public inbox for netdev@vger.kernel.org 
 help / color / mirror / Atom feed

From: Florian Westphal <fw@strlen•de>
To: netdev@vger•kernel.org
Cc: davem@davemloft•net, edumazet@google•com, kuba@kernel•org,
	pabeni@redhat•com, shakeelb@google•com, soheil@google•com,
	Florian Westphal <fw@strlen•de>
Subject: [PATCH net] net: avoid indirect memory pressure calls
Date: Fri, 24 Feb 2023 19:46:06 +0100	[thread overview]
Message-ID: <20230224184606.7101-1-fw@strlen.de> (raw)

There is a noticeable tcp performance regression (loopback or cross-netns),
seen with iperf3 -Z (sendfile mode) when generic retpolines are needed.

With SK_RECLAIM_THRESHOLD checks gone number of calls to enter/leave
memory pressure happen much more often. For TCP indirect calls are
used.

We can't remove the if-set-return short-circuit check in
tcp_enter_memory_pressure because there are callers other than
sk_enter_memory_pressure.  Doing a check in the sk wrapper too
reduces the indirect calls enough to recover some performance.

Before,
0.00-60.00  sec   322 GBytes  46.1 Gbits/sec                  receiver

After:
0.00-60.04  sec   359 GBytes  51.4 Gbits/sec                  receiver

"iperf3 -c $peer -t 60 -Z -f g", connected via veth in another netns.

Fixes: 4890b686f408 ("net: keep sk->sk_forward_alloc as small as possible")
Signed-off-by: Florian Westphal <fw@strlen•de>
---
 net/core/sock.c | 22 +++++++++++++---------
 1 file changed, 13 insertions(+), 9 deletions(-)

diff --git a/net/core/sock.c b/net/core/sock.c
index 341c565dbc26..45d247112aa5 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2809,22 +2809,26 @@ EXPORT_SYMBOL(sock_cmsg_send);
 
 static void sk_enter_memory_pressure(struct sock *sk)
 {
-	if (!sk->sk_prot->enter_memory_pressure)
+	unsigned long *memory_pressure = sk->sk_prot->memory_pressure;
+
+	if (!memory_pressure || READ_ONCE(*memory_pressure))
 		return;
 
-	sk->sk_prot->enter_memory_pressure(sk);
+	if (sk->sk_prot->enter_memory_pressure)
+		sk->sk_prot->enter_memory_pressure(sk);
 }
 
 static void sk_leave_memory_pressure(struct sock *sk)
 {
-	if (sk->sk_prot->leave_memory_pressure) {
-		sk->sk_prot->leave_memory_pressure(sk);
-	} else {
-		unsigned long *memory_pressure = sk->sk_prot->memory_pressure;
+	unsigned long *memory_pressure = sk->sk_prot->memory_pressure;
 
-		if (memory_pressure && READ_ONCE(*memory_pressure))
-			WRITE_ONCE(*memory_pressure, 0);
-	}
+	if (!memory_pressure || READ_ONCE(*memory_pressure) == 0)
+		return;
+
+	if (sk->sk_prot->leave_memory_pressure)
+		sk->sk_prot->leave_memory_pressure(sk);
+	else
+		WRITE_ONCE(*memory_pressure, 0);
 }
 
 DEFINE_STATIC_KEY_FALSE(net_high_order_alloc_disable_key);
-- 
2.39.2

next             reply	other threads:[~2023-02-24 18:49 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-02-24 18:46 Florian Westphal [this message]
2023-02-27 23:27 ` [PATCH net] net: avoid indirect memory pressure calls Jakub Kicinski
2023-02-28 16:28   ` Alexander Lobakin
2023-02-28 16:34     ` Florian Westphal
2023-02-28 16:35       ` Eric Dumazet
2023-02-28 16:44 ` Eric Dumazet
2023-02-28 17:42   ` Eric Dumazet
2023-03-01 12:31     ` Florian Westphal
2023-03-01 12:51       ` Eric Dumazet

find likely ancestor, descendant, or conflicting patches for this message:
( dfblob:341c565dbc2 dfblob:45d247112aa )
 OR (
bs:"[PATCH net] net: avoid indirect memory pressure calls" )
	(help)

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=20230224184606.7101-1-fw@strlen.de \
    --to=fw@strlen$(echo .)de \
    --cc=davem@davemloft$(echo .)net \
    --cc=edumazet@google$(echo .)com \
    --cc=kuba@kernel$(echo .)org \
    --cc=netdev@vger$(echo .)kernel.org \
    --cc=pabeni@redhat$(echo .)com \
    --cc=shakeelb@google$(echo .)com \
    --cc=soheil@google$(echo .)com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox