btrfs: add delayed_iput list head to btrfs inode
PATCH 1/1 btrfs: add delayed_iput list head to btrfs inode
Following the lead from Jeff Mahoney's comment in the code:
/* JDM: If this is fs-wide, why can't we add a pointer to
* btrfs_inode instead and avoid the allocation? */
Remove the NOFAIL kmalloc in btrfs_add_delayed_iput(), and just use a list head in the btrfs inode.
This does grow the btrfs inode by 16 bytes, but doesn't change slab cache utilization on my machine. Rearranging the btrfs inode could get back 8 bytes or so if people are worried about it.
---
fs/btrfs/btrfs_inode.h +2 -0
@@ -86,6 +86,8 @@ struct btrfs_inode {*/ struct list_head ordered_operations; +struct list_head delayed_iput; +/* node for the red-black tree that links inodes in subvolume root */ struct rb_node rb_node;
fs/btrfs/inode.c +8 -18
@@ -2119,34 +2119,24 @@ zeroit:return -EIO ; } -struct delayed_iput { -struct list_head list; -struct inode *inode; -}; - -/* JDM: If this is fs-wide, why can't we add a pointer to -* btrfs_inode instead and avoid the allocation? */ void btrfs_add_delayed_iput (struct inode *inode) { -struct btrfs_fs_info *fs_info =BTRFS_I (inode)->root->fs_info; -struct delayed_iput *delayed; +struct btrfs_inode *b_inode =BTRFS_I (inode); +struct btrfs_fs_info *fs_info = b_inode->root->fs_info;if (atomic_add_unless (&inode->i_count,-1 ,1 ))return ; - delayed =kmalloc (sizeof (*delayed),GFP_NOFS | __GFP_NOFAIL); - delayed->inode = inode; -spin_lock (&fs_info->delayed_iput_lock); -list_add_tail (&delayed->list, &fs_info->delayed_iputs); +list_add_tail (&b_inode->delayed_iput, &fs_info->delayed_iputs);spin_unlock (&fs_info->delayed_iput_lock); }void btrfs_run_delayed_iputs (struct btrfs_root *root) {LIST_HEAD (list); +struct btrfs_inode *b_inode;struct btrfs_fs_info *fs_info = root->fs_info; -struct delayed_iput *delayed;int empty;spin_lock (&fs_info->delayed_iput_lock);
@@ -2160,10 +2150,9 @@ void btrfs_run_delayed_iputs(struct btrfs_root *root)spin_unlock (&fs_info->delayed_iput_lock);while (!list_empty (&list)) { - delayed = list_entry(list.next, struct delayed_iput, list); -list_del (&delayed->list); -iput (delayed->inode); -kfree (delayed); + b_inode = list_entry(list.next, struct btrfs_inode, delayed_iput); +list_del (&b_inode->delayed_iput); +iput (&b_inode->vfs_inode); } }
@@ -7142,6 +7131,7 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)btrfs_ordered_inode_tree_init (&ei->ordered_tree);INIT_LIST_HEAD (&ei->delalloc_inodes);INIT_LIST_HEAD (&ei->ordered_operations); +INIT_LIST_HEAD (&ei->delayed_iput);RB_CLEAR_NODE (&ei->rb_node);return inode;
Quoted 4 lines
fs/btrfs/inode.c +2
-0+struct btrfs_inode *b_inode =BTRFS_I (inode); +struct btrfs_fs_info *fs_info = b_inode->root->fs_info;if (atomic_add_unless (&inode->i_count,-1 ,1 ))
fs/btrfs/inode.c zeroit: · line 2133
Quoted 10 lines
fs/btrfs/inode.c +1
-4return ; - delayed =kmalloc (sizeof (*delayed),GFP_NOFS | __GFP_NOFAIL); - delayed->inode = inode; -spin_lock (&fs_info->delayed_iput_lock); -list_add_tail (&delayed->list, &fs_info->delayed_iputs); +list_add_tail (&b_inode->delayed_iput, &fs_info->delayed_iputs);spin_unlock (&fs_info->delayed_iput_lock); }
Hmm. I'm not great with inode life cycles, but isn't this only safe if someone else can't get an i_count reference while this is in flight? It looks like the final iput does the unhashing, and so on, so couldn't an iget/iput race with this and try to add the inode's list_head twice?
