Hi Trond,
I'm seeing a hang when testing xfstests generic/013 on v4.1 with pNFS after this
patch:
On Wed, 2018-09-05 at 14:07 -0400, Trond Myklebust wrote:
> If someone interrupts a wait on one or more outstanding layoutgets in
> pnfs_update_layout() then return the ERESTARTSYS/EINTR error.
>
> Signed-off-by: Trond Myklebust <trond.myklebust@xxxxxxxxxxxxxxx>
> ---
> fs/nfs/pnfs.c | 26 ++++++++++++++++----------
> 1 file changed, 16 insertions(+), 10 deletions(-)
>
> diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
> index e8f232de484f..7d9a51e6b847 100644
> --- a/fs/nfs/pnfs.c
> +++ b/fs/nfs/pnfs.c
> @@ -1740,16 +1740,16 @@ static bool pnfs_within_mdsthreshold(struct
> nfs_open_context *ctx,
> return ret;
> }
>
> -static bool pnfs_prepare_to_retry_layoutget(struct pnfs_layout_hdr *lo)
> +static int pnfs_prepare_to_retry_layoutget(struct pnfs_layout_hdr *lo)
> {
> /*
> * send layoutcommit as it can hold up layoutreturn due to lseg
> * reference
> */
> pnfs_layoutcommit_inode(lo->plh_inode, false);
> - return !wait_on_bit_action(&lo->plh_flags, NFS_LAYOUT_RETURN,
> + return wait_on_bit_action(&lo->plh_flags, NFS_LAYOUT_RETURN,
> nfs_wait_bit_killable,
> - TASK_UNINTERRUPTIBLE);
> + TASK_KILLABLE);
> }
>
> static void nfs_layoutget_begin(struct pnfs_layout_hdr *lo)
> @@ -1830,7 +1830,9 @@ pnfs_update_layout(struct inode *ino,
> }
>
> lookup_again:
> - nfs4_client_recover_expired_lease(clp);
> + lseg = ERR_PTR(nfs4_client_recover_expired_lease(clp));
> + if (IS_ERR(lseg))
> + goto out;
> first = false;
> spin_lock(&ino->i_lock);
> lo = pnfs_find_alloc_layout(ino, ctx, gfp_flags);
> @@ -1863,9 +1865,9 @@ pnfs_update_layout(struct inode *ino,
> if (list_empty(&lo->plh_segs) &&
> atomic_read(&lo->plh_outstanding) != 0) {
> spin_unlock(&ino->i_lock);
> - if (wait_var_event_killable(&lo->plh_outstanding,
> - atomic_read(&lo->plh_outstanding) == 0
> - || !list_empty(&lo->plh_segs)))
> + lseg = ERR_PTR(wait_var_event_killable(&lo->plh_outstanding,
> + atomic_read(&lo->plh_outstanding)));
> + if (IS_ERR(lseg) || !list_empty(&lo->plh_segs))
Was dropping the "== 0" condition attached to the atomic_read() here a mistake?
I think what's happening is that my client is waiting for plh_outstanding to be
anything other than 0 when there isn't any work left to do.
Thanks,
Anna
> goto out_put_layout_hdr;
> pnfs_put_layout_hdr(lo);
> goto lookup_again;
> @@ -1898,8 +1900,11 @@ pnfs_update_layout(struct inode *ino,
> if (test_and_set_bit(NFS_LAYOUT_FIRST_LAYOUTGET,
> &lo->plh_flags)) {
> spin_unlock(&ino->i_lock);
> - wait_on_bit(&lo->plh_flags, NFS_LAYOUT_FIRST_LAYOUTGET,
> - TASK_UNINTERRUPTIBLE);
> + lseg = ERR_PTR(wait_on_bit(&lo->plh_flags,
> + NFS_LAYOUT_FIRST_LAYOUTGET,
> + TASK_KILLABLE));
> + if (IS_ERR(lseg))
> + goto out_put_layout_hdr;
> pnfs_put_layout_hdr(lo);
> dprintk("%s retrying\n", __func__);
> goto lookup_again;
> @@ -1925,7 +1930,8 @@ pnfs_update_layout(struct inode *ino,
> if (test_bit(NFS_LAYOUT_RETURN, &lo->plh_flags)) {
> spin_unlock(&ino->i_lock);
> dprintk("%s wait for layoutreturn\n", __func__);
> - if (pnfs_prepare_to_retry_layoutget(lo)) {
> + lseg = ERR_PTR(pnfs_prepare_to_retry_layoutget(lo));
> + if (!IS_ERR(lseg)) {
> if (first)
> pnfs_clear_first_layoutget(lo);
> pnfs_put_layout_hdr(lo);
