[Cluster-devel] [GFS2 PATCH] [TRY #2] GFS2: Prevent recovery before the local journal is set

[Steven Whitehouse <swhiteho@redhat.com>]

Hi,

On 02/05/14 15:05, Bob Peterson wrote:
> Hi,
>
> This patch uses a completion to prevent dlm's recovery process from
> referencing and trying to recover a journal before a journal has been
> opened.
>
> Regards,
>
> Bob Peterson
> Red Hat File Systems
There is one possible issue that I can see, which is the error case. If 
we have some error that occurs prior to getting to the complete_all() 
will we land up with a process that has requested recovery waiting 
forever? If we can resolve that, then I think this should be good to go,

Steve.

> Signed-off-by: Bob Peterson <rpeterso@redhat.com>
> ---
> diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
> index bdf70c1..04c062c 100644
> --- a/fs/gfs2/incore.h
> +++ b/fs/gfs2/incore.h
> @@ -730,6 +730,8 @@ struct gfs2_sbd {
>   	struct gfs2_holder sd_sc_gh;
>   	struct gfs2_holder sd_qc_gh;
>   
> +	struct completion sd_journal_ready;
> +
>   	/* Daemon stuff */
>   
>   	struct task_struct *sd_logd_process;
> diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
> index 22f9540..4535156 100644
> --- a/fs/gfs2/ops_fstype.c
> +++ b/fs/gfs2/ops_fstype.c
> @@ -94,6 +94,7 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb)
>   	INIT_LIST_HEAD(&sdp->sd_jindex_list);
>   	spin_lock_init(&sdp->sd_jindex_spin);
>   	mutex_init(&sdp->sd_jindex_mutex);
> +	init_completion(&sdp->sd_journal_ready);
>   
>   	INIT_LIST_HEAD(&sdp->sd_quota_list);
>   	mutex_init(&sdp->sd_quota_mutex);
> @@ -676,6 +677,7 @@ static int init_journal(struct gfs2_sbd *sdp, int undo)
>   
>   	if (sdp->sd_args.ar_spectator) {
>   		sdp->sd_jdesc = gfs2_jdesc_find(sdp, 0);
> +		complete_all(&sdp->sd_journal_ready);
>   		atomic_set(&sdp->sd_log_blks_free, sdp->sd_jdesc->jd_blocks);
>   		atomic_set(&sdp->sd_log_thresh1, 2*sdp->sd_jdesc->jd_blocks/5);
>   		atomic_set(&sdp->sd_log_thresh2, 4*sdp->sd_jdesc->jd_blocks/5);
> @@ -686,10 +688,13 @@ static int init_journal(struct gfs2_sbd *sdp, int undo)
>   			fs_err(sdp, "there are only %u journals (0 - %u)\n",
>   			       gfs2_jindex_size(sdp),
>   			       gfs2_jindex_size(sdp) - 1);
> +			complete_all(&sdp->sd_journal_ready);
>   			goto fail_jindex;
>   		}
>   		sdp->sd_jdesc = gfs2_jdesc_find(sdp, sdp->sd_lockstruct.ls_jid);
>   
> +		complete_all(&sdp->sd_journal_ready);
> +
>   		error = gfs2_glock_nq_num(sdp, sdp->sd_lockstruct.ls_jid,
>   					  &gfs2_journal_glops,
>   					  LM_ST_EXCLUSIVE, LM_FLAG_NOEXP,
> diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c
> index de25d55..02afa82 100644
> --- a/fs/gfs2/sys.c
> +++ b/fs/gfs2/sys.c
> @@ -407,6 +407,9 @@ int gfs2_recover_set(struct gfs2_sbd *sdp, unsigned jid)
>   	struct gfs2_jdesc *jd;
>   	int rv;
>   
> +	/* Wait for our primary journal to be initialized */
> +	wait_for_completion(&sdp->sd_journal_ready);
> +
>   	spin_lock(&sdp->sd_jindex_spin);
>   	rv = -EBUSY;
>   	if (sdp->sd_jdesc->jd_jid == jid)
>