2013-08-27 18:17:58 -06:00
|
|
|
/*
|
|
|
|
* Copyright (c) 2013 Red Hat, Inc. and Parallels Inc. All rights reserved.
|
|
|
|
* Authors: David Chinner and Glauber Costa
|
|
|
|
*
|
|
|
|
* Generic LRU infrastructure
|
|
|
|
*/
|
|
|
|
#include <linux/kernel.h>
|
|
|
|
#include <linux/module.h>
|
2013-08-27 18:18:00 -06:00
|
|
|
#include <linux/mm.h>
|
2013-08-27 18:17:58 -06:00
|
|
|
#include <linux/list_lru.h>
|
2013-08-27 18:18:18 -06:00
|
|
|
#include <linux/slab.h>
|
2013-08-27 18:17:58 -06:00
|
|
|
|
|
|
|
bool list_lru_add(struct list_lru *lru, struct list_head *item)
|
|
|
|
{
|
2013-08-27 18:18:00 -06:00
|
|
|
int nid = page_to_nid(virt_to_page(item));
|
|
|
|
struct list_lru_node *nlru = &lru->node[nid];
|
|
|
|
|
|
|
|
spin_lock(&nlru->lock);
|
|
|
|
WARN_ON_ONCE(nlru->nr_items < 0);
|
2013-08-27 18:17:58 -06:00
|
|
|
if (list_empty(item)) {
|
2013-08-27 18:18:00 -06:00
|
|
|
list_add_tail(item, &nlru->list);
|
|
|
|
if (nlru->nr_items++ == 0)
|
|
|
|
node_set(nid, lru->active_nodes);
|
|
|
|
spin_unlock(&nlru->lock);
|
2013-08-27 18:17:58 -06:00
|
|
|
return true;
|
|
|
|
}
|
2013-08-27 18:18:00 -06:00
|
|
|
spin_unlock(&nlru->lock);
|
2013-08-27 18:17:58 -06:00
|
|
|
return false;
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(list_lru_add);
|
|
|
|
|
|
|
|
bool list_lru_del(struct list_lru *lru, struct list_head *item)
|
|
|
|
{
|
2013-08-27 18:18:00 -06:00
|
|
|
int nid = page_to_nid(virt_to_page(item));
|
|
|
|
struct list_lru_node *nlru = &lru->node[nid];
|
|
|
|
|
|
|
|
spin_lock(&nlru->lock);
|
2013-08-27 18:17:58 -06:00
|
|
|
if (!list_empty(item)) {
|
|
|
|
list_del_init(item);
|
2013-08-27 18:18:00 -06:00
|
|
|
if (--nlru->nr_items == 0)
|
|
|
|
node_clear(nid, lru->active_nodes);
|
|
|
|
WARN_ON_ONCE(nlru->nr_items < 0);
|
|
|
|
spin_unlock(&nlru->lock);
|
2013-08-27 18:17:58 -06:00
|
|
|
return true;
|
|
|
|
}
|
2013-08-27 18:18:00 -06:00
|
|
|
spin_unlock(&nlru->lock);
|
2013-08-27 18:17:58 -06:00
|
|
|
return false;
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(list_lru_del);
|
|
|
|
|
2013-08-27 18:18:02 -06:00
|
|
|
unsigned long
|
|
|
|
list_lru_count_node(struct list_lru *lru, int nid)
|
2013-08-27 18:17:58 -06:00
|
|
|
{
|
2013-08-27 18:18:00 -06:00
|
|
|
unsigned long count = 0;
|
2013-08-27 18:18:02 -06:00
|
|
|
struct list_lru_node *nlru = &lru->node[nid];
|
2013-08-27 18:18:00 -06:00
|
|
|
|
2013-08-27 18:18:02 -06:00
|
|
|
spin_lock(&nlru->lock);
|
|
|
|
WARN_ON_ONCE(nlru->nr_items < 0);
|
|
|
|
count += nlru->nr_items;
|
|
|
|
spin_unlock(&nlru->lock);
|
2013-08-27 18:18:00 -06:00
|
|
|
|
|
|
|
return count;
|
|
|
|
}
|
2013-08-27 18:18:02 -06:00
|
|
|
EXPORT_SYMBOL_GPL(list_lru_count_node);
|
2013-08-27 18:18:00 -06:00
|
|
|
|
2013-08-27 18:18:02 -06:00
|
|
|
unsigned long
|
2013-08-27 18:18:00 -06:00
|
|
|
list_lru_walk_node(struct list_lru *lru, int nid, list_lru_walk_cb isolate,
