pan3793 commented on code in PR #50057:
URL: https://github.com/apache/spark/pull/50057#discussion_r1967578779
##########
core/benchmarks/ZStandardBenchmark-jdk21-results.txt:
##########
@@ -2,48 +2,48 @@
Benchmark ZStandardCompressionCodec
================================================================================================
-OpenJDK 64-Bit Server VM 21.0.6+7-LTS on Linux 6.8.0-1020-azure
+OpenJDK 64-Bit Server VM 21.0.6+7-LTS on Linux 6.8.0-1021-azure
AMD EPYC 7763 64-Core Processor
Benchmark ZStandardCompressionCodec: Best Time(ms) Avg
Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative
--------------------------------------------------------------------------------------------------------------------------------------
-Compression 10000 times at level 1 without buffer pool 656
668 12 0.0 65591.6 1.0X
-Compression 10000 times at level 2 without buffer pool 709
711 2 0.0 70934.6 0.9X
-Compression 10000 times at level 3 without buffer pool 814
818 5 0.0 81370.9 0.8X
-Compression 10000 times at level 1 with buffer pool 601
603 2 0.0 60100.1 1.1X
-Compression 10000 times at level 2 with buffer pool 634
636 2 0.0 63449.9 1.0X
-Compression 10000 times at level 3 with buffer pool 748
753 5 0.0 74789.7 0.9X
+Compression 10000 times at level 1 without buffer pool 650
666 11 0.0 65044.6 1.0X
+Compression 10000 times at level 2 without buffer pool 701
703 2 0.0 70071.2 0.9X
+Compression 10000 times at level 3 without buffer pool 804
807 2 0.0 80430.6 0.8X
+Compression 10000 times at level 1 with buffer pool 598
599 1 0.0 59810.5 1.1X
+Compression 10000 times at level 2 with buffer pool 631
640 17 0.0 63096.7 1.0X
+Compression 10000 times at level 3 with buffer pool 751
753 4 0.0 75051.1 0.9X
-OpenJDK 64-Bit Server VM 21.0.6+7-LTS on Linux 6.8.0-1020-azure
+OpenJDK 64-Bit Server VM 21.0.6+7-LTS on Linux 6.8.0-1021-azure
AMD EPYC 7763 64-Core Processor
Benchmark ZStandardCompressionCodec: Best Time(ms)
Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative
------------------------------------------------------------------------------------------------------------------------------------------
-Decompression 10000 times from level 1 without buffer pool 817
818 1 0.0 81723.2 1.0X
-Decompression 10000 times from level 2 without buffer pool 817
818 1 0.0 81729.4 1.0X
-Decompression 10000 times from level 3 without buffer pool 817
818 1 0.0 81719.7 1.0X
-Decompression 10000 times from level 1 with buffer pool 749
757 14 0.0 74864.9 1.1X
-Decompression 10000 times from level 2 with buffer pool 748
749 1 0.0 74789.1 1.1X
-Decompression 10000 times from level 3 with buffer pool 748
749 1 0.0 74811.6 1.1X
+Decompression 10000 times from level 1 without buffer pool 823
831 14 0.0 82254.2 1.0X
+Decompression 10000 times from level 2 without buffer pool 824
827 5 0.0 82359.1 1.0X
+Decompression 10000 times from level 3 without buffer pool 819
821 2 0.0 81925.1 1.0X
+Decompression 10000 times from level 1 with buffer pool 753
755 3 0.0 75284.1 1.1X
+Decompression 10000 times from level 2 with buffer pool 753
755 1 0.0 75344.7 1.1X
+Decompression 10000 times from level 3 with buffer pool 753
754 1 0.0 75263.0 1.1X
-OpenJDK 64-Bit Server VM 21.0.6+7-LTS on Linux 6.8.0-1020-azure
+OpenJDK 64-Bit Server VM 21.0.6+7-LTS on Linux 6.8.0-1021-azure
AMD EPYC 7763 64-Core Processor
Parallel Compression at level 3: Best Time(ms) Avg Time(ms)
Stdev(ms) Rate(M/s) Per Row(ns) Relative
------------------------------------------------------------------------------------------------------------------------
-Parallel Compression with 0 workers 57 59
1 0.0 447789.9 1.0X
-Parallel Compression with 1 workers 42 44
3 0.0 326565.8 1.4X
-Parallel Compression with 2 workers 39 41
1 0.0 303072.5 1.5X
-Parallel Compression with 4 workers 38 40
1 0.0 295414.4 1.5X
-Parallel Compression with 8 workers 40 42
1 0.0 315081.4 1.4X
-Parallel Compression with 16 workers 44 46
1 0.0 344861.3 1.3X
+Parallel Compression with 0 workers 76 77
1 0.0 592387.6 1.0X
+Parallel Compression with 1 workers 54 58
2 0.0 423673.8 1.4X
+Parallel Compression with 2 workers 46 48
2 0.0 359543.8 1.6X
+Parallel Compression with 4 workers 41 43
1 0.0 319843.4 1.9X
+Parallel Compression with 8 workers 44 46
1 0.0 342863.4 1.7X
+Parallel Compression with 16 workers 46 49
1 0.0 360070.9 1.6X
-OpenJDK 64-Bit Server VM 21.0.6+7-LTS on Linux 6.8.0-1020-azure
+OpenJDK 64-Bit Server VM 21.0.6+7-LTS on Linux 6.8.0-1021-azure
AMD EPYC 7763 64-Core Processor
Parallel Compression at level 9: Best Time(ms) Avg Time(ms)
Stdev(ms) Rate(M/s) Per Row(ns) Relative
------------------------------------------------------------------------------------------------------------------------
-Parallel Compression with 0 workers 158 160
1 0.0 1236127.4 1.0X
-Parallel Compression with 1 workers 189 191
2 0.0 1477461.1 0.8X
-Parallel Compression with 2 workers 113 118
9 0.0 880537.6 1.4X
-Parallel Compression with 4 workers 107 110
2 0.0 837459.4 1.5X
-Parallel Compression with 8 workers 114 115
2 0.0 888143.3 1.4X
-Parallel Compression with 16 workers 113 116
2 0.0 880682.5 1.4X
+Parallel Compression with 0 workers 261 263
2 0.0 2040351.0 1.0X
+Parallel Compression with 1 workers 283 285
2 0.0 2213386.4 0.9X
+Parallel Compression with 2 workers 158 167
5 0.0 1236532.4 1.7X
+Parallel Compression with 4 workers 148 152
3 0.0 1153928.1 1.8X
+Parallel Compression with 8 workers 155 159
4 0.0 1212956.7 1.7X
+Parallel Compression with 16 workers 155 157
2 0.0 1209082.3 1.7X
Review Comment:
I have opened an issue https://github.com/luben/zstd-jni/issues/350
--
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: reviews-unsubscr...@spark.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
