* Valid Benchmark Value & Methods @ 2015-05-07 11:24 Dewangga 2015-05-07 11:48 ` Martin Steigerwald 2015-05-07 11:49 ` Martin Steigerwald 0 siblings, 2 replies; 7+ messages in thread From: Dewangga @ 2015-05-07 11:24 UTC (permalink / raw) To: xfs@oss.sgi.com -----BEGIN PGP SIGNED MESSAGE----- Hash: SHA1 Hello! I'm new on XFS and curious about any tune/tweak regarding XFS filesystem on any raid array, non-raid, ssd or non-ssd. But, is there any valid value to determine about the performance? At least valid benchmark result (eg. using fio with some parameters, or any method). Then, about bsize, sectsz, etc, is there any wiki/guidelines how to set them on a right way? Regards, -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.17 (MingW32) iQEcBAEBAgAGBQJVS0tWAAoJEF1+odKB6YIxjcUIAJeTF8Bg810/lwqo8RCiuyLI UyAJJIkzSIdWk6JdGiPfYqWptCXJs7jPc66yKTJNVVdPQ0z0H5mBWDHb2qCe0/lO lSsGhBinyVaGzssVWYJjSlpee0h1nievBdCOGiqMU/W5uz/ZGR1WkK9gnu344BKb 3Xpt30oG3l+qTrswfqGDbyeU9X4ruUfi4bKYp+pzjELpxpVggDud+hjTsF44z422 +cpoeiHP6SsI/Nj2RUcXY+lP9VwemjbeG6a3rWRvQU4uwJOioy/QgnAnajDmjFaV GmmGYL5n35xy2IxE2b2MqWDcA+vvTYMf8P9CEEHoC2Rg+Iv9zx1HghBvjGiCGRM= =1mdR -----END PGP SIGNATURE----- _______________________________________________ xfs mailing list xfs@oss.sgi.com http://oss.sgi.com/mailman/listinfo/xfs ^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: Valid Benchmark Value & Methods 2015-05-07 11:24 Valid Benchmark Value & Methods Dewangga @ 2015-05-07 11:48 ` Martin Steigerwald 2015-05-07 11:49 ` Martin Steigerwald 1 sibling, 0 replies; 7+ messages in thread From: Martin Steigerwald @ 2015-05-07 11:48 UTC (permalink / raw) To: xfs; +Cc: Dewangga Am Donnerstag, 7. Mai 2015, 18:24:09 schrieb Dewangga: > Hello! > > I'm new on XFS and curious about any tune/tweak regarding XFS > filesystem on any raid array, non-raid, ssd or non-ssd. But, is there > any valid value to determine about the performance? At least valid > benchmark result (eg. using fio with some parameters, or any method). > > Then, about bsize, sectsz, etc, is there any wiki/guidelines how to > set them on a right way? Read and understand: http://xfs.org/index.php/XFS_FAQ#Q:_I_want_to_tune_my_XFS_filesystems_for_.3Csomething.3E then, if you want any concrete recommendation ask about your intended setup. Thanks, -- Martin 'Helios' Steigerwald - http://www.Lichtvoll.de GPG: 03B0 0D6C 0040 0710 4AFA B82F 991B EAAC A599 84C7 _______________________________________________ xfs mailing list xfs@oss.sgi.com http://oss.sgi.com/mailman/listinfo/xfs ^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: Valid Benchmark Value & Methods 2015-05-07 11:24 Valid Benchmark Value & Methods Dewangga 2015-05-07 11:48 ` Martin Steigerwald @ 2015-05-07 11:49 ` Martin Steigerwald 2015-05-07 12:16 ` Dewangga 1 sibling, 1 reply; 7+ messages in thread From: Martin Steigerwald @ 2015-05-07 11:49 UTC (permalink / raw) To: xfs; +Cc: Dewangga Am Donnerstag, 7. Mai 2015, 18:24:09 schrieb Dewangga: > Hello! > > I'm new on XFS and curious about any tune/tweak regarding XFS > filesystem on any raid array, non-raid, ssd or non-ssd. But, is there > any valid value to determine about the performance? At least valid > benchmark result (eg. using fio with some parameters, or any method). > > Then, about bsize, sectsz, etc, is there any wiki/guidelines how to > set them on a right way? Ok, one additional thing: Use recent kernel and userspace utilities. Cause defaults are updated sometimes and with recent tools you get best out of box experience. -- Martin 'Helios' Steigerwald - http://www.Lichtvoll.de GPG: 03B0 0D6C 0040 0710 4AFA B82F 991B EAAC A599 84C7 _______________________________________________ xfs mailing list xfs@oss.sgi.com http://oss.sgi.com/mailman/listinfo/xfs ^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: Valid Benchmark Value & Methods 2015-05-07 11:49 ` Martin Steigerwald @ 2015-05-07 12:16 ` Dewangga 2015-05-07 13:54 ` Martin Steigerwald 2015-05-07 22:55 ` Dave Chinner 0 siblings, 2 replies; 7+ messages in thread From: Dewangga @ 2015-05-07 12:16 UTC (permalink / raw) To: Martin Steigerwald, xfs -----BEGIN PGP SIGNED MESSAGE----- Hash: SHA1 Hello Martin, Thanks for your reply, yes I've read that link, but another question, is noatime,nodiratime,etc still valid for