Skip to content

[chore](be) Add FileScannerV2 review guidance#65475

Open
Gabriel39 wants to merge 9 commits into
apache:masterfrom
Gabriel39:codex/add-format-v2-review-guide
Open

[chore](be) Add FileScannerV2 review guidance#65475
Gabriel39 wants to merge 9 commits into
apache:masterfrom
Gabriel39:codex/add-format-v2-review-guide

Conversation

@Gabriel39

Copy link
Copy Markdown
Contributor

What problem does this PR solve?

Issue Number: None

Related PR: None

Problem Summary: Code reviews under be/src/format_v2 need persistent, directory-scoped guidance for the FileScannerV2 architecture and external-data correctness boundaries. This PR adds a local AGENTS.md and repository-local design/review references covering:

  • TableReader, TableColumnMapper, and FileReader responsibility boundaries
  • external lake/file format and writer compatibility
  • common FileReader index, predicate, cache, and virtual-column review checks
  • Parquet Row Group/Page/Row pruning, indexes, lazy materialization, and I/O behavior
  • ORC predicate-to-SARG conversion, Stripe/row-index/Bloom usage, and fallback correctness
  • focused correctness, interoperability, differential, and performance-test expectations

Detailed checklists are stored under docs/ and loaded on demand from the directory-scoped instructions to stay below the Codex instruction-size limit.

Release note

None

Check List (For Author)

  • Test: No need to test (documentation-only change; Markdown whitespace, local references, Mermaid fences, and English-only content were verified)
  • Behavior changed: No
  • Does this need documentation: No

### What problem does this PR solve?

Issue Number: None

Related PR: None

Problem Summary: Add directory-scoped review guidance for format_v2 so code reviews consistently check reader lifecycle, schema mapping, filtering and delete semantics, format boundaries, performance, and focused test coverage.

### Release note

None

### Check List (For Author)

- Test: No need to test (documentation-only review guidance)
- Behavior changed: No
- Does this need documentation: No
### What problem does this PR solve?

Issue Number: None

Related PR: None

Problem Summary: Extend the format_v2 review guide with explicit external compatibility checks across lake formats, file formats, writer implementations, versions, type semantics, capability detection, fallbacks, and interoperability testing.

### Release note

None

### Check List (For Author)

- Test: No need to test (documentation-only review guidance)
- Behavior changed: No
- Does this need documentation: No
### What problem does this PR solve?

Issue Number: None

Related PR: None

Problem Summary: Extend the format_v2 review guide with architecture and interface-contract checks derived from the FileScannerV2 design. Define the responsibility boundaries between Scanner, TableReader, TableColumnMapper, and FileReader, and identify concrete coupling patterns that reviews must reject.

### Release note

None

### Check List (For Author)

- Test: No need to test (documentation-only review guidance)
- Behavior changed: No
- Does this need documentation: No
### What problem does this PR solve?

Issue Number: None

Related PR: None

Problem Summary: Convert the FileScannerV2 architecture reference into a repository-local Markdown document, preserving its diagrams and design contracts, and update the format_v2 review guide to use the local reference instead of a Feishu URL.

### Release note

None

### Check List (For Author)

- Test: No need to test (documentation-only change)
- Behavior changed: No
- Does this need documentation: No
### What problem does this PR solve?

Issue Number: None

Related PR: None

Problem Summary: Add a repository-local Markdown reference for the FileScannerV2 Parquet scan pipeline and extend the format_v2 review guide with focused checks for Row Group, Page, and Row filtering, index safety, pruning cost, lazy materialization, observability, and differential correctness coverage.

### Release note

None

### Check List (For Author)

- Test: No need to test (documentation-only change)
- Behavior changed: No
- Does this need documentation: No
### What problem does this PR solve?

Issue Number: None

Related PR: None

Problem Summary: Extend the format_v2 review guide with focused ORC checks for Doris predicate to SDK SearchArgument conversion, literal and cast correctness, Split and Stripe selection, row-index and Bloom-filter usage, lazy materialization, pruning overhead, observability, and differential correctness tests.

