From: Wu Fengguang <wfg@mail.ustc.edu.cn>
To: linux-kernel@vger.kernel.org
Cc: Andrew Morton <akpm@osdl.org>,
Christoph Lameter <christoph@lameter.com>,
Rik van Riel <riel@redhat.com>,
Peter Zijlstra <a.p.zijlstra@chello.nl>,
Marcelo Tosatti <marcelo.tosatti@cyclades.com>,
Magnus Damm <magnus.damm@gmail.com>,
Nick Piggin <npiggin@suse.de>, Andrea Arcangeli <andrea@suse.de>,
Wu Fengguang <wfg@mail.ustc.edu.cn>
Subject: [PATCH 10/13] mm: let sc.nr_scanned/sc.nr_reclaimed accumulate
Date: Tue, 06 Dec 2005 21:56:18 +0800 [thread overview]
Message-ID: <20051206135922.125063000@localhost.localdomain> (raw)
In-Reply-To: 20051206135608.860737000@localhost.localdomain
[-- Attachment #1: mm-accumulate-nr-scanned-reclaimed-in-scan-control.patch --]
[-- Type: text/plain, Size: 4611 bytes --]
Now that there's no need to keep track of nr_scanned/nr_reclaimed for every
single round of shrink_zone(), remove the total_scanned/total_reclaimed and
let nr_scanned/nr_reclaimed accumulate between shrink_zone() calls.
Signed-off-by: Wu Fengguang <wfg@mail.ustc.edu.cn>
---
mm/vmscan.c | 36 ++++++++++++++----------------------
1 files changed, 14 insertions(+), 22 deletions(-)
--- linux-2.6.15-rc5-mm1.orig/mm/vmscan.c
+++ linux-2.6.15-rc5-mm1/mm/vmscan.c
@@ -1225,7 +1225,6 @@ int try_to_free_pages(struct zone **zone
{
int priority;
int ret = 0;
- int total_scanned = 0, total_reclaimed = 0;
struct reclaim_state *reclaim_state = current->reclaim_state;
struct scan_control sc;
int i;
@@ -1235,6 +1234,8 @@ int try_to_free_pages(struct zone **zone
sc.gfp_mask = gfp_mask;
sc.may_writepage = 0;
sc.may_swap = 1;
+ sc.nr_scanned = 0;
+ sc.nr_reclaimed = 0;
inc_page_state(allocstall);
@@ -1250,8 +1251,6 @@ int try_to_free_pages(struct zone **zone
/* The added 10 priorities are for scan rate balancing */
for (priority = DEF_PRIORITY + 10; priority >= 0; priority--) {
sc.nr_mapped = read_page_state(nr_mapped);
- sc.nr_scanned = 0;
- sc.nr_reclaimed = 0;
sc.priority = priority;
sc.nr_to_reclaim = SWAP_CLUSTER_MAX;
if (!priority)
@@ -1263,9 +1262,7 @@ int try_to_free_pages(struct zone **zone
sc.nr_reclaimed += reclaim_state->reclaimed_slab;
reclaim_state->reclaimed_slab = 0;
}
- total_scanned += sc.nr_scanned;
- total_reclaimed += sc.nr_reclaimed;
- if (total_reclaimed >= SWAP_CLUSTER_MAX) {
+ if (sc.nr_reclaimed >= SWAP_CLUSTER_MAX) {
ret = 1;
goto out;
}
@@ -1277,13 +1274,13 @@ int try_to_free_pages(struct zone **zone
* that's undesirable in laptop mode, where we *want* lumpy
* writeout. So in laptop mode, write out the whole world.
