tarun11Mavani commented on code in PR #19041:
URL: https://github.com/apache/pinot/pull/19041#discussion_r3797110296
##########
pinot-segment-local/src/main/java/org/apache/pinot/segment/local/segment/creator/impl/openstruct/OpenStructColumnSplitter.java:
##########
@@ -246,17 +254,57 @@ public void seal()
writeSparseJsonColumn(sparseKeys);
}
- if (_coercionFailures > 0) {
- LOGGER.info("OPEN_STRUCT '{}': dropped {} values due to type coercion
failures", _columnName, _coercionFailures);
- ServerMetrics serverMetrics = ServerMetrics.get();
- if (serverMetrics != null) {
-
serverMetrics.addMeteredGlobalValue(ServerMeter.OPEN_STRUCT_TYPE_COERCION_FAILURES,
_coercionFailures);
- }
+ long totalCoercionFailures =
_coercionFailuresPerKey.values().stream().mapToLong(Long::longValue).sum();
+ if (totalCoercionFailures > 0) {
+ LOGGER.info("OPEN_STRUCT '{}': dropped {} values due to type coercion
failures (keys: {})",
+ _columnName, totalCoercionFailures, _coercionFailuresPerKey);
+ }
+ long totalInferenceFailures =
_inferenceFailuresPerKey.values().stream().mapToLong(Long::longValue).sum();
+ if (totalInferenceFailures > 0) {
+ LOGGER.info("OPEN_STRUCT '{}': {} type inference failures fell back to
STRING (keys: {})",
+ _columnName, totalInferenceFailures, _inferenceFailuresPerKey);
}
+ emitMetrics(sparseKeys.size());
emitParentColumnMetadata(sparseKeys);
}
+ private void emitMetrics(int sparseKeyCount) {
+ ServerMetrics serverMetrics = ServerMetrics.get();
+ if (serverMetrics == null || _numDocs == 0) {
+ return;
+ }
+ String col = _columnName;
+
+ long totalCoercion =
_coercionFailuresPerKey.values().stream().mapToLong(Long::longValue).sum();
+ if (totalCoercion > 0) {
+ serverMetrics.addMeteredTableValue(_tableNameWithType, col,
+ ServerMeter.OPEN_STRUCT_TYPE_COERCION_FAILURES, totalCoercion);
+ }
+ long totalInference =
_inferenceFailuresPerKey.values().stream().mapToLong(Long::longValue).sum();
+ if (totalInference > 0) {
+ serverMetrics.addMeteredTableValue(_tableNameWithType, col,
+ ServerMeter.OPEN_STRUCT_TYPE_INFERENCE_FAILURES, totalInference);
+ }
+
+ serverMetrics.setOrUpdateTableGauge(_tableNameWithType, col,
+ ServerGauge.OPEN_STRUCT_DENSE_KEY_COUNT, _resolvedDenseKeys.size());
+ serverMetrics.setOrUpdateTableGauge(_tableNameWithType, col,
+ ServerGauge.OPEN_STRUCT_SPARSE_KEY_COUNT, sparseKeyCount);
+ serverMetrics.setOrUpdateTableGauge(_tableNameWithType, col,
+ ServerGauge.OPEN_STRUCT_TOTAL_KEYS_DISCOVERED,
_presenceBitmaps.size());
+
+ for (String key : _resolvedDenseKeys) {
+ RoaringBitmap presence = _presenceBitmaps.get(key);
+ if (presence != null) {
+ long fillPct = (long) presence.getCardinality() * 100 / _numDocs;
Review Comment:
Went with emitting them separately — dropped the percentage gauge.
`OPEN_STRUCT_LAST_SEGMENT_KEY_DOC_COUNT` (per-key) and
`OPEN_STRUCT_LAST_SEGMENT_DOC_COUNT` (denominator) are both raw counts now, so
a key present in 3 of 100k docs reports `3`, not `0`.
--
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]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
