From: Nick Piggin <piggin@cyberone.com.au>
To: Mike Fedyk <mfedyk@matchmail.com>
Cc: Chris Wedgwood <cw@f00f.org>, Linus Torvalds <torvalds@osdl.org>,
linux-kernel@vger.kernel.org
Subject: Re: Large slab cache in 2.6.1
Date: Sun, 22 Feb 2004 16:37:46 +1100 [thread overview]
Message-ID: <4038402A.4030708@cyberone.com.au> (raw)
In-Reply-To: <40383300.5010203@matchmail.com>
[-- Attachment #1: Type: text/plain, Size: 686 bytes --]
Mike Fedyk wrote:
> Nick Piggin wrote:
>
>>
>>
>> Nick Piggin wrote:
>>
>>>
>>> Actually I think the previous shrink_slab formula factors
>>> out to the right thing anyway, so nevermind this patch :P
>>>
>>>
>>
>> Although, nr_used_zone_pages probably shouldn't be counting
>> highmem zones, which might be our problem.
>
>
> What is the kernel parameter to disable highmem? I saw nohighio, but
> that's not it...
>
Not sure. That defeats the purpose of trying to get your setup
working nicely though ;)
Can you upgrade to 2.6.3-mm2? It would be ideal if you could
test this patch against that kernel due to the other VM changes.
Chris, could you test this too please? Thanks.
[-- Attachment #2: vm-shrink-slab-lowmem.patch --]
[-- Type: text/plain, Size: 3526 bytes --]
linux-2.6-npiggin/include/linux/mm.h | 2 +-
linux-2.6-npiggin/mm/page_alloc.c | 13 +++++++++----
linux-2.6-npiggin/mm/vmscan.c | 22 ++++++++++++----------
3 files changed, 22 insertions(+), 15 deletions(-)
diff -puN mm/vmscan.c~vm-shrink-slab-lowmem mm/vmscan.c
--- linux-2.6/mm/vmscan.c~vm-shrink-slab-lowmem 2004-02-22 16:35:06.000000000 +1100
+++ linux-2.6-npiggin/mm/vmscan.c 2004-02-22 16:35:06.000000000 +1100
@@ -145,7 +145,7 @@ static int shrink_slab(unsigned long sca
if (down_trylock(&shrinker_sem))
return 0;
- pages = nr_used_zone_pages();
+ pages = nr_lowmem_lru_pages();
list_for_each_entry(shrinker, &shrinker_list, list) {
unsigned long long delta;
@@ -857,7 +857,8 @@ shrink_zone(struct zone *zone, unsigned
*/
static int
shrink_caches(struct zone **zones, int priority, int *total_scanned,
- int gfp_mask, int nr_pages, struct page_state *ps)
+ int *lowmem_scanned, int gfp_mask, int nr_pages,
+ struct page_state *ps)
{
int ret = 0;
int i;
@@ -875,7 +876,10 @@ shrink_caches(struct zone **zones, int p
ret += shrink_zone(zone, gfp_mask,
to_reclaim, &nr_scanned, ps, priority);
+
*total_scanned += nr_scanned;
+ if (i < ZONE_HIGHMEM)
+ *lowmem_scanned += nr_scanned;
if (ret >= nr_pages)
break;
}
@@ -915,19 +919,17 @@ int try_to_free_pages(struct zone **zone
zones[i]->temp_priority = DEF_PRIORITY;
for (priority = DEF_PRIORITY; priority >= 0; priority--) {
- int total_scanned = 0;
+ int total_scanned = 0, lowmem_scanned = 0;
struct page_state ps;
get_page_state(&ps);
nr_reclaimed += shrink_caches(zones, priority, &total_scanned,
- gfp_mask, nr_pages, &ps);
+ &lowmem_scanned, gfp_mask, nr_pages, &ps);
- if (zones[0] - zones[0]->zone_pgdat->node_zones < ZONE_HIGHMEM) {
- shrink_slab(total_scanned, gfp_mask);
- if (reclaim_state) {
- nr_reclaimed += reclaim_state->reclaimed_slab;
- reclaim_state->reclaimed_slab = 0;
- }
+ shrink_slab(lowmem_scanned, gfp_mask);
+ if (reclaim_state) {
+ nr_reclaimed += reclaim_state->reclaimed_slab;
+ reclaim_state->reclaimed_slab = 0;
}
if (nr_reclaimed >= nr_pages) {
diff -puN mm/page_alloc.c~vm-shrink-slab-lowmem mm/page_alloc.c
--- linux-2.6/mm/page_alloc.c~vm-shrink-slab-lowmem 2004-02-22 16:35:06.000000000 +1100
+++ linux-2.6-npiggin/mm/page_alloc.c 2004-02-22 16:35:06.000000000 +1100
