summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorAndy Grover <andy.grover@oracle.com>2009-10-30 08:51:57 +0000
committerDavid S. Miller <davem@davemloft.net>2009-10-30 15:06:39 -0700
commitd521b63b27e3a397e0ef7ca86b6e813861083c83 (patch)
treed27bc29f9e0c7beb4b1e36b252ce71f6d008909f
parent0514f8a9c0cbd26afa70dc56406cc0ee1e134dcf (diff)
RDS/IB+IW: Move recv processing to a tasklet
Move receive processing from event handler to a tasklet. This should help prevent hangcheck timer from going off when RDS is under heavy load. Signed-off-by: Andy Grover <andy.grover@oracle.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-rw-r--r--net/rds/ib.h2
-rw-r--r--net/rds/ib_cm.c2
-rw-r--r--net/rds/ib_recv.c28
-rw-r--r--net/rds/iw.h2
-rw-r--r--net/rds/iw_cm.c2
-rw-r--r--net/rds/iw_recv.c28
6 files changed, 52 insertions, 12 deletions
diff --git a/net/rds/ib.h b/net/rds/ib.h
index 1378b854cac0..64df4e79b29f 100644
--- a/net/rds/ib.h
+++ b/net/rds/ib.h
@@ -98,6 +98,7 @@ struct rds_ib_connection {
struct rds_ib_send_work *i_sends;
/* rx */
+ struct tasklet_struct i_recv_tasklet;
struct mutex i_recv_mutex;
struct rds_ib_work_ring i_recv_ring;
struct rds_ib_incoming *i_ibinc;
@@ -303,6 +304,7 @@ void rds_ib_inc_free(struct rds_incoming *inc);
int rds_ib_inc_copy_to_user(struct rds_incoming *inc, struct iovec *iov,
size_t size);
void rds_ib_recv_cq_comp_handler(struct ib_cq *cq, void *context);
+void rds_ib_recv_tasklet_fn(unsigned long data);
void rds_ib_recv_init_ring(struct rds_ib_connection *ic);
void rds_ib_recv_clear_ring(struct rds_ib_connection *ic);
void rds_ib_recv_init_ack(struct rds_ib_connection *ic);
diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c
index c2d372f13dbb..9d320692a4fc 100644
--- a/net/rds/ib_cm.c
+++ b/net/rds/ib_cm.c
@@ -694,6 +694,8 @@ int rds_ib_conn_alloc(struct rds_connection *conn, gfp_t gfp)
return -ENOMEM;
INIT_LIST_HEAD(&ic->ib_node);
+ tasklet_init(&ic->i_recv_tasklet, rds_ib_recv_tasklet_fn,
+ (unsigned long) ic);
mutex_init(&ic->i_recv_mutex);
#ifndef KERNEL_HAS_ATOMIC64
spin_lock_init(&ic->i_ack_lock);
diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c
index 2f009d391c29..fe5ab8c6b964 100644
--- a/net/rds/ib_recv.c
+++ b/net/rds/ib_recv.c
@@ -825,17 +825,22 @@ void rds_ib_recv_cq_comp_handler(struct ib_cq *cq, void *context)
{
struct rds_connection *conn = context;
struct rds_ib_connection *ic = conn->c_transport_data;
- struct ib_wc wc;
- struct rds_ib_ack_state state = { 0, };
- struct rds_ib_recv_work *recv;
rdsdebug("conn %p cq %p\n", conn, cq);
rds_ib_stats_inc(s_ib_rx_cq_call);
- ib_req_notify_cq(cq, IB_CQ_SOLICITED);
+ tasklet_schedule(&ic->i_recv_tasklet);
+}
- while (ib_poll_cq(cq, 1, &wc) > 0) {
+static inline void rds_poll_cq(struct rds_ib_connection *ic,
+ struct rds_ib_ack_state *state)
+{
+ struct rds_connection *conn = ic->conn;
+ struct ib_wc wc;
+ struct rds_ib_recv_work *recv;
+
+ while (ib_poll_cq(ic->i_recv_cq, 1, &wc) > 0) {
rdsdebug("wc wr_id 0x%llx status %u byte_len %u imm_data %u\n",
(unsigned long long)wc.wr_id, wc.status, wc.byte_len,
be32_to_cpu(wc.ex.imm_data));
@@ -853,7 +858,7 @@ void rds_ib_recv_cq_comp_handler(struct ib_cq *cq, void *context)
if (rds_conn_up(conn) || rds_conn_connecting(conn)) {
/* We expect errors as the qp is drained during shutdown */
if (wc.status == IB_WC_SUCCESS) {
- rds_ib_process_recv(conn, recv, wc.byte_len, &state);
+ rds_ib_process_recv(conn, recv, wc.byte_len, state);
} else {
rds_ib_conn_error(conn, "recv completion on "
"%pI4 had status %u, disconnecting and "
@@ -864,6 +869,17 @@ void rds_ib_recv_cq_comp_handler(struct ib_cq *cq, void *context)
