Re: ppoll() stuck on POLLIN while TCP peer is sending
From: Mel Gorman <mgorman@suse.de>
Date: 2013-01-11 09:30:53
Also in:
linux-mm, lkml
From: Mel Gorman <mgorman@suse.de>
Date: 2013-01-11 09:30:53
Also in:
linux-mm, lkml
On Fri, Jan 11, 2013 at 12:51:05AM +0000, Eric Wong wrote:
Mel Gorman [off-list ref] wrote:quoted
mm: compaction: Partially revert capture of suitable high-order page<snip>quoted
Reported-by: Eric Wong <redacted> Cc: stable@vger.kernel.org Signed-off-by: Mel Gorman <mgorman@suse.de>Thanks, my original use case and test works great after several hours! Tested-by: Eric Wong <redacted>
Thanks very much Eric. I've resent the patch to Andrew so it should make its way to mainline. It'll fail to apply to 3.7-stable but I should get a notification from Greg when that happens and fix it up.
Unfortunately, I also hit a new bug in 3.8 (not in 3.7.x). based on Eric Dumazet's observations, sk_stream_wait_memory may be to blame. Fortunately this is easier to reproduce (I've cc-ed participants on this thread already): [ref]
It looks like the relevant fix for this has already been written by Eric Dumazet and picked up by David Miller. -- Mel Gorman SUSE Labs -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@kvack.org. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>