[gpfsug-discuss] gpfs performance monitoring

Ed Wahl ewahl at osc.edu
Thu Sep 4 15:13:48 BST 2014


Another known issue with slow "ls" can be the annoyance that is 'sssd' under newer OSs (rhel 6) and properly configuring this for remote auth.  I know on my nsd's I never did and the first ls in a directory where the cache is expired takes forever to make all the remote LDAP calls to get the UID info. bleh.

Ed

________________________________
From: gpfsug-discuss-bounces at gpfsug.org [gpfsug-discuss-bounces at gpfsug.org] on behalf of service at metamodul.com [service at metamodul.com]
Sent: Thursday, September 04, 2014 6:05 AM
To: gpfsug main discussion list
Subject: Re: [gpfsug-discuss] gpfs performance monitoring

> , any "ls" could take ages.

Check if you large directories either with many files or simply large.
Verify if you have NFS exported GPFS.
Verify that your cache settings on the clients are large enough ( maxStatCache , maxFilesToCache , sharedMemLimit )
Verify that you have dedicated metadata luns ( metadataOnly )

Reference:
https://www.ibm.com/developerworks/community/wikis/home?lang=en#!/wiki/General%20Parallel%20File%20System%20%28GPFS%29/page/Tuning%20Parameters

Note:
If possible monitor your metadata luns on the storage directly.

hth
Hajo




-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://gpfsug.org/pipermail/gpfsug-discuss_gpfsug.org/attachments/20140904/129caa21/attachment-0003.htm>


More information about the gpfsug-discuss mailing list