GFS2: let spectator mount do read only recovery

Previously, a spectator mount would not even attempt to do
journal recovery for a failed node.  This meant that if all
mounted nodes were spectators, everyone would be stuck after
a node failed, all waiting for recovery to be performed.
This is unnecessary since the failed node had a clean journal.

Instead, allow a spectator mount to do a partial "read only"
recovery, which means it will check if the failed journal is
clean, and if so, report a successful recovery.  If the failed
journal is not clean, it reports that journal recovery failed.
This makes it work the same as a read only mount on a read only
block device.

Signed-off-by: David Teigland <teigland@redhat.com>
Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
This commit is contained in:
David Teigland 2012-01-09 14:40:06 -05:00 committed by Steven Whitehouse
parent 49528b4e47
commit e8ca5cc571
3 changed files with 5 additions and 2 deletions

View File

@ -498,6 +498,7 @@ enum {
SDF_NORECOVERY = 4,
SDF_DEMOTE = 5,
SDF_NOJOURNALID = 6,
SDF_RORECOVERY = 7, /* read only recovery */
};
#define GFS2_FSNAME_LEN 256

View File

@ -1078,7 +1078,7 @@ static int fill_super(struct super_block *sb, struct gfs2_args *args, int silent
if (sdp->sd_args.ar_spectator) {
sb->s_flags |= MS_RDONLY;
set_bit(SDF_NORECOVERY, &sdp->sd_flags);
set_bit(SDF_RORECOVERY, &sdp->sd_flags);
}
if (sdp->sd_args.ar_posix_acl)
sb->s_flags |= MS_POSIXACL;

View File

@ -516,7 +516,9 @@ void gfs2_recover_func(struct work_struct *work)
if (error)
goto fail_gunlock_ji;
if (test_bit(SDF_JOURNAL_CHECKED, &sdp->sd_flags)) {
if (test_bit(SDF_RORECOVERY, &sdp->sd_flags)) {
ro = 1;
} else if (test_bit(SDF_JOURNAL_CHECKED, &sdp->sd_flags)) {
if (!test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags))
ro = 1;
} else {