Compare commits

..

6 Commits

Author SHA1 Message Date
Naman Verma
769022a799 Merge branch 'main' into nv/10890 2026-06-03 11:33:47 +05:30
Naman Verma
2a6539bd80 Merge branch 'main' into nv/10890 2026-04-27 11:31:28 +05:30
Naman Verma
7d2457d305 Merge branch 'main' into nv/10890 2026-04-20 15:35:03 +05:30
Naman Verma
71351b2856 Merge branch 'main' into nv/10890 2026-04-16 11:57:56 +05:30
Naman Verma
018c78f4ff fix: add metadata fetch to list metrics query to avoid CH timeouts due to sequential queries 2026-04-09 17:50:18 +05:30
Naman Verma
31e2c1b585 fix: combine metadata fetch into stats query to avoid ClickHouse timeouts due to sequential queries 2026-04-09 17:26:13 +05:30
5 changed files with 58 additions and 41 deletions

View File

@@ -190,7 +190,7 @@ services:
# - ../common/clickhouse/storage.xml:/etc/clickhouse-server/config.d/storage.xml
signoz:
!!merge <<: *db-depend
image: signoz/signoz:v0.127.0
image: signoz/signoz:v0.126.1
ports:
- "8080:8080" # signoz port
# - "6060:6060" # pprof port
@@ -213,7 +213,7 @@ services:
retries: 3
otel-collector:
!!merge <<: *db-depend
image: signoz/signoz-otel-collector:v0.144.5
image: signoz/signoz-otel-collector:v0.144.4
entrypoint:
- /bin/sh
command:
@@ -241,7 +241,7 @@ services:
replicas: 3
signoz-telemetrystore-migrator:
!!merge <<: *db-depend
image: signoz/signoz-otel-collector:v0.144.5
image: signoz/signoz-otel-collector:v0.144.4
environment:
- SIGNOZ_OTEL_COLLECTOR_CLICKHOUSE_DSN=tcp://clickhouse:9000
- SIGNOZ_OTEL_COLLECTOR_CLICKHOUSE_CLUSTER=cluster

View File

@@ -117,7 +117,7 @@ services:
# - ../common/clickhouse/storage.xml:/etc/clickhouse-server/config.d/storage.xml
signoz:
!!merge <<: *db-depend
image: signoz/signoz:v0.127.0
image: signoz/signoz:v0.126.1
ports:
- "8080:8080" # signoz port
volumes:
@@ -139,7 +139,7 @@ services:
retries: 3
otel-collector:
!!merge <<: *db-depend
image: signoz/signoz-otel-collector:v0.144.5
image: signoz/signoz-otel-collector:v0.144.4
entrypoint:
- /bin/sh
command:
@@ -167,7 +167,7 @@ services:
replicas: 3
signoz-telemetrystore-migrator:
!!merge <<: *db-depend
image: signoz/signoz-otel-collector:v0.144.5
image: signoz/signoz-otel-collector:v0.144.4
environment:
- SIGNOZ_OTEL_COLLECTOR_CLICKHOUSE_DSN=tcp://clickhouse:9000
- SIGNOZ_OTEL_COLLECTOR_CLICKHOUSE_CLUSTER=cluster

View File

@@ -181,7 +181,7 @@ services:
# - ../common/clickhouse/storage.xml:/etc/clickhouse-server/config.d/storage.xml
signoz:
!!merge <<: *db-depend
image: signoz/signoz:${VERSION:-v0.127.0}
image: signoz/signoz:${VERSION:-v0.126.1}
container_name: signoz
ports:
- "8080:8080" # signoz port
@@ -204,7 +204,7 @@ services:
retries: 3
otel-collector:
!!merge <<: *db-depend
image: signoz/signoz-otel-collector:${OTELCOL_TAG:-v0.144.5}
image: signoz/signoz-otel-collector:${OTELCOL_TAG:-v0.144.4}
container_name: signoz-otel-collector
entrypoint:
- /bin/sh
@@ -229,7 +229,7 @@ services:
- "4318:4318" # OTLP HTTP receiver
signoz-telemetrystore-migrator:
!!merge <<: *db-depend
image: signoz/signoz-otel-collector:${OTELCOL_TAG:-v0.144.5}
image: signoz/signoz-otel-collector:${OTELCOL_TAG:-v0.144.4}
container_name: signoz-telemetrystore-migrator
environment:
- SIGNOZ_OTEL_COLLECTOR_CLICKHOUSE_DSN=tcp://clickhouse:9000