### Release note

None

### Check List (For Author)

- Test: No need to test (documentation-only change)
- Behavior changed: No
- Does this need documentation: No
### What problem does this PR solve?

Issue Number: None

Related PR: None

Problem Summary: Add a mandatory cross-format FileReader review guide covering native index implementations, predicate and residual filtering, data and condition caches, physical and table virtual columns, performance observability, and differential correctness tests. Move detailed Parquet and ORC checklists out of AGENTS.md and retain mandatory local references to stay below the Codex instruction-size limit.

### Release note

None

### Check List (For Author)

- Test: No need to test (documentation-only change)
- Behavior changed: No
- Does this need documentation: No
### What problem does this PR solve?

Issue Number: None

Related PR: None

Problem Summary: Translate the repository-local FileScannerV2 overview and Parquet scan design documents from Chinese to English, including headings, tables, callouts, Mermaid diagrams, troubleshooting guidance, and design contracts. Keep filenames and AGENTS.md references unchanged.

### Release note

None

### Check List (For Author)

- Test: No need to test (documentation-only translation; Markdown and character scans passed)
- Behavior changed: No
- Does this need documentation: No
@hello-stephen

Copy link
Copy Markdown
Contributor

Thank you for your contribution to Apache Doris.
Don't know what should be done next? See How to process your PR.

Please clearly describe your PR:

  1. What problem was fixed (it's best to include specific error reporting information). How it was fixed.
  2. Which behaviors were modified. What was the previous behavior, what is it now, why was it modified, and what possible impacts might there be.
  3. What features were added. Why was this function added?
  4. Which code was refactored and why was this part of the code refactored?
  5. Which functions were optimized and what is the difference before and after the optimization?

@Gabriel39

Copy link
Copy Markdown
Contributor Author

run buildall

@hello-stephen

Copy link
Copy Markdown
Contributor
TPC-H: Total hot run time: 29139 ms
machine: 'aliyun_ecs.c7a.8xlarge_32C64G'
scripts: https://github.com/apache/doris/tree/master/tools/tpch-tools
Tpch sf100 test result on commit 152f05c5299847a965e7ab0d4f688dd3e792be2b, data reload: false

------ Round 1 ----------------------------------
============================================
q1	17693	4015	3994	3994
q2	2005	322	199	199
q3	10315	1453	811	811
q4	4679	470	344	344
q5	7489	843	571	571
q6	178	168	134	134
q7	770	835	616	616
q8	9310	1413	1446	1413
q9	5685	4347	4353	4347
q10	6741	1783	1531	1531
q11	498	345	309	309
q12	705	546	428	428
q13	18128	3246	2730	2730
q14	272	269	243	243
q15	q16	786	773	711	711
q17	987	1030	962	962
q18	7044	5838	5567	5567
q19	1361	1213	1103	1103
q20	752	683	538	538
q21	5875	2675	2291	2291
q22	425	352	297	297
Total cold run time: 101698 ms
Total hot run time: 29139 ms

----- Round 2, with runtime_filter_mode=off -----
============================================
q1	4320	4231	4233	4231
q2	287	312	213	213
q3	4525	4930	4389	4389
q4	2043	2142	1366	1366
q5	4456	4340	4310	4310
q6	227	176	125	125
q7	1736	1640	1841	1640
q8	2653	2167	2164	2164
q9	8046	8211	7886	7886
q10	4667	4722	4195	4195
q11	587	408	382	382
q12	838	772	549	549
q13	3288	3554	2918	2918
q14	302	288	291	288
q15	q16	717	755	663	663
q17	1366	1288	1279	1279
q18	8004	7285	7355	7285
q19	1146	1121	1114	1114
q20	2219	2228	1930	1930
q21	5216	4564	4414	4414
q22	514	443	425	425
Total cold run time: 57157 ms
Total hot run time: 51766 ms

