Files
VictoriaMetrics/app/vminsert/native/request_handler.go
f41gh7 78ad858ff7 app/{vminsert,vmagent}: drop time series on exceeding labels limits.
Previously, time series with labels exceeding the configured limits were truncated and written to storage, potentially causing data inconsistency. This could lead to collisions between time series and make it difficult to identify the source due to truncated labels.

This commit changes the behavior:
*  Such time series are now rejected outright.
* Rejected time series are logged to stdout, and corresponding counters are incremented.
* removes `vm_too_long_label_values_total`, `vm_too_long_label_names_total`, `vm_metrics_with_dropped_labels_total` metrics.
* adds new values `[too_many_labels,too_long_label_name,too_long_label_value]`  to `reason` label of the `vm_rows_ignored_total` metric name

related issues:
- https://github.com/VictoriaMetrics/VictoriaMetrics/issues/6928
- https://github.com/VictoriaMetrics/VictoriaMetrics/issues/7661
2024-12-10 22:15:38 +01:00

87 lines
2.9 KiB
Go

package native
import (
"net/http"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vminsert/netstorage"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vminsert/relabel"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/auth"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
parserCommon "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/common"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/native/stream"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/storage"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/tenantmetrics"
"github.com/VictoriaMetrics/metrics"
)
var (
rowsInserted = metrics.NewCounter(`vm_rows_inserted_total{type="native"}`)
rowsTenantInserted = tenantmetrics.NewCounterMap(`vm_tenant_inserted_rows_total{type="native"}`)
rowsPerInsert = metrics.NewHistogram(`vm_rows_per_insert{type="native"}`)
)
// InsertHandler processes `/api/v1/import/native` request.
func InsertHandler(at *auth.Token, req *http.Request) error {
extraLabels, err := parserCommon.GetExtraLabels(req)
if err != nil {
return err
}
isGzip := req.Header.Get("Content-Encoding") == "gzip"
return stream.Parse(req.Body, isGzip, func(block *stream.Block) error {
return insertRows(at, block, extraLabels)
})
}
func insertRows(at *auth.Token, block *stream.Block, extraLabels []prompbmarshal.Label) error {
ctx := netstorage.GetInsertCtx()
defer netstorage.PutInsertCtx(ctx)
// Update rowsInserted and rowsPerInsert before actual inserting,
// since relabeling can prevent from inserting the rows.
rowsLen := len(block.Values)
rowsInserted.Add(rowsLen)
if at != nil {
rowsTenantInserted.Get(at).Add(rowsLen)
}
rowsPerInsert.Update(float64(rowsLen))
ctx.Reset() // This line is required for initializing ctx internals.
hasRelabeling := relabel.HasRelabeling()
mn := &block.MetricName
ctx.Labels = ctx.Labels[:0]
ctx.AddLabelBytes(nil, mn.MetricGroup)
for j := range mn.Tags {
tag := &mn.Tags[j]
ctx.AddLabelBytes(tag.Key, tag.Value)
}
for j := range extraLabels {
label := &extraLabels[j]
ctx.AddLabel(label.Name, label.Value)
}
if !ctx.TryPrepareLabels(hasRelabeling) {
return nil
}
atLocal := ctx.GetLocalAuthToken(at)
ctx.MetricNameBuf = storage.MarshalMetricNameRaw(ctx.MetricNameBuf[:0], atLocal.AccountID, atLocal.ProjectID, ctx.Labels)
storageNodeIdx := ctx.GetStorageNodeIdx(atLocal, ctx.Labels)
values := block.Values
timestamps := block.Timestamps
if len(timestamps) != len(values) {
logger.Panicf("BUG: len(timestamps)=%d must match len(values)=%d", len(timestamps), len(values))
}
for j, value := range values {
timestamp := timestamps[j]
if err := ctx.WriteDataPointExt(storageNodeIdx, ctx.MetricNameBuf, timestamp, value); err != nil {
return err
}
}
if err := ctx.FlushBufs(); err != nil {
return err
}
if at == nil {
rowsTenantInserted.Get(atLocal).Add(rowsLen)
}
return nil
}