Commit Graph

681 Commits

Author SHA1 Message Date
Yingwen
14550429e9 chore: reduce SeriesScan sender timeout (#6983)
Signed-off-by: evenyag <realevenyag@gmail.com>
2025-09-17 07:02:47 +00:00
Lei, HUANG
c92ab4217f fix: avoid truncating SST statistics during flush (#6977)
fix/disable-parquet-stats-truncate:
 - **Update `memcomparable` Dependency**: Switched from crates.io to a Git repository for `memcomparable` in `Cargo.lock`, `mito-codec/Cargo.toml`, and removed it from `mito2/Cargo.toml`.
 - **Enhance Parquet Writer Properties**: Added `set_statistics_truncate_length` and `set_column_index_truncate_length` to `WriterProperties` in `parquet.rs`, `bulk/part.rs`, `partition_tree/data.rs`, and `writer.rs`.
 - **Add Test for Corrupt Scan**: Introduced a new test module `scan_corrupt.rs` in `mito2/src/engine` to verify handling of corrupt data.
 - **Update Test Data**: Modified test data in `flush.rs` to reflect changes in file sizes and sequences.

Signed-off-by: Lei, HUANG <mrsatangel@gmail.com>
2025-09-17 03:02:52 +00:00
Zhenchi
77981a7de5 fix: clean intm ignore notfound (#6971)
* fix: clean intm ignore notfound

Signed-off-by: Zhenchi <zhongzc_arch@outlook.com>

* address comments

Signed-off-by: Zhenchi <zhongzc_arch@outlook.com>

---------

Signed-off-by: Zhenchi <zhongzc_arch@outlook.com>
2025-09-17 02:58:03 +00:00
Lei, HUANG
9096c5ebbf chore: bump sequence on region edit (#6947)
* chore/update-sequence-on-region-edit:
 ### Commit Message

 Refactor `get_last_seq_num` Method Across Engines

 - **Change Return Type**: Updated the `get_last_seq_num` method to return `Result<SequenceNumber, BoxedError>` instead of `Result<Option<SequenceNumber>, BoxedError>` in the following files:
   - `src/datanode/src/tests.rs`
   - `src/file-engine/src/engine.rs`
   - `src/metric-engine/src/engine.rs`
   - `src/metric-engine/src/engine/read.rs`
   - `src/mito2/src/engine.rs`
   - `src/query/src/optimizer/test_util.rs`
   - `src/store-api/src/region_engine.rs`

 - **Enhance Region Edit Handling**: Modified `RegionWorkerLoop` in `src/mito2/src/worker/handle_manifest.rs` to update file sequences during region edits.

Signed-off-by: Lei, HUANG <mrsatangel@gmail.com>

* add committed_sequence to RegionEdit

Signed-off-by: Lei, HUANG <mrsatangel@gmail.com>

* chore/update-sequence-on-region-edit:
 ### Commit Message

 Refactor sequence retrieval method

 - **Renamed Method**: Changed `get_last_seq_num` to `get_committed_sequence` across multiple files to better reflect its purpose of retrieving the latest committed sequence.
   - Affected files: `tests.rs`, `engine.rs` in `file-engine`, `metric-engine`, `mito2`, `test_util.rs`, and `region_engine.rs`.
 - **Removed Unused Struct**: Deleted `RegionSequencesRequest` struct from `region_request.rs` as it is no longer needed.

Signed-off-by: Lei, HUANG <mrsatangel@gmail.com>

* chore/update-sequence-on-region-edit:
 **Add Committed Sequence Handling in Region Engine**

 - **`engine.rs`**: Introduced a new test module `bump_committed_sequence_test` to verify committed sequence handling.
 - **`bump_committed_sequence_test.rs`**: Added a test to ensure the committed sequence is correctly updated and persisted across region reopenings.
 - **`action.rs`**: Updated `RegionManifest` and `RegionManifestBuilder` to include `committed_sequence` for tracking.
 - **`manager.rs`**: Adjusted manifest size assertion to accommodate new committed sequence data.
 - **`opener.rs`**: Implemented logic to override committed sequence during region opening.
 - **`version.rs`**: Added `set_committed_sequence` method to update the committed sequence in `VersionControl`.

Signed-off-by: Lei, HUANG <mrsatangel@gmail.com>

* chore/update-sequence-on-region-edit:
 **Enhance `test_bump_committed_sequence` in `bump_committed_sequence_test.rs`**

 - Updated the test to include row operations using `build_rows`, `put_rows`, and `rows_schema` to verify the committed sequence behavior.
 - Adjusted assertions to reflect changes in committed sequence after row operations and region edits.
 - Added comments to clarify the expected behavior of committed sequence after reopening the region and replaying the WAL.

Signed-off-by: Lei, HUANG <mrsatangel@gmail.com>

* chore/update-sequence-on-region-edit:
 **Enhance Region Sequence Management**

 - **`bump_committed_sequence_test.rs`**: Updated test to handle region reopening and sequence management, ensuring committed sequences are correctly set and verified after edits.
 - **`opener.rs`**: Improved committed sequence handling by overriding it only if the manifest's sequence is greater than the replayed sequence. Added logging for mutation sequence replay.
 - **`region_write_ctx.rs`**: Modified `push_mutation` and `push_bulk` methods to adopt sequence numbers from parameters, enhancing sequence management during write operations.
 - **`handle_write.rs`**: Updated `RegionWorkerLoop` to pass sequence numbers in `push_bulk` and `push_mutation` methods, ensuring consistent sequence handling.

Signed-off-by: Lei, HUANG <mrsatangel@gmail.com>

* chore/update-sequence-on-region-edit:
 ### Remove Debug Logging from `opener.rs`

 - Removed debug logging for mutation sequences in `opener.rs` to clean up the output and improve performance.

