Skip to contentSkip to conversation

ocfs2 updates

PATCH New Mark Fasheh 1 participant 1 message Jan 20, 2006

Subsystems (3)
lore
Share & tools
lore
#0 lore raw

PATCH 1/1 ocfs2 updates

Please pull from 'upstream-linus' branch of
git://oss.oracle.com/home/sourcebo/git/ocfs2.git

to receive the following updates:

 Documentation/filesystems/ocfs2.txt |    1 
 fs/Kconfig                          |    2 
 fs/ocfs2/buffer_head_io.c           |   10 -
 fs/ocfs2/dlm/dlmcommon.h            |    1 
 fs/ocfs2/dlm/dlmdomain.c            |   18 ++
 fs/ocfs2/dlm/dlmmaster.c            |   24 +--
 fs/ocfs2/dlm/dlmrecovery.c          |  250 ++++++++++++++++++++++++++++++------
 fs/ocfs2/dlm/dlmunlock.c            |   13 +
 fs/ocfs2/dlm/userdlm.c              |    2 
 fs/ocfs2/extent_map.c               |    2 
 fs/ocfs2/inode.c                    |    6 
 fs/ocfs2/inode.h                    |    4 
 fs/ocfs2/journal.c                  |   14 +-
 fs/ocfs2/ocfs2.h                    |    3 
 fs/ocfs2/super.c                    |    8 -
 fs/ocfs2/uptodate.c                 |   12 -
 fs/ocfs2/uptodate.h                 |    2 
 17 files changed, 290 insertions(+), 82 deletions(-)

Adrian Bunk:
OCFS2: __init / __exit problem fs/ocfs2/dlm/dlmrecovery.c must #include <linux/delay.h>

Arjan van de Ven:
ocfs2: Semaphore to mutex conversion.

J. Bruce Fields:
[OCFS2] Documentation Fix

Jeff Mahoney:
ocfs2/dlm: fix compilation on ia64

Joel Becker:
o Remove confusing Kconfig text for CONFIGFS_FS.

Kurt Hackel:
ocfs2/dlm: fixes

Mark Fasheh:
[OCFS2] Make ip_io_sem a mutex

Documentation/filesystems/ocfs2.txt +1 -0
index f2595ca..4389c68 100644
@@ -35,6 +35,7 @@ Features which OCFS2 does not support ye
 	  be cluster coherent.
 	- quotas
 	- cluster aware flock
+	- cluster aware lockf
 	- Directory change notification (F_NOTIFY)
 	- Distributed Caching (F_SETLEASE/F_GETLEASE/break_lease)
 	- POSIX ACLs
fs/Kconfig +0 -2
index ef78e3a..a732bea 100644
@@ -883,8 +883,6 @@ config CONFIGFS_FS
 	  Both sysfs and configfs can and should exist together on the
 	  same system. One is not a replacement for the other.
 
-	  If unsure, say N.
-
 endmenu
 
 menu "Miscellaneous filesystems"
fs/ocfs2/buffer_head_io.c +5 -5
index d424041..bae3d75 100644
@@ -58,7 +58,7 @@ int ocfs2_write_block(struct ocfs2_super
 		goto out;
 	}
 
-	down(&OCFS2_I(inode)->ip_io_sem);
+	mutex_lock(&OCFS2_I(inode)->ip_io_mutex);
 
 	lock_buffer(bh);
 	set_buffer_uptodate(bh);
@@ -82,7 +82,7 @@ int ocfs2_write_block(struct ocfs2_super
 		brelse(bh);
 	}
 
