This is an automated email from the ASF dual-hosted git repository.
karan pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/druid.git
The following commit(s) were added to refs/heads/master by this push:
new 2c5c121c601 Add supervisorId as a dimension to task stat metrics
(#18920)
2c5c121c601 is described below
commit 2c5c121c601e933eed252542e2ca2a8069fd820b
Author: Lucas Capistrant <[email protected]>
AuthorDate: Thu Jan 15 22:20:44 2026 -0600
Add supervisorId as a dimension to task stat metrics (#18920)
* Add supervisorId as a dimension to task stats
'null' value for all tasks that are not of type SeekableStreamIndextask
* Refactor how non-supervisor tasks are handled
* update metrics
---
docs/operations/metrics.md | 10 +++++-----
.../embedded/indexing/KafkaClusterMetricsTest.java | 3 ++-
.../org/apache/druid/indexing/overlord/TaskQueue.java | 16 ++++++++++++++--
.../apache/druid/server/coordinator/stats/Dimension.java | 3 ++-
4 files changed, 23 insertions(+), 9 deletions(-)
diff --git a/docs/operations/metrics.md b/docs/operations/metrics.md
index a1d1af43e8b..f663990244e 100644
--- a/docs/operations/metrics.md
+++ b/docs/operations/metrics.md
@@ -318,11 +318,11 @@ If the JVM does not support CPU time measurement for the
current thread, `ingest
|`segment/added/bytes`|Size in bytes of new segments created.| `dataSource`,
`taskId`, `taskType`, `groupId`, `interval`, `tags`|Varies|
|`segment/moved/bytes`|Size in bytes of segments moved/archived via the Move
Task.| `dataSource`, `taskId`, `taskType`, `groupId`, `interval`, `tags`|Varies|
|`segment/nuked/bytes`|Size in bytes of segments deleted via the Kill Task.|
`dataSource`, `taskId`, `taskType`, `groupId`, `interval`, `tags`|Varies|
-|`task/success/count`|Number of successful tasks per emission period. This
metric is available only if the `TaskCountStatsMonitor` module is included.|
`dataSource`,`taskType`|Varies|
-|`task/failed/count`|Number of failed tasks per emission period. This metric
is available only if the `TaskCountStatsMonitor` module is
included.|`dataSource`,`taskType`|Varies|
-|`task/running/count`|Number of current running tasks. This metric is
available only if the `TaskCountStatsMonitor` module is
included.|`dataSource`,`taskType`|Varies|
-|`task/pending/count`|Number of current pending tasks. This metric is
available only if the `TaskCountStatsMonitor` module is
included.|`dataSource`,`taskType`|Varies|
-|`task/waiting/count`|Number of current waiting tasks. This metric is
available only if the `TaskCountStatsMonitor` module is
included.|`dataSource`,`taskType`|Varies|
+|`task/success/count`|Number of successful tasks per emission period. This
metric is available only if the `TaskCountStatsMonitor` module is included.|
`dataSource`,`taskType`, `supervisorId`|Varies|
+|`task/failed/count`|Number of failed tasks per emission period. This metric
is available only if the `TaskCountStatsMonitor` module is
included.|`dataSource`,`taskType`, `supervisorId`|Varies|
+|`task/running/count`|Number of current running tasks. This metric is
available only if the `TaskCountStatsMonitor` module is
included.|`dataSource`,`taskType`, `supervisorId`|Varies|
+|`task/pending/count`|Number of current pending tasks. This metric is
available only if the `TaskCountStatsMonitor` module is
included.|`dataSource`,`taskType`, `supervisorId`|Varies|
+|`task/waiting/count`|Number of current waiting tasks. This metric is
available only if the `TaskCountStatsMonitor` module is
included.|`dataSource`,`taskType`, `supervisorId`|Varies|
|`taskSlot/total/count`|Number of total task slots per emission period. This