@hello-stephen

Copy link
Copy Markdown
Contributor
TPC-DS: Total hot run time: 180458 ms
machine: 'aliyun_ecs.c7a.8xlarge_32C64G'
scripts: https://github.com/apache/doris/tree/master/tools/tpcds-tools
TPC-DS sf100 test result on commit 152f05c5299847a965e7ab0d4f688dd3e792be2b, data reload: false

query5	4320	652	487	487
query6	449	230	205	205
query7	4886	593	347	347
query8	330	188	170	170
query9	8756	4085	4055	4055
query10	475	344	292	292
query11	5928	2351	2118	2118
query12	162	105	101	101
query13	1256	610	465	465
query14	6217	5299	4968	4968
query14_1	4334	4327	4295	4295
query15	219	207	184	184
query16	1039	472	444	444
query17	963	740	601	601
query18	2432	475	353	353
query19	228	229	170	170
query20	112	106	113	106
query21	226	155	131	131
query22	13646	13699	13340	13340
query23	17338	16468	16065	16065
query23_1	16260	16254	16276	16254
query24	7501	1790	1300	1300
query24_1	1311	1288	1320	1288
query25	551	441	364	364
query26	1332	374	212	212
query27	2595	607	381	381
query28	4486	2001	2004	2001
query29	1093	615	479	479
query30	334	270	222	222
query31	1110	1091	974	974
query32	108	62	61	61
query33	516	315	249	249
query34	1172	1159	638	638
query35	760	806	657	657
query36	1402	1404	1247	1247
query37	150	108	94	94
query38	1881	1697	1665	1665
query39	922	916	892	892
query39_1	878	885	881	881
query40	242	167	144	144
query41	69	64	66	64
query42	93	101	91	91
query43	323	324	279	279
query44	1447	786	780	780
query45	200	185	175	175
query46	1074	1260	768	768
query47	2332	2317	2223	2223
query48	405	417	314	314
query49	580	417	311	311
query50	1043	413	353	353
query51	10802	10843	10727	10727
query52	85	89	75	75
query53	268	282	213	213
query54	295	263	248	248
query55	77	75	69	69
query56	312	315	296	296
query57	1458	1409	1323	1323
query58	326	259	280	259
query59	1581	1642	1405	1405
query60	324	288	263	263
query61	182	176	171	171
query62	692	651	592	592
query63	249	211	214	211
query64	2984	1165	1011	1011
query65	4859	4776	4742	4742
query66	1883	505	383	383
query67	29535	29428	29265	29265
query68	3200	1659	992	992
query69	402	305	274	274
query70	1066	985	932	932
query71	377	320	314	314
query72	3135	2743	2343	2343
query73	820	836	456	456
query74	5084	4961	4776	4776
query75	2623	2594	2232	2232
query76	2310	1225	808	808
query77	368	391	285	285
query78	12250	12261	11679	11679
query79	1396	1133	796	796
query80	968	542	449	449
query81	500	325	278	278
query82	561	153	119	119
query83	394	320	289	289
query84	330	165	134	134
query85	940	629	546	546
query86	407	292	268	268
query87	1832	1817	1750	1750
query88	3766	2844	2860	2844
query89	453	408	353	353
query90	1785	197	199	197
query91	200	193	163	163
query92	65	61	59	59
query93	1590	1534	975	975
query94	645	354	282	282
query95	783	588	478	478
query96	1039	826	354	354
query97	2660	2666	2535	2535
query98	212	208	200	200
query99	1155	1182	1040	1040
Total cold run time: 265071 ms
Total hot run time: 180458 ms