|
|
|
|
void *cb_arg, unsigned long *nr_to_walk)
|
|
|
|
{
|
|
|
|
|
|
|
|
struct list_lru_node *nlru = &lru->node[nid];
|
2013-08-27 18:17:58 -06:00
|
|
|
struct list_head *item, *n;
|
2013-08-27 18:18:00 -06:00
|
|
|
unsigned long isolated = 0;
|
2013-08-27 18:17:58 -06:00
|
|
|
|
2013-08-27 18:18:00 -06:00
|
|
|
spin_lock(&nlru->lock);
|
2013-08-27 18:17:58 -06:00
|
|
|
restart:
|
2013-08-27 18:18:00 -06:00
|
|
|
list_for_each_safe(item, n, &nlru->list) {
|
2013-08-27 18:17:58 -06:00
|
|
|
enum lru_status ret;
|
2013-08-27 18:18:01 -06:00
|
|
|
|
|
|
|
/*
|
|
|
|
* decrement nr_to_walk first so that we don't livelock if we
|
|
|
|
* get stuck on large numbesr of LRU_RETRY items
|
|
|
|
*/
|
mm: list_lru: fix almost infinite loop causing effective livelock
I've seen a fair number of issues with kswapd and other processes
appearing to get stuck in v3.12-rc. Using sysrq-p many times seems to
indicate that it gets stuck somewhere in list_lru_walk_node(), called
from prune_icache_sb() and super_cache_scan().
I never seem to be able to trigger a calltrace for functions above that
point.
So I decided to add the following to super_cache_scan():
@@ -81,10 +81,14 @@ static unsigned long super_cache_scan(struct shrinker *shrink,
inodes = list_lru_count_node(&sb->s_inode_lru, sc->nid);
dentries = list_lru_count_node(&sb->s_dentry_lru, sc->nid);
total_objects = dentries + inodes + fs_objects + 1;
+printk("%s:%u: %s: dentries %lu inodes %lu total %lu\n", current->comm, current->pid, __func__, dentries, inodes, total_objects);
/* proportion the scan between the caches */
dentries = mult_frac(sc->nr_to_scan, dentries, total_objects);
inodes = mult_frac(sc->nr_to_scan, inodes, total_objects);
+printk("%s:%u: %s: dentries %lu inodes %lu\n", current->comm, current->pid, __func__, dentries, inodes);
+BUG_ON(dentries == 0);
+BUG_ON(inodes == 0);
/*
* prune the dcache first as the icache is pinned by it, then
@@ -99,7 +103,7 @@ static unsigned long super_cache_scan(struct shrinker *shrink,
freed += sb->s_op->free_cached_objects(sb, fs_objects,
sc->nid);
}
-
+printk("%s:%u: %s: dentries %lu inodes %lu freed %lu\n", current->comm, current->pid, __func__, dentries, inodes, freed);
drop_super(sb);
return freed;
}
and shortly thereafter, having applied some pressure, I got this:
update-apt-xapi:1616: super_cache_scan: dentries 25632 inodes 2 total 25635
update-apt-xapi:1616: super_cache_scan: dentries 1023 inodes 0
------------[ cut here ]------------
Kernel BUG at c0101994 [verbose debug info unavailable]
Internal error: Oops - BUG: 0 [#3] SMP ARM
Modules linked in: fuse rfcomm bnep bluetooth hid_cypress
CPU: 0 PID: 1616 Comm: update-apt-xapi Tainted: G D 3.12.0-rc7+ #154
task: daea1200 ti: c3bf8000 task.ti: c3bf8000
PC is at super_cache_scan+0x1c0/0x278
LR is at trace_hardirqs_on+0x14/0x18
Process update-apt-xapi (pid: 1616, stack limit = 0xc3bf8240)
...
