[sheepdog] [PATCH 5/6] object cache: don't return when node_in_recovery()

Liu Yuan namei.unix at gmail.com
Wed Aug 1 12:03:49 CEST 2012


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

Because we have self retry mechanism, we are no longer afraid of node failure.

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

diff --git a/sheep/object_cache.c b/sheep/object_cache.c
index e34b12e..0a2e3f3 100644
--- a/sheep/object_cache.c
+++ b/sheep/object_cache.c
@@ -435,10 +435,6 @@ static void do_reclaim(struct work *work)
 {
 	struct object_cache_entry *entry, *n;
 
-	/* TODO confirm whether this check is necessary */
-	if (node_in_recovery())
-		return;
-
 	list_for_each_entry_revert_safe_rcu(entry, n,
 		       &sys_cache.cache_lru_list, lru_list) {
 		unsigned data_length;
@@ -787,10 +783,6 @@ static int object_cache_push(struct object_cache *oc)
 
 	int ret = SD_RES_SUCCESS;
 
-	if (node_in_recovery())
-		/* We don't do flushing in recovery */
-		return SD_RES_SUCCESS;
-
 	pthread_rwlock_wrlock(&oc->lock);
 	list_for_each_entry_safe(entry, t, &oc->dirty_list, dirty_list) {
 		ret = push_cache_object(oc->vid, entry->idx, entry->bmap,
-- 
1.7.10.2




More information about the sheepdog mailing list