@hello-stephen

Copy link
Copy Markdown
Contributor
ClickBench: Total hot run time: 25.04 s
machine: 'aliyun_ecs.c7a.8xlarge_32C64G'
scripts: https://github.com/apache/doris/tree/master/tools/clickbench-tools
ClickBench test result on commit 152f05c5299847a965e7ab0d4f688dd3e792be2b, data reload: false

query1	0.01	0.00	0.00
query2	0.10	0.05	0.05
query3	0.25	0.14	0.13
query4	1.61	0.14	0.14
query5	0.24	0.27	0.23
query6	1.27	1.06	1.06
query7	0.03	0.00	0.00
query8	0.06	0.04	0.04
query9	0.39	0.33	0.33
query10	0.56	0.56	0.56
query11	0.19	0.15	0.14
query12	0.20	0.14	0.14
query13	0.48	0.47	0.48
query14	1.01	1.02	1.02
query15	0.62	0.60	0.61
query16	0.31	0.31	0.32
query17	1.12	1.14	1.08
query18	0.23	0.22	0.21
query19	2.07	1.94	1.94
query20	0.02	0.01	0.01
query21	15.42	0.18	0.13
query22	4.98	0.06	0.05
query23	16.11	0.30	0.12
query24	2.93	0.43	0.33
query25	0.11	0.05	0.04
query26	0.73	0.20	0.14
query27	0.03	0.04	0.04
query28	3.52	0.91	0.53
query29	12.56	4.07	3.21
query30	0.28	0.15	0.16
query31	2.77	0.61	0.32
query32	3.22	0.59	0.48
query33	3.22	3.19	3.18
query34	15.65	4.25	3.52
query35	3.55	3.55	3.52
query36	0.55	0.45	0.44
query37	0.09	0.07	0.07
query38	0.05	0.04	0.04
query39	0.03	0.02	0.03
query40	0.18	0.16	0.15
query41	0.08	0.04	0.04
query42	0.04	0.03	0.03
query43	0.04	0.04	0.03
Total cold run time: 96.91 s
Total hot run time: 25.04 s

@Gabriel39

Copy link
Copy Markdown
Contributor Author

/review

@github-actions github-actions Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Reviewed PR #65475 at head 152f05c5299847a965e7ab0d4f688dd3e792be2b.

I reviewed the four add-only files:

  • be/src/format_v2/AGENTS.md
  • docs/file-scanner-v2-code-review-guide.md
  • docs/file-scanner-v2-design.md
  • docs/file-scanner-v2-parquet-scan-design.md

I did not find a substantiated blocking issue to raise inline. The new format-v2 review guide and linked design notes are consistent with the current FileScannerV2/TableReader/TableColumnMapper boundary, file-local/global identity model, conservative pruning and residual-filter requirements, condition-cache EOF/delete/runtime-filter safeguards, row-group/page planning flow, aggregate-pushdown constraints, and existing be/test/format_v2/ test layout.

Validation note: this runner is a shallow checkout and is missing .worktree_initialized and thirdparty/installed, so I treated this as a static review and did not run BE/FE builds or unit tests. The changed Markdown links were checked against the working tree.

Critical checkpoint conclusions:

  • Goal/test proof: the PR adds review/design documentation only; the added files are present, cross-linked, and aligned with current format-v2 code paths. No runtime behavior change or required new product test was identified.
  • Scope/focus: the change is focused on FileScannerV2 review guidance and architecture notes.
  • Concurrency/lifecycle: no code concurrency or lifecycle behavior is changed; the guidance calls out split isolation, cleanup, cache publication, and reader lifecycle review points.
  • Config/compatibility/persistence: no new config, storage format, protocol, or persistence behavior is introduced.
  • Parallel paths: Parquet/ORC/JNI/text/JSON/native and table-reader boundary guidance was checked against the current V2 dispatch and reader contracts.
  • Testing/CI: no executable tests were added because this is docs/review guidance; paths and Markdown links were checked, and git show --check reported no whitespace problems for the changed files.
  • Performance/observability: no runtime performance path is changed; the guidance preserves profile/cache/pruning observability expectations.

User focus: no additional user-provided focus points were supplied.

