memcg: avoid oom during moving charge

[deliverable/linux.git] / Documentation / cgroups / memory.txt

Memory Resource Controller

NOTE: The Memory Resource Controller has been generically been referred
to as the memory controller in this document. Do not confuse memory controller
used here with the memory controller that is used in hardware.

Salient features

a. Enable control of Anonymous, Page Cache (mapped and unmapped) and
   Swap Cache memory pages.
b. The infrastructure allows easy addition of other types of memory to control
c. Provides *zero overhead* for non memory controller users
d. Provides a double LRU: global memory pressure causes reclaim from the
   global LRU; a cgroup on hitting a limit, reclaims from the per
   cgroup LRU

Benefits and Purpose of the memory controller

The memory controller isolates the memory behaviour of a group of tasks
from the rest of the system. The article on LWN [12] mentions some probable
uses of the memory controller. The memory controller can be used to

a. Isolate an application or a group of applications
   Memory hungry applications can be isolated and limited to a smaller
   amount of memory.
b. Create a cgroup with limited amount of memory, this can be used
   as a good alternative to booting with mem=XXXX.
c. Virtualization solutions can control the amount of memory they want
   to assign to a virtual machine instance.
d. A CD/DVD burner could control the amount of memory used by the
   rest of the system to ensure that burning does not fail due to lack
   of available memory.
e. There are several other use cases, find one or use the controller just
   for fun (to learn and hack on the VM subsystem).

1. History

The memory controller has a long history. A request for comments for the memory
controller was posted by Balbir Singh [1]. At the time the RFC was posted
there were several implementations for memory control. The goal of the
RFC was to build consensus and agreement for the minimal features required
for memory control. The first RSS controller was posted by Balbir Singh[2]
in Feb 2007. Pavel Emelianov [3][4][5] has since posted three versions of the
RSS controller. At OLS, at the resource management BoF, everyone suggested
that we handle both page cache and RSS together. Another request was raised
to allow user space handling of OOM. The current memory controller is
at version 6; it combines both mapped (RSS) and unmapped Page
Cache Control [11].

2. Memory Control

Memory is a unique resource in the sense that it is present in a limited
amount. If a task requires a lot of CPU processing, the task can spread
its processing over a period of hours, days, months or years, but with
memory, the same physical memory needs to be reused to accomplish the task.

The memory controller implementation has been divided into phases. These
are:

1. Memory controller
2. mlock(2) controller
3. Kernel user memory accounting and slab control
4. user mappings length controller

The memory controller is the first controller developed.

2.1. Design

The core of the design is a counter called the res_counter. The res_counter
tracks the current memory usage and limit of the group of processes associated
with the controller. Each cgroup has a memory controller specific data
structure (mem_cgroup) associated with it.

2.2. Accounting

		+--------------------+
		|  mem_cgroup     |
		|  (res_counter)     |
		+--------------------+
		 /            ^      \
		/             |       \
           +---------------+  |        +---------------+
           | mm_struct     |  |....    | mm_struct     |
           |               |  |        |               |
           +---------------+  |        +---------------+
                              |
                              + --------------+
                                              |
           +---------------+           +------+--------+
           | page          +---------->  page_cgroup|
           |               |           |               |
           +---------------+           +---------------+

             (Figure 1: Hierarchy of Accounting)


Figure 1 shows the important aspects of the controller

1. Accounting happens per cgroup
2. Each mm_struct knows about which cgroup it belongs to
3. Each page has a pointer to the page_cgroup, which in turn knows the
   cgroup it belongs to

The accounting is done as follows: mem_cgroup_charge() is invoked to setup
the necessary data structures and check if the cgroup that is being charged
is over its limit. If it is then reclaim is invoked on the cgroup.
More details can be found in the reclaim section of this document.
If everything goes well, a page meta-data-structure called page_cgroup is
allocated and associated with the page.  This routine also adds the page to
the per cgroup LRU.

2.2.1 Accounting details

All mapped anon pages (RSS) and cache pages (Page Cache) are accounted.
(some pages which never be reclaimable and will not be on global LRU
 are not accounted. we just accounts pages under usual vm management.)

RSS pages are accounted at page_fault unless they've already been accounted
for earlier. A file page will be accounted for as Page Cache when it's
inserted into inode (radix-tree). While it's mapped into the page tables of
processes, duplicate accounting is carefully avoided.

A RSS page is unaccounted when it's fully unmapped. A PageCache page is
unaccounted when it's removed from radix-tree.

At page migration, accounting information is kept.

Note: we just account pages-on-lru because our purpose is to control amount
of used pages. not-on-lru pages are tend to be out-of-control from vm view.