-	up(&OCFS2_I(inode)->ip_io_sem);
+	mutex_unlock(&OCFS2_I(inode)->ip_io_mutex);
 out:
 	mlog_exit(ret);
 	return ret;
@@ -125,13 +125,13 @@ int ocfs2_read_blocks(struct ocfs2_super
 		flags &= ~OCFS2_BH_CACHED;
 
 	if (inode)
-		down(&OCFS2_I(inode)->ip_io_sem);
+		mutex_lock(&OCFS2_I(inode)->ip_io_mutex);
 	for (i = 0 ; i < nr ; i++) {
 		if (bhs[i] == NULL) {
 			bhs[i] = sb_getblk(sb, block++);
 			if (bhs[i] == NULL) {
 				if (inode)
-					up(&OCFS2_I(inode)->ip_io_sem);
+					mutex_unlock(&OCFS2_I(inode)->ip_io_mutex);
 				status = -EIO;
 				mlog_errno(status);
 				goto bail;
@@ -220,7 +220,7 @@ int ocfs2_read_blocks(struct ocfs2_super
 			ocfs2_set_buffer_uptodate(inode, bh);
 	}
 	if (inode)
-		up(&OCFS2_I(inode)->ip_io_sem);
+		mutex_unlock(&OCFS2_I(inode)->ip_io_mutex);
 
 	mlog(ML_BH_IO, "block=(%"MLFu64"), nr=(%d), cached=%s\n", block, nr,
 	     (!(flags & OCFS2_BH_CACHED) || ignore_cache) ? "no" : "yes");
fs/ocfs2/dlm/dlmcommon.h +1 -0
index 3fecba0..42eb53b 100644
@@ -657,6 +657,7 @@ void dlm_complete_thread(struct dlm_ctxt
 int dlm_launch_recovery_thread(struct dlm_ctxt *dlm);
 void dlm_complete_recovery_thread(struct dlm_ctxt *dlm);
 void dlm_wait_for_recovery(struct dlm_ctxt *dlm);
+int dlm_is_node_dead(struct dlm_ctxt *dlm, u8 node);
 
 void dlm_put(struct dlm_ctxt *dlm);
 struct dlm_ctxt *dlm_grab(struct dlm_ctxt *dlm);
fs/ocfs2/dlm/dlmdomain.c +17 -1
index da3c220..6ee3083 100644
@@ -573,8 +573,11 @@ static int dlm_query_join_handler(struct
 	spin_lock(&dlm_domain_lock);
 	dlm = __dlm_lookup_domain_full(query->domain, query->name_len);
 	/* Once the dlm ctxt is marked as leaving then we don't want
-	 * to be put in someone's domain map. */
+	 * to be put in someone's domain map. 
+	 * Also, explicitly disallow joining at certain troublesome
+	 * times (ie. during recovery). */
 	if (dlm && dlm->dlm_state != DLM_CTXT_LEAVING) {
+		int bit = query->node_idx;
 		spin_lock(&dlm->spinlock);
 
 		if (dlm->dlm_state == DLM_CTXT_NEW &&
@@ -586,6 +589,19 @@ static int dlm_query_join_handler(struct
 		} else if (dlm->joining_node != DLM_LOCK_RES_OWNER_UNKNOWN) {
 			/* Disallow parallel joins. */
 			response = JOIN_DISALLOW;
+		} else if (dlm->reco.state & DLM_RECO_STATE_ACTIVE) {
+			mlog(ML_NOTICE, "node %u trying to join, but recovery "
+			     "is ongoing.\n", bit);
+			response = JOIN_DISALLOW;
+		} else if (test_bit(bit, dlm->recovery_map)) {
+			mlog(ML_NOTICE, "node %u trying to join, but it "
+			     "still needs recovery.\n", bit);
+			response = JOIN_DISALLOW;
+		} else if (test_bit(bit, dlm->domain_map)) {
+			mlog(ML_NOTICE, "node %u trying to join, but it "
+			     "is still in the domain! needs recovery?\n",
+			     bit);
+			response = JOIN_DISALLOW;
 		} else {
 			/* Alright we're fully a part of this domain
 			 * so we keep some state as to who's joining
fs/ocfs2/dlm/dlmmaster.c +13 -11
index 27e984f..a3194fe 100644
@@ -1050,17 +1050,10 @@ static int dlm_restart_lock_mastery(stru
 	node = dlm_bitmap_diff_iter_next(&bdi, &sc);
 	while (node >= 0) {
 		if (sc == NODE_UP) {
-			/* a node came up.  easy.  might not even need
-			 * to talk to it if its node number is higher
-			 * or if we are already blocked. */
-			mlog(0, "node up! %d\n", node);
-			if (blocked)
-				goto next;
-
-			if (node > dlm->node_num) {
-				mlog(0, "node > this node. skipping.\n");
-				goto next;
-			}
+			/* a node came up.  clear any old vote from
+			 * the response map and set it in the vote map
+			 * then restart the mastery. */
+			mlog(ML_NOTICE, "node %d up while restarting\n", node);
 
