mirror of
https://github.com/GreptimeTeam/greptimedb.git
synced 2026-08-18 12:08:22 +00:00
Weny Xu
63ef18a74a
* fix(query): push down PromQL cast filters (#8407) * fix(query): push down PromQL cast filters Signed-off-by: discord9 <discord9@163.com> * test(query): cover cast preimage pushdown Signed-off-by: discord9 <discord9@163.com> * test(query): expand cast preimage coverage Signed-off-by: discord9 <discord9@163.com> * test(query): compare cast normalization rules Signed-off-by: discord9 <discord9@163.com> * test(query): update cast pushdown sqlness plans Signed-off-by: discord9 <discord9@163.com> --------- Signed-off-by: discord9 <discord9@163.com> (cherry picked from commit4f5dccf6bb) * fix: update datafusion-pg-catalog (#8417) (cherry picked from commit434e0c7682) * fix: global limit for distributed inspect streams (#8412) * fix: global limit for distributed inspect streams Signed-off-by: jeremyhi <fengjiachun@gmail.com> * fix: honor tighter filter fetch under global limit Signed-off-by: jeremyhi <fengjiachun@gmail.com> * fix: restore distribution after global limit Signed-off-by: jeremyhi <fengjiachun@gmail.com> * fix: preserve inherited distribution for global limit Signed-off-by: jeremyhi <fengjiachun@gmail.com> * fix: propagate inherited hash partitioning Signed-off-by: jeremyhi <fengjiachun@gmail.com> --------- Signed-off-by: jeremyhi <fengjiachun@gmail.com> (cherry picked from commit5bcc2e9d6b) * feat: update dashboard to v0.13.7 (#8431) (cherry picked from commitebfe4f6eb2) * fix: preserve repartitioned file refs during GC (#8445) * fix: preserve repartitioned file refs during GC Signed-off-by: discord9 <discord9@163.com> * refactor: clarify file refs target region Signed-off-by: discord9 <discord9@163.com> --------- Signed-off-by: discord9 <discord9@163.com> (cherry picked from commit149b687a92) * fix: repartition subset partition key joins (#8460) Signed-off-by: discord9 <discord9@163.com> (cherry picked from commitff2fa71d50) * fix: honor exclusive end in log queries (#8495) * fix: exclude logs end boundary Signed-off-by: discord9 <discord9@163.com> * fix: normalize log query date bounds Signed-off-by: discord9 <discord9@163.com> --------- Signed-off-by: discord9 <discord9@163.com> (cherry picked from commit99235e4b2d) * feat: skip oversized compaction tasks (#8466) fix: skip oversized compaction tasks Signed-off-by: jeremyhi <fengjiachun@gmail.com> (cherry picked from commit0fcf61c3fb) * feat: use scan output bytes for read costing (#8276) * feat: track scan output bytes and use them for read costing Track the actual byte count of each record batch produced by `RegionScanExec` and use it in place of the aggregated per-plan `memory_usage` as the `table_scan` cost input. This avoids double counting bytes that flow through multiple operators. A named constant `REGION_SCAN_EXEC_NAME` exposes the plan node name so downstream metric parsers remain correct if the struct is renamed. Affected files: - `src/table/src/table/metrics.rs` -- add `output_bytes` counter - `src/table/src/table/scan.rs` -- record bytes, export name constant - `src/query/src/dist_plan/merge_scan.rs` -- consume scan bytes Signed-off-by: Lei, HUANG <mrsatangel@gmail.com> * refactor: remove misleading `mem_used` gauge from scan metrics The `mem_used` gauge was used with `add()` on every output batch, but a RegionScan does not hold memory across polls — each batch is yielded immediately to the upstream operator. The gauge semantics were incorrect (cumulative `add()` on a gauge) and the