Minki/linux
1
0
Fork 1
mirror of https://github.com/torvalds/linux.git synced 2024-11-10 14:11:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

tcp: TCP_NOTSENT_LOWAT socket option

Browse Source 
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>
This commit is contained in:
Eric Dumazet 2013-07-22 20:27:07 -07:00 committed by David S. Miller
parent 64dc61306c
commit c9bee3b7fd
10 changed files with 61 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
Documentation/networking/ip-sysctl.txt
View File

@ -516,6 +516,19 @@ tcp_wmem - vector of 3 INTEGERs: min, default, max
this value is ignored.
Default: between 64K and 4MB, depending on RAM size.
tcp_notsent_lowat - UNSIGNED INTEGER
A TCP socket can control the amount of unsent bytes in its write queue,
thanks to TCP_NOTSENT_LOWAT socket option. poll()/select()/epoll()
reports POLLOUT events if the amount of unsent bytes is below a per
socket value, and if the write queue is not full. sendmsg() will
also not add new buffers if the limit is hit.
This global variable controls the amount of unsent data for
sockets not using TCP_NOTSENT_LOWAT. For these sockets, a change
to the global variable has immediate effect.
Default: UINT_MAX (0xFFFFFFFF)
tcp_workaround_signed_windows - BOOLEAN
If set, assume no receipt of a window scaling option means the
remote TCP is broken and treats the window as a signed quantity.

1
include/linux/tcp.h
View File

@ -238,6 +238,7 @@ struct tcp_sock {
u32 rcv_wnd; /* Current receiver window */
u32 write_seq; /* Tail(+1) of data held in tcp send buffer */
u32 notsent_lowat; /* TCP_NOTSENT_LOWAT */
u32 pushed_seq; /* Last pushed seq, required to talk to windows */
u32 lost_out; /* Lost packets */
u32 sacked_out; /* SACK'd packets */

19
include/net/sock.h
View File

@ -746,11 +746,6 @@ static inline int sk_stream_wspace(const struct sock *sk)
extern void sk_stream_write_space(struct sock *sk);
static inline bool sk_stream_memory_free(const struct sock *sk)
{
return sk->sk_wmem_queued < sk->sk_sndbuf;
}
/* OOB backlog add */
static inline void __sk_add_backlog(struct sock *sk, struct sk_buff *skb)
{
@ -950,6 +945,7 @@ struct proto {
unsigned int inuse_idx;
#endif
bool (*stream_memory_free)(const struct sock *sk);
/* Memory pressure */
void (*enter_memory_pressure)(struct sock *sk);
atomic_long_t *memory_allocated; /* Current allocated memory. */
@ -1088,11 +1084,22 @@ static inline struct cg_proto *parent_cg_proto(struct proto *proto,
}
#endif
static inline bool sk_stream_memory_free(const struct sock *sk)
{
if (sk->sk_wmem_queued >= sk->sk_sndbuf)
return false;
return sk->sk_prot->stream_memory_free ?
sk->sk_prot->stream_memory_free(sk) : true;
}
static inline bool sk_stream_is_writeable(const struct sock *sk)
{
return sk_stream_wspace(sk) >= sk_stream_min_wspace(sk);
return sk_stream_wspace(sk) >= sk_stream_min_wspace(sk) &&
sk_stream_memory_free(sk);
}
static inline bool sk_has_memory_pressure(const struct sock *sk)
{
return sk->sk_prot->memory_pressure != NULL;

14
include/net/tcp.h
View File

@ -284,6 +284,7 @@ extern int sysctl_tcp_thin_dupack;
extern int sysctl_tcp_early_retrans;
extern int sysctl_tcp_limit_output_bytes;
extern int sysctl_tcp_challenge_ack_limit;
extern unsigned int sysctl_tcp_notsent_lowat;
extern atomic_long_t tcp_memory_allocated;
extern struct percpu_counter tcp_sockets_allocated;
@ -1539,6 +1540,19 @@ extern int tcp_gro_complete(struct sk_buff *skb);
extern void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr,
__be32 daddr);
static inline u32 tcp_notsent_lowat(const struct tcp_sock *tp)
{
return tp->notsent_lowat ?: sysctl_tcp_notsent_lowat;
}
static inline bool tcp_stream_memory_free(const struct sock *sk)
{
const struct tcp_sock *tp = tcp_sk(sk);
u32 notsent_bytes = tp->write_seq - tp->snd_nxt;
return notsent_bytes < tcp_notsent_lowat(tp);
}
#ifdef CONFIG_PROC_FS
extern int tcp4_proc_init(void);
extern void tcp4_proc_exit(void);

1
include/uapi/linux/tcp.h
View File

@ -111,6 +111,7 @@ enum {
#define TCP_REPAIR_OPTIONS 22
#define TCP_FASTOPEN 23 /* Enable FastOpen on listeners */
#define TCP_TIMESTAMP 24
#define TCP_NOTSENT_LOWAT 25 /* limit number of unsent bytes in write queue */
struct tcp_repair_opt {
__u32 opt_code;

7
net/ipv4/sysctl_net_ipv4.c
View File

@ -554,6 +554,13 @@ static struct ctl_table ipv4_table[] = {
.proc_handler = proc_dointvec_minmax,
.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,

7
net/ipv4/tcp.c
View File

@ -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;
}

1
net/ipv4/tcp_ipv4.c
View File

@ -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,

3
net/ipv4/tcp_output.c
View File

@ -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);

1
net/ipv6/tcp_ipv6.c
View File

@ -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,