Netdev List
 help / color / mirror / Atom feed
From: Eric Dumazet <edumazet@google.com>
To: "David S. Miller" <davem@davemloft.net>
Cc: netdev <netdev@vger.kernel.org>, Jason Baron <jbaron@akamai.com>,
	Neal Cardwell <ncardwell@google.com>,
	Yuchung Cheng <ycheng@google.com>,
	Eric Dumazet <eric.dumazet@gmail.com>,
	Eric Dumazet <edumazet@google.com>
Subject: [PATCH net-next 6/6] tcp: halves tcp_mem[] limits
Date: Fri, 15 May 2015 07:53:58 -0700	[thread overview]
Message-ID: <1431701638-24451-7-git-send-email-edumazet@google.com> (raw)
In-Reply-To: <1431701638-24451-1-git-send-email-edumazet@google.com>

Allowing tcp to use ~19% of physical memory is way too much,
and allowed bugs to be hidden. Add to this that some drivers use a full
page per incoming frame, so real cost can be twice the advertized one.

Reduce tcp_mem by 50 % as a first step to sanity.

tcp_mem[0,1,2] defaults are now 4.68%, 6.25%, 9.37% of physical memory.

Signed-off-by: Eric Dumazet <edumazet@google.com>
---
 net/ipv4/tcp.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 9eabfd3e0925..c724195e5862 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3068,11 +3068,12 @@ __setup("thash_entries=", set_thash_entries);
 
 static void __init tcp_init_mem(void)
 {
-	unsigned long limit = nr_free_buffer_pages() / 8;
+	unsigned long limit = nr_free_buffer_pages() / 16;
+
 	limit = max(limit, 128UL);
-	sysctl_tcp_mem[0] = limit / 4 * 3;
-	sysctl_tcp_mem[1] = limit;
-	sysctl_tcp_mem[2] = sysctl_tcp_mem[0] * 2;
+	sysctl_tcp_mem[0] = limit / 4 * 3;		/* 4.68 % */
+	sysctl_tcp_mem[1] = limit;			/* 6.25 % */
+	sysctl_tcp_mem[2] = sysctl_tcp_mem[0] * 2;	/* 9.37 % */
 }
 
 void __init tcp_init(void)
-- 
2.2.0.rc0.207.ga3a616c

      parent reply	other threads:[~2015-05-15 15:01 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-05-15 14:53 [PATCH net-next 0/6] tcp: better handling of memory pressure Eric Dumazet
2015-05-15 14:53 ` [PATCH net-next 1/6] net: fix sk_mem_reclaim_partial() Eric Dumazet
2015-05-15 14:53 ` [PATCH net-next 2/6] tcp: rename sk_forced_wmem_schedule() to sk_forced_mem_schedule() Eric Dumazet
2015-05-15 14:53 ` [PATCH net-next 3/6] tcp: introduce tcp_under_memory_pressure() Eric Dumazet
2015-05-15 14:53 ` [PATCH net-next 4/6] tcp: fix behavior for epoll edge trigger Eric Dumazet
2015-05-15 14:53 ` [PATCH net-next 5/6] tcp: allow one skb to be received per socket under memory pressure Eric Dumazet
2015-05-15 18:20   ` Jason Baron
2015-05-15 18:22     ` Eric Dumazet
2015-05-15 14:53 ` Eric Dumazet [this message]

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=1431701638-24451-7-git-send-email-edumazet@google.com \
    --to=edumazet@google.com \
    --cc=davem@davemloft.net \
    --cc=eric.dumazet@gmail.com \
    --cc=jbaron@akamai.com \
    --cc=ncardwell@google.com \
    --cc=netdev@vger.kernel.org \
    --cc=ycheng@google.com \
    /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