linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Andrew Morton <akpm@osdl.org>
To: Christoph Lameter <clameter@sgi.com>
Cc: npiggin@suse.de, linux-mm@kvack.org
Subject: Re: ZVC: Support NR_SLAB_RECLAIM
Date: Fri, 25 Aug 2006 16:56:59 -0700	[thread overview]
Message-ID: <20060825165659.0d8c03d4.akpm@osdl.org> (raw)
In-Reply-To: <Pine.LNX.4.64.0608251500560.11154@schroedinger.engr.sgi.com>

On Fri, 25 Aug 2006 15:16:19 -0700 (PDT)
Christoph Lameter <clameter@sgi.com> wrote:

> Remove the atomic counter for slab_reclaim_pages and replace
> with a ZVC counter. NR_SLAB will now only count the
> unreclaimable slab pages whereas NR_SLAB_RECLAIM will count
> the reclaimable slab pages.

That's misleading.  We should rename NR_SLAB to NR_SLAB_UNRECLAIMABLE.  And
NR_SLAB_RECLAIM should be NR_SLAB_RECLAIMABLE, no?

Naming matters.

> --- linux-2.6.18-rc4-mm2.orig/drivers/base/node.c	2006-08-23 12:36:56.875425210 -0700
> +++ linux-2.6.18-rc4-mm2/drivers/base/node.c	2006-08-25 14:42:05.130443045 -0700
> @@ -68,7 +68,8 @@ static ssize_t node_read_meminfo(struct 
>  		       "Node %d PageTables:   %8lu kB\n"
>  		       "Node %d NFS Unstable: %8lu kB\n"
>  		       "Node %d Bounce:       %8lu kB\n"
> -		       "Node %d Slab:         %8lu kB\n",
> +		       "Node %d SlabUnrecl:   %8lu kB\n"
> +		       "Node %d SlabReclaim:  %8lu kB\n",
>  		       nid, K(i.totalram),
>  		       nid, K(i.freeram),
>  		       nid, K(i.totalram - i.freeram),
> @@ -88,7 +89,8 @@ static ssize_t node_read_meminfo(struct 
>  		       nid, K(node_page_state(nid, NR_PAGETABLE)),
>  		       nid, K(node_page_state(nid, NR_UNSTABLE_NFS)),
>  		       nid, K(node_page_state(nid, NR_BOUNCE)),
> -		       nid, K(node_page_state(nid, NR_SLAB)));
> +		       nid, K(node_page_state(nid, NR_SLAB)),
> +		       nid, K(node_page_state(nid, NR_SLAB_RECLAIM)));
>  	n += hugetlb_report_node_meminfo(nid, buf + n);
>  	return n;

That breaks anything which uses the Slab: field.  OK, so it's NUMA geeks
only.  But still..


> Index: linux-2.6.18-rc4-mm2/fs/proc/proc_misc.c
> ===================================================================
> --- linux-2.6.18-rc4-mm2.orig/fs/proc/proc_misc.c	2006-08-23 12:36:59.772706994 -0700
> +++ linux-2.6.18-rc4-mm2/fs/proc/proc_misc.c	2006-08-25 14:23:03.848552529 -0700
> @@ -170,7 +170,8 @@ static int meminfo_read_proc(char *page,
>  		"Writeback:    %8lu kB\n"
>  		"AnonPages:    %8lu kB\n"
>  		"Mapped:       %8lu kB\n"
> -		"Slab:         %8lu kB\n"
> +		"SlabUnrecl:   %8lu kB\n"
> +		"SlabReclaim:  %8lu kB\n"
>  		"PageTables:   %8lu kB\n"
>  		"NFS Unstable: %8lu kB\n"
>  		"Bounce:       %8lu kB\n"
> @@ -199,6 +200,7 @@ static int meminfo_read_proc(char *page,
>  		K(global_page_state(NR_ANON_PAGES)),
>  		K(global_page_state(NR_FILE_MAPPED)),
>  		K(global_page_state(NR_SLAB)),
> +		K(global_page_state(NR_SLAB_RECLAIM)),
>  		K(global_page_state(NR_PAGETABLE)),
>  		K(global_page_state(NR_UNSTABLE_NFS)),
>  		K(global_page_state(NR_BOUNCE)),

But surely there are tools out there which look at /proc/meminfo:Slab:.  We
cannot just go and breezily break them.

We can add new fields though, so let's just have Slab:, SlabUnrecl: (ug)
and SlabReclaim: (ug).

I'll drop zone_reclaim-dynamic-zone-based-slab-reclaim.patch due to churn here.


--
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>

  parent reply	other threads:[~2006-08-25 23:56 UTC|newest]

Thread overview: 11+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2006-08-25 22:16 Christoph Lameter
2006-08-25 22:22 ` zone_reclaim: dynamic zone based slab reclaim Christoph Lameter
2006-08-25 23:42   ` Andrew Morton
2006-08-26  0:27     ` Christoph Lameter
2006-08-26  0:48       ` Andrew Morton
2006-08-25 23:56 ` Andrew Morton [this message]
2006-08-26  0:30   ` ZVC: Support NR_SLAB_RECLAIM Christoph Lameter
2006-08-26  0:55     ` Andrew Morton
2006-08-26  0:58       ` Christoph Lameter
2006-08-26  1:07         ` Andrew Morton
2006-08-26  1:10           ` Christoph Lameter

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=20060825165659.0d8c03d4.akpm@osdl.org \
    --to=akpm@osdl.org \
    --cc=clameter@sgi.com \
    --cc=linux-mm@kvack.org \
    --cc=npiggin@suse.de \
    /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