SCIENTIFIC-LINUX-USERS Archives

June 2008

SCIENTIFIC-LINUX-USERS@LISTSERV.FNAL.GOV

Options: Use Monospaced Font
Show Text Part by Default
Condense Mail Headers

Message: [<< First] [< Prev] [Next >] [Last >>]
Topic: [<< First] [< Prev] [Next >] [Last >>]
Author: [<< First] [< Prev] [Next >] [Last >>]

Print Reply
Sender:
Mailling list for Scientific Linux users worldwide <[log in to unmask]>
Date:
Wed, 18 Jun 2008 12:47:20 -0400
MIME-version:
1.0
Reply-To:
Christopher Hunter <[log in to unmask]>
Content-type:
text/plain; format=flowed; charset=ISO-8859-1
Subject:
From:
Christopher Hunter <[log in to unmask]>
In-Reply-To:
Content-transfer-encoding:
7BIT
Comments:
To: Jan Schulze <[log in to unmask]> cc: [log in to unmask]
Parts/Attachments:
text/plain (44 lines)
I have similar problems but they are related to obtaining user login 
info over the network and not NFS.

Are you using ldap or NIS for user authorization/authentication ?
Do you use nscd (name switch caching daemon) on the clients ?


Jan Schulze wrote:
> Hi all,
> 
> I recently upgraded a number of NFS clients from SL 4.2 to SL 5.1. The
> NFS server is still running SL 4.2. Clients are acting very slow, e.g.
> 
> - after SSH authentication, it takes about 5 sec. for the console prompt
>  to appear
> - every 'ls' is slow
> - compiling stuff is terribly slow
> 
> It seems to have something to do with NFS - I'm having some NFS-mounted
> directories in my $PATH (TC shell). When I throw them out, everything is
> working as expected (e.g. compiling gcc was ~9 times faster). Please
> note, that the same $PATH does not noticeably slow things down on the
> old 4.2 systems.
> 
> I did comparisons compiling gcc on the old and new systems while running
> tcpdump. I found, that the new systems performed a lot more NFS lookups
> (by factor ~4). Everything else seemed normal.
> 
> File transfer to the NFS server is OK, no speed problems here. Tcpdump,
> however shows a lot of lines like this one, when copying files:
>   18:19:56.571906 IP bsnode02.0 > morphin.nfs: 1448 null
> 
> Load on the NFS server is much higher than before. I'm a little bit at a
> loss - how could I debug these issues further?
> 
> 
> Regards,
> Jan


-- 
Chris Hunter
Systems Programmer, Astronomy Yale University

ATOM RSS1 RSS2