[Gluster-devel] Rsync failure problem
skimber
nabble at simonkimber.co.uk
Tue Jul 15 14:12:54 UTC 2008
Further to my message below, I'm getting a lot (thousands?) of errors like
this in the glusterfsd server log:
2008-07-15 14:19:41 E [posix.c:1984:posix_setdents] brick-ns: Error creating
file /data/export-ns/mydata/myfile.txt with mode (0100644)
Nothing relevant in syslog or the client logs I don't think.
skimber wrote:
>
> Thanks for the responses.
>
> It turned out that the issue was with the disk in one of the clients.
> Using the other client machine it appears to be working fine, although it
> does seem very slow.
>
> An ls -l on a directory containing about 150 files took > 5 mins and the
> rsync will only go at a rate of roughly one file every 3 seconds, average
> size 30 to 50Kb.
>
> If I do the rsync to the client's local HD instead it's many files per
> second.
>
> I have tried adding the following to the end of the client config from my
> original post but it doesn't appear to have made any noticable difference:
>
> volume readahead
> type performance/read-ahead
> option page-size 128kB # 256KB is the default option
> option page-count 4 # 2 is default option
> option force-atime-update off # default is off
> subvolumes unify
> end-volume
>
> volume writebehind
> type performance/write-behind
> option aggregate-size 1MB # default is 0bytes
> option flush-behind on # default is 'off'
> subvolumes readahead
> end-volume
>
> volume io-cache
> type performance/io-cache
> option cache-size 64MB # default is 32MB
> option page-size 1MB # 128KB is default option
> option priority *:0 # default is '*:0'
> option force-revalidate-timeout 2 # default is 1
> subvolumes writebehind
> end-volume
>
>
> Can anyone tell me if I have done this correctly and/or suggest anything
> else I can do to fix this performance issue?
>
> Thanks
>
> Simon
>
--
View this message in context: http://www.nabble.com/Rsync-failure-problem-tp18420195p18466242.html
Sent from the gluster-devel mailing list archive at Nabble.com.
More information about the Gluster-devel
mailing list