Signed-off-by: Lei, HUANG <mrsatangel@gmail.com>

---------

Signed-off-by: Lei, HUANG <mrsatangel@gmail.com>
2025-09-16 16:22:25 +00:00
Yingwen
b8e0c49cb4 feat: add an flag to enable the experimental flat format (#6976)
* feat: add enable_experimental_flat_format flag to enable flat format

Signed-off-by: evenyag <realevenyag@gmail.com>

* refactor: extract build_scan_input for CompactionSstReaderBuilder

Signed-off-by: evenyag <realevenyag@gmail.com>

* chore: add compact memtable cost to flush metrics

Signed-off-by: evenyag <realevenyag@gmail.com>

* feat: Sets compact dispatcher for bulk memtable

Signed-off-by: evenyag <realevenyag@gmail.com>

* feat: Cast dictionary to target type in FlatProjectionMapper

Signed-off-by: evenyag <realevenyag@gmail.com>

* fix: add time index to FlatProjectionMapper::batch_schema

Signed-off-by: evenyag <realevenyag@gmail.com>

* chore: update config toml

Signed-off-by: evenyag <realevenyag@gmail.com>

* fix: pass flat_format to ProjectionMapper in CompactionSstReaderBuilder

Signed-off-by: evenyag <realevenyag@gmail.com>

---------

Signed-off-by: evenyag <realevenyag@gmail.com>
2025-09-16 09:33:12 +00:00
Zhenchi
db42ad42dc feat: add visible to sst entry for staging mode (#6964)
Signed-off-by: Zhenchi <zhongzc_arch@outlook.com>
2025-09-15 09:05:54 +00:00
Yingwen
b3aabb6706 feat: support flush and compact flat format files (#6949)
* feat: basic functions for flush/compact flat format

Signed-off-by: evenyag <realevenyag@gmail.com>

* feat: bridge flush and compaction for flat format

Signed-off-by: evenyag <realevenyag@gmail.com>

* feat: add write cache support

Signed-off-by: evenyag <realevenyag@gmail.com>

* style: fix clippy

Signed-off-by: evenyag <realevenyag@gmail.com>

* chore: change log level to debug

Signed-off-by: evenyag <realevenyag@gmail.com>

* refactor: wrap duplicated code to merge and dedup iter

Signed-off-by: evenyag <realevenyag@gmail.com>

* refactor: wrap some code into flush_flat_mem_ranges

Signed-off-by: evenyag <realevenyag@gmail.com>

* refactor: extract logic into do_flush_memtables

Signed-off-by: evenyag <realevenyag@gmail.com>

---------

Signed-off-by: evenyag <realevenyag@gmail.com>
2025-09-14 13:36:24 +00:00
Ruihang Xia
d86f489a74 fix: staging mode with proper region edit operations (#6962)
Signed-off-by: Ruihang Xia <waynestxia@gmail.com>
2025-09-12 04:39:42 +00:00
Yingwen
5e65581f94 feat: support flat format for SeriesScan (#6938)
* feat: Support flat format for SeriesScan

Signed-off-by: evenyag <realevenyag@gmail.com>

* test: simplify tests

Signed-off-by: evenyag <realevenyag@gmail.com>

* chore: update comment

Signed-off-by: evenyag <realevenyag@gmail.com>

* chore: only accumulate fetch time to scan_cost in SeriesDistributor of
the SeriesScan

Signed-off-by: evenyag <realevenyag@gmail.com>

* chore: update comment

Signed-off-by: evenyag <realevenyag@gmail.com>

---------

Signed-off-by: evenyag <realevenyag@gmail.com>
2025-09-11 06:12:53 +00:00
Ruihang Xia
2f6da3b718 feat: exiting staging mode on success case (#6913)
* clear staging directories on entering staging mode

Signed-off-by: Ruihang Xia <waynestxia@gmail.com>

* test and merger

Signed-off-by: Ruihang Xia <waynestxia@gmail.com>

* storage accessor

Signed-off-by: Ruihang Xia <waynestxia@gmail.com>

* exit on success

Signed-off-by: Ruihang Xia <waynestxia@gmail.com>

* use remove_all

Signed-off-by: Ruihang Xia <waynestxia@gmail.com>

---------

Signed-off-by: Ruihang Xia <waynestxia@gmail.com>
2025-09-10 01:52:55 +00:00
Ruihang Xia
83290be3ba feat: store partition expr per file in region manifest (#6849)
* feat: store partition expr per file in region manifest

Signed-off-by: Ruihang Xia <waynestxia@gmail.com>

* use deserialized form in memory

Signed-off-by: Ruihang Xia <waynestxia@gmail.com>

* test non-existing partition expr

Signed-off-by: Ruihang Xia <waynestxia@gmail.com>

* try remove partition expr dup

Signed-off-by: Ruihang Xia <waynestxia@gmail.com>

* Revert "try remove partition expr dup"

This reverts commit a0f2c8ca6a127ef356a5510466e84513cf4b13d8.

* fix merge test

Signed-off-by: Ruihang Xia <waynestxia@gmail.com>

* format doc

Signed-off-by: Ruihang Xia <waynestxia@gmail.com>

---------

Signed-off-by: Ruihang Xia <waynestxia@gmail.com>
2025-09-09 23:37:29 +00:00
Zhenchi
21ee981b49 feat: add origin_region_id and node_id to sst entry (#6937)
Signed-off-by: Zhenchi <zhongzc_arch@outlook.com>
2025-09-09 09:45:15 +00:00
Yingwen
9c22092189 feat: Implements compaction for bulk memtable (#6923)
* feat: initial bulk memtable compaction implementation

Signed-off-by: evenyag <realevenyag@gmail.com>

* feat: implement compact for memtable

Signed-off-by: evenyag <realevenyag@gmail.com>

* test: add tests for bulk memtable compaction

Signed-off-by: evenyag <realevenyag@gmail.com>

* style: clippy

Signed-off-by: evenyag <realevenyag@gmail.com>

* chore: address review comments

Signed-off-by: evenyag <realevenyag@gmail.com>

---------

Signed-off-by: evenyag <realevenyag@gmail.com>
2025-09-09 09:15:25 +00:00
Zhenchi
9fe84f6fbd feat(mito): backfill partition expr on region open (#6862)
* feat(mito): backfill partition expr on region open

