| Message ID | 20220514102739.41252-2-guangguan.wang@linux.alibaba.com (mailing list archive) |
|---|---|
| State | Superseded |
| Delegated to: | Netdev Maintainers |
| Headers | show |
| Series | net/smc: send and write inline optimization for smc | expand |
| Context | Check | Description |
|---|---|---|
| netdev/tree_selection | success | Clearly marked for net-next |
| netdev/fixes_present | success | Fixes tag not required for -next series |
| netdev/subject_prefix | success | Link |
| netdev/cover_letter | success | Series has a cover letter |
| netdev/patch_count | success | Link |
| netdev/header_inline | success | No static functions without inline keyword in header files |
| netdev/build_32bit | success | Errors and warnings before: 0 this patch: 0 |
| netdev/cc_maintainers | success | CCed 7 of 7 maintainers |
| netdev/build_clang | success | Errors and warnings before: 0 this patch: 0 |
| netdev/module_param | success | Was 0 now: 0 |
| netdev/verify_signedoff | success | Signed-off-by tag matches author and committer |
| netdev/verify_fixes | success | No Fixes tag |
| netdev/build_allmodconfig_warn | success | Errors and warnings before: 0 this patch: 0 |
| netdev/checkpatch | warning | WARNING: line length of 90 exceeds 80 columns |
| netdev/kdoc | success | Errors and warnings before: 0 this patch: 0 |
| netdev/source_inline | success | Was 0 now: 0 |
On Sat, May 14, 2022 at 06:27:38PM +0800, Guangguan Wang wrote: > As cdc msg's length is 44B, cdc msgs can be sent inline in > most rdma devices, which can help reducing sending latency. > > In my test environment, which are 2 VMs running on the same > physical host and whose NICs(ConnectX-4Lx) are working on > SR-IOV mode, qperf shows 0.4us-0.7us improvement in latency. > > Test command: > server: smc_run taskset -c 1 qperf > client: smc_run taskset -c 1 qperf <server ip> -oo \ > msg_size:1:2K:*2 -t 30 -vu tcp_lat > > The results shown below: > msgsize before after > 1B 11.9 us 11.2 us (-0.7 us) > 2B 11.7 us 11.2 us (-0.5 us) > 4B 11.7 us 11.3 us (-0.4 us) > 8B 11.6 us 11.2 us (-0.4 us) > 16B 11.7 us 11.3 us (-0.4 us) > 32B 11.7 us 11.3 us (-0.4 us) > 64B 11.7 us 11.2 us (-0.5 us) > 128B 11.6 us 11.2 us (-0.4 us) > 256B 11.8 us 11.2 us (-0.6 us) > 512B 11.8 us 11.4 us (-0.4 us) > 1KB 11.9 us 11.4 us (-0.5 us) > 2KB 12.1 us 11.5 us (-0.6 us) > > Reported-by: kernel test robot <lkp@intel.com> You don't need to add this tag, this tag represents who found the issue. Tested-by is reasonable. > Signed-off-by: Guangguan Wang <guangguan.wang@linux.alibaba.com> Reviewed-by: Tony Lu <tonylu@linux.alibaba.com> Thanks, Tony Lu > --- > net/smc/smc_ib.c | 1 + > net/smc/smc_wr.c | 5 ++++- > 2 files changed, 5 insertions(+), 1 deletion(-) > > diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c > index a3e2d3b89568..dcda4165d107 100644 > --- a/net/smc/smc_ib.c > +++ b/net/smc/smc_ib.c > @@ -671,6 +671,7 @@ int smc_ib_create_queue_pair(struct smc_link *lnk) > .max_recv_wr = SMC_WR_BUF_CNT * 3, > .max_send_sge = SMC_IB_MAX_SEND_SGE, > .max_recv_sge = sges_per_buf, > + .max_inline_data = 0, > }, > .sq_sig_type = IB_SIGNAL_REQ_WR, > .qp_type = IB_QPT_RC, > diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c > index 24be1d03fef9..26f8f240d9e8 100644 > --- a/net/smc/smc_wr.c > +++ b/net/smc/smc_wr.c > @@ -554,10 +554,11 @@ void smc_wr_remember_qp_attr(struct smc_link *lnk) > static void smc_wr_init_sge(struct smc_link *lnk) > { > int sges_per_buf = (lnk->lgr->smc_version == SMC_V2) ? 