kazusa
/
skywalking
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Add time unit in so11y latency metrics (#12719)

This commit is contained in:
kezhenxu94 2024-10-23 17:25:15 +08:00 committed by GitHub
parent 80d3e2951d
commit 38b775ed2a
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
35 changed files with 199 additions and 119 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
docs/en/changes/changes.md
View File

@ -12,6 +12,31 @@
* Add Component ID(5023) for the GoZero framework.
* Support Kong monitoring.
* Support adding additional attr[0-4] for service level metrics.
* All self observability histogram metrics names are suffixed with `_seconds` to indicate the time unit, as per [Prometheus metrics names guide](https://prometheus.io/docs/practices/naming/),
if you have any customized configuration files that utilize these metrics, you can migrate the metrics names with our helper script `tools/migrate-so11y-metrics-names.sh`,
this script migrates the metrics names in files `*.yaml`, `*.java`, and `*.json` files, review and adjust the script if you have other file types.
NOTE: the script doesn't migrate existing metrics data.
* `browser_error_log_in_latency` -> `browser_error_log_in_latency_seconds`
* `browser_perf_data_in_latency` -> `browser_perf_data_in_latency_seconds`
* `envoy_als_in_latency` -> `envoy_als_in_latency_seconds`
* `envoy_metric_in_latency` -> `envoy_metric_in_latency_seconds`
* `event_in_latency` -> `event_in_latency_seconds`
* `graphql_query_latency` -> `graphql_query_latency_seconds`
* `k8s_als_in_latency` -> `k8s_als_in_latency_seconds`
* `log_in_latency` -> `log_in_latency_seconds`
* `mesh_analysis_latency` -> `mesh_analysis_latency_seconds`
* `meter_batch_in_latency` -> `meter_batch_in_latency_seconds`
* `meter_in_latency` -> `meter_in_latency_seconds`
* `otel_logs_latency` -> `otel_logs_latency_seconds`
* `otel_metrics_latency` -> `otel_metrics_latency_seconds`
* `otel_spans_latency` -> `otel_spans_latency_seconds`
* `persistence_timer_bulk_all_latency` -> `persistence_timer_bulk_all_latency_seconds`
* `persistence_timer_bulk_execute_latency` -> `persistence_timer_bulk_execute_latency_seconds`
* `persistence_timer_bulk_prepare_latency` -> `persistence_timer_bulk_prepare_latency_seconds`
* `profile_task_in_latency` -> `profile_task_in_latency_seconds`
* `remote_in_latency` -> `remote_in_latency_seconds`
* `telegraf_in_latency` -> `telegraf_in_latency_seconds`
* `trace_in_latency` -> `trace_in_latency_seconds`
#### UI

