You are viewing a plain text version of this content. The canonical link for it is here.
Posted to github@datafusion.apache.org by "kosiew (via GitHub)" <gi...@apache.org> on 2026/07/11 06:53:50 UTC

[PR] Use `octet_length` for ClickBench Q27/Q28 byte-length semantics [datafusion]

kosiew opened a new pull request, #23475:
URL: https://github.com/apache/datafusion/pull/23475

   ### Which issue does this PR close?
   
   * Closes #23086
   
   ### Rationale for this change
   
   ClickBench Q27 and Q28 are intended to aggregate the **byte length** of string values, while DataFusion intentionally defines `length` as an alias for `character_length`, which counts UTF-8 characters rather than bytes. This change updates the in-repo ClickBench SQL to use `octet_length(...)` explicitly, aligning these benchmark queries with ClickBench's intended semantics without changing DataFusion's SQL behavior. 
   
   ### What changes are included in this PR?
   
   * Updated ClickBench Q27 to use `AVG(octet_length("URL"))` instead of `AVG(length("URL"))` in:
   
     * `benchmarks/queries/clickbench/queries/q27.sql`
     * `benchmarks/sql_benchmarks/clickbench/benchmarks/q27.benchmark`
   * Updated ClickBench Q28 to use `AVG(octet_length("Referer"))` instead of `AVG(length("Referer"))` in:
   
     * `benchmarks/queries/clickbench/queries/q28.sql`
     * `benchmarks/sql_benchmarks/clickbench/benchmarks/q28.benchmark`
   * Updated the corresponding SQLLogicTest (`clickbench.slt`) queries and expected `EXPLAIN` output so the logical and physical plans reference `octet_length(...)` rather than `character_length(...)` or `length(...)`.
   * Added brief comments in the benchmark SQL noting that `length(...)` in DataFusion counts characters and that `octet_length(...)` is used to preserve ClickBench byte-length semantics. 
   
   ### Are these changes tested?
   
   The patch updates the expected SQLLogicTest (`datafusion/sqllogictest/test_files/clickbench.slt`) output for Q27 and Q28 to reflect the new `octet_length(...)` plans. 
   
   No test execution or benchmark results are included in this patch. Performance was **not measured** as part of this change.
   
   ### Are there any user-facing changes?
   
   There are no user-facing API or SQL semantic changes. This change only updates the in-repo ClickBench benchmark queries and their corresponding SQLLogicTest expectations to use explicit byte-length semantics. 
   
   ### LLM-generated code disclosure
   
   This PR includes LLM-generated code and comments. All LLM-generated content has been manually reviewed.
   


-- 
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: github-unsubscribe@datafusion.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org
For additional commands, e-mail: github-help@datafusion.apache.org


Re: [PR] Use `octet_length` for ClickBench Q27/Q28 byte-length semantics [datafusion]

Posted by "adriangbot (via GitHub)" <gi...@apache.org>.
adriangbot commented on PR #23475:
URL: https://github.com/apache/datafusion/pull/23475#issuecomment-4943289719

   ๐Ÿค– Benchmark running (GKE) | [trigger](https://github.com/apache/datafusion/pull/23475#issuecomment-4943253066)
   **Instance:** `c4a-highmem-16` (12 vCPU / 65 GiB) | `Linux bench-c4943253066-972-2p9c4 6.12.85+ #1 SMP Mon May 11 08:17:35 UTC 2026 aarch64 GNU/Linux`
   <details><summary>CPU Details (lscpu)</summary>
   
   ```
   Architecture:                            aarch64
   CPU op-mode(s):                          64-bit
   Byte Order:                              Little Endian
   CPU(s):                                  16
   On-line CPU(s) list:                     0-15
   Vendor ID:                               ARM
   Model name:                              Neoverse-V2
   Model:                                   1
   Thread(s) per core:                      1
   Core(s) per cluster:                     16
   Socket(s):                               -
   Cluster(s):                              1
   Stepping:                                r0p1
   BogoMIPS:                                2000.00
   Flags:                                   fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh rng bti
   L1d cache:                               1 MiB (16 instances)
   L1i cache:                               1 MiB (16 instances)
   L2 cache:                                32 MiB (16 instances)
   L3 cache:                                80 MiB (1 instance)
   NUMA node(s):                            1
   NUMA node0 CPU(s):                       0-15
   Vulnerability Gather data sampling:      Not affected
   Vulnerability Indirect target selection: Not affected
   Vulnerability Itlb multihit:             Not affected
   Vulnerability L1tf:                      Not affected
   Vulnerability Mds:                       Not affected
   Vulnerability Meltdown:                  Not affected
   Vulnerability Mmio stale data:           Not affected
   Vulnerability Reg file data sampling:    Not affected
   Vulnerability Retbleed:                  Not affected
   Vulnerability Spec rstack overflow:      Not affected
   Vulnerability Spec store bypass:         Mitigation; Speculative Store Bypass disabled via prctl
   Vulnerability Spectre v1:                Mitigation; __user pointer sanitization
   Vulnerability Spectre v2:                Mitigation; CSV2, BHB
   Vulnerability Srbds:                     Not affected
   Vulnerability Tsa:                       Not affected
   Vulnerability Tsx async abort:           Not affected
   Vulnerability Vmscape:                   Not affected
   ```
   
   </details>
   
   Comparing octet_length-01-23086 (08d730a2c19d69120885f41c220d4350eceb48ed) to 3e058f0 (merge-base) [diff](https://github.com/apache/datafusion/compare/3e058f09c91a18c8f36b71a656231603b33888c2..08d730a2c19d69120885f41c220d4350eceb48ed) using: 27
   Results will be posted here when complete
   
   ---
   [File an issue](https://github.com/adriangb/datafusion-benchmarking/issues) against this benchmark runner


-- 
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: github-unsubscribe@datafusion.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org
For additional commands, e-mail: github-help@datafusion.apache.org


Re: [PR] Use `octet_length` for ClickBench Q27/Q28 byte-length semantics [datafusion]

Posted by "adriangbot (via GitHub)" <gi...@apache.org>.
adriangbot commented on PR #23475:
URL: https://github.com/apache/datafusion/pull/23475#issuecomment-4943568460

   ๐Ÿค– Benchmark running (GKE) | [trigger](https://github.com/apache/datafusion/pull/23475#issuecomment-4943549427)
   **Instance:** `c4a-highmem-16` (12 vCPU / 65 GiB) | `Linux bench-c4943549427-975-4prxj 6.12.85+ #1 SMP Mon May 11 08:17:35 UTC 2026 aarch64 GNU/Linux`
   <details><summary>CPU Details (lscpu)</summary>
   
   ```
   Architecture:                            aarch64
   CPU op-mode(s):                          64-bit
   Byte Order:                              Little Endian
   CPU(s):                                  16
   On-line CPU(s) list:                     0-15
   Vendor ID:                               ARM
   Model name:                              Neoverse-V2
   Model:                                   1
   Thread(s) per core:                      1
   Core(s) per cluster:                     16
   Socket(s):                               -
   Cluster(s):                              1
   Stepping:                                r0p1
   BogoMIPS:                                2000.00
   Flags:                                   fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh rng bti
   L1d cache:                               1 MiB (16 instances)
   L1i cache:                               1 MiB (16 instances)
   L2 cache:                                32 MiB (16 instances)
   L3 cache:                                80 MiB (1 instance)
   NUMA node(s):                            1
   NUMA node0 CPU(s):                       0-15
   Vulnerability Gather data sampling:      Not affected
   Vulnerability Indirect target selection: Not affected
   Vulnerability Itlb multihit:             Not affected
   Vulnerability L1tf:                      Not affected
   Vulnerability Mds:                       Not affected
   Vulnerability Meltdown:                  Not affected
   Vulnerability Mmio stale data:           Not affected
   Vulnerability Reg file data sampling:    Not affected
   Vulnerability Retbleed:                  Not affected
   Vulnerability Spec rstack overflow:      Not affected
   Vulnerability Spec store bypass:         Mitigation; Speculative Store Bypass disabled via prctl
   Vulnerability Spectre v1:                Mitigation; __user pointer sanitization
   Vulnerability Spectre v2:                Mitigation; CSV2, BHB
   Vulnerability Srbds:                     Not affected
   Vulnerability Tsa:                       Not affected
   Vulnerability Tsx async abort:           Not affected
   Vulnerability Vmscape:                   Not affected
   ```
   
   </details>
   
   Comparing octet_length-01-23086 (08d730a2c19d69120885f41c220d4350eceb48ed) to 3e058f0 (merge-base) [diff](https://github.com/apache/datafusion/compare/3e058f09c91a18c8f36b71a656231603b33888c2..08d730a2c19d69120885f41c220d4350eceb48ed) using: clickbench_1
   Results will be posted here when complete
   
   ---
   [File an issue](https://github.com/adriangb/datafusion-benchmarking/issues) against this benchmark runner


-- 
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: github-unsubscribe@datafusion.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org
For additional commands, e-mail: github-help@datafusion.apache.org


Re: [PR] Use `octet_length` for ClickBench Q27/Q28 byte-length semantics [datafusion]

Posted by "adriangbot (via GitHub)" <gi...@apache.org>.
adriangbot commented on PR #23475:
URL: https://github.com/apache/datafusion/pull/23475#issuecomment-4943684051

   ๐Ÿค– Benchmark completed (GKE) | [trigger](https://github.com/apache/datafusion/pull/23475#issuecomment-4943549427)
   
   **Instance:** `c4a-highmem-16` (12 vCPU / 65 GiB)
   
   <details><summary>CPU Details (lscpu)</summary>
   
   ```
   Architecture:                            aarch64
   CPU op-mode(s):                          64-bit
   Byte Order:                              Little Endian
   CPU(s):                                  16
   On-line CPU(s) list:                     0-15
   Vendor ID:                               ARM
   Model name:                              Neoverse-V2
   Model:                                   1
   Thread(s) per core:                      1
   Core(s) per cluster:                     16
   Socket(s):                               -
   Cluster(s):                              1
   Stepping:                                r0p1
   BogoMIPS:                                2000.00
   Flags:                                   fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh rng bti
   L1d cache:                               1 MiB (16 instances)
   L1i cache:                               1 MiB (16 instances)
   L2 cache:                                32 MiB (16 instances)
   L3 cache:                                80 MiB (1 instance)
   NUMA node(s):                            1
   NUMA node0 CPU(s):                       0-15
   Vulnerability Gather data sampling:      Not affected
   Vulnerability Indirect target selection: Not affected
   Vulnerability Itlb multihit:             Not affected
   Vulnerability L1tf:                      Not affected
   Vulnerability Mds:                       Not affected
   Vulnerability Meltdown:                  Not affected
   Vulnerability Mmio stale data:           Not affected
   Vulnerability Reg file data sampling:    Not affected
   Vulnerability Retbleed:                  Not affected
   Vulnerability Spec rstack overflow:      Not affected
   Vulnerability Spec store bypass:         Mitigation; Speculative Store Bypass disabled via prctl
   Vulnerability Spectre v1:                Mitigation; __user pointer sanitization
   Vulnerability Spectre v2:                Mitigation; CSV2, BHB
   Vulnerability Srbds:                     Not affected
   Vulnerability Tsa:                       Not affected
   Vulnerability Tsx async abort:           Not affected
   Vulnerability Vmscape:                   Not affected
   ```
   
