On 05/30/2012 10:21 AM, Hefty, Sean wrote:
If a user calls rrecv() after a blocking rsocket has been disconnected,
it will hang. This problem and the cause was reported by Sridhar Samudrala
<[email protected]>. It can be reproduced by running netserver -f -D
using the rs-preload library. A similar issue exists with rsend().
Fix this by not blocking on a CQ unless we're connected.
Signed-off-by: Sean Hefty<[email protected]>
---
Sridhar, can you please let me know if this fixes the hang you were seeing?
I moved the connected check inside holding the cq lock from the patch that
you sent me.
src/rsocket.c | 26 +++++++++++++++++++++++---
1 files changed, 23 insertions(+), 3 deletions(-)
diff --git a/src/rsocket.c b/src/rsocket.c
index 01b7248..8c96dc1 100644
--- a/src/rsocket.c
+++ b/src/rsocket.c
@@ -908,6 +908,11 @@ static int rs_can_send(struct rsocket *rs)
(rs->target_sgl[rs->target_sge].length != 0);
}
+static int rs_conn_can_send(struct rsocket *rs)
+{
+ return rs_can_send(rs) || (rs->state != rs_connected);
+}
+
static int rs_can_send_ctrl(struct rsocket *rs)
{
return rs->ctrl_avail;
@@ -918,6 +923,11 @@ static int rs_have_rdata(struct rsocket *rs)
return (rs->rmsg_head != rs->rmsg_tail);
}
+static int rs_conn_have_rdata(struct rsocket *rs)
+{
+ return rs_have_rdata(rs) || (rs->state != rs_connected);
+}
+
static int rs_all_sends_done(struct rsocket *rs)
{
return (rs->sqe_avail + rs->ctrl_avail) == RS_QP_SIZE;
@@ -980,7 +990,7 @@ ssize_t rrecv(int socket, void *buf, size_t len, int flags)
}
fastlock_acquire(&rs->rlock);
if (!rs_have_rdata(rs)) {
- ret = rs_process_cq(rs, rs_nonblocking(rs, flags),
rs_have_rdata);
+ ret = rs_process_cq(rs, rs_nonblocking(rs, flags),
rs_conn_have_rdata);
if (ret&& errno != ECONNRESET)
goto out;
}
@@ -1084,9 +1094,14 @@ ssize_t rsend(int socket, const void *buf, size_t len,
int flags)
fastlock_acquire(&rs->slock);
for (left = len; left; left -= xfer_size, buf += xfer_size) {
if (!rs_can_send(rs)) {
- ret = rs_process_cq(rs, rs_nonblocking(rs, flags),
rs_can_send);
+ ret = rs_process_cq(rs, rs_nonblocking(rs, flags),
+ rs_conn_can_send);
if (ret)
break;
+ if (rs->state != rs_connected) {
+ ret = ERR(ECONNRESET);
+ break;
+ }
}
if (olen< left) {
@@ -1193,9 +1208,14 @@ static ssize_t rsendv(int socket, const struct iovec
*iov, int iovcnt, int flags
fastlock_acquire(&rs->slock);
for (left = len; left; left -= xfer_size) {
if (!rs_can_send(rs)) {
- ret = rs_process_cq(rs, rs_nonblocking(rs, flags),
rs_can_send);
+ ret = rs_process_cq(rs, rs_nonblocking(rs, flags),
+ rs_conn_can_send);
if (ret)
break;
+ if (rs->state != rs_connected) {
+ ret = ERR(ECONNRESET);
+ break;
+ }
}
if (olen< left) {
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Sean, Have tested by applying only this patch in the entire series.
netperf now seems to be working.
Thanks
Pradeep
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