Signed-off-by: Zhenchi <zhongzc_arch@outlook.com>

* tiny polish

Signed-off-by: Zhenchi <zhongzc_arch@outlook.com>

* only writable leader persists

Signed-off-by: Zhenchi <zhongzc_arch@outlook.com>

* catchup needs backfill

Signed-off-by: Zhenchi <zhongzc_arch@outlook.com>

* add log

Signed-off-by: Zhenchi <zhongzc_arch@outlook.com>

* handle distribute mode

Signed-off-by: Zhenchi <zhongzc_arch@outlook.com>

* only when transfer to set gracefully

Signed-off-by: Zhenchi <zhongzc_arch@outlook.com>

* fix fmt

Signed-off-by: Zhenchi <zhongzc_arch@outlook.com>

---------

Signed-off-by: Zhenchi <zhongzc_arch@outlook.com>
2025-09-09 02:50:01 +00:00
Ruihang Xia
c9377e7c5a build: bump rust edition to 2024 (#6920)
* bump edition

Signed-off-by: Ruihang Xia <waynestxia@gmail.com>

* format

Signed-off-by: Ruihang Xia <waynestxia@gmail.com>

* gen keyword

Signed-off-by: Ruihang Xia <waynestxia@gmail.com>

* lifetime and env var

Signed-off-by: Ruihang Xia <waynestxia@gmail.com>

* one more gen fix

Signed-off-by: Ruihang Xia <waynestxia@gmail.com>

* lifetime of temporaries in tail expressions

Signed-off-by: Ruihang Xia <waynestxia@gmail.com>

* format again

Signed-off-by: Ruihang Xia <waynestxia@gmail.com>

* clippy nested if

Signed-off-by: Ruihang Xia <waynestxia@gmail.com>

* clippy let and return

Signed-off-by: Ruihang Xia <waynestxia@gmail.com>

---------

Signed-off-by: Ruihang Xia <waynestxia@gmail.com>
2025-09-08 02:37:18 +00:00
Weny Xu
658d07bfc8 feat: add written_bytes_since_open column to region_statistics table (#6904)
* feat: add `write_bytes` column to `region_statistics` table

Signed-off-by: WenyXu <wenymedia@gmail.com>

* chore: update comments

Signed-off-by: WenyXu <wenymedia@gmail.com>

* chore: rename `write_bytes` to `written_bytes`

Signed-off-by: WenyXu <wenymedia@gmail.com>

* chore: rename `written_bytes` to `written_bytes_since_open`

Signed-off-by: WenyXu <wenymedia@gmail.com>

* chore: apply suggestions

Signed-off-by: WenyXu <wenymedia@gmail.com>

---------

Signed-off-by: WenyXu <wenymedia@gmail.com>
2025-09-05 07:27:30 +00:00
discord9
f7c8d86ebb feat: file ref mgr (#6844)
* feat: file ref manager

Signed-off-by: discord9 <discord9@163.com>

* refactor: put file ref mgr to sep file

Signed-off-by: discord9 <discord9@163.com>

* chore: rename path

Signed-off-by: discord9 <discord9@163.com>

* test: ref path

Signed-off-by: discord9 <discord9@163.com>

* fix: pass node id

Signed-off-by: discord9 <discord9@163.com>

* chore: after rebase fix

Signed-off-by: discord9 <discord9@163.com>

* feat: exlucde already in manifest files

Signed-off-by: discord9 <discord9@163.com>

* docs: explain why it can work

Signed-off-by: discord9 <discord9@163.com>

* feat: also include manifest versions

Signed-off-by: discord9 <discord9@163.com>

* refactor: per review

Signed-off-by: discord9 <discord9@163.com>

* rename func to imply what's it actually doing

Signed-off-by: discord9 <discord9@163.com>

* more docs

Signed-off-by: discord9 <discord9@163.com>

* docs: expect gc worker to do the job right

Signed-off-by: discord9 <discord9@163.com>

* refactor: partially per review

Signed-off-by: discord9 <discord9@163.com>

* refactor: per review

Signed-off-by: discord9 <discord9@163.com>

* chore: unused

Signed-off-by: discord9 <discord9@163.com>

* metrics: change to per datanode instead

Signed-off-by: discord9 <discord9@163.com>

---------

Signed-off-by: discord9 <discord9@163.com>
2025-09-05 03:45:01 +00:00
Yingwen
8bbb396506 feat: Supports flat format in SeqScan and UnorderedScan (#6905)
* feat: support flat format in SeqScan

Signed-off-by: evenyag <realevenyag@gmail.com>

* feat: support flat format in unordered scan

Signed-off-by: evenyag <realevenyag@gmail.com>

* feat: support parallel read for flat format in SeqScan

Signed-off-by: evenyag <realevenyag@gmail.com>

* refactor: rename flat DedupReader to FlatDedupReader

Signed-off-by: evenyag <realevenyag@gmail.com>

* chore: address review comments

It also precomputes the input arrow schema

Signed-off-by: evenyag <realevenyag@gmail.com>

---------

Signed-off-by: evenyag <realevenyag@gmail.com>
2025-09-04 13:12:24 +00:00
Ruihang Xia
493a1efe65 feat: skip compaction on large file on append only mode (#6838)
* feat: skip compaction on large file on append only mode

