summaryrefslogtreecommitdiffstats
path: root/net
diff options
context:
space:
mode:
authorEric Dumazet <edumazet@google.com>2013-07-22 20:27:07 -0700
committerDavid S. Miller <davem@davemloft.net>2013-07-24 17:54:48 -0700
commitc9bee3b7fdecb0c1d070c7b54113b3bdfb9a3d36 (patch)
tree6bcaa39bbd312c070bf31b703df4d6bb2a44fea9 /net
parent64dc61306ce7da370833289739e2f52dfc6b37ba (diff)
downloadop-kernel-dev-c9bee3b7fdecb0c1d070c7b54113b3bdfb9a3d36.zip
op-kernel-dev-c9bee3b7fdecb0c1d070c7b54113b3bdfb9a3d36.tar.gz
tcp: TCP_NOTSENT_LOWAT socket option
Idea of this patch is to add optional limitation of number of unsent bytes in TCP sockets, to reduce usage of kernel memory. TCP receiver might announce a big window, and TCP sender autotuning might allow a large amount of bytes in write queue, but this has little performance impact if a large part of this buffering is wasted : Write queue needs to be large only to deal with large BDP, not necessarily to cope with scheduling delays (incoming ACKS make room for the application to queue more bytes) For most workloads, using a value of 128 KB or less is OK to give applications enough time to react to POLLOUT events in time (or being awaken in a blocking sendmsg()) This patch adds two ways to set the limit : 1) Per socket option TCP_NOTSENT_LOWAT 2) A sysctl (/proc/sys/net/ipv4/tcp_notsent_lowat) for sockets not using TCP_NOTSENT_LOWAT socket option (or setting a zero value) Default value being UINT_MAX (0xFFFFFFFF), meaning this has no effect. This changes poll()/select()/epoll() to report POLLOUT only if number of unsent bytes is below tp->nosent_lowat Note this might increase number of sendmsg()/sendfile() calls when using non blocking sockets, and increase number of context switches for blocking sockets. Note this is not related to SO_SNDLOWAT (as SO_SNDLOWAT is defined as : Specify the minimum number of bytes in the buffer until the socket layer will pass the data to the protocol) Tested: netperf sessions, and watching /proc/net/protocols "memory" column for TCP With 200 concurrent netperf -t TCP_STREAM sessions, amount of kernel memory used by TCP buffers shrinks by ~55 % (20567 pages instead of 45458) lpq83:~# echo -1 >/proc/sys/net/ipv4/tcp_notsent_lowat lpq83:~# (super_netperf 200 -t TCP_STREAM -H remote -l 90 &); sleep 60 ; grep TCP /proc/net/protocols TCPv6 1880 2 45458 no 208 yes ipv6 y y y y y y y y y y y y y n y y y y y TCP 1696 508 45458 no 208 yes kernel y y y y y y y y y y y y y n y y y y y lpq83:~# echo 131072 >/proc/sys/net/ipv4/tcp_notsent_lowat lpq83:~# (super_netperf 200 -t TCP_STREAM -H remote -l 90 &); sleep 60 ; grep TCP /proc/net/protocols TCPv6 1880 2 20567 no 208 yes ipv6 y y y y y y y y y y y y y n y y y y y TCP 1696 508 20567 no 208 yes kernel y y y y y y y y y y y y y n y y y y y Using 128KB has no bad effect on the throughput or cpu usage of a single flow, although there is an increase of context switches. A bonus is that we hold socket lock for a shorter amount of time and should improve latencies of ACK processing. lpq83:~# echo -1 >/proc/sys/net/ipv4/tcp_notsent_lowat lpq83:~# perf stat -e context-switches ./netperf -H 7.7.7.84 -t omni -l 20 -c -i10,3 OMNI Send TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 7.7.7.84 () port 0 AF_INET : +/-2.500% @ 99% conf. Local Remote Local Elapsed Throughput Throughput Local Local Remote Remote Local Remote Service Send Socket Recv Socket Send Time Units CPU CPU CPU CPU Service Service Demand Size Size Size (sec) Util Util Util Util Demand Demand Units Final Final % Method % Method 1651584 6291456 16384 20.00 17447.90 10^6bits/s 3.13 S -1.00 U 0.353 -1.000 usec/KB Performance counter stats for './netperf -H 7.7.7.84 -t omni -l 20 -c -i10,3': 412,514 context-switches 200.034645535 seconds time elapsed lpq83:~# echo 131072 >/proc/sys/net/ipv4/tcp_notsent_lowat lpq83:~# perf stat -e context-switches ./netperf -H 7.7.7.84 -t omni -l 20 -c -i10,3 OMNI Send TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 7.7.7.84 () port 0 AF_INET : +/-2.500% @ 99% conf. Local Remote Local Elapsed Throughput Throughput Local Local Remote Remote Local Remote Service Send Socket Recv Socket Send Time Units CPU CPU CPU CPU Service Service Demand Size Size Size (sec) Util Util Util Util Demand Demand Units Final Final % Method % Method 1593240 6291456 16384 20.00 17321.16 10^6bits/s 3.35 S -1.00 U 0.381 -1.000 usec/KB Performance counter stats for './netperf -H 7.7.7.84 -t omni -l 20 -c -i10,3': 2,675,818 context-switches 200.029651391 seconds time elapsed Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Neal Cardwell <ncardwell@google.com> Cc: Yuchung Cheng <ycheng@google.com> Acked-By: Yuchung Cheng <ycheng@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net')
-rw-r--r--net/ipv4/sysctl_net_ipv4.c7
-rw-r--r--net/ipv4/tcp.c7
-rw-r--r--net/ipv4/tcp_ipv4.c1
-rw-r--r--net/ipv4/tcp_output.c3
-rw-r--r--net/ipv6/tcp_ipv6.c1
5 files changed, 19 insertions, 0 deletions
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index b2c123c..69ed203 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -555,6 +555,13 @@ static struct ctl_table ipv4_table[] = {
.extra1 = &one,
},
{
+ .procname = "tcp_notsent_lowat",
+ .data = &sysctl_tcp_notsent_lowat,
+ .maxlen = sizeof(sysctl_tcp_notsent_lowat),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ {
.procname = "tcp_rmem",
.data = &sysctl_tcp_rmem,
.maxlen = sizeof(sysctl_tcp_rmem),
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 5eca906..c27e813 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2631,6 +2631,10 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
else
tp->tsoffset = val - tcp_time_stamp;
break;
+ case TCP_NOTSENT_LOWAT:
+ tp->notsent_lowat = val;
+ sk->sk_write_space(sk);
+ break;
default:
err = -ENOPROTOOPT;
break;
@@ -2847,6 +2851,9 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
case TCP_TIMESTAMP:
val = tcp_time_stamp + tp->tsoffset;
break;
+ case TCP_NOTSENT_LOWAT:
+ val = tp->notsent_lowat;
+ break;
default:
return -ENOPROTOOPT;
}
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 2e3f129..2a5d5c4 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2800,6 +2800,7 @@ struct proto tcp_prot = {
.unhash = inet_unhash,
.get_port = inet_csk_get_port,
.enter_memory_pressure = tcp_enter_memory_pressure,
+ .stream_memory_free = tcp_stream_memory_free,
.sockets_allocated = &tcp_sockets_allocated,
.orphan_count = &tcp_orphan_count,
.memory_allocated = &tcp_memory_allocated,
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 92fde8d..884efff 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -65,6 +65,9 @@ int sysctl_tcp_base_mss __read_mostly = TCP_BASE_MSS;
/* By default, RFC2861 behavior. */
int sysctl_tcp_slow_start_after_idle __read_mostly = 1;
+unsigned int sysctl_tcp_notsent_lowat __read_mostly = UINT_MAX;
+EXPORT_SYMBOL(sysctl_tcp_notsent_lowat);
+
static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
int push_one, gfp_t gfp);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 80fe69e..b792e87 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1924,6 +1924,7 @@ struct proto tcpv6_prot = {
.unhash = inet_unhash,
.get_port = inet_csk_get_port,
.enter_memory_pressure = tcp_enter_memory_pressure,
+ .stream_memory_free = tcp_stream_memory_free,
.sockets_allocated = &tcp_sockets_allocated,
.memory_allocated = &tcp_memory_allocated,
.memory_pressure = &tcp_memory_pressure,
OpenPOWER on IntegriCloud