value duplicated `output_bytes` anyway. Affected files: - `src/table/src/table/metrics.rs` — drop `mem_used` field and methods - `src/table/src/table/scan.rs` — remove `record_mem_usage` call Signed-off-by: Lei, HUANG <mrsatangel@gmail.com> * fix: use stable plan names for scan byte metrics Expose `plan_name` alongside rendered plan text so scan byte extraction no longer depends on EXPLAIN formatting. Keep old serialized metrics compatible by defaulting missing `plan_name`. Affected files: - `src/common/recordbatch/src/adapter.rs` -- add `plan_name` to `PlanMetrics` and populate it from `ExecutionPlan::name` - `src/query/src/dist_plan/merge_scan.rs` -- match `REGION_SCAN_EXEC_NAME` through `plan_name` Signed-off-by: Lei, HUANG <mrsatangel@gmail.com> * fix: preserve merge scan CPU read cost Record read cost whenever stream metrics are available, default scan bytes to zero, and aggregate scan output bytes across region scan nodes. Files: `src/query/src/dist_plan/merge_scan.rs` Signed-off-by: Lei, HUANG <mrsatangel@gmail.com> * fix: correct doc comment in `StreamMetrics` Fix doc comment on `StreamMetrics::new()` to reference the correct struct name (`StreamMetrics`) instead of the old `MemoryUsageMetrics`. - `src/table/src/table/metrics.rs` — fix struct name in doc comment Signed-off-by: Lei, HUANG <mrsatangel@gmail.com> --------- Signed-off-by: Lei, HUANG <mrsatangel@gmail.com> (cherry picked from commit4373c77d35) * fix: account logical record batch slice memory (#8480) * fix: account logical record batch slice memory Signed-off-by: jeremyhi <fengjiachun@gmail.com> * fix: account nested view payload memory Signed-off-by: jeremyhi <fengjiachun@gmail.com> * test: align scan memory expectation with logical size Signed-off-by: jeremyhi <fengjiachun@gmail.com> * refactor: name Arrow inline view limit Signed-off-by: jeremyhi <fengjiachun@gmail.com> * fix: account visible list child memory Signed-off-by: jeremyhi <fengjiachun@gmail.com> * fix: exclude null list child memory Signed-off-by: jeremyhi <fengjiachun@gmail.com> * fix: exclude null struct child memory Signed-off-by: jeremyhi <fengjiachun@gmail.com> * fix: account fixed-size list slices Signed-off-by: jeremyhi <fengjiachun@gmail.com> * fix: limit scan accounting to flat slices Signed-off-by: jeremyhi <fengjiachun@gmail.com> * docs: clarify nested view accounting scope Signed-off-by: jeremyhi <fengjiachun@gmail.com> * perf: reduce view memory accounting overhead Signed-off-by: jeremyhi <fengjiachun@gmail.com> * chore: fix benchmark license header Signed-off-by: jeremyhi <fengjiachun@gmail.com> * perf: optimize view slice accounting Signed-off-by: jeremyhi <fengjiachun@gmail.com> * test: cover sliced mixed-null view accounting Signed-off-by: jeremyhi <fengjiachun@gmail.com> * refactor: narrow slice accounting to arrow buffers Signed-off-by: jeremyhi <fengjiachun@gmail.com> * docs: note view accounting assumption Signed-off-by: jeremyhi <fengjiachun@gmail.com> --------- Signed-off-by: jeremyhi <fengjiachun@gmail.com> (cherry picked from commit9cde31a647) * fix: preserve distributed topk merge ordering (#8432) * fix: preserve distributed topk for scalar latest Signed-off-by: discord9 <discord9@163.com> * fix: preserve scalar latest ordering across merge scan Signed-off-by: discord9 <discord9@163.com> * fix: carry merge scan ordering from planner rewrite Signed-off-by: discord9 <discord9@163.com> * test: cover merge scan ordering metadata Signed-off-by: discord9 <discord9@163.com> * test: cover merge scan partition ordering