[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-ID: <20260117164255.785751-1-kuba@kernel.org>
Date: Sat, 17 Jan 2026 08:42:55 -0800
From: Jakub Kicinski <kuba@...nel.org>
To: edumazet@...gle.com
Cc: kuniyu@...gle.com,
ncardwell@...gle.com,
netdev@...r.kernel.org,
davem@...emloft.net,
pabeni@...hat.com,
andrew+netdev@...n.ch,
horms@...nel.org,
Jakub Kicinski <kuba@...nel.org>
Subject: [PATCH net-next] tcp: try to defer / return acked skbs to originating CPU
Running a memcache-like workload under production(ish) load
on a 300 thread AMD machine we see ~3% of CPU time spent
in kmem_cache_free() via tcp_ack(), freeing skbs from rtx queue.
This workloads pins workers away from softirq CPU so
the Tx skbs are pretty much always allocated on a different
CPU than where the ACKs arrive. Try to use the defer skb free
queue to return the skbs back to where they came from.
This results in a ~4% performance improvement for the workload.
Signed-off-by: Jakub Kicinski <kuba@...nel.org>
---
include/net/tcp.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/include/net/tcp.h b/include/net/tcp.h
index ef0fee58fde8..e290651da508 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -332,7 +332,7 @@ static inline void tcp_wmem_free_skb(struct sock *sk, struct sk_buff *skb)
sk_mem_uncharge(sk, skb->truesize);
else
sk_mem_uncharge(sk, SKB_TRUESIZE(skb_end_offset(skb)));
- __kfree_skb(skb);
+ skb_attempt_defer_free(skb);
}
void sk_forced_mem_schedule(struct sock *sk, int size);
--
2.52.0
Powered by blists - more mailing lists