From: npiggin@kernel.dk
To: linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org
Cc: linux-mm@kvack.org
Subject: [patch 04/35] vfs: convert inode and dentry caches to per-zone shrinker
Date: Tue, 19 Oct 2010 14:42:20 +1100 [thread overview]
Message-ID: <20101019034655.866685321@kernel.dk> (raw)
In-Reply-To: 20101019034216.319085068@kernel.dk
[-- Attachment #1: vfs-zone-shrinker.patch --]
[-- Type: text/plain, Size: 4924 bytes --]
Convert inode and dentry caches to per-zone shrinker API in preparation
for doing proper per-zone cache LRU lists. These two caches tend to be
the most important in the system after the pagecache lrus, so making these
per-zone will help to fix up the funny quirks in vmscan code that tries
to reconcile the whole zone-driven scanning with the global slab reclaim.
Cc: linux-mm@kvack.org
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
---
fs/dcache.c | 31 ++++++++++++++++++++-----------
fs/inode.c | 39 ++++++++++++++++++++++++---------------
2 files changed, 44 insertions(+), 26 deletions(-)
Index: linux-2.6/fs/dcache.c
===================================================================
--- linux-2.6.orig/fs/dcache.c 2010-10-19 14:35:42.000000000 +1100
+++ linux-2.6/fs/dcache.c 2010-10-19 14:36:53.000000000 +1100
@@ -534,7 +534,7 @@
*
* This function may fail to free any resources if all the dentries are in use.
*/
-static void prune_dcache(int count)
+static void prune_dcache(unsigned long count)
{
struct super_block *sb, *p = NULL;
int w_count;
@@ -887,7 +887,8 @@
EXPORT_SYMBOL(shrink_dcache_parent);
/*
- * Scan `nr' dentries and return the number which remain.
+ * shrink_dcache_memory scans and reclaims unused dentries. This function
+ * is defined according to the shrinker API described in linux/mm.h.
*
* We need to avoid reentering the filesystem if the caller is performing a
* GFP_NOFS allocation attempt. One example deadlock is:
@@ -895,22 +896,30 @@
* ext2_new_block->getblk->GFP->shrink_dcache_memory->prune_dcache->
* prune_one_dentry->dput->dentry_iput->iput->inode->i_sb->s_op->put_inode->
* ext2_discard_prealloc->ext2_free_blocks->lock_super->DEADLOCK.
- *
- * In this case we return -1 to tell the caller that we baled.
*/
-static int shrink_dcache_memory(struct shrinker *shrink, int nr, gfp_t gfp_mask)
+static void shrink_dcache_memory(struct shrinker *shrink,
+ struct zone *zone, unsigned long scanned,
+ unsigned long total, unsigned long global,
+ unsigned long flags, gfp_t gfp_mask)
{
- if (nr) {
- if (!(gfp_mask & __GFP_FS))
- return -1;
+ static unsigned long nr_to_scan;
+ unsigned long nr;
+
+ shrinker_add_scan(&nr_to_scan, scanned, global,
+ dentry_stat.nr_unused,
+ SHRINK_DEFAULT_SEEKS * 100 / sysctl_vfs_cache_pressure);
+ if (!(gfp_mask & __GFP_FS))
+ return;
+
+ while ((nr = shrinker_do_scan(&nr_to_scan, SHRINK_BATCH))) {
prune_dcache(nr);
+ count_vm_events(SLABS_SCANNED, nr);
+ cond_resched();
}
- return (dentry_stat.nr_unused / 100) * sysctl_vfs_cache_pressure;
}
static struct shrinker dcache_shrinker = {
- .shrink = shrink_dcache_memory,
- .seeks = DEFAULT_SEEKS,
+ .shrink_zone = shrink_dcache_memory,
};
/**
Index: linux-2.6/fs/inode.c
===================================================================
--- linux-2.6.orig/fs/inode.c 2010-10-19 14:35:42.000000000 +1100
+++ linux-2.6/fs/inode.c 2010-10-19 14:37:05.000000000 +1100
@@ -445,7 +445,7 @@
* If the inode has metadata buffers attached to mapping->private_list then
* try to remove them.
