[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>

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 {