From: Dave Chinner <david@fromorbit.com>
To: linux-fsdevel@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Subject: [PATCH 17/19] fs: Reduce inode I_FREEING and factor inode disposal
Date: Sat, 16 Oct 2010 19:14:11 +1100 [thread overview]
Message-ID: <1287216853-17634-18-git-send-email-david@fromorbit.com> (raw)
In-Reply-To: <1287216853-17634-1-git-send-email-david@fromorbit.com>
From: Dave Chinner <dchinner@redhat.com>
Inode reclaim can push many inodes into the I_FREEING state before
it actually frees them. During the time it gathers these inodes, it
can call iput(), invalidate_mapping_pages, be preempted, etc. As a
result, holding inodes in I_FREEING can cause pauses.
After the inode scalability work, there is not a big reason to batch
up inodes to reclaim them, so we can dispose them as they are found
from the LRU.
Unmount does a very similar reclaim process via invalidate_list(),
but currently uses the i_lru list to aggregate inodes for a batched
disposal. This requires taking the inode_lru_lock for every inode we
want to dispose. Instead, take the inodes off the superblock inode
list (as we already hold the lock) and use i_sb_list as the
aggregator for inodes to dispose to reduce lock traffic.
Further, iput_final() does the same inode cleanup as reclaim and
unmount, so convert them all to use a single function for destroying
inodes. This is written such that the callers can optimise list
removals to avoid unneccessary lock round trips when removing inodes
from lists.
Based on a patch originally from Nick Piggin.
Signed-off-by: Dave Chinner <dchinner@redhat.com>
---
fs/inode.c | 109 +++++++++++++++++++++++++++++++----------------------------
1 files changed, 57 insertions(+), 52 deletions(-)
diff --git a/fs/inode.c b/fs/inode.c
index 5cddf45..bea1657 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -32,6 +32,8 @@
*
* inode->i_lock is *always* the innermost lock.
*
+ * inode->i_lock is *always* the innermost lock.
+ *
* inode->i_lock protects:
* i_ref i_state
* inode hash lock protects:
@@ -49,8 +51,8 @@
*
* sb inode lock
* inode_lru_lock
- * wb->b_lock
- * inode->i_lock
+ * wb->b_lock
+ * inode->i_lock
*
* wb->b_lock
* sb_lock (pin sb for writeback)
@@ -460,6 +462,44 @@ static void evict(struct inode *inode)
}
/*
+ * Free the inode passed in, removing it from the lists it is still connected
+ * to but avoiding unnecessary lock round-trips for the lists it is no longer
+ * on.
+ *
+ * An inode must already be marked I_FREEING so that we avoid the inode being
+ * moved back onto lists if we race with other code that manipulates the lists
+ * (e.g. writeback_single_inode). The caller
+ */
+static void dispose_one_inode(struct inode *inode)
+{
+ BUG_ON(!(inode->i_state & I_FREEING));
+
+ /*
+ * move the inode off the IO lists and LRU once
+ * I_FREEING is set so that it won't get moved back on
+ * there if it is dirty.
+ */
+ if (!list_empty(&inode->i_wb_list))
+ inode_wb_list_del(inode);
+
+ if (!list_empty(&inode->i_lru))
+ inode_lru_list_del(inode);
+
+ if (!list_empty(&inode->i_sb_list)) {
+ spin_lock(&inode->i_sb->s_inodes_lock);
+ list_del_init(&inode->i_sb_list);
+ spin_unlock(&inode->i_sb->s_inodes_lock);
+ }
+
+ evict(inode);
+
+ remove_inode_hash(inode);
+ wake_up_inode(inode);
+ BUG_ON(inode->i_state != (I_FREEING | I_CLEAR));
+ destroy_inode(inode);
+}
+
+/*
* dispose_list - dispose of the contents of a local list
* @head: the head of the list to free
*
@@ -471,18 +511,10 @@ static void dispose_list(struct list_head *head)
while (!list_empty(head)) {
struct inode *inode;
- inode = list_first_entry(head, struct inode, i_lru);
- list_del_init(&inode->i_lru);
-
- evict(inode);
-
- remove_inode_hash(inode);
- spin_lock(&inode->i_sb->s_inodes_lock);
+ inode = list_first_entry(head, struct inode, i_sb_list);
list_del_init(&inode->i_sb_list);
- spin_unlock(&inode->i_sb->s_inodes_lock);
- wake_up_inode(inode);
- destroy_inode(inode);
+ dispose_one_inode(inode);
}
}
@@ -523,17 +555,8 @@ static int invalidate_list(struct super_block *sb, struct list_head *head,
inode->i_state |= I_FREEING;
spin_unlock(&inode->i_lock);
- /*
- * move the inode off the IO lists and LRU once
- * I_FREEING is set so that it won't get moved back on
- * there if it is dirty.
