[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <200901151605.21231.ionut.leonte@gmail.com>
Date: Thu, 15 Jan 2009 16:05:21 +0200
From: Ionut Leonte <ionut.leonte@...il.com>
To: Herbert Xu <herbert@...dor.apana.org.au>
Cc: linux-kernel@...r.kernel.org
Subject: Re: b44 - swapper: page allocation failure
On Thursday 15 January 2009 13:15:37 you wrote:
> You missed the all important order line before the stack trace.
> If it's order 0, then you're just out of memory, if it's greater
> than order 0, then either you're using jumbo frames or b44 is
> broken.
This is the test I've done: boot the system with 2.6.28 (config is copied from
2.6.27 which works ok); from another system attempt to scp a 45MB file to
this system; the scp stalls (and finally fails) at around 60%. This is 100%
reproducible in this way. Attached is the full dmesg output and the config.
The output of 'free' during all this:
total used free shared buffers cached
Mem: 3083944 114304 2969640 0 4160 61096
-/+ buffers/cache: 49048 3034896
Swap: 2104472 0 2104472
View attachment "dmesg-report" of type "text/plain" (114121 bytes)
View attachment "config" of type "text/plain" (64262 bytes)
Powered by blists - more mailing lists