diff options
author | Wen Gu <guwen@linux.alibaba.com> | 2022-07-14 17:44:04 +0800 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2022-07-18 11:19:17 +0100 |
commit | b8d199451c99b3796b840c350eb74b830c5c869b (patch) | |
tree | 093913b805c7371a39140ac2f603c9da08950b08 /net/smc/af_smc.c | |
parent | b984f370ed5182d180f92dbf14bdf847ff6ccc04 (diff) |
net/smc: Allow virtually contiguous sndbufs or RMBs for SMC-R
On long-running enterprise production servers, high-order contiguous
memory pages are usually very rare and in most cases we can only get
fragmented pages.
When replacing TCP with SMC-R in such production scenarios, attempting
to allocate high-order physically contiguous sndbufs and RMBs may result
in frequent memory compaction, which will cause unexpected hung issue
and further stability risks.
So this patch is aimed to allow SMC-R link group to use virtually
contiguous sndbufs and RMBs to avoid potential issues mentioned above.
Whether to use physically or virtually contiguous buffers can be set
by sysctl smcr_buf_type.
Note that using virtually contiguous buffers will bring an acceptable
performance regression, which can be mainly divided into two parts:
1) regression in data path, which is brought by additional address
translation of sndbuf by RNIC in Tx. But in general, translating
address through MTT is fast.
Taking 256KB sndbuf and RMB as an example, the comparisons in qperf
latency and bandwidth test with physically and virtually contiguous
buffers are as follows:
- client:
smc_run taskset -c <cpu> qperf <server> -oo msg_size:1:64K:*2\
-t 5 -vu tcp_{bw|lat}
- server:
smc_run taskset -c <cpu> qperf
[latency]
msgsize tcp smcr smcr-use-virt-buf
1 11.17 us 7.56 us 7.51 us (-0.67%)
2 10.65 us 7.74 us 7.56 us (-2.31%)
4 11.11 us 7.52 us 7.59 us ( 0.84%)
8 10.83 us 7.55 us 7.51 us (-0.48%)
16 11.21 us 7.46 us 7.51 us ( 0.71%)
32 10.65 us 7.53 us 7.58 us ( 0.61%)
64 10.95 us 7.74 us 7.80 us ( 0.76%)
128 11.14 us 7.83 us 7.87 us ( 0.47%)
256 10.97 us 7.94 us 7.92 us (-0.28%)
512 11.23 us 7.94 us 8.20 us ( 3.25%)
1024 11.60 us 8.12 us 8.20 us ( 0.96%)
2048 14.04 us 8.30 us 8.51 us ( 2.49%)
4096 16.88 us 9.13 us 9.07 us (-0.64%)
8192 22.50 us 10.56 us 11.22 us ( 6.26%)
16384 28.99 us 12.88 us 13.83 us ( 7.37%)
32768 40.13 us 16.76 us 16.95 us ( 1.16%)
65536 68.70 us 24.68 us 24.85 us ( 0.68%)
[bandwidth]
msgsize tcp smcr smcr-use-virt-buf
1 1.65 MB/s 1.59 MB/s 1.53 MB/s (-3.88%)
2 3.32 MB/s 3.17 MB/s 3.08 MB/s (-2.67%)
4 6.66 MB/s 6.33 MB/s 6.09 MB/s (-3.85%)
8 13.67 MB/s 13.45 MB/s 11.97 MB/s (-10.99%)
16 25.36 MB/s 27.15 MB/s 24.16 MB/s (-11.01%)
32 48.22 MB/s 54.24 MB/s 49.41 MB/s (-8.89%)
64 106.79 MB/s 107.32 MB/s 99.05 MB/s (-7.71%)
128 210.21 MB/s 202.46 MB/s 201.02 MB/s (-0.71%)
256 400.81 MB/s 416.81 MB/s 393.52 MB/s (-5.59%)
512 746.49 MB/s 834.12 MB/s 809.99 MB/s (-2.89%)
1024 1292.33 MB/s 1641.96 MB/s 1571.82 MB/s (-4.27%)
2048 2007.64 MB/s 2760.44 MB/s 2717.68 MB/s (-1.55%)
4096 2665.17 MB/s 4157.44 MB/s 4070.76 MB/s (-2.09%)
8192 3159.72 MB/s 4361.57 MB/s 4270.65 MB/s (-2.08%)
16384 4186.70 MB/s 4574.13 MB/s 4501.17 MB/s (-1.60%)
32768 4093.21 MB/s 4487.42 MB/s 4322.43 MB/s (-3.68%)
65536 4057.14 MB/s 4735.61 MB/s 4555.17 MB/s (-3.81%)
2) regression in buffer initialization and destruction path, which is
brought by additional MR operations of sndbufs. But thanks to link
group buffer reuse mechanism, the impact of this kind of regression
decreases as times of buffer reuse increases.
Taking 256KB sndbuf and RMB as an example, latency of some key SMC-R
buffer-related function obtained by bpftrace are as follows:
Function Phys-bufs Virt-bufs
smcr_new_buf_create() 67154 ns 79164 ns
smc_ib_buf_map_sg() 525 ns 928 ns
smc_ib_get_memory_region() 162294 ns 161191 ns
smc_wr_reg_send() 9957 ns 9635 ns
smc_ib_put_memory_region() 203548 ns 198374 ns
smc_ib_buf_unmap_sg() 508 ns 1158 ns
------------
Test environment notes:
1. Above tests run on 2 VMs within the same Host.
2. The NIC is ConnectX-4Lx, using SRIOV and passing through 2 VFs to
the each VM respectively.
