You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@doris.apache.org by "kaka11chen (via GitHub)" <gi...@apache.org> on 2024/01/04 08:51:21 UTC
[PR] [Opt](parquet-reader) Opt `ColumnSelectVector::set_run_length_null_map()` in parquet reader. [doris]
kaka11chen opened a new pull request, #29527:
URL: https://github.com/apache/doris/pull/29527
## Proposed changes
[Opt] (parquet-reader) Opt `ColumnSelectVector::set_run_length_null_map()` in parquet reader.
### Test Result:
tpch500,2 node:
```
select count(l_orderkey), count(l_extendedprice), count(l_discount), count(l_shipdate) from lineitem
where l_shipdate > '1995-03-15';
```
9 s to 7.9 s.
## Further comments
If this is a relatively large or complex change, kick off the discussion at [dev@doris.apache.org](mailto:dev@doris.apache.org) by explaining why you chose the solution you did and what alternatives you considered, etc...
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: commits-unsubscribe@doris.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@doris.apache.org
For additional commands, e-mail: commits-help@doris.apache.org
Re: [PR] [Opt](parquet-reader) Opt `ColumnSelectVector::set_run_length_null_map()` in parquet reader. [doris]
Posted by "yiguolei (via GitHub)" <gi...@apache.org>.
yiguolei merged PR #29527:
URL: https://github.com/apache/doris/pull/29527
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: commits-unsubscribe@doris.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@doris.apache.org
For additional commands, e-mail: commits-help@doris.apache.org
Re: [PR] [Opt](parquet-reader) Opt `ColumnSelectVector::set_run_length_null_map()` in parquet reader. [doris]
Posted by "doris-robot (via GitHub)" <gi...@apache.org>.
doris-robot commented on PR #29527:
URL: https://github.com/apache/doris/pull/29527#issuecomment-1876763147
TeamCity be ut coverage result:
Function Coverage: 36.64% (8616/23517)
Line Coverage: 28.67% (70017/244175)
Region Coverage: 27.65% (36238/131073)
Branch Coverage: 24.34% (18507/76040)
Coverage Report: http://coverage.selectdb-in.cc/coverage/b525de8bef59660d0cbc6d636eb1455fca8e9d26_b525de8bef59660d0cbc6d636eb1455fca8e9d26/report/index.html
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: commits-unsubscribe@doris.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@doris.apache.org
For additional commands, e-mail: commits-help@doris.apache.org
Re: [PR] [Opt](parquet-reader) Opt `ColumnSelectVector::set_run_length_null_map()` in parquet reader. [doris]
Posted by "doris-robot (via GitHub)" <gi...@apache.org>.
doris-robot commented on PR #29527:
URL: https://github.com/apache/doris/pull/29527#issuecomment-1876764271
TPC-H test result on machine: 'aliyun_ecs.c7a.8xlarge_32C64G', run with scripts in https://github.com/apache/doris/tree/master/tools/tpch-tools
```
Tpch sf100 test result on commit b525de8bef59660d0cbc6d636eb1455fca8e9d26, data reload: false
------ Round 1 ----------------------------------
q1 17670 5180 5097 5097
q2 2013 152 143 143
q3 10546 1078 1109 1078
q4 10177 787 841 787
q5 7796 2941 2848 2848
q6 225 141 137 137
q7 906 558 527 527
q8 9275 2009 2030 2009
q9 6781 6386 6353 6353
q10 8202 3057 3057 3057
q11 437 232 205 205
q12 390 232 227 227
q13 18021 3608 3619 3608
q14 238 224 208 208
q15 550 517 515 515
q16 453 394 396 394
q17 979 530 478 478
q18 7256 6705 6686 6686
q19 1609 1436 1306 1306
q20 717 350 332 332
q21 2838 2396 2444 2396
q22 384 346 327 327
Total cold run time: 107463 ms
Total hot run time: 38718 ms
----- Round 2, with runtime_filter_mode=off -----
q1 5117 5105 5091 5091
q2 333 230 233 230
q3 3291 3261 3244 3244
q4 2109 2020 2018 2018
q5 5773 5772 5773 5772
q6 210 126 127 126
q7 2346 1865 1875 1865
q8 3358 3453 3448 3448
q9 8770 8716 8733 8716
q10 3774 3853 3831 3831
q11 584 480 479 479
q12 794 638 619 619
q13 7996 3193 3171 3171
q14 319 262 272 262
q15 607 515 518 515
q16 561 492 506 492
q17 1942 1767 1749 1749
q18 8623 8334 8211 8211
q19 1648 1624 1621 1621
q20 2172 1954 1939 1939
q21 5608 5300 5208 5208
q22 525 472 496 472
Total cold run time: 66460 ms
Total hot run time: 59079 ms
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: commits-unsubscribe@doris.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@doris.apache.org
For additional commands, e-mail: commits-help@doris.apache.org
Re: [PR] [Opt](parquet-reader) Opt `ColumnSelectVector::set_run_length_null_map()` in parquet reader. [doris]
Posted by "github-actions[bot] (via GitHub)" <gi...@apache.org>.
