On Fri, 2011-05-06 at 16:44 +0100, Mel Gorman wrote: > On Fri, May 06, 2011 at 08:42:24AM +0100, Mel Gorman wrote: > > > > 1. High-order allocations? You machine is using i915 and RPC, something > > neither of my test machine uses. i915 is potentially a source for > > high-order allocations. I'm attaching a perl script. Please run it as > > ./watch-highorder.pl --output /tmp/highorders.txt > > while you are running tar. When kswapd is running for about 30 > > seconds, interrupt it with ctrl+c twice in quick succession and > > post /tmp/highorders.txt > > > > Colin send me this information for his test case at least and I see > > 11932 instances order=1 normal gfp_flags=GFP_NOWARN|GFP_NORETRY|GFP_COMP|GFP_NOMEMALLOC > => alloc_pages_current+0xa5/0x110 <ffffffff81149ef5> > => new_slab+0x1f5/0x290 <ffffffff81153645> > => __slab_alloc+0x262/0x390 <ffffffff81155192> > => kmem_cache_alloc+0x115/0x120 <ffffffff81155ab5> > => mempool_alloc_slab+0x15/0x20 <ffffffff8110e705> > => mempool_alloc+0x59/0x140 <ffffffff8110ea49> > => bio_alloc_bioset+0x3e/0xf0 <ffffffff811976ae> > => bio_alloc+0x15/0x30 <ffffffff81197805> > > Colin and James: Did you happen to switch from SLAB to SLUB between > 2.6.37 and 2.6.38? My own tests were against SLAB which might be why I > didn't see the problem. Am restarting the tests with SLUB. So I tested with SLAB instead of SLUB and I reliably ran my copy test for 4+ hours with several hundred iterations of the test. (Apologies for taking time to respond, but I was travelling). > -- To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html