From: Eric Dumazet <eric.dumazet@gmail.com>
To: Anton Blanchard <anton@samba.org>, David Miller <davem@davemloft.net>
Cc: netdev@vger.kernel.org, miltonm@bga.com
Subject: [PATCH] tcp: fix three tcp sysctls tuning
Date: Thu, 26 Aug 2010 07:15:53 +0200 [thread overview]
Message-ID: <1282799753.2681.714.camel@edumazet-laptop> (raw)
In-Reply-To: <20100826003834.GA17882@kryten>
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 litle 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>
---
net/ipv4/tcp.c | 24 +++++++-----------------
1 file changed, 7 insertions(+), 17 deletions(-)
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 197b9b7..e2add5f 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
next prev parent reply other threads:[~2010-08-26 5:15 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-08-25 7:16 Spurious "TCP: too many of orphaned sockets", unable to allocate sockets Anton Blanchard
2010-08-25 7:17 ` [PATCH] tcp: Fix sysctl_tcp_max_orphans when PAGE_SIZE != 4k Anton Blanchard
2010-08-25 7:39 ` Eric Dumazet
2010-08-25 7:59 ` David Miller
2010-08-25 17:50 ` Eric Dumazet
2010-08-25 23:57 ` David Miller
2010-08-26 0:38 ` Anton Blanchard
2010-08-26 3:53 ` David Miller
2010-08-26 6:36 ` Anton Blanchard
2010-08-26 4:45 ` Eric Dumazet
2010-08-26 5:15 ` Eric Dumazet [this message]
2010-08-26 6:02 ` [PATCH] tcp: fix three tcp sysctls tuning David Miller
2010-08-26 6:21 ` Eric Dumazet
2010-08-25 7:59 ` Spurious "TCP: too many of orphaned sockets", unable to allocate sockets David Miller
2010-08-25 8:20 ` David Miller
2010-08-25 8:47 ` Eric Dumazet
2010-08-25 9:28 ` David Miller
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1282799753.2681.714.camel@edumazet-laptop \
--to=eric.dumazet@gmail.com \
--cc=anton@samba.org \
--cc=davem@davemloft.net \
--cc=miltonm@bga.com \
--cc=netdev@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox