On Wed, Jan 15, 2020 at 9:59 PM Jeff Layton <jlayton@xxxxxxxxxx> wrote:
>
> When we issue an async create, we must ensure that any later on-the-wire
> requests involving it wait for the create reply.
>
> Expand i_ceph_flags to be an unsigned long, and add a new bit that
> MDS requests can wait on. If the bit is set in the inode when sending
> caps, then don't send it and just return that it has been delayed.
>
> Signed-off-by: Jeff Layton <jlayton@xxxxxxxxxx>
> ---
> fs/ceph/caps.c | 9 ++++++++-
> fs/ceph/dir.c | 2 +-
> fs/ceph/mds_client.c | 12 +++++++++++-
> fs/ceph/super.h | 4 +++-
> 4 files changed, 23 insertions(+), 4 deletions(-)
>
> diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
> index c983990acb75..9d1a3d6831f7 100644
> --- a/fs/ceph/caps.c
> +++ b/fs/ceph/caps.c
> @@ -511,7 +511,7 @@ static void __cap_delay_requeue(struct ceph_mds_client *mdsc,
> struct ceph_inode_info *ci,
> bool set_timeout)
> {
> - dout("__cap_delay_requeue %p flags %d at %lu\n", &ci->vfs_inode,
> + dout("__cap_delay_requeue %p flags 0x%lx at %lu\n", &ci->vfs_inode,
> ci->i_ceph_flags, ci->i_hold_caps_max);
> if (!mdsc->stopping) {
> spin_lock(&mdsc->cap_delay_lock);
> @@ -1298,6 +1298,13 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap,
> int delayed = 0;
> int ret;
>
> + /* Don't send anything if it's still being created. Return delayed */
> + if (ci->i_ceph_flags & CEPH_I_ASYNC_CREATE) {
> + spin_unlock(&ci->i_ceph_lock);
> + dout("%s async create in flight for %p\n", __func__, inode);
> + return 1;
> + }
> +
> held = cap->issued | cap->implemented;
> revoking = cap->implemented & ~cap->issued;
> retain &= ~revoking;
> diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
> index 0d97c2962314..b2bcd01ab4e9 100644
> --- a/fs/ceph/dir.c
> +++ b/fs/ceph/dir.c
> @@ -752,7 +752,7 @@ static struct dentry *ceph_lookup(struct inode *dir, struct dentry *dentry,
> struct ceph_dentry_info *di = ceph_dentry(dentry);
>
> spin_lock(&ci->i_ceph_lock);
> - dout(" dir %p flags are %d\n", dir, ci->i_ceph_flags);
> + dout(" dir %p flags are 0x%lx\n", dir, ci->i_ceph_flags);
> if (strncmp(dentry->d_name.name,
> fsc->mount_options->snapdir_name,
> dentry->d_name.len) &&
> diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
> index f06496bb5705..e49ca0533df1 100644
> --- a/fs/ceph/mds_client.c
> +++ b/fs/ceph/mds_client.c
> @@ -2806,14 +2806,24 @@ static void kick_requests(struct ceph_mds_client *mdsc, int mds)
> }
> }
>
> +static int ceph_wait_on_async_create(struct inode *inode)
> +{
> + struct ceph_inode_info *ci = ceph_inode(inode);
> +
> + return wait_on_bit(&ci->i_ceph_flags, CEPH_ASYNC_CREATE_BIT,
> + TASK_INTERRUPTIBLE);
> +}
> +
> int ceph_mdsc_submit_request(struct ceph_mds_client *mdsc, struct inode *dir,
> struct ceph_mds_request *req)
> {
> int err;
>
> /* take CAP_PIN refs for r_inode, r_parent, r_old_dentry */
> - if (req->r_inode)
> + if (req->r_inode) {
> + ceph_wait_on_async_create(req->r_inode);
This is waiting interruptibly, but ignoring the distinction between
CEPH_ASYNC_CREATE_BIT getting cleared and a signal. Do we care? If
not, it deserves a comment (or should ceph_wait_on_async_create() be
void?).
Thanks,
Ilya
