On Tue, 2011-10-18 at 13:01 -0400, Jim Rees wrote:
> I believe this one is still needed, and is missing from your tree. I can't
> remember the status, there was a lot of discussion, but I think this was the
> final result. Bergwolf? Others?
>
> commit 54cf1a33598abbe6431b573563116d8ecc8343b1
> Author: Peng Tao <bergwolf@xxxxxxxxx>
> Date: Mon Sep 12 20:47:21 2011 -0700
>
> nfs4: serialize layoutcommit
>
> Current pnfs_layoutcommit_inode can not handle parallel layoutcommit.
> And as Trond suggested , there is no need for client to optimize for
> parallel layoutcommit. So add NFS_INO_LAYOUTCOMMITTING flag to mark
> inflight layoutcommit and serialize lalyoutcommit with it. Also call
> mark_inode_dirty_sync if pnfs_layoutcommit_inode fails to issue
> layoutcommit, so that layoutcommit can be retried later.
> It also fixes the pls_lc_list corruption that Vitaliy found.
>
> Reported-by: Vitaliy Gusev <gusev.vitaliy@xxxxxxxxxxx>
> Signed-off-by: Peng Tao <peng_tao@xxxxxxx>
> Signed-off-by: Jim Rees <rees@xxxxxxxxx>
>
> diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
> index 4700fae..a7ce210 100644
> --- a/fs/nfs/nfs4proc.c
> +++ b/fs/nfs/nfs4proc.c
> @@ -5970,6 +5970,7 @@ static void nfs4_layoutcommit_release(void *calldata)
> {
> struct nfs4_layoutcommit_data *data = calldata;
> struct pnfs_layout_segment *lseg, *tmp;
> + unsigned long *bitlock = &NFS_I(data->args.inode)->flags;
>
> pnfs_cleanup_layoutcommit(data);
> /* Matched by references in pnfs_set_layoutcommit */
> @@ -5979,6 +5980,11 @@ static void nfs4_layoutcommit_release(void *calldata)
> &lseg->pls_flags))
> put_lseg(lseg);
> }
> +
> + clear_bit_unlock(NFS_INO_LAYOUTCOMMITTING, bitlock);
> + smp_mb__after_clear_bit();
> + wake_up_bit(bitlock, NFS_INO_LAYOUTCOMMITTING);
> +
> put_rpccred(data->cred);
> kfree(data);
> }
> diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
> index e550e88..0715fda 100644
> --- a/fs/nfs/pnfs.c
> +++ b/fs/nfs/pnfs.c
> @@ -1443,17 +1443,30 @@ pnfs_layoutcommit_inode(struct inode *inode, bool sync)
> /* Note kzalloc ensures data->res.seq_res.sr_slot == NULL */
> data = kzalloc(sizeof(*data), GFP_NOFS);
> if (!data) {
> - mark_inode_dirty_sync(inode);
> status = -ENOMEM;
> goto out;
> }
>
> + if (!test_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags))
> + goto out_free;
> + else if (test_and_set_bit(NFS_INO_LAYOUTCOMMITTING, &nfsi->flags)) {
We don't need an 'else' after a 'goto out' :-)
> + if (!sync) {
> + status = -EAGAIN;
> + goto out_free;
> + }
> + status = wait_on_bit_lock(&nfsi->flags, NFS_INO_LAYOUTCOMMITTING,
> + nfs_wait_bit_killable, TASK_KILLABLE);
> + if (status)
> + goto out_free;
> + }
> +
> INIT_LIST_HEAD(&data->lseg_list);
Why do this before the test of NFS_INO_LAYOUTCOMMIT?
> spin_lock(&inode->i_lock);
> if (!test_and_clear_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags)) {
> + clear_bit(NFS_INO_LAYOUTCOMMITTING, &nfsi->flags);
> spin_unlock(&inode->i_lock);
> - kfree(data);
> - goto out;
> + wake_up_bit(&nfsi->flags, NFS_INO_LAYOUTCOMMITTING);
> + goto out_free;
> }
>
> pnfs_list_write_lseg(inode, &data->lseg_list);
> @@ -1475,6 +1488,11 @@ pnfs_layoutcommit_inode(struct inode *inode, bool sync)
>
> status = nfs4_proc_layoutcommit(data, sync);
> out:
> + if (status)
> + mark_inode_dirty_sync(inode);
Shouldn't we be doing this in nfs4_layoutcommit_release() too?
> dprintk("<-- %s status %d\n", __func__, status);
> return status;
> +out_free:
> + kfree(data);
> + goto out;
> }
> diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
> index eaac770..c5b2b30 100644
> --- a/include/linux/nfs_fs.h
> +++ b/include/linux/nfs_fs.h
> @@ -230,6 +230,7 @@ struct nfs_inode {
> #define NFS_INO_COMMIT (7) /* inode is committing unstable writes */
> #define NFS_INO_PNFS_COMMIT (8) /* use pnfs code for commit */
> #define NFS_INO_LAYOUTCOMMIT (9) /* layoutcommit required */
> +#define NFS_INO_LAYOUTCOMMITTING (10) /* layoutcommit inflight */
>
> static inline struct nfs_inode *NFS_I(const struct inode *inode)
> {
--
Trond Myklebust
Linux NFS client maintainer
NetApp
Trond.Myklebust@xxxxxxxxxx
www.netapp.com
--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