   </details>
   
   <details><summary>Details</summary>
   <p>
   
   ```
   Comparing HEAD and octet_length-01-23086
   --------------------
   Benchmark clickbench_1.json
   --------------------
   โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”ณโ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”ณโ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”ณโ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”“
   โ”ƒ Query     โ”ƒ                                  HEAD โ”ƒ                 octet_length-01-23086 โ”ƒ        Change โ”ƒ
   โ”กโ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ•‡โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ•‡โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ•‡โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”ฉ
   โ”‚ QQuery 0  โ”‚           0.68 / 1.55 ยฑ1.62 / 4.79 ms โ”‚           0.67 / 1.43 ยฑ1.45 / 4.33 ms โ”‚ +1.08x faster โ”‚
   โ”‚ QQuery 1  โ”‚        13.83 / 14.21 ยฑ0.56 / 15.29 ms โ”‚        13.53 / 13.87 ยฑ0.51 / 14.86 ms โ”‚     no change โ”‚
   โ”‚ QQuery 2  โ”‚        40.25 / 40.71 ยฑ0.34 / 41.30 ms โ”‚        40.36 / 40.54 ยฑ0.12 / 40.74 ms โ”‚     no change โ”‚
   โ”‚ QQuery 3  โ”‚        36.07 / 36.82 ยฑ0.94 / 38.66 ms โ”‚        35.85 / 36.20 ยฑ0.30 / 36.62 ms โ”‚     no change โ”‚
   โ”‚ QQuery 4  โ”‚     239.75 / 242.77 ยฑ2.55 / 246.63 ms โ”‚     241.38 / 249.77 ยฑ7.28 / 263.00 ms โ”‚     no change โ”‚
   โ”‚ QQuery 5  โ”‚     426.44 / 436.38 ยฑ5.57 / 442.34 ms โ”‚     431.01 / 441.04 ยฑ6.52 / 447.76 ms โ”‚     no change โ”‚
   โ”‚ QQuery 6  โ”‚           0.74 / 0.83 ยฑ0.15 / 1.12 ms โ”‚           0.76 / 0.85 ยฑ0.15 / 1.16 ms โ”‚     no change โ”‚
   โ”‚ QQuery 7  โ”‚        15.47 / 15.63 ยฑ0.13 / 15.80 ms โ”‚        15.29 / 15.40 ยฑ0.09 / 15.55 ms โ”‚     no change โ”‚
   โ”‚ QQuery 8  โ”‚     363.56 / 365.26 ยฑ1.63 / 368.09 ms โ”‚    362.18 / 370.97 ยฑ10.11 / 389.85 ms โ”‚     no change โ”‚
   โ”‚ QQuery 9  โ”‚    537.63 / 557.09 ยฑ14.19 / 574.70 ms โ”‚    531.71 / 549.75 ยฑ12.97 / 571.02 ms โ”‚     no change โ”‚
   โ”‚ QQuery 10 โ”‚        85.32 / 88.20 ยฑ4.60 / 97.29 ms โ”‚      85.20 / 91.90 ยฑ11.79 / 115.40 ms โ”‚     no change โ”‚
   โ”‚ QQuery 11 โ”‚      99.52 / 103.49 ยฑ6.98 / 117.43 ms โ”‚       99.12 / 99.56 ยฑ0.49 / 100.18 ms โ”‚     no change โ”‚
   โ”‚ QQuery 12 โ”‚     451.62 / 459.04 ยฑ7.17 / 470.53 ms โ”‚     450.25 / 460.59 ยฑ8.86 / 475.50 ms โ”‚     no change โ”‚
   โ”‚ QQuery 13 โ”‚     473.72 / 483.32 ยฑ9.15 / 499.95 ms โ”‚    471.25 / 489.32 ยฑ13.38 / 511.92 ms โ”‚     no change โ”‚
   โ”‚ QQuery 14 โ”‚     456.20 / 463.17 ยฑ8.41 / 478.75 ms โ”‚    449.06 / 470.43 ยฑ13.84 / 490.38 ms โ”‚     no change โ”‚
   โ”‚ QQuery 15 โ”‚    293.88 / 311.05 ยฑ15.05 / 336.17 ms โ”‚     286.22 / 302.29 ยฑ9.42 / 314.92 ms โ”‚     no change โ”‚
   โ”‚ QQuery 16 โ”‚    636.29 / 652.24 ยฑ12.60 / 674.11 ms โ”‚    653.08 / 670.14 ยฑ12.92 / 684.06 ms โ”‚     no change โ”‚
   โ”‚ QQuery 17 โ”‚    642.08 / 657.75 ยฑ14.57 / 681.79 ms โ”‚    638.35 / 658.52 ยฑ12.04 / 673.24 ms โ”‚     no change โ”‚
   โ”‚ QQuery 18 โ”‚ 1253.28 / 1290.50 ยฑ46.18 / 1377.82 ms โ”‚ 1244.40 / 1290.22 ยฑ48.46 / 1376.37 ms โ”‚     no change โ”‚
   โ”‚ QQuery 19 โ”‚        34.03 / 36.32 ยฑ4.15 / 44.63 ms โ”‚        33.94 / 34.43 ยฑ0.33 / 34.81 ms โ”‚ +1.05x faster โ”‚
   โ”‚ QQuery 20 โ”‚    621.13 / 637.67 ยฑ11.15 / 649.49 ms โ”‚     616.93 / 627.58 ยฑ6.14 / 633.89 ms โ”‚     no change โ”‚
   โ”‚ QQuery 21 โ”‚     633.00 / 641.11 ยฑ6.30 / 649.60 ms โ”‚     626.44 / 637.92 ยฑ6.23 / 642.91 ms โ”‚     no change โ”‚
   โ”‚ QQuery 22 โ”‚ 1325.73 / 1350.62 ยฑ20.05 / 1386.33 ms โ”‚ 1309.93 / 1323.62 ยฑ10.47 / 1336.56 ms โ”‚     no change โ”‚
   โ”‚ QQuery 23 โ”‚ 3115.17 / 3144.89 ยฑ30.23 / 3183.93 ms โ”‚ 3057.21 / 3125.08 ยฑ38.20 / 3169.63 ms โ”‚     no change โ”‚
   โ”‚ QQuery 24 โ”‚    121.06 / 129.25 ยฑ14.28 / 157.80 ms โ”‚     119.79 / 124.00 ยฑ5.68 / 135.11 ms โ”‚     no change โ”‚
   โ”‚ QQuery 25 โ”‚     179.88 / 189.87 ยฑ9.00 / 203.04 ms โ”‚     183.13 / 187.75 ยฑ3.74 / 193.58 ms โ”‚     no change โ”‚
   โ”‚ QQuery 26 โ”‚     121.10 / 124.82 ยฑ3.59 / 129.30 ms โ”‚     120.96 / 125.47 ยฑ5.11 / 134.27 ms โ”‚     no change โ”‚
   โ”‚ QQuery 27 โ”‚    756.89 / 770.15 ยฑ10.61 / 782.33 ms โ”‚     757.74 / 769.54 ยฑ9.57 / 784.70 ms โ”‚     no change โ”‚
   โ”‚ QQuery 28 โ”‚ 3485.22 / 3536.32 ยฑ33.85 / 3587.97 ms โ”‚ 3489.89 / 3520.57 ยฑ33.60 / 3584.35 ms โ”‚     no change โ”‚
   โ”‚ QQuery 29 โ”‚       44.93 / 61.28 ยฑ20.14 / 99.21 ms โ”‚       44.23 / 60.20 ยฑ20.84 / 96.91 ms โ”‚     no change โ”‚
   โ”‚ QQuery 30 โ”‚    423.47 / 437.72 ยฑ15.36 / 461.48 ms โ”‚    418.55 / 428.57 ยฑ15.21 / 458.62 ms โ”‚     no change โ”‚
   โ”‚ QQuery 31 โ”‚    372.35 / 396.27 ยฑ16.72 / 421.73 ms โ”‚    362.72 / 388.47 ยฑ21.74 / 415.00 ms โ”‚     no change โ”‚
   โ”‚ QQuery 32 โ”‚   932.73 / 970.96 ยฑ29.30 / 1006.66 ms โ”‚  954.10 / 1013.81 ยฑ46.99 / 1071.29 ms โ”‚     no change โ”‚
   โ”‚ QQuery 33 โ”‚ 1497.35 / 1518.74 ยฑ17.79 / 1548.71 ms โ”‚ 1511.82 / 1532.70 ยฑ12.80 / 1547.65 ms โ”‚     no change โ”‚
   โ”‚ QQuery 34 โ”‚ 1511.20 / 1541.29 ยฑ23.49 / 1577.95 ms โ”‚  1525.58 / 1539.94 ยฑ9.68 / 1552.15 ms โ”‚     no change โ”‚
   โ”‚ QQuery 35 โ”‚    319.66 / 351.24 ยฑ23.67 / 392.37 ms โ”‚     322.53 / 335.59 ยฑ8.71 / 348.78 ms โ”‚     no change โ”‚
   โ”‚ QQuery 36 โ”‚     126.90 / 138.91 ยฑ8.23 / 150.71 ms โ”‚     139.62 / 155.22 ยฑ8.68 / 166.43 ms โ”‚  1.12x slower โ”‚
   โ”‚ QQuery 37 โ”‚        51.39 / 57.07 ยฑ5.14 / 65.16 ms โ”‚        54.52 / 57.63 ยฑ3.11 / 62.34 ms โ”‚     no change โ”‚
   โ”‚ QQuery 38 โ”‚        85.18 / 89.34 ยฑ4.35 / 97.14 ms โ”‚        85.07 / 90.55 ยฑ2.82 / 92.85 ms โ”‚     no change โ”‚
   โ”‚ QQuery 39 โ”‚     261.08 / 273.41 ยฑ8.91 / 286.10 ms โ”‚    252.24 / 274.97 ยฑ12.12 / 288.01 ms โ”‚     no change โ”‚
   โ”‚ QQuery 40 โ”‚        21.56 / 23.06 ยฑ0.92 / 24.26 ms โ”‚        19.87 / 21.64 ยฑ1.09 / 22.98 ms โ”‚ +1.07x faster โ”‚
   โ”‚ QQuery 41 โ”‚        19.24 / 21.23 ยฑ2.77 / 26.67 ms โ”‚        19.42 / 25.67 ยฑ8.05 / 39.73 ms โ”‚  1.21x slower โ”‚
   โ”‚ QQuery 42 โ”‚        18.81 / 19.14 ยฑ0.35 / 19.76 ms โ”‚        18.37 / 20.52 ยฑ3.82 / 28.16 ms โ”‚  1.07x slower โ”‚
   โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜
   โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”ณโ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”“
   โ”ƒ Benchmark Summary                    โ”ƒ            โ”ƒ
   โ”กโ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ•‡โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”ฉ
   โ”‚ Total Time (HEAD)                    โ”‚ 22680.68ms โ”‚
   โ”‚ Total Time (octet_length-01-23086)   โ”‚ 22674.25ms โ”‚
   โ”‚ Average Time (HEAD)                  โ”‚   527.46ms โ”‚
   โ”‚ Average Time (octet_length-01-23086) โ”‚   527.31ms โ”‚
   โ”‚ Queries Faster                       โ”‚          3 โ”‚
   โ”‚ Queries Slower                       โ”‚          3 โ”‚
   โ”‚ Queries with No Change               โ”‚         37 โ”‚
   โ”‚ Queries with Failure                 โ”‚          0 โ”‚
   โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜
   ```
   
   </p>
   </details>
   
   <details><summary>Resource Usage</summary>
   
   **clickbench_1 โ€” base (merge-base)**
   | Metric | Value |
   |--------|-------|
   | Wall time | 115.0s |
   | Peak memory | 11.9 GiB |
   | Avg memory | 3.8 GiB |
   | CPU user | 1045.0s |
   | CPU sys | 70.2s |
   | Peak spill | 0 B |
   
   **clickbench_1 โ€” branch**
   | Metric | Value |
   |--------|-------|
   | Wall time | 115.0s |
   | Peak memory | 11.2 GiB |
   | Avg memory | 3.9 GiB |
   | CPU user | 1045.8s |
   | CPU sys | 71.1s |
   | Peak spill | 0 B |
   
   </details>
   
   
   ---
   [File an issue](https://github.com/adriangb/datafusion-benchmarking/issues) against this benchmark runner


-- 
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: github-unsubscribe@datafusion.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org
For additional commands, e-mail: github-help@datafusion.apache.org


Re: [PR] Use `octet_length` for ClickBench Q27/Q28 byte-length semantics [datafusion]

Posted by "adriangbot (via GitHub)" <gi...@apache.org>.
adriangbot commented on PR #23475:
URL: https://github.com/apache/datafusion/pull/23475#issuecomment-4943512175

   ๐Ÿค– Benchmark completed (GKE) | [trigger](https://github.com/apache/datafusion/pull/23475#issuecomment-4943279827)
   
   **Instance:** `c4a-highmem-16` (12 vCPU / 65 GiB)
   
   <details><summary>CPU Details (lscpu)</summary>
   
   ```
   Architecture:                            aarch64
   CPU op-mode(s):                          64-bit
   Byte Order:                              Little Endian
   CPU(s):                                  16
   On-line CPU(s) list:                     0-15
   Vendor ID:                               ARM
   Model name:                              Neoverse-V2
   Model:                                   1
   Thread(s) per core:                      1
   Core(s) per cluster:                     16
   Socket(s):                               -
   Cluster(s):                              1
   Stepping:                                r0p1
   BogoMIPS:                                2000.00
   Flags:                                   fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh rng bti
   L1d cache:                               1 MiB (16 instances)
   L1i cache:                               1 MiB (16 instances)
   L2 cache:                                32 MiB (16 instances)
   L3 cache:                                80 MiB (1 instance)
   NUMA node(s):                            1
   NUMA node0 CPU(s):                       0-15
   Vulnerability Gather data sampling:      Not affected
   Vulnerability Indirect target selection: Not affected
   Vulnerability Itlb multihit:             Not affected
   Vulnerability L1tf:                      Not affected
   Vulnerability Mds:                       Not affected
   Vulnerability Meltdown:                  Not affected
   Vulnerability Mmio stale data:           Not affected
   Vulnerability Reg file data sampling:    Not affected
   Vulnerability Retbleed:                  Not affected
   Vulnerability Spec rstack overflow:      Not affected
   Vulnerability Spec store bypass:         Mitigation; Speculative Store Bypass disabled via prctl
   Vulnerability Spectre v1:                Mitigation; __user pointer sanitization
   Vulnerability Spectre v2:                Mitigation; CSV2, BHB
   Vulnerability Srbds:                     Not affected
   Vulnerability Tsa:                       Not affected
   Vulnerability Tsx async abort:           Not affected
   Vulnerability Vmscape:                   Not affected
   ```
   
   </details>
   
   <details><summary>Details</summary>
   <p>
   
   ```
   Comparing HEAD and octet_length-01-23086
   --------------------
   Benchmark clickbench_partitioned.json
   --------------------
   โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”ณโ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”ณโ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”ณโ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”“
   โ”ƒ Query     โ”ƒ                                  HEAD โ”ƒ                 octet_length-01-23086 โ”ƒ        Change โ”ƒ
   โ”กโ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ•‡โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ•‡โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ•‡โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”ฉ
   โ”‚ QQuery 0  โ”‚          1.24 / 4.11 ยฑ5.56 / 15.22 ms โ”‚          1.30 / 4.22 ยฑ5.69 / 15.59 ms โ”‚     no change โ”‚
   โ”‚ QQuery 1  โ”‚        13.25 / 13.82 ยฑ0.35 / 14.33 ms โ”‚        13.04 / 13.78 ยฑ0.48 / 14.40 ms โ”‚     no change โ”‚
   โ”‚ QQuery 2  โ”‚        37.38 / 37.62 ยฑ0.19 / 37.85 ms โ”‚        36.99 / 37.29 ยฑ0.42 / 38.11 ms โ”‚     no change โ”‚
   โ”‚ QQuery 3  โ”‚        31.85 / 32.91 ยฑ0.74 / 34.16 ms โ”‚        31.87 / 32.18 ยฑ0.36 / 32.89 ms โ”‚     no change โ”‚
   โ”‚ QQuery 4  โ”‚     242.89 / 247.86 ยฑ6.12 / 259.72 ms โ”‚     241.86 / 247.47 ยฑ4.13 / 253.66 ms โ”‚     no change โ”‚
   โ”‚ QQuery 5  โ”‚     288.21 / 290.80 ยฑ2.37 / 295.16 ms โ”‚     287.02 / 291.06 ยฑ2.97 / 294.08 ms โ”‚     no change โ”‚
   โ”‚ QQuery 6  โ”‚           1.29 / 1.46 ยฑ0.23 / 1.91 ms โ”‚           1.32 / 1.46 ยฑ0.23 / 1.92 ms โ”‚     no change โ”‚
   โ”‚ QQuery 7  โ”‚        14.90 / 17.32 ยฑ4.13 / 25.57 ms โ”‚        15.13 / 18.93 ยฑ6.80 / 32.51 ms โ”‚  1.09x slower โ”‚
   โ”‚ QQuery 8  โ”‚     345.54 / 353.86 ยฑ5.99 / 363.11 ms โ”‚     343.00 / 353.60 ยฑ8.37 / 365.14 ms โ”‚     no change โ”‚
   โ”‚ QQuery 9  โ”‚     487.96 / 494.23 ยฑ3.63 / 498.73 ms โ”‚    499.76 / 513.66 ยฑ14.93 / 542.42 ms โ”‚     no change โ”‚
   โ”‚ QQuery 10 โ”‚        73.67 / 75.46 ยฑ1.16 / 76.94 ms โ”‚       74.92 / 81.73 ยฑ9.91 / 101.33 ms โ”‚  1.08x slower โ”‚
   โ”‚ QQuery 11 โ”‚        86.64 / 87.77 ยฑ1.06 / 89.05 ms โ”‚       87.44 / 92.11 ยฑ8.38 / 108.84 ms โ”‚     no change โ”‚
   โ”‚ QQuery 12 โ”‚     279.91 / 290.16 ยฑ5.24 / 294.46 ms โ”‚     290.87 / 302.59 ยฑ7.84 / 313.35 ms โ”‚     no change โ”‚
   โ”‚ QQuery 13 โ”‚    387.08 / 405.83 ยฑ14.02 / 423.19 ms โ”‚     393.54 / 402.22 ยฑ7.91 / 416.54 ms โ”‚     no change โ”‚
   โ”‚ QQuery 14 โ”‚     303.36 / 306.32 ยฑ2.95 / 311.67 ms โ”‚    294.78 / 312.85 ยฑ10.81 / 324.57 ms โ”‚     no change โ”‚
   โ”‚ QQuery 15 โ”‚     307.26 / 314.46 ยฑ5.26 / 322.39 ms โ”‚    302.81 / 314.89 ยฑ10.45 / 330.17 ms โ”‚     no change โ”‚
   โ”‚ QQuery 16 โ”‚    646.18 / 674.88 ยฑ18.18 / 695.27 ms โ”‚    659.26 / 679.95 ยฑ15.29 / 700.79 ms โ”‚     no change โ”‚
   โ”‚ QQuery 17 โ”‚     671.01 / 679.48 ยฑ5.93 / 689.43 ms โ”‚    688.15 / 705.06 ยฑ11.84 / 719.38 ms โ”‚     no change โ”‚
   โ”‚ QQuery 18 โ”‚ 1319.05 / 1364.37 ยฑ27.71 / 1401.62 ms โ”‚ 1360.78 / 1378.25 ยฑ22.24 / 1420.81 ms โ”‚     no change โ”‚
   โ”‚ QQuery 19 โ”‚        29.32 / 31.11 ยฑ2.49 / 36.02 ms โ”‚        29.48 / 35.67 ยฑ7.27 / 45.67 ms โ”‚  1.15x slower โ”‚
   โ”‚ QQuery 20 โ”‚     522.97 / 530.55 ยฑ6.92 / 543.53 ms โ”‚     519.61 / 529.01 ยฑ8.70 / 545.30 ms โ”‚     no change โ”‚
   โ”‚ QQuery 21 โ”‚     520.91 / 529.30 ยฑ7.33 / 540.25 ms โ”‚     523.83 / 528.42 ยฑ6.62 / 541.45 ms โ”‚     no change โ”‚
   โ”‚ QQuery 22 โ”‚  1013.21 / 1026.42 ยฑ9.12 / 1039.70 ms โ”‚ 1032.60 / 1044.67 ยฑ10.68 / 1058.91 ms โ”‚     no change โ”‚
   โ”‚ QQuery 23 โ”‚ 3191.92 / 3236.95 ยฑ27.54 / 3267.96 ms โ”‚ 3258.26 / 3279.50 ยฑ17.49 / 3305.32 ms โ”‚     no change โ”‚
   โ”‚ QQuery 24 โ”‚        42.63 / 44.24 ยฑ2.69 / 49.61 ms โ”‚        42.73 / 48.90 ยฑ6.86 / 61.26 ms โ”‚  1.11x slower โ”‚
   โ”‚ QQuery 25 โ”‚     114.99 / 120.10 ยฑ6.85 / 133.41 ms โ”‚     114.30 / 115.71 ยฑ1.36 / 118.00 ms โ”‚     no change โ”‚
   โ”‚ QQuery 26 โ”‚        42.87 / 43.49 ยฑ0.41 / 43.96 ms โ”‚        43.18 / 47.16 ยฑ4.43 / 54.34 ms โ”‚  1.08x slower โ”‚
   โ”‚ QQuery 27 โ”‚     674.88 / 682.22 ยฑ7.51 / 696.26 ms โ”‚     682.77 / 687.47 ยฑ4.00 / 694.69 ms โ”‚     no change โ”‚
   โ”‚ QQuery 28 โ”‚ 3090.69 / 3139.62 ยฑ35.35 / 3186.48 ms โ”‚ 3124.35 / 3153.87 ยฑ28.94 / 3201.66 ms โ”‚     no change โ”‚
   โ”‚ QQuery 29 โ”‚       43.63 / 55.02 ยฑ14.60 / 79.43 ms โ”‚        42.63 / 43.12 ยฑ0.38 / 43.78 ms โ”‚ +1.28x faster โ”‚
   โ”‚ QQuery 30 โ”‚     333.63 / 338.78 ยฑ5.07 / 345.50 ms โ”‚     333.60 / 340.62 ยฑ8.02 / 354.88 ms โ”‚     no change โ”‚
   โ”‚ QQuery 31 โ”‚    307.52 / 318.44 ยฑ10.67 / 336.69 ms โ”‚    294.74 / 312.41 ยฑ12.28 / 326.17 ms โ”‚     no change โ”‚
   โ”‚ QQuery 32 โ”‚  993.47 / 1038.94 ยฑ34.19 / 1082.85 ms โ”‚ 1047.27 / 1082.10 ยฑ23.69 / 1115.91 ms โ”‚     no change โ”‚
   โ”‚ QQuery 33 โ”‚ 1570.50 / 1603.62 ยฑ17.47 / 1620.46 ms โ”‚ 1574.14 / 1609.84 ยฑ34.19 / 1674.99 ms โ”‚     no change โ”‚
   โ”‚ QQuery 34 โ”‚ 1571.88 / 1624.86 ยฑ51.98 / 1699.34 ms โ”‚ 1560.49 / 1610.80 ยฑ29.37 / 1652.12 ms โ”‚     no change โ”‚
   โ”‚ QQuery 35 โ”‚    315.58 / 336.26 ยฑ19.69 / 362.72 ms โ”‚    326.95 / 364.16 ยฑ38.47 / 431.02 ms โ”‚  1.08x slower โ”‚
   โ”‚ QQuery 36 โ”‚        69.27 / 74.39 ยฑ3.84 / 80.18 ms โ”‚        71.75 / 86.36 ยฑ9.56 / 96.27 ms โ”‚  1.16x slower โ”‚
   โ”‚ QQuery 37 โ”‚        37.53 / 45.48 ยฑ6.95 / 58.24 ms โ”‚        37.69 / 39.35 ยฑ2.63 / 44.54 ms โ”‚ +1.16x faster โ”‚
   โ”‚ QQuery 38 โ”‚        45.22 / 46.95 ยฑ2.58 / 52.08 ms โ”‚        41.57 / 43.07 ยฑ1.07 / 44.37 ms โ”‚ +1.09x faster โ”‚
   โ”‚ QQuery 39 โ”‚     153.21 / 162.81 ยฑ5.46 / 170.05 ms โ”‚     155.13 / 167.14 ยฑ6.08 / 171.16 ms โ”‚     no change โ”‚
   โ”‚ QQuery 40 โ”‚        15.42 / 16.33 ยฑ1.05 / 18.39 ms โ”‚        14.99 / 15.88 ยฑ0.94 / 17.29 ms โ”‚     no change โ”‚
   โ”‚ QQuery 41 โ”‚        14.93 / 15.32 ยฑ0.23 / 15.54 ms โ”‚        15.06 / 15.36 ยฑ0.22 / 15.71 ms โ”‚     no change โ”‚
   โ”‚ QQuery 42 โ”‚        14.24 / 14.55 ยฑ0.22 / 14.93 ms โ”‚        13.94 / 14.40 ยฑ0.25 / 14.64 ms โ”‚     no change โ”‚
   โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜
   โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”ณโ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”“
   โ”ƒ Benchmark Summary                    โ”ƒ            โ”ƒ
   โ”กโ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ•‡โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”ฉ
   โ”‚ Total Time (HEAD)                    โ”‚ 20768.48ms โ”‚
   โ”‚ Total Time (octet_length-01-23086)   โ”‚ 20998.27ms โ”‚
   โ”‚ Average Time (HEAD)                  โ”‚   482.99ms โ”‚
   โ”‚ Average Time (octet_length-01-23086) โ”‚   488.33ms โ”‚
   โ”‚ Queries Faster                       โ”‚          3 โ”‚
   โ”‚ Queries Slower                       โ”‚          7 โ”‚
   โ”‚ Queries with No Change               โ”‚         33 โ”‚
   โ”‚ Queries with Failure                 โ”‚          0 โ”‚
   โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜
   ```
   
