aboutsummaryrefslogtreecommitdiffstats
path: root/net
diff options
context:
space:
mode:
authorEric Dumazet <eric.dumazet@gmail.com>2010-08-25 23:02:17 -0700
committerDavid S. Miller <davem@davemloft.net>2010-08-25 23:02:17 -0700
commitc5ed63d66f24fd4f7089b5a6e087b0ce7202aa8e (patch)
tree140df25fef28c94f9ec1e5c29b4a8d0876da2fe8 /net
parentad1af0fedba14f82b240a03fe20eb9b2fdbd0357 (diff)
downloadmrst-s0i3-test-c5ed63d66f24fd4f7089b5a6e087b0ce7202aa8e.tar.gz
mrst-s0i3-test-c5ed63d66f24fd4f7089b5a6e087b0ce7202aa8e.tar.xz
mrst-s0i3-test-c5ed63d66f24fd4f7089b5a6e087b0ce7202aa8e.zip
tcp: fix three tcp sysctls tuning
As discovered by Anton Blanchard, current code to autotune tcp_death_row.sysctl_max_tw_buckets, sysctl_tcp_max_orphans and sysctl_max_syn_backlog makes little sense. The bigger a page is, the less tcp_max_orphans is : 4096 on a 512GB machine in Anton's case. (tcp_hashinfo.bhash_size * sizeof(struct inet_bind_hashbucket)) is much bigger if spinlock debugging is on. Its wrong to select bigger limits in this case (where kernel structures are also bigger) bhash_size max is 65536, and we get this value even for small machines. A better ground is to use size of ehash table, this also makes code shorter and more obvious. Based on a patch from Anton, and another from David. Reported-and-tested-by: Anton Blanchard <anton@samba.org> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net')
-rw-r--r--net/ipv4/tcp.c24
1 files changed, 7 insertions, 17 deletions
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 197b9b77fa3..e2add5ff9cb 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3209,7 +3209,7 @@ void __init tcp_init(void)
{
struct sk_buff *skb = NULL;
unsigned long nr_pages, limit;
- int order, i, max_share;
+ int i, max_share, cnt;
unsigned long jiffy = jiffies;
BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > sizeof(skb->cb));
@@ -3258,22 +3258,12 @@ void __init tcp_init(void)
INIT_HLIST_HEAD(&tcp_hashinfo.bhash[i].chain);
}
- /* Try to be a bit smarter and adjust defaults depending
- * on available memory.
- */
- for (order = 0; ((1 << order) << PAGE_SHIFT) <
- (tcp_hashinfo.bhash_size * sizeof(struct inet_bind_hashbucket));
- order++)
- ;
- if (order >= 4) {
- tcp_death_row.sysctl_max_tw_buckets = 180000;
- sysctl_tcp_max_orphans = 4096 << (order - 4);
- sysctl_max_syn_backlog = 1024;
- } else if (order < 3) {
- tcp_death_row.sysctl_max_tw_buckets >>= (3 - order);
- sysctl_tcp_max_orphans >>= (3 - order);
- sysctl_max_syn_backlog = 128;
- }
+
+ cnt = tcp_hashinfo.ehash_mask + 1;
+
+ tcp_death_row.sysctl_max_tw_buckets = cnt / 2;
+ sysctl_tcp_max_orphans = cnt / 2;
+ sysctl_max_syn_backlog = max(128, cnt / 256);
/* Set the pressure threshold to be a fraction of global memory that
* is up to 1/2 at 256 MB, decreasing toward zero with the amount of