- z
Quoted 6 lines · Zach Brown
Quoted 6 lines
fs/btrfs/inode.c +2
-0+struct btrfs_inode *b_inode =BTRFS_I (inode); +struct btrfs_fs_info *fs_info = b_inode->root->fs_info;if (atomic_add_unless (&inode->i_count,-1 ,1 ))return ;
Quoted 13 lines
fs/btrfs/inode.c zeroit: · line 2133
Quoted 8 lines
fs/btrfs/inode.c +1
-4- delayed =kmalloc (sizeof (*delayed),GFP_NOFS | __GFP_NOFAIL); - delayed->inode = inode; -spin_lock (&fs_info->delayed_iput_lock); -list_add_tail (&delayed->list, &fs_info->delayed_iputs); +list_add_tail (&b_inode->delayed_iput, &fs_info->delayed_iputs);spin_unlock (&fs_info->delayed_iput_lock); }Hmm. I'm not great with inode life cycles, but isn't this only safe if someone else can't get an
i_countreference while this is in flight? It looks like the final iput does the unhashing, and so on, so couldn't an iget/iput race with this and try to add the inode'slist_headtwice?
Yeah, same concern here. Basically this will result in inodes still being in use on unmount.
Actually I did a similar one, here is some disscussion:
https://patchwork.kernel.org/patch/1824711/
thanks,
liubo
Quoted 21 lines · Liu Bo
Quoted 15 lines · Zach Brown
Quoted 13 lines
fs/btrfs/inode.c +3
-4+struct btrfs_inode *b_inode =BTRFS_I (inode); +struct btrfs_fs_info *fs_info = b_inode->root->fs_info;if (atomic_add_unless (&inode->i_count,-1 ,1 ))return ; - delayed =kmalloc (sizeof (*delayed),GFP_NOFS | __GFP_NOFAIL); - delayed->inode = inode; -spin_lock (&fs_info->delayed_iput_lock); -list_add_tail (&delayed->list, &fs_info->delayed_iputs); +list_add_tail (&b_inode->delayed_iput, &fs_info->delayed_iputs);spin_unlock (&fs_info->delayed_iput_lock);Quoted 1 line
}
Quoted 4 lines
Hmm. I'm not great with inode life cycles, but isn't this only safe if someone else can't get an
i_countreference while this is in flight? It looks like the final iput does the unhashing, and so on, so couldn't an iget/iput race with this and try to add the inode'slist_headtwice?
Quoted 7 lines
Yeah, same concern here. Basically this will result in inodes still being in use on unmount.
Actually I did a similar one, here is some disscussion:
Ok, thanks all. We should remove Jeff's comment then, it sure sounded like a good idea...
Eric
Quoted 6 lines
thanks,
liubo
--
To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Quoted 21 lines · Liu Bo
Quoted 6 lines · Zach Brown
Quoted 6 lines
fs/btrfs/inode.c +2
-0+struct btrfs_inode *b_inode =BTRFS_I (inode); +struct btrfs_fs_info *fs_info = b_inode->root->fs_info;if (atomic_add_unless (&inode->i_count,-1 ,1 ))return ;Quoted 13 lines
fs/btrfs/inode.c zeroit: · line 2133
Quoted 8 lines
fs/btrfs/inode.c +1
-4- delayed =kmalloc (sizeof (*delayed),GFP_NOFS | __GFP_NOFAIL); - delayed->inode = inode; -spin_lock (&fs_info->delayed_iput_lock); -list_add_tail (&delayed->list, &fs_info->delayed_iputs); +list_add_tail (&b_inode->delayed_iput, &fs_info->delayed_iputs);spin_unlock (&fs_info->delayed_iput_lock); }Hmm. I'm not great with inode life cycles, but isn't this only safe if someone else can't get an
i_countreference while this is in flight? It looks like the final iput does the unhashing, and so on, so couldn't an iget/iput race with this and try to add the inode'slist_headtwice?
Quoted 6 lines
Yeah, same concern here. Basically this will result in inodes still being in use on unmount.
Actually I did a similar one, here is some disscussion:
I read it, thanks. Did you try the counter approach?
-Eric
Quoted 7 lines
thanks,
liubo
--
To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Quoted 22 lines · Eric Sandeen
Quoted 21 lines · Liu Bo
Quoted 19 lines · Zach Brown
Quoted 4 lines
fs/btrfs/inode.c +2
-0+struct btrfs_inode *b_inode =BTRFS_I (inode); +struct btrfs_fs_info *fs_info = b_inode->root->fs_info;if (atomic_add_unless (&inode->i_count,-1 ,1 ))fs/btrfs/inode.c zeroit: · line 2133
Quoted 10 lines
fs/btrfs/inode.c +1
-4return ; - delayed =kmalloc (sizeof (*delayed),GFP_NOFS | __GFP_NOFAIL); - delayed->inode = inode; -spin_lock (&fs_info->delayed_iput_lock); -list_add_tail (&delayed->list, &fs_info->delayed_iputs); +list_add_tail (&b_inode->delayed_iput, &fs_info->delayed_iputs);spin_unlock (&fs_info->delayed_iput_lock); }Hmm. I'm not great with inode life cycles, but isn't this only safe if someone else can't get an
i_countreference while this is in flight? It looks like the final iput does the unhashing, and so on, so couldn't an iget/iput race with this and try to add the inode'slist_headtwice?
