Re: [systemd-devel] [PATCH 2/2] compress: add benchmark-style test
On Sat, 2014-07-05 at 20:56 +0200, Zbigniew Jędrzejewski-Szmek wrote: This is useful to test the behaviour of the compressor for various buffer sizes. Time is limited to a minute per compression, since otherwise, when LZ4 takes more than a second which is necessary to reduce the noise, XZ takes more than 10 minutes. % build/test-compress-benchmark (without time limit) XZ: compressed decompressed 2535300963 bytes in 794.57s (3.04MiB/s), mean compresion 99.95%, skipped 3570 bytes LZ4: compressed decompressed 2535303543 bytes in 1.56s (1550.07MiB/s), mean compresion 99.60%, skipped 990 bytes Like your earlier comparison, this compares the wrong thing. If compression speed matters more than best compression ratio, you shouldn't use the default settings for xz. If you want to compare with LZ4, this benchmark should at least compare the equivalent of xz -0. ___ systemd-devel mailing list systemd-devel@lists.freedesktop.org http://lists.freedesktop.org/mailman/listinfo/systemd-devel
Re: [systemd-devel] [PATCH 2/2] compress: add benchmark-style test
On Mon, Jul 07, 2014 at 09:35:06PM +0300, Uoti Urpala wrote: On Sat, 2014-07-05 at 20:56 +0200, Zbigniew Jędrzejewski-Szmek wrote: This is useful to test the behaviour of the compressor for various buffer sizes. Time is limited to a minute per compression, since otherwise, when LZ4 takes more than a second which is necessary to reduce the noise, XZ takes more than 10 minutes. % build/test-compress-benchmark (without time limit) XZ: compressed decompressed 2535300963 bytes in 794.57s (3.04MiB/s), mean compresion 99.95%, skipped 3570 bytes LZ4: compressed decompressed 2535303543 bytes in 1.56s (1550.07MiB/s), mean compresion 99.60%, skipped 990 bytes Like your earlier comparison, this compares the wrong thing. If compression speed matters more than best compression ratio, you shouldn't use the default settings for xz. If you want to compare with LZ4, this benchmark should at least compare the equivalent of xz -0. The comparison should be done for whatever setting is used in journald and/or coredump. Since they both use the default preset now, that is what I'm comparing. It *is* likely that it should be changed, but that should happen in a separate patch anyway. Zbyszek ___ systemd-devel mailing list systemd-devel@lists.freedesktop.org http://lists.freedesktop.org/mailman/listinfo/systemd-devel
Re: [systemd-devel] [PATCH 2/2] compress: add benchmark-style test
On Mon, Jul 7, 2014 at 9:40 PM, Zbigniew Jędrzejewski-Szmek zbys...@in.waw.pl wrote: On Mon, Jul 07, 2014 at 09:35:06PM +0300, Uoti Urpala wrote: On Sat, 2014-07-05 at 20:56 +0200, Zbigniew Jędrzejewski-Szmek wrote: This is useful to test the behaviour of the compressor for various buffer sizes. Time is limited to a minute per compression, since otherwise, when LZ4 takes more than a second which is necessary to reduce the noise, XZ takes more than 10 minutes. % build/test-compress-benchmark (without time limit) XZ: compressed decompressed 2535300963 bytes in 794.57s (3.04MiB/s), mean compresion 99.95%, skipped 3570 bytes LZ4: compressed decompressed 2535303543 bytes in 1.56s (1550.07MiB/s), mean compresion 99.60%, skipped 990 bytes Like your earlier comparison, this compares the wrong thing. If compression speed matters more than best compression ratio, you shouldn't use the default settings for xz. If you want to compare with LZ4, this benchmark should at least compare the equivalent of xz -0. The comparison should be done for whatever setting is used in journald and/or coredump. No, The current defaults are irrelevant. The comparison should be done with values that indicate that introducing a new compression algorithm is needed. If xz *can* be instructed to reach acceptable results, we would better stick with it. Kay ___ systemd-devel mailing list systemd-devel@lists.freedesktop.org http://lists.freedesktop.org/mailman/listinfo/systemd-devel