   </p>
   </details>
   
   <details><summary>Resource Usage</summary>
   
   **clickbench_partitioned โ€” base (merge-base)**
   | Metric | Value |
   |--------|-------|
   | Wall time | 105.0s |
   | Peak memory | 11.1 GiB |
   | Avg memory | 4.3 GiB |
   | CPU user | 1070.6s |
   | CPU sys | 75.1s |
   | Peak spill | 0 B |
   
   **clickbench_partitioned โ€” branch**
   | Metric | Value |
   |--------|-------|
   | Wall time | 110.0s |
   | Peak memory | 11.9 GiB |
   | Avg memory | 4.4 GiB |
   | CPU user | 1069.1s |
   | CPU sys | 80.6s |
   | Peak spill | 0 B |
   
   </details>
   
   
   ---
   [File an issue](https://github.com/adriangb/datafusion-benchmarking/issues) against this benchmark runner


-- 
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: github-unsubscribe@datafusion.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org
For additional commands, e-mail: github-help@datafusion.apache.org


Re: [PR] Use `octet_length` for ClickBench Q27/Q28 byte-length semantics [datafusion]

Posted by "alamb (via GitHub)" <gi...@apache.org>.
alamb commented on PR #23475:
URL: https://github.com/apache/datafusion/pull/23475#issuecomment-4981229543

   > https://github.com/ClickHouse/ClickBench/pull/985
   
   Merged!


-- 
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: github-unsubscribe@datafusion.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org
For additional commands, e-mail: github-help@datafusion.apache.org


Re: [PR] Use `octet_length` for ClickBench Q27/Q28 byte-length semantics [datafusion]

Posted by "alamb (via GitHub)" <gi...@apache.org>.
alamb commented on code in PR #23475:
URL: https://github.com/apache/datafusion/pull/23475#discussion_r3566132187


##########
benchmarks/sql_benchmarks/clickbench/benchmarks/q27.benchmark:
##########
@@ -11,6 +11,7 @@ SELECT COUNT(*) > 0 from hits;
 true
 
 run
-SELECT "CounterID", AVG(length("URL")) AS l, COUNT(*) AS c FROM hits WHERE "URL" <> '' GROUP BY "CounterID" HAVING COUNT(*) > 100000 ORDER BY l DESC LIMIT 25;
+-- DataFusion length(...) counts characters; use octet_length(...) for ClickBench byte-length semantics.

Review Comment:
   yeah this duplication is unfortunate but I think @Omega359  is working to consolidate them all



-- 
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: github-unsubscribe@datafusion.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org
For additional commands, e-mail: github-help@datafusion.apache.org


Re: [PR] Use `octet_length` for ClickBench Q27/Q28 byte-length semantics [datafusion]

Posted by "adriangbot (via GitHub)" <gi...@apache.org>.
adriangbot commented on PR #23475:
URL: https://github.com/apache/datafusion/pull/23475#issuecomment-4943460132

   Benchmark for [this request](https://github.com/apache/datafusion/pull/23475#issuecomment-4943253066) failed.
   
   Last 20 lines of output:
   <details><summary>Click to expand</summary>
   
   ```
   # Micro-Benchmarks (specific operators and features)
   cancellation:           How long cancelling a query takes
   nlj:                    Benchmark for simple nested loop joins, testing various join scenarios
   hj:                     Benchmark for simple hash joins, testing various join scenarios
   smj:                    Benchmark for simple sort merge joins, testing various join scenarios
   dict:                   Benchmark for dictionary-encoded group-by scenarios
   compile_profile:        Compile and execute TPC-H across selected Cargo profiles, reporting timing and binary size
   
   
   โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”
   Supported Configuration (Environment Variables)
   โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”
   DATA_DIR            directory to store datasets
   CARGO_COMMAND       command that runs the benchmark binary
   DATAFUSION_DIR      directory to use (default /workspace/datafusion-base)
   RESULTS_NAME        folder where the benchmark files are stored
   PREFER_HASH_JOIN    Prefer hash join algorithm (default true)
   SIMULATE_LATENCY    Simulate object store latency to mimic S3 (default false)
   DATAFUSION_*        Set the given datafusion configuration
   
   ```
   
   </details>
   
   ---
   [File an issue](https://github.com/adriangb/datafusion-benchmarking/issues) against this benchmark runner


-- 
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: github-unsubscribe@datafusion.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org
For additional commands, e-mail: github-help@datafusion.apache.org


Re: [PR] Use `octet_length` for ClickBench Q27/Q28 byte-length semantics [datafusion]

Posted by "kosiew (via GitHub)" <gi...@apache.org>.
kosiew commented on PR #23475:
URL: https://github.com/apache/datafusion/pull/23475#issuecomment-4943279827

   run benchmark clickbench_partitioned


-- 
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: github-unsubscribe@datafusion.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org
For additional commands, e-mail: github-help@datafusion.apache.org


Re: [PR] Use `octet_length` for ClickBench Q27/Q28 byte-length semantics [datafusion]

Posted by "kosiew (via GitHub)" <gi...@apache.org>.
kosiew commented on PR #23475:
URL: https://github.com/apache/datafusion/pull/23475#issuecomment-4943493443

   show benchmark queue


-- 
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: github-unsubscribe@datafusion.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org
For additional commands, e-mail: github-help@datafusion.apache.org


Re: [PR] Use `octet_length` for ClickBench Q27/Q28 byte-length semantics [datafusion]

Posted by "adriangbot (via GitHub)" <gi...@apache.org>.
adriangbot commented on PR #23475:
URL: https://github.com/apache/datafusion/pull/23475#issuecomment-4943528395

   ๐Ÿค– Benchmark completed (GKE) | [trigger](https://github.com/apache/datafusion/pull/23475#issuecomment-4943253066)
   
