From: Allison Henderson <achender@kernel.org>
To: netdev@vger.kernel.org
Subject: [RFC 01/15] net/rds: Add per cp work queue
Date: Wed, 22 Oct 2025 12:17:01 -0700 [thread overview]
Message-ID: <20251022191715.157755-2-achender@kernel.org> (raw)
In-Reply-To: <20251022191715.157755-1-achender@kernel.org>
From: Allison Henderson <allison.henderson@oracle.com>
This patch adds a per connection workqueue which can be initialized
and used independently of the globally shared rds_wq.
This patch is the first in a series that aims to address tcp ack
timeouts during the tcp socket shutdown sequence.
This initial refactoring lays the ground work needed to alleviate
queue congestion during heavy reads and writes. The independently
managed queues will allow shutdowns and reconnects respond more quickly
before the peer(s) timeout waiting for the proper acks.
Signed-off-by: Allison Henderson <allison.henderson@oracle.com>
---
net/rds/connection.c | 5 +++--
net/rds/ib_recv.c | 2 +-
net/rds/ib_send.c | 2 +-
net/rds/rds.h | 1 +
net/rds/send.c | 8 ++++----
net/rds/tcp_recv.c | 2 +-
net/rds/tcp_send.c | 2 +-
net/rds/threads.c | 16 ++++++++--------
8 files changed, 20 insertions(+), 18 deletions(-)
diff --git a/net/rds/connection.c b/net/rds/connection.c
index 68bc88cce84e..dc7323707f45 100644
--- a/net/rds/connection.c
+++ b/net/rds/connection.c
@@ -269,6 +269,7 @@ static struct rds_connection *__rds_conn_create(struct net *net,
__rds_conn_path_init(conn, &conn->c_path[i],
is_outgoing);
conn->c_path[i].cp_index = i;
+ conn->c_path[i].cp_wq = rds_wq;
}
rcu_read_lock();
if (rds_destroy_pending(conn))
@@ -884,7 +885,7 @@ void rds_conn_path_drop(struct rds_conn_path *cp, bool destroy)
rcu_read_unlock();
return;
}
- queue_work(rds_wq, &cp->cp_down_w);
+ queue_work(cp->cp_wq, &cp->cp_down_w);
rcu_read_unlock();
}
EXPORT_SYMBOL_GPL(rds_conn_path_drop);
@@ -909,7 +910,7 @@ void rds_conn_path_connect_if_down(struct rds_conn_path *cp)
}
if (rds_conn_path_state(cp) == RDS_CONN_DOWN &&
!test_and_set_bit(RDS_RECONNECT_PENDING, &cp->cp_flags))
- queue_delayed_work(rds_wq, &cp->cp_conn_w, 0);
+ queue_delayed_work(cp->cp_wq, &cp->cp_conn_w, 0);
rcu_read_unlock();
}
EXPORT_SYMBOL_GPL(rds_conn_path_connect_if_down);
diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c
index 4248dfa816eb..357128d34a54 100644
--- a/net/rds/ib_recv.c
+++ b/net/rds/ib_recv.c
@@ -457,7 +457,7 @@ void rds_ib_recv_refill(struct rds_connection *conn, int prefill, gfp_t gfp)
(must_wake ||
(can_wait && rds_ib_ring_low(&ic->i_recv_ring)) ||
rds_ib_ring_empty(&ic->i_recv_ring))) {
- queue_delayed_work(rds_wq, &conn->c_recv_w, 1);
+ queue_delayed_work(conn->c_path->cp_wq, &conn->c_recv_w, 1);
}
if (can_wait)
cond_resched();
diff --git a/net/rds/ib_send.c b/net/rds/ib_send.c
index 4190b90ff3b1..e35bbb6ffb68 100644
--- a/net/rds/ib_send.c
+++ b/net/rds/ib_send.c
@@ -419,7 +419,7 @@ void rds_ib_send_add_credits(struct rds_connection *conn, unsigned int credits)
atomic_add(IB_SET_SEND_CREDITS(credits), &ic->i_credits);
if (test_and_clear_bit(RDS_LL_SEND_FULL, &conn->c_flags))
- queue_delayed_work(rds_wq, &conn->c_send_w, 0);
+ queue_delayed_work(conn->c_path->cp_wq, &conn->c_send_w, 0);