64
docs/en/setup/backend/grafana-cluster.json
View File

@ -1177,12 +1177,12 @@
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(trace_in_latency_count{job=\"$job\"}[1m]))",
"expr": "sum(rate(trace_in_latency_seconds_count{job=\"$job\"}[1m]))",
"legendFormat": "total",
"refId": "B"
},
{
"expr": "rate(trace_in_latency_count{job=\"$job\"}[1m])",
"expr": "rate(trace_in_latency_seconds_count{job=\"$job\"}[1m])",
"legendFormat": "{{instance}}-{{protocol}}",
"refId": "A"
}
@ -1271,7 +1271,7 @@
"steppedLine": false,
"targets": [
{
"expr": "increase(trace_in_latency_sum{job=\"$job\"}[1m])",
"expr": "increase(trace_in_latency_seconds_sum{job=\"$job\"}[1m])",
"format": "time_series",
"hide": false,
"instant": false,
@ -1454,12 +1454,12 @@
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(mesh_analysis_latency_count{job=\"$job\"}[1m]))",
"expr": "sum(rate(mesh_analysis_latency_seconds_count{job=\"$job\"}[1m]))",
"legendFormat": "total",
"refId": "A"
},
{
"expr": "rate(mesh_analysis_latency_count{job=\"$job\"}[1m])",
"expr": "rate(mesh_analysis_latency_seconds_count{job=\"$job\"}[1m])",
"legendFormat": "{{instance}}",
"refId": "B"
}
@ -1548,7 +1548,7 @@
"steppedLine": false,
"targets": [
{
"expr": "increase(mesh_analysis_latency_sum{job=\"$job\"}[1m])",
"expr": "increase(mesh_analysis_latency_seconds_sum{job=\"$job\"}[1m])",
"format": "time_series",
"hide": false,
"instant": false,
@ -1829,7 +1829,7 @@
"steppedLine": false,
"targets": [
{
"expr": "increase(k8s_als_in_latency_sum{job=\"$job\"}[1m])",
"expr": "increase(k8s_als_in_latency_seconds_sum{job=\"$job\"}[1m])",
"interval": "",
"legendFormat": "{{instance}}",
"refId": "A"
@ -2006,12 +2006,12 @@
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(meter_in_latency_count{job=\"$job\"}[1m]))",
"expr": "sum(rate(meter_in_latency_seconds_count{job=\"$job\"}[1m]))",
"legendFormat": "total",
"refId": "A"
},
{
"expr": "rate(meter_in_latency_count{job=\"$job\"}[1m])",
"expr": "rate(meter_in_latency_seconds_count{job=\"$job\"}[1m])",
"legendFormat": "{{instance}}-{{protocol}}",
"refId": "B"
}
@ -2100,7 +2100,7 @@
"steppedLine": false,
"targets": [
{
"expr": "increase(meter_in_latency_sum{job=\"$job\"}[1m])",
"expr": "increase(meter_in_latency_seconds_sum{job=\"$job\"}[1m])",
"format": "time_series",
"hide": false,
"instant": false,
@ -2287,12 +2287,12 @@
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(log_in_latency_count{job=\"$job\"}[1m]))",
"expr": "sum(rate(log_in_latency_seconds_count{job=\"$job\"}[1m]))",
"legendFormat": "total",
"refId": "A"
},
{
"expr": "rate(log_in_latency_count{job=\"$job\"}[1m])",
"expr": "rate(log_in_latency_seconds_count{job=\"$job\"}[1m])",
"legendFormat": "{{instance}}-{{protocol}}",
"refId": "B"
}
@ -2381,7 +2381,7 @@
"steppedLine": false,
"targets": [
{
"expr": "increase(log_in_latency_sum{job=\"$job\"}[1m])",
"expr": "increase(log_in_latency_seconds_sum{job=\"$job\"}[1m])",
"format": "time_series",
"hide": false,
"instant": false,
@ -2568,12 +2568,12 @@
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(event_in_latency_count{job=\"$job\"}[1m]))",
"expr": "sum(rate(event_in_latency_seconds_count{job=\"$job\"}[1m]))",
"legendFormat": "total",
"refId": "A"
},
{
"expr": "rate(event_in_latency_count{job=\"$job\"}[1m])",
"expr": "rate(event_in_latency_seconds_count{job=\"$job\"}[1m])",
"legendFormat": "{{instance}}-{{protocol}}",
"refId": "B"
}
@ -2662,7 +2662,7 @@
"steppedLine": false,
"targets": [
{
"expr": "increase(event_in_latency_sum{job=\"$job\"}[1m])",
"expr": "increase(event_in_latency_seconds_sum{job=\"$job\"}[1m])",
"format": "time_series",
"hide": false,
"instant": false,
@ -2849,12 +2849,12 @@
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(browser_perf_data_in_latency_count{job=\"$job\"}[1m]))",
"expr": "sum(rate(browser_perf_data_in_latency_seconds_count{job=\"$job\"}[1m]))",
"legendFormat": "total",
"refId": "A"
},
{
"expr": "rate(browser_perf_data_in_latency_count{job=\"$job\"}[1m])",
"expr": "rate(browser_perf_data_in_latency_seconds_count{job=\"$job\"}[1m])",
"legendFormat": "{{instance}}-{{protocol}}",
"refId": "B"
}
@ -2943,7 +2943,7 @@
"steppedLine": false,
"targets": [
{
"expr": "increase(browser_perf_data_in_latency_sum{job=\"$job\"}[1m])",
"expr": "increase(browser_perf_data_in_latency_seconds_sum{job=\"$job\"}[1m])",
"format": "time_series",
"hide": false,
"instant": false,
@ -3130,12 +3130,12 @@
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(browser_error_log_in_latency_count{job=\"$job\"}[1m]))",
"expr": "sum(rate(browser_error_log_in_latency_seconds_seconds_count{job=\"$job\"}[1m]))",
"legendFormat": "total",
"refId": "A"
},
{
"expr": "rate(browser_error_log_in_latency_count{job=\"$job\"}[1m])",
"expr": "rate(browser_error_log_in_latency_seconds_seconds_count{job=\"$job\"}[1m])",
"legendFormat": "{{instance}}-{{protocol}}",
"refId": "B"
}
@ -3224,7 +3224,7 @@
"steppedLine": false,
"targets": [
{
"expr": "increase(browser_error_log_in_latency_sum{job=\"$job\"}[1m])",
"expr": "increase(browser_error_log_in_latency_seconds_seconds_sum{job=\"$job\"}[1m])",
"format": "time_series",
"hide": false,
"instant": false,
@ -3692,13 +3692,13 @@
"steppedLine": false,
"targets": [
{
"expr": "sum(increase(trace_in_latency_count{job=\"$job\",protocol=~\"kafka-fetcher|grpc\"}[1h]))",
"expr": "sum(increase(trace_in_latency_seconds_count{job=\"$job\",protocol=~\"kafka-fetcher|grpc\"}[1h]))",
"interval": "1h",
"legendFormat": "Current Week",
"refId": "B"
},
{
"expr": "sum(increase(trace_in_latency_count{job=\"$job\",protocol=~\"kafka-fetcher|grpc\"}[1h] offset 1w))",
"expr": "sum(increase(trace_in_latency_seconds_count{job=\"$job\",protocol=~\"kafka-fetcher|grpc\"}[1h] offset 1w))",
"interval": "1h",
"legendFormat": "Last Week",
"refId": "A"
@ -3787,13 +3787,13 @@
"steppedLine": false,
"targets": [
{
"expr": "sum(increase(trace_in_latency_count{job=\"$job\",protocol=~\"kafka-fetcher|grpc\"}[1d]))",
"expr": "sum(increase(trace_in_latency_seconds_count{job=\"$job\",protocol=~\"kafka-fetcher|grpc\"}[1d]))",
"interval": "1d",
"legendFormat": "Current Week",
"refId": "B"
},
{
"expr": "sum(increase(trace_in_latency_count{job=\"$job\",protocol=~\"kafka-fetcher|grpc\"}[1d] offset 1w))",
"expr": "sum(increase(trace_in_latency_seconds_count{job=\"$job\",protocol=~\"kafka-fetcher|grpc\"}[1d] offset 1w))",
"interval": "1d",
"legendFormat": "Last Week",
"refId": "A"
@ -4066,12 +4066,12 @@
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(remote_in_latency_count{job=\"$job\"}[1m]))",
"expr": "sum(rate(remote_in_latency_seconds_count{job=\"$job\"}[1m]))",
"legendFormat": "total",
"refId": "A"
},
{
"expr": "rate(remote_in_latency_count{job=\"$job\"}[1m])",
"expr": "rate(remote_in_latency_seconds_count{job=\"$job\"}[1m])",
"legendFormat": "{{instance}}",
"refId": "B"
}
@ -4231,7 +4231,7 @@
"steppedLine": false,
"targets": [
{
"expr": "increase(persistence_timer_bulk_prepare_latency_count{job=\"$job\"}[1m])",
"expr": "increase(persistence_timer_bulk_prepare_latency_seconds_count{job=\"$job\"}[1m])",
"instant": false,
"interval": "1m",
"legendFormat": "{{instance}}",
@ -4322,7 +4322,7 @@
"steppedLine": false,
"targets": [
{
"expr": "increase(persistence_timer_bulk_prepare_latency_sum{job=\"$job\"}[1m])",
"expr": "increase(persistence_timer_bulk_prepare_latency_seconds_sum{job=\"$job\"}[1m])",
"interval": "1m",
"legendFormat": "{{instance}}",
"refId": "A"
@ -4412,7 +4412,7 @@
"steppedLine": false,
"targets": [
{
"expr": "increase(persistence_timer_bulk_execute_latency_count{job=\"$job\"}[1m])",
"expr": "increase(persistence_timer_bulk_execute_latency_seconds_count{job=\"$job\"}[1m])",
"interval": "1m",
"legendFormat": "{{instance}}",
"refId": "A"
@ -4502,7 +4502,7 @@
"steppedLine": false,
"targets": [
{
"expr": "increase(persistence_timer_bulk_execute_latency_sum{job=\"$job\"}[1m])",
"expr": "increase(persistence_timer_bulk_execute_latency_seconds_sum{job=\"$job\"}[1m])",
"interval": "1m",
"legendFormat": "{{instance}}",
"refId": "A"