*/
-static void prune_icache(int nr_to_scan)
+static void prune_icache(unsigned long nr_to_scan)
{
LIST_HEAD(freeable);
int nr_pruned = 0;
@@ -503,27 +503,36 @@
* not open and the dcache references to those inodes have already been
* reclaimed.
*
- * This function is passed the number of inodes to scan, and it returns the
- * total number of remaining possibly-reclaimable inodes.
+ * This function is defined according to shrinker API described in linux/mm.h.
*/
-static int shrink_icache_memory(struct shrinker *shrink, int nr, gfp_t gfp_mask)
+static void shrink_icache_memory(struct shrinker *shrink,
+ struct zone *zone, unsigned long scanned,
+ unsigned long total, unsigned long global,
+ unsigned long flags, gfp_t gfp_mask)
{
- if (nr) {
- /*
- * Nasty deadlock avoidance. We may hold various FS locks,
- * and we don't want to recurse into the FS that called us
- * in clear_inode() and friends..
- */
- if (!(gfp_mask & __GFP_FS))
- return -1;
+ static unsigned long nr_to_scan;
+ unsigned long nr;
+
+ shrinker_add_scan(&nr_to_scan, scanned, global,
+ inodes_stat.nr_unused,
+ SHRINK_DEFAULT_SEEKS * 100 / sysctl_vfs_cache_pressure);
+ /*
+ * Nasty deadlock avoidance. We may hold various FS locks,
+ * and we don't want to recurse into the FS that called us
+ * in clear_inode() and friends..
+ */
+ if (!(gfp_mask & __GFP_FS))
+ return;
+
+ while ((nr = shrinker_do_scan(&nr_to_scan, SHRINK_BATCH))) {
prune_icache(nr);
+ count_vm_events(SLABS_SCANNED, nr);
+ cond_resched();
}
- return (inodes_stat.nr_unused / 100) * sysctl_vfs_cache_pressure;
}
static struct shrinker icache_shrinker = {
- .shrink = shrink_icache_memory,
- .seeks = DEFAULT_SEEKS,
+ .shrink_zone = shrink_icache_memory,
};
static void __wait_on_freeing_inode(struct inode *inode);
next prev parent reply other threads:[~2010-10-19 3:56 UTC|newest]
Thread overview: 70+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-10-19 3:42 [patch 00/35] my inode scaling series for review npiggin
2010-10-19 3:42 ` [patch 01/35] bit_spinlock: add required includes npiggin
2010-10-19 3:42 ` [patch 02/35] kernel: add bl_list npiggin
2010-10-19 3:42 ` [patch 03/35] mm: implement per-zone shrinker npiggin
2010-10-19 4:49 ` KOSAKI Motohiro
2010-10-19 5:33 ` Nick Piggin
2010-10-19 5:40 ` KOSAKI Motohiro
2010-10-19 3:42 ` npiggin [this message]
2010-10-19 3:42 ` [patch 05/35] fs: icache lock s_inodes list npiggin
2010-10-19 3:42 ` [patch 06/35] fs: icache lock inode hash npiggin
2010-10-19 3:42 ` [patch 07/35] fs: icache lock i_state npiggin
2010-10-19 10:47 ` Miklos Szeredi
2010-10-19 17:06 ` Peter Zijlstra
2010-10-19 3:42 ` [patch 08/35] fs: icache lock i_count npiggin
2010-10-19 10:16 ` Boaz Harrosh
2010-10-20 2:14 ` Nick Piggin
2010-10-19 3:42 ` [patch 09/35] fs: icache lock lru/writeback lists npiggin
2010-10-19 3:42 ` [patch 10/35] fs: icache atomic inodes_stat npiggin
2010-10-19 3:42 ` [patch 11/35] fs: icache lock inode state npiggin
