We are seeing connections stuck with the LL_SEND_FULL bit getting
set and never cleared. This changes RDS to stop trusting the
LL_SEND_FULL bit and kick krdsd after any time we
see -ENOMEM from the ring allocation code.
Original patch by Chris Mason
Signed-off-by: Sowmini Varadhan <sowmini.varad...@oracle.com>
Reviewed-by: Ajaykumar Hotchandani <ajaykumar.hotchand...@oracle.com>
---
net/rds/send.c | 11 +++++++----
net/rds/threads.c | 2 ++
2 files changed, 9 insertions(+), 4 deletions(-)
diff --git a/net/rds/send.c b/net/rds/send.c
index 23135a8..9d9c90c 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -1108,8 +1108,10 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg,
size_t payload_len)
*/
rds_stats_inc(s_send_queued);
- if (!test_bit(RDS_LL_SEND_FULL, &conn->c_flags))
- rds_send_xmit(conn);
+ ret = rds_send_xmit(conn);
+ if (ret == -ENOMEM || ret == -EAGAIN)
+ queue_delayed_work(rds_wq, &conn->c_send_w, 1);
+
rds_message_put(rm);
return payload_len;
@@ -1165,8 +1167,9 @@ rds_send_pong(struct rds_connection *conn, __be16 dport)
rds_stats_inc(s_send_queued);
rds_stats_inc(s_send_pong);
- if (!test_bit(RDS_LL_SEND_FULL, &conn->c_flags))
- queue_delayed_work(rds_wq, &conn->c_send_w, 0);
+ ret = rds_send_xmit(conn);
+ if (ret == -ENOMEM || ret == -EAGAIN)
+ queue_delayed_work(rds_wq, &conn->c_send_w, 1);
rds_message_put(rm);
return 0;
diff --git a/net/rds/threads.c b/net/rds/threads.c
index dc2402e..454aa6d 100644
--- a/net/rds/threads.c
+++ b/net/rds/threads.c
@@ -162,7 +162,9 @@ void rds_send_worker(struct work_struct *work)
int ret;
if (rds_conn_state(conn) == RDS_CONN_UP) {
+ clear_bit(RDS_LL_SEND_FULL, &conn->c_flags);
ret = rds_send_xmit(conn);
+ cond_resched();
rdsdebug("conn %p ret %d\n", conn, ret);
switch (ret) {
case -EAGAIN:
--
1.7.1
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