Signed-off-by: Ruihang Xia <waynestxia@gmail.com>

* log ignored files

Signed-off-by: Ruihang Xia <waynestxia@gmail.com>

* format

Signed-off-by: Ruihang Xia <waynestxia@gmail.com>

* only ignore level 1 files

Signed-off-by: Ruihang Xia <waynestxia@gmail.com>

* early exit

Signed-off-by: Ruihang Xia <waynestxia@gmail.com>

* fix typo

Signed-off-by: Ruihang Xia <waynestxia@gmail.com>

---------

Signed-off-by: Ruihang Xia <waynestxia@gmail.com>
2025-09-04 12:01:09 +00:00
Yingwen
40a49ddc82 feat: implement basic write/read methods for bulk memtable (#6888)
* feat: implement basic write/read methods for bulk memtable

Signed-off-by: evenyag <realevenyag@gmail.com>

* chore: change update stats atomic ordering

We have already acquired the write lock so Relaxed ordering is fine

Signed-off-by: evenyag <realevenyag@gmail.com>

---------

Signed-off-by: evenyag <realevenyag@gmail.com>
2025-09-04 08:42:05 +00:00
Zhenchi
deb728c38a fix: move prune_region_dir to region drop (#6891)
* fix: move prune_region_dir to region drop

Signed-off-by: Zhenchi <zhongzc_arch@outlook.com>

* address comments

Signed-off-by: Zhenchi <zhongzc_arch@outlook.com>

---------

Signed-off-by: Zhenchi <zhongzc_arch@outlook.com>
2025-09-03 07:11:05 +00:00
Weny Xu
7cf47ccf54 fix: initialize remote WAL regions with correct flushed entry IDs (#6856)
* fix: initialize remote WAL regions with correct flushed entry IDs

Signed-off-by: WenyXu <wenymedia@gmail.com>

* chore: add logs

Signed-off-by: WenyXu <wenymedia@gmail.com>

* fix: correct latest offset

Signed-off-by: WenyXu <wenymedia@gmail.com>

* fix: update sqlness

Signed-off-by: WenyXu <wenymedia@gmail.com>

* feat: add replay checkpoint to catchup request

Signed-off-by: WenyXu <wenymedia@gmail.com>

* chore: apply suggestions

Signed-off-by: WenyXu <wenymedia@gmail.com>

* chore: logs

Signed-off-by: WenyXu <wenymedia@gmail.com>

* chore: apply suggestions

Signed-off-by: WenyXu <wenymedia@gmail.com>

---------

Signed-off-by: WenyXu <wenymedia@gmail.com>
2025-09-03 04:00:02 +00:00
Ruihang Xia
56db1d468a chore: fix typo (#6885)
Signed-off-by: Ruihang Xia <waynestxia@gmail.com>
2025-09-03 02:43:25 +00:00
Zhenchi
9b8f04b065 fix: prune intermediate dirs on index finish and region pruge (#6878)
* fix: prune intermediate dirs on index finish and region pruge

Signed-off-by: Zhenchi <zhongzc_arch@outlook.com>

* address comments

Signed-off-by: Zhenchi <zhongzc_arch@outlook.com>

---------

Signed-off-by: Zhenchi <zhongzc_arch@outlook.com>
2025-09-02 13:57:16 +00:00
Yingwen
8fc42aeb27 feat: Update parquet writer and indexer to support the flat format (#6866)
* feat: implements method to write flat batch for ParquetWriter

Signed-off-by: evenyag <realevenyag@gmail.com>

* feat: add update method for flat RecordBatch in Indexer

Signed-off-by: evenyag <realevenyag@gmail.com>

* feat: calls indexer to write flat batch in ParquetWriter

Signed-off-by: evenyag <realevenyag@gmail.com>

* fix: handle empty projection for flat format

Signed-off-by: evenyag <realevenyag@gmail.com>

* fix: eval array in precise_filter_flat

Signed-off-by: evenyag <realevenyag@gmail.com>

* feat: cache column lookup result in inverted indexer

Signed-off-by: evenyag <realevenyag@gmail.com>

* test: add test

Signed-off-by: evenyag <realevenyag@gmail.com>

* feat: support dict type in dense codec

Signed-off-by: evenyag <realevenyag@gmail.com>

* test: remove read part in test as it need modifying the reader

Signed-off-by: evenyag <realevenyag@gmail.com>

* feat: support dictionary type in other methods for dense codec

Signed-off-by: evenyag <realevenyag@gmail.com>

* refactor: fulltext use string array directly

Signed-off-by: evenyag <realevenyag@gmail.com>

---------

Signed-off-by: evenyag <realevenyag@gmail.com>
2025-09-02 12:48:34 +00:00
Yingwen
ab96703d8f chore: enlarge max file limit to 384 (#6868)
chore: enlarge max concurrent files to 384

Signed-off-by: evenyag <realevenyag@gmail.com>
2025-09-01 09:26:20 +00:00
zyy17
d585c23ba5 refactor: add stop methods for LocalFilePurger and CompactionRegion (#6848)
* refactor: add `LocalFilePurger::stop(&self)` and `stop_file_purger()` of `CompactionRegion`

Signed-off-by: zyy17 <zyylsxm@gmail.com>

* chore: rename methods

Signed-off-by: zyy17 <zyylsxm@gmail.com>

---------

Signed-off-by: zyy17 <zyylsxm@gmail.com>
2025-08-29 09:23:59 +00:00
discord9
bacd9c7d15 feat: add event ts to region manifest (#6751)
* feat: add event ts to region manifest

Signed-off-by: discord9 <discord9@163.com>

delete files

Signed-off-by: discord9 <discord9@163.com>

chore: clippy

Signed-off-by: discord9 <discord9@163.com>

lower concurrency

Signed-off-by: discord9 <discord9@163.com>

feat: gc use delta manifest to get expel time

Signed-off-by: discord9 <discord9@163.com>

docs: terminalogy

Signed-off-by: discord9 <discord9@163.com>

refactor: some advices from review

Signed-off-by: discord9 <discord9@163.com>

feat: manifest add removed files field

Signed-off-by: discord9 <discord9@163.com>

feat(WIP): add remove time in manifest

Signed-off-by: discord9 <discord9@163.com>

wip: more config

Signed-off-by: discord9 <discord9@163.com>

feat: manifest uodate removed files

Signed-off-by: discord9 <discord9@163.com>

test: add remove file opts field

Signed-off-by: discord9 <discord9@163.com>

test: fix test

Signed-off-by: discord9 <discord9@163.com>

chore: delete gc.rs

Signed-off-by: discord9 <discord9@163.com>

* feat: proper option name

Signed-off-by: discord9 <discord9@163.com>

* refactor: per review

Signed-off-by: discord9 <discord9@163.com>

* test: update manifest size

Signed-off-by: discord9 <discord9@163.com>

* test: fix eq

Signed-off-by: discord9 <discord9@163.com>

* refactor: some per review

Signed-off-by: discord9 <discord9@163.com>

* refactor: per review

Signed-off-by: discord9 <discord9@163.com>

* refactor: more per review

Signed-off-by: discord9 <discord9@163.com>

* test: update manifest size

Signed-off-by: discord9 <discord9@163.com>

* test: update config

Signed-off-by: discord9 <discord9@163.com>

* feat: keep count 0 means only use ttl

Signed-off-by: discord9 <discord9@163.com>

---------

Signed-off-by: discord9 <discord9@163.com>
2025-08-28 09:08:18 +00:00
Yingwen
32e73dad12 fix: use actual buf size as cache page value size (#6829)
* feat: cache the cloned page bytes

Signed-off-by: evenyag <realevenyag@gmail.com>

* feat: cache the whole row group pages

The opendal reader may merge IO requests so the pages of different
columns can share the same Bytes.
When we use a per-column page cache, the page cache may still referencing
the whole Bytes after eviction if there are other columns in the cache that
share the same Bytes.

Signed-off-by: evenyag <realevenyag@gmail.com>

* feat: check possible max byte range and copy pages if needed

Signed-off-by: evenyag <realevenyag@gmail.com>

* feat: always copy pages

Signed-off-by: evenyag <realevenyag@gmail.com>

* feat: returns the copied pages

Signed-off-by: evenyag <realevenyag@gmail.com>

* feat: compute cache size by MERGE_GAP

Signed-off-by: evenyag <realevenyag@gmail.com>

* feat: align to buf size

Signed-off-by: evenyag <realevenyag@gmail.com>

* feat: aligh to 2MB

Signed-off-by: evenyag <realevenyag@gmail.com>

* chore: remove unused code

Signed-off-by: evenyag <realevenyag@gmail.com>

* style: fix clippy

Signed-off-by: evenyag <realevenyag@gmail.com>

* chore: fix typo

Signed-off-by: evenyag <realevenyag@gmail.com>

* test: fix parquet read with cache test

Signed-off-by: evenyag <realevenyag@gmail.com>

---------

Signed-off-by: evenyag <realevenyag@gmail.com>
2025-08-28 03:37:11 +00:00
Weny Xu
566a647ec7 feat: add replay checkpoint to reduce overhead for remote WAL (#6816)
* feat: introduce `TopicRegionValue`

Signed-off-by: WenyXu <wenymedia@gmail.com>

* feat: persist region replay checkpoint

Signed-off-by: WenyXu <wenymedia@gmail.com>

* feat: introduce checkpoint

Signed-off-by: WenyXu <wenymedia@gmail.com>

* chore: udpate config.md

Signed-off-by: WenyXu <wenymedia@gmail.com>

* refactor: minor refactor

Signed-off-by: WenyXu <wenymedia@gmail.com>

* feat: send open region instructions with reply checkpoint

Signed-off-by: WenyXu <wenymedia@gmail.com>

* chore: use usize

Signed-off-by: WenyXu <wenymedia@gmail.com>

* fix: fix unit tests

Signed-off-by: WenyXu <wenymedia@gmail.com>

* fix: fix unit tests

Signed-off-by: WenyXu <wenymedia@gmail.com>

* feat: add topic name pattern

Signed-off-by: WenyXu <wenymedia@gmail.com>

* feat: enable wal prune by default

Signed-off-by: WenyXu <wenymedia@gmail.com>

* chore: apply suggestions

Signed-off-by: WenyXu <wenymedia@gmail.com>

* chore: apply suggestions

Signed-off-by: WenyXu <wenymedia@gmail.com>

---------

Signed-off-by: WenyXu <wenymedia@gmail.com>
2025-08-27 07:24:33 +00:00
Yingwen
906e1ca0bf feat: functions and structs to scan flat format file and mem ranges (#6817)
* feat: implement function to scan flat memtable ranges

Signed-off-by: evenyag <realevenyag@gmail.com>

* feat: implement function to scan flat file ranges

Signed-off-by: evenyag <realevenyag@gmail.com>

* chore: compat batch in scan file range

Signed-off-by: evenyag <realevenyag@gmail.com>

* chore: scan other ranges

Signed-off-by: evenyag <realevenyag@gmail.com>

* chore: fix compiler errors

Signed-off-by: evenyag <realevenyag@gmail.com>

---------

Signed-off-by: evenyag <realevenyag@gmail.com>
2025-08-27 06:31:30 +00:00
Arshdeep
8894cb5406 feat: resolve unused dependencies with cargo-udeps (#6578) (#6619)
* feat:resolve unused dependencies with cargo-udeps (#6578)

Signed-off-by: Arshdeep54 <balarsh535@gmail.com>

* Apply suggestion from @zyy17

Co-authored-by: zyy17 <zyylsxm@gmail.com>

* Apply suggestion from @zyy17

Co-authored-by: zyy17 <zyylsxm@gmail.com>

---------

Signed-off-by: Arshdeep54 <balarsh535@gmail.com>
Co-authored-by: Ning Sun <classicning@gmail.com>
Co-authored-by: zyy17 <zyylsxm@gmail.com>
2025-08-26 10:22:53 +00:00
Yingwen
d5575d3fa4 feat: add FlatConvertFormat to convert record batches in old format to the flat format (#6786)
* feat: add convert format to FlatReadFormat

