From: Pavel Emelianov <xemul@sw.ru>
To: Andrew Morton <akpm@osdl.org>, Paul Menage <menage@google.com>,
Srivatsa Vaddagiri <vatsa@in.ibm.com>,
Balbir Singh <balbir@in.ibm.com>
Cc: devel@openvz.org,
Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
containers@lists.osdl.org, Kirill Korotaev <dev@sw.ru>
Subject: [RFC][PATCH 5/7] Per-container OOM killer and page reclamation
Date: Tue, 06 Mar 2007 18:03:21 +0300 [thread overview]
Message-ID: <45ED82B9.8090306@sw.ru> (raw)
In-Reply-To: <45ED7DEC.7010403@sw.ru>
[-- Attachment #1: Type: text/plain, Size: 410 bytes --]
* container_try_to_free_pages() walks containers
page list and tries to shrink pages. This is based
on try_to_free_pages() and Co code.
Called from core code when no resource left at the
moment of page touching.
* container_out_of_memory() selects a process to be
killed which mm_struct belongs to container in question.
Called from core code when no resources left and no
pages were reclaimed.
[-- Attachment #2: diff-rss-container-oom-reclaim --]
[-- Type: text/plain, Size: 7897 bytes --]
diff -upr linux-2.6.20.orig/mm/oom_kill.c linux-2.6.20-0/mm/oom_kill.c
--- linux-2.6.20.orig/mm/oom_kill.c 2007-03-06 13:33:28.000000000 +0300
+++ linux-2.6.20-0/mm/oom_kill.c 2007-03-06 13:33:28.000000000 +0300
@@ -24,6 +24,7 @@
#include <linux/cpuset.h>
#include <linux/module.h>
#include <linux/notifier.h>
+#include <linux/rss_container.h>
int sysctl_panic_on_oom;
/* #define DEBUG */
@@ -47,7 +48,8 @@ int sysctl_panic_on_oom;
* of least surprise ... (be careful when you change it)
*/
-unsigned long badness(struct task_struct *p, unsigned long uptime)
+unsigned long badness(struct task_struct *p, unsigned long uptime,
+ struct rss_container *rss)
{
unsigned long points, cpu_time, run_time, s;
struct mm_struct *mm;
@@ -60,6 +62,13 @@ unsigned long badness(struct task_struct
return 0;
}
+#ifdef CONFIG_RSS_CONTAINER
+ if (rss != NULL && mm->rss_container != rss) {
+ task_unlock(p);
+ return 0;
+ }
+#endif
+
/*
* The memory size of the process is the basis for the badness.
*/
@@ -200,7 +209,8 @@ static inline int constrained_alloc(stru
*
* (not docbooked, we don't want this one cluttering up the manual)
*/
-static struct task_struct *select_bad_process(unsigned long *ppoints)
+static struct task_struct *select_bad_process(unsigned long *ppoints,
+ struct rss_container *rss)
{
struct task_struct *g, *p;
struct task_struct *chosen = NULL;
@@ -254,7 +264,7 @@ static struct task_struct *select_bad_pr
if (p->oomkilladj == OOM_DISABLE)
continue;
- points = badness(p, uptime.tv_sec);
+ points = badness(p, uptime.tv_sec, rss);
if (points > *ppoints || !chosen) {
chosen = p;
*ppoints = points;
@@ -435,7 +445,7 @@ retry:
* Rambo mode: Shoot down a process and hope it solves whatever
* issues we may have.
