diff mbox series

[v2,3/3] nvmet-tcp: support specifying the congestion-control

Message ID 20220311103414.8255-3-sunmingbao@tom.com (mailing list archive)
State Not Applicable
Delegated to: Netdev Maintainers
Headers show
Series [v2,1/3] tcp: export symbol tcp_set_congestion_control | expand

Checks

Context Check Description
netdev/fixes_present success Fixes tag not required for -next series
netdev/subject_prefix success Link
netdev/cover_letter warning Series does not have 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: 7 this patch: 7
netdev/cc_maintainers success CCed 4 of 4 maintainers
netdev/build_clang success Errors and warnings before: 6 this patch: 6
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: 3 this patch: 3
netdev/checkpatch warning CHECK: Alignment should match open parenthesis
netdev/kdoc fail Errors and warnings before: 12 this patch: 13
netdev/source_inline success Was 0 now: 0
netdev/tree_selection success Guessing tree name failed - patch did not apply, async

Commit Message

Mingbao Sun March 11, 2022, 10:34 a.m. UTC 
From: Mingbao Sun <tyler.sun@dell.com>

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 target side.

Implementation approach:
the following new file entry was created for user to specify the
congestion-control of each nvmet port.
'/sys/kernel/config/nvmet/ports/X/tcp_congestion'
Then later in nvmet_tcp_add_port, the specified congestion-control
would be applied to the listening socket of the nvmet port.

Signed-off-by: Mingbao Sun <tyler.sun@dell.com>
---
 drivers/nvme/target/configfs.c | 42 ++++++++++++++++++++++++++++++++++
 drivers/nvme/target/nvmet.h    |  1 +
 drivers/nvme/target/tcp.c      | 13 +++++++++++
 3 files changed, 56 insertions(+)

Comments

Sagi Grimberg March 13, 2022, 11:44 a.m. UTC | #1 
> From: Mingbao Sun <tyler.sun@dell.com>

Hey Mingbao,

> 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 target side.
> 
> Implementation approach:
> the following new file entry was created for user to specify the
> congestion-control of each nvmet port.
> '/sys/kernel/config/nvmet/ports/X/tcp_congestion'
> Then later in nvmet_tcp_add_port, the specified congestion-control
> would be applied to the listening socket of the nvmet port.

Please see my comments on the host side patch.

In addition, specifically on the chosen interface, why should this
be port specific? What is the use-case to configure this per-port?
diff mbox series

Patch

diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c
index 091a0ca16361..7b7d95f6f582 100644
--- a/drivers/nvme/target/configfs.c
+++ b/drivers/nvme/target/configfs.c
@@ -11,6 +11,7 @@ 
 #include <linux/ctype.h>
 #include <linux/pci.h>
 #include <linux/pci-p2pdma.h>
+#include <net/tcp.h>
 
 #include "nvmet.h"
 
@@ -222,6 +223,45 @@  static ssize_t nvmet_addr_trsvcid_store(struct config_item *item,
 
 CONFIGFS_ATTR(nvmet_, addr_trsvcid);
 
+static ssize_t nvmet_tcp_congestion_show(struct config_item *item,
+		char *page)
+{
+	struct nvmet_port *port = to_nvmet_port(item);
+
+	return snprintf(page, PAGE_SIZE, "%s\n",
+			port->tcp_congestion ? port->tcp_congestion : "");
+}
+
+static ssize_t nvmet_tcp_congestion_store(struct config_item *item,
+		const char *page, size_t count)
+{
+	struct nvmet_port *port = to_nvmet_port(item);
+	int len;
+	char *buf;
+
+	len = strcspn(page, "\n");
+	if (!len)
+		return -EINVAL;
+
+	if (nvmet_is_port_enabled(port, __func__))
+		return -EACCES;
+
+	buf = kmemdup_nul(page, len, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+	if (strlen(buf) >= TCP_CA_NAME_MAX) {
+		kfree(buf);
+		return -EINVAL;
+	}
+
+	kfree(port->tcp_congestion);
+	port->tcp_congestion = buf;
+
+	return count;
+}
+
+CONFIGFS_ATTR(nvmet_, tcp_congestion);
+
 static ssize_t nvmet_param_inline_data_size_show(struct config_item *item,
 		char *page)
 {
@@ -1597,6 +1637,7 @@  static void nvmet_port_release(struct config_item *item)
 	list_del(&port->global_entry);
 
 	kfree(port->ana_state);
+	kfree(port->tcp_congestion);
 	kfree(port);
 }
 
@@ -1605,6 +1646,7 @@  static struct configfs_attribute *nvmet_port_attrs[] = {
 	&nvmet_attr_addr_treq,
 	&nvmet_attr_addr_traddr,
 	&nvmet_attr_addr_trsvcid,
+	&nvmet_attr_tcp_congestion,
 	&nvmet_attr_addr_trtype,
 	&nvmet_attr_param_inline_data_size,
 #ifdef CONFIG_BLK_DEV_INTEGRITY
diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h
index 69637bf8f8e1..76a57c4c3456 100644
--- a/drivers/nvme/target/nvmet.h
+++ b/drivers/nvme/target/nvmet.h
@@ -145,6 +145,7 @@  struct nvmet_port {
 	struct config_group		ana_groups_group;
 	struct nvmet_ana_group		ana_default_group;
 	enum nvme_ana_state		*ana_state;
+	const char			*tcp_congestion;
 	void				*priv;
 	bool				enabled;
 	int				inline_data_size;
diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index 83ca577f72be..311383c6d7da 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -1741,6 +1741,19 @@  static int nvmet_tcp_add_port(struct nvmet_port *nport)
 	if (so_priority > 0)
 		sock_set_priority(port->sock->sk, so_priority);
 
+	if (nport->tcp_congestion) {
+		lock_sock(port->sock->sk);
+		ret = tcp_set_congestion_control(port->sock->sk,
+						 nport->tcp_congestion,
+						 true, true);
+		release_sock(port->sock->sk);
+		if (ret) {
+			pr_err("failed to set port socket's congestion to %s: %d\n",
+			       nport->tcp_congestion, ret);
+			goto err_sock;
+		}
+	}
+
 	ret = kernel_bind(port->sock, (struct sockaddr *)&port->addr,
 			sizeof(port->addr));
 	if (ret) {