Subagent conclusions: optimizer-rewrite reported no candidate findings for optimizer/rewrite semantic-equivalence concerns. tests-session-config reported no candidate findings for tests, expected outputs, session/config propagation, compatibility, links, or likely CI/style failures. Convergence round 1 ended with both live subagents reporting NO_NEW_VALUABLE_FINDINGS for the same final ledger/comment set.

@Gabriel39 Gabriel39 marked this pull request as ready for review July 11, 2026 05:00
@Gabriel39 Gabriel39 requested a review from yiguolei as a code owner July 11, 2026 05:00
### What problem does this PR solve?

Issue Number: None

Related PR: None

Problem Summary: Remove four superseded format_v2 and Parquet design documents after consolidating the active architecture and review guidance into the new repository-local FileScannerV2 documents.

### Release note

None

### Check List (For Author)

- Test: No need to test (documentation-only deletion; staged diff check passed)
- Behavior changed: No
- Does this need documentation: No
@Gabriel39

Copy link
Copy Markdown
Contributor Author

run buildall

@Gabriel39

Copy link
Copy Markdown
Contributor Author

/run buildall

@Gabriel39

Copy link
Copy Markdown
Contributor Author

/review

@github-actions github-actions Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Review summary:

I reviewed the full PR 65475 diff and relevant format_v2 code paths. I did not find any actionable correctness, compatibility, or documentation-link issue that needs an inline review comment.

Critical checkpoint conclusions:

  • Goal and proof: the PR adds directory-scoped FileScannerV2 review guidance and replacement design/review docs. The changed docs cover layer boundaries, schema mapping/materialization, predicate/delete/index pushdown, Parquet/ORC checks, compatibility, and test expectations. No runtime test is required for the docs-only change.
  • Scope and focus: the change is focused on review guidance and design references. The deleted older planning docs are no longer referenced, and the new docs preserve the review-relevant API boundaries, identity rules, pruning/caching guidance, and test coverage expectations.
  • Concurrency/lifecycle: no runtime code or lifecycle behavior changes. The lifecycle guidance was checked against the visible FileScannerV2/TableReader/ParquetReader flow.
  • Config/session/protocol/persistence: no config item, session variable, FE-BE protocol, storage format, or persistence behavior is changed.
  • Parallel code paths: the guide explicitly covers common FileReader, Parquet, ORC, JNI, text/CSV/JSON, and external table-format paths. I did not find a misleading omission that would create a review defect.
  • Tests and expected outputs: no tests were run because this is documentation-only. I did run static checks for whitespace, relative Markdown link targets, balanced code fences, deleted-doc references, changed-file scope, and exact PR head/base metadata.
  • Performance/observability: no runtime counters or metrics changed. The added guidance calls out pruning order, cache semantics, profile counters, and performance review risks.
  • User focus: the focus file contained no additional user-provided focus points.

Subagent conclusions:

  • optimizer-rewrite: no candidates became inline comments; the subagent reported no optimizer/rewrite, semantic-equivalence, aggregate, or parallel-path issue.
  • tests-session-config: no candidates became inline comments; the subagent reported no test guidance, expected-output, session/config, compatibility, stale-reference, or Markdown/style issue.
  • Final convergence Round 1 ended with both live subagents replying NO_NEW_VALUABLE_FINDINGS for the same current ledger and empty proposed final comment set.

Validation notes:

  • Verified PR head stayed at 4be9a4ccd6700686d62a33c82593f7dfaa0a0d08.
  • Existing inline review context was empty.
  • Local base ancestry was initially missing, so I fetched the exact base SHA and used GitHub PR metadata plus local base-to-head checks for review scope.