metric is available only if the `TaskSlotCountStatsMonitor` module is
included.| `category`|Varies|
|`taskSlot/idle/count`|Number of idle task slots per emission period. This
metric is available only if the `TaskSlotCountStatsMonitor` module is
included.| `category`|Varies|
|`taskSlot/used/count`|Number of busy task slots per emission period. This
metric is available only if the `TaskSlotCountStatsMonitor` module is
included.| `category`|Varies|
diff --git
a/embedded-tests/src/test/java/org/apache/druid/testing/embedded/indexing/KafkaClusterMetricsTest.java
b/embedded-tests/src/test/java/org/apache/druid/testing/embedded/indexing/KafkaClusterMetricsTest.java
index 8200bb33556..b2b47c8e5f0 100644
---
a/embedded-tests/src/test/java/org/apache/druid/testing/embedded/indexing/KafkaClusterMetricsTest.java
+++
b/embedded-tests/src/test/java/org/apache/druid/testing/embedded/indexing/KafkaClusterMetricsTest.java
@@ -197,7 +197,8 @@ public class KafkaClusterMetricsTest extends
EmbeddedClusterTestBase
// Wait for a task to succeed
overlord.latchableEmitter().waitForEventAggregate(
event -> event.hasMetricName("task/success/count")
- .hasDimension(DruidMetrics.DATASOURCE, dataSource),
+ .hasDimension(DruidMetrics.DATASOURCE, dataSource)
+ .hasDimension(DruidMetrics.SUPERVISOR_ID, supervisorId),
agg -> agg.hasSumAtLeast(1)
);
// Wait for some segments to be published
diff --git
a/indexing-service/src/main/java/org/apache/druid/indexing/overlord/TaskQueue.java
b/indexing-service/src/main/java/org/apache/druid/indexing/overlord/TaskQueue.java
index 5f64e18e942..01447abaa83 100644
---
a/indexing-service/src/main/java/org/apache/druid/indexing/overlord/TaskQueue.java
+++
b/indexing-service/src/main/java/org/apache/druid/indexing/overlord/TaskQueue.java
@@ -52,6 +52,7 @@ import
org.apache.druid.indexing.common.task.batch.parallel.SinglePhaseParallelI
import org.apache.druid.indexing.overlord.config.DefaultTaskConfig;
import org.apache.druid.indexing.overlord.config.TaskLockConfig;
import org.apache.druid.indexing.overlord.config.TaskQueueConfig;
+import org.apache.druid.indexing.seekablestream.SeekableStreamIndexTask;
import org.apache.druid.java.util.common.DateTimes;
import org.apache.druid.java.util.common.ISE;
import org.apache.druid.java.util.common.StringUtils;
@@ -1210,7 +1211,18 @@ public class TaskQueue
if (task == null) {
return RowKey.empty();
}
- return RowKey.with(Dimension.DATASOURCE, task.getDataSource())
- .and(Dimension.TASK_TYPE, task.getType());
+
+ String supervisorId = null;
+ if (task instanceof SeekableStreamIndexTask) {
+ supervisorId = ((SeekableStreamIndexTask<?, ?, ?>)
task).getSupervisorId();
+ }
+
+ RowKey.Builder builder = RowKey.with(Dimension.DATASOURCE,
task.getDataSource())
+ .with(Dimension.TASK_TYPE, task.getType());
+
+ if (supervisorId != null) {
+ builder.with(Dimension.SUPERVISOR_ID, supervisorId);
+ }
+ return builder.build();
}
}
diff --git
a/server/src/main/java/org/apache/druid/server/coordinator/stats/Dimension.java
b/server/src/main/java/org/apache/druid/server/coordinator/stats/Dimension.java
index 7001f7fa455..9f662f9186f 100644
---
a/server/src/main/java/org/apache/druid/server/coordinator/stats/Dimension.java
+++
b/server/src/main/java/org/apache/druid/server/coordinator/stats/Dimension.java
@@ -30,7 +30,8 @@ public enum Dimension
DUTY("duty"),
DUTY_GROUP("dutyGroup"),
DESCRIPTION("description"),
- SERVER("server");
+ SERVER("server"),
+ SUPERVISOR_ID("supervisorId");
private final String reportedName;
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
