Hi everyone, Here are new releases of bio-cgroup. Changes from the previous version are as follows: - Accurate dirty-page tracking Support migrating pages between bio-cgroups with minimum overhead, but I think such a situation is quite rare. - Fix a bug of swapcache page handling Sometimes, "bad page state" is occurred since the memory controller has temporarily changed the swapcache page handling. The following is the list of patches: [PATCH 0/5] bio-cgroup: Introduction [PATCH 1/5] bio-cgroup: Split the cgroup memory subsystem into two parts [PATCH 2/5] bio-cgroup: Remove a lot of "#ifdef"s [PATCH 3/5] bio-cgroup: Implement the bio-cgroup [PATCH 4/5] bio-cgroup: Add a cgroup support to dm-ioband [PATCH 5/5] bio-cgroup: Dirty page tracking You have to apply the patch dm-ioband v1.5.0 before applying this series of patches. The dm-ioband patch can be found at: http://people.valinux.co.jp/~ryov/dm-ioband/ And you have to select the following config options when compiling kernel: CONFIG_CGROUPS=y CONFIG_CGROUP_BIO=y And I recommend you should also select the options for cgroup memory subsystem, because it makes it possible to give some I/O bandwidth and some memory to a certain cgroup to control delayed write requests and the processes in the cgroup will be able to make pages dirty only inside the cgroup even when the given bandwidth is narrow. CONFIG_RESOURCE_COUNTERS=y CONFIG_CGROUP_MEM_RES_CTLR=y Please see the following site for more information: http://people.valinux.co.jp/~ryov/bio-cgroup/ -------------------------------------------------------- The following shows how to use dm-ioband with cgroups. Please assume that you want make two cgroups, which we call "bio cgroup" here, to track down block I/Os and assign them to ioband device "ioband1". First, mount the bio cgroup filesystem. # mount -t cgroup -o bio none /cgroup/bio Then, make new bio cgroups and put some processes in them. # mkdir /cgroup/bio/bgroup1 # mkdir /cgroup/bio/bgroup2 # echo 1234 > /cgroup/bio/bgroup1/tasks # echo 5678 > /cgroup/bio/bgroup1/tasks Now, check the ID of each bio cgroup which is just created. # cat /cgroup/bio/bgroup1/bio.id 1 # cat /cgroup/bio/bgroup2/bio.id 2 Finally, attach the cgroups to "ioband1" and assign them weights. # dmsetup message ioband1 0 type cgroup # dmsetup message ioband1 0 attach 1 # dmsetup message ioband1 0 attach 2 # dmsetup message ioband1 0 weight 1:30 # dmsetup message ioband1 0 weight 2:60 You can also make use of the dm-ioband administration tool if you want. The tool will be found here: http://people.valinux.co.jp/~kaizuka/dm-ioband/iobandctl/manual.html You can set up the device with the tool as follows. In this case, you don't need to know the IDs of the cgroups. # iobandctl.py group /dev/mapper/ioband1 cgroup /cgroup/bio/bgroup1:30 /cgroup/bio/bgroup2:60 Thanks, Ryo Tsuruta
Ryo Tsuruta
2008-Sep-19 11:01 UTC
[PATCH 1/5] bio-cgroup: Split the cgroup memory subsystem into two parts
This patch splits the cgroup memory subsystem into two parts.
One is for tracking pages to find out the owners. The other is
for controlling how much amount of memory should be assigned to
each cgroup.
With this patch, you can use the page tracking mechanism even if
the memory subsystem is off.
Based on 2.6.27-rc1-mm1
Signed-off-by: Ryo Tsuruta <ryov at valinux.co.jp>
Signed-off-by: Hirokazu Takahashi <taka at valinux.co.jp>
diff -Ndupr linux-2.6.27-rc1-mm1.ioband/include/linux/memcontrol.h
linux-2.6.27-rc1-mm1.cg0/include/linux/memcontrol.h
--- linux-2.6.27-rc1-mm1.ioband/include/linux/memcontrol.h 2008-09-19
10:54:43.000000000 +0900
+++ linux-2.6.27-rc1-mm1.cg0/include/linux/memcontrol.h 2008-09-19
18:50:25.000000000 +0900
@@ -20,12 +20,62 @@
#ifndef _LINUX_MEMCONTROL_H
#define _LINUX_MEMCONTROL_H
+#include <linux/rcupdate.h>
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/bit_spinlock.h>
+
struct mem_cgroup;
struct page_cgroup;
struct page;
struct mm_struct;
+#ifdef CONFIG_CGROUP_PAGE
+/*
+ * We use the lower bit of the page->page_cgroup pointer as a bit spin
+ * lock. We need to ensure that page->page_cgroup is at least two
+ * byte aligned (based on comments from Nick Piggin). But since
+ * bit_spin_lock doesn't actually set that lock bit in a non-debug
+ * uniprocessor kernel, we should avoid setting it here too.