Signed-off-by: evenyag <realevenyag@gmail.com>

* test: test convert format

Signed-off-by: evenyag <realevenyag@gmail.com>

* fix: only convert string pks to dictionary

Signed-off-by: evenyag <realevenyag@gmail.com>

---------

Signed-off-by: evenyag <realevenyag@gmail.com>
2025-08-25 06:47:06 +00:00
Zhenchi
6839b5aef4 feat(mito): list SSTs from manifest and storage (#6766)
* feat(engine): list SSTs from manifest and storage

Signed-off-by: Zhenchi <zhongzc_arch@outlook.com>

* mito engine only

Signed-off-by: Zhenchi <zhongzc_arch@outlook.com>

* try best to remove allocation

Signed-off-by: Zhenchi <zhongzc_arch@outlook.com>

* address comments

Signed-off-by: Zhenchi <zhongzc_arch@outlook.com>

---------

Signed-off-by: Zhenchi <zhongzc_arch@outlook.com>
2025-08-22 09:22:42 +00:00
Weny Xu
896d72191e feat: introduce PersistStatsHandler (#6777)
* feat: add `Inserter` trait and impl

Signed-off-by: WenyXu <wenymedia@gmail.com>

* chore: import items

Signed-off-by: WenyXu <wenymedia@gmail.com>

* feat: introduce `PersistStatsHandler`

Signed-off-by: WenyXu <wenymedia@gmail.com>

* chore: disable persisting stats in sqlness

Signed-off-by: WenyXu <wenymedia@gmail.com>

* reset channel manager

Signed-off-by: WenyXu <wenymedia@gmail.com>

* chore: apply suggestions

Signed-off-by: WenyXu <wenymedia@gmail.com>

* chore: avoid to collect

Signed-off-by: WenyXu <wenymedia@gmail.com>

* refactor: remove insert options

Signed-off-by: WenyXu <wenymedia@gmail.com>

* refactor: use `write_bytes` instead of `write_bytes_per_sec`

Signed-off-by: WenyXu <wenymedia@gmail.com>

* refactor: compute write bytes delta

Signed-off-by: WenyXu <wenymedia@gmail.com>

* chore: apply suggestions

Signed-off-by: WenyXu <wenymedia@gmail.com>

* test: add unit tests

Signed-off-by: WenyXu <wenymedia@gmail.com>

* chore: apply suggestions

Signed-off-by: WenyXu <wenymedia@gmail.com>

* Update src/meta-srv/src/handler/persist_stats_handler.rs

Co-authored-by: Yingwen <realevenyag@gmail.com>

---------

Signed-off-by: WenyXu <wenymedia@gmail.com>
Co-authored-by: Yingwen <realevenyag@gmail.com>
2025-08-21 09:34:58 +00:00
Yingwen
2995eddca5 feat: Implements FlatCompatBatch to adapt schema in flat format (#6771)
* feat: compat flat wip

Signed-off-by: evenyag <realevenyag@gmail.com>

* feat: rewrite key

Signed-off-by: evenyag <realevenyag@gmail.com>

* feat: support append key

Signed-off-by: evenyag <realevenyag@gmail.com>

* refactor: Split rewrite logic

Signed-off-by: evenyag <realevenyag@gmail.com>

* refactor: rename CompatFlatBatch to FlatCompatBatch

Signed-off-by: evenyag <realevenyag@gmail.com>

* feat: compat primary key

Signed-off-by: evenyag <realevenyag@gmail.com>

* chore: address fixme

Signed-off-by: evenyag <realevenyag@gmail.com>

* feat: new CompatBatch if need convert

Signed-off-by: evenyag <realevenyag@gmail.com>

* feat: use different compat

Signed-off-by: evenyag <realevenyag@gmail.com>

* refactor: plain_projection -> flat_projection

Signed-off-by: evenyag <realevenyag@gmail.com>

* feat: test compat

Signed-off-by: evenyag <realevenyag@gmail.com>

* test: test FlatCompatBatch

Signed-off-by: evenyag <realevenyag@gmail.com>

* feat: fix warnings and remove unused code

Signed-off-by: evenyag <realevenyag@gmail.com>

* fix: support compat tags with dictionary types

Signed-off-by: evenyag <realevenyag@gmail.com>

* style: fix clippy

Signed-off-by: evenyag <realevenyag@gmail.com>

* chore: reuse column_id_values

Signed-off-by: evenyag <realevenyag@gmail.com>

* chore: avoid zero pk values len

Signed-off-by: evenyag <realevenyag@gmail.com>

---------

Signed-off-by: evenyag <realevenyag@gmail.com>
2025-08-20 12:36:14 +00:00
Yingwen
8fc3a9a9d7 feat: Implements async FlatMergeReader and FlatDedupReader (#6761)
* refactor: Add Flat prefix to MergeIterator and DedupIterator

Signed-off-by: evenyag <realevenyag@gmail.com>

* feat: implement MergeReader for RecordBatch

Signed-off-by: evenyag <realevenyag@gmail.com>

* refactor: use GenericNode for IterNode

Signed-off-by: evenyag <realevenyag@gmail.com>

* feat: flat merge reader to stream

Signed-off-by: evenyag <realevenyag@gmail.com>

* feat: implement FlatDedupReader

Signed-off-by: evenyag <realevenyag@gmail.com>

* chore: add a benchmark for FlatMergeIterator

Signed-off-by: evenyag <realevenyag@gmail.com>

* refactor: rename plain_projection to flat_projection

Signed-off-by: evenyag <realevenyag@gmail.com>

---------

Signed-off-by: evenyag <realevenyag@gmail.com>
2025-08-19 06:30:59 +00:00
Ruihang Xia
b652ea52ee fix: partition tree's dict size metrics mismatch (#6746)
fix: partition tree metrics mismatch