github-actions[bot] commented on PR #29527:
URL: https://github.com/apache/doris/pull/29527#issuecomment-1876732210
clang-tidy review says "All clean, LGTM! :+1:"
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: commits-unsubscribe@doris.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@doris.apache.org
For additional commands, e-mail: commits-help@doris.apache.org
Re: [PR] [Opt](parquet-reader) Opt `ColumnSelectVector::set_run_length_null_map()` in parquet reader. [doris]
Posted by "github-actions[bot] (via GitHub)" <gi...@apache.org>.
github-actions[bot] commented on PR #29527:
URL: https://github.com/apache/doris/pull/29527#issuecomment-1878024782
PR approved by at least one committer and no changes requested.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: commits-unsubscribe@doris.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@doris.apache.org
For additional commands, e-mail: commits-help@doris.apache.org
Re: [PR] [Opt](parquet-reader) Opt `ColumnSelectVector::set_run_length_null_map()` in parquet reader. [doris]
Posted by "doris-robot (via GitHub)" <gi...@apache.org>.
doris-robot commented on PR #29527:
URL: https://github.com/apache/doris/pull/29527#issuecomment-1876780374
TPC-DS test result on machine: 'aliyun_ecs.c7a.8xlarge_32C64G', run with scripts in https://github.com/apache/doris/tree/master/tools/tpcds-tools
```
TPC-DS sf100 test result on commit b525de8bef59660d0cbc6d636eb1455fca8e9d26, data reload: false
run tpcds-sf100 query with default conf and session variables
query1 953 344 331 331
query2 6442 1932 1948 1932
query3 6660 209 205 205
query4 28275 22434 22458 22434
query5 3965 542 509 509
query6 283 182 185 182
query7 4576 276 259 259
query8 217 194 194 194
query9 8225 2497 2614 2497
query10 507 227 245 227
query11 16300 15594 15730 15594
query12 139 73 74 73
query13 1633 311 312 311
query14 11816 7068 7104 7068
query15 219 186 194 186
query16 6417 265 260 260
query17 1884 509 503 503
query18 1949 260 258 258
query19 186 133 132 132
query20 78 77 72 72
query21 184 100 93 93
query22 4884 4811 4582 4582
query23 31935 30980 31050 30980
query24 11902 2754 2814 2754
query25 602 349 338 338
query26 1736 140 135 135
query27 2928 269 275 269
query28 7195 1876 1859 1859
query29 2067 379 394 379
query30 308 143 146 143
query31 962 769 776 769
query32 87 59 53 53
query33 738 253 249 249
query34 918 446 432 432
query35 880 781 769 769
query36 1306 1180 1201 1180
query37 188 62 78 62
query38 3373 3253 3215 3215
query39 1314 1284 1253 1253
query40 298 87 86 86
query41 38 37 35 35
query42 95 82 83 82
query43 538 483 506 483
query44 1044 686 698 686
query45 198 197 183 183
query46 1063 644 636 636
query47 1600 1512 1614 1512
query48 339 253 265 253
query49 1214 307 313 307
query50 751 318 365 318
query51 5557 5256 5346 5256
query52 91 80 81 80
query53 209 147 141 141
query54 1373 562 549 549
query55 91 78 83 78
query56 202 186 193 186
query57 1047 946 887 887
query58 235 205 195 195
query59 2742 2599 2630 2599
query60 232 222 227 222
query61 87 86 85 85
query62 646 456 469 456
query63 159 141 138 138
query64 6053 1716 1714 1714
query65 3316 3257 3241 3241
query66 1390 350 344 344
query67 15603 15160 15308 15160
query68 11022 501 523 501
query69 507 246 254 246
query70 1680 1578 1555 1555
query71 499 213 219 213
query72 5678 3598 3603 3598
query73 2122 312 305 305
query74 7013 6362 6430 6362
query75 4819 2288 2285 2285
query76 6319 1112 1088 1088
query77 659 241 268 241
query78 9163 8583 8563 8563
query79 2149 506 486 486
query80 686 348 338 338
query81 467 212 209 209
query82 204 96 91 91
query83 166 138 147 138
query84 245 54 53 53
query85 956 286 282 282
query86 399 412 416 412
query87 3518 3372 3352 3352
query88 3207 2247 2228 2228
query89 366 255 261 255
query90 1956 195 191 191
query91 128 93 93 93
query92 58 47 48 47
query93 3140 484 424 424
query94 831 180 176 176
query95 460 416 401 401
query96 633 313 316 313
query97 4262 4120 4165 4120
query98 208 185 216 185
query99 1111 842 833 833
Total cold run time: 295073 ms
Total hot run time: 178237 ms
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: commits-unsubscribe@doris.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@doris.apache.org
For additional commands, e-mail: commits-help@doris.apache.org
Re: [PR] [Opt](parquet-reader) Opt `ColumnSelectVector::set_run_length_null_map()` in parquet reader. [doris]
Posted by "doris-robot (via GitHub)" <gi...@apache.org>.
