-
Notifications
You must be signed in to change notification settings - Fork 2.1k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[FEATURE] adding otlp endpoint #7996
Draft
nicolastakashi
wants to merge
4
commits into
thanos-io:main
Choose a base branch
from
nicolastakashi:chore/adding-otlp-endpoint
base: main
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
+357
−1
Draft
Changes from all commits
Commits
Show all changes
4 commits
Select commit
Hold shift + click to select a range
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,214 @@ | ||
| // Copyright (c) The Thanos Authors. | ||
| // Licensed under the Apache License 2.0. | ||
|
|
||
| package receive | ||
|
|
||
| import ( | ||
| "context" | ||
| "net/http" | ||
| "strconv" | ||
|
|
||
| "github.com/go-kit/log" | ||
| "github.com/go-kit/log/level" | ||
| "github.com/pkg/errors" | ||
| "github.com/prometheus/prometheus/prompb" | ||
| "github.com/prometheus/prometheus/storage/remote" | ||
| "github.com/prometheus/prometheus/storage/remote/otlptranslator/prometheusremotewrite" | ||
| "github.com/thanos-io/thanos/pkg/store/labelpb" | ||
| tprompb "github.com/thanos-io/thanos/pkg/store/storepb/prompb" | ||
| "github.com/thanos-io/thanos/pkg/tenancy" | ||
| "github.com/thanos-io/thanos/pkg/tracing" | ||
| "go.opentelemetry.io/collector/pdata/pmetric" | ||
| ) | ||
|
|
||
| func (h *Handler) receiveOTLPHTTP(w http.ResponseWriter, r *http.Request) { | ||
| var err error | ||
| span, ctx := tracing.StartSpan(r.Context(), "receiveOTLPHTTP") | ||
| span.SetTag("receiver.mode", string(h.receiverMode)) | ||
| defer span.Finish() | ||
|
|
||
| tenant, err := tenancy.GetTenantFromHTTP(r, h.options.TenantHeader, h.options.DefaultTenantID, h.options.TenantField) | ||
| if err != nil { | ||
| level.Error(h.logger).Log("msg", "error getting tenant from HTTP", "err", err) | ||
| http.Error(w, err.Error(), http.StatusBadRequest) | ||
| return | ||
| } | ||
|
|
||
| tLogger := log.With(h.logger, "tenant", tenant) | ||
| span.SetTag("tenant", tenant) | ||
|
|
||
| writeGate := h.Limiter.WriteGate() | ||
| tracing.DoInSpan(r.Context(), "receive_write_gate_ismyturn", func(ctx context.Context) { | ||
| err = writeGate.Start(r.Context()) | ||
| }) | ||
|
|
||
| defer writeGate.Done() | ||
| if err != nil { | ||
| level.Error(tLogger).Log("err", err, "msg", "internal server error") | ||
|
Check failure Code scanning / CodeQL Clear-text logging of sensitive information High Sensitive data returned by HTTP request headers Error loading related location Loading |
||
| http.Error(w, err.Error(), http.StatusInternalServerError) | ||
| return | ||
| } | ||
|
|
||
| under, err := h.Limiter.HeadSeriesLimiter().isUnderLimit(tenant) | ||
| if err != nil { | ||
| level.Error(tLogger).Log("msg", "error while limiting", "err", err.Error()) | ||
| } | ||
|
|
||
| // Fail request fully if tenant has exceeded set limit. | ||
| if !under { | ||
| http.Error(w, "tenant is above active series limit", http.StatusTooManyRequests) | ||
| return | ||
| } | ||
|
|
||
| requestLimiter := h.Limiter.RequestLimiter() | ||
| req, err := remote.DecodeOTLPWriteRequest(r) | ||
| if err != nil { | ||
| level.Error(h.logger).Log("msg", "Error decoding remote write request", "err", err.Error()) | ||
| http.Error(w, err.Error(), http.StatusBadRequest) | ||
| return | ||
| } | ||
|
|
||
| promTimeSeries, err := h.convertToPrometheusFormat(ctx, req.Metrics()) | ||
| if err != nil { | ||
| http.Error(w, err.Error(), http.StatusBadRequest) | ||
| return | ||
| } | ||
|
|
||
| prwMetrics := make([]tprompb.TimeSeries, 0, len(promTimeSeries)) | ||
| totalSamples := 0 | ||
| var tpromTs tprompb.TimeSeries | ||
|
|
||
| for _, ts := range promTimeSeries { | ||
| tpromTs = tprompb.TimeSeries{ | ||
| Labels: makeLabels(ts.Labels), | ||
| Samples: makeSamples(ts.Samples), | ||
| Exemplars: makeExemplars(ts.Exemplars), | ||
| } | ||
| totalSamples += len(ts.Samples) | ||
| prwMetrics = append(prwMetrics, tpromTs) | ||
| } | ||
|
|
||
| if !requestLimiter.AllowSeries(tenant, int64(len(prwMetrics))) { | ||
| http.Error(w, "too many timeseries", http.StatusRequestEntityTooLarge) | ||
| return | ||
| } | ||
|
|
||
| if !requestLimiter.AllowSamples(tenant, int64(totalSamples)) { | ||
| http.Error(w, "too many samples", http.StatusRequestEntityTooLarge) | ||
| return | ||
| } | ||
|
|
||
| rep := uint64(0) | ||
| // If the header is empty, we assume the request is not yet replicated. | ||
| if replicaRaw := r.Header.Get(h.options.ReplicaHeader); replicaRaw != "" { | ||
| if rep, err = strconv.ParseUint(replicaRaw, 10, 64); err != nil { | ||