Signed-off-by: Ruihang Xia <waynestxia@gmail.com>
2025-08-18 08:36:35 +00:00
Weny Xu
f64fc3a57a feat: add RateMeter for tracking memtable write throughput (#6744)
* feat: introduce `RateMeter`

Signed-off-by: WenyXu <wenymedia@gmail.com>

* chore: apply suggestions

Signed-off-by: WenyXu <wenymedia@gmail.com>

---------

Signed-off-by: WenyXu <wenymedia@gmail.com>
2025-08-18 06:45:31 +00:00
LFC
f9d2a89a0c chore: update datafusion family (#6675)
* chore: update datafusion family

Signed-off-by: luofucong <luofc@foxmail.com>

* fix ci

Signed-off-by: luofucong <luofc@foxmail.com>

* use official otel-arrow-rust

Signed-off-by: luofucong <luofc@foxmail.com>

* rebase

Signed-off-by: luofucong <luofc@foxmail.com>

* use the official orc-rust

Signed-off-by: luofucong <luofc@foxmail.com>

* resolve PR comments

Signed-off-by: luofucong <luofc@foxmail.com>

* remove the empty lines

Signed-off-by: luofucong <luofc@foxmail.com>

* try following PR comments

Signed-off-by: luofucong <luofc@foxmail.com>

---------

Signed-off-by: luofucong <luofc@foxmail.com>
2025-08-15 12:41:49 +00:00
Yingwen
60e01c7c3d feat: Implements last-non-null dedup strategy for flat format (#6709)
* feat: Implements FlatLastNonNull strategy

Dedup rows and keep last non null fields

Signed-off-by: evenyag <realevenyag@gmail.com>

* test: add basic test for FlatLastNonNull

Signed-off-by: evenyag <realevenyag@gmail.com>

* test: port more last non null test

Signed-off-by: evenyag <realevenyag@gmail.com>

* fix: do merge rows after delete op

Signed-off-by: evenyag <realevenyag@gmail.com>

* style: fix clippy

Signed-off-by: evenyag <realevenyag@gmail.com>

* refactor: rename num_pk_columns to field_column_start

So we can support different format later

Signed-off-by: evenyag <realevenyag@gmail.com>

* chore: address comment

Signed-off-by: evenyag <realevenyag@gmail.com>

---------

Signed-off-by: evenyag <realevenyag@gmail.com>
2025-08-14 14:38:47 +00:00
Weny Xu
021ad09c21 refactor: simplify WAL pruning procedure and introduce region flush trigger (#6741)
* chore: add logs

Signed-off-by: WenyXu <wenymedia@gmail.com>

* refactor: update wal config for metasrv

Signed-off-by: WenyXu <wenymedia@gmail.com>

* feat: introduce region flush trigger

Signed-off-by: WenyXu <wenymedia@gmail.com>

* fix: debug assert

Signed-off-by: WenyXu <wenymedia@gmail.com>

* chore: log level

Signed-off-by: WenyXu <wenymedia@gmail.com>

* refactor: simplify wal prune procedure

Signed-off-by: WenyXu <wenymedia@gmail.com>

* chore: upgrade rskafka

Signed-off-by: WenyXu <wenymedia@gmail.com>

* feat: always flush inactive regions

Signed-off-by: WenyXu <wenymedia@gmail.com>

* refactor: refactor flush trigger

Signed-off-by: WenyXu <wenymedia@gmail.com>

* chore: remove unused code

Signed-off-by: WenyXu <wenymedia@gmail.com>

* fix: typo

Signed-off-by: WenyXu <wenymedia@gmail.com>

* fix: update unit tests

Signed-off-by: WenyXu <wenymedia@gmail.com>

* chore: add metrics

Signed-off-by: WenyXu <wenymedia@gmail.com>

* chore: rename

Signed-off-by: WenyXu <wenymedia@gmail.com>

* chore: apply suggestions from CR

Signed-off-by: WenyXu <wenymedia@gmail.com>

---------

Signed-off-by: WenyXu <wenymedia@gmail.com>
2025-08-14 14:15:30 +00:00
discord9
2a3e4c7a82 fix: truncate manifest action compat (#6742)
* fix: truncate manifest action compat

Signed-off-by: discord9 <discord9@163.com>

* refactor: use simpler compat

Signed-off-by: discord9 <discord9@163.com>

---------

Signed-off-by: discord9 <discord9@163.com>
2025-08-14 14:05:17 +00:00
Ruihang Xia
4d97754cb4 feat: persist manifest, SST and index files to staging dir (#6726)
* make flush and access layer aware of staging mode

Signed-off-by: Ruihang Xia <waynestxia@gmail.com>

* staging flag in flush notify

Signed-off-by: Ruihang Xia <waynestxia@gmail.com>

* staging manifest

Signed-off-by: Ruihang Xia <waynestxia@gmail.com>

* index methods

Signed-off-by: Ruihang Xia <waynestxia@gmail.com>

* only stage manifest

Signed-off-by: Ruihang Xia <waynestxia@gmail.com>

* improve comment

Signed-off-by: Ruihang Xia <waynestxia@gmail.com>

---------

Signed-off-by: Ruihang Xia <waynestxia@gmail.com>
2025-08-14 06:02:31 +00:00
Zhenchi
fb3b1d4866 feat: Store partition expr in RegionMetadata (#6699)
* wire partition.expr_json option constant and parsing

test(mito2): manifest roundtrip persists partition_expr JSON

test(mito2): create/open with partition.expr_json persists in manifest

docs: add comments for partition.expr_json option and RegionOptions.partition_expr

serde: include RegionOptions.partition_expr (skip if None)

test(mito2): doc intent and verify runtime backfill + persistence-after-alter for partition expr

