[reiserfs-list] Re: [PATCH CFT] tons of logging patches
Hello everyone, I've uploaded 03-data-logging-24.diff, which fixes a tail packing oops in data=journal mode, and fixes the data=ordered slow down (5-10%) introduced in -23. -23 flushed all the ordered buffer heads with the journal lock held, which meant no new transactions could start while the ordered buffers were being flushed. This was safe but slower. -24 flushes them right before the commit blocks (like -19 did), and only flushes the tail conversion targets with the journal lock held. Doing the tail conversion targets later risks losing the tail data after a crash. Thanks to [EMAIL PROTECTED] who reported the ordered write bug in -19 and the data=journal oops in -23. -chris
Re: [reiserfs-list] Re: [PATCH CFT] tons of logging patches
On Fri, 2002-08-02 at 08:28, Chris Mason wrote: > Hello everyone, > > I've uploaded 03-data-logging-24.diff, which fixes a tail packing oops > in data=journal mode, and fixes the data=ordered slow down (5-10%) > introduced in -23. Whoops, I neglected to mention that data=ordered is now the default in the patch. You can mount with -o data=writeback if you don't want ordered data writes. -chris
Re: [reiserfs-list] Re: [PATCH CFT] tons of logging patches
Chris Mason wrote: >On Fri, 2002-08-02 at 08:28, Chris Mason wrote: > > >>Hello everyone, >> >>I've uploaded 03-data-logging-24.diff, which fixes a tail packing oops >>in data=journal mode, and fixes the data=ordered slow down (5-10%) >>introduced in -23. >> >> > >Whoops, I neglected to mention that data=ordered is now the default in >the patch. You can mount with -o data=writeback if you don't want >ordered data writes. > >-chris > > > > > > we just saw a benchmark in which data=ordered caused a major slowdown. Does this patch fix this? Edward and Elena, I want thorough benchmarking of this. -- Hans
Re: [reiserfs-list] Re: [PATCH CFT] tons of logging patches
On Fri, 2002-08-02 at 08:59, Hans Reiser wrote: > > > we just saw a benchmark in which data=ordered caused a major slowdown. > Does this patch fix this? > > Edward and Elena, I want thorough benchmarking of this. > The last fract_tree benchmarks were on older patches, Manual Krause's benchmark was more showing the difference between a used and a fresh filesystem, and he was using -23 which had data=ordered performance issues fixed in -24. More benchmarking does need to be done, the patch isn't set in stone yet ;-) -chris
Re: [reiserfs-list] data-logging time comparison
On 08/02/2002 01:24 AM, Manuel Krause wrote: > Hi! > > Maybe you are interested in my recent backup time comparison. I simply > copied the partitions with "cp -ax /.../a/. /.../b/" where "/.../b/" is > a freshly created reiserfs. I hope the comparison is readable and makes > sense for someone. > O.k. I made a new comparison with just the data-logging patch replaced by the new -24, and now, only using fresh filesystems. I added the related lines from tonight to show the improvement. File size distribution statistics are available via email upon request (131kB as .tar.gz). Best wishes, Manuel partition 1: /dev/hdd7 2722896 1925876797020 71% /mnt/alpha (is my / filesystem) new FS noatime,notail,data=writeback real 3m11.881s user 0m1.600s sys 0m49.040s ~9,802MB/s =100% new FS noatime,notail,data=ordered real 3m19.895s user 0m1.400s sys 0m49.890s ~9,409MB/s96% new FS noatime,notail,data=journal real 6m48.534s user 0m1.570s sys 1m0.830s~4,604MB/s47% new FS noatime,notail "data-logging-23" (real 3m18.826s user 0m1.310s sys 0m49.710s) ~9,478MB/s97% new FS noatime,notail,data=ordered "data-logging-23" (real 4m6.866s user 0m1.620s sys 0m50.120s) ~7,633MB/s78% partition 2: /dev/hdd11 5550248 4490128 1060120 81% /mnt/alpha (is my software "repository") new FS noatime,notail,data=writeback real 8m46.739s user 0m1.430s sys 1m32.110s ~8,325MB/s =100% new FS noatime,notail,data=ordered real 8m56.040s user 0m1.410s sys 1m27.920s ~8,180MB/s98% new FS noatime,notail,data=journal real 18m36.456s user 0m1.750s sys 1m58.480s ~3,928MB/s47% new FS noatime,notail partition 86% full, "data-logging-23" (real 9m20.956s user 0m1.680s sys 1m39.190s) ~8,248MB/s99% new FS noatime,notail,data=ordered part. 86% full, "data-logging-23" (real 11m54.513s user 0m1.910s sys 1m38.460s) ~6,476MB/s78%
