diff options
author | Zhu Yanjun <yanjun.zhu@oracle.com> | 2018-02-27 06:04:32 -0500 |
---|---|---|
committer | Jason Gunthorpe <jgg@mellanox.com> | 2018-03-07 15:56:14 -0700 |
commit | 86af617641512f4aeb78fd25dcec7e0f4bb1d5e5 (patch) | |
tree | 996c99efb1b426b73d0e0f2f2f6437fa1755848f /drivers/infiniband/sw | |
parent | 63cf1a902c9dd6b0761861ea87fce3663f59403b (diff) | |
download | linux-stable-86af617641512f4aeb78fd25dcec7e0f4bb1d5e5.tar.gz linux-stable-86af617641512f4aeb78fd25dcec7e0f4bb1d5e5.tar.bz2 linux-stable-86af617641512f4aeb78fd25dcec7e0f4bb1d5e5.zip |
IB/rxe: remove unnecessary skb_clone
In send_atomic_ack function, it is not necessary to make a
skb_clone. To gain better performance (high throughput and
low latency), this skb_clone is removed.
The following tests are made.
server client
--------- ---------
|1.1.1.1|<----rxe-channel--->|1.1.1.2|
--------- ---------
On server: rping -s -a 1.1.1.1 -v -C 1000 -S 512
On client: rping -c -a 1.1.1.1 -v -C 1000 -S 512
The kernel config CONFIG_DEBUG_KMEMLEAK is enabled on both server
and client.
This test runs for several hours. There is no memory leak and the whole
system can work well.
Based on the above network, the following tests are made.
Server: ibv_rc_pingpong -d rxe0 -g 1
Client: ibv_rc_pingpong -d rxe0 -g 1 1.1.1.1
The test results on Server(10 tests are made).
Before:
Throughput is 137.07 Mbit/sec
Latency is 517.76 usec/iter
After:
Throughput is 148.85 Mbit/sec
Latency is 476.64 usec/iter
The throughput is enhanced and the latency is reduced.
CC: Srinivas Eeda <srinivas.eeda@oracle.com>
CC: Junxiao Bi <junxiao.bi@oracle.com>
Signed-off-by: Zhu Yanjun <yanjun.zhu@oracle.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
Diffstat (limited to 'drivers/infiniband/sw')
-rw-r--r-- | drivers/infiniband/sw/rxe/rxe_resp.c | 15 |
1 files changed, 3 insertions, 12 deletions
diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c index d37bb9b97569..a65c9969f7fc 100644 --- a/drivers/infiniband/sw/rxe/rxe_resp.c +++ b/drivers/infiniband/sw/rxe/rxe_resp.c @@ -969,7 +969,6 @@ static int send_atomic_ack(struct rxe_qp *qp, struct rxe_pkt_info *pkt, int rc = 0; struct rxe_pkt_info ack_pkt; struct sk_buff *skb; - struct sk_buff *skb_copy; struct rxe_dev *rxe = to_rdev(qp->ibqp.device); struct resp_res *res; @@ -981,14 +980,7 @@ static int send_atomic_ack(struct rxe_qp *qp, struct rxe_pkt_info *pkt, goto out; } - skb_copy = skb_clone(skb, GFP_ATOMIC); - if (skb_copy) - rxe_add_ref(qp); /* for the new SKB */ - else { - pr_warn("Could not clone atomic response\n"); - rc = -ENOMEM; - goto out; - } + rxe_add_ref(qp); res = &qp->resp.resources[qp->resp.res_head]; free_rd_atomic_resource(qp, res); @@ -998,19 +990,18 @@ static int send_atomic_ack(struct rxe_qp *qp, struct rxe_pkt_info *pkt, memset((unsigned char *)SKB_TO_PKT(skb) + sizeof(ack_pkt), 0, sizeof(skb->cb) - sizeof(ack_pkt)); + refcount_inc(&skb->users); res->type = RXE_ATOMIC_MASK; res->atomic.skb = skb; res->first_psn = ack_pkt.psn; res->last_psn = ack_pkt.psn; res->cur_psn = ack_pkt.psn; - rc = rxe_xmit_packet(rxe, qp, &ack_pkt, skb_copy); + rc = rxe_xmit_packet(rxe, qp, &ack_pkt, skb); if (rc) { pr_err_ratelimited("Failed sending ack\n"); rxe_drop_ref(qp); - kfree_skb(skb_copy); } - out: return rc; } |