*/
- if (total_scanned > SWAP_CLUSTER_MAX * 3 / 2) {
- wakeup_pdflush(laptop_mode ? 0 : total_scanned);
+ if (sc.nr_scanned > SWAP_CLUSTER_MAX * 3 / 2) {
+ wakeup_pdflush(laptop_mode ? 0 : sc.nr_scanned);
sc.may_writepage = 1;
}
/* Take a nap, wait for some writeback to complete */
- if (sc.nr_scanned && priority < DEF_PRIORITY)
+ if (priority < DEF_PRIORITY)
blk_congestion_wait(WRITE, HZ/10);
}
out:
@@ -1329,18 +1326,17 @@ static int balance_pgdat(pg_data_t *pgda
int all_zones_ok;
int priority;
int i;
- int total_scanned, total_reclaimed;
struct reclaim_state *reclaim_state = current->reclaim_state;
struct scan_control sc;
struct zone *prev_zone = pgdat->node_zones;
loop_again:
- total_scanned = 0;
- total_reclaimed = 0;
sc.gfp_mask = GFP_KERNEL;
sc.may_writepage = 0;
sc.may_swap = 1;
sc.nr_mapped = read_page_state(nr_mapped);
+ sc.nr_scanned = 0;
+ sc.nr_reclaimed = 0;
inc_page_state(pageoutrun);
@@ -1355,8 +1351,6 @@ loop_again:
for (priority = DEF_PRIORITY; priority >= 0; priority--) {
all_zones_ok = 1;
- sc.nr_scanned = 0;
- sc.nr_reclaimed = 0;
sc.priority = priority;
sc.nr_to_reclaim = nr_pages ? nr_pages : SWAP_CLUSTER_MAX;
@@ -1417,19 +1411,17 @@ scan_swspd:
reclaim_state->reclaimed_slab = 0;
shrink_slab(prev_zone, priority, GFP_KERNEL);
sc.nr_reclaimed += reclaim_state->reclaimed_slab;
- total_reclaimed += sc.nr_reclaimed;
- total_scanned += sc.nr_scanned;
/*
* If we've done a decent amount of scanning and
* the reclaim ratio is low, start doing writepage
* even in laptop mode
*/
- if (total_scanned > SWAP_CLUSTER_MAX * 2 &&
- total_scanned > total_reclaimed+total_reclaimed/2)
+ if (sc.nr_scanned > SWAP_CLUSTER_MAX * 2 &&
+ sc.nr_scanned > sc.nr_reclaimed + sc.nr_reclaimed / 2)
sc.may_writepage = 1;
- if (nr_pages && to_free > total_reclaimed)
+ if (nr_pages && to_free > sc.nr_reclaimed)
continue; /* swsusp: need to do more work */
if (all_zones_ok)
break; /* kswapd: all done */
@@ -1437,7 +1429,7 @@ scan_swspd:
* OK, kswapd is getting into trouble. Take a nap, then take
* another pass across the zones.
*/
- if (total_scanned && priority < DEF_PRIORITY - 2)
+ if (priority < DEF_PRIORITY - 2)
blk_congestion_wait(WRITE, HZ/10);
/*
@@ -1446,7 +1438,7 @@ scan_swspd:
* matches the direct reclaim path behaviour in terms of impact
* on zone->*_priority.
*/
- if ((total_reclaimed >= SWAP_CLUSTER_MAX) && (!nr_pages))
+ if (sc.nr_reclaimed >= SWAP_CLUSTER_MAX && !nr_pages)
break;
}
for (i = 0; i < pgdat->nr_zones; i++) {
@@ -1459,7 +1451,7 @@ scan_swspd:
goto loop_again;
}
- return total_reclaimed;
+ return sc.nr_reclaimed;
}
/*
--
next prev parent reply other threads:[~2005-12-06 13:36 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2005-12-06 13:56 [PATCH 00/13] Balancing the scan rate of major caches V2 Wu Fengguang
2005-12-06 13:56 ` [PATCH 01/13] mm: restore sc.nr_to_reclaim Wu Fengguang
2005-12-06 13:56 ` [PATCH 02/13] mm: simplify kswapd reclaim code Wu Fengguang
2005-12-06 13:56 ` [PATCH 03/13] mm: supporting variables and functions for balanced zone aging Wu Fengguang
2005-12-06 13:56 ` [PATCH 04/13] mm: balance zone aging in direct reclaim path Wu Fengguang
2005-12-06 13:56 ` [PATCH 05/13] mm: balance zone aging in kswapd " Wu Fengguang
2005-12-06 14:19 ` Wu Fengguang
2005-12-06 13:56 ` [PATCH 06/13] mm: balance slab aging Wu Fengguang
2005-12-06 13:56 ` [PATCH 07/13] mm: balance active/inactive list scan rates Wu Fengguang
2005-12-06 13:56 ` [PATCH 08/13] mm: remove unnecessary variable and loop Wu Fengguang
2005-12-06 13:56 ` [PATCH 09/13] mm: remove swap_cluster_max from scan_control Wu Fengguang
2005-12-06 13:56 ` Wu Fengguang [this message]
2005-12-06 13:56 ` [PATCH 11/13] mm: fold sc.may_writepage and sc.may_swap into sc.flags Wu Fengguang
2005-12-06 13:56 ` [PATCH 12/13] mm: add page reclaim debug traces Wu Fengguang
2005-12-06 13:56 ` [PATCH 13/13] mm: fix minor scan count bugs Wu Fengguang
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=20051206135922.125063000@localhost.localdomain \
--to=wfg@mail.ustc.edu.cn \
--cc=a.p.zijlstra@chello.nl \
--cc=akpm@osdl.org \
--cc=andrea@suse.de \
--cc=christoph@lameter.com \
--cc=linux-kernel@vger.kernel.org \
--cc=magnus.damm@gmail.com \
--cc=marcelo.tosatti@cyclades.com \
--cc=npiggin@suse.de \
--cc=riel@redhat.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