- */
- inode_wb_list_del(inode);
-
- spin_lock(&inode_lru_lock);
- list_move(&inode->i_lru, dispose);
- percpu_counter_dec(&nr_inodes_unused);
- spin_unlock(&inode_lru_lock);
+ /* save a lock round trip by removing the inode here. */
+ list_move(&inode->i_sb_list, dispose);
continue;
}
spin_unlock(&inode->i_lock);
@@ -552,17 +575,17 @@ static int invalidate_list(struct super_block *sb, struct list_head *head,
*/
int invalidate_inodes(struct super_block *sb)
{
- int busy;
LIST_HEAD(throw_away);
+ int busy;
down_write(&iprune_sem);
spin_lock(&sb->s_inodes_lock);
fsnotify_unmount_inodes(&sb->s_inodes);
busy = invalidate_list(sb, &sb->s_inodes, &throw_away);
spin_unlock(&sb->s_inodes_lock);
+ up_write(&iprune_sem);
dispose_list(&throw_away);
- up_write(&iprune_sem);
return busy;
}
@@ -600,7 +623,6 @@ static int can_unuse(struct inode *inode)
*/
static void prune_icache(int nr_to_scan)
{
- LIST_HEAD(freeable);
int nr_scanned;
unsigned long reap = 0;
@@ -660,15 +682,15 @@ static void prune_icache(int nr_to_scan)
inode->i_state |= I_FREEING;
spin_unlock(&inode->i_lock);
- /*
- * move the inode off the io lists and lru once
- * i_freeing is set so that it won't get moved back on
- * there if it is dirty.
- */
- inode_wb_list_del(inode);
-
- list_move(&inode->i_lru, &freeable);
+ /* save a lock round trip by removing the inode here. */
+ list_del_init(&inode->i_lru);
percpu_counter_dec(&nr_inodes_unused);
+ spin_unlock(&inode_lru_lock);
+
+ dispose_one_inode(inode);
+ cond_resched();
+
+ spin_lock(&inode_lru_lock);
}
if (current_is_kswapd())
__count_vm_events(KSWAPD_INODESTEAL, reap);
@@ -676,7 +698,6 @@ static void prune_icache(int nr_to_scan)
__count_vm_events(PGINODESTEAL, reap);
spin_unlock(&inode_lru_lock);
- dispose_list(&freeable);
up_read(&iprune_sem);
}
@@ -1461,23 +1482,7 @@ static void iput_final(struct inode *inode)
inode->i_state |= I_FREEING;
spin_unlock(&inode->i_lock);
- /*
- * After we delete the inode from the LRU and IO lists here, we avoid
- * moving dirty inodes back onto the LRU now because I_FREEING is set
- * and hence writeback_single_inode() won't move the inode around.