performance tuning guidance? Even the default mount options only "rw,inode64,seclabel,attr2". Is it still increase the performance if the additional mount options added? On 5/7/2015 18:49, Martin Steigerwald wrote: > Am Donnerstag, 7. Mai 2015, 18:24:09 schrieb Dewangga: >> Hello! >> >> I'm new on XFS and curious about any tune/tweak regarding XFS >> filesystem on any raid array, non-raid, ssd or non-ssd. But, is >> there any valid value to determine about the performance? At >> least valid benchmark result (eg. using fio with some parameters, >> or any method). >> >> Then, about bsize, sectsz, etc, is there any wiki/guidelines how >> to set them on a right way? > > Ok, one additional thing: > > Use recent kernel and userspace utilities. > > Cause defaults are updated sometimes and with recent tools you get > best out of box experience. > -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.17 (MingW32) iQEcBAEBAgAGBQJVS1eBAAoJEF1+odKB6YIxyQwH/Am1bC+YhydmoWOknAMgjrEI 3mTmeUu0O/p90+DsXPS04zjht18XzsZKVTASVraPgPcrgzoqlHtHflK55++YIKp2 SLbFI2IexNLNbffyUgM7NCCpEjKZLkN8v4eNP2ylSgQqK4DTzwWPDypF16FX/rlc 2WuvQINR345i8rwjPryMbZAHiCem3ewYssx34jfH5NPh9CoRo1mnuFCEHzz9IG3L 4u0Z7zTKHZQPDaRzC3MVO5wOZNelnWXcP2TwiDJF3LgdEzWTinQGthEKy5ytSPPI xRZvJnzUvXWt6JNuWCUjtIUV3ODhBctfkk200wvMUyBdQg7Zo+OiXXOyaA24GsU= =wHBL -----END PGP SIGNATURE----- _______________________________________________ xfs mailing list xfs@oss.sgi.com http://oss.sgi.com/mailman/listinfo/xfs ^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: Valid Benchmark Value & Methods 2015-05-07 12:16 ` Dewangga @ 2015-05-07 13:54 ` Martin Steigerwald 2015-05-07 22:55 ` Dave Chinner 1 sibling, 0 replies; 7+ messages in thread From: Martin Steigerwald @ 2015-05-07 13:54 UTC (permalink / raw) To: Dewangga; +Cc: xfs Am Donnerstag, 7. Mai 2015, 19:16:02 schrieb Dewangga: > Hello Martin, > Thanks for your reply, yes I've read that link, but another question, > is noatime,nodiratime,etc still valid for performance tuning guidance? > Even the default mount options only "rw,inode64,seclabel,attr2". > > Is it still increase the performance if the additional mount options > added? noatime implies nodiratime as far as I know. And yes, it can help for databases for example. I think official recommendation for MySQL and PostgreSQL is to use noatime. There is a post by Theodore T´so somewhere about make clean workload on Ext4 with noatime, relatime and strictatime handling and only noatime considerably reduced the amount of writes. noatime is a generic tuning option which can help with other filesystems as well. -- Martin 'Helios' Steigerwald - http://www.Lichtvoll.de GPG: 03B0 0D6C 0040 0710 4AFA B82F 991B EAAC A599 84C7 _______________________________________________ xfs mailing list xfs@oss.sgi.com http://oss.sgi.com/mailman/listinfo/xfs ^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: Valid Benchmark Value & Methods 2015-05-07 12:16 ` Dewangga 2015-05-07 13:54 ` Martin Steigerwald @ 2015-05-07 22:55 ` Dave Chinner 2015-05-08 5:53 ` Dewangga Bachrul Alam 1 sibling, 1 reply; 7+ messages in thread From: Dave Chinner @ 2015-05-07 22:55 UTC (permalink / raw) To: Dewangga; +Cc: xfs On Thu, May 07, 2015 at 07:16:02PM +0700, Dewangga wrote: > -----BEGIN PGP SIGNED MESSAGE----- > Hash: SHA1 > > Hello Martin, > Thanks for your reply, yes I've read that link, but another question, > is noatime,nodiratime,etc still valid for performance tuning guidance? You may have read it, but I don't think it sunk in.... > Even the default mount options only "rw,inode64,seclabel,attr2". Where's relatime(*)? That's been a default for a lot longer than inode64... $ grep "root " /proc/mounts /dev/root / xfs rw,relatime,attr2,inode64,noquota 0 0 $ > Is it still increase the performance if the additional mount options > added? Depends on your workload, which is more critical to understand than anything else. Why? because it's your workload that is going to determine if twiddling a knob is going to have any effect on performance. Once you understand the workload and what the bottlenecks are, then you can look at what knobs the filesystem provides to alleviate those bottlenecks. IOWs, asking the question "how do I tune my filesystem for best performance" is, fundamentally, the wrong way to go about