-
Notifications
You must be signed in to change notification settings - Fork 1.5k
Add upsert support for offline tables #17789
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Open
xiangfu0
wants to merge
2
commits into
apache:master
Choose a base branch
from
xiangfu0:feature/offline-table-upsert-support
base: master
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
+582
−36
Open
Changes from all commits
Commits
Show all changes
2 commits
Select commit
Hold shift + click to select a range
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -31,6 +31,7 @@ | |
| import org.apache.pinot.common.exception.TableNotFoundException; | ||
| import org.apache.pinot.common.metrics.ServerQueryPhase; | ||
| import org.apache.pinot.core.data.manager.InstanceDataManager; | ||
| import org.apache.pinot.core.data.manager.offline.OfflineTableDataManager; | ||
| import org.apache.pinot.core.data.manager.realtime.RealtimeTableDataManager; | ||
| import org.apache.pinot.core.query.pruner.SegmentPrunerService; | ||
| import org.apache.pinot.core.query.pruner.SegmentPrunerStatistics; | ||
|
|
@@ -81,10 +82,9 @@ public static SingleTableExecutionInfo create(InstanceDataManager instanceDataMa | |
| indexSegments.add(segmentDataManager.getSegment()); | ||
| } | ||
| } else { | ||
| RealtimeTableDataManager rtdm = (RealtimeTableDataManager) tableDataManager; | ||
| TableUpsertMetadataManager tumm = rtdm.getTableUpsertMetadataManager(); | ||
| TableUpsertMetadataManager tumm = getTableUpsertMetadataManager(tableDataManager); | ||
| boolean isUsingConsistencyMode = | ||
| rtdm.getTableUpsertMetadataManager().getContext().getConsistencyMode() != UpsertConfig.ConsistencyMode.NONE; | ||
| tumm.getContext().getConsistencyMode() != UpsertConfig.ConsistencyMode.NONE; | ||
| if (isUsingConsistencyMode) { | ||
|
Comment on lines
+85
to
88
|
||
| tumm.lockForSegmentContexts(); | ||
| } | ||
|
|
@@ -134,12 +134,25 @@ private static boolean isUpsertTable(TableDataManager tableDataManager) { | |
| // those segments in the list of segments for query to process on the server, otherwise, the query will see less | ||
| // than expected valid docs from the upsert table. | ||
| if (tableDataManager instanceof RealtimeTableDataManager) { | ||
| RealtimeTableDataManager rtdm = (RealtimeTableDataManager) tableDataManager; | ||
| return rtdm.isUpsertEnabled(); | ||
| return ((RealtimeTableDataManager) tableDataManager).isUpsertEnabled(); | ||
| } | ||
| if (tableDataManager instanceof OfflineTableDataManager) { | ||
| return ((OfflineTableDataManager) tableDataManager).isUpsertEnabled(); | ||
| } | ||
| return false; | ||
| } | ||
|
|
||
| @Nullable | ||
| private static TableUpsertMetadataManager getTableUpsertMetadataManager(TableDataManager tableDataManager) { | ||
| if (tableDataManager instanceof RealtimeTableDataManager) { | ||
| return ((RealtimeTableDataManager) tableDataManager).getTableUpsertMetadataManager(); | ||
| } | ||
| if (tableDataManager instanceof OfflineTableDataManager) { | ||
| return ((OfflineTableDataManager) tableDataManager).getTableUpsertMetadataManager(); | ||
| } | ||
| return null; | ||
| } | ||
|
|
||
| private SingleTableExecutionInfo(TableDataManager tableDataManager, List<SegmentDataManager> segmentDataManagers, | ||
| List<IndexSegment> indexSegments, Map<IndexSegment, SegmentContext> providedSegmentContexts, | ||
| List<String> segmentsToQuery, List<String> optionalSegments, List<String> notAcquiredSegments) { | ||
|
|
||
Oops, something went wrong.
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Offline upsert path doesn’t handle the partition upsert metadata manager’s preload mode. Unlike RealtimeTableDataManager, this code never calls
preloadSegments(...)and doesn’t branch onpartitionUpsertMetadataManager.isPreloading()to usepreloadSegment(...). If preload is enabled in the upsert config, the preload flag may remain true and segments will be processed via the slower add/replace path (and potentially with different registration ordering than intended). Consider adding the preload trigger (based on ZK metadata partition id) and a preload branch mirroring the realtime implementation.