mudhorn/prometheus
1
0
Fork 0
mirror of https://github.com/prometheus/prometheus.git synced 2024-11-09 23:24:05 -08:00
Code Issues Actions 3 Packages Projects Releases Wiki Activity

Log rule name when evaluating rule groups' Eval function logs anything (#10454)

Browse source 
* Add benchingmark test for rule group eval

Signed-off-by: Alvin Lin <alvinlin@amazon.com>
This commit is contained in:
Alvin Lin 2022-03-21 11:52:20 -07:00 committed by GitHub
parent 69e9eadfd3
commit cd739214dd
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 9 additions and 9 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

18
rules/manager.go
View file

@ -306,7 +306,7 @@ func NewGroup(o GroupOptions) *Group {
done: make(chan struct{}),
managerDone: o.done,
terminated: make(chan struct{}),
logger: log.With(o.Opts.Logger, "group", o.Name),
logger: log.With(o.Opts.Logger, "file", o.File, "group", o.Name),
metrics: metrics,
}
}
@ -607,7 +607,7 @@ func (g *Group) Eval(ctx context.Context, ts time.Time) {
// Canceled queries are intentional termination of queries. This normally
// happens on shutdown and thus we skip logging of any errors here.
if _, ok := err.(promql.ErrQueryCanceled); !ok {
level.Warn(g.logger).Log("msg", "Evaluating rule failed", "rule", rule, "err", err)
level.Warn(g.logger).Log("name", rule.Name(), "index", i, "msg", "Evaluating rule failed", "rule", rule, "err", err)
}
return
}
@ -631,7 +631,7 @@ func (g *Group) Eval(ctx context.Context, ts time.Time) {
rule.SetLastError(err)
g.metrics.EvalFailures.WithLabelValues(GroupKey(g.File(), g.Name())).Inc()
level.Warn(g.logger).Log("msg", "Rule sample appending failed", "err", err)
level.Warn(g.logger).Log("name", rule.Name(), "index", i, "msg", "Rule sample appending failed", "err", err)
return
}
g.seriesInPreviousEval[i] = seriesReturned
@ -645,12 +645,12 @@ func (g *Group) Eval(ctx context.Context, ts time.Time) {
switch errors.Cause(err) {
case storage.ErrOutOfOrderSample:
numOutOfOrder++
level.Debug(g.logger).Log("msg", "Rule evaluation result discarded", "err", err, "sample", s)
level.Debug(g.logger).Log("name", rule.Name(), "index", i, "msg", "Rule evaluation result discarded", "err", err, "sample", s)
case storage.ErrDuplicateSampleForTimestamp:
numDuplicates++
level.Debug(g.logger).Log("msg", "Rule evaluation result discarded", "err", err, "sample", s)
level.Debug(g.logger).Log("name", rule.Name(), "index", i, "msg", "Rule evaluation result discarded", "err", err, "sample", s)
default:
level.Warn(g.logger).Log("msg", "Rule evaluation result discarded", "err", err, "sample", s)
level.Warn(g.logger).Log("name", rule.Name(), "index", i, "msg", "Rule evaluation result discarded", "err", err, "sample", s)
}
} else {
buf := [1024]byte{}
@ -658,10 +658,10 @@ func (g *Group) Eval(ctx context.Context, ts time.Time) {
}
}
if numOutOfOrder > 0 {
level.Warn(g.logger).Log("msg", "Error on ingesting out-of-order result from rule evaluation", "numDropped", numOutOfOrder)
level.Warn(g.logger).Log("name", rule.Name(), "index", i, "msg", "Error on ingesting out-of-order result from rule evaluation", "numDropped", numOutOfOrder)
}
if numDuplicates > 0 {
level.Warn(g.logger).Log("msg", "Error on ingesting results from rule evaluation with different value but same timestamp", "numDropped", numDuplicates)
level.Warn(g.logger).Log("name", rule.Name(), "index", i, "msg", "Error on ingesting results from rule evaluation with different value but same timestamp", "numDropped", numDuplicates)
}
for metric, lset := range g.seriesInPreviousEval[i] {
@ -674,7 +674,7 @@ func (g *Group) Eval(ctx context.Context, ts time.Time) {
// Do not count these in logging, as this is expected if series
// is exposed from a different rule.
default:
level.Warn(g.logger).Log("msg", "Adding stale sample failed", "sample", lset.String(), "err", err)
level.Warn(g.logger).Log("name", rule.Name(), "index", i, "msg", "Adding stale sample failed", "sample", lset.String(), "err", err)
}
}
}