add partition expr to create request

Signed-off-by: Zhenchi <zhongzc_arch@outlook.com>

* add create_with_partition_expr_persists_manifest

Signed-off-by: Zhenchi <zhongzc_arch@outlook.com>

* pass partition expr to create request

Signed-off-by: Zhenchi <zhongzc_arch@outlook.com>

* polish

Signed-off-by: Zhenchi <zhongzc_arch@outlook.com>

* fix sqlness

Signed-off-by: Zhenchi <zhongzc_arch@outlook.com>

* fix test

Signed-off-by: Zhenchi <zhongzc_arch@outlook.com>

* remove unused dep

Signed-off-by: Zhenchi <zhongzc_arch@outlook.com>

---------

Signed-off-by: Zhenchi <zhongzc_arch@outlook.com>
Co-authored-by: Ruihang Xia <waynestxia@gmail.com>
2025-08-13 22:05:37 +00:00
Weny Xu
8659412cac feat: introduce PeriodicTopicStatsReporter (#6730)
* refactor: introduce `PeriodicTopicStatsReporter`

Signed-off-by: WenyXu <wenymedia@gmail.com>

* chore: apply suggestions from CR

Signed-off-by: WenyXu <wenymedia@gmail.com>

* fix: fix typo

Signed-off-by: WenyXu <wenymedia@gmail.com>

* chore: remote wal tests styling

Signed-off-by: WenyXu <wenymedia@gmail.com>

* fix: fix unit test

Signed-off-by: WenyXu <wenymedia@gmail.com>

* chore: apply suggestions

Signed-off-by: WenyXu <wenymedia@gmail.com>

* fix: handling region wal options not found

Signed-off-by: WenyXu <wenymedia@gmail.com>

* chore: apply suggestions from CR

Signed-off-by: WenyXu <wenymedia@gmail.com>

* fix: minor

Signed-off-by: WenyXu <wenymedia@gmail.com>

* chore: upgrade greptime-proto

Signed-off-by: WenyXu <wenymedia@gmail.com>

---------

Signed-off-by: WenyXu <wenymedia@gmail.com>
2025-08-13 11:46:50 +00:00
Ruihang Xia
8a44137f37 chore: prefix debug_assertion only variables with underscore (#6727)
Signed-off-by: Ruihang Xia <waynestxia@gmail.com>
2025-08-13 02:50:16 +00:00
Yingwen
1977ae50ee feat: Projection mapper for flat schema (#6679)
* feat: plain projection mapper wip

Signed-off-by: evenyag <realevenyag@gmail.com>

* refactor: change ProjectionMapper to enum

Signed-off-by: evenyag <realevenyag@gmail.com>

* feat: convert plain batch

Signed-off-by: evenyag <realevenyag@gmail.com>

* test: add tests for the mapper

Signed-off-by: evenyag <realevenyag@gmail.com>

* chore: allow dead code

Signed-off-by: evenyag <realevenyag@gmail.com>

* style: format code

Signed-off-by: evenyag <realevenyag@gmail.com>

* chore: fix compiler errors

Signed-off-by: evenyag <realevenyag@gmail.com>

* feat: change PlainProjectionMapper to FlatProjectionMapper

Signed-off-by: evenyag <realevenyag@gmail.com>

* test: fix projection tests

Signed-off-by: evenyag <realevenyag@gmail.com>

* style: fmt code

Signed-off-by: evenyag <realevenyag@gmail.com>

* style: fix clippy

Signed-off-by: evenyag <realevenyag@gmail.com>

* chore: Address  comments

Removes some unwrap()

Signed-off-by: evenyag <realevenyag@gmail.com>

* style: fmt

Signed-off-by: evenyag <realevenyag@gmail.com>

* chore: address comment

as_plain -> as_flat

Signed-off-by: evenyag <realevenyag@gmail.com>

---------

Signed-off-by: evenyag <realevenyag@gmail.com>
2025-08-12 07:36:23 +00:00
Ruihang Xia
25f926ea7d feat: mito region staging state (#6664)
* fix: not mark all deleted when partial trunc (#6654)

* fix: not mark all deleted when partial trunc&not update manifest when partial file range is empty

Signed-off-by: discord9 <discord9@163.com>

* docs: note

Signed-off-by: discord9 <discord9@163.com>

---------

Signed-off-by: discord9 <discord9@163.com>
Signed-off-by: Ruihang Xia <waynestxia@gmail.com>

* some tests and DdlRequest

Signed-off-by: Ruihang Xia <waynestxia@gmail.com>

* stage transit

Signed-off-by: Ruihang Xia <waynestxia@gmail.com>

* address CR comments

Signed-off-by: Ruihang Xia <waynestxia@gmail.com>

* correct error type

Signed-off-by: Ruihang Xia <waynestxia@gmail.com>

---------

Signed-off-by: discord9 <discord9@163.com>
Signed-off-by: Ruihang Xia <waynestxia@gmail.com>
Co-authored-by: discord9 <55937128+discord9@users.noreply.github.com>
2025-08-12 03:17:47 +00:00
Yingwen
e4454e0c7d feat: Implements last row dedup strategy for flat format (#6695)
* feat: implement FlatLastRow dedup strategy

Signed-off-by: evenyag <realevenyag@gmail.com>

* fix: fix dedup metrics

Add tests for iter with FlatLastRow strategy

Signed-off-by: evenyag <realevenyag@gmail.com>

* chore: fix delete metrics

Signed-off-by: evenyag <realevenyag@gmail.com>

* chore: address review comments

Signed-off-by: evenyag <realevenyag@gmail.com>

* style: fix clippy

Signed-off-by: evenyag <realevenyag@gmail.com>

* refactor: move BatchLastRow position

Signed-off-by: evenyag <realevenyag@gmail.com>

* style: fix typos

Signed-off-by: evenyag <realevenyag@gmail.com>

---------

Signed-off-by: evenyag <realevenyag@gmail.com>
2025-08-11 07:44:45 +00:00