[PATCH v2 2/3] nvme-tcp: support specifying the congestion-control
From: Mingbao Sun <hidden>
Date: 2022-03-11 10:35:54
Also in:
linux-nvme, lkml
Subsystem:
nvm express driver, the rest · Maintainers:
Keith Busch, Jens Axboe, Christoph Hellwig, Sagi Grimberg, Linus Torvalds
From: Mingbao Sun <redacted> congestion-control could have a noticeable impaction on the performance of TCP-based communications. This is of course true to NVMe_over_TCP. Different congestion-controls (e.g., cubic, dctcp) are suitable for different scenarios. Proper adoption of congestion control would benefit the performance. On the contrary, the performance could be destroyed. Though we can specify the congestion-control of NVMe_over_TCP via writing '/proc/sys/net/ipv4/tcp_congestion_control', but this also changes the congestion-control of all the future TCP sockets that have not been explicitly assigned the congestion-control, thus bringing potential impaction on their performance. So it makes sense to make NVMe_over_TCP support specifying the congestion-control. And this commit addresses the host side. Implementation approach: a new option called 'tcp_congestion' was created in fabrics opt_tokens for 'nvme connect' command to passed in the congestion-control specified by the user. Then later in nvme_tcp_alloc_queue, the specified congestion-control would be applied to the relevant sockets of the host side. Signed-off-by: Mingbao Sun <redacted> --- drivers/nvme/host/fabrics.c | 18 ++++++++++++++++++ drivers/nvme/host/fabrics.h | 2 ++ drivers/nvme/host/tcp.c | 17 ++++++++++++++++- 3 files changed, 36 insertions(+), 1 deletion(-)
diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
index ee79a6d639b4..ecd1ec4e473a 100644
--- a/drivers/nvme/host/fabrics.c
+++ b/drivers/nvme/host/fabrics.c@@ -10,6 +10,7 @@ #include <linux/mutex.h> #include <linux/parser.h> #include <linux/seq_file.h> +#include <net/tcp.h> #include "nvme.h" #include "fabrics.h"
@@ -548,6 +549,7 @@ static const match_table_t opt_tokens = { { NVMF_OPT_TOS, "tos=%d" }, { NVMF_OPT_FAIL_FAST_TMO, "fast_io_fail_tmo=%d" }, { NVMF_OPT_DISCOVERY, "discovery" }, + { NVMF_OPT_TCP_CONGESTION, "tcp_congestion=%s" }, { NVMF_OPT_ERR, NULL } };
@@ -829,6 +831,21 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts, case NVMF_OPT_DISCOVERY: opts->discovery_nqn = true; break; + case NVMF_OPT_TCP_CONGESTION: + p = match_strdup(args); + if (!p) { + ret = -ENOMEM; + goto out; + } + if (strlen(p) >= TCP_CA_NAME_MAX) { + ret = -EINVAL; + kfree(p); + goto out; + } + + kfree(opts->tcp_congestion); + opts->tcp_congestion = p; + break; default: pr_warn("unknown parameter or missing value '%s' in ctrl creation request\n", p);
@@ -947,6 +964,7 @@ void nvmf_free_options(struct nvmf_ctrl_options *opts) kfree(opts->subsysnqn); kfree(opts->host_traddr); kfree(opts->host_iface); + kfree(opts->tcp_congestion); kfree(opts); } EXPORT_SYMBOL_GPL(nvmf_free_options);
diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h
index c3203ff1c654..25fdc169949d 100644
--- a/drivers/nvme/host/fabrics.h
+++ b/drivers/nvme/host/fabrics.h@@ -68,6 +68,7 @@ enum { NVMF_OPT_FAIL_FAST_TMO = 1 << 20, NVMF_OPT_HOST_IFACE = 1 << 21, NVMF_OPT_DISCOVERY = 1 << 22, + NVMF_OPT_TCP_CONGESTION = 1 << 23, }; /**
@@ -117,6 +118,7 @@ struct nvmf_ctrl_options { unsigned int nr_io_queues; unsigned int reconnect_delay; bool discovery_nqn; + const char *tcp_congestion; bool duplicate_connect; unsigned int kato; struct nvmf_host *host;
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 10fc45d95b86..8491f96a39e5 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c@@ -1487,6 +1487,20 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, if (nctrl->opts->tos >= 0) ip_sock_set_tos(queue->sock->sk, nctrl->opts->tos); + if (nctrl->opts->mask & NVMF_OPT_TCP_CONGESTION) { + lock_sock(queue->sock->sk); + ret = tcp_set_congestion_control(queue->sock->sk, + nctrl->opts->tcp_congestion, + true, true); + release_sock(queue->sock->sk); + if (ret) { + dev_err(nctrl->device, + "failed to set TCP congestion to %s: %d\n", + nctrl->opts->tcp_congestion, ret); + goto err_sock; + } + } + /* Set 10 seconds timeout for icresp recvmsg */ queue->sock->sk->sk_rcvtimeo = 10 * HZ;
@@ -2650,7 +2664,8 @@ static struct nvmf_transport_ops nvme_tcp_transport = { NVMF_OPT_HOST_TRADDR | NVMF_OPT_CTRL_LOSS_TMO | NVMF_OPT_HDR_DIGEST | NVMF_OPT_DATA_DIGEST | NVMF_OPT_NR_WRITE_QUEUES | NVMF_OPT_NR_POLL_QUEUES | - NVMF_OPT_TOS | NVMF_OPT_HOST_IFACE, + NVMF_OPT_TOS | NVMF_OPT_HOST_IFACE | + NVMF_OPT_TCP_CONGESTION, .create_ctrl = nvme_tcp_create_ctrl, };
--
2.26.2