Re: [PATCH]: Free pages from local pcp lists under tight memory conditions

[Nick Piggin]

Paul Jackson wrote:
> Rohit wrote:
>
> > Can you please comment on the performance delta on the MPI workload
> > because of this change in batch values. 
>
>
> I can't -- all I know is what I read in Jack Steiner's posts
> of April 5, 2005, referenced earlier in this thread.

It was something fairly large. Basically having a power of 2 batch size
meant that 2 concurrent allocators (presumably setting up the working
area) would alternately pull in power of 2 chunks of memory, which
caused each CPU to only get pages of ~half of its cache's possible
colours.

The fix is not by any means a single value for all workloads, it simply
avoids powers of 2 batch size. Note this will have very little effect
on single threaded allocators and will do nothing for cache colouring
there, however it is important for concurrent allocators.

Nick

--
SUSE Labs, Novell Inc.

Send instant messages to your online friends http://au.messenger.yahoo.com 
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/