mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-12 05:48:40 +00:00
1d3d4437ea
The list_lru infrastructure already keeps per-node LRU lists in its node-specific list_lru_node arrays and provide us with a per-node API, and the shrinkers are properly equiped with node information. This means that we can now focus our shrinking effort in a single node, but the work that is deferred from one run to another is kept global at nr_in_batch. Work can be deferred, for instance, during direct reclaim under a GFP_NOFS allocation, where situation, all the filesystem shrinkers will be prevented from running and accumulate in nr_in_batch the amount of work they should have done, but could not. This creates an impedance problem, where upon node pressure, work deferred will accumulate and end up being flushed in other nodes. The problem we describe is particularly harmful in big machines, where many nodes can accumulate at the same time, all adding to the global counter nr_in_batch. As we accumulate more and more, we start to ask for the caches to flush even bigger numbers. The result is that the caches are depleted and do not stabilize. To achieve stable steady state behavior, we need to tackle it differently. In this patch we keep the deferred count per-node, in the new array nr_deferred[] (the name is also a bit more descriptive) and will never accumulate that to other nodes. Signed-off-by: Glauber Costa <glommer@openvz.org> Cc: Dave Chinner <dchinner@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Artem Bityutskiy <artem.bityutskiy@linux.intel.com> Cc: Arve Hjønnevåg <arve@android.com> Cc: Carlos Maiolino <cmaiolino@redhat.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Chuck Lever <chuck.lever@oracle.com> Cc: Daniel Vetter <daniel.vetter@ffwll.ch> Cc: David Rientjes <rientjes@google.com> Cc: Gleb Natapov <gleb@redhat.com> Cc: Greg Thelen <gthelen@google.com> Cc: J. Bruce Fields <bfields@redhat.com> Cc: Jan Kara <jack@suse.cz> Cc: Jerome Glisse <jglisse@redhat.com> Cc: John Stultz <john.stultz@linaro.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Kent Overstreet <koverstreet@google.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Thomas Hellstrom <thellstrom@vmware.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
75 lines
2.7 KiB
C
75 lines
2.7 KiB
C
#ifndef _LINUX_SHRINKER_H
|
|
#define _LINUX_SHRINKER_H
|
|
|
|
/*
|
|
* This struct is used to pass information from page reclaim to the shrinkers.
|
|
* We consolidate the values for easier extention later.
|
|
*
|
|
* The 'gfpmask' refers to the allocation we are currently trying to
|
|
* fulfil.
|
|
*
|
|
* Note that 'shrink' will be passed nr_to_scan == 0 when the VM is
|
|
* querying the cache size, so a fastpath for that case is appropriate.
|
|
*/
|
|
struct shrink_control {
|
|
gfp_t gfp_mask;
|
|
|
|
/* How many slab objects shrinker() should scan and try to reclaim */
|
|
unsigned long nr_to_scan;
|
|
|
|
/* shrink from these nodes */
|
|
nodemask_t nodes_to_scan;
|
|
/* current node being shrunk (for NUMA aware shrinkers) */
|
|
int nid;
|
|
};
|
|
|
|
#define SHRINK_STOP (~0UL)
|
|
/*
|
|
* A callback you can register to apply pressure to ageable caches.
|
|
*
|
|
* @shrink() should look through the least-recently-used 'nr_to_scan' entries
|
|
* and attempt to free them up. It should return the number of objects which
|
|
* remain in the cache. If it returns -1, it means it cannot do any scanning at
|
|
* this time (eg. there is a risk of deadlock).
|
|
*
|
|
* @count_objects should return the number of freeable items in the cache. If
|
|
* there are no objects to free or the number of freeable items cannot be
|
|
* determined, it should return 0. No deadlock checks should be done during the
|
|
* count callback - the shrinker relies on aggregating scan counts that couldn't
|
|
* be executed due to potential deadlocks to be run at a later call when the
|
|
* deadlock condition is no longer pending.
|
|
*
|
|
* @scan_objects will only be called if @count_objects returned a non-zero
|
|
* value for the number of freeable objects. The callout should scan the cache
|
|
* and attempt to free items from the cache. It should then return the number
|
|
* of objects freed during the scan, or SHRINK_STOP if progress cannot be made
|
|
* due to potential deadlocks. If SHRINK_STOP is returned, then no further
|
|
* attempts to call the @scan_objects will be made from the current reclaim
|
|
* context.
|
|
*
|
|
* @flags determine the shrinker abilities, like numa awareness
|
|
*/
|
|
struct shrinker {
|
|
int (*shrink)(struct shrinker *, struct shrink_control *sc);
|
|
unsigned long (*count_objects)(struct shrinker *,
|
|
struct shrink_control *sc);
|
|
unsigned long (*scan_objects)(struct shrinker *,
|
|
struct shrink_control *sc);
|
|
|
|
int seeks; /* seeks to recreate an obj */
|
|
long batch; /* reclaim batch size, 0 = default */
|
|
unsigned long flags;
|
|
|
|
/* These are for internal use */
|
|
struct list_head list;
|
|
/* objs pending delete, per node */
|
|
atomic_long_t *nr_deferred;
|
|
};
|
|
#define DEFAULT_SEEKS 2 /* A good number if you don't know better. */
|
|
|
|
/* Flags */
|
|
#define SHRINKER_NUMA_AWARE (1 << 0)
|
|
|
|
extern int register_shrinker(struct shrinker *);
|
|
extern void unregister_shrinker(struct shrinker *);
|
|
#endif
|