summaryrefslogtreecommitdiff
path: root/include/linux/pagemap.h
diff options
context:
space:
mode:
authorJohannes Weiner <hannes@cmpxchg.org>2021-11-09 05:31:24 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2021-11-09 21:02:48 +0300
commit51b8c1fe250d1bd70c1722dc3c414f5cff2d7cca (patch)
treecd8daabd1ee0974a3d230c802bebac4217e09844 /include/linux/pagemap.h
parent658f9ae761b5965893727dd4edcdad56e5a439bb (diff)
downloadlinux-51b8c1fe250d1bd70c1722dc3c414f5cff2d7cca.tar.xz
vfs: keep inodes with page cache off the inode shrinker LRU
Historically (pre-2.5), the inode shrinker used to reclaim only empty inodes and skip over those that still contained page cache. This caused problems on highmem hosts: struct inode could put fill lowmem zones before the cache was getting reclaimed in the highmem zones. To address this, the inode shrinker started to strip page cache to facilitate reclaiming lowmem. However, this comes with its own set of problems: the shrinkers may drop actively used page cache just because the inodes are not currently open or dirty - think working with a large git tree. It further doesn't respect cgroup memory protection settings and can cause priority inversions between containers. Nowadays, the page cache also holds non-resident info for evicted cache pages in order to detect refaults. We've come to rely heavily on this data inside reclaim for protecting the cache workingset and driving swap behavior. We also use it to quantify and report workload health through psi. The latter in turn is used for fleet health monitoring, as well as driving automated memory sizing of workloads and containers, proactive reclaim and memory offloading schemes. The consequences of dropping page cache prematurely is that we're seeing subtle and not-so-subtle failures in all of the above-mentioned scenarios, with the workload generally entering unexpected thrashing states while losing the ability to reliably detect it. To fix this on non-highmem systems at least, going back to rotating inodes on the LRU isn't feasible. We've tried (commit a76cf1a474d7 ("mm: don't reclaim inodes with many attached pages")) and failed (commit 69056ee6a8a3 ("Revert "mm: don't reclaim inodes with many attached pages"")). The issue is mostly that shrinker pools attract pressure based on their size, and when objects get skipped the shrinkers remember this as deferred reclaim work. This accumulates excessive pressure on the remaining inodes, and we can quickly eat into heavily used ones, or dirty ones that require IO to reclaim, when there potentially is plenty of cold, clean cache around still. Instead, this patch keeps populated inodes off the inode LRU in the first place - just like an open file or dirty state would. An otherwise clean and unused inode then gets queued when the last cache entry disappears. This solves the problem without reintroducing the reclaim issues, and generally is a bit more scalable than having to wade through potentially hundreds of thousands of busy inodes. Locking is a bit tricky because the locks protecting the inode state (i_lock) and the inode LRU (lru_list.lock) don't nest inside the irq-safe page cache lock (i_pages.xa_lock). Page cache deletions are serialized through i_lock, taken before the i_pages lock, to make sure depopulated inodes are queued reliably. Additions may race with deletions, but we'll check again in the shrinker. If additions race with the shrinker itself, we're protected by the i_lock: if find_inode() or iput() win, the shrinker will bail on the elevated i_count or I_REFERENCED; if the shrinker wins and goes ahead with the inode, it will set I_FREEING and inhibit further igets(), which will cause the other side to create a new instance of the inode instead. Link: https://lkml.kernel.org/r/20210614211904.14420-4-hannes@cmpxchg.org Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Roman Gushchin <guro@fb.com> Cc: Tejun Heo <tj@kernel.org> Cc: Dave Chinner <david@fromorbit.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'include/linux/pagemap.h')
-rw-r--r--include/linux/pagemap.h50
1 files changed, 50 insertions, 0 deletions
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 62db6b0176b9..5c74a45ff97a 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -24,6 +24,56 @@ static inline bool mapping_empty(struct address_space *mapping)
}
/*
+ * mapping_shrinkable - test if page cache state allows inode reclaim
+ * @mapping: the page cache mapping
+ *
+ * This checks the mapping's cache state for the pupose of inode
+ * reclaim and LRU management.
+ *
+ * The caller is expected to hold the i_lock, but is not required to
+ * hold the i_pages lock, which usually protects cache state. That's
+ * because the i_lock and the list_lru lock that protect the inode and
+ * its LRU state don't nest inside the irq-safe i_pages lock.
+ *
+ * Cache deletions are performed under the i_lock, which ensures that
+ * when an inode goes empty, it will reliably get queued on the LRU.
+ *
+ * Cache additions do not acquire the i_lock and may race with this
+ * check, in which case we'll report the inode as shrinkable when it
+ * has cache pages. This is okay: the shrinker also checks the
+ * refcount and the referenced bit, which will be elevated or set in
+ * the process of adding new cache pages to an inode.
+ */
+static inline bool mapping_shrinkable(struct address_space *mapping)
+{
+ void *head;
+
+ /*
+ * On highmem systems, there could be lowmem pressure from the
+ * inodes before there is highmem pressure from the page
+ * cache. Make inodes shrinkable regardless of cache state.
+ */
+ if (IS_ENABLED(CONFIG_HIGHMEM))
+ return true;
+
+ /* Cache completely empty? Shrink away. */
+ head = rcu_access_pointer(mapping->i_pages.xa_head);
+ if (!head)
+ return true;
+
+ /*
+ * The xarray stores single offset-0 entries directly in the
+ * head pointer, which allows non-resident page cache entries
+ * to escape the shadow shrinker's list of xarray nodes. The
+ * inode shrinker needs to pick them up under memory pressure.
+ */
+ if (!xa_is_node(head) && xa_is_value(head))
+ return true;
+
+ return false;
+}
+
+/*
* Bits in mapping->flags.
*/
enum mapping_flags {