   **Instance:** `c4a-highmem-16` (12 vCPU / 65 GiB)
   
   <details><summary>CPU Details (lscpu)</summary>
   
   ```
   Architecture:                            aarch64
   CPU op-mode(s):                          64-bit
   Byte Order:                              Little Endian
   CPU(s):                                  16
   On-line CPU(s) list:                     0-15
   Vendor ID:                               ARM
   Model name:                              Neoverse-V2
   Model:                                   1
   Thread(s) per core:                      1
   Core(s) per cluster:                     16
   Socket(s):                               -
   Cluster(s):                              1
   Stepping:                                r0p1
   BogoMIPS:                                2000.00
   Flags:                                   fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh rng bti
   L1d cache:                               1 MiB (16 instances)
   L1i cache:                               1 MiB (16 instances)
   L2 cache:                                32 MiB (16 instances)
   L3 cache:                                80 MiB (1 instance)
   NUMA node(s):                            1
   NUMA node0 CPU(s):                       0-15
   Vulnerability Gather data sampling:      Not affected
   Vulnerability Indirect target selection: Not affected
   Vulnerability Itlb multihit:             Not affected
   Vulnerability L1tf:                      Not affected
   Vulnerability Mds:                       Not affected
   Vulnerability Meltdown:                  Not affected
   Vulnerability Mmio stale data:           Not affected
   Vulnerability Reg file data sampling:    Not affected
   Vulnerability Retbleed:                  Not affected
   Vulnerability Spec rstack overflow:      Not affected
   Vulnerability Spec store bypass:         Mitigation; Speculative Store Bypass disabled via prctl
   Vulnerability Spectre v1:                Mitigation; __user pointer sanitization
   Vulnerability Spectre v2:                Mitigation; CSV2, BHB
   Vulnerability Srbds:                     Not affected
   Vulnerability Tsa:                       Not affected
   Vulnerability Tsx async abort:           Not affected
   Vulnerability Vmscape:                   Not affected
   ```
   
   </details>
   
   <details><summary>Details</summary>
   <p>
   
   ```
   Comparing HEAD and octet_length-01-23086
   --------------------
   Benchmark clickbench_1.json
   --------------------
   โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”ณโ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”ณโ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”ณโ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”“
   โ”ƒ Query     โ”ƒ                                  HEAD โ”ƒ                 octet_length-01-23086 โ”ƒ        Change โ”ƒ
   โ”กโ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ•‡โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ•‡โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ•‡โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”ฉ
   โ”‚ QQuery 0  โ”‚           0.67 / 1.43 ยฑ1.45 / 4.33 ms โ”‚           0.68 / 1.44 ยฑ1.46 / 4.36 ms โ”‚     no change โ”‚
   โ”‚ QQuery 1  โ”‚        14.14 / 14.44 ยฑ0.40 / 15.22 ms โ”‚        13.43 / 13.89 ยฑ0.48 / 14.69 ms โ”‚     no change โ”‚
   โ”‚ QQuery 2  โ”‚        40.92 / 41.28 ยฑ0.40 / 42.03 ms โ”‚        40.60 / 40.92 ยฑ0.22 / 41.20 ms โ”‚     no change โ”‚
   โ”‚ QQuery 3  โ”‚        36.80 / 37.41 ยฑ0.78 / 38.94 ms โ”‚        36.61 / 36.99 ยฑ0.23 / 37.33 ms โ”‚     no change โ”‚
   โ”‚ QQuery 4  โ”‚     243.21 / 245.33 ยฑ1.50 / 246.93 ms โ”‚     242.00 / 246.85 ยฑ4.96 / 255.63 ms โ”‚     no change โ”‚
   โ”‚ QQuery 5  โ”‚     425.38 / 434.34 ยฑ5.84 / 440.97 ms โ”‚     429.23 / 435.39 ยฑ5.10 / 442.08 ms โ”‚     no change โ”‚
   โ”‚ QQuery 6  โ”‚           0.73 / 0.86 ยฑ0.15 / 1.15 ms โ”‚           0.75 / 0.85 ยฑ0.16 / 1.17 ms โ”‚     no change โ”‚
   โ”‚ QQuery 7  โ”‚        16.13 / 16.30 ยฑ0.23 / 16.73 ms โ”‚        15.46 / 15.58 ยฑ0.08 / 15.69 ms โ”‚     no change โ”‚
   โ”‚ QQuery 8  โ”‚     355.36 / 363.01 ยฑ5.31 / 370.22 ms โ”‚    351.43 / 371.23 ยฑ13.57 / 391.78 ms โ”‚     no change โ”‚
   โ”‚ QQuery 9  โ”‚    534.84 / 550.42 ยฑ12.82 / 572.49 ms โ”‚    528.35 / 546.71 ยฑ14.97 / 570.17 ms โ”‚     no change โ”‚
   โ”‚ QQuery 10 โ”‚        87.06 / 89.98 ยฑ5.01 / 99.97 ms โ”‚        85.11 / 87.14 ยฑ1.93 / 90.51 ms โ”‚     no change โ”‚
   โ”‚ QQuery 11 โ”‚     100.13 / 102.05 ยฑ1.72 / 104.76 ms โ”‚       98.65 / 99.57 ยฑ0.81 / 100.59 ms โ”‚     no change โ”‚
   โ”‚ QQuery 12 โ”‚    442.11 / 454.46 ยฑ14.74 / 483.45 ms โ”‚    440.56 / 455.08 ยฑ21.64 / 497.65 ms โ”‚     no change โ”‚
   โ”‚ QQuery 13 โ”‚    448.46 / 478.12 ยฑ15.23 / 491.29 ms โ”‚    466.90 / 496.15 ยฑ22.92 / 525.08 ms โ”‚     no change โ”‚
   โ”‚ QQuery 14 โ”‚     444.91 / 458.90 ยฑ8.84 / 469.82 ms โ”‚    451.69 / 471.82 ยฑ18.24 / 501.71 ms โ”‚     no change โ”‚
   โ”‚ QQuery 15 โ”‚    288.59 / 308.16 ยฑ19.51 / 342.08 ms โ”‚    292.29 / 306.00 ยฑ13.20 / 327.07 ms โ”‚     no change โ”‚
   โ”‚ QQuery 16 โ”‚    630.19 / 645.91 ยฑ10.31 / 658.98 ms โ”‚    642.96 / 661.05 ยฑ11.37 / 675.13 ms โ”‚     no change โ”‚
   โ”‚ QQuery 17 โ”‚    639.94 / 654.77 ยฑ15.03 / 680.43 ms โ”‚     646.53 / 653.06 ยฑ5.30 / 660.90 ms โ”‚     no change โ”‚
   โ”‚ QQuery 18 โ”‚ 1252.01 / 1284.82 ยฑ22.16 / 1314.98 ms โ”‚ 1272.43 / 1308.26 ยฑ28.07 / 1355.26 ms โ”‚     no change โ”‚
   โ”‚ QQuery 19 โ”‚        34.85 / 37.51 ยฑ4.52 / 46.54 ms โ”‚        34.44 / 34.84 ยฑ0.28 / 35.21 ms โ”‚ +1.08x faster โ”‚
   โ”‚ QQuery 20 โ”‚    626.57 / 647.07 ยฑ11.86 / 660.01 ms โ”‚    625.78 / 644.83 ยฑ21.45 / 686.10 ms โ”‚     no change โ”‚
   โ”‚ QQuery 21 โ”‚     628.14 / 640.88 ยฑ9.58 / 656.82 ms โ”‚    631.53 / 647.50 ยฑ11.25 / 661.67 ms โ”‚     no change โ”‚
   โ”‚ QQuery 22 โ”‚ 1316.76 / 1337.72 ยฑ24.38 / 1385.45 ms โ”‚ 1324.60 / 1336.46 ยฑ11.84 / 1357.84 ms โ”‚     no change โ”‚
   โ”‚ QQuery 23 โ”‚ 3121.10 / 3147.06 ยฑ18.93 / 3174.97 ms โ”‚ 3108.99 / 3159.49 ยฑ38.28 / 3203.87 ms โ”‚     no change โ”‚
   โ”‚ QQuery 24 โ”‚    122.04 / 129.92 ยฑ11.24 / 151.51 ms โ”‚     121.45 / 125.07 ยฑ3.47 / 131.69 ms โ”‚     no change โ”‚
   โ”‚ QQuery 25 โ”‚     181.67 / 189.40 ยฑ5.57 / 197.78 ms โ”‚     183.81 / 189.13 ยฑ4.94 / 196.49 ms โ”‚     no change โ”‚
   โ”‚ QQuery 26 โ”‚     123.11 / 124.89 ยฑ2.77 / 130.41 ms โ”‚     123.41 / 125.49 ยฑ1.54 / 127.55 ms โ”‚     no change โ”‚
   โ”‚ QQuery 27 โ”‚     756.29 / 765.65 ยฑ8.62 / 779.83 ms โ”‚    764.77 / 780.35 ยฑ14.24 / 801.93 ms โ”‚     no change โ”‚
   โ”‚ QQuery 28 โ”‚ 3496.01 / 3518.59 ยฑ16.94 / 3546.22 ms โ”‚ 3480.49 / 3523.93 ยฑ25.20 / 3557.33 ms โ”‚     no change โ”‚
   โ”‚ QQuery 29 โ”‚       44.56 / 52.69 ยฑ11.40 / 74.54 ms โ”‚       44.69 / 55.95 ยฑ16.22 / 87.61 ms โ”‚  1.06x slower โ”‚
   โ”‚ QQuery 30 โ”‚    410.94 / 428.78 ยฑ10.17 / 438.58 ms โ”‚    415.10 / 434.94 ยฑ16.09 / 450.25 ms โ”‚     no change โ”‚
   โ”‚ QQuery 31 โ”‚    380.04 / 399.55 ยฑ13.31 / 416.58 ms โ”‚    369.37 / 400.77 ยฑ24.98 / 435.92 ms โ”‚     no change โ”‚
   โ”‚ QQuery 32 โ”‚   960.70 / 985.04 ยฑ22.78 / 1025.43 ms โ”‚   926.70 / 971.60 ยฑ42.38 / 1044.09 ms โ”‚     no change โ”‚
   โ”‚ QQuery 33 โ”‚  1520.18 / 1529.35 ยฑ8.87 / 1540.89 ms โ”‚ 1489.29 / 1505.41 ยฑ13.81 / 1528.23 ms โ”‚     no change โ”‚
   โ”‚ QQuery 34 โ”‚ 1514.84 / 1550.70 ยฑ23.90 / 1584.54 ms โ”‚ 1521.03 / 1553.00 ยฑ31.74 / 1608.39 ms โ”‚     no change โ”‚
   โ”‚ QQuery 35 โ”‚     315.88 / 322.14 ยฑ3.74 / 326.81 ms โ”‚    310.47 / 348.40 ยฑ40.18 / 401.50 ms โ”‚  1.08x slower โ”‚
   โ”‚ QQuery 36 โ”‚     128.28 / 142.27 ยฑ9.85 / 157.30 ms โ”‚    132.46 / 147.73 ยฑ16.75 / 177.85 ms โ”‚     no change โ”‚
   โ”‚ QQuery 37 โ”‚        54.39 / 58.08 ยฑ3.70 / 64.44 ms โ”‚        54.27 / 57.41 ยฑ2.87 / 62.77 ms โ”‚     no change โ”‚
   โ”‚ QQuery 38 โ”‚        82.09 / 89.77 ยฑ4.34 / 93.71 ms โ”‚        86.68 / 90.96 ยฑ3.74 / 97.18 ms โ”‚     no change โ”‚
   โ”‚ QQuery 39 โ”‚    243.07 / 268.15 ยฑ12.85 / 277.95 ms โ”‚     262.20 / 272.90 ยฑ7.26 / 279.62 ms โ”‚     no change โ”‚
   โ”‚ QQuery 40 โ”‚        20.70 / 23.06 ยฑ2.07 / 26.78 ms โ”‚        20.04 / 20.94 ยฑ1.03 / 22.94 ms โ”‚ +1.10x faster โ”‚
   โ”‚ QQuery 41 โ”‚        19.01 / 25.27 ยฑ7.66 / 39.58 ms โ”‚        18.44 / 21.96 ยฑ4.17 / 30.10 ms โ”‚ +1.15x faster โ”‚
   โ”‚ QQuery 42 โ”‚        18.26 / 18.82 ยฑ0.50 / 19.41 ms โ”‚        18.20 / 18.80 ยฑ0.66 / 20.04 ms โ”‚     no change โ”‚
   โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜
   โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”ณโ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”“
   โ”ƒ Benchmark Summary                    โ”ƒ            โ”ƒ
   โ”กโ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ•‡โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”ฉ
   โ”‚ Total Time (HEAD)                    โ”‚ 22614.36ms โ”‚
   โ”‚ Total Time (octet_length-01-23086)   โ”‚ 22715.86ms โ”‚
   โ”‚ Average Time (HEAD)                  โ”‚   525.92ms โ”‚
   โ”‚ Average Time (octet_length-01-23086) โ”‚   528.28ms โ”‚
   โ”‚ Queries Faster                       โ”‚          3 โ”‚
   โ”‚ Queries Slower                       โ”‚          2 โ”‚
   โ”‚ Queries with No Change               โ”‚         38 โ”‚
   โ”‚ Queries with Failure                 โ”‚          0 โ”‚
   โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜
   ```
   