+ */
+#define PAGE_CGROUP_LOCK_BIT 0x0
+#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK)
+#define PAGE_CGROUP_LOCK (1 << PAGE_CGROUP_LOCK_BIT)
+#else
+#define PAGE_CGROUP_LOCK 0x0
+#endif
+
+/*
+ * A page_cgroup page is associated with every page descriptor. The
+ * page_cgroup helps us identify information about the cgroup
+ */
+struct page_cgroup {
#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+ struct list_head lru; /* per cgroup LRU list */
+ struct mem_cgroup *mem_cgroup;
+#endif /* CONFIG_CGROUP_MEM_RES_CTLR */
+ struct page *page;
+ int flags;
+};
+#define PAGE_CGROUP_FLAG_CACHE (0x1) /* charged as cache */
+#define PAGE_CGROUP_FLAG_ACTIVE (0x2) /* page is active in this cgroup */
+#define PAGE_CGROUP_FLAG_FILE (0x4) /* page is file system backed */
+#define PAGE_CGROUP_FLAG_UNEVICTABLE (0x8) /* page is unevictableable */
+
+static inline void lock_page_cgroup(struct page *page)
+{
+ bit_spin_lock(PAGE_CGROUP_LOCK_BIT, &page->page_cgroup);
+}
+
+static inline int try_lock_page_cgroup(struct page *page)
+{
+ return bit_spin_trylock(PAGE_CGROUP_LOCK_BIT, &page->page_cgroup);
+}
+
+static inline void unlock_page_cgroup(struct page *page)
+{
+ bit_spin_unlock(PAGE_CGROUP_LOCK_BIT, &page->page_cgroup);
+}
#define page_reset_bad_cgroup(page) ((page)->page_cgroup = 0)
@@ -34,45 +84,15 @@ extern int mem_cgroup_charge(struct page
gfp_t gfp_mask);
extern int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
gfp_t gfp_mask);
-extern void mem_cgroup_move_lists(struct page *page, enum lru_list lru);
extern void mem_cgroup_uncharge_page(struct page *page);
extern void mem_cgroup_uncharge_cache_page(struct page *page);
-extern int mem_cgroup_shrink_usage(struct mm_struct *mm, gfp_t gfp_mask);
-
-extern unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
- struct list_head *dst,
- unsigned long *scanned, int order,
- int mode, struct zone *z,
- struct mem_cgroup *mem_cont,
- int active, int file);
-extern void mem_cgroup_out_of_memory(struct mem_cgroup *mem, gfp_t gfp_mask);
-int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem);
-
-extern struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p);
-
-#define mm_match_cgroup(mm, cgroup) \
- ((cgroup) == mem_cgroup_from_task((mm)->owner))
extern int
mem_cgroup_prepare_migration(struct page *page, struct page *newpage);
extern void mem_cgroup_end_migration(struct page *page);
+extern void page_cgroup_init(void);
-/*
- * For memory reclaim.
- */
-extern int mem_cgroup_calc_mapped_ratio(struct mem_cgroup *mem);
-extern long mem_cgroup_reclaim_imbalance(struct mem_cgroup *mem);
-
-extern int mem_cgroup_get_reclaim_priority(struct mem_cgroup *mem);
-extern void mem_cgroup_note_reclaim_priority(struct mem_cgroup *mem,
- int priority);
-extern void mem_cgroup_record_reclaim_priority(struct mem_cgroup *mem,
- int priority);
-
-extern long mem_cgroup_calc_reclaim(struct mem_cgroup *mem, struct zone *zone,
- int priority, enum lru_list lru);
-
-#else /* CONFIG_CGROUP_MEM_RES_CTLR */
+#else /* CONFIG_CGROUP_PAGE */
static inline void page_reset_bad_cgroup(struct page *page)
{
}
@@ -102,6 +122,53 @@ static inline void mem_cgroup_uncharge_c
{
}
+static inline int
+mem_cgroup_prepare_migration(struct page *page, struct page *newpage)
+{
+ return 0;
+}
+
+static inline void mem_cgroup_end_migration(struct page *page)
+{
+}
+#endif /* CONFIG_CGROUP_PAGE */
+
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+
+extern void mem_cgroup_move_lists(struct page *page, enum lru_list lru);
+extern int mem_cgroup_shrink_usage(struct mm_struct *mm, gfp_t gfp_mask);
+
+extern unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
+ struct list_head *dst,
+ unsigned long *scanned, int order,
+ int mode, struct zone *z,
+ struct mem_cgroup *mem_cont,
+ int active, int file);
+extern void mem_cgroup_out_of_memory(struct mem_cgroup *mem, gfp_t gfp_mask);
+int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem);
+
+extern struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p);
+
+#define mm_match_cgroup(mm, cgroup) \
+ ((cgroup) == mem_cgroup_from_task((mm)->owner))
+
+/*
+ * For memory reclaim.