Backtrace:
(super_cache_scan) from [<c00cd69c>] (shrink_slab+0x254/0x4c8)
(shrink_slab) from [<c00d09a0>] (try_to_free_pages+0x3a0/0x5e0)
(try_to_free_pages) from [<c00c59cc>] (__alloc_pages_nodemask+0x5)
(__alloc_pages_nodemask) from [<c00e07c0>] (__pte_alloc+0x2c/0x13)
(__pte_alloc) from [<c00e3a70>] (handle_mm_fault+0x84c/0x914)
(handle_mm_fault) from [<c001a4cc>] (do_page_fault+0x1f0/0x3bc)
(do_page_fault) from [<c001a7b0>] (do_translation_fault+0xac/0xb8)
(do_translation_fault) from [<c000840c>] (do_DataAbort+0x38/0xa0)
(do_DataAbort) from [<c00133f8>] (__dabt_usr+0x38/0x40)
Notice that we had a very low number of inodes, which were reduced to
zero my mult_frac().
Now, prune_icache_sb() calls list_lru_walk_node() passing that number of
inodes (0) into that as the number of objects to scan:
long prune_icache_sb(struct super_block *sb, unsigned long nr_to_scan,
int nid)
{
LIST_HEAD(freeable);
long freed;
freed = list_lru_walk_node(&sb->s_inode_lru, nid, inode_lru_isolate,
&freeable, &nr_to_scan);
which does:
unsigned long
list_lru_walk_node(struct list_lru *lru, int nid, list_lru_walk_cb isolate,
void *cb_arg, unsigned long *nr_to_walk)
{
struct list_lru_node *nlru = &lru->node[nid];
struct list_head *item, *n;
unsigned long isolated = 0;
spin_lock(&nlru->lock);
restart:
list_for_each_safe(item, n, &nlru->list) {
enum lru_status ret;
/*
* decrement nr_to_walk first so that we don't livelock if we
* get stuck on large numbesr of LRU_RETRY items
*/
if (--(*nr_to_walk) == 0)
break;
So, if *nr_to_walk was zero when this function was entered, that means
we're wanting to operate on (~0UL)+1 objects - which might as well be
infinite.
Clearly this is not correct behaviour. If we think about the behaviour
of this function when *nr_to_walk is 1, then clearly it's wrong - we
decrement first and then test for zero - which results in us doing
nothing at all. A post-decrement would give the desired behaviour -
we'd try to walk one object and one object only if *nr_to_walk were one.
It also gives the correct behaviour for zero - we exit at this point.
Fixes: 5cedf721a7cd ("list_lru: fix broken LRU_RETRY behaviour")
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Cc: Dave Chinner <dchinner@redhat.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andrew Morton <akpm@linux-foundation.org>
[ Modified to make sure we never underflow the count: this function gets
called in a loop, so the 0 -> ~0ul transition is dangerous - Linus ]
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-10-30 08:16:16 -06:00
|
|
|
if (!*nr_to_walk)
|
2013-08-27 18:18:01 -06:00
|
|
|
break;
|
mm: list_lru: fix almost infinite loop causing effective livelock
I've seen a fair number of issues with kswapd and other processes
appearing to get stuck in v3.12-rc. Using sysrq-p many times seems to
indicate that it gets stuck somewhere in list_lru_walk_node(), called
from prune_icache_sb() and super_cache_scan().
I never seem to be able to trigger a calltrace for functions above that
point.