   </p>
   </details>
   
   <details><summary>Resource Usage</summary>
   
   **clickbench_1 โ€” base (merge-base)**
   | Metric | Value |
   |--------|-------|
   | Wall time | 115.0s |
   | Peak memory | 12.1 GiB |
   | Avg memory | 3.7 GiB |
   | CPU user | 1044.9s |
   | CPU sys | 71.4s |
   | Peak spill | 0 B |
   
   **clickbench_1 โ€” branch**
   | Metric | Value |
   |--------|-------|
   | Wall time | 115.0s |
   | Peak memory | 10.3 GiB |
   | Avg memory | 3.8 GiB |
   | CPU user | 1042.6s |
   | CPU sys | 71.4s |
   | Peak spill | 0 B |
   
   </details>
   
   
   ---
   [File an issue](https://github.com/adriangb/datafusion-benchmarking/issues) against this benchmark runner


-- 
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: github-unsubscribe@datafusion.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org
For additional commands, e-mail: github-help@datafusion.apache.org


Re: [PR] Use `octet_length` for ClickBench Q27/Q28 byte-length semantics [datafusion]

Posted by "kosiew (via GitHub)" <gi...@apache.org>.
kosiew merged PR #23475:
URL: https://github.com/apache/datafusion/pull/23475


-- 
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: github-unsubscribe@datafusion.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org
For additional commands, e-mail: github-help@datafusion.apache.org


Re: [PR] Use `octet_length` for ClickBench Q27/Q28 byte-length semantics [datafusion]

Posted by "kosiew (via GitHub)" <gi...@apache.org>.
kosiew commented on PR #23475:
URL: https://github.com/apache/datafusion/pull/23475#issuecomment-4943549427

   run benchmark clickbench_1 clickbench_partitioned


-- 
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: github-unsubscribe@datafusion.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org
For additional commands, e-mail: github-help@datafusion.apache.org


Re: [PR] Use `octet_length` for ClickBench Q27/Q28 byte-length semantics [datafusion]

Posted by "adriangbot (via GitHub)" <gi...@apache.org>.
adriangbot commented on PR #23475:
URL: https://github.com/apache/datafusion/pull/23475#issuecomment-4943674058

   ๐Ÿค– Benchmark completed (GKE) | [trigger](https://github.com/apache/datafusion/pull/23475#issuecomment-4943549427)
   
   **Instance:** `c4a-highmem-16` (12 vCPU / 65 GiB)
   
   <details><summary>CPU Details (lscpu)</summary>
   
   ```
   Architecture:                            aarch64
   CPU op-mode(s):                          64-bit
   Byte Order:                              Little Endian
   CPU(s):                                  16
   On-line CPU(s) list:                     0-15
   Vendor ID:                               ARM
   Model name:                              Neoverse-V2
   Model:                                   1
   Thread(s) per core:                      1
   Core(s) per cluster:                     16
   Socket(s):                               -
   Cluster(s):                              1
   Stepping:                                r0p1
   BogoMIPS:                                2000.00
   Flags:                                   fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh rng bti
   L1d cache:                               1 MiB (16 instances)
   L1i cache:                               1 MiB (16 instances)
   L2 cache:                                32 MiB (16 instances)
   L3 cache:                                80 MiB (1 instance)
   NUMA node(s):                            1
   NUMA node0 CPU(s):                       0-15
   Vulnerability Gather data sampling:      Not affected
   Vulnerability Indirect target selection: Not affected
   Vulnerability Itlb multihit:             Not affected
   Vulnerability L1tf:                      Not affected
   Vulnerability Mds:                       Not affected
   Vulnerability Meltdown:                  Not affected
   Vulnerability Mmio stale data:           Not affected
   Vulnerability Reg file data sampling:    Not affected
   Vulnerability Retbleed:                  Not affected
   Vulnerability Spec rstack overflow:      Not affected
   Vulnerability Spec store bypass:         Mitigation; Speculative Store Bypass disabled via prctl
   Vulnerability Spectre v1:                Mitigation; __user pointer sanitization
   Vulnerability Spectre v2:                Mitigation; CSV2, BHB
   Vulnerability Srbds:                     Not affected
   Vulnerability Tsa:                       Not affected
   Vulnerability Tsx async abort:           Not affected
   Vulnerability Vmscape:                   Not affected
   ```
   
   </details>
   
   <details><summary>Details</summary>
   <p>
   
   ```
   Comparing HEAD and octet_length-01-23086
   --------------------
   Benchmark clickbench_partitioned.json
   --------------------
   โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”ณโ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”ณโ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”ณโ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”“
   โ”ƒ Query     โ”ƒ                                   HEAD โ”ƒ                  octet_length-01-23086 โ”ƒ        Change โ”ƒ
   โ”กโ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ•‡โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ•‡โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ•‡โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”ฉ
   โ”‚ QQuery 0  โ”‚           1.20 / 3.87 ยฑ5.25 / 14.36 ms โ”‚           1.22 / 3.99 ยฑ5.43 / 14.84 ms โ”‚     no change โ”‚
   โ”‚ QQuery 1  โ”‚         13.26 / 13.54 ยฑ0.16 / 13.68 ms โ”‚         12.72 / 12.97 ยฑ0.15 / 13.20 ms โ”‚     no change โ”‚
   โ”‚ QQuery 2  โ”‚         36.68 / 37.18 ยฑ0.46 / 37.94 ms โ”‚         36.48 / 36.70 ยฑ0.25 / 37.18 ms โ”‚     no change โ”‚
   โ”‚ QQuery 3  โ”‚         31.29 / 31.94 ยฑ0.75 / 33.32 ms โ”‚         30.85 / 31.19 ยฑ0.17 / 31.32 ms โ”‚     no change โ”‚
   โ”‚ QQuery 4  โ”‚      225.95 / 229.11 ยฑ2.48 / 231.83 ms โ”‚     221.78 / 234.15 ยฑ14.05 / 261.00 ms โ”‚     no change โ”‚
   โ”‚ QQuery 5  โ”‚     272.01 / 294.56 ยฑ13.01 / 307.19 ms โ”‚     277.15 / 290.51 ยฑ11.22 / 305.72 ms โ”‚     no change โ”‚
   โ”‚ QQuery 6  โ”‚            1.47 / 1.61 ยฑ0.18 / 1.96 ms โ”‚            1.25 / 1.42 ยฑ0.25 / 1.90 ms โ”‚ +1.13x faster โ”‚
   โ”‚ QQuery 7  โ”‚         15.19 / 16.05 ยฑ0.64 / 16.84 ms โ”‚         13.81 / 14.38 ยฑ0.85 / 16.07 ms โ”‚ +1.12x faster โ”‚
   โ”‚ QQuery 8  โ”‚     331.61 / 345.64 ยฑ14.35 / 372.72 ms โ”‚     333.13 / 350.79 ยฑ10.81 / 366.17 ms โ”‚     no change โ”‚
   โ”‚ QQuery 9  โ”‚      454.47 / 461.71 ยฑ6.23 / 470.61 ms โ”‚      456.15 / 462.23 ยฑ6.22 / 472.22 ms โ”‚     no change โ”‚
   โ”‚ QQuery 10 โ”‚         71.72 / 75.79 ยฑ6.10 / 87.95 ms โ”‚         71.82 / 72.71 ยฑ0.89 / 74.39 ms โ”‚     no change โ”‚
   โ”‚ QQuery 11 โ”‚         84.31 / 84.73 ยฑ0.35 / 85.21 ms โ”‚         83.01 / 84.69 ยฑ2.56 / 89.75 ms โ”‚     no change โ”‚
   โ”‚ QQuery 12 โ”‚      266.45 / 272.80 ยฑ4.16 / 278.90 ms โ”‚      265.29 / 272.72 ยฑ5.86 / 281.33 ms โ”‚     no change โ”‚
   โ”‚ QQuery 13 โ”‚      381.22 / 392.18 ยฑ8.83 / 403.41 ms โ”‚     358.88 / 378.13 ยฑ15.73 / 401.04 ms โ”‚     no change โ”‚
   โ”‚ QQuery 14 โ”‚      282.89 / 291.20 ยฑ6.23 / 301.30 ms โ”‚     282.28 / 292.45 ยฑ13.30 / 318.48 ms โ”‚     no change โ”‚
   โ”‚ QQuery 15 โ”‚      271.92 / 276.10 ยฑ3.97 / 282.40 ms โ”‚     264.91 / 278.51 ยฑ12.69 / 300.12 ms โ”‚     no change โ”‚
   โ”‚ QQuery 16 โ”‚      603.83 / 617.87 ยฑ9.39 / 633.15 ms โ”‚     617.76 / 629.27 ยฑ10.77 / 649.61 ms โ”‚     no change โ”‚
   โ”‚ QQuery 17 โ”‚     698.49 / 713.85 ยฑ11.47 / 733.66 ms โ”‚     623.31 / 661.14 ยฑ34.65 / 714.66 ms โ”‚ +1.08x faster โ”‚
   โ”‚ QQuery 18 โ”‚  1275.31 / 1365.80 ยฑ71.42 / 1451.90 ms โ”‚  1233.47 / 1263.87 ยฑ26.90 / 1302.46 ms โ”‚ +1.08x faster โ”‚
   โ”‚ QQuery 19 โ”‚         28.85 / 29.20 ยฑ0.44 / 30.06 ms โ”‚         28.02 / 28.33 ยฑ0.26 / 28.80 ms โ”‚     no change โ”‚
   โ”‚ QQuery 20 โ”‚     517.92 / 528.09 ยฑ11.71 / 545.40 ms โ”‚      515.76 / 525.12 ยฑ6.48 / 534.23 ms โ”‚     no change โ”‚
   โ”‚ QQuery 21 โ”‚      514.58 / 518.59 ยฑ4.34 / 524.57 ms โ”‚      518.47 / 526.53 ยฑ7.32 / 540.38 ms โ”‚     no change โ”‚
   โ”‚ QQuery 22 โ”‚   985.60 / 1006.86 ยฑ24.24 / 1052.18 ms โ”‚   1052.09 / 1062.85 ยฑ7.14 / 1070.38 ms โ”‚  1.06x slower โ”‚
   โ”‚ QQuery 23 โ”‚  3059.20 / 3128.76 ยฑ46.58 / 3181.98 ms โ”‚  3093.35 / 3158.70 ยฑ59.08 / 3252.16 ms โ”‚     no change โ”‚
   โ”‚ QQuery 24 โ”‚         41.62 / 44.93 ยฑ3.88 / 52.47 ms โ”‚         41.31 / 43.31 ยฑ2.86 / 48.92 ms โ”‚     no change โ”‚
   โ”‚ QQuery 25 โ”‚      112.07 / 116.37 ยฑ4.38 / 124.59 ms โ”‚      113.50 / 117.46 ยฑ3.69 / 123.22 ms โ”‚     no change โ”‚
   โ”‚ QQuery 26 โ”‚         41.92 / 43.79 ยฑ2.10 / 47.80 ms โ”‚         42.41 / 42.95 ยฑ0.31 / 43.34 ms โ”‚     no change โ”‚
   โ”‚ QQuery 27 โ”‚      670.61 / 675.43 ยฑ4.14 / 680.41 ms โ”‚      674.36 / 684.38 ยฑ6.04 / 692.21 ms โ”‚     no change โ”‚
   โ”‚ QQuery 28 โ”‚  3051.67 / 3085.80 ยฑ41.64 / 3167.82 ms โ”‚  3048.94 / 3074.91 ยฑ24.51 / 3116.97 ms โ”‚     no change โ”‚
   โ”‚ QQuery 29 โ”‚         41.46 / 43.10 ยฑ2.26 / 47.36 ms โ”‚         41.49 / 52.85 ยฑ9.22 / 60.62 ms โ”‚  1.23x slower โ”‚
   โ”‚ QQuery 30 โ”‚      301.18 / 314.63 ยฑ7.89 / 324.58 ms โ”‚      305.25 / 311.77 ยฑ4.20 / 316.31 ms โ”‚     no change โ”‚
   โ”‚ QQuery 31 โ”‚     286.54 / 301.59 ยฑ13.47 / 320.48 ms โ”‚      279.45 / 290.70 ยฑ6.56 / 298.35 ms โ”‚     no change โ”‚
   โ”‚ QQuery 32 โ”‚   956.33 / 1086.08 ยฑ97.38 / 1258.85 ms โ”‚    947.49 / 982.59 ยฑ24.85 / 1016.63 ms โ”‚ +1.11x faster โ”‚
   โ”‚ QQuery 33 โ”‚ 1486.63 / 1622.80 ยฑ105.51 / 1753.46 ms โ”‚  1448.35 / 1486.55 ยฑ35.37 / 1546.56 ms โ”‚ +1.09x faster โ”‚
   โ”‚ QQuery 34 โ”‚  1502.44 / 1538.97 ยฑ53.36 / 1644.71 ms โ”‚ 1478.64 / 1632.17 ยฑ120.98 / 1783.99 ms โ”‚  1.06x slower โ”‚
   โ”‚ QQuery 35 โ”‚     281.74 / 319.49 ยฑ33.46 / 358.05 ms โ”‚     349.90 / 371.40 ยฑ28.67 / 427.23 ms โ”‚  1.16x slower โ”‚
   โ”‚ QQuery 36 โ”‚         65.91 / 68.77 ยฑ4.00 / 76.67 ms โ”‚         66.63 / 72.64 ยฑ5.04 / 78.80 ms โ”‚  1.06x slower โ”‚
   โ”‚ QQuery 37 โ”‚         37.10 / 42.03 ยฑ3.09 / 46.17 ms โ”‚         35.87 / 38.65 ยฑ3.09 / 43.05 ms โ”‚ +1.09x faster โ”‚
   โ”‚ QQuery 38 โ”‚         41.39 / 46.93 ยฑ7.47 / 61.69 ms โ”‚         40.15 / 46.52 ยฑ4.26 / 51.49 ms โ”‚     no change โ”‚
   โ”‚ QQuery 39 โ”‚      143.66 / 150.71 ยฑ4.49 / 157.02 ms โ”‚     134.24 / 152.60 ยฑ11.01 / 166.27 ms โ”‚     no change โ”‚
   โ”‚ QQuery 40 โ”‚         14.18 / 16.70 ยฑ2.24 / 19.83 ms โ”‚         14.29 / 14.46 ยฑ0.27 / 14.99 ms โ”‚ +1.16x faster โ”‚
   โ”‚ QQuery 41 โ”‚         13.98 / 14.36 ยฑ0.27 / 14.79 ms โ”‚         14.08 / 18.07 ยฑ5.77 / 29.05 ms โ”‚  1.26x slower โ”‚
   โ”‚ QQuery 42 โ”‚         13.53 / 16.55 ยฑ3.89 / 23.28 ms โ”‚         13.10 / 15.10 ยฑ3.64 / 22.37 ms โ”‚ +1.10x faster โ”‚
   โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜
   โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”ณโ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”“
   โ”ƒ Benchmark Summary                    โ”ƒ            โ”ƒ
   โ”กโ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ•‡โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”ฉ
   โ”‚ Total Time (HEAD)                    โ”‚ 20286.04ms โ”‚
   โ”‚ Total Time (octet_length-01-23086)   โ”‚ 20122.42ms โ”‚
   โ”‚ Average Time (HEAD)                  โ”‚   471.77ms โ”‚
   โ”‚ Average Time (octet_length-01-23086) โ”‚   467.96ms โ”‚
   โ”‚ Queries Faster                       โ”‚          9 โ”‚
   โ”‚ Queries Slower                       โ”‚          6 โ”‚
   โ”‚ Queries with No Change               โ”‚         28 โ”‚
   โ”‚ Queries with Failure                 โ”‚          0 โ”‚
   โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜
   ```
   
   </p>
   </details>
   
   <details><summary>Resource Usage</summary>
   
   **clickbench_partitioned โ€” base (merge-base)**
   | Metric | Value |
   |--------|-------|
   | Wall time | 105.0s |
   | Peak memory | 11.4 GiB |
   | Avg memory | 4.4 GiB |
   | CPU user | 1037.9s |
   | CPU sys | 73.2s |
   | Peak spill | 0 B |
   
   **clickbench_partitioned โ€” branch**
   | Metric | Value |
   |--------|-------|
   | Wall time | 105.0s |
   | Peak memory | 12.3 GiB |
   | Avg memory | 4.4 GiB |
   | CPU user | 1031.8s |
   | CPU sys | 73.2s |
   | Peak spill | 0 B |
   
   </details>
   
   
   ---
   [File an issue](https://github.com/adriangb/datafusion-benchmarking/issues) against this benchmark runner


-- 
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: github-unsubscribe@datafusion.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org
For additional commands, e-mail: github-help@datafusion.apache.org


Re: [PR] Use `octet_length` for ClickBench Q27/Q28 byte-length semantics [datafusion]

Posted by "kosiew (via GitHub)" <gi...@apache.org>.
kosiew commented on PR #23475:
URL: https://github.com/apache/datafusion/pull/23475#issuecomment-4943264419

   show benchmark queue


-- 
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: github-unsubscribe@datafusion.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org
For additional commands, e-mail: github-help@datafusion.apache.org


Re: [PR] Use `octet_length` for ClickBench Q27/Q28 byte-length semantics [datafusion]

Posted by "adriangbot (via GitHub)" <gi...@apache.org>.
adriangbot commented on PR #23475:
URL: https://github.com/apache/datafusion/pull/23475#issuecomment-4943577998

   ๐Ÿค– Benchmark running (GKE) | [trigger](https://github.com/apache/datafusion/pull/23475#issuecomment-4943549427)
   **Instance:** `c4a-highmem-16` (12 vCPU / 65 GiB) | `Linux bench-c4943549427-976-tlsj8 6.12.85+ #1 SMP Mon May 11 08:17:35 UTC 2026 aarch64 GNU/Linux`
   <details><summary>CPU Details (lscpu)</summary>
   
   ```
   Architecture:                            aarch64
   CPU op-mode(s):                          64-bit
   Byte Order:                              Little Endian
   CPU(s):                                  16
   On-line CPU(s) list:                     0-15
   Vendor ID:                               ARM
   Model name:                              Neoverse-V2
   Model:                                   1
   Thread(s) per core:                      1
   Core(s) per cluster:                     16
   Socket(s):                               -
   Cluster(s):                              1
   Stepping:                                r0p1
   BogoMIPS:                                2000.00
   Flags:                                   fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh rng bti
   L1d cache:                               1 MiB (16 instances)
   L1i cache:                               1 MiB (16 instances)
   L2 cache:                                32 MiB (16 instances)
   L3 cache:                                80 MiB (1 instance)
   NUMA node(s):                            1
   NUMA node0 CPU(s):                       0-15
   Vulnerability Gather data sampling:      Not affected
   Vulnerability Indirect target selection: Not affected
   Vulnerability Itlb multihit:             Not affected
   Vulnerability L1tf:                      Not affected
   Vulnerability Mds:                       Not affected
   Vulnerability Meltdown:                  Not affected
   Vulnerability Mmio stale data:           Not affected
   Vulnerability Reg file data sampling:    Not affected
   Vulnerability Retbleed:                  Not affected
   Vulnerability Spec rstack overflow:      Not affected
   Vulnerability Spec store bypass:         Mitigation; Speculative Store Bypass disabled via prctl
   Vulnerability Spectre v1:                Mitigation; __user pointer sanitization
   Vulnerability Spectre v2:                Mitigation; CSV2, BHB
   Vulnerability Srbds:                     Not affected
   Vulnerability Tsa:                       Not affected
   Vulnerability Tsx async abort:           Not affected
   Vulnerability Vmscape:                   Not affected
   ```
   
   </details>
   
   Comparing octet_length-01-23086 (08d730a2c19d69120885f41c220d4350eceb48ed) to 3e058f0 (merge-base) [diff](https://github.com/apache/datafusion/compare/3e058f09c91a18c8f36b71a656231603b33888c2..08d730a2c19d69120885f41c220d4350eceb48ed) using: clickbench_partitioned
   Results will be posted here when complete
   
   ---
   [File an issue](https://github.com/adriangb/datafusion-benchmarking/issues) against this benchmark runner


-- 
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: github-unsubscribe@datafusion.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org
For additional commands, e-mail: github-help@datafusion.apache.org


Re: [PR] Use `octet_length` for ClickBench Q27/Q28 byte-length semantics [datafusion]

Posted by "adriangbot (via GitHub)" <gi...@apache.org>.
adriangbot commented on PR #23475:
URL: https://github.com/apache/datafusion/pull/23475#issuecomment-4943303636