+ */
+extern int mem_cgroup_calc_mapped_ratio(struct mem_cgroup *mem);
+extern long mem_cgroup_reclaim_imbalance(struct mem_cgroup *mem);
+
+extern int mem_cgroup_get_reclaim_priority(struct mem_cgroup *mem);
+extern void mem_cgroup_note_reclaim_priority(struct mem_cgroup *mem,
+ int priority);
+extern void mem_cgroup_record_reclaim_priority(struct mem_cgroup *mem,
+ int priority);
+
+extern long mem_cgroup_calc_reclaim(struct mem_cgroup *mem, struct zone *zone,
+ int priority, enum lru_list lru);
+
+#else /* CONFIG_CGROUP_MEM_RES_CTLR */
+
static inline int mem_cgroup_shrink_usage(struct mm_struct *mm, gfp_t gfp_mask)
{
return 0;
@@ -122,16 +189,6 @@ static inline int task_in_mem_cgroup(str
return 1;
}
-static inline int
-mem_cgroup_prepare_migration(struct page *page, struct page *newpage)
-{
- return 0;
-}
-
-static inline void mem_cgroup_end_migration(struct page *page)
-{
-}
-
static inline int mem_cgroup_calc_mapped_ratio(struct mem_cgroup *mem)
{
return 0;
@@ -163,7 +220,8 @@ static inline long mem_cgroup_calc_recla
{
return 0;
}
-#endif /* CONFIG_CGROUP_MEM_CONT */
+
+#endif /* CONFIG_CGROUP_MEM_RES_CTLR */
#endif /* _LINUX_MEMCONTROL_H */
diff -Ndupr linux-2.6.27-rc1-mm1.ioband/include/linux/mm_types.h
linux-2.6.27-rc1-mm1.cg0/include/linux/mm_types.h
--- linux-2.6.27-rc1-mm1.ioband/include/linux/mm_types.h 2008-09-19
10:54:43.000000000 +0900
+++ linux-2.6.27-rc1-mm1.cg0/include/linux/mm_types.h 2008-09-19
18:50:26.000000000 +0900
@@ -92,7 +92,7 @@ struct page {
void *virtual; /* Kernel virtual address (NULL if
not kmapped, ie. highmem) */
#endif /* WANT_PAGE_VIRTUAL */
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+#ifdef CONFIG_CGROUP_PAGE
unsigned long page_cgroup;
#endif
diff -Ndupr linux-2.6.27-rc1-mm1.ioband/init/Kconfig
linux-2.6.27-rc1-mm1.cg0/init/Kconfig
--- linux-2.6.27-rc1-mm1.ioband/init/Kconfig 2008-09-19 10:54:43.000000000 +0900
+++ linux-2.6.27-rc1-mm1.cg0/init/Kconfig 2008-09-19 18:50:26.000000000 +0900
@@ -418,6 +418,10 @@ config CGROUP_MEMRLIMIT_CTLR
memory RSS and Page Cache control. Virtual address space control
is provided by this controller.
+config CGROUP_PAGE
+ def_bool y
+ depends on CGROUP_MEM_RES_CTLR
+
config SYSFS_DEPRECATED
bool
diff -Ndupr linux-2.6.27-rc1-mm1.ioband/mm/Makefile
linux-2.6.27-rc1-mm1.cg0/mm/Makefile
--- linux-2.6.27-rc1-mm1.ioband/mm/Makefile 2008-09-19 10:54:43.000000000 +0900
+++ linux-2.6.27-rc1-mm1.cg0/mm/Makefile 2008-09-19 18:50:26.000000000 +0900
@@ -34,5 +34,5 @@ obj-$(CONFIG_FS_XIP) += filemap_xip.o
obj-$(CONFIG_MIGRATION) += migrate.o
obj-$(CONFIG_SMP) += allocpercpu.o
obj-$(CONFIG_QUICKLIST) += quicklist.o
-obj-$(CONFIG_CGROUP_MEM_RES_CTLR) += memcontrol.o
+obj-$(CONFIG_CGROUP_PAGE) += memcontrol.o
obj-$(CONFIG_CGROUP_MEMRLIMIT_CTLR) += memrlimitcgroup.o
diff -Ndupr linux-2.6.27-rc1-mm1.ioband/mm/memcontrol.c
linux-2.6.27-rc1-mm1.cg0/mm/memcontrol.c
--- linux-2.6.27-rc1-mm1.ioband/mm/memcontrol.c 2008-09-19 10:54:43.000000000
+0900
+++ linux-2.6.27-rc1-mm1.cg0/mm/memcontrol.c 2008-09-19 18:50:26.000000000 +0900
@@ -36,10 +36,25 @@
#include <asm/uaccess.h>
-struct cgroup_subsys mem_cgroup_subsys __read_mostly;
+enum charge_type {
+ MEM_CGROUP_CHARGE_TYPE_CACHE = 0,
+ MEM_CGROUP_CHARGE_TYPE_MAPPED,
+ MEM_CGROUP_CHARGE_TYPE_FORCE, /* used by force_empty */
+};
+
+static void __mem_cgroup_uncharge_common(struct page *, enum charge_type);
+
static struct kmem_cache *page_cgroup_cache __read_mostly;
+
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+struct cgroup_subsys mem_cgroup_subsys __read_mostly;
#define MEM_CGROUP_RECLAIM_RETRIES 5
+static inline int mem_cgroup_disabled(void)
+{
+ return mem_cgroup_subsys.disabled;
+}
+
/*
* Statistics for memory cgroup.
*/
@@ -136,35 +151,6 @@ struct mem_cgroup {
};
static struct mem_cgroup init_mem_cgroup;
-/*
- * We use the lower bit of the page->page_cgroup pointer as a bit spin
- * lock. We need to ensure that page->page_cgroup is at least two
- * byte aligned (based on comments from Nick Piggin). But since
- * bit_spin_lock doesn't actually set that lock bit in a non-debug
- * uniprocessor kernel, we should avoid setting it here too.
- */
-#define PAGE_CGROUP_LOCK_BIT 0x0
-#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK)
-#define PAGE_CGROUP_LOCK (1 << PAGE_CGROUP_LOCK_BIT)
-#else
-#define PAGE_CGROUP_LOCK 0x0
-#endif
-
-/*
- * A page_cgroup page is associated with every page descriptor. The
- * page_cgroup helps us identify information about the cgroup
- */
-struct page_cgroup {
- struct list_head lru; /* per cgroup LRU list */
- struct page *page;
- struct mem_cgroup *mem_cgroup;
- int flags;
-};
-#define PAGE_CGROUP_FLAG_CACHE (0x1) /* charged as cache */
-#define PAGE_CGROUP_FLAG_ACTIVE (0x2) /* page is active in this cgroup */
-#define PAGE_CGROUP_FLAG_FILE (0x4) /* page is file system backed */
-#define PAGE_CGROUP_FLAG_UNEVICTABLE (0x8) /* page is unevictableable */
-
static int page_cgroup_nid(struct page_cgroup *pc)
{
return page_to_nid(pc->page);
@@ -175,12 +161,6 @@ static enum zone_type page_cgroup_zid(st
return page_zonenum(pc->page);
}
-enum charge_type {
- MEM_CGROUP_CHARGE_TYPE_CACHE = 0,
- MEM_CGROUP_CHARGE_TYPE_MAPPED,
- MEM_CGROUP_CHARGE_TYPE_FORCE, /* used by force_empty */
-};
-
/*
* Always modified under lru lock. Then, not necessary to preempt_disable()
*/
@@ -248,37 +228,6 @@ struct mem_cgroup *mem_cgroup_from_task(
struct mem_cgroup, css);
}
-static inline int page_cgroup_locked(struct page *page)
-{
- return bit_spin_is_locked(PAGE_CGROUP_LOCK_BIT, &page->page_cgroup);
-}
-
-static void page_assign_page_cgroup(struct page *page, struct page_cgroup *pc)
-{
- VM_BUG_ON(!page_cgroup_locked(page));
- page->page_cgroup = ((unsigned long)pc | PAGE_CGROUP_LOCK);
-}
-
-struct page_cgroup *page_get_page_cgroup(struct page *page)
-{
- return (struct page_cgroup *) (page->page_cgroup & ~PAGE_CGROUP_LOCK);
-}
-
-static void lock_page_cgroup(struct page *page)
-{
- bit_spin_lock(PAGE_CGROUP_LOCK_BIT, &page->page_cgroup);
-}
-
-static int try_lock_page_cgroup(struct page *page)
-{
- return bit_spin_trylock(PAGE_CGROUP_LOCK_BIT, &page->page_cgroup);
-}
-
-static void unlock_page_cgroup(struct page *page)
-{
- bit_spin_unlock(PAGE_CGROUP_LOCK_BIT, &page->page_cgroup);
-}
-
static void __mem_cgroup_remove_list(struct mem_cgroup_per_zone *mz,
struct page_cgroup *pc)
{
@@ -367,7 +316,7 @@ void mem_cgroup_move_lists(struct page *
struct mem_cgroup_per_zone *mz;
unsigned long flags;
- if (mem_cgroup_subsys.disabled)
+ if (mem_cgroup_disabled())
return;
/*
@@ -506,273 +455,6 @@ unsigned long mem_cgroup_isolate_pages(u
}
/*
- * Charge the memory controller for page usage.
- * Return
- * 0 if the charge was successful
- * < 0 if the cgroup is over its limit
- */
-static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm,
- gfp_t gfp_mask, enum charge_type ctype,
- struct mem_cgroup *memcg)
-{
- struct mem_cgroup *mem;
- struct page_cgroup *pc;
- unsigned long flags;
- unsigned long nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
- struct mem_cgroup_per_zone *mz;
-
- pc = kmem_cache_alloc(page_cgroup_cache, gfp_mask);
- if (unlikely(pc == NULL))
- goto err;
-
- /*
- * We always charge the cgroup the mm_struct belongs to.
- * The mm_struct's mem_cgroup changes on task migration if the
- * thread group leader migrates. It's possible that mm is not
- * set, if so charge the init_mm (happens for pagecache usage).
- */
- if (likely(!memcg)) {
- rcu_read_lock();
- mem = mem_cgroup_from_task(rcu_dereference(mm->owner));
- /*
- * For every charge from the cgroup, increment reference count
- */
- css_get(&mem->css);
- rcu_read_unlock();
- } else {
- mem = memcg;
- css_get(&memcg->css);
- }
-
- while (res_counter_charge(&mem->res, PAGE_SIZE)) {
- if (!(gfp_mask & __GFP_WAIT))
- goto out;
-
- if (try_to_free_mem_cgroup_pages(mem, gfp_mask))
- continue;
-
- /*
- * try_to_free_mem_cgroup_pages() might not give us a full
- * picture of reclaim. Some pages are reclaimed and might be
- * moved to swap cache or just unmapped from the cgroup.
- * Check the limit again to see if the reclaim reduced the
- * current usage of the cgroup before giving up
- */
- if (res_counter_check_under_limit(&mem->res))
- continue;
-
- if (!nr_retries--) {
- mem_cgroup_out_of_memory(mem, gfp_mask);
- goto out;
- }
- }
-
- pc->mem_cgroup = mem;
- pc->page = page;
- /*
- * If a page is accounted as a page cache, insert to inactive list.
- * If anon, insert to active list.
- */
- if (ctype == MEM_CGROUP_CHARGE_TYPE_CACHE) {
- pc->flags = PAGE_CGROUP_FLAG_CACHE;
- if (page_is_file_cache(page))
- pc->flags |= PAGE_CGROUP_FLAG_FILE;
- else
- pc->flags |= PAGE_CGROUP_FLAG_ACTIVE;
- } else
- pc->flags = PAGE_CGROUP_FLAG_ACTIVE;
-
- lock_page_cgroup(page);
- if (unlikely(page_get_page_cgroup(page))) {
- unlock_page_cgroup(page);
- res_counter_uncharge(&mem->res, PAGE_SIZE);
- css_put(&mem->css);
- kmem_cache_free(page_cgroup_cache, pc);
- goto done;
- }
- page_assign_page_cgroup(page, pc);
-
- mz = page_cgroup_zoneinfo(pc);
- spin_lock_irqsave(&mz->lru_lock, flags);
- __mem_cgroup_add_list(mz, pc);
- spin_unlock_irqrestore(&mz->lru_lock, flags);
-
- unlock_page_cgroup(page);
-done:
- return 0;
-out:
- css_put(&mem->css);
- kmem_cache_free(page_cgroup_cache, pc);
-err:
- return -ENOMEM;
-}
-
-int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask)
-{
- if (mem_cgroup_subsys.disabled)
- return 0;
-
- /*
- * If already mapped, we don't have to account.
- * If page cache, page->mapping has address_space.
- * But page->mapping may have out-of-use anon_vma pointer,
- * detecit it by PageAnon() check. newly-mapped-anon's page->mapping
- * is NULL.
- */
- if (page_mapped(page) || (page->mapping && !PageAnon(page)))
- return 0;
- if (unlikely(!mm))
- mm = &init_mm;
- return mem_cgroup_charge_common(page, mm, gfp_mask,
- MEM_CGROUP_CHARGE_TYPE_MAPPED, NULL);
-}
-
-int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
- gfp_t gfp_mask)
-{
- if (mem_cgroup_subsys.disabled)
- return 0;
-
- /*
- * Corner case handling. This is called from add_to_page_cache()
- * in usual. But some FS (shmem) precharges this page before calling it
- * and call add_to_page_cache() with GFP_NOWAIT.
- *
- * For GFP_NOWAIT case, the page may be pre-charged before calling
- * add_to_page_cache(). (See shmem.c) check it here and avoid to call
- * charge twice. (It works but has to pay a bit larger cost.)
- */
- if (!(gfp_mask & __GFP_WAIT)) {
- struct page_cgroup *pc;
-
- lock_page_cgroup(page);
- pc = page_get_page_cgroup(page);
- if (pc) {
- VM_BUG_ON(pc->page != page);
- VM_BUG_ON(!pc->mem_cgroup);
- unlock_page_cgroup(page);
- return 0;
- }
- unlock_page_cgroup(page);
- }
-
- if (unlikely(!mm))
- mm = &init_mm;
-
- return mem_cgroup_charge_common(page, mm, gfp_mask,
- MEM_CGROUP_CHARGE_TYPE_CACHE, NULL);
-}
-
-/*
- * uncharge if !page_mapped(page)
- */
-static void
-__mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
-{
- struct page_cgroup *pc;
- struct mem_cgroup *mem;
- struct mem_cgroup_per_zone *mz;
- unsigned long flags;
-
- if (mem_cgroup_subsys.disabled)
- return;
-
- /*
- * Check if our page_cgroup is valid
- */
- lock_page_cgroup(page);
- pc = page_get_page_cgroup(page);
- if (unlikely(!pc))
- goto unlock;
-
- VM_BUG_ON(pc->page != page);
-
- if ((ctype == MEM_CGROUP_CHARGE_TYPE_MAPPED)
- && ((pc->flags & PAGE_CGROUP_FLAG_CACHE)
- || page_mapped(page)))
- goto unlock;
-
- mz = page_cgroup_zoneinfo(pc);
- spin_lock_irqsave(&mz->lru_lock, flags);
- __mem_cgroup_remove_list(mz, pc);
- spin_unlock_irqrestore(&mz->lru_lock, flags);
-
- page_assign_page_cgroup(page, NULL);
- unlock_page_cgroup(page);
-
- mem = pc->mem_cgroup;
- res_counter_uncharge(&mem->res, PAGE_SIZE);
- css_put(&mem->css);
-
- kmem_cache_free(page_cgroup_cache, pc);
- return;
-unlock:
- unlock_page_cgroup(page);
-}
-
-void mem_cgroup_uncharge_page(struct page *page)
-{
- __mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_MAPPED);
-}
-
-void mem_cgroup_uncharge_cache_page(struct page *page)
-{
- VM_BUG_ON(page_mapped(page));
- __mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_CACHE);
-}
-
-/*
- * Before starting migration, account against new page.
- */
-int mem_cgroup_prepare_migration(struct page *page, struct page *newpage)
-{
- struct page_cgroup *pc;
- struct mem_cgroup *mem = NULL;
- enum charge_type ctype = MEM_CGROUP_CHARGE_TYPE_MAPPED;
- int ret = 0;
-
- if (mem_cgroup_subsys.disabled)
- return 0;
-
- lock_page_cgroup(page);
- pc = page_get_page_cgroup(page);
- if (pc) {
- mem = pc->mem_cgroup;
- css_get(&mem->css);
- if (pc->flags & PAGE_CGROUP_FLAG_CACHE)
- ctype = MEM_CGROUP_CHARGE_TYPE_CACHE;
- }
- unlock_page_cgroup(page);
- if (mem) {
- ret = mem_cgroup_charge_common(newpage, NULL, GFP_KERNEL,
- ctype, mem);
- css_put(&mem->css);
- }
- return ret;
-}
-
-/* remove redundant charge if migration failed*/
-void mem_cgroup_end_migration(struct page *newpage)
-{
- /*
- * At success, page->mapping is not NULL.
- * special rollback care is necessary when
- * 1. at migration failure. (newpage->mapping is cleared in this case)
- * 2. the newpage was moved but not remapped again because the task
- * exits and the newpage is obsolete. In this case, the new page
- * may be a swapcache. So, we just call mem_cgroup_uncharge_page()
- * always for avoiding mess. The page_cgroup will be removed if
- * unnecessary. File cache pages is still on radix-tree. Don't
- * care it.
- */
- if (!newpage->mapping)
- __mem_cgroup_uncharge_common(newpage,
- MEM_CGROUP_CHARGE_TYPE_FORCE);
- else if (PageAnon(newpage))
- mem_cgroup_uncharge_page(newpage);
-}
-
-/*
* A call to try to shrink memory usage under specified resource controller.
* This is typically used for page reclaiming for shmem for reducing side
* effect of page allocation from shmem, which is used by some mem_cgroup.
@@ -783,7 +465,7 @@ int mem_cgroup_shrink_usage(struct mm_st
int progress = 0;
int retry = MEM_CGROUP_RECLAIM_RETRIES;
- if (mem_cgroup_subsys.disabled)
+ if (mem_cgroup_disabled())
return 0;
rcu_read_lock();
@@ -1104,7 +786,7 @@ mem_cgroup_create(struct cgroup_subsys *
if (unlikely((cont->parent) == NULL)) {
mem = &init_mem_cgroup;
- page_cgroup_cache = KMEM_CACHE(page_cgroup, SLAB_PANIC);
+ page_cgroup_init();
} else {
mem = mem_cgroup_alloc();
if (!mem)
@@ -1188,3 +870,324 @@ struct cgroup_subsys mem_cgroup_subsys .attach =
mem_cgroup_move_task,
.early_init = 0,
};
+
+#else /* CONFIG_CGROUP_MEM_RES_CTLR */
+
+static inline int mem_cgroup_disabled(void)
+{
+ return 1;
+}
+#endif /* CONFIG_CGROUP_MEM_RES_CTLR */
+
+static inline int page_cgroup_locked(struct page *page)
+{
+ return bit_spin_is_locked(PAGE_CGROUP_LOCK_BIT, &page->page_cgroup);
+}
+
+static void page_assign_page_cgroup(struct page *page, struct page_cgroup *pc)
+{
+ VM_BUG_ON(!page_cgroup_locked(page));
+ page->page_cgroup = ((unsigned long)pc | PAGE_CGROUP_LOCK);
+}
+
+struct page_cgroup *page_get_page_cgroup(struct page *page)
+{
+ return (struct page_cgroup *) (page->page_cgroup & ~PAGE_CGROUP_LOCK);
+}
+
+/*
+ * Charge the memory controller for page usage.
+ * Return
+ * 0 if the charge was successful
+ * < 0 if the cgroup is over its limit
+ */
+static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm,
+ gfp_t gfp_mask, enum charge_type ctype,
+ struct mem_cgroup *memcg)
+{
+ struct page_cgroup *pc;
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+ struct mem_cgroup *mem;
+ unsigned long flags;
+ unsigned long nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
+ struct mem_cgroup_per_zone *mz;
+#endif /* CONFIG_CGROUP_MEM_RES_CTLR */
+
+ pc = kmem_cache_alloc(page_cgroup_cache, gfp_mask);
+ if (unlikely(pc == NULL))
+ goto err;
+
+ /*
+ * We always charge the cgroup the mm_struct belongs to.
+ * The mm_struct's mem_cgroup changes on task migration if the
+ * thread group leader migrates. It's possible that mm is not
+ * set, if so charge the init_mm (happens for pagecache usage).
