[Ocfs2-users] very slow writes

Jay V jvasaoo at gmail.com
Thu May 10 14:05:37 PDT 2012


On Thu, May 10, 2012 at 1:59 PM, Jay V <jvasaoo at gmail.com> wrote:
> Ever since the file system reached 82% full, the file system has gone to a
> crawl and stalls of only writing up to 10 mb/s, even going as slow as a few
> kbytes/sec. The file system may be fragmented. Is there a defrag tool?
>
> I have tried many options, but nothing seems to work. "data=writeback" does
> seem to work. We have checked the logs, debugs, traces trying to figure out
> the probelm, but with no success.
>

I meant to say data=writeback does not seem to work.

> Features:
> Compat: backup-super strict-journal-super
> Incompat: sparse inline-data
> RO Compat: unwritten
> debugfs.ocfs2 -R "stats" /dev/drbd2
>         Revision: 0.90
>         Mount Count: 0   Max Mount Count: 20
>         State: 0   Errors: 0
>         Check Interval: 0   Last Check: Sat Mar 17 05:51:42 2012
>         Creator OS: 0
>         Feature Compat: 3 backup-super strict-journal-super
>         Feature Incompat: 80 sparse inline-data
>         Tunefs Incomplete: 0
>         Feature RO compat: 1 unwritten
>         Root Blknum: 5   System Dir Blknum: 6
>         First Cluster Group Blknum: 3
>         Block Size Bits: 12   Cluster Size Bits: 12
>         Max Node Slots: 2
>         Extended Attributes Inline Size: 0
>         Label: imepool2
>         UUID: 5AAD4275BEBA4F96B8FEE7274FC4D043
>         Hash: 0 (0x0)
>         DX Seeds: 0 0 0 (0x00000000 0x00000000 0x00000000)
>         Cluster stack: classic o2cb
>         Cluster flags: 0
>         Inode: 2   Mode: 00   Generation: 2084865048 (0x7c448418)
>         FS Generation: 2084865048 (0x7c448418)
>         CRC32: 00000000   ECC: 0000
>         Type: Unknown   Attr: 0x0   Flags: Valid System Superblock
>         Dynamic Features: (0x0)
>         User: 0 (root)   Group: 0 (root)   Size: 0
>         Links: 0   Clusters: 3496426618
>         ctime: 0x4aa1e6e7 0x0 -- Fri Sep  4 21:19:51.0 2009
>         atime: 0x0 0x0 -- Wed Dec 31 16:00:00.0 1969
>         mtime: 0x4aa1e6e7 0x0 -- Fri Sep  4 21:19:51.0 2009
>         dtime: 0x0 -- Wed Dec 31 16:00:00 1969
>         Refcount Block: 0
>         Last Extblk: 0   Orphan Slot: 0
>         Sub Alloc Slot: Global   Sub Alloc Bit: 65535
>
> Version OCFS2 1.8.0:
> filename:
> /lib/modules/2.6.39-100.5.1.el6uek.x86_64/kernel/fs/ocfs2/ocfs2.ko
> license:        GPL
> author:         Oracle
> version:        1.8.0
> description:    OCFS2 1.8.0
> srcversion:     A427F5E2A962D0808C8478F
> depends:        jbd2,ocfs2_stackglue,ocfs2_nodemanager
> vermagic:       2.6.39-100.5.1.el6uek.x86_64 SMP mod_unload modversions
> mounted options: rw,_netdev,noatime,nodiratime,heartbeat=local
>
> When deleting files it seems to help temporarily. I like to be able to go
> over 82% without this degradation.
>
> I want to minimize downtime as this filesystem is 15TB. Is there a feature I
> can enable such as "discontig-bg" that will help??
>
> Thanks so much for your help!
> -Jay



More information about the Ocfs2-users mailing list