[sheepdog] [PATCH] recovery: fix incomplete recovery because of faulty oid scheduling

[Liu Yuan]

From: Liu Yuan <tailai.ly at taobao.com>

tests/010 will fail sometimes to catch this bug.

When auto-recover is disabled, if we prepare_schedule_oid on the same oid
multiple times, it will break finish_schedule_oid to wrongly squeeze some
victim oid out of rw->oids array, then this node will never have a chance to
recover the ejected oids.

Signed-off-by: Liu Yuan <tailai.ly at taobao.com>
---
 sheep/recovery.c |   15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/sheep/recovery.c b/sheep/recovery.c
index 23babe0..6b39e0a 100644
--- a/sheep/recovery.c
+++ b/sheep/recovery.c
@@ -237,18 +237,18 @@ static inline void prepare_schedule_oid(uint64_t oid)
 				   oid);
 			return;
 		}
-	/*
-	 * When auto recovery is enabled, the oid is currently being
-	 * recovered
-	 */
-	if (!sys->disable_recovery && rw->oids[rw->done] == oid)
+	/* The oid is currently being recovered */
+	if (rw->oids[rw->done] == oid) {
+		if (rw->suspended == true) {
+			rw->suspended = false;
+			queue_work(sys->recovery_wqueue, &rw->work);
+		}
 		return;
+	}
 	rw->nr_prio_oids++;
 	rw->prio_oids = xrealloc(rw->prio_oids,
 				 rw->nr_prio_oids * sizeof(uint64_t));
 	rw->prio_oids[rw->nr_prio_oids - 1] = oid;
-	resume_suspended_recovery();
-
 	sd_dprintf("%"PRIx64" nr_prio_oids %d", oid, rw->nr_prio_oids);
 }
 
@@ -291,6 +291,7 @@ bool oid_in_recovery(uint64_t oid)
 	}
 
 	prepare_schedule_oid(oid);
+	resume_suspended_recovery();
 	return true;
 }
 
-- 
1.7.9.5