From 567e4b79731c352a17d73c483959f795d3593e03 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 6 Feb 2015 12:59:01 -0800 Subject: net: rfs: add hash collision detection Receive Flow Steering is a nice solution but suffers from hash collisions when a mix of connected and unconnected traffic is received on the host, when flow hash table is populated. Also, clearing flow in inet_release() makes RFS not very good for short lived flows, as many packets can follow close(). (FIN , ACK packets, ...) This patch extends the information stored into global hash table to not only include cpu number, but upper part of the hash value. I use a 32bit value, and dynamically split it in two parts. For host with less than 64 possible cpus, this gives 6 bits for the cpu number, and 26 (32-6) bits for the upper part of the hash. Since hash bucket selection use low order bits of the hash, we have a full hash match, if /proc/sys/net/core/rps_sock_flow_entries is big enough. If the hash found in flow table does not match, we fallback to RPS (if it is enabled for the rxqueue). This means that a packet for an non connected flow can avoid the IPI through a unrelated/victim CPU. This also means we no longer have to clear the table at socket close time, and this helps short lived flows performance. Signed-off-by: Eric Dumazet Acked-by: Tom Herbert Signed-off-by: David S. Miller --- include/net/sock.h | 24 +----------------------- 1 file changed, 1 insertion(+), 23 deletions(-) (limited to 'include/net') diff --git a/include/net/sock.h b/include/net/sock.h index d28b8fededd6..e13824570b0f 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -857,18 +857,6 @@ static inline void sock_rps_record_flow_hash(__u32 hash) #endif } -static inline void sock_rps_reset_flow_hash(__u32 hash) -{ -#ifdef CONFIG_RPS - struct rps_sock_flow_table *sock_flow_table; - - rcu_read_lock(); - sock_flow_table = rcu_dereference(rps_sock_flow_table); - rps_reset_sock_flow(sock_flow_table, hash); - rcu_read_unlock(); -#endif -} - static inline void sock_rps_record_flow(const struct sock *sk) { #ifdef CONFIG_RPS @@ -876,28 +864,18 @@ static inline void sock_rps_record_flow(const struct sock *sk) #endif } -static inline void sock_rps_reset_flow(const struct sock *sk) -{ -#ifdef CONFIG_RPS - sock_rps_reset_flow_hash(sk->sk_rxhash); -#endif -} - static inline void sock_rps_save_rxhash(struct sock *sk, const struct sk_buff *skb) { #ifdef CONFIG_RPS - if (unlikely(sk->sk_rxhash != skb->hash)) { - sock_rps_reset_flow(sk); + if (unlikely(sk->sk_rxhash != skb->hash)) sk->sk_rxhash = skb->hash; - } #endif } static inline void sock_rps_reset_rxhash(struct sock *sk) { #ifdef CONFIG_RPS - sock_rps_reset_flow(sk); sk->sk_rxhash = 0; #endif } -- cgit v1.2.3