 			/* redo the master request, but only for the new node */
 			mlog(0, "sending request to new node\n");
@@ -2005,6 +1998,15 @@ fail:
 				break;
 
 			mlog(0, "timed out during migration\n");
+			/* avoid hang during shutdown when migrating lockres 
+			 * to a node which also goes down */
+			if (dlm_is_node_dead(dlm, target)) {
+				mlog(0, "%s:%.*s: expected migration target %u "
+				     "is no longer up.  restarting.\n",
+				     dlm->name, res->lockname.len,
+				     res->lockname.name, target);
+				ret = -ERESTARTSYS;
+			}
 		}
 		if (ret == -ERESTARTSYS) {
 			/* migration failed, detach and clean up mle */
fs/ocfs2/dlm/dlmrecovery.c +213 -37

427 lines not on this page · raw message

fs/ocfs2/dlm/dlmunlock.c +13 -0
index cec2ce1..c95f08d 100644
@@ -188,6 +188,19 @@ static enum dlm_status dlmunlock_common(
 			actions &= ~(DLM_UNLOCK_REMOVE_LOCK|
 				     DLM_UNLOCK_REGRANT_LOCK|
 				     DLM_UNLOCK_CLEAR_CONVERT_TYPE);
+		} else if (status == DLM_RECOVERING || 
+			   status == DLM_MIGRATING || 
+			   status == DLM_FORWARD) {
+			/* must clear the actions because this unlock
+			 * is about to be retried.  cannot free or do
+			 * any list manipulation. */
+			mlog(0, "%s:%.*s: clearing actions, %s\n",
+			     dlm->name, res->lockname.len,
+			     res->lockname.name,
+			     status==DLM_RECOVERING?"recovering":
+			     (status==DLM_MIGRATING?"migrating":
+			      "forward"));
+			actions = 0;
 		}
 		if (flags & LKM_CANCEL)
 			lock->cancel_pending = 0;
fs/ocfs2/dlm/userdlm.c +1 -1
index e1fdd28..c3764f4 100644
@@ -27,7 +27,7 @@
  * Boston, MA 021110-1307, USA.
  */
 
-#include <asm/signal.h>
+#include <linux/signal.h>
 
 #include <linux/module.h>
 #include <linux/fs.h>
fs/ocfs2/extent_map.c +1 -1
index f2fb40c..eb2bd8a 100644
@@ -988,7 +988,7 @@ int __init init_ocfs2_extent_maps(void)
 	return 0;
 }
 
-void __exit exit_ocfs2_extent_maps(void)
+void exit_ocfs2_extent_maps(void)
 {
 	kmem_cache_destroy(ocfs2_em_ent_cachep);
 }
fs/ocfs2/inode.c +3 -3
index d4ecc06..8122489 100644
@@ -903,10 +903,10 @@ void ocfs2_clear_inode(struct inode *ino
 			"Clear inode of %"MLFu64", inode is locked\n",
 			oi->ip_blkno);
 
-	mlog_bug_on_msg(down_trylock(&oi->ip_io_sem),
-			"Clear inode of %"MLFu64", io_sem is locked\n",
+	mlog_bug_on_msg(!mutex_trylock(&oi->ip_io_mutex),
+			"Clear inode of %"MLFu64", io_mutex is locked\n",
 			oi->ip_blkno);
-	up(&oi->ip_io_sem);
+	mutex_unlock(&oi->ip_io_mutex);
 
 	/*
 	 * down_trylock() returns 0, down_write_trylock() returns 1
fs/ocfs2/inode.h +2 -2
index 9b01774..84c5079 100644
@@ -46,10 +46,10 @@ struct ocfs2_inode_info
 	struct list_head		ip_io_markers;
 	int				ip_orphaned_slot;
 
