On Sun, 2011-09-11 at 21:48 -0700, Peng Tao wrote:
> Current pnfs_layoutcommit_inode can not handle parallel layoutcommit.
> As Trond suggested, there is no need for client to optimize for
> parallel layoutcommit. The patch add NFS_INO_LAYOUTCOMMITTING flag to
> mark inflight layoutcommit and serialize lalyoutcommit with it.
> 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>
> ---
> fs/nfs/nfs4proc.c | 6 ++++++
> fs/nfs/pnfs.c | 9 +++++++++
> include/linux/nfs_fs.h | 1 +
> 3 files changed, 16 insertions(+), 0 deletions(-)
>
> 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 b483bbc..fb71def 100644
> --- a/fs/nfs/pnfs.c
> +++ b/fs/nfs/pnfs.c
> @@ -1451,10 +1451,19 @@ pnfs_layoutcommit_inode(struct inode *inode, bool sync)
> goto out;
> }
>
> + if (!test_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags) ||
> + (status = wait_on_bit_lock(&nfsi->flags, NFS_INO_LAYOUTCOMMITTING,
> + nfs_wait_bit_killable, TASK_KILLABLE))) {
You want the sleeping behaviour above to be subject to the 'sync' flag
(in the same way we do for regular commit). If !sync, then try to grab
the bit lock anyway, and exit on failure.
> + kfree(data);
> + goto out;
> + }
> +
> INIT_LIST_HEAD(&data->lseg_list);
> 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);
> + wake_up_bit(&nfsi->flags, NFS_INO_LAYOUTCOMMITTING);
> 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