*/
- p = select_bad_process(&points);
+ p = select_bad_process(&points, NULL);
if (PTR_ERR(p) == -1UL)
goto out;
@@ -464,3 +474,27 @@ out:
if (!test_thread_flag(TIF_MEMDIE))
schedule_timeout_uninterruptible(1);
}
+
+#ifdef CONFIG_RSS_CONTAINER
+void container_out_of_memory(struct rss_container *rss)
+{
+ unsigned long points = 0;
+ struct task_struct *p;
+
+ container_lock();
+ read_lock(&tasklist_lock);
+retry:
+ p = select_bad_process(&points, rss);
+ if (PTR_ERR(p) == -1UL)
+ goto out;
+
+ if (!p)
+ p = current;
+
+ if (oom_kill_process(p, points, "Container out of memory"))
+ goto retry;
+out:
+ read_unlock(&tasklist_lock);
+ container_unlock();
+}
+#endif
diff -upr linux-2.6.20.orig/mm/vmscan.c linux-2.6.20-0/mm/vmscan.c
--- linux-2.6.20.orig/mm/vmscan.c 2007-02-04 21:44:54.000000000 +0300
+++ linux-2.6.20-0/mm/vmscan.c 2007-03-06 13:33:28.000000000 +0300
@@ -45,6 +45,8 @@
#include "internal.h"
+#include <linux/rss_container.h>
+
struct scan_control {
/* Incremented by the number of inactive pages that were scanned */
unsigned long nr_scanned;
@@ -1097,6 +1099,194 @@ out:
return ret;
}
+#ifdef CONFIG_RSS_CONTAINER
+/*
+ * These are containers' inactive and active pages shrinkers.
+ * Thes works like shrink_inactive_list() and shrink_active_list()
+ *
+ * Two main differences is that container_isolate_pages() is used to isolate
+ * pages, and that reclaim_mapped is considered to be 1 as hitting BC
+ * limit implies we have to shrink _mapped_ pages
+ */
+static unsigned long container_shrink_pages_inactive(unsigned long max_scan,
+ struct rss_container *rss, struct scan_control *sc)
+{
+ LIST_HEAD(page_list);
+ unsigned long nr_scanned = 0;
+ unsigned long nr_reclaimed = 0;
+
+ do {
+ struct page *page;
+ unsigned long nr_taken;
+ unsigned long nr_scan;
+ struct zone *z;
+
+ nr_taken = container_isolate_pages(sc->swap_cluster_max, rss,
+ &page_list, 0, &nr_scan);
+
+ nr_scanned += nr_scan;
+ nr_reclaimed += shrink_page_list(&page_list, sc);
+ if (nr_taken == 0)
+ goto done;
+
+ while (!list_empty(&page_list)) {
+ page = lru_to_page(&page_list);
+ z = page_zone(page);
+
+ spin_lock_irq(&z->lru_lock);
+ VM_BUG_ON(PageLRU(page));
+ SetPageLRU(page);
+ list_del(&page->lru);
+ if (PageActive(page))
+ add_page_to_active_list(z, page);
+ else
+ add_page_to_inactive_list(z, page);
+ spin_unlock_irq(&z->lru_lock);
+
+ put_page(page);
+ }
+ } while (nr_scanned < max_scan);
+done:
+ return nr_reclaimed;
+}
+
+static void container_shrink_pages_active(unsigned long nr_pages,
+ struct rss_container *rss, struct scan_control *sc)
+{
+ LIST_HEAD(l_hold);
+ LIST_HEAD(l_inactive);
+ LIST_HEAD(l_active);
+ struct page *page;
+ unsigned long nr_scanned;
+ unsigned long nr_deactivated = 0;
+ struct zone *z;
+
+ container_isolate_pages(nr_pages, rss, &l_hold, 1, &nr_scanned);
+
+ while (!list_empty(&l_hold)) {
+ cond_resched();
+ page = lru_to_page(&l_hold);
+ list_del(&page->lru);
+ if (page_mapped(page)) {