48
docs/en/setup/backend/grafana-instance.json
View File

@ -1787,7 +1787,7 @@
"steppedLine": false,
"targets": [
{
"expr": "rate(trace_in_latency_count{instance=\"$instance\",job=\"$job\"}[1m])",
"expr": "rate(trace_in_latency_seconds_count{instance=\"$instance\",job=\"$job\"}[1m])",
"format": "time_series",
"hide": false,
"intervalFactor": 1,
@ -1879,7 +1879,7 @@
"steppedLine": false,
"targets": [
{
"expr": "increase(trace_in_latency_sum{instance=\"$instance\",job=\"$job\"}[1m])",
"expr": "increase(trace_in_latency_seconds_sum{instance=\"$instance\",job=\"$job\"}[1m])",
"format": "time_series",
"hide": false,
"instant": false,
@ -2064,7 +2064,7 @@
"steppedLine": false,
"targets": [
{
"expr": "rate(mesh_analysis_latency_count{instance=\"$instance\",job=\"$job\"}[1m])",
"expr": "rate(mesh_analysis_latency_seconds_count{instance=\"$instance\",job=\"$job\"}[1m])",
"format": "time_series",
"hide": false,
"intervalFactor": 1,
@ -2156,7 +2156,7 @@
"steppedLine": false,
"targets": [
{
"expr": "increase(mesh_analysis_latency_sum{instance=\"$instance\",job=\"$job\"}[1m])",
"expr": "increase(mesh_analysis_latency_seconds_sum{instance=\"$instance\",job=\"$job\"}[1m])",
"format": "time_series",
"hide": false,
"instant": false,
@ -2426,7 +2426,7 @@
"steppedLine": false,
"targets": [
{
"expr": "increase(k8s_als_in_latency_sum{instance=\"$instance\",job=\"$job\"}[1m])",
"expr": "increase(k8s_als_in_latency_seconds_sum{instance=\"$instance\",job=\"$job\"}[1m])",
"interval": "",
"legendFormat": "",
"refId": "A"
@ -2599,7 +2599,7 @@
"steppedLine": false,
"targets": [
{
"expr": "rate(meter_in_latency_count{instance=\"$instance\",job=\"$job\"}[1m])",
"expr": "rate(meter_in_latency_seconds_count{instance=\"$instance\",job=\"$job\"}[1m])",
"format": "time_series",
"hide": false,
"intervalFactor": 1,
@ -2691,7 +2691,7 @@
"steppedLine": false,
"targets": [
{
"expr": "increase(meter_in_latency_sum{instance=\"$instance\",job=\"$job\"}[1m])",
"expr": "increase(meter_in_latency_seconds_sum{instance=\"$instance\",job=\"$job\"}[1m])",
"format": "time_series",
"hide": false,
"instant": false,
@ -2876,7 +2876,7 @@
"steppedLine": false,
"targets": [
{
"expr": "rate(log_in_latency_count{instance=\"$instance\",job=\"$job\"}[1m])",
"expr": "rate(log_in_latency_seconds_count{instance=\"$instance\",job=\"$job\"}[1m])",
"format": "time_series",
"hide": false,
"intervalFactor": 1,
@ -2968,7 +2968,7 @@
"steppedLine": false,
"targets": [
{
"expr": "increase(log_in_latency_sum{instance=\"$instance\",job=\"$job\"}[1m])",
"expr": "increase(log_in_latency_seconds_sum{instance=\"$instance\",job=\"$job\"}[1m])",
"format": "time_series",
"hide": false,
"instant": false,
@ -3153,7 +3153,7 @@
"steppedLine": false,
"targets": [
{
"expr": "rate(event_in_latency_count{instance=\"$instance\",job=\"$job\"}[1m])",
"expr": "rate(event_in_latency_seconds_count{instance=\"$instance\",job=\"$job\"}[1m])",
"format": "time_series",
"hide": false,
"intervalFactor": 1,
@ -3245,7 +3245,7 @@
"steppedLine": false,
"targets": [
{
"expr": "increase(event_in_latency_sum{instance=\"$instance\",job=\"$job\"}[1m])",
"expr": "increase(event_in_latency_seconds_sum{instance=\"$instance\",job=\"$job\"}[1m])",
"format": "time_series",
"hide": false,
"instant": false,
@ -3430,7 +3430,7 @@
"steppedLine": false,
"targets": [
{
"expr": "rate(browser_perf_data_in_latency_count{instance=\"$instance\",job=\"$job\"}[1m])",
"expr": "rate(browser_perf_data_in_latency_seconds_count{instance=\"$instance\",job=\"$job\"}[1m])",
"format": "time_series",
"hide": false,
"intervalFactor": 1,
@ -3522,7 +3522,7 @@
"steppedLine": false,
"targets": [
{
"expr": "increase(browser_perf_data_in_latency_sum{instance=\"$instance\",job=\"$job\"}[1m])",
"expr": "increase(browser_perf_data_in_latency_seconds_sum{instance=\"$instance\",job=\"$job\"}[1m])",
"format": "time_series",
"hide": false,
"instant": false,
@ -3707,7 +3707,7 @@
"steppedLine": false,
"targets": [
{
"expr": "rate(browser_error_log_in_latency_count{instance=\"$instance\",job=\"$job\"}[1m])",
"expr": "rate(browser_error_log_in_latency_seconds_seconds_count{instance=\"$instance\",job=\"$job\"}[1m])",
"format": "time_series",
"hide": false,
"intervalFactor": 1,
@ -3799,7 +3799,7 @@
"steppedLine": false,
"targets": [
{
"expr": "increase(browser_error_log_in_latency_sum{instance=\"$instance\",job=\"$job\"}[1m])",
"expr": "increase(browser_error_log_in_latency_seconds_seconds_sum{instance=\"$instance\",job=\"$job\"}[1m])",
"format": "time_series",
"hide": false,
"instant": false,
@ -4261,7 +4261,7 @@
"steppedLine": false,
"targets": [
{
"expr": "sum(increase(trace_in_latency_count{job=\"$job\",instance=\"$instance\",protocol=~\"kafka-fetcher|grpc\"}[1h]))",
"expr": "sum(increase(trace_in_latency_seconds_count{job=\"$job\",instance=\"$instance\",protocol=~\"kafka-fetcher|grpc\"}[1h]))",
"format": "time_series",
"hide": false,
"interval": "1h",
@ -4270,7 +4270,7 @@
"refId": "A"
},
{
"expr": "sum(increase(trace_in_latency_count{job=\"$job\",instance=\"$instance\",protocol=~\"kafka-fetcher|grpc\"}[1h] offset 1w))",
"expr": "sum(increase(trace_in_latency_seconds_count{job=\"$job\",instance=\"$instance\",protocol=~\"kafka-fetcher|grpc\"}[1h] offset 1w))",
"interval": "1h",
"legendFormat": "Last Week",
"refId": "B"
@ -4359,7 +4359,7 @@
"steppedLine": false,
"targets": [
{
"expr": "sum(increase(trace_in_latency_count{job=\"$job\",instance=\"$instance\",protocol=~\"kafka-fetcher|grpc\"}[1d]))",
"expr": "sum(increase(trace_in_latency_seconds_count{job=\"$job\",instance=\"$instance\",protocol=~\"kafka-fetcher|grpc\"}[1d]))",
"format": "time_series",
"hide": false,
"interval": "1d",
@ -4368,7 +4368,7 @@
"refId": "A"
},
{
"expr": "sum(increase(trace_in_latency_count{job=\"$job\",instance=\"$instance\",protocol=~\"kafka-fetcher|grpc\"}[1d] offset 1w))",
"expr": "sum(increase(trace_in_latency_seconds_count{job=\"$job\",instance=\"$instance\",protocol=~\"kafka-fetcher|grpc\"}[1d] offset 1w))",
"interval": "1d",
"legendFormat": "Last Week",
"refId": "B"
@ -4641,7 +4641,7 @@
"steppedLine": false,
"targets": [
{
"expr": "rate(remote_in_latency_count{instance=\"$instance\",job=\"$job\"}[1m])",
"expr": "rate(remote_in_latency_seconds_count{instance=\"$instance\",job=\"$job\"}[1m])",
"format": "time_series",
"hide": false,
"intervalFactor": 1,
@ -4796,7 +4796,7 @@
"steppedLine": false,
"targets": [
{
"expr": "increase(persistence_timer_bulk_prepare_latency_count{instance=\"$instance\",job=\"$job\"}[1m])",
"expr": "increase(persistence_timer_bulk_prepare_latency_seconds_count{instance=\"$instance\",job=\"$job\"}[1m])",
"format": "time_series",
"hide": false,
"interval": "1m",
@ -4889,7 +4889,7 @@
"steppedLine": false,
"targets": [
{
"expr": "increase(persistence_timer_bulk_prepare_latency_sum{instance=\"$instance\",job=\"$job\"}[1m])",
"expr": "increase(persistence_timer_bulk_prepare_latency_seconds_sum{instance=\"$instance\",job=\"$job\"}[1m])",
"format": "time_series",
"hide": false,
"interval": "1m",
@ -4982,7 +4982,7 @@
"steppedLine": false,
"targets": [
{
"expr": "increase(persistence_timer_bulk_execute_latency_count{instance=\"$instance\",job=\"$job\"}[1m])",
"expr": "increase(persistence_timer_bulk_execute_latency_seconds_count{instance=\"$instance\",job=\"$job\"}[1m])",
"format": "time_series",
"hide": false,
"interval": "1m",
@ -5075,7 +5075,7 @@
"steppedLine": false,
"targets": [
{
"expr": "increase(persistence_timer_bulk_execute_latency_sum{instance=\"$instance\",job=\"$job\"}[1m])",
"expr": "increase(persistence_timer_bulk_execute_latency_seconds_sum{instance=\"$instance\",job=\"$job\"}[1m])",
"format": "time_series",
"hide": false,
"interval": "1m",

