[CentOS] swapper: page allocation failure. order:1, mode:0x20

[Tim Nelson]

----- Original Message -----
> On Thu, Oct 18, 2012 at 03:44:30PM -0500, Tim Nelson wrote:
> > Oct 18 03:10:52 backup kernel: Pid: 0, comm: swapper Not tainted
> > 2.6.32-279.9.1.el6.x86_64 #1
> 
> ...
> 
> > Oct 18 03:10:52 backup kernel: [<ffffffff814927ed>] ?
> > tcp_v4_syn_recv_sock+0x4d/0x310
> > Oct 18 03:10:52 backup kernel: [<ffffffff81494d26>] ?
> > tcp_check_req+0x226/0x460
> > Oct 18 03:10:52 backup kernel: [<ffffffff8148a6d6>] ?
> > tcp_rcv_state_process+0x126/0xa10
> 
> > Any thoughts on the cause? The system has 16GB of RAM, and whenever
> 
> It's not a normal "out of memory" error.
> 
> > checked, there is no swap usage. Is this a memory error (bad RAM)?
> 
> I see this sometimes on my linode using their custom kernel when
> doing
> lots of network communication (rsync'ing files).  It looks like an
> issue with the TCP/IP4 stack.  When I switched to IP6 then the
> messages
> went away.
> 

Interesting! I too am running heavy rsync operations on this host, and the messages appear to come once an evening when the rsync jobs are running. Of note though, the kernel is stock from the CentOS repos, nothing special. Is this possibly a known 'issue' or 'bug' with CentOS (or upstream)?

--Tim