Re: [Bug #14141] order 2 page allocation failures in iwlagn

[Frans Pop <elendil@planet.nl>]

Some initial results; all negative I'm afraid.

On Wednesday 14 October 2009, Mel Gorman wrote:
> This is what I found. The following were the possible commits that might
> be causing the problem.

> 56e49d2..f166777 -- reclaim
>         I would have considered this strong candidates except again, the
>         last good commit happened after this point. If other obvious
>         candidates don't crop up, it might be worth double checking
>         within this range, particularly commit 56e49d2 vmscan: evict
>         use-once pages first as it is targeted at streaming-IO workloads
>         which would include your music workload.

Reverted 56e49d2 on top of .31.1; no change.

> 5c87ead..e9bb35d -- inactive ratio changes
>         These patches should be harmless but just in case, please
>         compare the output of
>         # grep inactive_ratio /proc/zoneinfo
>         on 2.6.30 and 2.6.31 and make sure the ratios are the same.

The same for both (and for .32). DMA: 1; DMA32: 3

>         Commit b70d94e altered how zonelists were selected during
>         allocation. This was tested fairly heavily but if the testing
>         missed something, it would mean that some allocations are not
>         using the zones they should be.

Reverted on top of .31.1; no change.

>         Commit bc75d33 is totally harmless but it mentions
>         min_free_kbytes. I checked on my machine to make sure
>         min_free_kbytes was the same on both 2.6.30 and 2.6.31. Can you
>         check that this is true for your machine? If min_free_kbytes
>         decreased, it could explain GFP_ATOMIC failures.

Virtually identical. .30: 5704; .31/.32: 5711

> After this point, your analysis indicates that things are already broken
> but lets look at some of the candidates anyway.  Out of curiousity,
> was CONFIG_UNEVICTABLE_LRU unset in your .config for 2.6.30? I could
> only find your 2.6.31 .config. If it was, it might be worth reverting
> 6837765963f1723e80ca97b1fae660f3a60d77df and unsetting it in 2.6.31 and
> seeing what happens.

CONFIG_UNEVICTABLE_LRU was set and during bisections I've always accepted 
the default, which was "y".

> Commit ee993b135ec75a93bd5c45e636bb210d2975159b altered how lumpy
> reclaim works but it should have been harmless. It does not cleanly
> revert but it's easy to manually revert.

Reverted on top of .31.1; no change.

I'll do some more digging in the 'akpm' merge.

--
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>