2 : 1; > + bool send_inline = (lnk->qp_attr.cap.max_inline_data > SMC_WR_TX_SIZE); > u32 i; > > for (i = 0; i < lnk->wr_tx_cnt; i++) { > - lnk->wr_tx_sges[i].addr = > + lnk->wr_tx_sges[i].addr = send_inline ? (uintptr_t)(&lnk->wr_tx_bufs[i]) : > lnk->wr_tx_dma_addr + i * SMC_WR_BUF_SIZE; > lnk->wr_tx_sges[i].length = SMC_WR_TX_SIZE; > lnk->wr_tx_sges[i].lkey = lnk->roce_pd->local_dma_lkey; > @@ -575,6 +576,8 @@ static void smc_wr_init_sge(struct smc_link *lnk) > lnk->wr_tx_ibs[i].opcode = IB_WR_SEND; > lnk->wr_tx_ibs[i].send_flags = > IB_SEND_SIGNALED | IB_SEND_SOLICITED; > + if (send_inline) > + lnk->wr_tx_ibs[i].send_flags |= IB_SEND_INLINE; > lnk->wr_tx_rdmas[i].wr_tx_rdma[0].wr.opcode = IB_WR_RDMA_WRITE; > lnk->wr_tx_rdmas[i].wr_tx_rdma[1].wr.opcode = IB_WR_RDMA_WRITE; > lnk->wr_tx_rdmas[i].wr_tx_rdma[0].wr.sg_list = > -- > 2.24.3 (Apple Git-128)
diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c index a3e2d3b89568..dcda4165d107 100644 --- a/net/smc/smc_ib.c +++ b/net/smc/smc_ib.c @@ -671,6 +671,7 @@ int smc_ib_create_queue_pair(struct smc_link *lnk) .max_recv_wr = SMC_WR_BUF_CNT * 3, .max_send_sge = SMC_IB_MAX_SEND_SGE, .max_recv_sge = sges_per_buf, + .max_inline_data = 0, }, .sq_sig_type = IB_SIGNAL_REQ_WR, .qp_type = IB_QPT_RC, diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c index 24be1d03fef9..26f8f240d9e8 100644 --- a/net/smc/smc_wr.c +++ b/net/smc/smc_wr.c @@ -554,10 +554,11 @@ void smc_wr_remember_qp_attr(struct smc_link *lnk) static void smc_wr_init_sge(struct smc_link *lnk) { int sges_per_buf = (lnk->lgr->smc_version == SMC_V2) ? 2 : 1; + bool send_inline = (lnk->qp_attr.cap.max_inline_data > SMC_WR_TX_SIZE); u32 i; for (i = 0; i < lnk->wr_tx_cnt; i++) { - lnk->wr_tx_sges[i].addr = + lnk->wr_tx_sges[i].addr = send_inline ? (uintptr_t)(&lnk->wr_tx_bufs[i]) : lnk->wr_tx_dma_addr + i * SMC_WR_BUF_SIZE; lnk->wr_tx_sges[i].length = SMC_WR_TX_SIZE; lnk->wr_tx_sges[i].lkey = lnk->roce_pd->local_dma_lkey; @@ -575,6 +576,8 @@ static void smc_wr_init_sge(struct smc_link *lnk) lnk->wr_tx_ibs[i].opcode = IB_WR_SEND; lnk->wr_tx_ibs[i].send_flags = IB_SEND_SIGNALED | IB_SEND_SOLICITED; + if (send_inline) + lnk->wr_tx_ibs[i].send_flags |= IB_SEND_INLINE; lnk->wr_tx_rdmas[i].wr_tx_rdma[0].wr.opcode = IB_WR_RDMA_WRITE; lnk->wr_tx_rdmas[i].wr_tx_rdma[1].wr.opcode = IB_WR_RDMA_WRITE; lnk->wr_tx_rdmas[i].wr_tx_rdma[0].wr.sg_list =
As cdc msg's length is 44B, cdc msgs can be sent inline in most rdma devices, which can help reducing sending latency. In my test environment, which are 2 VMs running on the same physical host and whose NICs(ConnectX-4Lx) are working on SR-IOV mode, qperf shows 0.4us-0.7us improvement in latency. Test command: server: smc_run taskset -c 1 qperf client: smc_run taskset -c 1 qperf <server ip> -oo \ msg_size:1:2K:*2 -t 30 -vu tcp_lat The results shown below: msgsize before after 1B 11.9 us 11.2 us (-0.7 us) 2B 11.7 us 11.2 us (-0.5 us) 4B 11.7 us 11.3 us (-0.4 us) 8B 11.6 us 11.2 us (-0.4 us) 16B 11.7 us 11.3 us (-0.4 us) 32B 11.7 us 11.3 us (-0.4 us) 64B 11.7 us 11.2 us (-0.5 us) 128B 11.6 us 11.2 us (-0.4 us) 256B 11.8 us 11.2 us (-0.6 us) 512B 11.8 us 11.4 us (-0.4 us) 1KB 11.9 us 11.4 us (-0.5 us) 2KB 12.1 us 11.5 us (-0.6 us) Reported-by: kernel test robot <lkp@intel.com> Signed-off-by: Guangguan Wang <guangguan.wang@linux.alibaba.com> --- net/smc/smc_ib.c | 1 + net/smc/smc_wr.c | 5 ++++- 2 files changed, 5 insertions(+), 1 deletion(-)