obtaining best filesystem performance. The questions that need to be answered are "what bottlenecks does my application have?" followed by "what does the filesystem provide to alleviate those bottlenecks". i.e. understand the problem you need to solve *before* you try to solve it, otherwise you "solve" the wrong problem... Cheers, Dave. (*) An example of exactly what I'm talking abou there. The default option of relatime gets >95% of the benefit of noatime onmost workloads compared to the old strictatime behaviour, but unlike noatime it still retains atime updates. IOWs there's a pretty good chance that noatime has little measurable impact on your application's performance, but understanding and benchmarking anything other than your application won't tell you this. -- Dave Chinner david@fromorbit.com _______________________________________________ xfs mailing list xfs@oss.sgi.com http://oss.sgi.com/mailman/listinfo/xfs ^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: Valid Benchmark Value & Methods 2015-05-07 22:55 ` Dave Chinner @ 2015-05-08 5:53 ` Dewangga Bachrul Alam 0 siblings, 0 replies; 7+ messages in thread From: Dewangga Bachrul Alam @ 2015-05-08 5:53 UTC (permalink / raw) To: Dave Chinner; +Cc: xfs Hello Dave! On 05/08/2015 05:55 AM, Dave Chinner wrote: > On Thu, May 07, 2015 at 07:16:02PM +0700, Dewangga wrote: >> -----BEGIN PGP SIGNED MESSAGE----- >> Hash: SHA1 >> >> Hello Martin, >> Thanks for your reply, yes I've read that link, but another question, >> is noatime,nodiratime,etc still valid for performance tuning guidance? > > You may have read it, but I don't think it sunk in.... > >> Even the default mount options only "rw,inode64,seclabel,attr2". > > Where's relatime(*)? That's been a default for a lot longer than > inode64... > > $ grep "root " /proc/mounts > /dev/root / xfs rw,relatime,attr2,inode64,noquota 0 0 > $ > I forgot write it, but relatime still exists on default mount options. >> Is it still increase the performance if the additional mount options >> added? > > Depends on your workload, which is more critical to understand than > anything else. Why? because it's your workload that is going to > determine if twiddling a knob is going to have any effect on > performance. Once you understand the workload and what the > bottlenecks are, then you can look at what knobs the filesystem > provides to alleviate those bottlenecks. > > IOWs, asking the question "how do I tune my filesystem for best > performance" is, fundamentally, the wrong way to go about obtaining > best filesystem performance. The questions that need to be answered > are "what bottlenecks does my application have?" followed by "what > does the filesystem provide to alleviate those bottlenecks". > > i.e. understand the problem you need to solve *before* you try to > solve it, otherwise you "solve" the wrong problem... > > Cheers, > > Dave. > > (*) An example of exactly what I'm talking abou there. The default > option of relatime gets >95% of the benefit of noatime onmost > workloads compared to the old strictatime behaviour, but unlike > noatime it still retains atime updates. IOWs there's a pretty good > chance that noatime has little measurable impact on your > application's performance, but understanding and benchmarking > anything other than your application won't tell you this. > Okay dave, got it. Standard optimize performance is add mount options like noatime and nodiratime, any additional performance tune is depends on the apps and the workloads. Thanks anyway :) _______________________________________________ xfs mailing list xfs@oss.sgi.com http://oss.sgi.com/mailman/listinfo/xfs ^ permalink raw reply [flat|nested] 7+ messages in thread
end of thread, other threads:[~2015-05-08 5:53 UTC | newest] Thread overview: 7+ messages (download: mbox.gz follow: Atom feed -- links below jump to the message on this page -- 2015-05-07 11:24 Valid Benchmark Value & Methods Dewangga 2015-05-07 11:48 ` Martin Steigerwald 2015-05-07 11:49 ` Martin Steigerwald 2015-05-07 12:16 ` Dewangga 2015-05-07 13:54 ` Martin Steigerwald 2015-05-07 22:55 ` Dave Chinner 2015-05-08 5:53 ` Dewangga Bachrul Alam
This is a public inbox, see mirroring instructions for how to clone and mirror all data and code used for this inbox