2010-10-19 3:42 ` [patch 12/35] fs: inode atomic last_ino, iunique lock npiggin
2010-10-19 3:42 ` [patch 13/35] fs: icache remove inode_lock npiggin
2010-10-19 3:42 ` [patch 14/35] fs: icache factor hash lock into functions npiggin
2010-10-19 3:42 ` [patch 15/35] fs: icache per-bucket inode hash locks npiggin
2010-10-19 3:42 ` [patch 16/35] fs: icache lazy inode lru npiggin
2010-10-19 3:42 ` [patch 17/35] fs: icache RCU free inodes npiggin
2010-10-19 3:42 ` [patch 18/35] fs: avoid inode RCU freeing for pseudo fs npiggin
2010-10-19 3:42 ` [patch 19/35] fs: icache remove redundant i_sb_list umount locking npiggin
2010-10-20 12:46 ` Al Viro
2010-10-20 13:03 ` Nick Piggin
2010-10-20 13:27 ` Al Viro
2010-10-19 3:42 ` [patch 20/35] fs: icache rcu walk for i_sb_list npiggin
2010-10-19 3:42 ` [patch 21/35] fs: icache per-cpu nr_inodes, non-atomic nr_unused counters npiggin
2010-10-19 3:42 ` [patch 22/35] fs: icache per-cpu last_ino allocator npiggin
2010-10-19 3:42 ` [patch 23/35] fs: icache use per-CPU lists and locks for sb inode lists npiggin
2010-10-19 15:33 ` Miklos Szeredi
2010-10-20 2:37 ` Nick Piggin
2010-10-19 3:42 ` [patch 24/35] fs: icache use RCU to avoid locking in hash lookups npiggin
2010-10-19 3:42 ` [patch 25/35] fs: icache reduce some locking overheads npiggin
2010-10-19 3:42 ` [patch 26/35] fs: icache alloc anonymous inode allocation npiggin
2010-10-19 15:50 ` Miklos Szeredi
2010-10-20 2:38 ` Nick Piggin
2010-10-19 16:33 ` Christoph Hellwig
2010-10-20 3:07 ` Nick Piggin
2010-10-19 3:42 ` [patch 27/35] fs: icache split IO and LRU lists npiggin
2010-10-19 16:12 ` Miklos Szeredi
2010-10-20 2:41 ` Nick Piggin
2010-10-19 3:42 ` [patch 28/35] fs: icache split writeback and lru locks npiggin
2010-10-19 3:42 ` [patch 29/35] fs: icache per-bdi writeback list locking npiggin
2010-10-19 3:42 ` [patch 30/35] fs: icache lazy LRU avoid LRU locking after IO operation npiggin
2010-10-19 3:42 ` [patch 31/35] fs: icache per-zone inode LRU npiggin
2010-10-19 12:38 ` Dave Chinner
2010-10-20 2:35 ` Nick Piggin
2010-10-20 3:12 ` Nick Piggin
2010-10-20 9:43 ` Dave Chinner
2010-10-20 10:02 ` Nick Piggin
2010-10-20 3:14 ` KOSAKI Motohiro
2010-10-20 3:20 ` Nick Piggin
2010-10-20 3:29 ` KOSAKI Motohiro
2010-10-20 10:19 ` Dave Chinner
2010-10-20 10:41 ` Nick Piggin
2010-10-19 3:42 ` [patch 32/35] fs: icache minimise I_FREEING latency npiggin
2010-10-19 3:42 ` [patch 33/35] fs: icache introduce inode_get/inode_get_ilock npiggin
2010-10-19 10:17 ` Boaz Harrosh
2010-10-20 2:17 ` Nick Piggin
2010-10-19 3:42 ` [patch 34/35] fs: inode rename i_count to i_refs npiggin
2010-10-19 3:42 ` [patch 35/35] fs: icache document more lock orders npiggin
2010-10-19 16:22 ` [patch 00/35] my inode scaling series for review Christoph Hellwig
2010-10-20 3:05 ` Nick Piggin
2010-10-20 13:14 ` Al Viro
2010-10-20 13:59 ` Nick Piggin
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20101019034655.866685321@kernel.dk \
--to=npiggin@kernel.dk \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).