aboutsummaryrefslogtreecommitdiffstats
path: root/net/ipv4/tcp_ipv4.c
diff options
context:
space:
mode:
authorEric Dumazet <dada1@cosmosbay.com>2007-02-08 17:16:46 -0500
committerDavid S. Miller <davem@davemloft.net>2007-02-08 17:16:46 -0500
commitdbca9b2750e3b1ee6f56a616160ccfc12e8b161f (patch)
treebf84c0acb5495fc95bc616d32b8af946f2e3bca9 /net/ipv4/tcp_ipv4.c
parenteac3731bd04c7131478722a3c148b78774553116 (diff)
[NET]: change layout of ehash table
ehash table layout is currently this one : First half of this table is used by sockets not in TIME_WAIT state Second half of it is used by sockets in TIME_WAIT state. This is non optimal because of for a given hash or socket, the two chain heads are located in separate cache lines. Moreover the locks of the second half are never used. If instead of this halving, we use two list heads in inet_ehash_bucket instead of only one, we probably can avoid one cache miss, and reduce ram usage, particularly if sizeof(rwlock_t) is big (various CONFIG_DEBUG_SPINLOCK, CONFIG_DEBUG_LOCK_ALLOC settings). So we still halves the table but we keep together related chains to speedup lookups and socket state change. In this patch I did not try to align struct inet_ehash_bucket, but a future patch could try to make this structure have a convenient size (a power of two or a multiple of L1_CACHE_SIZE). I guess rwlock will just vanish as soon as RCU is plugged into ehash :) , so maybe we dont need to scratch our heads to align the bucket... Note : In case struct inet_ehash_bucket is not a power of two, we could probably change alloc_large_system_hash() (in case it use __get_free_pages()) to free the unused space. It currently allocates a big zone, but the last quarter of it could be freed. Again, this should be a temporary 'problem'. Patch tested on ipv4 tcp only, but should be OK for IPV6 and DCCP. Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/ipv4/tcp_ipv4.c')
-rw-r--r--net/ipv4/tcp_ipv4.c4
1 files changed, 2 insertions, 2 deletions
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 383e4b52dbde..f51d6404c61c 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2051,7 +2051,7 @@ static void *established_get_first(struct seq_file *seq)
2051 } 2051 }
2052 st->state = TCP_SEQ_STATE_TIME_WAIT; 2052 st->state = TCP_SEQ_STATE_TIME_WAIT;
2053 inet_twsk_for_each(tw, node, 2053 inet_twsk_for_each(tw, node,
2054 &tcp_hashinfo.ehash[st->bucket + tcp_hashinfo.ehash_size].chain) { 2054 &tcp_hashinfo.ehash[st->bucket].twchain) {
2055 if (tw->tw_family != st->family) { 2055 if (tw->tw_family != st->family) {
2056 continue; 2056 continue;
2057 } 2057 }
@@ -2107,7 +2107,7 @@ get_tw:
2107 } 2107 }
2108 2108
2109 st->state = TCP_SEQ_STATE_TIME_WAIT; 2109 st->state = TCP_SEQ_STATE_TIME_WAIT;
2110 tw = tw_head(&tcp_hashinfo.ehash[st->bucket + tcp_hashinfo.ehash_size].chain); 2110 tw = tw_head(&tcp_hashinfo.ehash[st->bucket].twchain);
2111 goto get_tw; 2111 goto get_tw;
2112found: 2112found:
2113 cur = sk; 2113 cur = sk;