WARN_ON(IB_GET_SEND_CREDITS(credits) >= 16384);
diff --git a/net/rds/rds.h b/net/rds/rds.h
index 5b1c072e2e7f..11fa304f2164 100644
--- a/net/rds/rds.h
+++ b/net/rds/rds.h
@@ -118,6 +118,7 @@ struct rds_conn_path {
void *cp_transport_data;
+ struct workqueue_struct *cp_wq;
atomic_t cp_state;
unsigned long cp_send_gen;
unsigned long cp_flags;
diff --git a/net/rds/send.c b/net/rds/send.c
index 0b3d0ef2f008..ed8d84a74c34 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -458,7 +458,7 @@ int rds_send_xmit(struct rds_conn_path *cp)
if (rds_destroy_pending(cp->cp_conn))
ret = -ENETUNREACH;
else
- queue_delayed_work(rds_wq, &cp->cp_send_w, 1);
+ queue_delayed_work(cp->cp_wq, &cp->cp_send_w, 1);
rcu_read_unlock();
} else if (raced) {
rds_stats_inc(s_send_lock_queue_raced);
@@ -1380,7 +1380,7 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
if (rds_destroy_pending(cpath->cp_conn))
ret = -ENETUNREACH;
else
- queue_delayed_work(rds_wq, &cpath->cp_send_w, 1);
+ queue_delayed_work(cpath->cp_wq, &cpath->cp_send_w, 1);
rcu_read_unlock();
}
if (ret)
@@ -1470,10 +1470,10 @@ rds_send_probe(struct rds_conn_path *cp, __be16 sport,
rds_stats_inc(s_send_queued);
rds_stats_inc(s_send_pong);
- /* schedule the send work on rds_wq */
+ /* schedule the send work on cp_wq */
rcu_read_lock();
if (!rds_destroy_pending(cp->cp_conn))
- queue_delayed_work(rds_wq, &cp->cp_send_w, 1);
+ queue_delayed_work(cp->cp_wq, &cp->cp_send_w, 1);
rcu_read_unlock();
rds_message_put(rm);
diff --git a/net/rds/tcp_recv.c b/net/rds/tcp_recv.c
index 7997a19d1da3..b7cf7f451430 100644
--- a/net/rds/tcp_recv.c
+++ b/net/rds/tcp_recv.c
@@ -327,7 +327,7 @@ void rds_tcp_data_ready(struct sock *sk)
if (rds_tcp_read_sock(cp, GFP_ATOMIC) == -ENOMEM) {
rcu_read_lock();
if (!rds_destroy_pending(cp->cp_conn))
- queue_delayed_work(rds_wq, &cp->cp_recv_w, 0);
+ queue_delayed_work(cp->cp_wq, &cp->cp_recv_w, 0);
rcu_read_unlock();
}
out:
diff --git a/net/rds/tcp_send.c b/net/rds/tcp_send.c
index 7d284ac7e81a..4e82c9644aa6 100644
--- a/net/rds/tcp_send.c
+++ b/net/rds/tcp_send.c
@@ -201,7 +201,7 @@ void rds_tcp_write_space(struct sock *sk)
rcu_read_lock();
if ((refcount_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf &&
!rds_destroy_pending(cp->cp_conn))
- queue_delayed_work(rds_wq, &cp->cp_send_w, 0);
+ queue_delayed_work(cp->cp_wq, &cp->cp_send_w, 0);
rcu_read_unlock();
out:
diff --git a/net/rds/threads.c b/net/rds/threads.c
index 1f424cbfcbb4..639302bab51e 100644
--- a/net/rds/threads.c
+++ b/net/rds/threads.c
@@ -89,8 +89,8 @@ void rds_connect_path_complete(struct rds_conn_path *cp, int curr)
set_bit(0, &cp->cp_conn->c_map_queued);
rcu_read_lock();
if (!rds_destroy_pending(cp->cp_conn)) {
- queue_delayed_work(rds_wq, &cp->cp_send_w, 0);
- queue_delayed_work(rds_wq, &cp->cp_recv_w, 0);
+ queue_delayed_work(cp->cp_wq, &cp->cp_send_w, 0);
+ queue_delayed_work(cp->cp_wq, &cp->cp_recv_w, 0);
}
rcu_read_unlock();
cp->cp_conn->c_proposed_version = RDS_PROTOCOL_VERSION;
@@ -140,7 +140,7 @@ void rds_queue_reconnect(struct rds_conn_path *cp)
cp->cp_reconnect_jiffies = rds_sysctl_reconnect_min_jiffies;
rcu_read_lock();
if (!rds_destroy_pending(cp->cp_conn))
- queue_delayed_work(rds_wq, &cp->cp_conn_w, 0);