2.3 Shared Page Accounting

Shared pages are accounted on the basis of the first touch approach. The
cgroup that first touches a page is accounted for the page. The principle
behind this approach is that a cgroup that aggressively uses a shared
page will eventually get charged for it (once it is uncharged from
the cgroup that brought it in -- this will happen on memory pressure).

Exception: If CONFIG_CGROUP_CGROUP_MEM_RES_CTLR_SWAP is not used..
When you do swapoff and make swapped-out pages of shmem(tmpfs) to
be backed into memory in force, charges for pages are accounted against the
caller of swapoff rather than the users of shmem.


2.4 Swap Extension (CONFIG_CGROUP_MEM_RES_CTLR_SWAP)
Swap Extension allows you to record charge for swap. A swapped-in page is
charged back to original page allocator if possible.

When swap is accounted, following files are added.
 - memory.memsw.usage_in_bytes.
 - memory.memsw.limit_in_bytes.

usage of mem+swap is limited by memsw.limit_in_bytes.

* why 'mem+swap' rather than swap.
The global LRU(kswapd) can swap out arbitrary pages. Swap-out means
to move account from memory to swap...there is no change in usage of
mem+swap. In other words, when we want to limit the usage of swap without
affecting global LRU, mem+swap limit is better than just limiting swap from
OS point of view.

* What happens when a cgroup hits memory.memsw.limit_in_bytes
When a cgroup his memory.memsw.limit_in_bytes, it's useless to do swap-out
in this cgroup. Then, swap-out will not be done by cgroup routine and file
caches are dropped. But as mentioned above, global LRU can do swapout memory
from it for sanity of the system's memory management state. You can't forbid
it by cgroup.

2.5 Reclaim

Each cgroup maintains a per cgroup LRU that consists of an active
and inactive list. When a cgroup goes over its limit, we first try
to reclaim memory from the cgroup so as to make space for the new
pages that the cgroup has touched. If the reclaim is unsuccessful,
an OOM routine is invoked to select and kill the bulkiest task in the
cgroup.

The reclaim algorithm has not been modified for cgroups, except that
pages that are selected for reclaiming come from the per cgroup LRU
list.

NOTE: Reclaim does not work for the root cgroup, since we cannot set any
limits on the root cgroup.

2. Locking

The memory controller uses the following hierarchy

1. zone->lru_lock is used for selecting pages to be isolated
2. mem->per_zone->lru_lock protects the per cgroup LRU (per zone)
3. lock_page_cgroup() is used to protect page->page_cgroup

3. User Interface

0. Configuration

a. Enable CONFIG_CGROUPS
b. Enable CONFIG_RESOURCE_COUNTERS
c. Enable CONFIG_CGROUP_MEM_RES_CTLR

1. Prepare the cgroups
# mkdir -p /cgroups
# mount -t cgroup none /cgroups -o memory

2. Make the new group and move bash into it
# mkdir /cgroups/0
# echo $$ >  /cgroups/0/tasks

Since now we're in the 0 cgroup,
We can alter the memory limit:
# echo 4M > /cgroups/0/memory.limit_in_bytes

NOTE: We can use a suffix (k, K, m, M, g or G) to indicate values in kilo,
mega or gigabytes.
NOTE: We can write "-1" to reset the *.limit_in_bytes(unlimited).
NOTE: We cannot set limits on the root cgroup any more.

# cat /cgroups/0/memory.limit_in_bytes
4194304

NOTE: The interface has now changed to display the usage in bytes
instead of pages

We can check the usage:
# cat /cgroups/0/memory.usage_in_bytes
1216512

A successful write to this file does not guarantee a successful set of
this limit to the value written into the file.  This can be due to a
number of factors, such as rounding up to page boundaries or the total
availability of memory on the system.  The user is required to re-read
this file after a write to guarantee the value committed by the kernel.

# echo 1 > memory.limit_in_bytes
# cat memory.limit_in_bytes
4096

The memory.failcnt field gives the number of times that the cgroup limit was
exceeded.

The memory.stat file gives accounting information. Now, the number of
caches, RSS and Active pages/Inactive pages are shown.

4. Testing

Balbir posted lmbench, AIM9, LTP and vmmstress results [10] and [11].
Apart from that v6 has been tested with several applications and regular
daily use. The controller has also been tested on the PPC64, x86_64 and
UML platforms.

4.1 Troubleshooting

Sometimes a user might find that the application under a cgroup is
terminated. There are several causes for this:

1. The cgroup limit is too low (just too low to do anything useful)
2. The user is using anonymous memory and swap is turned off or too low

A sync followed by echo 1 > /proc/sys/vm/drop_caches will help get rid of
some of the pages cached in the cgroup (page cache pages).