So I decided to add the following to super_cache_scan():
@@ -81,10 +81,14 @@ static unsigned long super_cache_scan(struct shrinker *shrink,
inodes = list_lru_count_node(&sb->s_inode_lru, sc->nid);
dentries = list_lru_count_node(&sb->s_dentry_lru, sc->nid);
total_objects = dentries + inodes + fs_objects + 1;
+printk("%s:%u: %s: dentries %lu inodes %lu total %lu\n", current->comm, current->pid, __func__, dentries, inodes, total_objects);
/* proportion the scan between the caches */
dentries = mult_frac(sc->nr_to_scan, dentries, total_objects);
inodes = mult_frac(sc->nr_to_scan, inodes, total_objects);
+printk("%s:%u: %s: dentries %lu inodes %lu\n", current->comm, current->pid, __func__, dentries, inodes);
+BUG_ON(dentries == 0);
+BUG_ON(inodes == 0);
/*
* prune the dcache first as the icache is pinned by it, then
@@ -99,7 +103,7 @@ static unsigned long super_cache_scan(struct shrinker *shrink,
freed += sb->s_op->free_cached_objects(sb, fs_objects,
sc->nid);
}
-
+printk("%s:%u: %s: dentries %lu inodes %lu freed %lu\n", current->comm, current->pid, __func__, dentries, inodes, freed);
drop_super(sb);
return freed;
}
and shortly thereafter, having applied some pressure, I got this:
update-apt-xapi:1616: super_cache_scan: dentries 25632 inodes 2 total 25635
update-apt-xapi:1616: super_cache_scan: dentries 1023 inodes 0
------------[ cut here ]------------
Kernel BUG at c0101994 [verbose debug info unavailable]
Internal error: Oops - BUG: 0 [#3] SMP ARM
Modules linked in: fuse rfcomm bnep bluetooth hid_cypress
CPU: 0 PID: 1616 Comm: update-apt-xapi Tainted: G D 3.12.0-rc7+ #154
task: daea1200 ti: c3bf8000 task.ti: c3bf8000
PC is at super_cache_scan+0x1c0/0x278
LR is at trace_hardirqs_on+0x14/0x18
Process update-apt-xapi (pid: 1616, stack limit = 0xc3bf8240)
...
Backtrace:
(super_cache_scan) from [<c00cd69c>] (shrink_slab+0x254/0x4c8)
(shrink_slab) from [<c00d09a0>] (try_to_free_pages+0x3a0/0x5e0)
(try_to_free_pages) from [<c00c59cc>] (__alloc_pages_nodemask+0x5)
(__alloc_pages_nodemask) from [<c00e07c0>] (__pte_alloc+0x2c/0x13)
(__pte_alloc) from [<c00e3a70>] (handle_mm_fault+0x84c/0x914)
(handle_mm_fault) from [<c001a4cc>] (do_page_fault+0x1f0/0x3bc)
(do_page_fault) from [<c001a7b0>] (do_translation_fault+0xac/0xb8)
(do_translation_fault) from [<c000840c>] (do_DataAbort+0x38/0xa0)
(do_DataAbort) from [<c00133f8>] (__dabt_usr+0x38/0x40)
Notice that we had a very low number of inodes, which were reduced to
zero my mult_frac().
Now, prune_icache_sb() calls list_lru_walk_node() passing that number of
inodes (0) into that as the number of objects to scan:
long prune_icache_sb(struct super_block *sb, unsigned long nr_to_scan,
int nid)
{
LIST_HEAD(freeable);
long freed;
freed = list_lru_walk_node(&sb->s_inode_lru, nid, inode_lru_isolate,
&freeable, &nr_to_scan);
which does:
unsigned long
list_lru_walk_node(struct list_lru *lru, int nid, list_lru_walk_cb isolate,
void *cb_arg, unsigned long *nr_to_walk)
{
struct list_lru_node *nlru = &lru->node[nid];
struct list_head *item, *n;
unsigned long isolated = 0;
spin_lock(&nlru->lock);
restart:
list_for_each_safe(item, n, &nlru->list) {
enum lru_status ret;
/*
* decrement nr_to_walk first so that we don't livelock if we
* get stuck on large numbesr of LRU_RETRY items
*/
if (--(*nr_to_walk) == 0)
break;
So, if *nr_to_walk was zero when this function was entered, that means
we're wanting to operate on (~0UL)+1 objects - which might as well be
infinite.
Clearly this is not correct behaviour. If we think about the behaviour
of this function when *nr_to_walk is 1, then clearly it's wrong - we
decrement first and then test for zero - which results in us doing
nothing at all. A post-decrement would give the desired behaviour -
we'd try to walk one object and one object only if *nr_to_walk were one.
It also gives the correct behaviour for zero - we exit at this point.