@hello-stephen

Copy link
Copy Markdown
Contributor

BE Regression && UT Coverage Report

Increment line coverage 100% (0/0) 🎉

Increment coverage report
Complete coverage report

Category Coverage
Function Coverage 74.67% (30141/40368)
Line Coverage 58.68% (330892/563878)
Region Coverage 55.22% (276440/500634)
Branch Coverage 56.61% (122488/216359)

@hello-stephen

Copy link
Copy Markdown
Contributor
TPC-H: Total hot run time: 28975 ms
machine: 'aliyun_ecs.c7a.8xlarge_32C64G'
scripts: https://github.com/apache/doris/tree/master/tools/tpch-tools
Tpch sf100 test result on commit 4be9a4ccd6700686d62a33c82593f7dfaa0a0d08, data reload: false

------ Round 1 ----------------------------------
============================================
q1	17688	4046	3989	3989
q2	2058	312	203	203
q3	10276	1382	840	840
q4	4681	469	338	338
q5	7541	848	566	566
q6	201	173	141	141
q7	763	841	632	632
q8	10103	1501	1696	1501
q9	6125	4395	4396	4395
q10	6801	1774	1505	1505
q11	506	341	310	310
q12	746	577	444	444
q13	18114	3353	2721	2721
q14	289	266	241	241
q15	q16	788	779	705	705
q17	1755	1173	778	778
q18	6895	5716	5493	5493
q19	2802	1273	957	957
q20	781	661	538	538
q21	5868	2636	2382	2382
q22	434	360	296	296
Total cold run time: 105215 ms
Total hot run time: 28975 ms

----- Round 2, with runtime_filter_mode=off -----
============================================
q1	4436	4242	4340	4242
q2	293	318	234	234
q3	4553	4937	4416	4416
q4	2064	2164	1364	1364
q5	4468	4280	4279	4279
q6	224	187	163	163
q7	2212	1958	1597	1597
q8	2494	2186	2128	2128
q9	7857	7928	7797	7797
q10	4753	4730	4265	4265
q11	658	547	407	407
q12	752	750	571	571
q13	3408	3632	3014	3014
q14	300	311	262	262
q15	q16	722	731	686	686
q17	1383	1334	1362	1334
q18	7912	7444	6798	6798
q19	1075	1072	1067	1067
q20	2224	2209	1935	1935
q21	5260	4636	4483	4483
q22	515	457	420	420
Total cold run time: 57563 ms
Total hot run time: 51462 ms

@hello-stephen

Copy link
Copy Markdown
Contributor
TPC-DS: Total hot run time: 180138 ms
machine: 'aliyun_ecs.c7a.8xlarge_32C64G'
scripts: https://github.com/apache/doris/tree/master/tools/tpcds-tools
TPC-DS sf100 test result on commit 4be9a4ccd6700686d62a33c82593f7dfaa0a0d08, data reload: false