4.2 Task migration

When a task migrates from one cgroup to another, it's charge is not
carried forward by default. The pages allocated from the original cgroup still
remain charged to it, the charge is dropped when the page is freed or
reclaimed.

Note: You can move charges of a task along with task migration. See 8.

4.3 Removing a cgroup

A cgroup can be removed by rmdir, but as discussed in sections 4.1 and 4.2, a
cgroup might have some charge associated with it, even though all
tasks have migrated away from it.
Such charges are freed(at default) or moved to its parent. When moved,
both of RSS and CACHES are moved to parent.
If both of them are busy, rmdir() returns -EBUSY. See 5.1 Also.

Charges recorded in swap information is not updated at removal of cgroup.
Recorded information is discarded and a cgroup which uses swap (swapcache)
will be charged as a new owner of it.


5. Misc. interfaces.

5.1 force_empty
  memory.force_empty interface is provided to make cgroup's memory usage empty.
  You can use this interface only when the cgroup has no tasks.
  When writing anything to this

  # echo 0 > memory.force_empty

  Almost all pages tracked by this memcg will be unmapped and freed. Some of
  pages cannot be freed because it's locked or in-use. Such pages are moved
  to parent and this cgroup will be empty. But this may return -EBUSY in
  some too busy case.

  Typical use case of this interface is that calling this before rmdir().
  Because rmdir() moves all pages to parent, some out-of-use page caches can be
  moved to the parent. If you want to avoid that, force_empty will be useful.

5.2 stat file

memory.stat file includes following statistics

cache		- # of bytes of page cache memory.
rss		- # of bytes of anonymous and swap cache memory.
pgpgin		- # of pages paged in (equivalent to # of charging events).
pgpgout		- # of pages paged out (equivalent to # of uncharging events).
active_anon	- # of bytes of anonymous and  swap cache memory on active
		  lru list.
inactive_anon	- # of bytes of anonymous memory and swap cache memory on
		  inactive lru list.
active_file	- # of bytes of file-backed memory on active lru list.
inactive_file	- # of bytes of file-backed memory on inactive lru list.
unevictable	- # of bytes of memory that cannot be reclaimed (mlocked etc).

The following additional stats are dependent on CONFIG_DEBUG_VM.

inactive_ratio		- VM internal parameter. (see mm/page_alloc.c)
recent_rotated_anon	- VM internal parameter. (see mm/vmscan.c)
recent_rotated_file	- VM internal parameter. (see mm/vmscan.c)
recent_scanned_anon	- VM internal parameter. (see mm/vmscan.c)
recent_scanned_file	- VM internal parameter. (see mm/vmscan.c)

Memo:
	recent_rotated means recent frequency of lru rotation.
	recent_scanned means recent # of scans to lru.
	showing for better debug please see the code for meanings.

Note:
	Only anonymous and swap cache memory is listed as part of 'rss' stat.
	This should not be confused with the true 'resident set size' or the
	amount of physical memory used by the cgroup. Per-cgroup rss
	accounting is not done yet.

5.3 swappiness
  Similar to /proc/sys/vm/swappiness, but affecting a hierarchy of groups only.

  Following cgroups' swapiness can't be changed.
  - root cgroup (uses /proc/sys/vm/swappiness).
  - a cgroup which uses hierarchy and it has child cgroup.
  - a cgroup which uses hierarchy and not the root of hierarchy.


6. Hierarchy support

The memory controller supports a deep hierarchy and hierarchical accounting.
The hierarchy is created by creating the appropriate cgroups in the
cgroup filesystem. Consider for example, the following cgroup filesystem
hierarchy

		root
	     /  |   \
           /	|    \
	  a	b	c
			| \
			|  \
			d   e

In the diagram above, with hierarchical accounting enabled, all memory
usage of e, is accounted to its ancestors up until the root (i.e, c and root),
that has memory.use_hierarchy enabled.  If one of the ancestors goes over its
limit, the reclaim algorithm reclaims from the tasks in the ancestor and the
children of the ancestor.

6.1 Enabling hierarchical accounting and reclaim

The memory controller by default disables the hierarchy feature. Support
can be enabled by writing 1 to memory.use_hierarchy file of the root cgroup

# echo 1 > memory.use_hierarchy

The feature can be disabled by

# echo 0 > memory.use_hierarchy

NOTE1: Enabling/disabling will fail if the cgroup already has other
cgroups created below it.

NOTE2: This feature can be enabled/disabled per subtree.

7. Soft limits

Soft limits allow for greater sharing of memory. The idea behind soft limits
is to allow control groups to use as much of the memory as needed, provided

a. There is no memory contention
b. They do not exceed their hard limit

When the system detects memory contention or low memory control groups
are pushed back to their soft limits. If the soft limit of each control
group is very high, they are pushed back as much as possible to make
sure that one control group does not starve the others of memory.

Please note that soft limits is a best effort feature, it comes with
no guarantees, but it does its best to make sure that when memory is
heavily contended for, memory is allocated based on the soft limit
hints/setup. Currently soft limit based reclaim is setup such that
it gets invoked from balance_pgdat (kswapd).

7.1 Interface

Soft limits can be setup by using the following commands (in this example we
assume a soft limit of 256 megabytes)

# echo 256M > memory.soft_limit_in_bytes

If we want to change this to 1G, we can at any time use

# echo 1G > memory.soft_limit_in_bytes

NOTE1: Soft limits take effect over a long period of time, since they involve
       reclaiming memory for balancing between memory cgroups
NOTE2: It is recommended to set the soft limit always below the hard limit,
       otherwise the hard limit will take precedence.

8. Move charges at task migration

Users can move charges associated with a task along with task migration, that
is, uncharge task's pages from the old cgroup and charge them to the new cgroup.

8.1 Interface

This feature is disabled by default. It can be enabled(and disabled again) by
writing to memory.move_charge_at_immigrate of the destination cgroup.

If you want to enable it:

# echo (some positive value) > memory.move_charge_at_immigrate

Note: Each bits of move_charge_at_immigrate has its own meaning about what type
      of charges should be moved. See 8.2 for details.
Note: Charges are moved only when you move mm->owner, IOW, a leader of a thread
      group.
Note: If we cannot find enough space for the task in the destination cgroup, we
      try to make space by reclaiming memory. Task migration may fail if we
      cannot make enough space.
Note: It can take several seconds if you move charges in giga bytes order.

And if you want disable it again:

# echo 0 > memory.move_charge_at_immigrate

8.2 Type of charges which can be move

Each bits of move_charge_at_immigrate has its own meaning about what type of
charges should be moved.

  bit | what type of charges would be moved ?
 -----+------------------------------------------------------------------------
   0  | A charge of an anonymous page(or swap of it) used by the target task.
      | Those pages and swaps must be used only by the target task. You must
      | enable Swap Extension(see 2.4) to enable move of swap charges.

Note: Those pages and swaps must be charged to the old cgroup.
Note: More type of pages(e.g. file cache, shmem,) will be supported by other
      bits in future.

8.3 TODO

- Add support for other types of pages(e.g. file cache, shmem, etc.).
- Implement madvise(2) to let users decide the vma to be moved or not to be
  moved.
- All of moving charge operations are done under cgroup_mutex. It's not good
  behavior to hold the mutex too long, so we may need some trick.

9. TODO

1. Add support for accounting huge pages (as a separate controller)
2. Make per-cgroup scanner reclaim not-shared pages first
3. Teach controller to account for shared-pages
4. Start reclamation in the background when the limit is
   not yet hit but the usage is getting closer

Summary

Overall, the memory controller has been a stable controller and has been
commented and discussed quite extensively in the community.

References

1. Singh, Balbir. RFC: Memory Controller, http://lwn.net/Articles/206697/
2. Singh, Balbir. Memory Controller (RSS Control),
   http://lwn.net/Articles/222762/
3. Emelianov, Pavel. Resource controllers based on process cgroups
   http://lkml.org/lkml/2007/3/6/198
4. Emelianov, Pavel. RSS controller based on process cgroups (v2)
   http://lkml.org/lkml/2007/4/9/78
5. Emelianov, Pavel. RSS controller based on process cgroups (v3)
   http://lkml.org/lkml/2007/5/30/244
6. Menage, Paul. Control Groups v10, http://lwn.net/Articles/236032/
7. Vaidyanathan, Srinivasan, Control Groups: Pagecache accounting and control
   subsystem (v3), http://lwn.net/Articles/235534/
8. Singh, Balbir. RSS controller v2 test results (lmbench),
   http://lkml.org/lkml/2007/5/17/232
9. Singh, Balbir. RSS controller v2 AIM9 results
   http://lkml.org/lkml/2007/5/18/1
10. Singh, Balbir. Memory controller v6 test results,
    http://lkml.org/lkml/2007/8/19/36
11. Singh, Balbir. Memory controller introduction (v6),
    http://lkml.org/lkml/2007/8/17/69
12. Corbet, Jonathan, Controlling memory use in cgroups,
    http://lwn.net/Articles/243795/