+ */
+ if (likely(!memcg)) {
+ rcu_read_lock();
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+ mem = mem_cgroup_from_task(rcu_dereference(mm->owner));
+ /*
+ * For every charge from the cgroup, increment reference count
+ */
+ css_get(&mem->css);
+#endif /* CONFIG_CGROUP_MEM_RES_CTLR */
+ rcu_read_unlock();
+ } else {
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+ mem = memcg;
+ css_get(&memcg->css);
+#endif /* CONFIG_CGROUP_MEM_RES_CTLR */
+ }
+
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+ while (res_counter_charge(&mem->res, PAGE_SIZE)) {
+ if (!(gfp_mask & __GFP_WAIT))
+ goto out;
+
+ if (try_to_free_mem_cgroup_pages(mem, gfp_mask))
+ continue;
+
+ /*
+ * try_to_free_mem_cgroup_pages() might not give us a full
+ * picture of reclaim. Some pages are reclaimed and might be
+ * moved to swap cache or just unmapped from the cgroup.
+ * Check the limit again to see if the reclaim reduced the
+ * current usage of the cgroup before giving up
+ */
+ if (res_counter_check_under_limit(&mem->res))
+ continue;
+
+ if (!nr_retries--) {
+ mem_cgroup_out_of_memory(mem, gfp_mask);
+ goto out;
+ }
+ }
+ pc->mem_cgroup = mem;
+#endif /* CONFIG_CGROUP_MEM_RES_CTLR */
+
+ pc->page = page;
+ /*
+ * If a page is accounted as a page cache, insert to inactive list.
+ * If anon, insert to active list.
+ */
+ if (ctype == MEM_CGROUP_CHARGE_TYPE_CACHE) {
+ pc->flags = PAGE_CGROUP_FLAG_CACHE;
+ if (page_is_file_cache(page))
+ pc->flags |= PAGE_CGROUP_FLAG_FILE;
+ else
+ pc->flags |= PAGE_CGROUP_FLAG_ACTIVE;
+ } else
+ pc->flags = PAGE_CGROUP_FLAG_ACTIVE;
+
+ lock_page_cgroup(page);
+ if (unlikely(page_get_page_cgroup(page))) {
+ unlock_page_cgroup(page);
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+ res_counter_uncharge(&mem->res, PAGE_SIZE);
+ css_put(&mem->css);
+#endif /* CONFIG_CGROUP_MEM_RES_CTLR */
+ kmem_cache_free(page_cgroup_cache, pc);
+ goto done;
+ }
+ page_assign_page_cgroup(page, pc);
+
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+ mz = page_cgroup_zoneinfo(pc);
+ spin_lock_irqsave(&mz->lru_lock, flags);
+ __mem_cgroup_add_list(mz, pc);
+ spin_unlock_irqrestore(&mz->lru_lock, flags);
+#endif /* CONFIG_CGROUP_MEM_RES_CTLR */
+
+ unlock_page_cgroup(page);
+done:
+ return 0;
+out:
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+ css_put(&mem->css);
+#endif /* CONFIG_CGROUP_MEM_RES_CTLR */
+ kmem_cache_free(page_cgroup_cache, pc);
+err:
+ return -ENOMEM;
+}
+
+int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask)
+{
+ if (mem_cgroup_disabled())
+ return 0;
+
+ /*
+ * If already mapped, we don't have to account.
+ * If page cache, page->mapping has address_space.
+ * But page->mapping may have out-of-use anon_vma pointer,
+ * detecit it by PageAnon() check. newly-mapped-anon's page->mapping
+ * is NULL.
+ */
+ if (page_mapped(page) || (page->mapping && !PageAnon(page)))
+ return 0;
+ if (unlikely(!mm))
+ mm = &init_mm;
+ return mem_cgroup_charge_common(page, mm, gfp_mask,
+ MEM_CGROUP_CHARGE_TYPE_MAPPED, NULL);
+}
+
+int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
+ gfp_t gfp_mask)
+{
+ if (mem_cgroup_disabled())
+ return 0;
+
+ /*
+ * Corner case handling. This is called from add_to_page_cache()
+ * in usual. But some FS (shmem) precharges this page before calling it
+ * and call add_to_page_cache() with GFP_NOWAIT.
+ *
+ * For GFP_NOWAIT case, the page may be pre-charged before calling
+ * add_to_page_cache(). (See shmem.c) check it here and avoid to call
+ * charge twice. (It works but has to pay a bit larger cost.)
