app/vlselect: add start_offset query arg for /select/logsql/tail endpoint for returning historical logs before live tailing

(cherry picked from commit 3a5f1019ba)
This commit is contained in:
Aliaksandr Valialkin 2024-11-06 12:51:47 +01:00 committed by hagen1778
parent 98fe1950a1
commit ab3b4020b4
No known key found for this signature in database
GPG key ID: E92986095E0DD614
3 changed files with 22 additions and 4 deletions

View file

@ -407,6 +407,13 @@ func ProcessLiveTailRequest(ctx context.Context, w http.ResponseWriter, r *http.
} }
refreshInterval := time.Millisecond * time.Duration(refreshIntervalMsecs) refreshInterval := time.Millisecond * time.Duration(refreshIntervalMsecs)
startOffsetMsecs, err := httputils.GetDuration(r, "start_offset", 5*1000)
if err != nil {
httpserver.Errorf(w, r, "%s", err)
return
}
startOffset := startOffsetMsecs * 1e6
ctxWithCancel, cancel := context.WithCancel(ctx) ctxWithCancel, cancel := context.WithCancel(ctx)
tp := newTailProcessor(cancel) tp := newTailProcessor(cancel)
@ -414,6 +421,7 @@ func ProcessLiveTailRequest(ctx context.Context, w http.ResponseWriter, r *http.
defer ticker.Stop() defer ticker.Stop()
end := time.Now().UnixNano() end := time.Now().UnixNano()
start := end - startOffset
doneCh := ctxWithCancel.Done() doneCh := ctxWithCancel.Done()
flusher, ok := w.(http.Flusher) flusher, ok := w.(http.Flusher)
if !ok { if !ok {
@ -421,14 +429,12 @@ func ProcessLiveTailRequest(ctx context.Context, w http.ResponseWriter, r *http.
} }
qOrig := q qOrig := q
for { for {
start := end - tailOffsetNsecs
end = time.Now().UnixNano()
q = qOrig.Clone(end) q = qOrig.Clone(end)
q.AddTimeFilter(start, end) q.AddTimeFilter(start, end)
// q.Optimize() call is needed for converting '*' into filterNoop. // q.Optimize() call is needed for converting '*' into filterNoop.
// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/6785#issuecomment-2358547733 // See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/6785#issuecomment-2358547733
q.Optimize() q.Optimize()
if err := vlstorage.RunQuery(ctxWithCancel, tenantIDs, q, tp.writeBlock); err != nil { if err := vlstorage.RunQuery(ctxWithCancel, tenantIDs, q, tp.writeBlock); err != nil {
httpserver.Errorf(w, r, "cannot execute tail query [%s]: %s", q, err) httpserver.Errorf(w, r, "cannot execute tail query [%s]: %s", q, err)
return return
@ -447,6 +453,8 @@ func ProcessLiveTailRequest(ctx context.Context, w http.ResponseWriter, r *http.
case <-doneCh: case <-doneCh:
return return
case <-ticker.C: case <-ticker.C:
start = end - tailOffsetNsecs
end = time.Now().UnixNano()
} }
} }
} }

View file

@ -15,6 +15,7 @@ according to [these docs](https://docs.victoriametrics.com/victorialogs/quicksta
## tip ## tip
* FEATURE: support returning historical logs from [live tailing API](https://docs.victoriametrics.com/victorialogs/querying/#live-tailing) via `start_offset` query arg. For example, request to `/select/logsql/tail?query=*&start_offset=5m` returns logs for the last 5 minutes before starting returning live tailing logs for the given `query`.
* FEATURE: add an ability to specify extra fields for logs ingested via [HTTP-based data ingestion protocols](https://docs.victoriametrics.com/victorialogs/data-ingestion/#http-apis). See `extra_fields` query arg and `VL-Extra-Fields` HTTP header in [these docs](https://docs.victoriametrics.com/victorialogs/data-ingestion/#http-parameters). * FEATURE: add an ability to specify extra fields for logs ingested via [HTTP-based data ingestion protocols](https://docs.victoriametrics.com/victorialogs/data-ingestion/#http-apis). See `extra_fields` query arg and `VL-Extra-Fields` HTTP header in [these docs](https://docs.victoriametrics.com/victorialogs/data-ingestion/#http-parameters).
* BUGFIX: Properly parse structured metadata when ingesting logs with Loki ingestion protocol. An issue has been introduced in [v0.3.0](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/tag/v0.3.0-victorialogs). See [this issue](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/7431) for the details. * BUGFIX: Properly parse structured metadata when ingesting logs with Loki ingestion protocol. An issue has been introduced in [v0.3.0](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/tag/v0.3.0-victorialogs). See [this issue](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/7431) for the details.

View file

@ -130,7 +130,8 @@ curl -N http://localhost:9428/select/logsql/tail -d 'query=error'
``` ```
The `-N` command-line flag is essential to pass to `curl` during live tailing, since otherwise curl may delay displaying matching logs The `-N` command-line flag is essential to pass to `curl` during live tailing, since otherwise curl may delay displaying matching logs
because of internal response buffering. because of internal response buffering. It is recommended using [vlogscli](https://docs.victoriametrics.com/victorialogs/querying/vlogscli/) for live tailing -
see [these docs](https://docs.victoriametrics.com/victorialogs/querying/vlogscli/#live-tailing).
The `<query>` must conform the following rules: The `<query>` must conform the following rules:
@ -146,6 +147,14 @@ The `<query>` must conform the following rules:
- It is recommended to return [`_stream_id`](https://docs.victoriametrics.com/victorialogs/keyconcepts/#stream-fields) field for more accurate live tailing - It is recommended to return [`_stream_id`](https://docs.victoriametrics.com/victorialogs/keyconcepts/#stream-fields) field for more accurate live tailing
across multiple streams. across multiple streams.
Live tailing supports returning historical logs, which were ingested into VictoriaLogs before the start of live tailing. Pass `start_offset=<d>` query
arg to `/select/logsql/tail` where `<d>` is the duration for returning historical logs. For example, the following request returns historical logs
which were ingested into VictoriaLogs during the last hour, before starting live tailing:
```sh
curl -N http://localhost:9428/select/logsql/tail -d 'query=*' -d 'start_offset=1h'
```
**Performance tip**: live tailing works the best if it matches newly ingested logs at relatively slow rate (e.g. up to 1K matching logs per second), **Performance tip**: live tailing works the best if it matches newly ingested logs at relatively slow rate (e.g. up to 1K matching logs per second),
e.g. it is optimized for the case when real humans inspect the output of live tailing in the real time. If live tailing returns logs at too high rate, e.g. it is optimized for the case when real humans inspect the output of live tailing in the real time. If live tailing returns logs at too high rate,
then it is recommended adding more specific [filters](https://docs.victoriametrics.com/victorialogs/logsql/#filters) to the `<query>`, so it matches less logs. then it is recommended adding more specific [filters](https://docs.victoriametrics.com/victorialogs/logsql/#filters) to the `<query>`, so it matches less logs.