doris-robot commented on PR #29527:
URL: https://github.com/apache/doris/pull/29527#issuecomment-1876779520
TPC-H test result on machine: 'aliyun_ecs.c7a.8xlarge_32C64G', run with scripts in https://github.com/apache/doris/tree/master/tools/tpch-tools
```
Tpch sf100 test result on commit b525de8bef59660d0cbc6d636eb1455fca8e9d26, data reload: false
run tpch-sf100 query with default conf and session variables
q1 5500 5187 5126 5126
q2 395 170 158 158
q3 1450 1138 1239 1138
q4 1077 834 847 834
q5 3108 3147 3123 3123
q6 230 139 136 136
q7 991 567 497 497
q8 2157 2294 2210 2210
q9 6724 6684 6678 6678
q10 3172 3116 3141 3116
q11 353 209 215 209
q12 383 233 241 233
q13 4393 3630 3655 3630
q14 239 215 224 215
q15 594 542 529 529
q16 455 407 404 404
q17 1044 535 512 512
q18 7125 6763 6759 6759
q19 1641 1508 1645 1508
q20 538 326 364 326
q21 2898 2450 2519 2450
q22 396 338 330 330
Total cold run time: 44863 ms
Total hot run time: 40121 ms
run tpch-sf100 query with default conf and set session variable runtime_filter_mode=off
q1 5158 5117 5093 5093
q2 341 241 246 241
q3 3348 3320 3327 3320
q4 2162 2071 2039 2039
q5 5964 5938 5952 5938
q6 223 127 131 127
q7 2380 1971 1967 1967
q8 3565 3659 3659 3659
q9 9010 8996 9012 8996
q10 3868 3907 3896 3896
q11 574 510 501 501
q12 802 636 657 636
q13 3883 3215 3203 3203
q14 304 279 278 278
q15 595 531 535 531
q16 567 524 502 502
q17 2038 1839 1812 1812
q18 8732 8357 8402 8357
q19 1742 1680 1697 1680
q20 2260 1974 1957 1957
q21 5649 5282 5303 5282
q22 563 475 484 475
Total cold run time: 63728 ms
Total hot run time: 60490 ms
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: commits-unsubscribe@doris.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@doris.apache.org
For additional commands, e-mail: commits-help@doris.apache.org
Re: [PR] [Opt](parquet-reader) Opt `ColumnSelectVector::set_run_length_null_map()` in parquet reader. [doris]
Posted by "kaka11chen (via GitHub)" <gi...@apache.org>.
kaka11chen commented on PR #29527:
URL: https://github.com/apache/doris/pull/29527#issuecomment-1876723245
run buildall
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: commits-unsubscribe@doris.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@doris.apache.org
For additional commands, e-mail: commits-help@doris.apache.org
Re: [PR] [Opt](parquet-reader) Opt `ColumnSelectVector::set_run_length_null_map()` in parquet reader. [doris]
Posted by "doris-robot (via GitHub)" <gi...@apache.org>.
doris-robot commented on PR #29527:
URL: https://github.com/apache/doris/pull/29527#issuecomment-1876785446
(From new machine)TeamCity pipeline, clickbench performance test result:
the sum of best hot time: 47.26 seconds
stream load tsv: 581 seconds loaded 74807831229 Bytes, about 122 MB/s
stream load json: 19 seconds loaded 2358488459 Bytes, about 118 MB/s
stream load orc: 66 seconds loaded 1101869774 Bytes, about 15 MB/s
stream load parquet: 32 seconds loaded 861443392 Bytes, about 25 MB/s
insert into select: 28.2 seconds inserted 10000000 Rows, about 354K ops/s
storage size: 17183807302 Bytes
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: commits-unsubscribe@doris.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@doris.apache.org
For additional commands, e-mail: commits-help@doris.apache.org
Re: [PR] [Opt](parquet-reader) Opt `ColumnSelectVector::set_run_length_null_map()` in parquet reader. [doris]
Posted by "github-actions[bot] (via GitHub)" <gi...@apache.org>.
github-actions[bot] commented on PR #29527:
URL: https://github.com/apache/doris/pull/29527#issuecomment-1878024877
PR approved by anyone and no changes requested.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: commits-unsubscribe@doris.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@doris.apache.org
For additional commands, e-mail: commits-help@doris.apache.org