-	struct semaphore		ip_io_sem;
+	struct mutex			ip_io_mutex;
 
 	/* Used by the journalling code to attach an inode to a
-	 * handle.  These are protected by ip_io_sem in order to lock
+	 * handle.  These are protected by ip_io_mutex in order to lock
 	 * out other I/O to the inode until we either commit or
 	 * abort. */
 	struct list_head		ip_handle_list;
fs/ocfs2/journal.c +7 -7
index 303c8d9..ccabed9 100644
@@ -401,7 +401,7 @@ int ocfs2_journal_access(struct ocfs2_jo
 	 * j_trans_barrier for us. */
 	ocfs2_set_inode_lock_trans(OCFS2_SB(inode->i_sb)->journal, inode);
 
-	down(&OCFS2_I(inode)->ip_io_sem);
+	mutex_lock(&OCFS2_I(inode)->ip_io_mutex);
 	switch (type) {
 	case OCFS2_JOURNAL_ACCESS_CREATE:
 	case OCFS2_JOURNAL_ACCESS_WRITE:
@@ -416,7 +416,7 @@ int ocfs2_journal_access(struct ocfs2_jo
 		status = -EINVAL;
 		mlog(ML_ERROR, "Uknown access type!\n");
 	}
-	up(&OCFS2_I(inode)->ip_io_sem);
+	mutex_unlock(&OCFS2_I(inode)->ip_io_mutex);
 
 	if (status < 0)
 		mlog(ML_ERROR, "Error %d getting %d access to buffer!\n",
@@ -1072,10 +1072,10 @@ restart:
 					NULL);
 
 bail:
-	down(&osb->recovery_lock);
+	mutex_lock(&osb->recovery_lock);
 	if (!status &&
 	    !ocfs2_node_map_is_empty(osb, &osb->recovery_map)) {
-		up(&osb->recovery_lock);
+		mutex_unlock(&osb->recovery_lock);
 		goto restart;
 	}
 
@@ -1083,7 +1083,7 @@ bail:
 	mb(); /* sync with ocfs2_recovery_thread_running */
 	wake_up(&osb->recovery_event);
 
-	up(&osb->recovery_lock);
+	mutex_unlock(&osb->recovery_lock);
 
 	mlog_exit(status);
 	/* no one is callint kthread_stop() for us so the kthread() api
@@ -1098,7 +1098,7 @@ void ocfs2_recovery_thread(struct ocfs2_
 	mlog_entry("(node_num=%d, osb->node_num = %d)\n",
 		   node_num, osb->node_num);
 
-	down(&osb->recovery_lock);
+	mutex_lock(&osb->recovery_lock);
 	if (osb->disable_recovery)
 		goto out;
 
@@ -1120,7 +1120,7 @@ void ocfs2_recovery_thread(struct ocfs2_
 	}
 
 out:
-	up(&osb->recovery_lock);
+	mutex_unlock(&osb->recovery_lock);
 	wake_up(&osb->recovery_event);
 
 	mlog_exit_void();
fs/ocfs2/ocfs2.h +2 -1
index f468c60..8d8e477 100644
@@ -33,6 +33,7 @@
 #include <linux/rbtree.h>
 #include <linux/workqueue.h>
 #include <linux/kref.h>
+#include <linux/mutex.h>
 
 #include "cluster/nodemanager.h"
 #include "cluster/heartbeat.h"
@@ -233,7 +234,7 @@ struct ocfs2_super
 	struct proc_dir_entry *proc_sub_dir; /* points to /proc/fs/ocfs2/<maj_min> */
 
 	atomic_t vol_state;
-	struct semaphore recovery_lock;
+	struct mutex recovery_lock;
 	struct task_struct *recovery_thread_task;
 	int disable_recovery;
 	wait_queue_head_t checkpoint_event;
fs/ocfs2/super.c +4 -4
index 364d64b..e7e17bd 100644
@@ -932,7 +932,7 @@ static void ocfs2_inode_init_once(void *
 		oi->ip_dir_start_lookup = 0;
 
 		init_rwsem(&oi->ip_alloc_sem);
-		init_MUTEX(&(oi->ip_io_sem));
+		mutex_init(&oi->ip_io_mutex);
 
 		oi->ip_blkno = 0ULL;
 		oi->ip_clusters = 0;
@@ -1137,9 +1137,9 @@ static void ocfs2_dismount_volume(struct
 
