summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
authorsantosh.shilimkar@oracle.com <santosh.shilimkar@oracle.com>2015-08-23 01:45:30 +0300
committerDavid S. Miller <davem@davemloft.net>2015-08-25 23:35:30 +0300
commit3049147ca7c8426268433d16d7546a51dede316d (patch)
treee1769bc94b7d2744c5bd3724887e018a17469b67 /net
parent4f73113c63bae5cd092c93c2a9835b9d3c7f0b54 (diff)
downloadlinux-3049147ca7c8426268433d16d7546a51dede316d.tar.xz
RDS: Make sure we do a signaled send for large-send
WR(Work Requests )always generate a WC(Work Completion) with signaled send. Default RDS ib code is setup for un-signaled completion. Since RDS connction is persistent, we can end up sending the data even after large-send when the remote end is not active(for any reason). By doing a signaled send at least once per large-send, we can at least detect the problem in work completion handler there by avoiding sending more data to inactive remote. Reviewed-by: Ajaykumar Hotchandani <ajaykumar.hotchandani@oracle.com> Signed-off-by: Santosh Shilimkar <ssantosh@kernel.org> Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net')
-rw-r--r--net/rds/ib_send.c5
1 files changed, 5 insertions, 0 deletions
diff --git a/net/rds/ib_send.c b/net/rds/ib_send.c
index 5d0a704fa039..c576ebeb4115 100644
--- a/net/rds/ib_send.c
+++ b/net/rds/ib_send.c
@@ -709,6 +709,11 @@ int rds_ib_xmit(struct rds_connection *conn, struct rds_message *rm,
if (scat == &rm->data.op_sg[rm->data.op_count]) {
prev->s_op = ic->i_data_op;
prev->s_wr.send_flags |= IB_SEND_SOLICITED;
+ if (!(prev->s_wr.send_flags & IB_SEND_SIGNALED)) {
+ ic->i_unsignaled_wrs = rds_ib_sysctl_max_unsig_wrs;
+ prev->s_wr.send_flags |= IB_SEND_SIGNALED;
+ nr_sig++;
+ }
ic->i_data_op = NULL;
}