule_Exec_Negative(t *testing.T) {
|
||||
ar.q = fq
|
||||
|
||||
// successful attempt
|
||||
// label `job` will be overridden by rule extra label, the original value will be reserved by "exported_job"
|
||||
fq.Add(metricWithValueAndLabels(t, 1, "__name__", "foo", "job", "bar"))
|
||||
fq.Add(metricWithValueAndLabels(t, 1, "__name__", "foo", "job", "baz"))
|
||||
_, err := ar.exec(context.TODO(), time.Now(), 0)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
// label `__name__` will be omitted and get duplicated results here
|
||||
fq.Add(metricWithValueAndLabels(t, 1, "__name__", "foo_1", "job", "bar"))
|
||||
// label `job` will collide with rule extra label and will make both time series equal
|
||||
fq.Add(metricWithValueAndLabels(t, 1, "__name__", "foo", "job", "baz"))
|
||||
_, err = ar.exec(context.TODO(), time.Now(), 0)
|
||||
if !errors.Is(err, errDuplicate) {
|
||||
t.Fatalf("expected to have %s error; got %s", errDuplicate, err)
|
||||
@@ -955,22 +897,20 @@ func TestAlertingRule_Template(t *testing.T) {
|
||||
metricWithValueAndLabels(t, 10, "__name__", "second", "instance", "bar", alertNameLabel, "override"),
|
||||
},
|
||||
map[uint64]*notifier.Alert{
|
||||
hash(map[string]string{alertNameLabel: "override label", "exported_alertname": "override", "instance": "foo"}): {
|
||||
hash(map[string]string{alertNameLabel: "override label", "instance": "foo"}): {
|
||||
Labels: map[string]string{
|
||||
alertNameLabel: "override label",
|
||||
"exported_alertname": "override",
|
||||
"instance": "foo",
|
||||
alertNameLabel: "override label",
|
||||
"instance": "foo",
|
||||
},
|
||||
Annotations: map[string]string{
|
||||
"summary": `first: Too high connection number for "foo"`,
|
||||
"description": `override: It is 2 connections for "foo"`,
|
||||
},
|
||||
},
|
||||
hash(map[string]string{alertNameLabel: "override label", "exported_alertname": "override", "instance": "bar"}): {
|
||||
hash(map[string]string{alertNameLabel: "override label", "instance": "bar"}): {
|
||||
Labels: map[string]string{
|
||||
alertNameLabel: "override label",
|
||||
"exported_alertname": "override",
|
||||
"instance": "bar",
|
||||
alertNameLabel: "override label",
|
||||
"instance": "bar",
|
||||
},
|
||||
Annotations: map[string]string{
|
||||
"summary": `second: Too high connection number for "bar"`,
|
||||
@@ -999,18 +939,14 @@ func TestAlertingRule_Template(t *testing.T) {
|
||||
},
|
||||
map[uint64]*notifier.Alert{
|
||||
hash(map[string]string{
|
||||
alertNameLabel: "OriginLabels",
|
||||
"exported_alertname": "originAlertname",
|
||||
alertGroupNameLabel: "Testing",
|
||||
"exported_alertgroup": "originGroupname",
|
||||
"instance": "foo",
|
||||
alertNameLabel: "OriginLabels",
|
||||
alertGroupNameLabel: "Testing",
|
||||
"instance": "foo",
|
||||
}): {
|
||||
Labels: map[string]string{
|
||||
alertNameLabel: "OriginLabels",
|
||||
"exported_alertname": "originAlertname",
|
||||
alertGroupNameLabel: "Testing",
|
||||
"exported_alertgroup": "originGroupname",
|
||||
"instance": "foo",
|
||||
alertNameLabel: "OriginLabels",
|
||||
alertGroupNameLabel: "Testing",
|
||||
"instance": "foo",
|
||||
},
|
||||
Annotations: map[string]string{
|
||||
"summary": `Alert "originAlertname(originGroupname)" for instance foo`,
|
||||
@@ -1054,7 +990,7 @@ func TestAlertsToSend(t *testing.T) {
|
||||
for i, a := range alerts {
|
||||
ar.alerts[uint64(i)] = a
|
||||
}
|
||||
gotAlerts := ar.alertsToSend(resolveDuration, resendDelay)
|
||||
gotAlerts := ar.alertsToSend(ts, resolveDuration, resendDelay)
|
||||
if gotAlerts == nil && expAlerts == nil {
|
||||
return
|
||||
}
|
||||
@@ -1070,36 +1006,60 @@ func TestAlertsToSend(t *testing.T) {
|
||||
})
|
||||
for i, exp := range expAlerts {
|
||||
got := gotAlerts[i]
|
||||
if got.Name != exp.Name {
|
||||
t.Fatalf("expected Name to be %v; got %v", exp.Name, got.Name)
|
||||