View File

@@ -109,7 +109,7 @@ services:
# - ../common/clickhouse/storage.xml:/etc/clickhouse-server/config.d/storage.xml
signoz:
!!merge <<: *db-depend
image: signoz/signoz:${VERSION:-v0.127.0}
image: signoz/signoz:${VERSION:-v0.126.1}
container_name: signoz
ports:
- "8080:8080" # signoz port
@@ -132,7 +132,7 @@ services:
retries: 3
otel-collector:
!!merge <<: *db-depend
image: signoz/signoz-otel-collector:${OTELCOL_TAG:-v0.144.5}
image: signoz/signoz-otel-collector:${OTELCOL_TAG:-v0.144.4}
container_name: signoz-otel-collector
entrypoint:
- /bin/sh
@@ -157,7 +157,7 @@ services:
- "4318:4318" # OTLP HTTP receiver
signoz-telemetrystore-migrator:
!!merge <<: *db-depend
image: signoz/signoz-otel-collector:${OTELCOL_TAG:-v0.144.5}
image: signoz/signoz-otel-collector:${OTELCOL_TAG:-v0.144.4}
container_name: signoz-telemetrystore-migrator
environment:
- SIGNOZ_OTEL_COLLECTOR_CLICKHOUSE_DSN=tcp://clickhouse:9000

