+1
−1
+20
−10
+13
−6
Loading
Eric Dumazet says: ==================== tcp: even faster connect() under stress This is a followup on the prior series, "tcp: scale connect() under pressure" Now spinlocks are no longer in the picture, we see a very high cost of the inet6_ehashfn() function. In this series (of 2), I change how lport contributes to inet6_ehashfn() to ensure better cache locality and call inet6_ehashfn() only once per connect() system call. This brings an additional 229 % increase of performance for "neper/tcp_crr -6 -T 200 -F 30000" stress test, while greatly improving latency metrics. Before: latency_min=0.014131929 latency_max=17.895073144 latency_mean=0.505675853 latency_stddev=2.125164772 num_samples=307884 throughput=139866.80 After: latency_min=0.003041375 latency_max=7.056589232 latency_mean=0.141075048 latency_stddev=0.526900516 num_samples=312996 throughput=320677.21 ==================== Link: https://patch.msgid.link/20250305034550.879255-1-edumazet@google.com Signed-off-by:Jakub Kicinski <kuba@kernel.org>