Re: [systemd-devel] [PATCH 2/2] compress: add benchmark-style test
On Mon, Jul 07, 2014 at 09:47:15PM +0200, Kay Sievers wrote: On Mon, Jul 7, 2014 at 9:40 PM, Zbigniew Jędrzejewski-Szmek zbys...@in.waw.pl wrote: On Mon, Jul 07, 2014 at 09:35:06PM +0300, Uoti Urpala wrote: On Sat, 2014-07-05 at 20:56 +0200, Zbigniew Jędrzejewski-Szmek wrote: This is useful to test the behaviour of the compressor for various buffer sizes. Time is limited to a minute per compression, since otherwise, when LZ4 takes more than a second which is necessary to reduce the noise, XZ takes more than 10 minutes. % build/test-compress-benchmark (without time limit) XZ: compressed decompressed 2535300963 bytes in 794.57s (3.04MiB/s), mean compresion 99.95%, skipped 3570 bytes LZ4: compressed decompressed 2535303543 bytes in 1.56s (1550.07MiB/s), mean compresion 99.60%, skipped 990 bytes Like your earlier comparison, this compares the wrong thing. If compression speed matters more than best compression ratio, you shouldn't use the default settings for xz. If you want to compare with LZ4, this benchmark should at least compare the equivalent of xz -0. The comparison should be done for whatever setting is used in journald and/or coredump. No, The current defaults are irrelevant. The comparison should be done with values that indicate that introducing a new compression algorithm is needed. If xz *can* be instructed to reach acceptable results, we would better stick with it. With preset=default (6): XZ: compressed decompressed 220536103 bytes in 60.03s (3.50MiB/s), ... With 0: XZ: compressed decompressed 2535300963 bytes in 33.01s (73.25MiB/s), ... LZ4: compressed decompressed 2535303543 bytes in 1.31s (1838.75MiB/s), ... Zbyszek ___ systemd-devel mailing list systemd-devel@lists.freedesktop.org http://lists.freedesktop.org/mailman/listinfo/systemd-devel
Re: [systemd-devel] [PATCH 2/2] compress: add benchmark-style test
On Mon, Jul 7, 2014 at 10:33 PM, Zbigniew Jędrzejewski-Szmek zbys...@in.waw.pl wrote: On Mon, Jul 07, 2014 at 09:47:15PM +0200, Kay Sievers wrote: On Mon, Jul 7, 2014 at 9:40 PM, Zbigniew Jędrzejewski-Szmek zbys...@in.waw.pl wrote: On Mon, Jul 07, 2014 at 09:35:06PM +0300, Uoti Urpala wrote: On Sat, 2014-07-05 at 20:56 +0200, Zbigniew Jędrzejewski-Szmek wrote: This is useful to test the behaviour of the compressor for various buffer sizes. Time is limited to a minute per compression, since otherwise, when LZ4 takes more than a second which is necessary to reduce the noise, XZ takes more than 10 minutes. % build/test-compress-benchmark (without time limit) XZ: compressed decompressed 2535300963 bytes in 794.57s (3.04MiB/s), mean compresion 99.95%, skipped 3570 bytes LZ4: compressed decompressed 2535303543 bytes in 1.56s (1550.07MiB/s), mean compresion 99.60%, skipped 990 bytes Like your earlier comparison, this compares the wrong thing. If compression speed matters more than best compression ratio, you shouldn't use the default settings for xz. If you want to compare with LZ4, this benchmark should at least compare the equivalent of xz -0. The comparison should be done for whatever setting is used in journald and/or coredump. No, The current defaults are irrelevant. The comparison should be done with values that indicate that introducing a new compression algorithm is needed. If xz *can* be instructed to reach acceptable results, we would better stick with it. With preset=default (6): XZ: compressed decompressed 220536103 bytes in 60.03s (3.50MiB/s), ... With 0: XZ: compressed decompressed 2535300963 bytes in 33.01s (73.25MiB/s), ... LZ4: compressed decompressed 2535303543 bytes in 1.31s (1838.75MiB/s), ... Interesting numbers. Thanks for providing them. Kay ___ systemd-devel mailing list systemd-devel@lists.freedesktop.org http://lists.freedesktop.org/mailman/listinfo/systemd-devel
