Restructure per-filesystem reclaim

Originally when the ARC prune callback was introduced the idea was
to register a single callback for the ZPL.  The ARC could invoke this
call back if it needed the ZPL to drop dentries, inodes, or other
cache objects which might be pinning buffers in the ARC.  The ZPL
would iterate over all ZFS super blocks and perform the reclaim.

For the most part this design has worked well but due to limitations
in 2.6.35 and earlier kernels there were some problems.  This patch
is designed to address those issues.

1) iterate_supers_type() is not provided by all kernels which makes
it impossible to safely iterate over all zpl_fs_type filesystems in
a single callback.  The most straight forward and portable way to
resolve this is to register a callback per-filesystem during mount.
The arc_*_prune_callback() functions have always supported multiple
callbacks so this is functionally a very small change.

2) Commit 050d22b removed the non-portable shrink_dcache_memory()
and shrink_icache_memory() functions and didn't replace them with
equivalent functionality.  This meant that for Linux 3.1 and older
kernels the ARC had no mechanism to drop dentries and inodes from
the caches if needed.  This patch adds that missing functionality
by calling shrink_dcache_parent() to release dentries which may be
pinning inodes.  This will result in all unused cache entries being
dropped which is a bit heavy handed but it's the only interface
available for old kernels.

3) A zpl_drop_inode() callback is registered for kernels older than
2.6.35 which do not support the .evict_inode callback.  This ensures
that when the last reference on an inode is dropped it is immediately
removed from the cache.  If this isn't done than inode can end up on
the global unused LRU with no mechanism available to ZFS to drop them.
Since the ARC buffers are not dropped the hottest inodes can still
be recreated without performing disk IO.

Signed-off-by: Brian Behlendorf <[email protected]>
Signed-off-by: Pavel Snajdr <[email protected]>
Issue #3160

1 files changed, 11 insertions, 30 deletions

diff --git a/module/zfs/zpl_super.c b/module/zfs/zpl_super.c
index 47cc2fcf4..ef0f9d311 100644
--- a/module/zfs/zpl_super.c
+++ b/module/zfs/zpl_super.c
@@ -110,6 +110,12 @@ zpl_evict_inode(struct inode *ip)
 #else
 
 static void
+zpl_drop_inode(struct inode *ip)
+{
+	generic_delete_inode(ip);
+}
+
+static void
 zpl_clear_inode(struct inode *ip)
 {
 	fstrans_cookie_t cookie;
@@ -125,7 +131,6 @@ zpl_inode_delete(struct inode *ip)
 	truncate_setsize(ip, 0);
 	clear_inode(ip);
 }
-
 #endif /* HAVE_EVICT_INODE */
 
 static void
@@ -276,37 +281,13 @@ zpl_kill_sb(struct super_block *sb)
 #endif /* HAVE_S_INSTANCES_LIST_HEAD */
 }
 
-#if defined(HAVE_SHRINK) || defined(HAVE_SPLIT_SHRINKER_CALLBACK)
-/*
- * Linux 3.1 - 3.x API
- *
- * The Linux 3.1 API introduced per-sb cache shrinkers to replace the
- * global ones.  This allows us a mechanism to cleanly target a specific
- * zfs file system when the dnode and inode caches grow too large.
- *
- * In addition, the 3.0 kernel added the iterate_supers_type() helper
- * function which is used to safely walk all of the zfs file systems.
- */
-static void
-zpl_prune_sb(struct super_block *sb, void *arg)
-{
-	int objects = 0;
-	int error;
-
-	error = -zfs_sb_prune(sb, *(unsigned long *)arg, &objects);
-	ASSERT3S(error, <=, 0);
-}
-#endif /* defined(HAVE_SHRINK) || defined(HAVE_SPLIT_SHRINKER_CALLBACK) */
-
 void
-zpl_prune_sbs(int64_t bytes_to_scan, void *private)
+zpl_prune_sb(int64_t nr_to_scan, void *arg)
 {
-#if defined(HAVE_SHRINK) || defined(HAVE_SPLIT_SHRINKER_CALLBACK)
-	unsigned long nr_to_scan = (bytes_to_scan / sizeof (znode_t));
+	struct super_block *sb = (struct super_block *)arg;
+	int objects = 0;
 
-	iterate_supers_type(&zpl_fs_type, zpl_prune_sb, &nr_to_scan);
-	kmem_reap();
-#endif /* defined(HAVE_SHRINK) || defined(HAVE_SPLIT_SHRINKER_CALLBACK) */
+	(void) -zfs_sb_prune(sb, nr_to_scan, &objects);
 }
 
 #ifdef HAVE_NR_CACHED_OBJECTS
@@ -343,10 +324,10 @@ const struct super_operations zpl_super_operations = {
 	.destroy_inode		= zpl_inode_destroy,
 	.dirty_inode		= zpl_dirty_inode,
 	.write_inode		= NULL,
-	.drop_inode		= NULL,
 #ifdef HAVE_EVICT_INODE
 	.evict_inode		= zpl_evict_inode,
 #else
+	.drop_inode		= zpl_drop_inode,
 	.clear_inode		= zpl_clear_inode,
 	.delete_inode		= zpl_inode_delete,
 #endif /* HAVE_EVICT_INODE */