+ if ((total_swap_pages == 0 && PageAnon(page)) ||
+ page_referenced(page, 0)) {
+ list_add(&page->lru, &l_active);
+ continue;
+ }
+ }
+ nr_deactivated++;
+ list_add(&page->lru, &l_inactive);
+ }
+
+ while (!list_empty(&l_inactive)) {
+ page = lru_to_page(&l_inactive);
+ z = page_zone(page);
+
+ spin_lock_irq(&z->lru_lock);
+ VM_BUG_ON(PageLRU(page));
+ SetPageLRU(page);
+ VM_BUG_ON(!PageActive(page));
+ ClearPageActive(page);
+
+ list_move(&page->lru, &z->inactive_list);
+ z->nr_inactive++;
+ spin_unlock_irq(&z->lru_lock);
+
+ put_page(page);
+ }
+
+ while (!list_empty(&l_active)) {
+ page = lru_to_page(&l_active);
+ z = page_zone(page);
+
+ spin_lock_irq(&z->lru_lock);
+ VM_BUG_ON(PageLRU(page));
+ SetPageLRU(page);
+ VM_BUG_ON(!PageActive(page));
+ list_move(&page->lru, &z->active_list);
+ z->nr_active++;
+ spin_unlock_irq(&z->lru_lock);
+
+ put_page(page);
+ }
+}
+
+/*
+ * This is a reworked shrink_zone() routine - it scans active pages firts,
+ * then inactive and returns the number of pages reclaimed
+ */
+static unsigned long container_shrink_pages(int priority,
+ struct rss_container *rss, struct scan_control *sc)
+{
+ unsigned long nr_pages;
+ unsigned long nr_to_scan;
+ unsigned long nr_reclaimed = 0;
+
+ nr_pages = (container_nr_physpages(rss) >> priority) + 1;
+ if (nr_pages < sc->swap_cluster_max)
+ nr_pages = 0;
+
+ while (nr_pages) {
+ nr_to_scan = min(nr_pages, (unsigned long)sc->swap_cluster_max);
+ nr_pages -= nr_to_scan;
+ container_shrink_pages_active(nr_to_scan, rss, sc);
+ }
+
+ nr_pages = (container_nr_physpages(rss) >> priority) + 1;
+ if (nr_pages < sc->swap_cluster_max)
+ nr_pages = 0;
+
+ while (nr_pages) {
+ nr_to_scan = min(nr_pages, (unsigned long)sc->swap_cluster_max);
+ nr_pages -= nr_to_scan;
+ nr_reclaimed += container_shrink_pages_inactive(nr_to_scan, rss, sc);
+ }
+
+ throttle_vm_writeout();
+ return nr_reclaimed;
+}
+
+/*
+ * This functions works like try_to_free_pages() - it tries
+ * to shrink bc's pages with increasing priority
+ */
+unsigned long container_try_to_free_pages(struct rss_container *rss)
+{
+ int priority;
+ int ret = 0;
+ unsigned long total_scanned = 0;
+ unsigned long nr_reclaimed = 0;
+ struct scan_control sc = {
+ .gfp_mask = GFP_KERNEL,
+ .may_writepage = !laptop_mode,
+ .swap_cluster_max = SWAP_CLUSTER_MAX,
+ .may_swap = 1,
+ .swappiness = vm_swappiness,
+ };
+
+ for (priority = DEF_PRIORITY; priority >= 0; priority--) {
+ sc.nr_scanned = 0;
+ nr_reclaimed += container_shrink_pages(priority, rss, &sc);
+ total_scanned += sc.nr_scanned;
+ if (nr_reclaimed > 1) {
+ ret = 1;
+ goto out;
+ }
+
+ if (total_scanned > sc.swap_cluster_max +
+ sc.swap_cluster_max / 2) {
+ wakeup_pdflush(laptop_mode ? 0 : total_scanned);
+ sc.may_writepage = 1;
+ }
+
+ if (sc.nr_scanned && priority < DEF_PRIORITY - 2)
+ congestion_wait(WRITE, HZ/10);
+ }
+out:
+ return ret;
+}
+#endif
+
/*
* For kswapd, balance_pgdat() will work across all this node's zones until
* they are all at pages_high.