Fixes: 5cedf721a7cd ("list_lru: fix broken LRU_RETRY behaviour")
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Cc: Dave Chinner <dchinner@redhat.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andrew Morton <akpm@linux-foundation.org>
[ Modified to make sure we never underflow the count: this function gets
called in a loop, so the 0 -> ~0ul transition is dangerous - Linus ]
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-10-30 08:16:16 -06:00
|
|
|
--*nr_to_walk;
|
2013-08-27 18:18:01 -06:00
|
|
|
|
2013-08-27 18:18:00 -06:00
|
|
|
ret = isolate(item, &nlru->lock, cb_arg);
|
2013-08-27 18:17:58 -06:00
|
|
|
switch (ret) {
|
mm: keep page cache radix tree nodes in check
Previously, page cache radix tree nodes were freed after reclaim emptied
out their page pointers. But now reclaim stores shadow entries in their
place, which are only reclaimed when the inodes themselves are
reclaimed. This is problematic for bigger files that are still in use
after they have a significant amount of their cache reclaimed, without
any of those pages actually refaulting. The shadow entries will just
sit there and waste memory. In the worst case, the shadow entries will
accumulate until the machine runs out of memory.
To get this under control, the VM will track radix tree nodes
exclusively containing shadow entries on a per-NUMA node list. Per-NUMA
rather than global because we expect the radix tree nodes themselves to
be allocated node-locally and we want to reduce cross-node references of
otherwise independent cache workloads. A simple shrinker will then
reclaim these nodes on memory pressure.
A few things need to be stored in the radix tree node to implement the
shadow node LRU and allow tree deletions coming from the list:
1. There is no index available that would describe the reverse path
from the node up to the tree root, which is needed to perform a
deletion. To solve this, encode in each node its offset inside the
parent. This can be stored in the unused upper bits of the same
member that stores the node's height at no extra space cost.
2. The number of shadow entries needs to be counted in addition to the
regular entries, to quickly detect when the node is ready to go to
the shadow node LRU list. The current entry count is an unsigned
int but the maximum number of entries is 64, so a shadow counter
can easily be stored in the unused upper bits.
3. Tree modification needs tree lock and tree root, which are located
in the address space, so store an address_space backpointer in the
node. The parent pointer of the node is in a union with the 2-word
rcu_head, so the backpointer comes at no extra cost as well.
4. The node needs to be linked to an LRU list, which requires a list
head inside the node. This does increase the size of the node, but
it does not change the number of objects that fit into a slab page.
[akpm@linux-foundation.org: export the right function]
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Minchan Kim <minchan@kernel.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Bob Liu <bob.liu@oracle.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Luigi Semenzato <semenzato@google.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Metin Doslu <metin@citusdata.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Ozgun Erdogan <ozgun@citusdata.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Roman Gushchin <klamm@yandex-team.ru>
Cc: Ryan Mallon <rmallon@gmail.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-03 15:47:56 -06:00
|
|
|
case LRU_REMOVED_RETRY:
|
|
|
|
assert_spin_locked(&nlru->lock);
|
2013-08-27 18:17:58 -06:00
|
|
|
case LRU_REMOVED:
|
2013-08-27 18:18:00 -06:00
|
|
|
if (--nlru->nr_items == 0)
|
|
|
|
node_clear(nid, lru->active_nodes);
|
|
|
|
WARN_ON_ONCE(nlru->nr_items < 0);
|
|
|
|
isolated++;
|
mm: keep page cache radix tree nodes in check
Previously, page cache radix tree nodes were freed after reclaim emptied
out their page pointers. But now reclaim stores shadow entries in their
place, which are only reclaimed when the inodes themselves are
reclaimed. This is problematic for bigger files that are still in use
after they have a significant amount of their cache reclaimed, without
any of those pages actually refaulting. The shadow entries will just
sit there and waste memory. In the worst case, the shadow entries will
accumulate until the machine runs out of memory.
To get this under control, the VM will track radix tree nodes
exclusively containing shadow entries on a per-NUMA node list. Per-NUMA
rather than global because we expect the radix tree nodes themselves to
be allocated node-locally and we want to reduce cross-node references of
otherwise independent cache workloads. A simple shrinker will then
reclaim these nodes on memory pressure.
A few things need to be stored in the radix tree node to implement the
shadow node LRU and allow tree deletions coming from the list:
1. There is no index available that would describe the reverse path
from the node up to the tree root, which is needed to perform a
deletion. To solve this, encode in each node its offset inside the
parent. This can be stored in the unused upper bits of the same
member that stores the node's height at no extra space cost.
2. The number of shadow entries needs to be counted in addition to the
regular entries, to quickly detect when the node is ready to go to
the shadow node LRU list. The current entry count is an unsigned
int but the maximum number of entries is 64, so a shadow counter
can easily be stored in the unused upper bits.
