linux-btrfs.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Josef Bacik <josef@redhat.com>
To: Martin Mailand <martin@tuxadero.com>
Cc: Josef Bacik <josef@redhat.com>,
	Christian Brunner <christian@brunner-muc.de>,
	Sage Weil <sage@newdream.net>,
	linux-btrfs@vger.kernel.org, ceph-devel@vger.kernel.org
Subject: Re: Ceph on btrfs 3.4rc
Date: Fri, 11 May 2012 15:16:23 -0400	[thread overview]
Message-ID: <20120511191623.GB3503@localhost.localdomain> (raw)
In-Reply-To: <4FAD5B7E.5040801@tuxadero.com>

On Fri, May 11, 2012 at 08:33:34PM +0200, Martin Mailand wrote:
> Hi Josef,
> 
> Am 11.05.2012 15:31, schrieb Josef Bacik:
> >That previous patch was against btrfs-next, this patch is against 3.4-rc6 if you
> >are on mainline.  Thanks,
> 
> I tried your patch against mainline, after a few minutes I hit this bug.
> 

Heh duh, sorry, try this one instead.  Thanks,

Josef

diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 9b9b15f..54af1fa 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -57,9 +57,6 @@ struct btrfs_inode {
 	/* used to order data wrt metadata */
 	struct btrfs_ordered_inode_tree ordered_tree;
 
-	/* for keeping track of orphaned inodes */
-	struct list_head i_orphan;
-
 	/* list of all the delalloc inodes in the FS.  There are times we need
 	 * to write all the delalloc pages to disk, and this list is used
 	 * to walk them all.
@@ -156,6 +153,7 @@ struct btrfs_inode {
 	unsigned dummy_inode:1;
 	unsigned in_defrag:1;
 	unsigned delalloc_meta_reserved:1;
+	unsigned has_orphan_item:1;
 
 	/*
 	 * always compress this one file
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 8fd7233..aad2600 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1375,7 +1375,7 @@ struct btrfs_root {
 	struct list_head root_list;
 
 	spinlock_t orphan_lock;
-	struct list_head orphan_list;
+	atomic_t orphan_inodes;
 	struct btrfs_block_rsv *orphan_block_rsv;
 	int orphan_item_inserted;
 	int orphan_cleanup_state;
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index a7ffc88..ff3bf4b 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1153,7 +1153,6 @@ static void __setup_root(u32 nodesize, u32 leafsize, u32 sectorsize,
 	root->orphan_block_rsv = NULL;
 
 	INIT_LIST_HEAD(&root->dirty_list);
-	INIT_LIST_HEAD(&root->orphan_list);
 	INIT_LIST_HEAD(&root->root_list);
 	spin_lock_init(&root->orphan_lock);
 	spin_lock_init(&root->inode_lock);
@@ -1166,6 +1165,7 @@ static void __setup_root(u32 nodesize, u32 leafsize, u32 sectorsize,
 	atomic_set(&root->log_commit[0], 0);
 	atomic_set(&root->log_commit[1], 0);
 	atomic_set(&root->log_writers, 0);
+	atomic_set(&root->orphan_inodes, 0);
 	root->log_batch = 0;
 	root->log_transid = 0;
 	root->last_log_commit = 0;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 61b16c6..5ba68d0 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -2072,12 +2072,12 @@ void btrfs_orphan_commit_root(struct btrfs_trans_handle *trans,
 	struct btrfs_block_rsv *block_rsv;
 	int ret;
 
-	if (!list_empty(&root->orphan_list) ||
+	if (atomic_read(&root->orphan_inodes) ||
 	    root->orphan_cleanup_state != ORPHAN_CLEANUP_DONE)
 		return;
 
 	spin_lock(&root->orphan_lock);
-	if (!list_empty(&root->orphan_list)) {
+	if (atomic_read(&root->orphan_inodes)) {
 		spin_unlock(&root->orphan_lock);
 		return;
 	}
@@ -2134,8 +2134,8 @@ int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct inode *inode)
 		block_rsv = NULL;
 	}
 
-	if (list_empty(&BTRFS_I(inode)->i_orphan)) {
-		list_add(&BTRFS_I(inode)->i_orphan, &root->orphan_list);
+	if (!BTRFS_I(inode)->has_orphan_item) {
+		BTRFS_I(inode)->has_orphan_item = 1;
 #if 0
 		/*
 		 * For proper ENOSPC handling, we should do orphan
@@ -2148,6 +2148,7 @@ int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct inode *inode)
 			insert = 1;
 #endif
 		insert = 1;
+		atomic_inc(&root->orphan_inodes);
 	}
 
 	if (!BTRFS_I(inode)->orphan_meta_reserved) {
@@ -2195,9 +2196,13 @@ int btrfs_orphan_del(struct btrfs_trans_handle *trans, struct inode *inode)
 	int release_rsv = 0;
 	int ret = 0;
 
+	/*
+	 * evict_inode gets called without holding the i_mutex so we need to
+	 * take the orphan lock to make sure we are safe in messing with these.
+	 */
 	spin_lock(&root->orphan_lock);
-	if (!list_empty(&BTRFS_I(inode)->i_orphan)) {
-		list_del_init(&BTRFS_I(inode)->i_orphan);
+	if (BTRFS_I(inode)->has_orphan_item) {
+		BTRFS_I(inode)->has_orphan_item = 0;
 		delete_item = 1;
 	}
 
@@ -2215,6 +2220,9 @@ int btrfs_orphan_del(struct btrfs_trans_handle *trans, struct inode *inode)
 	if (release_rsv)
 		btrfs_orphan_release_metadata(inode);
 
+	if (trans && delete_item)
+		atomic_dec(&root->orphan_inodes);
+
 	return 0;
 }
 
@@ -2352,9 +2360,8 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
 		 * add this inode to the orphan list so btrfs_orphan_del does
 		 * the proper thing when we hit it
 		 */
-		spin_lock(&root->orphan_lock);
-		list_add(&BTRFS_I(inode)->i_orphan, &root->orphan_list);
-		spin_unlock(&root->orphan_lock);
+		atomic_inc(&root->orphan_inodes);
+		BTRFS_I(inode)->has_orphan_item = 1;
 
 		/* if we have links, this was a truncate, lets do that */
 		if (inode->i_nlink) {
@@ -3671,7 +3678,7 @@ void btrfs_evict_inode(struct inode *inode)
 	btrfs_wait_ordered_range(inode, 0, (u64)-1);
 
 	if (root->fs_info->log_root_recovering) {
-		BUG_ON(!list_empty(&BTRFS_I(inode)->i_orphan));
+		BUG_ON(!BTRFS_I(inode)->has_orphan_item);
 		goto no_delete;
 	}
 
@@ -6914,6 +6921,7 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
 	ei->dummy_inode = 0;
 	ei->in_defrag = 0;
 	ei->delalloc_meta_reserved = 0;
+	ei->has_orphan_item = 0;
 	ei->force_compress = BTRFS_COMPRESS_NONE;
 
 	ei->delayed_node = NULL;
@@ -6927,7 +6935,6 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
 	mutex_init(&ei->log_mutex);
 	mutex_init(&ei->delalloc_mutex);
 	btrfs_ordered_inode_tree_init(&ei->ordered_tree);
-	INIT_LIST_HEAD(&ei->i_orphan);
 	INIT_LIST_HEAD(&ei->delalloc_inodes);
 	INIT_LIST_HEAD(&ei->ordered_operations);
 	RB_CLEAR_NODE(&ei->rb_node);
@@ -6972,13 +6979,11 @@ void btrfs_destroy_inode(struct inode *inode)
 		spin_unlock(&root->fs_info->ordered_extent_lock);
 	}
 
-	spin_lock(&root->orphan_lock);
-	if (!list_empty(&BTRFS_I(inode)->i_orphan)) {
+	if (BTRFS_I(inode)->has_orphan_item) {
 		printk(KERN_INFO "BTRFS: inode %llu still on the orphan list\n",
 		       (unsigned long long)btrfs_ino(inode));
-		list_del_init(&BTRFS_I(inode)->i_orphan);
+		atomic_dec(&root->orphan_inodes);
 	}
-	spin_unlock(&root->orphan_lock);
 
 	while (1) {
 		ordered = btrfs_lookup_first_ordered_extent(inode, (u64)-1);
-- 
1.7.7.6


  reply	other threads:[~2012-05-11 19:16 UTC|newest]

Thread overview: 45+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-04-20 15:09 Ceph on btrfs 3.4rc Christian Brunner
2012-04-23  7:20 ` Christian Brunner
2012-04-24 15:21 ` Josef Bacik
2012-04-24 16:26   ` Sage Weil
2012-04-24 17:33     ` Josef Bacik
2012-04-24 17:41       ` Neil Horman
2012-04-27 11:02     ` Christian Brunner
2012-05-03 14:13       ` Josef Bacik
2012-05-03 15:17         ` Josh Durgin
2012-05-03 15:20           ` Josef Bacik
2012-05-03 16:38             ` Josh Durgin
2012-05-03 19:49               ` Josef Bacik
2012-05-04 20:24                 ` Christian Brunner
2012-05-09 20:25                   ` Josef Bacik
2012-05-10 17:40       ` Josef Bacik
2012-05-10 20:35       ` Josef Bacik
2012-05-11 13:31         ` Josef Bacik
2012-05-11 18:33           ` Martin Mailand
2012-05-11 19:16             ` Josef Bacik [this message]
2012-05-14 14:19               ` Martin Mailand
2012-05-14 14:20                 ` Josef Bacik
2012-05-16 19:20                   ` Josef Bacik
2012-05-17 10:29                     ` Martin Mailand
2012-05-17 14:43                       ` Josef Bacik
2012-05-17 15:12                         ` Martin Mailand
2012-05-17 19:43                           ` Josef Bacik
2012-05-17 20:54                             ` Christian Brunner
2012-05-17 21:18                               ` Martin Mailand
2012-05-18 14:48                                 ` Josef Bacik
2012-05-18 17:24                                   ` Martin Mailand
2012-05-18 19:01                                     ` Josef Bacik
2012-05-18 20:11                                       ` Martin Mailand
2012-05-21  3:59                                       ` Miao Xie
2012-05-22 10:29                                         ` Christian Brunner
2012-05-22 17:33                                           ` Josef Bacik
2012-05-23 12:34                                             ` Christian Brunner
2012-05-23 14:12                                               ` Josef Bacik
2012-05-23 15:02                                               ` Josef Bacik
2012-05-23 19:12                                                 ` Martin Mailand
2012-05-24  6:03                                                   ` Martin Mailand
2012-05-24  9:37                                                     ` Christian Brunner
2012-05-22 13:31                                         ` Josef Bacik
2012-05-11 13:46         ` Christian Brunner
2012-04-29 21:09 ` tsuna
2012-04-30 10:28   ` Christian Brunner

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=20120511191623.GB3503@localhost.localdomain \
    --to=josef@redhat.com \
    --cc=ceph-devel@vger.kernel.org \
    --cc=christian@brunner-muc.de \
    --cc=linux-btrfs@vger.kernel.org \
    --cc=martin@tuxadero.com \
    --cc=sage@newdream.net \
    /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).