[opt](inverted index) Enhance I/O statistics collection for the inverted index in file cache scenarios #48950
Conversation
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
Contributor
|
Thank you for your contribution to Apache Doris. Please clearly describe your PR:
|
zzzxl1993
force-pushed
the
202503121322
branch
2 times, most recently
from
75a9b79 to
2dc3954
Compare
gavinchou
previously approved these changes
May 11, 2025
Contributor
|
PR approved by at least one committer and no changes requested. |
github-actions
bot
added
the
approved
Contributor
|
PR approved by anyone and no changes requested. |
github-actions
bot
removed
the
approved
…ted index in file cache scenarios
github-actions
bot
added
the
approved
Contributor
|
PR approved by at least one committer and no changes requested. |
gavinchou
approved these changes
May 30, 2025
There was a problem hiding this comment.
Pull Request Overview
This PR adds IOContext propagation to various inverted index reader and query components and extends file cache statistics and profiling to separately track inverted-index-specific I/O metrics.
- Pass
io::IOContextthrough inverted index readers, visitors, and query classes for context-aware I/O. - Introduce new fields in
FileCacheStatisticsandFileCacheProfileReporterfor inverted-index local/remote I/O counts, bytes, and timers. - Update
CachedRemoteFileReaderto increment the new inverted-index counters when reading data.
Reviewed Changes
Copilot reviewed 24 out of 24 changed files in this pull request and generated no comments.
Show a summary per file
| File | Description |
|---|---|
| be/src/olap/rowset/segment_v2/inverted_index_reader.{h,cpp} | Add io_ctx parameter paths and store in InvertedIndexVisitor. |
| be/src/olap/rowset/segment_v2/inverted_index/util/*.h | Add io_ctx to ensure_term_* helper signatures. |
| be/src/olap/rowset/segment_v2/inverted_index/query/*.{h,cpp} | Store and use _io_ctx when calling Lucene readers. |
| be/src/io/io_common.h | Define new inverted-index-specific statistics fields. |
| be/src/io/cache/cached_remote_file_reader.cpp | Update inverted-index I/O stats in _update_stats. |
| be/src/io/cache/block_file_cache_profile.h | Add and update profiling counters for inverted-index I/O metrics. |
Comments suppressed due to low confidence (3)
be/src/io/cache/block_file_cache_profile.h:129
- [nitpick] The counter name 'inverted_index_bytes_scanned_from_cache' is inconsistent with the statistic field 'inverted_index_bytes_read_from_local'. Consider renaming one to match the other (e.g., use 'bytes_read_from_cache' or rename the struct field to 'bytes_scanned_from_cache').
inverted_index_bytes_scanned_from_cache = ADD_CHILD_COUNTER_WITH_LEVEL(
be/src/io/cache/block_file_cache_profile.h:159
- [nitpick] Updating 'inverted_index_bytes_scanned_from_cache' from 'statistics->inverted_index_bytes_read_from_local' highlights the naming mismatch. Aligning these names will reduce confusion when analyzing profiling output.
COUNTER_UPDATE(inverted_index_bytes_scanned_from_cache,
be/src/io/cache/cached_remote_file_reader.cpp:357
- New inverted-index-specific counters are updated here. Consider adding or updating unit tests to verify that 'inverted_index_num_local_io_total', 'inverted_index_num_remote_io_total', and related byte/timer counters are correctly incremented under both cache hits and misses.
if (is_inverted_index) {
Member
|
run buildall |
TPC-H: Total hot run time: 33874 ms |
TPC-DS: Total hot run time: 192977 ms |
ClickBench: Total hot run time: 29.41 s |
koarz
pushed a commit
to koarz/doris
that referenced
this pull request
Jun 4, 2025
…ted index in file cache scenarios (apache#48950) Problem Summary: add io statistics in file cache stats for inverted index
This was referenced Jun 26, 2025
dataroaring
pushed a commit
that referenced
this pull request
Jun 27, 2025
koarz
pushed a commit
to koarz/doris
that referenced
this pull request
Jul 3, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
7 participants
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.
What problem does this PR solve?
Issue Number: close #xxx
Related PR: #xxx
Problem Summary:
Release note
None
Check List (For Author)
Test
Behavior changed:
Does this need documentation?
Check List (For Reviewer who merge this PR)