if got.LastSent != exp.LastSent {
|
||||
t.Fatalf("expected LastSent to be %v; got %v", exp.LastSent, got.LastSent)
|
||||
}
|
||||
if got.End != exp.End {
|
||||
t.Fatalf("expected End to be %v; got %v", exp.End, got.End)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
f( // check if firing alerts need to be sent with non-zero resendDelay
|
||||
[]*notifier.Alert{
|
||||
{Name: "a", State: notifier.StateFiring, Start: ts},
|
||||
// no need to resend firing
|
||||
{Name: "b", State: notifier.StateFiring, Start: ts, LastSent: ts.Add(-30 * time.Second), End: ts.Add(5 * time.Minute)},
|
||||
// last message is for resolved, send firing message this time
|
||||
{Name: "c", State: notifier.StateFiring, Start: ts, LastSent: ts.Add(-30 * time.Second), End: ts.Add(-1 * time.Minute)},
|
||||
// resend firing
|
||||
{Name: "d", State: notifier.StateFiring, Start: ts, LastSent: ts.Add(-1 * time.Minute)},
|
||||
},
|
||||
[]*notifier.Alert{{Name: "a"}, {Name: "c"}, {Name: "d"}},
|
||||
f( // send firing alert with custom resolve time
|
||||
[]*notifier.Alert{{State: notifier.StateFiring}},
|
||||
[]*notifier.Alert{{LastSent: ts, End: ts.Add(5 * time.Minute)}},
|
||||
5*time.Minute, time.Minute,
|
||||
)
|
||||
f( // check if resolved alerts need to be sent with non-zero resendDelay
|
||||
[]*notifier.Alert{
|
||||
{Name: "a", State: notifier.StateInactive, ResolvedAt: ts, LastSent: ts.Add(-30 * time.Second)},
|
||||
// no need to resend resolved
|
||||
{Name: "b", State: notifier.StateInactive, ResolvedAt: ts, LastSent: ts},
|
||||
// resend resolved
|
||||
{Name: "c", State: notifier.StateInactive, ResolvedAt: ts.Add(-1 * time.Minute), LastSent: ts.Add(-1 * time.Minute)},
|
||||
},
|
||||
[]*notifier.Alert{{Name: "a"}, {Name: "c"}},
|
||||
f( // resolve inactive alert at the current timestamp
|
||||
[]*notifier.Alert{{State: notifier.StateInactive, ResolvedAt: ts}},
|
||||
[]*notifier.Alert{{LastSent: ts, End: ts}},
|
||||
time.Minute, time.Minute,
|
||||
)
|
||||
f( // mixed case of firing and resolved alerts. Names are added for deterministic sorting
|
||||
[]*notifier.Alert{{Name: "a", State: notifier.StateFiring}, {Name: "b", State: notifier.StateInactive, ResolvedAt: ts}},
|
||||
[]*notifier.Alert{{Name: "a", LastSent: ts, End: ts.Add(5 * time.Minute)}, {Name: "b", LastSent: ts, End: ts}},
|
||||
5*time.Minute, time.Minute,
|
||||
)
|
||||
f( // mixed case of pending and resolved alerts. Names are added for deterministic sorting
|
||||
[]*notifier.Alert{{Name: "a", State: notifier.StatePending}, {Name: "b", State: notifier.StateInactive, ResolvedAt: ts}},
|
||||
[]*notifier.Alert{{Name: "b", LastSent: ts, End: ts}},
|
||||
5*time.Minute, time.Minute,
|
||||
)
|
||||
f( // attempt to send alert that was already sent in the resendDelay interval
|
||||
[]*notifier.Alert{{State: notifier.StateFiring, LastSent: ts.Add(-time.Second)}},
|
||||
nil,
|
||||
time.Minute, time.Minute,
|
||||
)
|
||||
f( // attempt to send alert that was sent out of the resendDelay interval
|
||||
[]*notifier.Alert{{State: notifier.StateFiring, LastSent: ts.Add(-2 * time.Minute)}},
|
||||
[]*notifier.Alert{{LastSent: ts, End: ts.Add(time.Minute)}},
|
||||
time.Minute, time.Minute,
|
||||
)
|
||||
f( // alert must be sent even if resendDelay interval is 0
|
||||
[]*notifier.Alert{{State: notifier.StateFiring, LastSent: ts.Add(-time.Second)}},
|
||||
[]*notifier.Alert{{LastSent: ts, End: ts.Add(time.Minute)}},
|
||||
time.Minute, 0,
|
||||
)
|
||||
f( // inactive alert which has been sent already
|
||||
[]*notifier.Alert{{State: notifier.StateInactive, LastSent: ts.Add(-time.Second), ResolvedAt: ts.Add(-2 * time.Second)}},
|
||||
nil,
|
||||
time.Minute, time.Minute,
|
||||
)
|
||||
f( // inactive alert which has been resolved after last send
|
||||
[]*notifier.Alert{{State: notifier.StateInactive, LastSent: ts.Add(-time.Second), ResolvedAt: ts}},
|
||||