3. Tree modification needs tree lock and tree root, which are located
in the address space, so store an address_space backpointer in the
node. The parent pointer of the node is in a union with the 2-word
rcu_head, so the backpointer comes at no extra cost as well.
4. The node needs to be linked to an LRU list, which requires a list
head inside the node. This does increase the size of the node, but
it does not change the number of objects that fit into a slab page.
[akpm@linux-foundation.org: export the right function]
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Minchan Kim <minchan@kernel.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Bob Liu <bob.liu@oracle.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Luigi Semenzato <semenzato@google.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Metin Doslu <metin@citusdata.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Ozgun Erdogan <ozgun@citusdata.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Roman Gushchin <klamm@yandex-team.ru>
Cc: Ryan Mallon <rmallon@gmail.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-03 15:47:56 -06:00
|
|
|
/*
|
|
|
|
* If the lru lock has been dropped, our list
|
|
|
|
* traversal is now invalid and so we have to
|
|
|
|
* restart from scratch.
|
|
|
|
*/
|
|
|
|
if (ret == LRU_REMOVED_RETRY)
|
|
|
|
goto restart;
|
2013-08-27 18:17:58 -06:00
|
|
|
break;
|
|
|
|
case LRU_ROTATE:
|
2013-08-27 18:18:00 -06:00
|
|
|
list_move_tail(item, &nlru->list);
|
2013-08-27 18:17:58 -06:00
|
|
|
break;
|
|
|
|
case LRU_SKIP:
|
|
|
|
break;
|
|
|
|
case LRU_RETRY:
|
2013-08-27 18:18:01 -06:00
|
|
|
/*
|
|
|
|
* The lru lock has been dropped, our list traversal is
|
|
|
|
* now invalid and so we have to restart from scratch.
|
|
|
|
*/
|
mm: keep page cache radix tree nodes in check
Previously, page cache radix tree nodes were freed after reclaim emptied
out their page pointers. But now reclaim stores shadow entries in their
place, which are only reclaimed when the inodes themselves are
reclaimed. This is problematic for bigger files that are still in use
after they have a significant amount of their cache reclaimed, without
any of those pages actually refaulting. The shadow entries will just
sit there and waste memory. In the worst case, the shadow entries will
accumulate until the machine runs out of memory.
To get this under control, the VM will track radix tree nodes
exclusively containing shadow entries on a per-NUMA node list. Per-NUMA
rather than global because we expect the radix tree nodes themselves to
be allocated node-locally and we want to reduce cross-node references of
otherwise independent cache workloads. A simple shrinker will then
reclaim these nodes on memory pressure.
A few things need to be stored in the radix tree node to implement the
shadow node LRU and allow tree deletions coming from the list:
1. There is no index available that would describe the reverse path
from the node up to the tree root, which is needed to perform a
deletion. To solve this, encode in each node its offset inside the
parent. This can be stored in the unused upper bits of the same
member that stores the node's height at no extra space cost.
2. The number of shadow entries needs to be counted in addition to the
regular entries, to quickly detect when the node is ready to go to
the shadow node LRU list. The current entry count is an unsigned
int but the maximum number of entries is 64, so a shadow counter
can easily be stored in the unused upper bits.
3. Tree modification needs tree lock and tree root, which are located
in the address space, so store an address_space backpointer in the
node. The parent pointer of the node is in a union with the 2-word
rcu_head, so the backpointer comes at no extra cost as well.
4. The node needs to be linked to an LRU list, which requires a list
head inside the node. This does increase the size of the node, but
it does not change the number of objects that fit into a slab page.
[akpm@linux-foundation.org: export the right function]
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Minchan Kim <minchan@kernel.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Bob Liu <bob.liu@oracle.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Luigi Semenzato <semenzato@google.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Metin Doslu <metin@citusdata.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Ozgun Erdogan <ozgun@citusdata.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Roman Gushchin <klamm@yandex-team.ru>
Cc: Ryan Mallon <rmallon@gmail.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-03 15:47:56 -06:00
|
|
|
assert_spin_locked(&nlru->lock);
|
2013-08-27 18:17:58 -06:00
|
|
|
goto restart;
|
|
|
|
default:
|
|
|
|
BUG();
|
|
|
|
}
|
|
|
|
}
|
2013-08-27 18:18:00 -06:00
|
|
|
|
|
|
|
spin_unlock(&nlru->lock);
|
|
|
|
return isolated;
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(list_lru_walk_node);
|
|
|
|
|
mm: keep page cache radix tree nodes in check
Previously, page cache radix tree nodes were freed after reclaim emptied
out their page pointers. But now reclaim stores shadow entries in their
place, which are only reclaimed when the inodes themselves are
reclaimed. This is problematic for bigger files that are still in use
after they have a significant amount of their cache reclaimed, without
any of those pages actually refaulting. The shadow entries will just
sit there and waste memory. In the worst case, the shadow entries will
accumulate until the machine runs out of memory.