   ๐Ÿค– Benchmark running (GKE) | [trigger](https://github.com/apache/datafusion/pull/23475#issuecomment-4943279827)
   **Instance:** `c4a-highmem-16` (12 vCPU / 65 GiB) | `Linux bench-c4943279827-973-25tz8 6.12.85+ #1 SMP Mon May 11 08:17:35 UTC 2026 aarch64 GNU/Linux`
   <details><summary>CPU Details (lscpu)</summary>
   
   ```
   Architecture:                            aarch64
   CPU op-mode(s):                          64-bit
   Byte Order:                              Little Endian
   CPU(s):                                  16
   On-line CPU(s) list:                     0-15
   Vendor ID:                               ARM
   Model name:                              Neoverse-V2
   Model:                                   1
   Thread(s) per core:                      1
   Core(s) per cluster:                     16
   Socket(s):                               -
   Cluster(s):                              1
   Stepping:                                r0p1
   BogoMIPS:                                2000.00
   Flags:                                   fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh rng bti
   L1d cache:                               1 MiB (16 instances)
   L1i cache:                               1 MiB (16 instances)
   L2 cache:                                32 MiB (16 instances)
   L3 cache:                                80 MiB (1 instance)
   NUMA node(s):                            1
   NUMA node0 CPU(s):                       0-15
   Vulnerability Gather data sampling:      Not affected
   Vulnerability Indirect target selection: Not affected
   Vulnerability Itlb multihit:             Not affected
   Vulnerability L1tf:                      Not affected
   Vulnerability Mds:                       Not affected
   Vulnerability Meltdown:                  Not affected
   Vulnerability Mmio stale data:           Not affected
   Vulnerability Reg file data sampling:    Not affected
   Vulnerability Retbleed:                  Not affected
   Vulnerability Spec rstack overflow:      Not affected
   Vulnerability Spec store bypass:         Mitigation; Speculative Store Bypass disabled via prctl
   Vulnerability Spectre v1:                Mitigation; __user pointer sanitization
   Vulnerability Spectre v2:                Mitigation; CSV2, BHB
   Vulnerability Srbds:                     Not affected
   Vulnerability Tsa:                       Not affected
   Vulnerability Tsx async abort:           Not affected
   Vulnerability Vmscape:                   Not affected
   ```
   
   </details>
   
   Comparing octet_length-01-23086 (08d730a2c19d69120885f41c220d4350eceb48ed) to 3e058f0 (merge-base) [diff](https://github.com/apache/datafusion/compare/3e058f09c91a18c8f36b71a656231603b33888c2..08d730a2c19d69120885f41c220d4350eceb48ed) using: clickbench_partitioned
   Results will be posted here when complete
   
   ---
   [File an issue](https://github.com/adriangb/datafusion-benchmarking/issues) against this benchmark runner


-- 
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: github-unsubscribe@datafusion.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org
For additional commands, e-mail: github-help@datafusion.apache.org


Re: [PR] Use `octet_length` for ClickBench Q27/Q28 byte-length semantics [datafusion]

Posted by "adriangbot (via GitHub)" <gi...@apache.org>.
adriangbot commented on PR #23475:
URL: https://github.com/apache/datafusion/pull/23475#issuecomment-4943288021

   ๐Ÿค– Benchmark running (GKE) | [trigger](https://github.com/apache/datafusion/pull/23475#issuecomment-4943253066)
   **Instance:** `c4a-highmem-16` (12 vCPU / 65 GiB) | `Linux bench-c4943253066-971-mkmpl 6.12.85+ #1 SMP Mon May 11 08:17:35 UTC 2026 aarch64 GNU/Linux`
   <details><summary>CPU Details (lscpu)</summary>
   
   ```
   Architecture:                            aarch64
   CPU op-mode(s):                          64-bit
   Byte Order:                              Little Endian
   CPU(s):                                  16
   On-line CPU(s) list:                     0-15
   Vendor ID:                               ARM
   Model name:                              Neoverse-V2
   Model:                                   1
   Thread(s) per core:                      1
   Core(s) per cluster:                     16
   Socket(s):                               -
   Cluster(s):                              1
   Stepping:                                r0p1
   BogoMIPS:                                2000.00
   Flags:                                   fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh rng bti
   L1d cache:                               1 MiB (16 instances)
   L1i cache:                               1 MiB (16 instances)
   L2 cache:                                32 MiB (16 instances)
   L3 cache:                                80 MiB (1 instance)
   NUMA node(s):                            1
   NUMA node0 CPU(s):                       0-15
   Vulnerability Gather data sampling:      Not affected
   Vulnerability Indirect target selection: Not affected
   Vulnerability Itlb multihit:             Not affected
   Vulnerability L1tf:                      Not affected
   Vulnerability Mds:                       Not affected
   Vulnerability Meltdown:                  Not affected
   Vulnerability Mmio stale data:           Not affected
   Vulnerability Reg file data sampling:    Not affected
   Vulnerability Retbleed:                  Not affected
   Vulnerability Spec rstack overflow:      Not affected
   Vulnerability Spec store bypass:         Mitigation; Speculative Store Bypass disabled via prctl
   Vulnerability Spectre v1:                Mitigation; __user pointer sanitization
   Vulnerability Spectre v2:                Mitigation; CSV2, BHB
   Vulnerability Srbds:                     Not affected
   Vulnerability Tsa:                       Not affected
   Vulnerability Tsx async abort:           Not affected
   Vulnerability Vmscape:                   Not affected
   ```
   
   </details>
   
   Comparing octet_length-01-23086 (08d730a2c19d69120885f41c220d4350eceb48ed) to 3e058f0 (merge-base) [diff](https://github.com/apache/datafusion/compare/3e058f09c91a18c8f36b71a656231603b33888c2..08d730a2c19d69120885f41c220d4350eceb48ed) using: clickbench_1
   Results will be posted here when complete
   
   ---
   [File an issue](https://github.com/adriangb/datafusion-benchmarking/issues) against this benchmark runner


-- 
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: github-unsubscribe@datafusion.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org
For additional commands, e-mail: github-help@datafusion.apache.org


Re: [PR] Use `octet_length` for ClickBench Q27/Q28 byte-length semantics [datafusion]

Posted by "kosiew (via GitHub)" <gi...@apache.org>.
kosiew commented on PR #23475:
URL: https://github.com/apache/datafusion/pull/23475#issuecomment-4943545618

   clickbench_partitioned:
   ```
   โ”‚ QQuery 27 โ”‚     674.88 / 682.22 ยฑ7.51 / 696.26 ms โ”‚     682.77 / 687.47 ยฑ4.00 / 694.69 ms โ”‚     no change โ”‚
   โ”‚ QQuery 28 โ”‚ 3090.69 / 3139.62 ยฑ35.35 / 3186.48 ms โ”‚ 3124.35 / 3153.87 ยฑ28.94 / 3201.66 ms โ”‚     no change โ”‚
   ```
   
   clickbench_1
   ```
   โ”‚ QQuery 27 โ”‚     756.29 / 765.65 ยฑ8.62 / 779.83 ms โ”‚    764.77 / 780.35 ยฑ14.24 / 801.93 ms โ”‚     no change โ”‚
   โ”‚ QQuery 28 โ”‚ 3496.01 / 3518.59 ยฑ16.94 / 3546.22 ms โ”‚ 3480.49 / 3523.93 ยฑ25.20 / 3557.33 ms โ”‚     no change โ”‚
   ```


-- 
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: github-unsubscribe@datafusion.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org
For additional commands, e-mail: github-help@datafusion.apache.org


Re: [PR] Use `octet_length` for ClickBench Q27/Q28 byte-length semantics [datafusion]

Posted by "adriangbot (via GitHub)" <gi...@apache.org>.
adriangbot commented on PR #23475:
URL: https://github.com/apache/datafusion/pull/23475#issuecomment-4943264765

   Hi @kosiew, you asked to view the benchmark queue (https://github.com/apache/datafusion/pull/23475#issuecomment-4943264419).
   
   | Comment | Repo | PR | User | Benchmarks | Status |
   | --- | --- | --- | --- | --- | --- |
   | [#4943253066](https://github.com/apache/datafusion/pull/23475#issuecomment-4943253066) | apache/datafusion | #23475 | kosiew | ["clickbench_1"] | running |
   | [#4943253066](https://github.com/apache/datafusion/pull/23475#issuecomment-4943253066) | apache/datafusion | #23475 | kosiew | ["27"] | running |
   
   ---
   [File an issue](https://github.com/adriangb/datafusion-benchmarking/issues) against this benchmark runner


-- 
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: github-unsubscribe@datafusion.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org
For additional commands, e-mail: github-help@datafusion.apache.org


Re: [PR] Use `octet_length` for ClickBench Q27/Q28 byte-length semantics [datafusion]

Posted by "kosiew (via GitHub)" <gi...@apache.org>.
kosiew commented on PR #23475:
URL: https://github.com/apache/datafusion/pull/23475#issuecomment-4943253066

   run benchmark clickbench_1 27


-- 
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: github-unsubscribe@datafusion.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org
For additional commands, e-mail: github-help@datafusion.apache.org


Re: [PR] Use `octet_length` for ClickBench Q27/Q28 byte-length semantics [datafusion]

Posted by "adriangbot (via GitHub)" <gi...@apache.org>.
adriangbot commented on PR #23475:
URL: https://github.com/apache/datafusion/pull/23475#issuecomment-4943493742

   Hi @kosiew, you asked to view the benchmark queue (https://github.com/apache/datafusion/pull/23475#issuecomment-4943493443).
   
   | Comment | Repo | PR | User | Benchmarks | Status |
   | --- | --- | --- | --- | --- | --- |
   | [#4943253066](https://github.com/apache/datafusion/pull/23475#issuecomment-4943253066) | apache/datafusion | #23475 | kosiew | ["clickbench_1"] | running |
   | [#4943279827](https://github.com/apache/datafusion/pull/23475#issuecomment-4943279827) | apache/datafusion | #23475 | kosiew | ["clickbench_partitioned"] | running |
   | [#4943332517](https://github.com/apache/datafusion/pull/23420#issuecomment-4943332517) | apache/datafusion | #23420 | zhuqi-lucas | ["clickbench_partitioned"] | running |
   
   ---
   [File an issue](https://github.com/adriangb/datafusion-benchmarking/issues) against this benchmark runner


-- 
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: github-unsubscribe@datafusion.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org
For additional commands, e-mail: github-help@datafusion.apache.org


Re: [PR] Use `octet_length` for ClickBench Q27/Q28 byte-length semantics [datafusion]

Posted by "kosiew (via GitHub)" <gi...@apache.org>.
kosiew commented on PR #23475:
URL: https://github.com/apache/datafusion/pull/23475#issuecomment-4966935673

   @alamb 
   
   > before we merge this PR, I think we should make a PR to update ClickBench itself to ensure our benchmarks in this repo match the queries in ClickBench itself.
   
   https://github.com/ClickHouse/ClickBench/pull/985


-- 
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: github-unsubscribe@datafusion.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org
For additional commands, e-mail: github-help@datafusion.apache.org