query5	4704	648	507	507
query6	450	217	195	195
query7	4920	592	358	358
query8	334	186	175	175
query9	8772	4092	4065	4065
query10	468	347	284	284
query11	5947	2389	2139	2139
query12	155	107	103	103
query13	1260	584	439	439
query14	6455	5353	5008	5008
query14_1	4315	4321	4330	4321
query15	224	215	177	177
query16	1046	472	461	461
query17	1138	715	590	590
query18	2556	477	358	358
query19	214	196	152	152
query20	114	111	107	107
query21	234	160	135	135
query22	13766	13772	13467	13467
query23	17398	16620	16258	16258
query23_1	16356	16347	16191	16191
query24	7560	1766	1319	1319
query24_1	1323	1319	1343	1319
query25	581	488	412	412
query26	1341	362	211	211
query27	2556	603	384	384
query28	4466	2006	2020	2006
query29	1090	641	492	492
query30	342	255	226	226
query31	1117	1103	981	981
query32	113	62	63	62
query33	546	321	263	263
query34	1162	1114	666	666
query35	773	805	666	666
query36	1363	1400	1270	1270
query37	156	113	93	93
query38	1889	1714	1661	1661
query39	927	907	899	899
query39_1	880	873	891	873
query40	257	172	185	172
query41	67	62	62	62
query42	93	92	92	92
query43	324	317	282	282
query44	1411	777	774	774
query45	191	191	185	185
query46	1098	1258	719	719
query47	2290	2355	2179	2179
query48	406	395	302	302
query49	577	412	310	310
query50	1008	412	340	340
query51	11053	10798	10700	10700
query52	84	85	72	72
query53	256	279	194	194
query54	273	242	205	205
query55	80	70	66	66
query56	292	308	275	275
query57	1422	1393	1317	1317
query58	285	247	254	247
query59	1548	1637	1370	1370
query60	291	263	244	244
query61	148	152	144	144
query62	708	644	582	582
query63	247	205	209	205
query64	2805	1021	888	888
query65	4873	4798	4794	4794
query66	1807	518	380	380
query67	29544	29553	28752	28752
query68	3108	1633	941	941
query69	399	301	245	245
query70	1093	973	938	938
query71	361	316	307	307
query72	3110	2690	2366	2366
query73	797	766	429	429
query74	5125	4926	4738	4738
query75	2623	2601	2221	2221
query76	2310	1192	766	766
query77	339	384	285	285
query78	12250	12415	11776	11776
query79	2179	1129	760	760
query80	1291	546	454	454
query81	535	316	286	286
query82	578	156	123	123
query83	360	313	287	287
query84	274	158	129	129
query85	922	607	520	520
query86	423	284	278	278
query87	1842	1814	1758	1758
query88	3755	2812	2805	2805
query89	449	400	350	350
query90	1883	205	198	198
query91	204	190	162	162
query92	65	61	53	53
query93	1784	1636	942	942
query94	708	370	318	318
query95	797	502	471	471
query96	1023	836	356	356
query97	2692	2668	2526	2526
query98	215	211	203	203
query99	1156	1165	1011	1011
Total cold run time: 267457 ms
Total hot run time: 180138 ms

@hello-stephen

Copy link
Copy Markdown
Contributor
ClickBench: Total hot run time: 24.96 s
machine: 'aliyun_ecs.c7a.8xlarge_32C64G'
scripts: https://github.com/apache/doris/tree/master/tools/clickbench-tools
ClickBench test result on commit 4be9a4ccd6700686d62a33c82593f7dfaa0a0d08, data reload: false

query1	0.01	0.01	0.00
query2	0.10	0.04	0.05
query3	0.26	0.14	0.14
query4	1.60	0.14	0.14
query5	0.23	0.22	0.22
query6	1.23	1.07	1.06
query7	0.03	0.01	0.01
query8	0.06	0.04	0.04
query9	0.38	0.31	0.31
query10	0.55	0.56	0.55
query11	0.21	0.15	0.14
query12	0.18	0.14	0.14
query13	0.46	0.46	0.47
query14	1.02	1.01	0.99
query15	0.60	0.60	0.58
query16	0.33	0.33	0.31
query17	1.11	1.14	1.12
query18	0.22	0.21	0.21
query19	2.03	1.87	1.98
query20	0.02	0.01	0.01
query21	15.42	0.19	0.13
query22	4.99	0.05	0.05
query23	16.09	0.30	0.12
query24	3.02	0.44	0.32
query25	0.12	0.05	0.04
query26	0.74	0.20	0.16
query27	0.03	0.04	0.03
query28	3.47	0.96	0.54
query29	12.48	4.05	3.20
query30	0.26	0.15	0.16
query31	2.76	0.62	0.30
query32	3.22	0.59	0.50
query33	3.21	3.24	3.30
query34	15.47	4.22	3.54
query35	3.55	3.56	3.51
query36	0.55	0.42	0.43
query37	0.09	0.06	0.06
query38	0.05	0.04	0.04
query39	0.03	0.03	0.03
query40	0.19	0.17	0.15
query41	0.09	0.03	0.03
query42	0.04	0.03	0.03
query43	0.05	0.04	0.03
Total cold run time: 96.55 s
Total hot run time: 24.96 s

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants