From: Paul Menage <menage@google.com>
To: akpm@linuxfoundation.org, balbir@linux.vnet.ibm.com,
"Serge E. Hallyn" <serue@us.ibm.com>,
Cedric Le Goater <clg@fr.ibm.com>,
"Eric W. Biederman" <ebiederm@xmission.com>,
Pavel Emelianov <xemul@openvz.org>,
David Rientjes <rientjes@google.com>,
Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>,
Peter Zijlstra <a.p.zijlstra@chello.nl>,
pj@sgi.com, containers@lists.osdl.org,
linux-kernel@vger.kernel.org
Subject: [PATCH 31/33] memory controller make page_referenced container aware v7
Date: Mon, 17 Sep 2007 14:03:38 -0700 [thread overview]
Message-ID: <20070917210431.179207000@menage.corp.google.com> (raw)
In-Reply-To: 20070917210307.116234000@menage.corp.google.com
[-- Attachment #1: memory-controller-make-page_referenced-container-aware-v7.patch --]
[-- Type: text/plain, Size: 6744 bytes --]
From: Balbir Singh <balbir@linux.vnet.ibm.com>
(container->cgroup renaming by Paul Menage <menage@google.com>)
Make page_referenced() cgroup aware. Without this patch, page_referenced()
can cause a page to be skipped while reclaiming pages. This patch ensures
that other cgroups do not hold pages in a particular cgroup hostage. It
is required to ensure that shared pages are freed from a cgroup when they
are not actively referenced from the cgroup that brought them in
Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Signed-off-by: Paul Menage <menage@google.com>
---
include/linux/memcontrol.h | 6 ++++++
include/linux/rmap.h | 5 +++--
mm/memcontrol.c | 5 +++++
mm/rmap.c | 30 ++++++++++++++++++++++++------
mm/vmscan.c | 4 ++--
5 files changed, 40 insertions(+), 10 deletions(-)
diff -puN include/linux/memcontrol.h~memory-controller-make-page_referenced-cgroup-aware-v7 include/linux/memcontrol.h
--- a/include/linux/memcontrol.h~memory-controller-make-page_referenced-cgroup-aware-v7
+++ a/include/linux/memcontrol.h
@@ -43,6 +43,7 @@ extern unsigned long mem_cgroup_isola
int active);
extern void mem_cgroup_out_of_memory(struct mem_cgroup *mem);
extern int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm);
+extern struct mem_cgroup *mm_cgroup(struct mm_struct *mm);
static inline void mem_cgroup_uncharge_page(struct page *page)
{
@@ -93,6 +94,11 @@ static inline int mem_cgroup_cache_ch
return 0;
}
+static inline struct mem_cgroup *mm_cgroup(struct mm_struct *mm)
+{
+ return NULL;
+}
+
#endif /* CONFIG_CGROUP_MEM_CONT */
#endif /* _LINUX_MEMCONTROL_H */
diff -puN include/linux/rmap.h~memory-controller-make-page_referenced-cgroup-aware-v7 include/linux/rmap.h
--- a/include/linux/rmap.h~memory-controller-make-page_referenced-cgroup-aware-v7
+++ a/include/linux/rmap.h
@@ -8,6 +8,7 @@
#include <linux/slab.h>
#include <linux/mm.h>
#include <linux/spinlock.h>
+#include <linux/memcontrol.h>
/*
* The anon_vma heads a list of private "related" vmas, to scan if
@@ -86,7 +87,7 @@ static inline void page_dup_rmap(struct
/*
* Called from mm/vmscan.c to handle paging out
*/
-int page_referenced(struct page *, int is_locked);
+int page_referenced(struct page *, int is_locked, struct mem_cgroup *cnt);
int try_to_unmap(struct page *, int ignore_refs);
/*
@@ -114,7 +115,7 @@ int page_mkclean(struct page *);
#define anon_vma_prepare(vma) (0)
#define anon_vma_link(vma) do {} while (0)
-#define page_referenced(page,l) TestClearPageReferenced(page)
+#define page_referenced(page,l,cnt) TestClearPageReferenced(page)
#define try_to_unmap(page, refs) SWAP_FAIL
static inline int page_mkclean(struct page *page)
diff -puN mm/memcontrol.c~memory-controller-make-page_referenced-cgroup-aware-v7 mm/memcontrol.c
--- a/mm/memcontrol.c~memory-controller-make-page_referenced-cgroup-aware-v7
+++ a/mm/memcontrol.c
@@ -109,6 +109,11 @@ struct mem_cgroup *mem_cgroup_from
struct mem_cgroup, css);
}
+inline struct mem_cgroup *mm_cgroup(struct mm_struct *mm)
+{
+ return rcu_dereference(mm->mem_cgroup);
+}
+
void mm_init_cgroup(struct mm_struct *mm, struct task_struct *p)
{
struct mem_cgroup *mem;
diff -puN mm/rmap.c~memory-controller-make-page_referenced-cgroup-aware-v7 mm/rmap.c
--- a/mm/rmap.c~memory-controller-make-page_referenced-cgroup-aware-v7
+++ a/mm/rmap.c
@@ -299,7 +299,8 @@ out:
return referenced;
}
-static int page_referenced_anon(struct page *page)
+static int page_referenced_anon(struct page *page,
+ struct mem_cgroup *mem_cont)
{
unsigned int mapcount;
struct anon_vma *anon_vma;
@@ -312,6 +313,13 @@ static int page_referenced_anon(struct p
mapcount = page_mapcount(page);
list_for_each_entry(vma, &anon_vma->head, anon_vma_node) {
+ /*
+ * If we are reclaiming on behalf of a cgroup, skip
+ * counting on behalf of references from different
+ * cgroups
+ */
+ if (mem_cont && (mm_cgroup(vma->vm_mm) != mem_cont))
+ continue;
referenced += page_referenced_one(page, vma, &mapcount);
if (!mapcount)
break;
@@ -332,7 +340,8 @@ static int page_referenced_anon(struct p
*
* This function is only called from page_referenced for object-based pages.
