diff options
author | Benjamin Marzinski <bmarzins@redhat.com> | 2007-08-23 13:19:05 -0500 |
---|---|---|
committer | Steven Whitehouse <swhiteho@redhat.com> | 2007-10-10 08:55:48 +0100 |
commit | c4f68a130fc1795e4a75ec5bdaf9e85d86c22419 (patch) | |
tree | 37251ae5634d4b73b5224e3e8679f92472de0ebe /fs/gfs2/incore.h | |
parent | d1e2777d4f419a865ddccdb9b3412021d0e4de51 (diff) | |
download | linux-c4f68a130fc1795e4a75ec5bdaf9e85d86c22419.tar.gz linux-c4f68a130fc1795e4a75ec5bdaf9e85d86c22419.tar.xz |
[GFS2] delay glock demote for a minimum hold time
When a lot of IO, with some distributed mmap IO, is run on a GFS2 filesystem in
a cluster, it will deadlock. The reason is that do_no_page() will repeatedly
call gfs2_sharewrite_nopage(), because each node keeps giving up the glock
too early, and is forced to call unmap_mapping_range(). This bumps the
mapping->truncate_count sequence count, forcing do_no_page() to retry. This
patch institutes a minimum glock hold time a tenth a second. This insures
that even in heavy contention cases, the node has enough time to get some
useful work done before it gives up the glock.
A second issue is that when gfs2_glock_dq() is called from within a page fault
to demote a lock, and the associated page needs to be written out, it will
try to acqire a lock on it, but it has already been locked at a higher level.
This patch puts makes gfs2_glock_dq() use the work queue as well, to avoid this
issue. This is the same patch as Steve Whitehouse originally proposed to fix
this issue, execpt that gfs2_glock_dq() now grabs a reference to the glock
before it queues up the work on it.
Signed-off-by: Benjamin E. Marzinski <bmarzins@redhat.com>
Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
Diffstat (limited to 'fs/gfs2/incore.h')
-rw-r--r-- | fs/gfs2/incore.h | 5 |
1 files changed, 5 insertions, 0 deletions
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h index 1390b30daf19..23b611aa70d2 100644 --- a/fs/gfs2/incore.h +++ b/fs/gfs2/incore.h @@ -11,6 +11,7 @@ #define __INCORE_DOT_H__ #include <linux/fs.h> +#include <linux/workqueue.h> #define DIO_WAIT 0x00000010 #define DIO_METADATA 0x00000020 @@ -130,6 +131,7 @@ struct gfs2_glock_operations { int (*go_lock) (struct gfs2_holder *gh); void (*go_unlock) (struct gfs2_holder *gh); const int go_type; + const unsigned long go_min_hold_time; }; enum { @@ -161,6 +163,7 @@ enum { GLF_LOCK = 1, GLF_STICKY = 2, GLF_DEMOTE = 3, + GLF_PENDING_DEMOTE = 4, GLF_DIRTY = 5, }; @@ -193,6 +196,7 @@ struct gfs2_glock { u64 gl_vn; unsigned long gl_stamp; + unsigned long gl_tchange; void *gl_object; struct list_head gl_reclaim; @@ -203,6 +207,7 @@ struct gfs2_glock { struct gfs2_log_element gl_le; struct list_head gl_ail_list; atomic_t gl_ail_count; + struct delayed_work gl_work; }; struct gfs2_alloc { |