4
oap-server/server-core/src/main/java/org/apache/skywalking/oap/server/core/analysis/meter/function/avg/AvgHistogramFunction.java
View File

@ -48,8 +48,8 @@ import lombok.extern.slf4j.Slf4j;
* The acceptable bucket value should be a result from one of "increase", "rate" and "irate" query functions. That means
* the value is the increase or per-second instant rate of increase in a specific range.
*
* Example: "persistence_timer_bulk_execute_latency" is histogram, the possible PromQL format of acceptable bucket value
* should be: "increase(persistence_timer_bulk_execute_latency{service="oap-server", instance="localhost:1234"}[5m])"
* Example: "persistence_timer_bulk_execute_latency_seconds" is histogram, the possible PromQL format of acceptable bucket value
* should be: "increase(persistence_timer_bulk_execute_latency_seconds{service="oap-server", instance="localhost:1234"}[5m])"
*/
@MeterFunction(functionName = "avgHistogram")
@Slf4j

4
oap-server/server-core/src/main/java/org/apache/skywalking/oap/server/core/analysis/meter/function/avg/AvgHistogramPercentileFunction.java
View File

@ -62,8 +62,8 @@ import org.apache.skywalking.oap.server.library.util.CollectionUtils;
* Then AvgPercentileFunction calculates percentile based on the above buckets.
*
* Example:
* "persistence_timer_bulk_execute_latency" is histogram, the possible PromQL format of acceptable bucket value should be:
* "increase(persistence_timer_bulk_execute_latency{service="oap-server", instance="localhost:1234"}[5m])"
* "persistence_timer_bulk_execute_latency_seconds" is histogram, the possible PromQL format of acceptable bucket value should be:
* "increase(persistence_timer_bulk_execute_latency_seconds{service="oap-server", instance="localhost:1234"}[5m])"
*/
@MeterFunction(functionName = "avgHistogramPercentile")
@Slf4j

2
oap-server/server-core/src/main/java/org/apache/skywalking/oap/server/core/remote/RemoteServiceHandler.java
View File

@ -87,7 +87,7 @@ public class RemoteServiceHandler extends RemoteServiceGrpc.RemoteServiceImplBas
.provider()
.getService(MetricsCreator.class)
.createHistogramMetric(
"remote_in_latency",
"remote_in_latency_seconds",
"The latency(server side) of inside remote inside aggregate rpc.",
MetricsTag.EMPTY_KEY, MetricsTag.EMPTY_VALUE
);

6
oap-server/server-core/src/main/java/org/apache/skywalking/oap/server/core/storage/PersistenceTimer.java
View File

@ -68,14 +68,14 @@ public enum PersistenceTimer {
MetricsTag.EMPTY_KEY, MetricsTag.EMPTY_VALUE
);
prepareLatency = metricsCreator.createHistogramMetric(
"persistence_timer_bulk_prepare_latency",
"persistence_timer_bulk_prepare_latency_seconds",
"Latency of the prepare stage in persistence timer",
MetricsTag.EMPTY_KEY, MetricsTag.EMPTY_VALUE,
// 50ms -> 30s should be a proper range for the persistence timer prepare stage
.05, .075, .1, .25, .5, .75, 1, 3, 5, 10, 30
);
executeLatency = metricsCreator.createHistogramMetric(
"persistence_timer_bulk_execute_latency",
"persistence_timer_bulk_execute_latency_seconds",
"Latency of the execute stage in persistence timer",
MetricsTag.EMPTY_KEY, MetricsTag.EMPTY_VALUE,
// 500ms -> 2min should be a proper range for the persistence timer execute stage
@ -83,7 +83,7 @@ public enum PersistenceTimer {
0.5, 1, 3, 5, 10, 15, 20, 25, 50, 120
);
allLatency = metricsCreator.createHistogramMetric(
"persistence_timer_bulk_all_latency", "Latency of the all stage in persistence timer",
"persistence_timer_bulk_all_latency_seconds", "Latency of the all stage in persistence timer",
MetricsTag.EMPTY_KEY, MetricsTag.EMPTY_VALUE,
// 500ms -> 2min should be a proper range for the persistence timer
0.5, 1, 3, 5, 10, 15, 20, 25, 50, 120

2
oap-server/server-fetcher-plugin/kafka-fetcher-plugin/src/main/java/org/apache/skywalking/oap/server/analyzer/agent/kafka/provider/handler/LogHandler.java
View File

@ -49,7 +49,7 @@ public class LogHandler extends AbstractKafkaHandler {
.provider()
.getService(MetricsCreator.class);
histogram = metricsCreator.createHistogramMetric(
"log_in_latency",
"log_in_latency_seconds",
"The process latency of log",
new MetricsTag.Keys("protocol", "data_format"),
new MetricsTag.Values("kafka", getDataFormat())

4
oap-server/server-fetcher-plugin/kafka-fetcher-plugin/src/main/java/org/apache/skywalking/oap/server/analyzer/agent/kafka/provider/handler/MeterServiceHandler.java
View File

@ -50,13 +50,13 @@ public class MeterServiceHandler extends AbstractKafkaHandler {
.provider()
.getService(MetricsCreator.class);
histogram = metricsCreator.createHistogramMetric(
"meter_in_latency",
"meter_in_latency_seconds",
"The process latency of meter",
new MetricsTag.Keys("protocol"),
new MetricsTag.Values("kafka")
);
histogramBatch = metricsCreator.createHistogramMetric(
"meter_batch_in_latency",
"meter_batch_in_latency_seconds",
"The process latency of meter",
new MetricsTag.Keys("protocol"),
new MetricsTag.Values("kafka")

2
oap-server/server-fetcher-plugin/kafka-fetcher-plugin/src/main/java/org/apache/skywalking/oap/server/analyzer/agent/kafka/provider/handler/ProfileTaskHandler.java
View File