*/
-static int page_referenced_file(struct page *page)
+static int page_referenced_file(struct page *page,
+ struct mem_cgroup *mem_cont)
{
unsigned int mapcount;
struct address_space *mapping = page->mapping;
@@ -365,6 +374,13 @@ static int page_referenced_file(struct p
mapcount = page_mapcount(page);
vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
+ /*
+ * If we are reclaiming on behalf of a cgroup, skip
+ * counting on behalf of references from different
+ * cgroups
+ */
+ if (mem_cont && (mm_cgroup(vma->vm_mm) != mem_cont))
+ continue;
if ((vma->vm_flags & (VM_LOCKED|VM_MAYSHARE))
== (VM_LOCKED|VM_MAYSHARE)) {
referenced++;
@@ -387,7 +403,8 @@ static int page_referenced_file(struct p
* Quick test_and_clear_referenced for all mappings to a page,
* returns the number of ptes which referenced the page.
*/
-int page_referenced(struct page *page, int is_locked)
+int page_referenced(struct page *page, int is_locked,
+ struct mem_cgroup *mem_cont)
{
int referenced = 0;
@@ -399,14 +416,15 @@ int page_referenced(struct page *page, i
if (page_mapped(page) && page->mapping) {
if (PageAnon(page))
- referenced += page_referenced_anon(page);
+ referenced += page_referenced_anon(page, mem_cont);
else if (is_locked)
- referenced += page_referenced_file(page);
+ referenced += page_referenced_file(page, mem_cont);
else if (TestSetPageLocked(page))
referenced++;
else {
if (page->mapping)
- referenced += page_referenced_file(page);
+ referenced +=
+ page_referenced_file(page, mem_cont);
unlock_page(page);
}
}
diff -puN mm/vmscan.c~memory-controller-make-page_referenced-cgroup-aware-v7 mm/vmscan.c
--- a/mm/vmscan.c~memory-controller-make-page_referenced-cgroup-aware-v7
+++ a/mm/vmscan.c
@@ -503,7 +503,7 @@ static unsigned long shrink_page_list(st
goto keep_locked;
}
- referenced = page_referenced(page, 1);
+ referenced = page_referenced(page, 1, sc->mem_cgroup);
/* In active use or really unfreeable? Activate it. */
if (sc->order <= PAGE_ALLOC_COSTLY_ORDER &&
referenced && page_mapping_inuse(page))
@@ -1057,7 +1057,7 @@ force_reclaim_mapped:
if (page_mapped(page)) {
if (!reclaim_mapped ||
(total_swap_pages == 0 && PageAnon(page)) ||
- page_referenced(page, 0)) {
+ page_referenced(page, 0, sc->mem_cgroup)) {
list_add(&page->lru, &l_active);
continue;
}
_
--
next prev parent reply other threads:[~2007-09-17 21:12 UTC|newest]
Thread overview: 46+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-09-17 21:03 [PATCH 00/33] Rename "Task Containers" to "Control Groups" Paul Menage
2007-09-17 21:03 ` [PATCH 01/33] task containersv11 basic task container framework Paul Menage
2007-09-17 21:03 ` [PATCH 02/33] task containersv11 basic task container framework fix Paul Menage
2007-09-17 21:03 ` [PATCH 03/33] task containersv11 add tasks file interface Paul Menage
2007-10-03 8:09 ` Paul Jackson
2007-10-03 15:16 ` Paul Menage
2007-10-03 17:51 ` Paul Jackson
2007-10-03 18:15 ` Paul Menage
2007-10-04 2:46 ` Paul Jackson
2007-10-04 2:53 ` Paul Menage
2007-10-04 2:55 ` Paul Jackson
2007-09-17 21:03 ` [PATCH 04/33] task containersv11 add fork exit hooks Paul Menage
2007-09-17 21:03 ` [PATCH 05/33] task containersv11 add container_clone interface Paul Menage
2007-09-17 21:03 ` [PATCH 06/33] task containersv11 add procfs interface Paul Menage
