Skip to content

fix(metrics): use _counts histogram for replication tasks lag #7716

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.

Sign up for GitHub

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

Open
zawadzkidiana wants to merge 1 commit into
base: master
Choose a base branch
from
+5 −5
Open

fix(metrics): use _counts histogram for replication tasks lag #7716

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion common/metrics/config.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,7 +47,7 @@ var HistogramMigrationMetrics = map[string]struct{}{
// Replication task processor histograms (PR #7685).
// Dual-emitted as timer + histogram.
"replication_tasks_lag": {},
"replication_tasks_lag_ns": {},
"replication_tasks_lag_counts": {},
"replication_tasks_applied_latency": {},
"replication_tasks_applied_latency_ns": {},

Expand Down
2 changes: 1 addition & 1 deletion common/metrics/defs.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3541,7 +3541,7 @@ var MetricDefs = map[ServiceIdx]map[MetricIdx]metricDefinition{
ReplicationTasksApplied: {metricName: "replication_tasks_applied", metricType: Counter},
ReplicationTasksFailed: {metricName: "replication_tasks_failed", metricType: Counter},
ReplicationTasksLag: {metricName: "replication_tasks_lag", metricType: Timer},
ExponentialReplicationTasksLag: {metricName: "replication_tasks_lag_ns", metricType: Histogram, exponentialBuckets: Mid1ms24h},
ExponentialReplicationTasksLag: {metricName: "replication_tasks_lag_counts", metricType: Histogram, intExponentialBuckets: Mid1To16k},
ReplicationTasksLagRaw: {metricName: "replication_tasks_lag_raw", metricType: Timer},
ReplicationTasksDelay: {metricName: "replication_tasks_delay", metricType: Histogram, buckets: ReplicationTaskDelayBucket},
ReplicationTasksFetched: {metricName: "replication_tasks_fetched", metricType: Timer},
Expand Down
6 changes: 3 additions & 3 deletions service/history/replication/task_processor.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -278,12 +278,12 @@ func (p *taskProcessorImpl) cleanupAckedReplicationTasks() error {
persistence.HistoryTaskCategoryReplication,
p.currentCluster,
).GetTaskID()
lag := time.Duration(maxReadLevel - minAckLevel)
lagCount := int(maxReadLevel - minAckLevel)
scope := p.metricsClient.Scope(metrics.ReplicationTaskFetcherScope,
metrics.TargetClusterTag(p.currentCluster),
)
scope.RecordTimer(metrics.ReplicationTasksLag, lag)
scope.ExponentialHistogram(metrics.ExponentialReplicationTasksLag, lag)
scope.RecordTimer(metrics.ReplicationTasksLag, time.Duration(lagCount))
scope.IntExponentialHistogram(metrics.ExponentialReplicationTasksLag, lagCount)
for {
pageSize := p.config.ReplicatorTaskDeleteBatchSize()
resp, err := p.shard.GetExecutionManager().RangeCompleteHistoryTask(
Expand Down
Loading