[]*notifier.Alert{{LastSent: ts, End: ts}},
|
||||
time.Minute, time.Minute,
|
||||
)
|
||||
}
|
||||
|
||||
func newTestRuleWithLabels(name string, labels ...string) *AlertingRule {
|
||||
@@ -1118,72 +1078,12 @@ func newTestAlertingRule(name string, waitFor time.Duration) *AlertingRule {
|
||||
EvalInterval: waitFor,
|
||||
alerts: make(map[uint64]*notifier.Alert),
|
||||
state: &ruleState{entries: make([]StateEntry, 10)},
|
||||
metrics: &alertingRuleMetrics{
|
||||
errors: utils.GetOrCreateCounter(fmt.Sprintf(`vmalert_alerting_rules_errors_total{alertname=%q}`, name)),
|
||||
},
|
||||
}
|
||||
return &rule
|
||||
}
|
||||
|
||||
func newTestAlertingRuleWithEvalInterval(name string, waitFor, evalInterval time.Duration) *AlertingRule {
|
||||
rule := newTestAlertingRule(name, waitFor)
|
||||
rule.EvalInterval = evalInterval
|
||||
return rule
|
||||
}
|
||||
|
||||
func newTestAlertingRuleWithKeepFiring(name string, waitFor, keepFiringFor time.Duration) *AlertingRule {
|
||||
rule := newTestAlertingRule(name, waitFor)
|
||||
rule.KeepFiringFor = keepFiringFor
|
||||
return rule
|
||||
}
|
||||
|
||||
func TestAlertingRule_ToLabels(t *testing.T) {
|
||||
metric := datasource.Metric{
|
||||
Labels: []datasource.Label{
|
||||
{Name: "instance", Value: "0.0.0.0:8800"},
|
||||
{Name: "group", Value: "vmalert"},
|
||||
{Name: "alertname", Value: "ConfigurationReloadFailure"},
|
||||
},
|
||||
Values: []float64{1},
|
||||
Timestamps: []int64{time.Now().UnixNano()},
|
||||
}
|
||||
|
||||
ar := &AlertingRule{
|
||||
Labels: map[string]string{
|
||||
"instance": "override", // this should override instance with new value
|
||||
"group": "vmalert", // this shouldn't have effect since value in metric is equal
|
||||
},
|
||||
Expr: "sum(vmalert_alerting_rules_error) by(instance, group, alertname) > 0",
|
||||
Name: "AlertingRulesError",
|
||||
GroupName: "vmalert",
|
||||
}
|
||||
|
||||
expectedOriginLabels := map[string]string{
|
||||
"instance": "0.0.0.0:8800",
|
||||
"group": "vmalert",
|
||||
"alertname": "ConfigurationReloadFailure",
|
||||
"alertgroup": "vmalert",
|
||||
}
|
||||
|
||||
expectedProcessedLabels := map[string]string{
|
||||
"instance": "override",
|
||||
"exported_instance": "0.0.0.0:8800",
|
||||
"alertname": "AlertingRulesError",
|
||||
"exported_alertname": "ConfigurationReloadFailure",
|
||||
"group": "vmalert",
|
||||
"alertgroup": "vmalert",
|
||||
}
|
||||
|
||||
ls, err := ar.toLabels(metric, nil)
|
||||
if err != nil {
|
||||
t.Fatalf("unexpected error: %s", err)
|
||||
}
|
||||
|
||||
if !reflect.DeepEqual(ls.origin, expectedOriginLabels) {
|
||||
t.Errorf("origin labels mismatch, got: %v, want: %v", ls.origin, expectedOriginLabels)
|
||||
}
|
||||
|
||||
if !reflect.DeepEqual(ls.processed, expectedProcessedLabels) {
|
||||
t.Errorf("processed labels mismatch, got: %v, want: %v", ls.processed, expectedProcessedLabels)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -704,7 +704,7 @@ func (e *executor) exec(ctx context.Context, r Rule, ts time.Time, resolveDurati
|
||||
return nil
|
||||
}
|
||||
|
||||
alerts := ar.alertsToSend(resolveDuration, *resendDelay)
|
||||
alerts := ar.alertsToSend(ts, resolveDuration, *resendDelay)
|
||||
if len(alerts) < 1 {
|
||||
return nil
|
||||
}
|
||||
@@ -724,7 +724,7 @@ func (e *executor) exec(ctx context.Context, r Rule, ts time.Time, resolveDurati
|
||||
return errGr.Err()
|
||||
}
|
||||
|
||||
// getStaleSeries checks whether there are stale series from previously sent ones.
|
||||
// getStaledSeries checks whether there are stale series from previously sent ones.
|
||||
func (e *executor) getStaleSeries(r Rule, tss []prompbmarshal.TimeSeries, timestamp time.Time) []prompbmarshal.TimeSeries {
|
||||
ruleLabels := make(map[string][]prompbmarshal.Label, len(tss))
|
||||
for _, ts := range tss {
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user