[INET]: speedup inet (tcp/dccp) lookups
Arnaldo and I agreed it could be applied now, because I have other
pending patches depending on this one (Thank you Arnaldo)
(The other important patch moves skc_refcnt in a separate cache line,
so that the SMP/NUMA performance doesnt suffer from cache line ping pongs)
1) First some performance data :
--------------------------------
tcp_v4_rcv() wastes a *lot* of time in __inet_lookup_established()
The most time critical code is :
sk_for_each(sk, node, &head->chain) {
if (INET_MATCH(sk, acookie, saddr, daddr, ports, dif))
goto hit; /* You sunk my battleship! */
}
The sk_for_each() does use prefetch() hints but only the begining of
"struct sock" is prefetched.
As INET_MATCH first comparison uses inet_sk(__sk)->daddr, wich is far
away from the begining of "struct sock", it has to bring into CPU
cache cold cache line. Each iteration has to use at least 2 cache
lines.
This can be problematic if some chains are very long.
2) The goal
-----------
The idea I had is to change things so that INET_MATCH() may return
FALSE in 99% of cases only using the data already in the CPU cache,
using one cache line per iteration.
3) Description of the patch
---------------------------
Adds a new 'unsigned int skc_hash' field in 'struct sock_common',
filling a 32 bits hole on 64 bits platform.
struct sock_common {
unsigned short skc_family;
volatile unsigned char skc_state;
unsigned char skc_reuse;
int skc_bound_dev_if;
struct hlist_node skc_node;
struct hlist_node skc_bind_node;
atomic_t skc_refcnt;
+ unsigned int skc_hash;
struct proto *skc_prot;
};
Store in this 32 bits field the full hash, not masked by (ehash_size -
1) Using this full hash as the first comparison done in INET_MATCH
permits us immediatly skip the element without touching a second cache
line in case of a miss.
Suppress the sk_hashent/tw_hashent fields since skc_hash (aliased to
sk_hash and tw_hash) already contains the slot number if we mask with
(ehash_size - 1)
File include/net/inet_hashtables.h
64 bits platforms :
#define INET_MATCH(__sk, __hash, __cookie, __saddr, __daddr, __ports, __dif)\
(((__sk)->sk_hash == (__hash))
((*((__u64 *)&(inet_sk(__sk)->daddr)))== (__cookie)) && \
((*((__u32 *)&(inet_sk(__sk)->dport))) == (__ports)) && \
(!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif))))
32bits platforms:
#define TCP_IPV4_MATCH(__sk, __hash, __cookie, __saddr, __daddr, __ports, __dif)\
(((__sk)->sk_hash == (__hash)) && \
(inet_sk(__sk)->daddr == (__saddr)) && \
(inet_sk(__sk)->rcv_saddr == (__daddr)) && \
(!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif))))
- Adds a prefetch(head->chain.first) in
__inet_lookup_established()/__tcp_v4_check_established() and
__inet6_lookup_established()/__tcp_v6_check_established() and
__dccp_v4_check_established() to bring into cache the first element of the
list, before the {read|write}_lock(&head->lock);
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Acked-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 40fe6af..ae088d1 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -62,27 +62,27 @@
const int dif = sk->sk_bound_dev_if;
INET_ADDR_COOKIE(acookie, saddr, daddr)
const __u32 ports = INET_COMBINED_PORTS(inet->dport, lport);
- const int hash = inet_ehashfn(daddr, lport, saddr, inet->dport,
- dccp_hashinfo.ehash_size);
- struct inet_ehash_bucket *head = &dccp_hashinfo.ehash[hash];
+ unsigned int hash = inet_ehashfn(daddr, lport, saddr, inet->dport);
+ struct inet_ehash_bucket *head = inet_ehash_bucket(&dccp_hashinfo, hash);
const struct sock *sk2;
const struct hlist_node *node;
struct inet_timewait_sock *tw;
+ prefetch(head->chain.first);
write_lock(&head->lock);
/* Check TIME-WAIT sockets first. */
sk_for_each(sk2, node, &(head + dccp_hashinfo.ehash_size)->chain) {
tw = inet_twsk(sk2);
- if (INET_TW_MATCH(sk2, acookie, saddr, daddr, ports, dif))
+ if (INET_TW_MATCH(sk2, hash, acookie, saddr, daddr, ports, dif))
goto not_unique;
}
tw = NULL;
/* And established part... */
sk_for_each(sk2, node, &head->chain) {
- if (INET_MATCH(sk2, acookie, saddr, daddr, ports, dif))
+ if (INET_MATCH(sk2, hash, acookie, saddr, daddr, ports, dif))
goto not_unique;
}
@@ -90,7 +90,7 @@
* in hash table socket with a funny identity. */
inet->num = lport;
inet->sport = htons(lport);
- sk->sk_hashent = hash;
+ sk->sk_hash = hash;
BUG_TRAP(sk_unhashed(sk));
__sk_add_node(sk, &head->chain);
sock_prot_inc_use(sk->sk_prot);