Quoted 8 lines
Quoted 6 lines
Yeah, same concern here. Basically this will result in inodes still being in use on unmount.
Actually I did a similar one, here is some disscussion:
I read it, thanks. Did you try the counter approach?
Yes, it'll bring a tradeoff situation.
With counter, we need to lock the list all the time instead of doing a splice on the list and unlocking it. I think splice would be faster so I didn't go further(I MIGHT be wrong on this)..
thanks,
liubo
-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1
Quoted 29 lines · Liu Bo
Quoted 28 lines · Eric Sandeen
Quoted 26 lines · Liu Bo
Quoted 5 lines · Zach Brown
Quoted 5 lines
(quoted diff) +1
-0+ struct btrfs_inode *b_inode = BTRFS_I(inode); + struct
btrfs_fs_info*fs_info=b_inode->root->fs_info;if (
atomic_add_unless(&inode->i_count, -1, 1)) return;Quoted 13 lines
Quoted 7 lines
(quoted diff) +0
-1- delayed = kmalloc(sizeof(*delayed), GFP_NOFS |
__GFP_NOFAIL); -delayed->inode= inode; -spin_lock(&fs_info->delayed_iput_lock); -list_add_tail(&delayed->list, &fs_info->delayed_iputs); +list_add_tail(&b_inode->delayed_iput, &fs_info->delayed_iputs);spin_unlock(&fs_info->delayed_iput_lock); }Hmm. I'm not great with inode life cycles, but isn't this only safe if someone else can't get an
i_countreference while this is in flight? It looks like the final iput does the unhashing, and so on, so couldn't an iget/iput race with this and try to add the inode'slist_headtwice?Yeah, same concern here. Basically this will result in inodes still being in use on unmount.
Actually I did a similar one, here is some disscussion:
Quoted 7 lines
Quoted 1 line
I read it, thanks. Did you try the counter approach?
Yes, it'll bring a tradeoff situation.
With counter, we need to lock the list all the time instead of doing a splice on the list and unlocking it. I think splice would be faster so I didn't go further(I MIGHT be wrong on this)..
Thanks for looking into this. I left this note to myself during the development of the error handling patches while on a tangent to try to eliminate NOFAIL allocs. It's not the alloc/free that's the issue (though eliminating these can probably only help), it's that NOFAIL allocs essentially become locks when memory pressure is high enough that the NOFAIL functionality gets invoked. OTOH, bailing out of that path when we encounter an allocation failure is impossible.
- -Jeff
- --
Jeff Mahoney
SUSE Labs
-----BEGIN PGP SIGNATURE-----
Version: GnuPG/MacGPG2 v2.0.18 (Darwin)
Comment: GPGTools - http://gpgtools.org
iQIcBAEBAgAGBQJRGfB3AAoJEB57S2MheeWy/E4QALVJ2YI1zbwCHnkUia+yuT40 LoYfyRJoTiKwnwiFeByy98tX9WxVnXGZUVpR8GMwVuLfDIMyVgQmaAicqiirHHHD ySNV3jsyz8HCOb6ALu7eQyWy4F8yBD1HG75njvvzVO+zUlSsaKGmfvsXS0f4ubCk hyxg7OujW++cWg+WOedCZsg2n7kF34MLPJiyjS1E1vw8DZW3tHKWgv/hyJIzp+JK wIZQPrzNUTp0kS4N6+b8rJnXTNkj7zMhWPYeJdIMIG9/+oDr2r1N/XedYMY7fkdS g7Gj28nmTtufYlTcgztL6MHFwxm/tRQNl85+lRU/zYFKIR0ok4+1kFrpZ5KcF97m NZeGSsSiaZfMXE+t6B/AgagFJUws+y/RHBJ/V9paMNjsojLRUBVPQOdeHw355XVm lJeTtyElA+SSawPkzf2115IEj1EgFmHIouSQJdUCPoTfS126NHhH0PYX2GHgAs8b 1ImyG9E/Z/JswVRzAxWGQSffdxzg5Vb8P8w7LzAlIdToVa0tM3Q2n9h3a0vcl83m NQEqe3+GnsflB2xSVyoztVx+ZL8664HC1UzIjgb7oUihGHe7gJZ4uqDgaClGprKh pQyvr8zsbjeMwpvlqv7gRQDFyY3JKK4W5UeS/pGjTM7ORS1LmEUTR5S4pQknTUgc Qj/bH6806My5pW3VB5i5
=ZSdX
-----END PGP SIGNATURE-----