From d26b3a7c4b3b26319f18bb645de93eba8f4bdcd5 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 31 Jul 2012 05:45:30 +0000 Subject: ipv4: percpu nh_rth_output cache Input path is mostly run under RCU and doesnt touch dst refcnt But output path on forwarding or UDP workloads hits badly dst refcount, and we have lot of false sharing, for example in ipv4_mtu() when reading rt->rt_pmtu Using a percpu cache for nh_rth_output gives a nice performance increase at a small cost. 24 udpflood test on my 24 cpu machine (dummy0 output device) (each process sends 1.000.000 udp frames, 24 processes are started) before : 5.24 s after : 2.06 s For reference, time on linux-3.5 : 6.60 s Signed-off-by: Eric Dumazet Tested-by: Alexander Duyck Signed-off-by: David S. Miller --- include/net/ip_fib.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/net/ip_fib.h') diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index e521a03515b1..e331746029b4 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -21,6 +21,7 @@ #include #include #include +#include struct fib_config { u8 fc_dst_len; @@ -81,7 +82,7 @@ struct fib_nh { __be32 nh_gw; __be32 nh_saddr; int nh_saddr_genid; - struct rtable __rcu *nh_rth_output; + struct rtable __rcu * __percpu *nh_pcpu_rth_output; struct rtable __rcu *nh_rth_input; struct fnhe_hash_bucket *nh_exceptions; }; -- cgit v1.2.3