3. VMs' vCPUs are binded to different physical CPUs, and the binded
physical CPUs are isolated by `isolcpus=xxx` cmdline.
4. NICs' queue number are set to 1.
Signed-off-by: Wen Gu <guwen@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/smc/af_smc.c')
-rw-r--r-- | net/smc/af_smc.c | 66 |
1 files changed, 58 insertions, 8 deletions
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 9497a3b9ad09..6e70d9c10b78 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -487,6 +487,29 @@ static void smc_copy_sock_settings_to_smc(struct smc_sock *smc) smc_copy_sock_settings(&smc->sk, smc->clcsock->sk, SK_FLAGS_CLC_TO_SMC); } +/* register the new vzalloced sndbuf on all links */ +static int smcr_lgr_reg_sndbufs(struct smc_link *link, + struct smc_buf_desc *snd_desc) +{ + struct smc_link_group *lgr = link->lgr; + int i, rc = 0; + + if (!snd_desc->is_vm) + return -EINVAL; + + /* protect against parallel smcr_link_reg_buf() */ + mutex_lock(&lgr->llc_conf_mutex); + for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { + if (!smc_link_active(&lgr->lnk[i])) + continue; + rc = smcr_link_reg_buf(&lgr->lnk[i], snd_desc); + if (rc) + break; + } + mutex_unlock(&lgr->llc_conf_mutex); + return rc; +} + /* register the new rmb on all links */ static int smcr_lgr_reg_rmbs(struct smc_link *link, struct smc_buf_desc *rmb_desc) @@ -498,13 +521,13 @@ static int smcr_lgr_reg_rmbs(struct smc_link *link, if (rc) return rc; /* protect against parallel smc_llc_cli_rkey_exchange() and - * parallel smcr_link_reg_rmb() + * parallel smcr_link_reg_buf() */ mutex_lock(&lgr->llc_conf_mutex); for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { if (!smc_link_active(&lgr->lnk[i])) continue; - rc = smcr_link_reg_rmb(&lgr->lnk[i], rmb_desc); + rc = smcr_link_reg_buf(&lgr->lnk[i], rmb_desc); if (rc) goto out; } @@ -550,8 +573,15 @@ static int smcr_clnt_conf_first_link(struct smc_sock *smc) smc_wr_remember_qp_attr(link); - if (smcr_link_reg_rmb(link, smc->conn.rmb_desc)) - return SMC_CLC_DECL_ERR_REGRMB; + /* reg the sndbuf if it was vzalloced */ + if (smc->conn.sndbuf_desc->is_vm) { + if (smcr_link_reg_buf(link, smc->conn.sndbuf_desc)) + return SMC_CLC_DECL_ERR_REGBUF; + } + + /* reg the rmb */ + if (smcr_link_reg_buf(link, smc->conn.rmb_desc)) + return SMC_CLC_DECL_ERR_REGBUF; /* confirm_rkey is implicit on 1st contact */ smc->conn.rmb_desc->is_conf_rkey = true; @@ -1221,8 +1251,15 @@ static int smc_connect_rdma(struct smc_sock *smc, goto connect_abort; } } else { + /* reg sendbufs if they were vzalloced */ + if (smc->conn.sndbuf_desc->is_vm) { + if (smcr_lgr_reg_sndbufs(link, smc->conn.sndbuf_desc)) { + reason_code = SMC_CLC_DECL_ERR_REGBUF; + goto connect_abort; + } + } if (smcr_lgr_reg_rmbs(link, smc->conn.rmb_desc)) { - reason_code = SMC_CLC_DECL_ERR_REGRMB; + reason_code = SMC_CLC_DECL_ERR_REGBUF; goto connect_abort; } } @@ -1749,8 +1786,15 @@ static int smcr_serv_conf_first_link(struct smc_sock *smc) struct smc_llc_qentry *qentry; int rc; - if (smcr_link_reg_rmb(link, smc->conn.rmb_desc)) - return SMC_CLC_DECL_ERR_REGRMB; + /* reg the sndbuf if it was vzalloced*/ + if (smc->conn.sndbuf_desc->is_vm) { + if (smcr_link_reg_buf(link, smc->conn.sndbuf_desc)) + return SMC_CLC_DECL_ERR_REGBUF; + } + + /* reg the rmb */ + if (smcr_link_reg_buf(link, smc->conn.rmb_desc)) + return SMC_CLC_DECL_ERR_REGBUF; /* send CONFIRM LINK request to client over the RoCE fabric */ rc = smc_llc_send_confirm_link(link, SMC_LLC_REQ); @@ -2109,8 +2153,14 @@ static int smc_listen_rdma_reg(struct smc_sock *new_smc, bool local_first) struct smc_connection *conn = &new_smc->conn; if (!local_first) { + /* reg sendbufs if they were vzalloced */ + if (conn->sndbuf_desc->is_vm) { + if (smcr_lgr_reg_sndbufs(conn->lnk, + conn->sndbuf_desc)) + return SMC_CLC_DECL_ERR_REGBUF; + } if (smcr_lgr_reg_rmbs(conn->lnk, conn->rmb_desc)) - return SMC_CLC_DECL_ERR_REGRMB; + return SMC_CLC_DECL_ERR_REGBUF; } return 0; |