[Bug 14830] When other IO is running sync times go to 10 to 20 minutes

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



http://bugzilla.kernel.org/show_bug.cgi?id=14830





--- Comment #16 from Michael Godfrey <godfrey@xxxxxxxxxxxxxxxx>  2010-01-29 06:37:55 ---
I had a chance to try noop and deadline:

With the amount of testing that I could do they seemed to behave
about the same, and:

1. the task timeouts are gone.

2. sync, which used to take over 20 minutes is consistently
   about 10 minutes.  I did retest by setting scheduler back
   to cfg and the sync time went back to 24 minutes.

3. I also tried 2 variations:
   1. rsync from source to target:  rsync machinea:/aaa bbb
   2. rsync of an NFS-mounted filesystem to local filesystem.
      (i.e the rsync thought it was local:  rsync aaa/  bbb,
      but aaa was NFS-mounted (NFS3).
   These two variation behaved just about identically.

I have left the system set to deadline, as recommended.  With
this setting (and with noop) things like du seem quicker too.

So, this is good, but 10 minutes for sync is still way too long.
With these systems, I cannot compile debug kernels or stuff like
that.  They are in use for backup.

Any other suggestions?

Michael

-- 
Configure bugmail: http://bugzilla.kernel.org/userprefs.cgi?tab=email
------- You are receiving this mail because: -------
You are watching the assignee of the bug.
--
To unsubscribe from this list: send the line "unsubscribe linux-ext4" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[Index of Archives]     [Reiser Filesystem Development]     [Ceph FS]     [Kernel Newbies]     [Security]     [Netfilter]     [Bugtraq]     [Linux FS]     [Yosemite National Park]     [MIPS Linux]     [ARM Linux]     [Linux Security]     [Linux RAID]     [Samba]     [Device Mapper]     [Linux Media]

  Powered by Linux