Re: 2.6.29.1: nfsd: page allocation failure - nfsd or kernel problem?

[Michael Tokarev <mjt@tls.msk.ru>]

Michael Tokarev wrote:
> Justin Piszcz wrote:
>> Package: nfs-kernel-server
>> Version: 1.1.6-1
>> Distribution: Debian Testing
>> Architecture: 64-bit
>>
>> [6042655.755870] Pid: 7093, comm: nfsd Not tainted 2.6.29.1 #4
>> [6042655.755872] Call Trace:
>> [6042655.755874]  <IRQ>  [<ffffffff802850fd>]  
>> __alloc_pages_internal+0x3dd/0x4e0
>> [6042655.755885]  [<ffffffff802a738b>] cache_alloc_refill+0x2fb/0x570
>> [6042655.755887]  [<ffffffff802a76db>] __kmalloc+0xdb/0xe0
> 
> Was about to send this same report.
> 
> The thing continues servicing files it seems, but after some quite
> good delay.
> 
> This happens after massive amount of writes.  2.6.29.4 does the
> same thing.  Here it is, for comparison:
> 
> Jun 13 17:06:42 gnome vmunix: nfsd: page allocation failure. order:0, mode:0x20
> Jun 13 17:06:42 gnome vmunix: Call Trace:
> Jun 13 17:06:42 gnome vmunix:  <IRQ>  [<ffffffff8029559d>]  __alloc_pages_internal+0x3fd/0x500
> Jun 13 17:06:42 gnome vmunix:  [<ffffffff802bd4c3>]  cache_alloc_refill+0x313/0x5c0
> Jun 13 17:06:42 gnome vmunix:  [<ffffffff802bd873>] __kmalloc+0x103/0x110
> Jun 13 17:06:42 gnome vmunix:  [<ffffffff803dca6d>] __alloc_skb+0x6d/0x150
...

Justin, by the way, what's the underlying filesystem on the server?

I've seen this error on 2 machines already (both running 2.6.29.x x86-64),
and in both cases the filesystem on the server was xfs.  May this be
related somehow to http://bugzilla.kernel.org/show_bug.cgi?id=13375 ?
That one is different, but also about xfs and nfs.  I'm trying to
reproduce the problem on different filesystem...

/mjt