Messages in this thread |  | | | Date | Thu, 4 Sep 2008 16:14:33 -0700 | | From | Andrew Morton <> | | Subject | Re: [PATCH] VM: Implements the swap-out page-clustering technique |
| |
On Thu, 04 Sep 2008 15:34:30 +0330 "Hamid R. Jahanjou" <hamid.jahanjou@gmail.com> wrote:
> Implements the idea of swap-out page clustering from *BSD for > Linux. Each time a candidate page is to be swapped out, > virtually-nearby pages are scanned to find eligible pages to be > swapped out too as a cluster. This technique increases the likelihood of > bringing in related data on a page fault and decreases swap space > fragmentation in the long run. Currently, Linux searches only > physically-nearby pages which is not optimal since, over time, physically- > adjacent pages may become unrelated.
I tried that once. The code all worked as-designed but didn't seem to improve performance much across a spread of workloads.
> The code can be statically tuned. No benchmarks. I'm not sure whether > the added complexity is acceptable.
Benchmarks are essential, please. Good ones.
The whole point of the patch is to improve performance. If we don't know whether it improves performance, we cannot proceed in any way.
Secondly, please don't just dump a pile of new code in our laps and expect us to pick through it and work out what it does and how it does it. Please at least provide a carefully-written english-language description of the design and implementation.
Thirdly, I'd suggest that this code be converted into vaguely standard kernel coding style sooner rather than later. Convert it to use eight-column hard tabs then check it with scripts/checkpatch.pl, thanks.
|  |