shangxinli commented on code in PR #19868:
URL: https://github.com/apache/hudi/pull/19868#discussion_r3991771395
##########
hudi-client/hudi-client-common/src/test/java/org/apache/hudi/metadata/TestHoodieBackedTableMetadataWriter.java:
##########
@@ -651,4 +651,83 @@ void testPerformTableServicesWithFailureHandling(
// Verify metrics are incremented when there's a failure
verify(metrics,
times(1)).incrementMetric(HoodieMetadataMetrics.PENDING_COMPACTIONS_FAILURES,
1);
}
+
+ @Test
+ void performTableServicesReportsCompletedDeltaCommitsSinceLastCompaction()
throws Exception {
+ // A completed compaction, then three completed delta commits after it,
plus one still inflight.
+ // The gauge must count the three completed instants only, so that it
stays comparable to
+ // hoodie.compact.inline.max.delta.commits, which the compaction trigger
evaluates the same way.
+ List<HoodieInstant> instants = new ArrayList<>();
+ instants.add(INSTANT_GENERATOR.createNewInstant(
+ HoodieInstant.State.COMPLETED, HoodieTimeline.DELTA_COMMIT_ACTION,
"001", "0011"));
+ instants.add(INSTANT_GENERATOR.createNewInstant(
+ HoodieInstant.State.COMPLETED, HoodieTimeline.COMMIT_ACTION, "002",
"0021"));
+ instants.add(INSTANT_GENERATOR.createNewInstant(
+ HoodieInstant.State.COMPLETED, HoodieTimeline.DELTA_COMMIT_ACTION,
"003", "0031"));
+ instants.add(INSTANT_GENERATOR.createNewInstant(
+ HoodieInstant.State.COMPLETED, HoodieTimeline.DELTA_COMMIT_ACTION,
"004", "0041"));
+ instants.add(INSTANT_GENERATOR.createNewInstant(
+ HoodieInstant.State.COMPLETED, HoodieTimeline.DELTA_COMMIT_ACTION,
"005", "0051"));
+ instants.add(INSTANT_GENERATOR.createNewInstant(
+ HoodieInstant.State.INFLIGHT, HoodieTimeline.DELTA_COMMIT_ACTION,
"006"));
+
+ HoodieMetadataMetrics metrics = mock(HoodieMetadataMetrics.class);
+ writerForTableServices(metrics,
createMockTimeline(instants)).performTableServices(Option.empty(), true);
+
+ verify(metrics, times(1)).updateDeltaCommitsSinceLastCompaction(3L);
+ }
+
+ @Test
+ void performTableServicesReportsAllDeltaCommitsWhenNeverCompacted() throws
Exception {
Review Comment:
Folded into one `@ParameterizedTest` over `(instants, expected)`. Added a
failure-path assertion as well, since the sample now runs in `finally`.
##########
hudi-client/hudi-client-common/src/test/java/org/apache/hudi/metadata/TestHoodieBackedTableMetadataWriter.java:
##########
@@ -523,7 +523,7 @@ private static void setField(Object target, String name,
Object value) throws Ex
}
@SuppressWarnings("deprecation")
- private HoodieActiveTimeline createMockTimeline(List<HoodieInstant>
instants) {
+ private static HoodieActiveTimeline createMockTimeline(List<HoodieInstant>
instants) {
Review Comment:
Reverted, unnecessary churn.
##########
hudi-client/hudi-client-common/src/test/java/org/apache/hudi/metadata/TestHoodieBackedTableMetadataWriter.java:
##########
@@ -651,4 +651,83 @@ void testPerformTableServicesWithFailureHandling(
// Verify metrics are incremented when there's a failure
verify(metrics,
times(1)).incrementMetric(HoodieMetadataMetrics.PENDING_COMPACTIONS_FAILURES,
1);
}
+
+ @Test
+ void performTableServicesReportsCompletedDeltaCommitsSinceLastCompaction()
throws Exception {
+ // A completed compaction, then three completed delta commits after it,
plus one still inflight.
+ // The gauge must count the three completed instants only, so that it
stays comparable to
+ // hoodie.compact.inline.max.delta.commits, which the compaction trigger
evaluates the same way.
Review Comment:
Right, `hoodie.metadata.compact.max.delta.commits` is the key operators
actually set. Fixed.
##########
hudi-common/src/main/java/org/apache/hudi/metadata/HoodieMetadataMetrics.java:
##########
@@ -164,6 +181,48 @@ public void updateSizeMetrics(HoodieTableMetaClient
metaClient, HoodieBackedTabl
for (Map.Entry<String, String> e : stats.entrySet()) {
setMetric(e.getKey(), Long.parseLong(e.getValue()));
}
+ long totalBaseFiles = sumStat(stats, metadataPartitions,
STAT_COUNT_BASE_FILES);
Review Comment:
Both of these are resolved by dropping the three size gauges rather than
documenting the gating: only `deltaCommitsSinceLastCompaction` remains, and it
is not gated on `hoodie.metadata.enable.detailed.metrics`. @voonhous thanks for
pinning down the default and the derivability, that is what decided it.
##########
hudi-common/src/main/java/org/apache/hudi/metadata/HoodieMetadataMetrics.java:
##########
@@ -84,6 +85,22 @@ public class HoodieMetadataMetrics implements Serializable {
public static final String LOG_COMPACTION_FAILURES =
"logcompaction_failures";
public static final String PENDING_COMPACTIONS_FAILURES =
"pending_compactions_failures";
+ // Metadata table compaction health. The existing per-partition
baseFileCount/logFileCount gauges
+ // show the current shape of the metadata table, but not whether compaction
is keeping up with it.
+ // Completed delta commits on the metadata table since the last completed
compaction, sampled before
+ // table services run. On a healthy table this sawtooths up to
hoodie.metadata.compact.max.delta.commits
+ // and falls back after each compaction, so alert on a multiple of that
config rather than on the
+ // config value itself. A value that climbs past the peak and keeps going
means metadata table
+ // compaction is not being scheduled or is failing.
+ public static final String STAT_DELTA_COMMITS_SINCE_LAST_COMPACTION =
"deltaCommitsSinceLastCompaction";
+ // Base and log file counts summed across all enabled metadata partitions.
+ public static final String STAT_TOTAL_BASE_FILE_COUNT = "totalBaseFileCount";
+ public static final String STAT_TOTAL_LOG_FILE_COUNT = "totalLogFileCount";
+ // Log files per base file across the whole metadata table, as a percentage,
since gauges are long
+ // valued: 100 means one log file per base file, 500 means five. A rising
value means readers must
Review Comment:
Moot now, those three constants are gone.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
