I mounted the filesystem with trace logging turned on and can see that
after the last successful READDIRP there is a lot of other connections
being made the clients repeatedly which takes minutes to complete.
Please see attached for log file.
On Sun, 2014-02-16 at 06:28 +0000, Franco Broi wrote: > Hi all
>
> I've been trying to understand why Gluster dht is so slow when listing
some directories and not others. strace'ing ls on a directory of directories
shows it pause on the last getdents. I wrote a simple perl script to open the
directory and read the entries, it shows the same effect, the last call to
readdir which returns NULL takes nearly a minute to return. Doing a recursive
read on the sub directories can take 10 minutes...
>
> Any ideas what's happening here? It doesn't happen on all
directories, especially not newly created ones.
>
> Cheers,
>
> ________________________________
>
>
> This email and any files transmitted with it are confidential and are
intended solely for the use of the individual or entity to whom they are
addressed. If you are not the original recipient or the person responsible for
delivering the email to the intended recipient, be advised that you have
received this email in error, and that any use, dissemination, forwarding,
printing, or copying of this email is strictly prohibited. If you received this
email in error, please immediately notify the sender and delete the original.
>
> _______________________________________________
> Gluster-users mailing list
> Gluster-users at gluster.org
> http://supercolony.gluster.org/mailman/listinfo/gluster-users
-------------- next part --------------
A non-text attachment was scrubbed...
Name: glusterfs.log.gz
Type: application/gzip
Size: 45086 bytes
Desc: not available
URL:
<http://supercolony.gluster.org/pipermail/gluster-users/attachments/20140217/116b61cc/attachment.bin>