@@ -772,13 +772,18 @@ unsigned int nr_free_pages(void)
EXPORT_SYMBOL(nr_free_pages);
-unsigned int nr_used_zone_pages(void)
+unsigned int nr_lowmem_lru_pages(void)
{
+ pg_data_t *pgdat;
unsigned int pages = 0;
- struct zone *zone;
- for_each_zone(zone)
- pages += zone->nr_active + zone->nr_inactive;
+ for_each_pgdat(pgdat) {
+ int i;
+ for (i = 0; i < ZONE_HIGHMEM; i++) {
+ struct zone *zone = pgdat->node_zones + i;
+ pages += zone->nr_active + zone->nr_inactive;
+ }
+ }
return pages;
}
diff -puN include/linux/mm.h~vm-shrink-slab-lowmem include/linux/mm.h
--- linux-2.6/include/linux/mm.h~vm-shrink-slab-lowmem 2004-02-22 16:35:06.000000000 +1100
+++ linux-2.6-npiggin/include/linux/mm.h 2004-02-22 16:35:06.000000000 +1100
@@ -625,7 +625,7 @@ static inline struct vm_area_struct * fi
extern struct vm_area_struct *find_extend_vma(struct mm_struct *mm, unsigned long addr);
-extern unsigned int nr_used_zone_pages(void);
+extern unsigned int nr_lowmem_lru_pages(void);
extern struct page * vmalloc_to_page(void *addr);
extern struct page * follow_page(struct mm_struct *mm, unsigned long address,
_
next prev parent reply other threads:[~2004-02-22 5:37 UTC|newest]
Thread overview: 56+ messages / expand[flat|nested] mbox.gz Atom feed top
2004-02-22 0:50 Large slab cache in 2.6.1 Mike Fedyk
2004-02-22 1:09 ` Mike Fedyk
2004-02-22 1:20 ` William Lee Irwin III
2004-02-22 2:03 ` Mike Fedyk
2004-02-22 2:17 ` William Lee Irwin III
2004-02-22 2:38 ` Nick Piggin
2004-02-22 2:46 ` William Lee Irwin III
2004-02-22 2:40 ` Mike Fedyk
2004-02-22 2:58 ` Nick Piggin
2004-02-22 2:33 ` Nick Piggin
2004-02-22 2:46 ` Nick Piggin
2004-02-22 2:54 ` Nick Piggin
2004-02-22 2:36 ` Chris Wedgwood
2004-02-22 3:03 ` Linus Torvalds
2004-02-22 3:11 ` Chris Wedgwood
2004-02-22 3:28 ` Linus Torvalds
2004-02-22 3:29 ` Chris Wedgwood
2004-02-22 3:31 ` Chris Wedgwood
2004-02-22 4:01 ` Nick Piggin
2004-02-22 4:10 ` Nick Piggin
2004-02-22 4:30 ` Nick Piggin
2004-02-22 4:41 ` Mike Fedyk
2004-02-22 5:37 ` Nick Piggin [this message]
2004-02-22 5:44 ` Chris Wedgwood
2004-02-22 5:52 ` Nick Piggin
2004-02-22 5:50 ` Mike Fedyk
2004-02-22 6:01 ` Nick Piggin
2004-02-22 6:17 ` Andrew Morton
2004-02-22 6:35 ` Nick Piggin
2004-02-22 6:57 ` Andrew Morton
2004-02-22 7:20 ` Nick Piggin
2004-02-22 8:36 ` Chris Wedgwood
2004-02-22 9:13 ` Andrew Morton
2004-02-23 0:16 ` Nick Piggin
2004-02-23 0:26 ` Andrew Morton
2004-02-23 0:34 ` Nick Piggin
2004-02-23 0:46 ` Andrew Morton
2004-02-23 0:54 ` Nick Piggin
2004-02-23 1:00 ` Andrew Morton
2004-02-23 1:06 ` Nick Piggin
2004-02-22 6:45 ` Mike Fedyk
2004-02-22 6:58 ` Nick Piggin
2004-02-22 7:20 ` Mike Fedyk
2004-02-22 6:09 ` Andrew Morton
2004-02-22 17:05 ` Linus Torvalds
2004-02-23 0:29 ` Nick Piggin
2004-02-22 6:15 ` Andrew Morton
2004-02-22 16:08 ` Martin J. Bligh
2004-02-22 17:55 ` Jamie Lokier
2004-02-23 3:45 ` Mike Fedyk
2004-02-22 21:13 ` Dipankar Sarma
2004-02-22 14:03 ` Ed Tomlinson
2004-02-23 2:28 ` Mike Fedyk
2004-02-23 3:33 ` Ed Tomlinson
2004-02-22 3:21 ` Mike Fedyk
-- strict thread matches above, loose matches on Subject: below --
2004-02-22 11:00 Manfred Spraul
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=4038402A.4030708@cyberone.com.au \
--to=piggin@cyberone.com.au \
--cc=cw@f00f.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mfedyk@matchmail.com \
--cc=torvalds@osdl.org \
/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