2007-09-17 21:03 ` [PATCH 07/33] task containersv11 shared container subsystem group arrays Paul Menage
2007-09-17 21:03 ` [PATCH 08/33] task containersv11 shared container subsystem group arrays avoid lockdep warning Paul Menage
2007-09-17 21:03 ` [PATCH 09/33] task containersv11 shared container subsystem group arrays include fix Paul Menage
2007-09-17 21:03 ` [PATCH 10/33] task containersv11 automatic userspace notification of idle containers Paul Menage
2007-09-17 21:03 ` [PATCH 11/33] task containersv11 make cpusets a client of containers Paul Menage
2007-10-04 9:53 ` Paul Jackson
2007-10-04 15:16 ` Paul Menage
2007-10-04 17:31 ` Paul Jackson
2007-10-04 17:32 ` Paul Jackson
2007-09-17 21:03 ` [PATCH 12/33] task containersv11 example cpu accounting subsystem Paul Menage
2007-09-17 21:03 ` [PATCH 13/33] task containersv11 simple task container debug info subsystem Paul Menage
2007-09-17 21:03 ` [PATCH 14/33] task-containersv11-basic-task-container-framework-containers-fix-refcount-bug Paul Menage
2007-09-17 21:03 ` [PATCH 15/33] task-containersv11-add-container_clone-interface-cgroups-fix-refcount-bug Paul Menage
2007-09-17 21:03 ` [PATCH 16/33] add containerstats v3 Paul Menage
2007-09-17 21:03 ` [PATCH 17/33] add containerstats v3 fix Paul Menage
2007-09-17 21:03 ` [PATCH 18/33] containers implement namespace tracking subsystem Paul Menage
2007-09-17 21:03 ` [PATCH 19/33] containers implement namespace tracking subsystem fix order of container subsystems in init kconfig Paul Menage
2007-09-17 21:03 ` [PATCH 20/33] memory controller add documentation Paul Menage
2007-09-18 16:53 ` Randy Dunlap
2007-09-17 21:03 ` [PATCH 21/33] memory controller resource counters v7 Paul Menage
2007-09-17 21:03 ` [PATCH 22/33] memory controller resource counters v7 fix Paul Menage
2007-09-17 21:03 ` [PATCH 23/33] memory controller containers setup v7 Paul Menage
2007-09-17 21:03 ` [PATCH 24/33] memory controller accounting " Paul Menage
2007-09-17 21:03 ` [PATCH 25/33] memory controller memory accounting v7 Paul Menage
2007-09-17 21:03 ` [PATCH 26/33] memory controller task migration v7 Paul Menage
2007-09-17 21:03 ` [PATCH 27/33] memory controller add per container lru and reclaim v7 Paul Menage
2007-09-17 21:03 ` [PATCH 28/33] memory controller add per container lru and reclaim v7 fix Paul Menage
2007-09-17 21:03 ` [PATCH 29/33] memory controller oom handling v7 Paul Menage
2007-09-17 21:03 ` [PATCH 30/33] memory controller add switch to control what type of pages to limit v7 Paul Menage
2007-09-17 21:03 ` Paul Menage [this message]
2007-09-17 21:03 ` [PATCH 32/33] memory-controller-improve-user-interface Paul Menage
2007-09-17 21:03 ` [PATCH 33/33] memory-controller-make-charging-gfp-mask-aware Paul Menage
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=20070917210431.179207000@menage.corp.google.com \
--to=menage@google.com \
--cc=a.p.zijlstra@chello.nl \
--cc=akpm@linuxfoundation.org \
--cc=balbir@linux.vnet.ibm.com \
--cc=clg@fr.ibm.com \
--cc=containers@lists.osdl.org \
--cc=ebiederm@xmission.com \
--cc=linux-kernel@vger.kernel.org \
--cc=nickpiggin@yahoo.com.au \
--cc=pj@sgi.com \
--cc=rientjes@google.com \
--cc=serue@us.ibm.com \
--cc=svaidy@linux.vnet.ibm.com \
--cc=xemul@openvz.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