From fee096deb4f33897937b974cb2c5168bab7935be Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 19 Nov 2009 18:12:05 +0000 Subject: CacheFiles: Catch an overly long wait for an old active object Catch an overly long wait for an old, dying active object when we want to replace it with a new one. The probability is that all the slow-work threads are hogged, and the delete can't get a look in. What we do instead is: (1) if there's nothing in the slow work queue, we sleep until either the dying object has finished dying or there is something in the slow work queue behind which we can queue our object. (2) if there is something in the slow work queue, we return ETIMEDOUT to fscache_lookup_object(), which then puts us back on the slow work queue, presumably behind the deletion that we're blocked by. We are then deferred for a while until we work our way back through the queue - without blocking a slow-work thread unnecessarily. A backtrace similar to the following may appear in the log without this patch: INFO: task kslowd004:5711 blocked for more than 120 seconds. "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. kslowd004 D 0000000000000000 0 5711 2 0x00000080 ffff88000340bb80 0000000000000046 ffff88002550d000 0000000000000000 ffff88002550d000 0000000000000007 ffff88000340bfd8 ffff88002550d2a8 000000000000ddf0 00000000000118c0 00000000000118c0 ffff88002550d2a8 Call Trace: [] ? trace_hardirqs_on+0xd/0xf [] ? cachefiles_wait_bit+0x0/0xd [cachefiles] [] cachefiles_wait_bit+0x9/0xd [cachefiles] [] __wait_on_bit+0x43/0x76 [] ? ext3_xattr_get+0x1ec/0x270 [] out_of_line_wait_on_bit+0x69/0x74 [] ? cachefiles_wait_bit+0x0/0xd [cachefiles] [] ? wake_bit_function+0x0/0x2e [] cachefiles_mark_object_active+0x203/0x23b [cachefiles] [] cachefiles_walk_to_object+0x558/0x827 [cachefiles] [] cachefiles_lookup_object+0xac/0x12a [cachefiles] [] fscache_lookup_object+0x1c7/0x214 [fscache] [] fscache_object_state_machine+0xa5/0x52d [fscache] [] fscache_object_slow_work_execute+0x5f/0xa0 [fscache] [] slow_work_execute+0x18f/0x2d1 [] slow_work_thread+0x1c5/0x308 [] ? autoremove_wake_function+0x0/0x34 [] ? slow_work_thread+0x0/0x308 [] kthread+0x7a/0x82 [] child_rip+0xa/0x20 [] ? restore_args+0x0/0x30 [] ? kthread+0x0/0x82 [] ? child_rip+0x0/0x20 1 lock held by kslowd004/5711: #0: (&sb->s_type->i_mutex_key#7/1){+.+.+.}, at: [] cachefiles_walk_to_object+0x1b3/0x827 [cachefiles] Signed-off-by: David Howells --- Documentation/filesystems/caching/fscache.txt | 1 + 1 file changed, 1 insertion(+) (limited to 'Documentation') diff --git a/Documentation/filesystems/caching/fscache.txt b/Documentation/filesystems/caching/fscache.txt index 3c23411956bb..a91e2e2095b0 100644 --- a/Documentation/filesystems/caching/fscache.txt +++ b/Documentation/filesystems/caching/fscache.txt @@ -235,6 +235,7 @@ proc files. neg=N Number of negative lookups made pos=N Number of positive lookups made crt=N Number of objects created by lookup + tmo=N Number of lookups timed out and requeued Updates n=N Number of update cookie requests seen nul=N Number of upd reqs given a NULL parent run=N Number of upd reqs granted CPU time -- cgit v1.2.2