next prev parent reply other threads:[~2007-03-06 15:00 UTC|newest]
Thread overview: 129+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-03-06 14:42 [RFC][PATCH 0/7] Resource controllers based on process containers Pavel Emelianov
2007-03-06 14:49 ` [RFC][PATCH 1/7] Resource counters Pavel Emelianov
2007-03-07 4:03 ` Balbir Singh
2007-03-07 7:19 ` Pavel Emelianov
2007-03-09 16:37 ` Herbert Poetzl
2007-03-11 9:01 ` Pavel Emelianov
2007-03-11 19:00 ` Eric W. Biederman
2007-03-12 1:16 ` Herbert Poetzl
2007-03-13 9:09 ` Eric W. Biederman
2007-03-13 9:27 ` Pavel Emelianov
2007-03-13 9:49 ` [Devel] " Kirill Korotaev
2007-03-13 15:21 ` Herbert Poetzl
2007-03-13 15:41 ` Pavel Emelianov
2007-03-13 16:07 ` Srivatsa Vaddagiri
2007-03-14 7:12 ` Pavel Emelianov
2007-03-15 16:51 ` Eric W. Biederman
2007-03-13 16:32 ` Herbert Poetzl
2007-03-06 14:55 ` [RFC][PATCH 2/7] RSS controller core Pavel Emelianov
2007-03-06 22:00 ` Andrew Morton
2007-03-09 16:48 ` Herbert Poetzl
2007-03-11 9:08 ` Pavel Emelianov
2007-03-11 14:32 ` Herbert Poetzl
2007-03-11 15:04 ` Pavel Emelianov
2007-03-12 0:41 ` Herbert Poetzl
2007-03-12 8:31 ` Pavel Emelianov
2007-03-12 9:55 ` Balbir Singh
2007-03-12 23:43 ` Herbert Poetzl
2007-03-13 1:57 ` Balbir Singh
2007-03-13 2:24 ` Srivatsa Vaddagiri
2007-03-13 16:06 ` Herbert Poetzl
2007-03-11 12:26 ` Kirill Korotaev
2007-03-11 12:51 ` Andrew Morton
2007-03-11 15:51 ` Balbir Singh
2007-03-11 19:34 ` Eric W. Biederman
2007-03-12 9:23 ` [Devel] " Kirill Korotaev
2007-03-13 9:26 ` Eric W. Biederman
2007-03-13 15:43 ` Kirill Korotaev
2007-03-12 1:00 ` Herbert Poetzl
2007-03-12 9:02 ` Pavel Emelianov
2007-03-12 21:11 ` Herbert Poetzl
2007-03-13 7:17 ` Pavel Emelianov
2007-03-13 15:05 ` Herbert Poetzl
2007-03-13 15:32 ` Pavel Emelianov
2007-03-13 15:10 ` Kirill Korotaev
2007-03-13 15:11 ` Herbert Poetzl
2007-03-13 15:54 ` Kirill Korotaev
2007-03-12 18:42 ` Dave Hansen
2007-03-12 22:41 ` Herbert Poetzl
2007-03-12 23:02 ` Dave Hansen
2007-03-18 16:58 ` Eric W. Biederman
2007-03-13 6:04 ` Andrew Morton
2007-03-13 10:19 ` [Devel] " Kirill Korotaev
2007-03-13 11:48 ` Andrew Morton
2007-03-13 14:59 ` Herbert Poetzl
2007-03-13 17:05 ` Dave Hansen
2007-03-14 15:38 ` Mel Gorman
2007-03-14 20:42 ` Dave Hansen
2007-03-20 18:57 ` Mel Gorman
2007-03-18 22:44 ` [Devel] " Paul Menage
2007-03-19 17:41 ` Eric W. Biederman
2007-03-13 17:26 ` Dave Hansen
2007-03-13 19:09 ` Alan Cox
2007-03-13 20:28 ` Dave Hansen
2007-03-16 0:55 ` Eric W. Biederman
2007-03-16 16:31 ` Dave Hansen
2007-03-16 18:54 ` Eric W. Biederman
2007-03-16 19:46 ` Dave Hansen
2007-03-18 17:42 ` Eric W. Biederman
2007-03-19 15:48 ` Herbert Poetzl
2007-03-20 16:15 ` controlling mmap()'d vs read/write() pages Dave Hansen
