ocfs2/dlm: Fix a race between migrate request and exit domain

Patch address a racing migrate request message and an exit domain message.
Instead of blocking exit domains for the duration of the migrate, we ignore
failure to deliver that message. This is because an exiting domain should
not have any active locks and thus has no role to play in the migration.

Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
This commit is contained in:
Sunil Mushran 2008-12-16 15:49:19 -08:00 committed by Mark Fasheh
parent 58896c4d0e
commit 2b83256407
1 changed files with 19 additions and 4 deletions

View File

@ -2949,7 +2949,7 @@ static int dlm_do_migrate_request(struct dlm_ctxt *dlm,
struct dlm_node_iter *iter)
{
struct dlm_migrate_request migrate;
int ret, status = 0;
int ret, skip, status = 0;
int nodenum;
memset(&migrate, 0, sizeof(migrate));
@ -2966,12 +2966,27 @@ static int dlm_do_migrate_request(struct dlm_ctxt *dlm,
nodenum == new_master)
continue;
/* We could race exit domain. If exited, skip. */
spin_lock(&dlm->spinlock);
skip = (!test_bit(nodenum, dlm->domain_map));
spin_unlock(&dlm->spinlock);
if (skip) {
clear_bit(nodenum, iter->node_map);
continue;
}
ret = o2net_send_message(DLM_MIGRATE_REQUEST_MSG, dlm->key,
&migrate, sizeof(migrate), nodenum,
&status);
if (ret < 0)
mlog_errno(ret);
else if (status < 0) {
if (ret < 0) {
mlog(0, "migrate_request returned %d!\n", ret);
if (!dlm_is_host_down(ret)) {
mlog(ML_ERROR, "unhandled error=%d!\n", ret);
BUG();
}
clear_bit(nodenum, iter->node_map);
ret = 0;
} else if (status < 0) {
mlog(0, "migrate request (node %u) returned %d!\n",
nodenum, status);
ret = status;