@ -49,7 +49,7 @@ public class ProfileTaskHandler extends AbstractKafkaHandler {
.provider()
.getService(MetricsCreator.class);
histogram = metricsCreator.createHistogramMetric(
"profile_task_in_latency",
"profile_task_in_latency_seconds",
"The process latency of profile task",
new Keys("protocol"),
new Values("kafka")

2
oap-server/server-fetcher-plugin/kafka-fetcher-plugin/src/main/java/org/apache/skywalking/oap/server/analyzer/agent/kafka/provider/handler/TraceSegmentHandler.java
View File

@ -54,7 +54,7 @@ public class TraceSegmentHandler extends AbstractKafkaHandler {
.provider().getService(MetricsCreator.class);
histogram = metricsCreator.createHistogramMetric(
"trace_in_latency",
"trace_in_latency_seconds",
"The process latency of trace data",
new MetricsTag.Keys("protocol"),
new MetricsTag.Values("kafka")

2
oap-server/server-query-plugin/query-graphql-plugin/src/main/java/org/apache/skywalking/oap/query/graphql/GraphQLQueryHandler.java
View File

@ -48,7 +48,7 @@ public class GraphQLQueryHandler {
.provider()
.getService(MetricsCreator.class)
.createHistogramMetric(
"graphql_query_latency",
"graphql_query_latency_seconds",
"The processing latency of graphql query",
MetricsTag.EMPTY_KEY,
MetricsTag.EMPTY_VALUE);

2
oap-server/server-receiver-plugin/envoy-metrics-receiver-plugin/src/main/java/org/apache/skywalking/oap/server/receiver/envoy/AccessLogServiceGRPCHandler.java
View File

@ -86,7 +86,7 @@ public class AccessLogServiceGRPCHandler extends AccessLogServiceGrpc.AccessLogS
MetricsTag.EMPTY_VALUE
);
histogram = metricCreator.createHistogramMetric(
"envoy_als_in_latency", "The process latency of service ALS metric receiver", MetricsTag.EMPTY_KEY,
"envoy_als_in_latency_seconds", "The process latency of service ALS metric receiver", MetricsTag.EMPTY_KEY,
MetricsTag.EMPTY_VALUE
);
sourceDispatcherCounter = metricCreator.createCounter(

2
oap-server/server-receiver-plugin/envoy-metrics-receiver-plugin/src/main/java/org/apache/skywalking/oap/server/receiver/envoy/MetricServiceGRPCHandler.java
View File

@ -69,7 +69,7 @@ public class MetricServiceGRPCHandler extends MetricsServiceGrpc.MetricsServiceI
MetricsTag.EMPTY_VALUE
);
histogram = metricsCreator.createHistogramMetric(
"envoy_metric_in_latency", "The process latency of service metrics receiver", MetricsTag.EMPTY_KEY,
"envoy_metric_in_latency_seconds", "The process latency of service metrics receiver", MetricsTag.EMPTY_KEY,
MetricsTag.EMPTY_VALUE
);

2
oap-server/server-receiver-plugin/otel-receiver-plugin/src/main/java/org/apache/skywalking/oap/server/receiver/otel/otlp/OpenTelemetryLogHandler.java
View File

@ -64,7 +64,7 @@ public class OpenTelemetryLogHandler
@Getter(lazy = true)
private final HistogramMetrics processHistogram = getMetricsCreator().createHistogramMetric(
"otel_logs_latency",
"otel_logs_latency_seconds",
"The latency to process the logs request",
MetricsTag.EMPTY_KEY,
MetricsTag.EMPTY_VALUE

2
oap-server/server-receiver-plugin/otel-receiver-plugin/src/main/java/org/apache/skywalking/oap/server/receiver/otel/otlp/OpenTelemetryMetricRequestProcessor.java
View File

@ -85,7 +85,7 @@ public class OpenTelemetryMetricRequestProcessor implements Service {
@Getter(lazy = true)
private final HistogramMetrics processHistogram = getMetricsCreator().createHistogramMetric(
"otel_metrics_latency",
"otel_metrics_latency_seconds",
"The latency to process the metrics request",
MetricsTag.EMPTY_KEY,
MetricsTag.EMPTY_VALUE,

2
oap-server/server-receiver-plugin/otel-receiver-plugin/src/main/java/org/apache/skywalking/oap/server/receiver/otel/otlp/OpenTelemetryTraceHandler.java
View File

@ -74,7 +74,7 @@ public class OpenTelemetryTraceHandler
@Getter(lazy = true)
private final HistogramMetrics processHistogram = getMetricsCreator().createHistogramMetric(
"otel_spans_latency",
"otel_spans_latency_seconds",
"The latency to process the span request",
MetricsTag.EMPTY_KEY,
MetricsTag.EMPTY_VALUE

4
oap-server/server-receiver-plugin/skywalking-browser-receiver-plugin/src/main/java/org/apache/skywalking/oap/server/receiver/browser/provider/handler/grpc/BrowserPerfServiceHandler.java
View File

@ -69,7 +69,7 @@ public class BrowserPerfServiceHandler extends BrowserPerfServiceGrpc.BrowserPer
// performance
perfHistogram = metricsCreator.createHistogramMetric(
"browser_perf_data_in_latency", "The process latency of browser performance data",
"browser_perf_data_in_latency_seconds", "The process latency of browser performance data",
new MetricsTag.Keys("protocol"), new MetricsTag.Values("grpc")
);
perfErrorCounter = metricsCreator.createCounter(
@ -79,7 +79,7 @@ public class BrowserPerfServiceHandler extends BrowserPerfServiceGrpc.BrowserPer
// error log
errorLogHistogram = metricsCreator.createHistogramMetric(
"browser_error_log_in_latency", "The process latency of browser error log", new MetricsTag.Keys("protocol"),
"browser_error_log_in_latency_seconds_seconds", "The process latency of browser error log", new MetricsTag.Keys("protocol"),
new MetricsTag.Values("grpc")
);
logErrorCounter = metricsCreator.createCounter(

4
oap-server/server-receiver-plugin/skywalking-browser-receiver-plugin/src/main/java/org/apache/skywalking/oap/server/receiver/browser/provider/handler/rest/BrowserPerfServiceHTTPHandler.java
View File

@ -64,7 +64,7 @@ public class BrowserPerfServiceHTTPHandler {
.getService(MetricsCreator.class);
perfHistogram = metricsCreator.createHistogramMetric(
"browser_perf_data_in_latency", "The process latency of browser performance data",
"browser_perf_data_in_latency_seconds", "The process latency of browser performance data",
new MetricsTag.Keys("protocol"), new MetricsTag.Values("http")
);
perfErrorCounter = metricsCreator.createCounter(
@ -73,7 +73,7 @@ public class BrowserPerfServiceHTTPHandler {
);
errorLogHistogram = metricsCreator.createHistogramMetric(
"browser_error_log_in_latency", "The process latency of browser error log", new MetricsTag.Keys("protocol"),
"browser_error_log_in_latency_seconds_seconds", "The process latency of browser error log", new MetricsTag.Keys("protocol"),
new MetricsTag.Values("http")
);
logErrorCounter = metricsCreator.createCounter(