 	/* disable any new recovery threads and wait for any currently
 	 * running ones to exit. Do this before setting the vol_state. */
-	down(&osb->recovery_lock);
+	mutex_lock(&osb->recovery_lock);
 	osb->disable_recovery = 1;
-	up(&osb->recovery_lock);
+	mutex_unlock(&osb->recovery_lock);
 	wait_event(osb->recovery_event, !ocfs2_recovery_thread_running(osb));
 
 	/* At this point, we know that no more recovery threads can be
@@ -1283,7 +1283,7 @@ static int ocfs2_initialize_super(struct
 	snprintf(osb->dev_str, sizeof(osb->dev_str), "%u,%u",
 		 MAJOR(osb->sb->s_dev), MINOR(osb->sb->s_dev));
 
-	init_MUTEX(&osb->recovery_lock);
+	mutex_init(&osb->recovery_lock);
 
 	osb->disable_recovery = 0;
 	osb->recovery_thread_task = NULL;
fs/ocfs2/uptodate.c +6 -6
index 3a0458f..300b5be 100644
@@ -388,7 +388,7 @@ out_free:
 	}
 }
 
-/* Item insertion is guarded by ip_io_sem, so the insertion path takes
+/* Item insertion is guarded by ip_io_mutex, so the insertion path takes
  * advantage of this by not rechecking for a duplicate insert during
  * the slow case. Additionally, if the cache needs to be bumped up to
  * a tree, the code will not recheck after acquiring the lock --
@@ -418,7 +418,7 @@ void ocfs2_set_buffer_uptodate(struct in
 	     (unsigned long long) bh->b_blocknr);
 
 	/* No need to recheck under spinlock - insertion is guarded by
-	 * ip_io_sem */
+	 * ip_io_mutex */
 	spin_lock(&oi->ip_lock);
 	if (ocfs2_insert_can_use_array(oi, ci)) {
 		/* Fast case - it's an array and there's a free
@@ -440,7 +440,7 @@ void ocfs2_set_buffer_uptodate(struct in
 
 /* Called against a newly allocated buffer. Most likely nobody should
  * be able to read this sort of metadata while it's still being
- * allocated, but this is careful to take ip_io_sem anyway. */
+ * allocated, but this is careful to take ip_io_mutex anyway. */
 void ocfs2_set_new_buffer_uptodate(struct inode *inode,
 				   struct buffer_head *bh)
 {
@@ -451,9 +451,9 @@ void ocfs2_set_new_buffer_uptodate(struc
 
 	set_buffer_uptodate(bh);
 
-	down(&oi->ip_io_sem);
+	mutex_lock(&oi->ip_io_mutex);
 	ocfs2_set_buffer_uptodate(inode, bh);
-	up(&oi->ip_io_sem);
+	mutex_unlock(&oi->ip_io_mutex);
 }
 
 /* Requires ip_lock. */
@@ -537,7 +537,7 @@ int __init init_ocfs2_uptodate_cache(voi
 	return 0;
 }
 
-void __exit exit_ocfs2_uptodate_cache(void)
+void exit_ocfs2_uptodate_cache(void)
 {
 	if (ocfs2_uptodate_cachep)
 		kmem_cache_destroy(ocfs2_uptodate_cachep);
fs/ocfs2/uptodate.h +1 -1
index e5aacdf..01cd32d 100644
@@ -27,7 +27,7 @@
 #define OCFS2_UPTODATE_H
 
 int __init init_ocfs2_uptodate_cache(void);
-void __exit exit_ocfs2_uptodate_cache(void);
+void exit_ocfs2_uptodate_cache(void);
 
 void ocfs2_metadata_cache_init(struct inode *inode);
 void ocfs2_metadata_cache_purge(struct inode *inode);