diff options
author | Eric Dumazet <edumazet@google.com> | 2015-02-06 23:59:01 +0300 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2015-02-09 03:53:57 +0300 |
commit | 567e4b79731c352a17d73c483959f795d3593e03 (patch) | |
tree | 4af65c205a8b65cfc5fd7b42e7b8750728230616 /include/net/sock.h | |
parent | 096a4cfa5807aa89c78ce12309c0b1c10cf88184 (diff) | |
download | linux-567e4b79731c352a17d73c483959f795d3593e03.tar.xz |
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 <edumazet@google.com>
Acked-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'include/net/sock.h')
-rw-r--r-- | include/net/sock.h | 24 |
1 files changed, 1 insertions, 23 deletions
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 } |