summaryrefslogtreecommitdiff
path: root/net/rds/af_rds.c
diff options
context:
space:
mode:
authorSantosh Shilimkar <santosh.shilimkar@oracle.com>2012-02-03 20:09:23 +0400
committerSantosh Shilimkar <ssantosh@kernel.org>2015-09-30 19:43:24 +0300
commit8b0a6b461e2ccc95363e0547aa4f43ba2e02b096 (patch)
treeab5d09ccb54b090f1ecf02af7466b236a0163328 /net/rds/af_rds.c
parent59fe4606748f7016e9e02bbd26da185f8620661a (diff)
downloadlinux-8b0a6b461e2ccc95363e0547aa4f43ba2e02b096.tar.xz
RDS: make socket bind/release locking scheme simple and more efficient
RDS bind and release locking scheme is very inefficient. It uses RCU for maintaining the bind hash-table which is great but it also needs to hold spinlock for [add/remove]_bound(). So overall usecase, the hash-table concurrent speedup doesn't pay off. In fact blocking nature of synchronize_rcu() makes the RDS socket shutdown too slow which hurts RDS performance since connection shutdown and re-connect happens quite often to maintain the RC part of the protocol. So we make the locking scheme simpler and more efficient by replacing spin_locks with reader/writer locks and getting rid off rcu for bind hash-table. In subsequent patch, we also covert the global lock with per-bucket lock to reduce the global lock contention. Signed-off-by: Santosh Shilimkar <ssantosh@kernel.org> Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Diffstat (limited to 'net/rds/af_rds.c')
-rw-r--r--net/rds/af_rds.c6
1 files changed, 0 insertions, 6 deletions
diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c
index a2f28a6d4dc5..dc087666217a 100644
--- a/net/rds/af_rds.c
+++ b/net/rds/af_rds.c
@@ -72,13 +72,7 @@ static int rds_release(struct socket *sock)
rds_clear_recv_queue(rs);
rds_cong_remove_socket(rs);
- /*
- * the binding lookup hash uses rcu, we need to
- * make sure we synchronize_rcu before we free our
- * entry
- */
rds_remove_bound(rs);
- synchronize_rcu();
rds_send_drop_to(rs, NULL);
rds_rdma_drop_keys(rs);