2007-03-20 21:19 ` Eric W. Biederman
2007-03-23 0:51 ` Herbert Poetzl
2007-03-23 5:57 ` Nick Piggin
2007-03-23 10:12 ` Eric W. Biederman
2007-03-23 10:47 ` Nick Piggin
2007-03-23 12:21 ` Eric W. Biederman
2007-03-28 7:33 ` Nick Piggin
2007-03-23 16:41 ` Dave Hansen
2007-03-23 18:16 ` Herbert Poetzl
2007-03-28 9:18 ` Balbir Singh
2007-03-14 16:47 ` [RFC][PATCH 2/7] RSS controller core Mel Gorman
2007-03-07 5:37 ` Balbir Singh
2007-03-07 7:27 ` Pavel Emelianov
2007-03-06 14:58 ` [RFC][PATCH 3/7] Data structures changes for RSS accounting Pavel Emelianov
2007-03-11 19:13 ` Eric W. Biederman
2007-03-12 16:16 ` Kirill Korotaev
2007-03-12 16:48 ` Dave Hansen
2007-03-12 17:19 ` Pavel Emelianov
2007-03-12 17:27 ` Dave Hansen
2007-03-13 7:10 ` Pavel Emelianov
2007-03-12 17:21 ` Balbir Singh
2007-03-06 15:00 ` [RFC][PATCH 4/7] RSS accounting hooks over the code Pavel Emelianov
2007-03-11 19:14 ` Eric W. Biederman
2007-03-12 16:23 ` Kirill Korotaev
2007-03-12 16:50 ` Dave Hansen
2007-03-12 17:07 ` Kirill Korotaev
2007-03-12 17:33 ` Dave Hansen
2007-03-13 9:43 ` Eric W. Biederman
2007-03-12 23:54 ` Herbert Poetzl
2007-03-13 9:58 ` Eric W. Biederman
2007-03-13 10:25 ` Nick Piggin
2007-03-13 16:01 ` Eric W. Biederman
2007-03-14 3:51 ` Nick Piggin
2007-03-14 6:42 ` Balbir Singh
2007-03-14 6:57 ` Nick Piggin
2007-03-14 7:48 ` Balbir Singh
2007-03-14 13:25 ` Vaidyanathan Srinivasan
2007-03-14 13:49 ` Nick Piggin
2007-03-14 14:43 ` Vaidyanathan Srinivasan
2007-03-14 16:16 ` Kirill Korotaev
2007-03-15 5:01 ` Nick Piggin
2007-03-15 5:44 ` Balbir Singh
2007-03-28 20:15 ` Ethan Solomita
2007-03-14 15:37 ` Cedric Le Goater
2007-03-14 15:45 ` Pavel Emelianov
2007-03-06 15:03 ` Pavel Emelianov [this message]
2007-03-09 21:21 ` [RFC][PATCH 5/7] Per-container OOM killer and page reclamation Balbir Singh
2007-03-11 8:41 ` Pavel Emelianov
2007-03-06 15:04 ` [RFC][PATCH 6/7] Account for the number of tasks within container Pavel Emelianov
2007-03-07 2:00 ` Paul Menage
2007-03-07 7:13 ` Pavel Emelianov
2007-03-08 13:49 ` Paul Menage
2007-03-11 8:36 ` Pavel Emelianov
2007-03-06 15:07 ` [RFC][PATCH 7/7] Account for the number of files opened " Pavel Emelianov
2007-03-07 2:02 ` [RFC][PATCH 0/7] Resource controllers based on process containers Paul Menage
2007-03-07 7:30 ` Pavel Emelianov
2007-03-07 6:52 ` Balbir Singh
2007-03-07 7:32 ` Pavel Emelianov
2007-03-07 9:43 ` Kirill Korotaev
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=45ED82B9.8090306@sw.ru \
--to=xemul@sw.ru \
--cc=akpm@osdl.org \
--cc=balbir@in.ibm.com \
--cc=containers@lists.osdl.org \
--cc=dev@sw.ru \
--cc=devel@openvz.org \
--cc=linux-kernel@vger.kernel.org \
--cc=menage@google.com \
--cc=vatsa@in.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).