[sheepdog] [PATCH] sheep: increase buffer while in cinfo collection

Liu Yuan liuyuan at cmss.chinamobile.com
Mon Feb 9 09:00:32 CET 2015


Even with a 3 node cluster and only 1 vdi, killing one node and joining it back
the error message that "buffer too small" will pop out twice, this means 512 is
too small even for a single VDI cluster.

Making it as 4K will mitigat the problem a bit.

Signed-off-by: Liu Yuan <liuyuan at cmss.chinamobile.com>
---
 sheep/group.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sheep/group.c b/sheep/group.c
index 85b9249..5ab2c0c 100644
--- a/sheep/group.c
+++ b/sheep/group.c
@@ -702,7 +702,7 @@ static struct vdi_state *do_cinfo_collection_work(uint32_t epoch,
 						  int *nr_vdi_states)
 {
 	struct vdi_state *vs = NULL;
-	unsigned int rlen = 512;
+	unsigned int rlen = 4096;
 	struct sd_req hdr;
 	struct sd_rsp *rsp = (struct sd_rsp *)&hdr;
 	int ret;
-- 
1.9.1






More information about the sheepdog mailing list