+ */
+ if (!(gfp_mask & __GFP_WAIT)) {
+ struct page_cgroup *pc;
+
+ lock_page_cgroup(page);
+ pc = page_get_page_cgroup(page);
+ if (pc) {
+ VM_BUG_ON(pc->page != page);
+ VM_BUG_ON(!pc->mem_cgroup);
+ unlock_page_cgroup(page);
+ return 0;
+ }
+ unlock_page_cgroup(page);
+ }
+
+ if (unlikely(!mm))
+ mm = &init_mm;
+
+ return mem_cgroup_charge_common(page, mm, gfp_mask,
+ MEM_CGROUP_CHARGE_TYPE_CACHE, NULL);
+}
+
+/*
+ * uncharge if !page_mapped(page)
+ */
+static void
+__mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
+{
+ struct page_cgroup *pc;
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+ struct mem_cgroup *mem;
+ struct mem_cgroup_per_zone *mz;
+ unsigned long flags;
+#endif /* CONFIG_CGROUP_MEM_RES_CTLR */
+
+ if (mem_cgroup_disabled())
+ return;
+
+ /*
+ * Check if our page_cgroup is valid
+ */
+ lock_page_cgroup(page);
+ pc = page_get_page_cgroup(page);
+ if (unlikely(!pc))
+ goto unlock;
+
+ VM_BUG_ON(pc->page != page);
+
+ if ((ctype == MEM_CGROUP_CHARGE_TYPE_MAPPED)
+ && ((pc->flags & PAGE_CGROUP_FLAG_CACHE)
+ || page_mapped(page)))
+ goto unlock;
+
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+ mz = page_cgroup_zoneinfo(pc);
+ spin_lock_irqsave(&mz->lru_lock, flags);
+ __mem_cgroup_remove_list(mz, pc);
+ spin_unlock_irqrestore(&mz->lru_lock, flags);
+#endif /* CONFIG_CGROUP_MEM_RES_CTLR */
+
+ page_assign_page_cgroup(page, NULL);
+ unlock_page_cgroup(page);
+
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+ mem = pc->mem_cgroup;
+ res_counter_uncharge(&mem->res, PAGE_SIZE);
+ css_put(&mem->css);
+#endif /* CONFIG_CGROUP_MEM_RES_CTLR */
+
+ kmem_cache_free(page_cgroup_cache, pc);
+ return;
+unlock:
+ unlock_page_cgroup(page);
+}
+
+void mem_cgroup_uncharge_page(struct page *page)
+{
+ __mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_MAPPED);
+}
+
+void mem_cgroup_uncharge_cache_page(struct page *page)
+{
+ VM_BUG_ON(page_mapped(page));
+ __mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_CACHE);
+}
+
+/*
+ * Before starting migration, account against new page.
+ */
+int mem_cgroup_prepare_migration(struct page *page, struct page *newpage)
+{
+ struct page_cgroup *pc;
+ struct mem_cgroup *mem = NULL;
+ enum charge_type ctype = MEM_CGROUP_CHARGE_TYPE_MAPPED;
+ int ret = 0;
+
+ if (mem_cgroup_disabled())
+ return 0;
+
+ lock_page_cgroup(page);
+ pc = page_get_page_cgroup(page);
+ if (pc) {
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+ mem = pc->mem_cgroup;
+ css_get(&mem->css);
+#endif /* CONFIG_CGROUP_MEM_RES_CTLR */
+ if (pc->flags & PAGE_CGROUP_FLAG_CACHE)
+ ctype = MEM_CGROUP_CHARGE_TYPE_CACHE;
+ }
+ unlock_page_cgroup(page);
+ if (mem) {
+ ret = mem_cgroup_charge_common(newpage, NULL, GFP_KERNEL,
+ ctype, mem);
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+ css_put(&mem->css);
+#endif /* CONFIG_CGROUP_MEM_RES_CTLR */
+ }
+ return ret;
+}
+
+/* remove redundant charge if migration failed*/
+void mem_cgroup_end_migration(struct page *newpage)
+{
+ /*
+ * At success, page->mapping is not NULL.
+ * special rollback care is necessary when
+ * 1. at migration failure. (newpage->mapping is cleared in this case)
+ * 2. the newpage was moved but not remapped again because the task
+ * exits and the newpage is obsolete. In this case, the new page
+ * may be a swapcache. So, we just call mem_cgroup_uncharge_page()
+ * always for avoiding mess. The page_cgroup will be removed if
+ * unnecessary. File cache pages is still on radix-tree. Don't
+ * care it.
+ */
+ if (!newpage->mapping)
+ __mem_cgroup_uncharge_common(newpage,
+ MEM_CGROUP_CHARGE_TYPE_FORCE);
+ else if (PageAnon(newpage))
+ mem_cgroup_uncharge_page(newpage);
+}
+
+void page_cgroup_init()
+{
+ if (!page_cgroup_cache)
+ page_cgroup_cache = KMEM_CACHE(page_cgroup, SLAB_PANIC);
+}
Hi,> Hi everyone, > > Here are new releases of bio-cgroup. > Changes from the previous version are as follows: > > - Accurate dirty-page tracking > Support migrating pages between bio-cgroups with minimum overhead,I'm the one implementing this code. The implementation isn't finished yet that this this code can't handle mmapped file pages correctly. Actually, the same problem goes with the task I/O accounting mechanism since the two of them are using the same hook This happens when starting to free pages under memory pressure. Dirty bit of a pte will be moved into PG_Dirty flag of the associated page. This can be done in another process context, while the hook try to charge this operation to the current process.> but I think such a situation is quite rare.I implemented it though, I don't think this case often happens since it's not normal that several processes try to write the same block of a file. Thanks, Hirokazu Takahashi.