rds_ib_ring_free(&ic->i_recv_ring, 1);
}
+}
+
+void rds_ib_recv_tasklet_fn(unsigned long data)
+{
+ struct rds_ib_connection *ic = (struct rds_ib_connection *) data;
+ struct rds_connection *conn = ic->conn;
+ struct rds_ib_ack_state state = { 0, };
+
+ rds_poll_cq(ic, &state);
+ ib_req_notify_cq(ic->i_recv_cq, IB_CQ_SOLICITED);
+ rds_poll_cq(ic, &state);
if (state.ack_next_valid)
rds_ib_set_ack(ic, state.ack_next, state.ack_required);
diff --git a/net/rds/iw.h b/net/rds/iw.h
index dd72b62bd506..eef2f0c28476 100644
--- a/net/rds/iw.h
+++ b/net/rds/iw.h
@@ -119,6 +119,7 @@ struct rds_iw_connection {
struct rds_iw_send_work *i_sends;
/* rx */
+ struct tasklet_struct i_recv_tasklet;
struct mutex i_recv_mutex;
struct rds_iw_work_ring i_recv_ring;
struct rds_iw_incoming *i_iwinc;
@@ -330,6 +331,7 @@ void rds_iw_inc_free(struct rds_incoming *inc);
int rds_iw_inc_copy_to_user(struct rds_incoming *inc, struct iovec *iov,
size_t size);
void rds_iw_recv_cq_comp_handler(struct ib_cq *cq, void *context);
+void rds_iw_recv_tasklet_fn(unsigned long data);
void rds_iw_recv_init_ring(struct rds_iw_connection *ic);
void rds_iw_recv_clear_ring(struct rds_iw_connection *ic);
void rds_iw_recv_init_ack(struct rds_iw_connection *ic);
diff --git a/net/rds/iw_cm.c b/net/rds/iw_cm.c
index a416b0d492b1..394cf6b4d0aa 100644
--- a/net/rds/iw_cm.c
+++ b/net/rds/iw_cm.c
@@ -696,6 +696,8 @@ int rds_iw_conn_alloc(struct rds_connection *conn, gfp_t gfp)
return -ENOMEM;
INIT_LIST_HEAD(&ic->iw_node);
+ tasklet_init(&ic->i_recv_tasklet, rds_iw_recv_tasklet_fn,
+ (unsigned long) ic);
mutex_init(&ic->i_recv_mutex);
#ifndef KERNEL_HAS_ATOMIC64
spin_lock_init(&ic->i_ack_lock);
diff --git a/net/rds/iw_recv.c b/net/rds/iw_recv.c
index 9f98150af19f..24fc53f03833 100644
--- a/net/rds/iw_recv.c
+++ b/net/rds/iw_recv.c
@@ -784,17 +784,22 @@ void rds_iw_recv_cq_comp_handler(struct ib_cq *cq, void *context)
{
struct rds_connection *conn = context;
struct rds_iw_connection *ic = conn->c_transport_data;
- struct ib_wc wc;
- struct rds_iw_ack_state state = { 0, };
- struct rds_iw_recv_work *recv;
rdsdebug("conn %p cq %p\n", conn, cq);
rds_iw_stats_inc(s_iw_rx_cq_call);
- ib_req_notify_cq(cq, IB_CQ_SOLICITED);
+ tasklet_schedule(&ic->i_recv_tasklet);
+}
- while (ib_poll_cq(cq, 1, &wc) > 0) {
+static inline void rds_poll_cq(struct rds_iw_connection *ic,
+ struct rds_iw_ack_state *state)
+{
+ struct rds_connection *conn = ic->conn;
+ struct ib_wc wc;
+ struct rds_iw_recv_work *recv;
+
+ while (ib_poll_cq(ic->i_recv_cq, 1, &wc) > 0) {
rdsdebug("wc wr_id 0x%llx status %u byte_len %u imm_data %u\n",
(unsigned long long)wc.wr_id, wc.status, wc.byte_len,
be32_to_cpu(wc.ex.imm_data));
@@ -812,7 +817,7 @@ void rds_iw_recv_cq_comp_handler(struct ib_cq *cq, void *context)
if (rds_conn_up(conn) || rds_conn_connecting(conn)) {
/* We expect errors as the qp is drained during shutdown */
if (wc.status == IB_WC_SUCCESS) {
- rds_iw_process_recv(conn, recv, wc.byte_len, &state);
+ rds_iw_process_recv(conn, recv, wc.byte_len, state);
} else {
rds_iw_conn_error(conn, "recv completion on "
"%pI4 had status %u, disconnecting and "
@@ -823,6 +828,17 @@ void rds_iw_recv_cq_comp_handler(struct ib_cq *cq, void *context)
rds_iw_ring_free(&ic->i_recv_ring, 1);
}
+}
+
+void rds_iw_recv_tasklet_fn(unsigned long data)
+{
+ struct rds_iw_connection *ic = (struct rds_iw_connection *) data;
+ struct rds_connection *conn = ic->conn;
+ struct rds_iw_ack_state state = { 0, };
+
+ rds_poll_cq(ic, &state);
+ ib_req_notify_cq(ic->i_recv_cq, IB_CQ_SOLICITED);
+ rds_poll_cq(ic, &state);
if (state.ack_next_valid)
rds_iw_set_ack(ic, state.ack_next, state.ack_required);