To get this under control, the VM will track radix tree nodes
exclusively containing shadow entries on a per-NUMA node list. Per-NUMA
rather than global because we expect the radix tree nodes themselves to
be allocated node-locally and we want to reduce cross-node references of
otherwise independent cache workloads. A simple shrinker will then
reclaim these nodes on memory pressure.
A few things need to be stored in the radix tree node to implement the
shadow node LRU and allow tree deletions coming from the list:
1. There is no index available that would describe the reverse path
from the node up to the tree root, which is needed to perform a
deletion. To solve this, encode in each node its offset inside the
parent. This can be stored in the unused upper bits of the same
member that stores the node's height at no extra space cost.
2. The number of shadow entries needs to be counted in addition to the
regular entries, to quickly detect when the node is ready to go to
the shadow node LRU list. The current entry count is an unsigned
int but the maximum number of entries is 64, so a shadow counter
can easily be stored in the unused upper bits.
3. Tree modification needs tree lock and tree root, which are located
in the address space, so store an address_space backpointer in the
node. The parent pointer of the node is in a union with the 2-word
rcu_head, so the backpointer comes at no extra cost as well.
4. The node needs to be linked to an LRU list, which requires a list
head inside the node. This does increase the size of the node, but
it does not change the number of objects that fit into a slab page.
[akpm@linux-foundation.org: export the right function]
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Minchan Kim <minchan@kernel.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Bob Liu <bob.liu@oracle.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Luigi Semenzato <semenzato@google.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Metin Doslu <metin@citusdata.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Ozgun Erdogan <ozgun@citusdata.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Roman Gushchin <klamm@yandex-team.ru>
Cc: Ryan Mallon <rmallon@gmail.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-03 15:47:56 -06:00
|
|
|
int list_lru_init_key(struct list_lru *lru, struct lock_class_key *key)
|
2013-08-27 18:17:58 -06:00
|
|
|
{
|
2013-08-27 18:18:00 -06:00
|
|
|
int i;
|
2013-08-27 18:18:18 -06:00
|
|
|
size_t size = sizeof(*lru->node) * nr_node_ids;
|
|
|
|
|
|
|
|
lru->node = kzalloc(size, GFP_KERNEL);
|
|
|
|
if (!lru->node)
|
|
|
|
return -ENOMEM;
|
2013-08-27 18:17:58 -06:00
|
|
|
|
2013-08-27 18:18:00 -06:00
|
|
|
nodes_clear(lru->active_nodes);
|
2013-08-27 18:18:18 -06:00
|
|
|
for (i = 0; i < nr_node_ids; i++) {
|
2013-08-27 18:18:00 -06:00
|
|
|
spin_lock_init(&lru->node[i].lock);
|
mm: keep page cache radix tree nodes in check
Previously, page cache radix tree nodes were freed after reclaim emptied
out their page pointers. But now reclaim stores shadow entries in their
place, which are only reclaimed when the inodes themselves are
reclaimed. This is problematic for bigger files that are still in use
after they have a significant amount of their cache reclaimed, without
any of those pages actually refaulting. The shadow entries will just
sit there and waste memory. In the worst case, the shadow entries will
accumulate until the machine runs out of memory.
To get this under control, the VM will track radix tree nodes
exclusively containing shadow entries on a per-NUMA node list. Per-NUMA
rather than global because we expect the radix tree nodes themselves to
be allocated node-locally and we want to reduce cross-node references of
otherwise independent cache workloads. A simple shrinker will then
reclaim these nodes on memory pressure.
