tcp: change tcp_adv_win_scale and tcp_rmem[2]

[ Upstream commit b49960a05e32121d29316cfdf653894b88ac9190 ]

tcp_adv_win_scale default value is 2, meaning we expect a good citizen
skb to have skb->len / skb->truesize ratio of 75% (3/4)

In 2.6 kernels we (mis)accounted for typical MSS=1460 frame :
1536 + 64 + 256 = 1856 'estimated truesize', and 1856 * 3/4 = 1392.
So these skbs were considered as not bloated.

With recent truesize fixes, a typical MSS=1460 frame truesize is now the
more precise :
2048 + 256 = 2304. But 2304 * 3/4 = 1728.
So these skb are not good citizen anymore, because 1460 < 1728

(GRO can escape this problem because it build skbs with a too low
truesize.)

This also means tcp advertises a too optimistic window for a given
allocated rcvspace : When receiving frames, sk_rmem_alloc can hit
sk_rcvbuf limit and we call tcp_prune_queue()/tcp_collapse() too often,
especially when application is slow to drain its receive queue or in
case of losses (netperf is fast, scp is slow). This is a major latency
source.

We should adjust the len/truesize ratio to 50% instead of 75%

This patch :

1) changes tcp_adv_win_scale default to 1 instead of 2

2) increase tcp_rmem[2] limit from 4MB to 6MB to take into account
better truesize tracking and to allow autotuning tcp receive window to
reach same value than before. Note that same amount of kernel memory is
consumed compared to 2.6 kernels.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Tom Herbert <therbert@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 589f2da5d5454dd96f828c01168aecb84770473f..a4399f5fb23a258dcc4cbef030d322fc19040a17 100644 (file)
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -137,7 +137,7 @@ tcp_adv_win_scale - INTEGER
        (if tcp_adv_win_scale > 0) or bytes-bytes/2^(-tcp_adv_win_scale),
        if it is <= 0.
        Possible values are [-31, 31], inclusive.
-       Default: 2
+       Default: 1
 
 tcp_allowed_congestion_control - STRING
        Show/set the congestion control choices available to non-privileged
@@ -397,7 +397,7 @@ tcp_rmem - vector of 3 INTEGERs: min, default, max
        net.core.rmem_max.  Calling setsockopt() with SO_RCVBUF disables
        automatic tuning of that socket's receive buffer size, in which
        case this value is ignored.
-       Default: between 87380B and 4MB, depending on RAM size.
+       Default: between 87380B and 6MB, depending on RAM size.
 
 tcp_sack - BOOLEAN
        Enable select acknowledgments (SACKS).

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 7904db453578c21a9bff24621ae8b3d62e0e7393..8f826b1aab4b5ae84dce253e28422a2a0fe76e57 100644 (file)
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3216,7 +3216,7 @@ void __init tcp_init(void)
 {
        struct sk_buff *skb = NULL;
        unsigned long limit;
-       int i, max_share, cnt;
+       int i, max_rshare, max_wshare, cnt;
        unsigned long jiffy = jiffies;
 
        BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > sizeof(skb->cb));
@@ -3280,15 +3280,16 @@ void __init tcp_init(void)
 
        /* Set per-socket limits to no more than 1/128 the pressure threshold */
        limit = ((unsigned long)sysctl_tcp_mem[1]) << (PAGE_SHIFT - 7);
-       max_share = min(4UL*1024*1024, limit);
+       max_wshare = min(4UL*1024*1024, limit);
+       max_rshare = min(6UL*1024*1024, limit);
 
        sysctl_tcp_wmem[0] = SK_MEM_QUANTUM;
        sysctl_tcp_wmem[1] = 16*1024;
-       sysctl_tcp_wmem[2] = max(64*1024, max_share);
+       sysctl_tcp_wmem[2] = max(64*1024, max_wshare);
 
        sysctl_tcp_rmem[0] = SK_MEM_QUANTUM;
        sysctl_tcp_rmem[1] = 87380;
-       sysctl_tcp_rmem[2] = max(87380, max_share);
+       sysctl_tcp_rmem[2] = max(87380, max_rshare);
 
        printk(KERN_INFO "TCP: Hash tables configured "
               "(established %u bind %u)\n",

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index db07c9ed8b8ba4651967d8ff2e46359e732193ad..97269278355a6d1f8184c9b45b3a184547fc113b 100644 (file)
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -83,7 +83,7 @@ int sysctl_tcp_ecn __read_mostly = 2;
 EXPORT_SYMBOL(sysctl_tcp_ecn);
 int sysctl_tcp_dsack __read_mostly = 1;
 int sysctl_tcp_app_win __read_mostly = 31;
-int sysctl_tcp_adv_win_scale __read_mostly = 2;
+int sysctl_tcp_adv_win_scale __read_mostly = 1;
 EXPORT_SYMBOL(sysctl_tcp_adv_win_scale);
 
 int sysctl_tcp_stdurg __read_mostly;