gate Signed-off-by: discord9 <discord9@163.com> * fix: require adjacent merge sort for ordering metadata Signed-off-by: discord9 <discord9@163.com> * test: update ordering sqlness plans Signed-off-by: discord9 <discord9@163.com> * fix: preserve distributed topk merge ordering Signed-off-by: discord9 <discord9@163.com> * test: cover latest per series queries Signed-off-by: discord9 <discord9@163.com> * test: update distributed merge sort sqlness Signed-off-by: discord9 <discord9@163.com> * test: cover merge scan ordering partition gate Signed-off-by: discord9 <discord9@163.com> * test: cover merge scan over-partition ordering Signed-off-by: discord9 <discord9@163.com> * test: cover distributed latest with low parallelism Signed-off-by: discord9 <discord9@163.com> * fix: keep distributed merge sort opaque Signed-off-by: discord9 <discord9@163.com> * test: assert distributed scalar latest merge sort Signed-off-by: discord9 <discord9@163.com> * test: clarify merge scan ordering helper Signed-off-by: discord9 <discord9@163.com> * fix: complete merge sort exec delegation Signed-off-by: discord9 <discord9@163.com> * docs: explain merge sort limit pushdown Signed-off-by: discord9 <discord9@163.com> * test: cover merge sort optimizer opacity Signed-off-by: discord9 <discord9@163.com> * docs: explain merge sort optimizer hooks Signed-off-by: discord9 <discord9@163.com> * test: cover merge sort optimizer hooks Signed-off-by: discord9 <discord9@163.com> * fix: preserve merge sort child topk Signed-off-by: discord9 <discord9@163.com> * test: update order by topk plan Signed-off-by: discord9 <discord9@163.com> * fix: recognize merge sort global fetch Signed-off-by: discord9 <discord9@163.com> --------- Signed-off-by: discord9 <discord9@163.com> (cherry picked from commitb30765e5e9) * fix: reject out-of-range PostgreSQL numeric UInt64 (#8517) Signed-off-by: discord9 <discord9@163.com> (cherry picked from commitd48f296144) * fix(log-store): deduplicate Kafka WAL multipart records (#8514) * fix(log-store): deduplicate Kafka WAL multipart records Signed-off-by: WenyXu <wenymedia@gmail.com> * fix(log-store): preserve delayed Kafka WAL entry offsets Signed-off-by: WenyXu <wenymedia@gmail.com> * fix(log-store): reject conflicting Kafka WAL last records Signed-off-by: WenyXu <wenymedia@gmail.com> * fix(log-store): emit Kafka WAL entries on last record Signed-off-by: WenyXu <wenymedia@gmail.com> * fix(log-store): discard duplicate Kafka WAL first records Signed-off-by: WenyXu <wenymedia@gmail.com> --------- Signed-off-by: WenyXu <wenymedia@gmail.com> (cherry picked from commit912db22417) * fix: apply log query limit after expressions (#8496) Signed-off-by: discord9 <discord9@163.com> (cherry picked from commit1122d1e7d7) * fix(query): delegate merge sort cardinality effect (#8532) Signed-off-by: discord9 <discord9@163.com> (cherry picked from commit887fdf7513) * fix: upgrade datafusion fork (#8438) Signed-off-by: jeremyhi <fengjiachun@gmail.com> (cherry picked from commitf12a1da3de) * chore: bump version Signed-off-by: WenyXu <wenymedia@gmail.com> --------- Signed-off-by: discord9 <discord9@163.com> Signed-off-by: jeremyhi <fengjiachun@gmail.com> Signed-off-by: Lei, HUANG <mrsatangel@gmail.com> Signed-off-by: WenyXu <wenymedia@gmail.com> Co-authored-by: discord9 <discord9@163.com> Co-authored-by: Ning Sun <sunng@protonmail.com> Co-authored-by: jeremyhi <jiachun_feng@proton.me> Co-authored-by: sun <sunchang_long@163.com> Co-authored-by: Lei, HUANG <6406592+v0y4g3r@users.noreply.github.com>