View File

@@ -138,7 +138,14 @@ func (m *module) listMeterMetrics(ctx context.Context, params *metricsexplorerty
func (m *module) listMetrics(ctx context.Context, orgID valuer.UUID, params *metricsexplorertypes.ListMetricsParams) (*metricsexplorertypes.ListMetricsResponse, error) {
sb := sqlbuilder.NewSelectBuilder()
sb.Select("DISTINCT metric_name")
sb.Select(
"metric_name",
"anyLast(description) AS description",
"anyLast(type) AS metric_type",
"argMax(unit, unix_milli) AS metric_unit",
"anyLast(temporality) AS temporality",
"anyLast(is_monotonic) AS is_monotonic",
)
if params.Start != nil && params.End != nil {
start, end, distributedTsTable, _ := telemetrymetrics.WhichTSTableToUse(uint64(*params.Start), uint64(*params.End), nil)
@@ -157,6 +164,7 @@ func (m *module) listMetrics(ctx context.Context, orgID valuer.UUID, params *met
sb.Where(sb.Like("lower(metric_name)", fmt.Sprintf("%%%s%%", searchLower)))
}
sb.GroupBy("metric_name")
sb.OrderBy("metric_name ASC")
sb.Limit(params.Limit)
@@ -170,43 +178,47 @@ func (m *module) listMetrics(ctx context.Context, orgID valuer.UUID, params *met
}
defer rows.Close()
metricNames := make([]string, 0)
var metrics []metricsexplorertypes.ListMetric
var metricNames []string
for rows.Next() {
var name string
if err := rows.Scan(&name); err != nil {
return nil, errors.WrapInternalf(err, errors.CodeInternal, "failed to scan metric name")
var metric metricsexplorertypes.ListMetric
if err := rows.Scan(
&metric.MetricName,
&metric.Description,
&metric.MetricType,
&metric.MetricUnit,
&metric.Temporality,
&metric.IsMonotonic,
); err != nil {
return nil, errors.WrapInternalf(err, errors.CodeInternal, "failed to scan metric")
}
metricNames = append(metricNames, name)
metrics = append(metrics, metric)
metricNames = append(metricNames, metric.MetricName)
}
if err := rows.Err(); err != nil {
return nil, errors.WrapInternalf(err, errors.CodeInternal, "error iterating metric names")
return nil, errors.WrapInternalf(err, errors.CodeInternal, "error iterating metrics")
}
if len(metricNames) == 0 {
if len(metrics) == 0 {
return &metricsexplorertypes.ListMetricsResponse{
Metrics: []metricsexplorertypes.ListMetric{},
}, nil
}
metadata, err := m.GetMetricMetadataMulti(ctx, orgID, metricNames)
// Overlay any user-updated metadata on top of the timeseries metadata.
updatedMetadata, err := m.fetchUpdatedMetadata(ctx, orgID, metricNames)
if err != nil {
return nil, err
}
metrics := make([]metricsexplorertypes.ListMetric, 0, len(metricNames))
for _, name := range metricNames {
metric := metricsexplorertypes.ListMetric{
MetricName: name,
for i := range metrics {
if meta, ok := updatedMetadata[metrics[i].MetricName]; ok && meta != nil {
metrics[i].Description = meta.Description
metrics[i].MetricType = meta.MetricType
metrics[i].MetricUnit = meta.MetricUnit
metrics[i].Temporality = meta.Temporality
metrics[i].IsMonotonic = meta.IsMonotonic
}
if meta, ok := metadata[name]; ok && meta != nil {
metric.Description = meta.Description
metric.MetricType = meta.MetricType
metric.MetricUnit = meta.MetricUnit
metric.Temporality = meta.Temporality
metric.IsMonotonic = meta.IsMonotonic
}
metrics = append(metrics, metric)
}
return &metricsexplorertypes.ListMetricsResponse{
@@ -243,19 +255,18 @@ func (m *module) GetStats(ctx context.Context, orgID valuer.UUID, req *metricsex
}, nil
}
// Get metadata for all metrics
// Overlay any user-updated metadata on top of the timeseries metadata
// that was already fetched in the combined query.
metricNames := make([]string, len(metricStats))
for i := range metricStats {
metricNames[i] = metricStats[i].MetricName
}
metadata, err := m.GetMetricMetadataMulti(ctx, orgID, metricNames)
updatedMetadata, err := m.fetchUpdatedMetadata(ctx, orgID, metricNames)
if err != nil {
return nil, err
}
// Enrich stats with metadata
enrichStatsWithMetadata(metricStats, metadata)
enrichStatsWithMetadata(metricStats, updatedMetadata)
return &metricsexplorertypes.StatsResponse{
Metrics: metricStats,
@@ -984,11 +995,14 @@ func (m *module) fetchMetricsStatsWithSamples(
samplesTable, _ := telemetrymetrics.WhichSamplesTableToUse(uint64(req.Start), uint64(req.End), metrictypes.UnspecifiedType, metrictypes.TimeAggregationUnspecified, nil)
countExp := telemetrymetrics.CountExpressionForSamplesTable(samplesTable)
// Timeseries counts per metric
// Timeseries counts and metadata per metric.
tsSB := sqlbuilder.NewSelectBuilder()
tsSB.Select(
"metric_name",
"uniq(fingerprint) AS timeseries",
"anyLast(description) AS description",
"anyLast(type) AS metric_type",
"argMax(unit, unix_milli) AS metric_unit",
)
tsSB.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, distributedTsTable))
tsSB.Where(tsSB.Between("unix_milli", start, end))
@@ -1036,6 +1050,9 @@ func (m *module) fetchMetricsStatsWithSamples(
"COALESCE(ts.timeseries, 0) AS timeseries",
"COALESCE(s.samples, 0) AS samples",
"COUNT(*) OVER() AS total",
"ts.description AS description",
"ts.metric_type AS metric_type",
"ts.metric_unit AS metric_unit",
)
finalSB.From("__time_series_counts ts")
finalSB.JoinWithOption(sqlbuilder.FullOuterJoin, "__sample_counts s", "ts.metric_name = s.metric_name")
@@ -1071,7 +1088,7 @@ func (m *module) fetchMetricsStatsWithSamples(
metricStat metricsexplorertypes.Stat
rowTotal uint64
)
if err := rows.Scan(&metricStat.MetricName, &metricStat.TimeSeries, &metricStat.Samples, &rowTotal); err != nil {
if err := rows.Scan(&metricStat.MetricName, &metricStat.TimeSeries, &metricStat.Samples, &rowTotal, &metricStat.Description, &metricStat.MetricType, &metricStat.MetricUnit); err != nil {
return nil, 0, errors.WrapInternalf(err, errors.CodeInternal, "failed to scan metrics stats row")
}
metricStats = append(metricStats, metricStat)