lkml.org 
[lkml]   [2013]   [May]   [20]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: [RFCv2][PATCH 0/5] mm: Batch page reclamation under shink_page_list
On Thu, May 16, 2013 at 01:34:27PM -0700, Dave Hansen wrote:
> These are an update of Tim Chen's earlier work:
>
> http://lkml.kernel.org/r/1347293960.9977.70.camel@schen9-DESK
>
> I broke the patches up a bit more, and tried to incorporate some
> changes based on some feedback from Mel and Andrew.
>
> Changes for v2:
> * use page_mapping() accessor instead of direct access
> to page->mapping (could cause crashes when running in
> to swap cache pages.
> * group the batch function's introduction patch with
> its first use
> * rename a few functions as suggested by Mel
> * Ran some single-threaded tests to look for regressions
> caused by the batching. If there is overhead, it is only
> in the worst-case scenarios, and then only in hundreths of
> a percent of CPU time.
>
> If you're curious how effective the batching is, I have a quick
> and dirty patch to keep some stats:
>
> https://www.sr71.net/~dave/intel/rmb-stats-only.patch
>

Didn't do any performance comparison but did a kernel build with 2 make threads
per core in a memory constrained situation w/ zswap add got an average batch
size of 6.6 pages with the batch being empty on ~10% of calls.

rmb call: 423464
rmb pages: 2790332
rmb empty: 41408

The WARN_ONCE only gave me one stack for the first empty batch and, for what
it's worth, it was from kswapd.

Tested-by: Seth Jennings <sjenning@linux.vnet.ibm.com>



\
 
 \ /
  Last update: 2013-05-21 00:41    [W:0.264 / U:1.816 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site