The patch titled
Subject: fs, mm: account buffer_head to kmemcg
has been added to the -mm tree. Its filename is
fs-mm-account-buffer_head-to-kmemcg.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/fs-mm-account-buffer_head-to-kmemcg.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/fs-mm-account-buffer_head-to-kmemcg.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Shakeel Butt <shakeelb@xxxxxxxxxx>
Subject: fs, mm: account buffer_head to kmemcg
The buffer_head can consume a significant amount of system memory and is
directly related to the amount of page cache. In our production
environment we have observed that a lot of machines are spending a
significant amount of memory as buffer_head and can not be left as system
memory overhead.
Charging buffer_head is not as simple as adding __GFP_ACCOUNT to the
allocation. The buffer_heads can be allocated in a memcg different from
the memcg of the page for which buffer_heads are being allocated. One
concrete example is memory reclaim. The reclaim can trigger I/O of pages
of any memcg on the system. So, the right way to charge buffer_head is to
extract the memcg from the page for which buffer_heads are being allocated
and then use targeted memcg charging API.
Link: http://lkml.kernel.org/r/20180627191250.209150-3-shakeelb@xxxxxxxxxx
Signed-off-by: Shakeel Butt <shakeelb@xxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxxxx>
Cc: Jan Kara <jack@xxxxxxx>
Cc: Amir Goldstein <amir73il@xxxxxxxxx>
Cc: Greg Thelen <gthelen@xxxxxxxxxx>
Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: Vladimir Davydov <vdavydov.dev@xxxxxxxxx>
Cc: Roman Gushchin <guro@xxxxxx>
Cc: Alexander Viro <viro@xxxxxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
diff -puN fs/buffer.c~fs-mm-account-buffer_head-to-kmemcg fs/buffer.c
--- a/fs/buffer.c~fs-mm-account-buffer_head-to-kmemcg
+++ a/fs/buffer.c
@@ -45,6 +45,7 @@
#include <linux/mpage.h>
#include <linux/bit_spinlock.h>
#include <linux/pagevec.h>
+#include <linux/sched/mm.h>
#include <trace/events/block.h>
static int fsync_buffers_list(spinlock_t *lock, struct list_head *list);
@@ -815,10 +816,14 @@ struct buffer_head *alloc_page_buffers(s
struct buffer_head *bh, *head;
gfp_t gfp = GFP_NOFS;
long offset;
+ struct mem_cgroup *memcg;
if (retry)
gfp |= __GFP_NOFAIL;
+ memcg = get_mem_cgroup_from_page(page);
+ memalloc_use_memcg(memcg);
+
head = NULL;
offset = PAGE_SIZE;
while ((offset -= size) >= 0) {
@@ -835,6 +840,9 @@ struct buffer_head *alloc_page_buffers(s
/* Link the buffer to its page */
set_bh_page(bh, page, offset);
}
+out:
+ memalloc_unuse_memcg();
+ mem_cgroup_put(memcg);
return head;
/*
* In case anything failed, we just free everything we got.
@@ -848,7 +856,7 @@ no_grow:
} while (head);
}
- return NULL;
+ goto out;
}
EXPORT_SYMBOL_GPL(alloc_page_buffers);
diff -puN include/linux/memcontrol.h~fs-mm-account-buffer_head-to-kmemcg include/linux/memcontrol.h
--- a/include/linux/memcontrol.h~fs-mm-account-buffer_head-to-kmemcg
+++ a/include/linux/memcontrol.h
@@ -372,6 +372,8 @@ struct mem_cgroup *mem_cgroup_from_task(
struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm);
+struct mem_cgroup *get_mem_cgroup_from_page(struct page *page);
+
static inline
struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css){
return css ? container_of(css, struct mem_cgroup, css) : NULL;
@@ -849,6 +851,11 @@ static inline struct mem_cgroup *get_mem
{
return NULL;
}
+
+static inline struct mem_cgroup *get_mem_cgroup_from_page(struct page *page)
+{
+ return NULL;
+}
static inline void mem_cgroup_put(struct mem_cgroup *memcg)
{
diff -puN mm/memcontrol.c~fs-mm-account-buffer_head-to-kmemcg mm/memcontrol.c
--- a/mm/memcontrol.c~fs-mm-account-buffer_head-to-kmemcg
+++ a/mm/memcontrol.c
@@ -714,6 +714,28 @@ struct mem_cgroup *get_mem_cgroup_from_m
EXPORT_SYMBOL(get_mem_cgroup_from_mm);
/**
+ * get_mem_cgroup_from_page: Obtain a reference on given page's memcg.
+ * @page: page from which memcg should be extracted.
+ *
+ * Obtain a reference on page->memcg and returns it if successful. Otherwise
+ * root_mem_cgroup is returned.
+ */
+struct mem_cgroup *get_mem_cgroup_from_page(struct page *page)
+{
+ struct mem_cgroup *memcg = page->mem_cgroup;
+
+ if (mem_cgroup_disabled())
+ return NULL;
+
+ rcu_read_lock();
+ if (!memcg || !css_tryget_online(&memcg->css))
+ memcg = root_mem_cgroup;
+ rcu_read_unlock();
+ return memcg;
+}
+EXPORT_SYMBOL(get_mem_cgroup_from_page);
+
+/**
* If current->active_memcg is non-NULL, do not fallback to current->mm->memcg.
*/
static __always_inline struct mem_cgroup *get_mem_cgroup_from_current(void)
_
Patches currently in -mm which might be from shakeelb@xxxxxxxxxx are
slub-track-number-of-slabs-irrespective-of-config_slub_debug.patch
fs-fsnotify-account-fsnotify-metadata-to-kmemcg.patch
fs-mm-account-buffer_head-to-kmemcg.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