+ queue_delayed_work(cp->cp_wq, &cp->cp_conn_w, 0);
rcu_read_unlock();
return;
}
@@ -151,7 +151,7 @@ void rds_queue_reconnect(struct rds_conn_path *cp)
conn, &conn->c_laddr, &conn->c_faddr);
rcu_read_lock();
if (!rds_destroy_pending(cp->cp_conn))
- queue_delayed_work(rds_wq, &cp->cp_conn_w,
+ queue_delayed_work(cp->cp_wq, &cp->cp_conn_w,
rand % cp->cp_reconnect_jiffies);
rcu_read_unlock();
@@ -203,11 +203,11 @@ void rds_send_worker(struct work_struct *work)
switch (ret) {
case -EAGAIN:
rds_stats_inc(s_send_immediate_retry);
- queue_delayed_work(rds_wq, &cp->cp_send_w, 0);
+ queue_delayed_work(cp->cp_wq, &cp->cp_send_w, 0);
break;
case -ENOMEM:
rds_stats_inc(s_send_delayed_retry);
- queue_delayed_work(rds_wq, &cp->cp_send_w, 2);
+ queue_delayed_work(cp->cp_wq, &cp->cp_send_w, 2);
break;
default:
break;
@@ -228,11 +228,11 @@ void rds_recv_worker(struct work_struct *work)
switch (ret) {
case -EAGAIN:
rds_stats_inc(s_recv_immediate_retry);
- queue_delayed_work(rds_wq, &cp->cp_recv_w, 0);
+ queue_delayed_work(cp->cp_wq, &cp->cp_recv_w, 0);
break;
case -ENOMEM:
rds_stats_inc(s_recv_delayed_retry);
- queue_delayed_work(rds_wq, &cp->cp_recv_w, 2);
+ queue_delayed_work(cp->cp_wq, &cp->cp_recv_w, 2);
break;
default:
break;
--
2.43.0
next prev parent reply other threads:[~2025-10-22 19:17 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-10-22 19:17 [RFC 00/15] net/rds: RDS-TCP bug fix collection Allison Henderson
2025-10-22 19:17 ` Allison Henderson [this message]
2025-10-22 19:17 ` [RFC 02/15] net/rds: Give each connection its own workqueue Allison Henderson
2025-10-22 19:17 ` [RFC 03/15] net/rds: Change return code from rds_send_xmit() when lock is taken Allison Henderson
2025-10-22 19:17 ` [RFC 04/15] net/rds: No shortcut out of RDS_CONN_ERROR Allison Henderson
2025-10-22 19:17 ` [RFC 05/15] net/rds: rds_tcp_accept_one ought to not discard messages Allison Henderson
2025-10-22 19:17 ` [RFC 06/15] net/rds: new extension header: rdma bytes Allison Henderson
2025-10-22 19:17 ` [RFC 07/15] net/rds: Encode cp_index in TCP source port Allison Henderson
2025-10-22 19:17 ` [RFC 08/15] net/rds: rds_tcp_conn_path_shutdown must not discard messages Allison Henderson
2025-10-22 19:17 ` [RFC 09/15] net/rds: Kick-start TCP receiver after accept Allison Henderson
2025-10-22 19:17 ` [RFC 10/15] net/rds: Clear reconnect pending bit Allison Henderson
2025-10-22 19:17 ` [RFC 11/15] net/rds: Use the first lane until RDS_EXTHDR_NPATHS arrives Allison Henderson
2025-10-22 19:17 ` [RFC 12/15] net/rds: Trigger rds_send_ping() more than once Allison Henderson
2025-10-22 19:17 ` [RFC 13/15] net/rds: Delegate fan-out to a background worker Allison Henderson
2025-10-22 19:17 ` [RFC 14/15] net/rds: Use proper peer port number even when not connected Allison Henderson
2025-10-22 19:17 ` [RFC 15/15] net/rds: rds_sendmsg should not discard payload_len Allison Henderson
2025-10-22 22:04 ` [RFC 00/15] net/rds: RDS-TCP bug fix collection Allison Henderson
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20251022191715.157755-2-achender@kernel.org \
--to=achender@kernel.org \
--cc=netdev@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).