| http.Error(w, "could not parse replica header", http.StatusBadRequest) | ||
| return | ||
| } | ||
| } | ||
|
|
||
| wreq := tprompb.WriteRequest{ | ||
| Timeseries: prwMetrics, | ||
| // TODO Handle metadata, requires thanos receiver support ingesting metadata | ||
| //Metadata: otlptranslator.OtelMetricsToMetadata(), | ||
| } | ||
|
|
||
| // Exit early if the request contained no data. We don't support metadata yet. We also cannot fail here, because | ||
| // this would mean lack of forward compatibility for remote write proto. | ||
| if len(wreq.Timeseries) == 0 { | ||
| // TODO(yeya24): Handle remote write metadata. | ||
| if len(wreq.Metadata) > 0 { | ||
| // TODO(bwplotka): Do we need this error message? | ||
| level.Debug(tLogger).Log("msg", "only metadata from client; metadata ingestion not supported; skipping") | ||
| return | ||
| } | ||
| level.Debug(tLogger).Log("msg", "empty remote write request; client bug or newer remote write protocol used?; skipping") | ||
| return | ||
| } | ||
|
|
||
| // Apply relabeling configs. | ||
| h.relabel(&wreq) | ||
| if len(wreq.Timeseries) == 0 { | ||
| level.Debug(tLogger).Log("msg", "remote write request dropped due to relabeling.") | ||
| return | ||
| } | ||
|
|
||
| responseStatusCode := http.StatusOK | ||
| tenantStats, err := h.handleRequest(ctx, rep, tenant, &wreq) | ||
| if err != nil { | ||
| level.Debug(tLogger).Log("msg", "failed to handle request", "err", err.Error()) | ||
| switch errors.Cause(err) { | ||
| case errNotReady: | ||
| responseStatusCode = http.StatusServiceUnavailable | ||
| case errUnavailable: | ||
| responseStatusCode = http.StatusServiceUnavailable | ||
| case errConflict: | ||
| responseStatusCode = http.StatusConflict | ||
| case errBadReplica: | ||
| responseStatusCode = http.StatusBadRequest | ||
| default: | ||
| level.Error(tLogger).Log("err", err, "msg", "internal server error") | ||
|
Check failure Code scanning / CodeQL Clear-text logging of sensitive information High Sensitive data returned by HTTP request headers Error loading related location Loading |
||
| responseStatusCode = http.StatusInternalServerError | ||
| } | ||
| http.Error(w, err.Error(), responseStatusCode) | ||
| } | ||
|
|
||
| for tenant, stats := range tenantStats { | ||
| h.writeTimeseriesTotal.WithLabelValues(strconv.Itoa(responseStatusCode), tenant).Observe(float64(stats.timeseries)) | ||
| h.writeSamplesTotal.WithLabelValues(strconv.Itoa(responseStatusCode), tenant).Observe(float64(stats.totalSamples)) | ||
| } | ||
|
|
||
| } | ||
|
|
||
| func (h *Handler) convertToPrometheusFormat(ctx context.Context, pmetrics pmetric.Metrics) ([]prompb.TimeSeries, error) { | ||
| promConverter := prometheusremotewrite.NewPrometheusConverter() | ||
| settings := prometheusremotewrite.Settings{ | ||
| AddMetricSuffixes: true, | ||
| DisableTargetInfo: true, // this must to be configured | ||
| PromoteResourceAttributes: []string{"service.name", "service.namespace"}, // this must to be configured | ||
| } | ||
|
|
||
| annots, err := promConverter.FromMetrics(ctx, pmetrics, settings) | ||
| ws, _ := annots.AsStrings("", 0, 0) | ||
| if len(ws) > 0 { | ||
| level.Warn(h.logger).Log("msg", "Warnings translating OTLP metrics to Prometheus write request", "warnings", ws) | ||
| } | ||
|
|
||
| if err != nil { | ||
| level.Error(h.logger).Log("msg", "Error translating OTLP metrics to Prometheus write request", "err", err) | ||
| return nil, err | ||
| } | ||
|
|
||
| return promConverter.TimeSeries(), nil | ||
| } | ||
|
|
||
| func makeLabels(in []prompb.Label) []labelpb.ZLabel { | ||
| out := make([]labelpb.ZLabel, 0, len(in)) | ||
| for _, l := range in { | ||
| out = append(out, labelpb.ZLabel{Name: l.Name, Value: l.Value}) | ||
| } | ||
| return out | ||
| } | ||
|
|
||
| func makeSamples(in []prompb.Sample) []tprompb.Sample { | ||
| out := make([]tprompb.Sample, 0, len(in)) | ||
| for _, s := range in { | ||
| out = append(out, tprompb.Sample{ | ||
| Value: s.Value, | ||
| Timestamp: s.Timestamp, | ||
| }) | ||
| } | ||
| return out | ||
| } | ||
|
|
||
| func makeExemplars(in []prompb.Exemplar) []tprompb.Exemplar { | ||
| out := make([]tprompb.Exemplar, 0, len(in)) | ||
| for _, e := range in { | ||
| out = append(out, tprompb.Exemplar{ | ||
| Labels: makeLabels(e.Labels), | ||
| Value: e.Value, | ||
| Timestamp: e.Timestamp, | ||
| }) | ||
| } | ||
| return out | ||
| } | ||
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Check failure
Code scanning / CodeQL
Clear-text logging of sensitive information High