2
oap-server/server-receiver-plugin/skywalking-ebpf-receiver-plugin/src/main/java/org/apache/skywalking/oap/server/receiver/ebpf/provider/handler/AccessLogServiceHandler.java
View File

@ -110,7 +110,7 @@ public class AccessLogServiceHandler extends EBPFAccessLogServiceGrpc.EBPFAccess
"k8s_als_error_streams", "The error count of eBPF log streams that OAP failed to process", MetricsTag.EMPTY_KEY,
MetricsTag.EMPTY_VALUE);
this.processHistogram = metricsCreator.createHistogramMetric(
"k8s_als_in_latency", "The processing latency of eBPF log streams", MetricsTag.EMPTY_KEY,
"k8s_als_in_latency_seconds", "The processing latency of eBPF log streams", MetricsTag.EMPTY_KEY,
MetricsTag.EMPTY_VALUE);
this.dropCounter = metricsCreator.createCounter(
"k8s_als_drop_count", "The count of eBPF log entries dropped", MetricsTag.EMPTY_KEY,

2
oap-server/server-receiver-plugin/skywalking-event-receiver-plugin/src/main/java/org/apache/skywalking/oap/server/receiver/event/grpc/EventGrpcServiceHandler.java
View File

@ -54,7 +54,7 @@ public class EventGrpcServiceHandler extends EventServiceGrpc.EventServiceImplBa
.getService(EventAnalyzerService.class);
histogram = metricsCreator.createHistogramMetric(
"event_in_latency", "The process latency of event data",
"event_in_latency_seconds", "The process latency of event data",
new MetricsTag.Keys("protocol"), new MetricsTag.Values("grpc")
);
errorCounter = metricsCreator.createCounter(

2
oap-server/server-receiver-plugin/skywalking-event-receiver-plugin/src/main/java/org/apache/skywalking/oap/server/receiver/event/rest/EventRestServiceHandler.java
View File

@ -52,7 +52,7 @@ public class EventRestServiceHandler {
.getService(EventAnalyzerService.class);
histogram = metricsCreator.createHistogramMetric(
"event_in_latency", "The process latency of event data",
"event_in_latency_seconds", "The process latency of event data",
new MetricsTag.Keys("protocol"), new MetricsTag.Values("http")
);
errorCounter = metricsCreator.createCounter(

2
oap-server/server-receiver-plugin/skywalking-log-receiver-plugin/src/main/java/org/apache/skywalking/oap/server/receiver/log/provider/handler/grpc/LogReportServiceGrpcHandler.java
View File

@ -52,7 +52,7 @@ public class LogReportServiceGrpcHandler extends LogReportServiceGrpc.LogReportS
.getService(ILogAnalyzerService.class);
histogram = metricsCreator.createHistogramMetric(
"log_in_latency", "The process latency of log",
"log_in_latency_seconds", "The process latency of log",
new MetricsTag.Keys("protocol"), new MetricsTag.Values("grpc")
);
errorCounter = metricsCreator.createCounter("log_analysis_error_count", "The error number of log analysis",

2
oap-server/server-receiver-plugin/skywalking-log-receiver-plugin/src/main/java/org/apache/skywalking/oap/server/receiver/log/provider/handler/rest/LogReportServiceHTTPHandler.java
View File

@ -49,7 +49,7 @@ public class LogReportServiceHTTPHandler {
.getService(ILogAnalyzerService.class);
histogram = metricsCreator.createHistogramMetric(
"log_in_latency", "The process latency of log",
"log_in_latency_seconds", "The process latency of log",
new MetricsTag.Keys("protocol"), new MetricsTag.Values("http")
);
errorCounter = metricsCreator.createCounter(

2
oap-server/server-receiver-plugin/skywalking-mesh-receiver-plugin/src/main/java/org/apache/skywalking/aop/server/receiver/mesh/TelemetryDataDispatcher.java
View File

@ -77,7 +77,7 @@ public class TelemetryDataDispatcher {
.provider()
.getService(NamingControl.class);
MESH_ANALYSIS_METRICS = metricsCreator.createHistogramMetric(
"mesh_analysis_latency", "The process latency of service mesh telemetry", MetricsTag.EMPTY_KEY,
"mesh_analysis_latency_seconds", "The process latency of service mesh telemetry", MetricsTag.EMPTY_KEY,
MetricsTag.EMPTY_VALUE
);
MESH_ERROR_METRICS = metricsCreator.createCounter("mesh_analysis_error_count",

2
oap-server/server-receiver-plugin/skywalking-meter-receiver-plugin/src/main/java/org/apache/skywalking/oap/server/receiver/meter/provider/handler/MeterServiceHandler.java
View File

@ -51,7 +51,7 @@ public class MeterServiceHandler extends MeterReportServiceGrpc.MeterReportServi
.provider()
.getService(MetricsCreator.class);
histogram = metricsCreator.createHistogramMetric(
"meter_in_latency", "The process latency of meter",
"meter_in_latency_seconds", "The process latency of meter",
new MetricsTag.Keys("protocol"), new MetricsTag.Values("grpc")
);
errorCounter = metricsCreator.createCounter("meter_analysis_error_count", "The error number of meter analysis",

2
oap-server/server-receiver-plugin/skywalking-telegraf-receiver-plugin/src/main/java/org/apache/skywalking/oap/server/receiver/telegraf/provider/handler/TelegrafServiceHandler.java
View File

@ -59,7 +59,7 @@ public class TelegrafServiceHandler {
.getService(MetricsCreator.class);
histogram = metricsCreator.createHistogramMetric(
"telegraf_in_latency", "The process latency of telegraf data",
"telegraf_in_latency_seconds", "The process latency of telegraf data",
new MetricsTag.Keys("protocol"), new MetricsTag.Values("http")
);

2
oap-server/server-receiver-plugin/skywalking-trace-receiver-plugin/src/main/java/org/apache/skywalking/oap/server/receiver/trace/provider/handler/v8/grpc/TraceSegmentReportServiceHandler.java
View File

@ -51,7 +51,7 @@ public class TraceSegmentReportServiceHandler extends TraceSegmentReportServiceG
.provider()
.getService(MetricsCreator.class);
histogram = metricsCreator.createHistogramMetric(
"trace_in_latency", "The process latency of trace data",
"trace_in_latency_seconds", "The process latency of trace data",
new MetricsTag.Keys("protocol"), new MetricsTag.Values("grpc")
);
errorCounter = metricsCreator.createCounter("trace_analysis_error_count", "The error number of trace analysis",

2
oap-server/server-receiver-plugin/skywalking-trace-receiver-plugin/src/main/java/org/apache/skywalking/oap/server/receiver/trace/provider/handler/v8/rest/TraceSegmentReportHandler.java
View File

@ -46,7 +46,7 @@ public class TraceSegmentReportHandler {
.provider()
.getService(MetricsCreator.class);
histogram = metricsCreator.createHistogramMetric(
"trace_in_latency", "The process latency of trace data",
"trace_in_latency_seconds", "The process latency of trace data",
new MetricsTag.Keys("protocol"), new MetricsTag.Values("http")
);
errorCounter = metricsCreator.createCounter(

2
oap-server/server-receiver-plugin/zipkin-receiver-plugin/src/main/java/org/apache/skywalking/oap/server/receiver/zipkin/handler/ZipkinSpanHTTPHandler.java
View File

