From: Nitin Gupta <ngupta@vflare.org>
To: Seth Jennings <sjenning@linux.vnet.ibm.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
Andrew Morton <akpm@linux-foundation.org>,
Minchan Kim <minchan@kernel.org>,
Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>,
Dan Magenheimer <dan.magenheimer@oracle.com>,
Robert Jennings <rcj@linux.vnet.ibm.com>,
Jenifer Hopper <jhopper@us.ibm.com>, Mel Gorman <mgorman@suse.de>,
Johannes Weiner <jweiner@redhat.com>,
Rik van Riel <riel@redhat.com>,
Larry Woodman <lwoodman@redhat.com>,
linux-mm@kvack.org, linux-kernel@vger.kernel.org,
devel@driverdev.osuosl.org
Subject: Re: [PATCHv2 4/9] staging: zsmalloc: make CLASS_DELTA relative to PAGE_SIZE
Date: Thu, 24 Jan 2013 16:17:55 -0800 [thread overview]
Message-ID: <CAPkvG_c48ZfwBRKCXSZrnVo=GgoLpqsRrF=8DEAwfFFVhb=1ZA@mail.gmail.com> (raw)
In-Reply-To: <1357590280-31535-5-git-send-email-sjenning@linux.vnet.ibm.com>
On Mon, Jan 7, 2013 at 12:24 PM, Seth Jennings
<sjenning@linux.vnet.ibm.com> wrote:
> Right now ZS_SIZE_CLASS_DELTA is hardcoded to be 16. This
> creates 254 classes for systems with 4k pages. However, on
> PPC64 with 64k pages, it creates 4095 classes which is far
> too many.
>
> This patch makes ZS_SIZE_CLASS_DELTA relative to PAGE_SIZE
> so that regardless of the page size, there will be the same
> number of classes.
>
> Signed-off-by: Seth Jennings <sjenning@linux.vnet.ibm.com>
> ---
> drivers/staging/zsmalloc/zsmalloc-main.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/drivers/staging/zsmalloc/zsmalloc-main.c b/drivers/staging/zsmalloc/zsmalloc-main.c
> index 825e124..3543047 100644
> --- a/drivers/staging/zsmalloc/zsmalloc-main.c
> +++ b/drivers/staging/zsmalloc/zsmalloc-main.c
> @@ -141,7 +141,7 @@
> * ZS_MIN_ALLOC_SIZE and ZS_SIZE_CLASS_DELTA must be multiple of ZS_ALIGN
> * (reason above)
> */
> -#define ZS_SIZE_CLASS_DELTA 16
> +#define ZS_SIZE_CLASS_DELTA (PAGE_SIZE >> 8)
> #define ZS_SIZE_CLASSES ((ZS_MAX_ALLOC_SIZE - ZS_MIN_ALLOC_SIZE) / \
> ZS_SIZE_CLASS_DELTA + 1)
>
Actually, there is no point creating size classes beyond [M/(M+1)] * PAGE_SIZE
where M is the maximum number of system pages in a zspage. All size classes
beyond this size can be collapsed with PAGE_SIZE size class. This can
significantly reduce number of size classes created but I think changes needed
to do this would be more involved, so perhaps, should be done in another
patch.
Can you please resend part of this series (patch 1 to patch 4) which deals
just with zsmalloc separately? I haven't yet looked into zswap itself so would
help with zsmalloc bits are separated out.
Acked-by: Nitin Gupta <ngupta@vflare.org>
next prev parent reply other threads:[~2013-01-25 0:18 UTC|newest]
Thread overview: 43+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-01-07 20:24 [PATCHv2 0/9] zswap: compressed swap caching Seth Jennings
2013-01-07 20:24 ` [PATCHv2 1/9] staging: zsmalloc: add gfp flags to zs_create_pool Seth Jennings
2013-01-25 0:08 ` Nitin Gupta
2013-01-25 1:33 ` Minchan Kim
2013-01-25 15:07 ` Seth Jennings
2013-01-25 15:56 ` Dan Magenheimer
2013-01-28 2:59 ` Minchan Kim
2013-01-30 16:11 ` Konrad Rzeszutek Wilk
2013-01-31 5:21 ` Minchan Kim
2013-01-25 21:26 ` Rik van Riel
2013-01-07 20:24 ` [PATCHv2 2/9] staging: zsmalloc: remove unsed pool name Seth Jennings
2013-01-25 0:09 ` Nitin Gupta
2013-01-25 21:50 ` Rik van Riel
2013-01-07 20:24 ` [PATCHv2 3/9] staging: zsmalloc: add page alloc/free callbacks Seth Jennings
2013-01-25 0:11 ` Nitin Gupta
2013-01-25 21:55 ` Rik van Riel
2013-01-07 20:24 ` [PATCHv2 4/9] staging: zsmalloc: make CLASS_DELTA relative to PAGE_SIZE Seth Jennings
2013-01-25 0:17 ` Nitin Gupta [this message]
2013-01-25 16:38 ` Seth Jennings
2013-01-07 20:24 ` [PATCHv2 5/9] debugfs: add get/set for atomic types Seth Jennings
2013-01-07 20:32 ` Greg Kroah-Hartman
2013-01-07 20:41 ` Seth Jennings
2013-01-25 16:45 ` Seth Jennings
2013-01-25 21:35 ` Greg Kroah-Hartman
2013-01-07 20:24 ` [PATCHv2 6/9] zsmalloc: promote to lib/ Seth Jennings
2013-01-28 4:01 ` Minchan Kim
2013-01-28 4:32 ` Minchan Kim
2013-01-28 17:41 ` Seth Jennings
2013-01-07 20:24 ` [PATCHv2 7/9] mm: break up swap_writepage() for frontswap backends Seth Jennings
2013-01-28 4:22 ` Minchan Kim
2013-01-28 17:26 ` Seth Jennings
2013-01-28 23:46 ` Minchan Kim
2013-01-07 20:24 ` [PATCHv2 8/9] zswap: add to mm/ Seth Jennings
2013-01-08 17:15 ` Dave Hansen
2013-01-08 17:54 ` Dan Magenheimer
2013-01-25 22:44 ` Rik van Riel
2013-01-25 23:15 ` Dan Magenheimer
2013-01-28 15:27 ` Seth Jennings
2013-01-29 10:21 ` Lord Glauber Costa of Sealand
2013-02-07 16:13 ` Seth Jennings
2013-02-11 19:13 ` Dan Magenheimer
2013-01-07 20:24 ` [PATCHv2 9/9] zswap: add documentation Seth Jennings
2013-01-22 18:10 ` [PATCHv2 0/9] zswap: compressed swap caching Seth Jennings
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to='CAPkvG_c48ZfwBRKCXSZrnVo=GgoLpqsRrF=8DEAwfFFVhb=1ZA@mail.gmail.com' \
--to=ngupta@vflare.org \
--cc=akpm@linux-foundation.org \
--cc=dan.magenheimer@oracle.com \
--cc=devel@driverdev.osuosl.org \
--cc=gregkh@linuxfoundation.org \
--cc=jhopper@us.ibm.com \
--cc=jweiner@redhat.com \
--cc=konrad.wilk@oracle.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=lwoodman@redhat.com \
--cc=mgorman@suse.de \
--cc=minchan@kernel.org \
--cc=rcj@linux.vnet.ibm.com \
--cc=riel@redhat.com \
--cc=sjenning@linux.vnet.ibm.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).