- */
- inode_wb_list_del(inode);
- inode_lru_list_del(inode);
-
- spin_lock(&sb->s_inodes_lock);
- list_del_init(&inode->i_sb_list);
- spin_unlock(&sb->s_inodes_lock);
-
- evict(inode);
- remove_inode_hash(inode);
- wake_up_inode(inode);
- BUG_ON(inode->i_state != (I_FREEING | I_CLEAR));
- destroy_inode(inode);
+ dispose_one_inode(inode);
}
/**
--
1.7.1
next prev parent reply other threads:[~2010-10-16 8:15 UTC|newest]
Thread overview: 59+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-10-16 8:13 Inode Lock Scalability V4 Dave Chinner
2010-10-16 8:13 ` [PATCH 01/19] fs: switch bdev inode bdi's correctly Dave Chinner
2010-10-16 9:30 ` Nick Piggin
2010-10-16 16:31 ` Christoph Hellwig
2010-10-16 8:13 ` [PATCH 02/19] kernel: add bl_list Dave Chinner
2010-10-16 9:51 ` Nick Piggin
2010-10-16 16:32 ` Christoph Hellwig
2010-10-16 8:13 ` [PATCH 03/19] fs: Convert nr_inodes and nr_unused to per-cpu counters Dave Chinner
2010-10-16 8:29 ` Eric Dumazet
2010-10-16 10:04 ` Dave Chinner
2010-10-16 10:27 ` Eric Dumazet
2010-10-16 17:26 ` Peter Zijlstra
2010-10-17 1:09 ` Dave Chinner
2010-10-17 1:12 ` Christoph Hellwig
2010-10-17 2:16 ` Dave Chinner
2010-10-16 8:13 ` [PATCH 04/19] fs: Implement lazy LRU updates for inodes Dave Chinner
2010-10-16 9:29 ` Nick Piggin
2010-10-16 16:59 ` Christoph Hellwig
2010-10-16 17:29 ` Nick Piggin
2010-10-16 17:34 ` Nick Piggin
2010-10-17 0:47 ` Christoph Hellwig
2010-10-17 0:47 ` Christoph Hellwig
2010-10-17 2:09 ` Nick Piggin
2010-10-17 1:53 ` Dave Chinner
2010-10-16 8:13 ` [PATCH 05/19] fs: inode split IO and LRU lists Dave Chinner
2010-10-16 8:14 ` [PATCH 06/19] fs: Clean up inode reference counting Dave Chinner
2010-10-16 8:14 ` [PATCH 07/19] exofs: use iput() for inode reference count decrements Dave Chinner
2010-10-16 8:14 ` [PATCH 08/19] fs: rework icount to be a locked variable Dave Chinner
2010-10-16 8:14 ` [PATCH 09/19] fs: Factor inode hash operations into functions Dave Chinner
2010-10-16 8:14 ` [PATCH 10/19] fs: Introduce per-bucket inode hash locks Dave Chinner
2010-10-16 8:14 ` [PATCH 11/19] fs: add a per-superblock lock for the inode list Dave Chinner
2010-10-16 8:14 ` [PATCH 12/19] fs: split locking of inode writeback and LRU lists Dave Chinner
2010-10-16 8:14 ` [PATCH 13/19] fs: Protect inode->i_state with the inode->i_lock Dave Chinner
2010-10-16 8:14 ` [PATCH 14/19] fs: introduce a per-cpu last_ino allocator Dave Chinner
2010-10-16 8:14 ` [PATCH 15/19] fs: Make iunique independent of inode_lock Dave Chinner
2010-10-16 8:14 ` [PATCH 16/19] fs: icache remove inode_lock Dave Chinner
2010-10-16 8:14 ` Dave Chinner [this message]
2010-10-17 1:30 ` [PATCH 17/19] fs: Reduce inode I_FREEING and factor inode disposal Christoph Hellwig
2010-10-17 2:49 ` Nick Piggin
2010-10-17 4:13 ` Dave Chinner
2010-10-17 4:35 ` Nick Piggin
2010-10-17 5:13 ` Nick Piggin
2010-10-17 6:52 ` Dave Chinner
2010-10-17 7:05 ` Nick Piggin
2010-10-17 23:39 ` Dave Chinner
2010-10-18 21:27 ` Sage Weil
2010-10-19 3:54 ` Nick Piggin
2010-10-16 8:14 ` [PATCH 18/19] fs: split __inode_add_to_list Dave Chinner
2010-10-16 8:14 ` [PATCH 19/19] fs: do not assign default i_ino in new_inode Dave Chinner
2010-10-16 9:09 ` Eric Dumazet
2010-10-16 16:35 ` Christoph Hellwig
2010-10-18 9:11 ` Eric Dumazet
2010-10-18 14:48 ` Christoph Hellwig
2010-10-16 17:55 ` Inode Lock Scalability V4 Nick Piggin
2010-10-17 2:47 ` Dave Chinner
2010-10-17 2:55 ` Nick Piggin
2010-10-17 2:57 ` Nick Piggin
2010-10-17 6:10 ` Dave Chinner
2010-10-17 6:34 ` 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=1287216853-17634-18-git-send-email-david@fromorbit.com \
--to=david@fromorbit.com \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.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).