@ -51,7 +51,7 @@ public class ZipkinSpanHTTPHandler {
.provider()
.getService(MetricsCreator.class);
histogram = metricsCreator.createHistogramMetric(
"trace_in_latency", "The process latency of trace data",
"trace_in_latency_seconds", "The process latency of trace data",
new MetricsTag.Keys("protocol"), new MetricsTag.Values("zipkin-http")
);
errorCounter = metricsCreator.createCounter(

2
oap-server/server-receiver-plugin/zipkin-receiver-plugin/src/main/java/org/apache/skywalking/oap/server/receiver/zipkin/kafka/KafkaHandler.java
View File

@ -91,7 +91,7 @@ public class KafkaHandler {
.provider()
.getService(MetricsCreator.class);
histogram = metricsCreator.createHistogramMetric(
"trace_in_latency",
"trace_in_latency_seconds",
"The process latency of trace data",
new MetricsTag.Keys("protocol"),
new MetricsTag.Values("zipkin-kafka")

44
oap-server/server-starter/src/main/resources/otel-rules/oap.yaml
View File

@ -49,15 +49,15 @@ metricsRules:
.tag({tags -> if (tags['gc'] == 'PS Scavenge' || tags['gc'] == 'Copy' || tags['gc'] == 'ParNew' || tags['gc'] == 'G1 Young Generation') {tags.gc = 'young_gc_time'} })
.tag({tags -> if (tags['gc'] == 'PS MarkSweep' || tags['gc'] == 'MarkSweepCompact' || tags['gc'] == 'ConcurrentMarkSweep' || tags['gc'] == 'G1 Old Generation') {tags.gc = 'old_gc_time'} })
- name: instance_trace_count
exp: trace_in_latency_count.sum(['service', 'host_name']).increase('PT1M')
exp: trace_in_latency_seconds_count.sum(['service', 'host_name']).increase('PT1M')
- name: instance_trace_latency_percentile
exp: trace_in_latency.sum(['le', 'service', 'host_name']).increase('PT1M').histogram().histogram_percentile([50,70,90,99])
exp: trace_in_latency_seconds.sum(['le', 'service', 'host_name']).increase('PT1M').histogram().histogram_percentile([50,70,90,99])
- name: instance_trace_analysis_error_count
exp: trace_analysis_error_count.sum(['service', 'host_name']).increase('PT1M')
- name: instance_mesh_count
exp: mesh_analysis_latency_count.sum(['service', 'host_name']).increase('PT1M')
exp: mesh_analysis_latency_seconds_count.sum(['service', 'host_name']).increase('PT1M')
- name: instance_mesh_latency_percentile
exp: mesh_analysis_latency.sum(['le', 'service', 'host_name']).increase('PT1M').histogram().histogram_percentile([50,70,90,99])
exp: mesh_analysis_latency_seconds.sum(['le', 'service', 'host_name']).increase('PT1M').histogram().histogram_percentile([50,70,90,99])
- name: instance_mesh_analysis_error_count
exp: mesh_analysis_error_count.sum(['service', 'host_name']).increase('PT1M')
- name: instance_metrics_aggregation
@ -65,15 +65,15 @@ metricsRules:
metrics_aggregation.tagEqual('dimensionality', 'minute').sum(['service', 'host_name', 'level']).increase('PT1M')
.tag({tags -> if (tags['level'] == '1') {tags.level = 'L1 aggregation'} }).tag({tags -> if (tags['level'] == '2') {tags.level = 'L2 aggregation'} })
- name: instance_persistence_execute_percentile
exp: persistence_timer_bulk_execute_latency.sum(['le', 'service', 'host_name']).increase('PT5M').histogram().histogram_percentile([50,70,90,99])
exp: persistence_timer_bulk_execute_latency_seconds.sum(['le', 'service', 'host_name']).increase('PT5M').histogram().histogram_percentile([50,70,90,99])
- name: instance_persistence_prepare_percentile
exp: persistence_timer_bulk_prepare_latency.sum(['le', 'service', 'host_name']).increase('PT5M').histogram().histogram_percentile([50,70,90,99])
exp: persistence_timer_bulk_prepare_latency_seconds.sum(['le', 'service', 'host_name']).increase('PT5M').histogram().histogram_percentile([50,70,90,99])
- name: instance_persistence_error_count
exp: persistence_timer_bulk_error_count.sum(['service', 'host_name']).increase('PT1M')
- name: instance_persistence_execute_count
exp: persistence_timer_bulk_execute_latency_count.sum(['service', 'host_name']).increase('PT1M')
exp: persistence_timer_bulk_execute_latency_seconds_count.sum(['service', 'host_name']).increase('PT1M')
- name: instance_persistence_prepare_count
exp: persistence_timer_bulk_prepare_latency_count.sum(['service', 'host_name']).increase('PT1M')
exp: persistence_timer_bulk_prepare_latency_seconds_count.sum(['service', 'host_name']).increase('PT1M')
- name: instance_metrics_persistent_cache
exp: metrics_persistent_cache.sum(['service', 'host_name', 'status']).increase('PT1M')
- name: jvm_thread_live_count
@ -101,26 +101,26 @@ metricsRules:
- name: instance_k8s_als_drop
exp: k8s_als_drop_count.sum(['service', 'host_name']).increase('PT1M')
- name: instance_k8s_als_latency_percentile
exp: k8s_als_in_latency.sum(['le', 'service', 'host_name']).increase('PT1M').histogram().histogram_percentile([50,70,90,99])
exp: k8s_als_in_latency_seconds.sum(['le', 'service', 'host_name']).increase('PT1M').histogram().histogram_percentile([50,70,90,99])
- name: instance_k8s_als_streams
exp: k8s_als_in_latency_count.sum(['service', 'host_name']).increase('PT1M')
exp: k8s_als_in_latency_seconds_count.sum(['service', 'host_name']).increase('PT1M')
- name: instance_k8s_als_error_streams
exp: k8s_als_error_streams.sum(['service', 'host_name']).increase('PT1M')
- name: otel_metrics_received
exp: otel_metrics_latency_count.sum(['service', 'host_name']).increase('PT1M')
exp: otel_metrics_latency_seconds_count.sum(['service', 'host_name']).increase('PT1M')
- name: otel_logs_received
exp: otel_logs_latency_count.sum(['service', 'host_name']).increase('PT1M')
exp: otel_logs_latency_seconds_count.sum(['service', 'host_name']).increase('PT1M')
- name: otel_spans_received
exp: otel_spans_latency_count.sum(['service', 'host_name']).increase('PT1M')
- name: otel_metrics_latency_percentile
exp: otel_metrics_latency.sum(['le', 'service', 'host_name']).increase('PT1M').histogram().histogram_percentile([50,70,90,99])
- name: otel_logs_latency_percentile
exp: otel_logs_latency.sum(['le', 'service', 'host_name']).increase('PT1M').histogram().histogram_percentile([50,70,90,99])
- name: otel_spans_latency_percentile
exp: otel_spans_latency.sum(['le', 'service', 'host_name']).increase('PT1M').histogram().histogram_percentile([50,70,90,99])
- name: graphql_query_latency_percentile
exp: graphql_query_latency.sum(['le', 'service', 'host_name']).increase('PT5M').histogram().histogram_percentile([50,70,90,99])
exp: otel_spans_latency_seconds_count.sum(['service', 'host_name']).increase('PT1M')
- name: otel_metrics_latency_seconds_percentile
exp: otel_metrics_latency_seconds.sum(['le', 'service', 'host_name']).increase('PT1M').histogram().histogram_percentile([50,70,90,99])
- name: otel_logs_latency_seconds_percentile
exp: otel_logs_latency_seconds.sum(['le', 'service', 'host_name']).increase('PT1M').histogram().histogram_percentile([50,70,90,99])
- name: otel_spans_latency_seconds_percentile
exp: otel_spans_latency_seconds.sum(['le', 'service', 'host_name']).increase('PT1M').histogram().histogram_percentile([50,70,90,99])
- name: graphql_query_latency_seconds_percentile
exp: graphql_query_latency_seconds.sum(['le', 'service', 'host_name']).increase('PT5M').histogram().histogram_percentile([50,70,90,99])
- name: instance_graphql_query_count
exp: graphql_query_latency_count.sum(['service', 'host_name']).increase('PT1M')
exp: graphql_query_latency_seconds_count.sum(['service', 'host_name']).increase('PT1M')
- name: instance_graphql_query_error_count
exp: graphql_query_error_count.sum(['service', 'host_name']).increase('PT1M')

