Date: Tue, 16 Dec 2008 22:21:55 +0100
From: Willy Tarreau <w@1wt.eu>
To: Trond Myklebust <trond.myklebust@fys.uio.no>
Cc: Harry Edmon <harry@atmos.washington.edu>, Max Kellermann <max@duempel.org>,
       linux-kernel@vger.kernel.org, linux-nfs@vger.kernel.org,
       stable@kernel.org
Subject: Re: High load in 2.6.27, NFS / rpcauth_lookup_credcache()?
Message-ID: <20081216212155.GA581@1wt.eu>
References: <20081022091207.GA12996@squirrel.roonstrasse.net> <20081023123628.GA18549@squirrel.roonstrasse.net> <1224773745.7625.4.camel@localhost> <4946EBFA.60700@atmos.washington.edu> <1229432553.7257.4.camel@heimdal.trondhjem.org>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <1229432553.7257.4.camel@heimdal.trondhjem.org>
User-Agent: Mutt/1.5.11
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 4456
Lines: 105

On Tue, Dec 16, 2008 at 08:02:33AM -0500, Trond Myklebust wrote:
> On Mon, 2008-12-15 at 15:44 -0800, Harry Edmon wrote:
> > Trond Myklebust wrote:
> > > On Thu, 2008-10-23 at 14:36 +0200, Max Kellermann wrote:
> > >   
> > >> On 2008/10/22 11:12, Max Kellermann <max@duempel.org> wrote:
> > >>     
> > >>> after I was able to fix http://lkml.org/lkml/2008/10/17/147, the
> > >>> server which was already upgraded to 2.6.27.2 still gets very high
> > >>> load.  It is a web server with NFS file storage (NetApp), and while
> > >>> the others in the cluster (kernel 2.6.25) have a load of 1-3, 2.6.27.2
> > >>> gets 30-50.
> > >>>
> > >>> I did an oprofile, with the following results (server just started,
> > >>> load "only" 5-10):
> > >>>
> > >>> 87593    56.1116  (no location information)   vmlinux
> > >>> vmlinux                  rpcauth_lookup_credcache
> > >>> 16037    10.2732  auth_generic.c:0            vmlinux
> > >>> vmlinux                  generic_match
> > >>> 6460      4.1382  (no location information)   php4
> > >>> php4                     (no symbols)
> > >>> 2478      1.5874  (no location information)   libc-2.7.so
> > >>> libc-2.7.so              (no symbols)
> > >>> [...]
> > >>>
> > >>> We havn't configured any special authentication method.  It is a NFSv3
> > >>> over UDP mount, but the kernel has NFSv4 and therefore KRB5 enabled.
> > >>>
> > >>> Any ideas why rpcauth_lookup_credcache() goes overboard with CPU
> > >>> usage?
> > >>>       
> > >> I have bisected the problem: 98a8e323 is the result ("SUNRPC: Add a
> > >> helper rpcauth_lookup_generic_cred()").  5c691044 is ok.
> > >>
> > >> See the attached oprofile annotation data for both commits.  I guess
> > >> that the function rpcauth_lookup_credcache() is waiting for a spinlock
> > >> too often and too long.  Trond, any idea?
> > >>     
> > >
> > > Can you add a '-v' to the rpc.gssd daemon startup line? I'd like to see
> > > how often you are creating new gss contexts.
> > >
> > >   
> > >> Harry: added you to Cc because your problem sounds similar.
> > >>     
> > >
> > > Harry's problem is should be unrelated. afaik, he is seeing a problem
> > > with userland RPC code, not kernel rpc code.
> > >
> > > Trond
> > >
> > >   
> > I am finally getting some time to look at my problem that I originally 
> > reported in October (SUNRPC problem with 2.6.26 and beyond), and I am 
> > seeing the same behavior as Max Kellermann when my machine slows as I 
> > described earlier.  The system in question is currently running 
> > 2.6.27.7.  Here is what I see when it is misbehaving:
> > 
> > samples  %        image name               app name                 
> > symbol name
> > 11380517 57.4191  sunrpc.ko                sunrpc                   
> > rpcauth_lookup_credcache
> > 3263657  16.4664  sunrpc.ko                sunrpc                   
> > generic_match
> > 1081287   5.4555  vmlinux                  vmlinux                  
> > copy_user_generic_string
> > 499407    2.5197  vmlinux                  vmlinux                  
> > __posix_lock_file
> > [...]
> > 
> > And here is what I see when I stop the programs that are chewing up all 
> > the system time, and then starting them up again:
> > 
> > samples  %        image name               app name                 
> > symbol name
> > 6372650  21.7978  vmlinux                  vmlinux                  
> > copy_user_generic_string
> > 5401386  18.4755  sunrpc.ko                sunrpc                   
> > rpcauth_lookup_credcache
> > 3018753  10.3257  vmlinux                  vmlinux                  
> > __posix_lock_file
> > 1050095   3.5919  sunrpc.ko                sunrpc                   
> > generic_match
> > 
> > 
> > and I am not using Kerberos with NFSv4 (i.e. no rpc.gssd).  Did you ever 
> > find a solution for this problem with rpcauth_lookup_credcache?
> 
> http://git.kernel.org/?p=linux/kernel/git/torvalds/linux-2.6.git&a=commitdiff&h=23918b03060f6e572168fdde1798a905679d2e06

Trond, this should be included into next stable, right ?

It's fortunate because I know someone else who recently described me the
same problem under the same circumstances when migrating from 2.6.22 to
2.6.27.

Regards,
Willy

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/