A few things need to be stored in the radix tree node to implement the
shadow node LRU and allow tree deletions coming from the list:
1. There is no index available that would describe the reverse path
from the node up to the tree root, which is needed to perform a
deletion. To solve this, encode in each node its offset inside the
parent. This can be stored in the unused upper bits of the same
member that stores the node's height at no extra space cost.
2. The number of shadow entries needs to be counted in addition to the
regular entries, to quickly detect when the node is ready to go to
the shadow node LRU list. The current entry count is an unsigned
int but the maximum number of entries is 64, so a shadow counter
can easily be stored in the unused upper bits.
3. Tree modification needs tree lock and tree root, which are located
in the address space, so store an address_space backpointer in the
node. The parent pointer of the node is in a union with the 2-word
rcu_head, so the backpointer comes at no extra cost as well.
4. The node needs to be linked to an LRU list, which requires a list
head inside the node. This does increase the size of the node, but
it does not change the number of objects that fit into a slab page.
[akpm@linux-foundation.org: export the right function]
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Minchan Kim <minchan@kernel.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Bob Liu <bob.liu@oracle.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Luigi Semenzato <semenzato@google.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Metin Doslu <metin@citusdata.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Ozgun Erdogan <ozgun@citusdata.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Roman Gushchin <klamm@yandex-team.ru>
Cc: Ryan Mallon <rmallon@gmail.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-03 15:47:56 -06:00
|
|
|
if (key)
|
|
|
|
lockdep_set_class(&lru->node[i].lock, key);
|
2013-08-27 18:18:00 -06:00
|
|
|
INIT_LIST_HEAD(&lru->node[i].list);
|
|
|
|
lru->node[i].nr_items = 0;
|
|
|
|
}
|
2013-08-27 18:17:58 -06:00
|
|
|
return 0;
|
|
|
|
}
|
mm: keep page cache radix tree nodes in check
Previously, page cache radix tree nodes were freed after reclaim emptied
out their page pointers. But now reclaim stores shadow entries in their
place, which are only reclaimed when the inodes themselves are
reclaimed. This is problematic for bigger files that are still in use
after they have a significant amount of their cache reclaimed, without
any of those pages actually refaulting. The shadow entries will just
sit there and waste memory. In the worst case, the shadow entries will
accumulate until the machine runs out of memory.
To get this under control, the VM will track radix tree nodes
exclusively containing shadow entries on a per-NUMA node list. Per-NUMA
rather than global because we expect the radix tree nodes themselves to
be allocated node-locally and we want to reduce cross-node references of
otherwise independent cache workloads. A simple shrinker will then
reclaim these nodes on memory pressure.
A few things need to be stored in the radix tree node to implement the
shadow node LRU and allow tree deletions coming from the list:
1. There is no index available that would describe the reverse path
from the node up to the tree root, which is needed to perform a
deletion. To solve this, encode in each node its offset inside the
parent. This can be stored in the unused upper bits of the same
member that stores the node's height at no extra space cost.
2. The number of shadow entries needs to be counted in addition to the
regular entries, to quickly detect when the node is ready to go to
the shadow node LRU list. The current entry count is an unsigned
int but the maximum number of entries is 64, so a shadow counter
can easily be stored in the unused upper bits.
3. Tree modification needs tree lock and tree root, which are located
in the address space, so store an address_space backpointer in the
node. The parent pointer of the node is in a union with the 2-word
rcu_head, so the backpointer comes at no extra cost as well.
4. The node needs to be linked to an LRU list, which requires a list
head inside the node. This does increase the size of the node, but
it does not change the number of objects that fit into a slab page.
[akpm@linux-foundation.org: export the right function]
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Minchan Kim <minchan@kernel.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Bob Liu <bob.liu@oracle.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Luigi Semenzato <semenzato@google.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Metin Doslu <metin@citusdata.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Ozgun Erdogan <ozgun@citusdata.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Roman Gushchin <klamm@yandex-team.ru>
Cc: Ryan Mallon <rmallon@gmail.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-03 15:47:56 -06:00
|
|
|
EXPORT_SYMBOL_GPL(list_lru_init_key);
|
2013-08-27 18:18:18 -06:00
|
|
|
|
|
|
|
void list_lru_destroy(struct list_lru *lru)
|
|
|
|
{
|
|
|
|
kfree(lru->node);
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(list_lru_destroy);
|