8
oap-server/server-starter/src/main/resources/ui-initialized-templates/so11y_oap/so11y-instance.json
View File

@ -324,7 +324,7 @@
"i": "16",
"type": "Widget",
"expressions": [
"relabels(meter_oap_graphql_query_latency_percentile{p='50,75,90,95,99'},p='50,75,90,95,99',percentile='50,75,90,95,99')"
"relabels(meter_oap_graphql_query_latency_seconds_percentile{p='50,75,90,95,99'},p='50,75,90,95,99',percentile='50,75,90,95,99')"
],
"graph": {
"type": "Line",
@ -606,7 +606,7 @@
"i": "22",
"type": "Widget",
"expressions": [
"relabels(meter_oap_otel_metrics_latency_percentile{p='50,75,90,95,99'},p='50,75,90,95,99',percentile='50,75,90,95,99')"
"relabels(meter_oap_otel_metrics_latency_seconds_percentile{p='50,75,90,95,99'},p='50,75,90,95,99',percentile='50,75,90,95,99')"
],
"graph": {
"type": "Line",
@ -628,7 +628,7 @@
"i": "23",
"type": "Widget",
"expressions": [
"relabels(meter_oap_otel_spans_latency_percentile{p='50,75,90,95,99'},p='50,75,90,95,99',percentile='50,75,90,95,99')"
"relabels(meter_oap_otel_spans_latency_seconds_percentile{p='50,75,90,95,99'},p='50,75,90,95,99',percentile='50,75,90,95,99')"
],
"graph": {
"type": "Line",
@ -650,7 +650,7 @@
"i": "24",
"type": "Widget",
"expressions": [
"relabels(meter_oap_otel_logs_latency_percentile{p='50,75,90,95,99'},p='50,75,90,95,99',percentile='50,75,90,95,99')"
"relabels(meter_oap_otel_logs_latency_seconds_percentile{p='50,75,90,95,99'},p='50,75,90,95,99',percentile='50,75,90,95,99')"
],
"graph": {
"type": "Line",

4
test/e2e-v2/cases/exporter/kafka/exporter-cases.yaml
View File

@ -17,7 +17,7 @@ cases:
# verify traces
- query: |
sleep 10;
trace_in=$(curl -s http://${oap_host}:${oap_1234} | grep trace_in_latency_count{ | awk '{print $2}'); \
trace_in=$(curl -s http://${oap_host}:${oap_1234} | grep trace_in_latency_seconds_count{ | awk '{print $2}'); \
trace_out=$(curl -s http://${oap_host}:${oap_1234} | grep kafka_exporter_trace_success_count{ | awk '{print $2}'); \
awk 'BEGIN {print '$trace_out/$trace_in'}' | yq e '{"result": .}' -
expected: expected/result.yml
@ -28,7 +28,7 @@ cases:
curl -X POST http://${provider_host}:${provider_9090}/logs/trigger > /dev/null;
curl -X POST http://${provider_host}:${provider_9090}/logs/trigger > /dev/null;
sleep 10;
log_in=$(curl -s http://${oap_host}:${oap_1234} | grep log_in_latency_count{ | awk '{print $2}'); \
log_in=$(curl -s http://${oap_host}:${oap_1234} | grep log_in_latency_seconds_count{ | awk '{print $2}'); \
log_out=$(curl -s http://${oap_host}:${oap_1234} | grep kafka_exporter_log_success_count{ | awk '{print $2}'); \
awk 'BEGIN {print '$log_out/$log_in'}' | yq e '{"result": .}' -
expected: expected/result.yml

55
tools/migrate-so11y-metrics-names.sh Executable file
View File

@ -0,0 +1,55 @@
#!/usr/bin/env bash
#
# Licensed to the Apache Software Foundation (ASF) under one or more
# contributor license agreements. See the NOTICE file distributed with
# this work for additional information regarding copyright ownership.
# The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with
# the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
# This script relies on few environment variables to determine source code package
# behavior, those variables are:
# RELEASE_VERSION -- The version of this source package.
# For example: RELEASE_VERSION=5.0.0-alpha
NAME_MAPPINGS=$(cat <<EOF
browser_error_log_in_latency=browser_error_log_in_latency_seconds
browser_perf_data_in_latency=browser_perf_data_in_latency_seconds
envoy_als_in_latency=envoy_als_in_latency_seconds
envoy_metric_in_latency=envoy_metric_in_latency_seconds
event_in_latency=event_in_latency_seconds
graphql_query_latency=graphql_query_latency_seconds
k8s_als_in_latency=k8s_als_in_latency_seconds
log_in_latency=log_in_latency_seconds
mesh_analysis_latency=mesh_analysis_latency_seconds
meter_batch_in_latency=meter_batch_in_latency_seconds
meter_in_latency=meter_in_latency_seconds
otel_logs_latency=otel_logs_latency_seconds
otel_metrics_latency=otel_metrics_latency_seconds
otel_spans_latency=otel_spans_latency_seconds
persistence_timer_bulk_all_latency=persistence_timer_bulk_all_latency_seconds
persistence_timer_bulk_execute_latency=persistence_timer_bulk_execute_latency_seconds
persistence_timer_bulk_prepare_latency=persistence_timer_bulk_prepare_latency_seconds
profile_task_in_latency=profile_task_in_latency_seconds
remote_in_latency=remote_in_latency_seconds
telegraf_in_latency=telegraf_in_latency_seconds
trace_in_latency=trace_in_latency_seconds
EOF
)
while IFS= read -r line; do
IFS='=' read -r original_name new_name description <<< "$line"
find . -type f \( -name "*.yaml" -o -name "*.yml" -o -name "*.java" -o -name "*.json" \) \
| xargs -I{} sed -i '' "s/$original_name/$new_name/g" {};
done <<< "$NAME_MAPPINGS"