tcp/dccp: get rid of central timewait timer

Using a timer wheel for timewait sockets was nice ~15 years ago when
memory was expensive and machines had a single processor.

This does not scale, code is ugly and source of huge latencies
(Typically 30 ms have been seen, cpus spinning on death_lock spinlock.)

We can afford to use an extra 64 bytes per timewait sock and spread
timewait load to all cpus to have better behavior.

Tested:

On following test, /proc/sys/net/ipv4/tcp_tw_recycle is set to 1
on the target (lpaa24)

Before patch :

lpaa23:~# ./super_netperf 200 -H lpaa24 -t TCP_CC -l 60 -- -p0,0
419594

lpaa23:~# ./super_netperf 200 -H lpaa24 -t TCP_CC -l 60 -- -p0,0
437171

While test is running, we can observe 25 or even 33 ms latencies.

lpaa24:~# ping -c 1000 -i 0.02 -qn lpaa23
...
1000 packets transmitted, 1000 received, 0% packet loss, time 20601ms
rtt min/avg/max/mdev = 0.020/0.217/25.771/1.535 ms, pipe 2

lpaa24:~# ping -c 1000 -i 0.02 -qn lpaa23
...
1000 packets transmitted, 1000 received, 0% packet loss, time 20702ms
rtt min/avg/max/mdev = 0.019/0.183/33.761/1.441 ms, pipe 2

After patch :

About 90% increase of throughput :

lpaa23:~# ./super_netperf 200 -H lpaa24 -t TCP_CC -l 60 -- -p0,0
810442

lpaa23:~# ./super_netperf 200 -H lpaa24 -t TCP_CC -l 60 -- -p0,0
800992

And latencies are kept to minimal values during this load, even
if network utilization is 90% higher :

lpaa24:~# ping -c 1000 -i 0.02 -qn lpaa23
...
1000 packets transmitted, 1000 received, 0% packet loss, time 19991ms
rtt min/avg/max/mdev = 0.023/0.064/0.360/0.042 ms

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 3 insertions, 16 deletions

diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c
index 332f7d6d9942..5f566663e47f 100644
--- a/net/dccp/minisocks.c
+++ b/net/dccp/minisocks.c
@@ -27,28 +27,16 @@
 
 struct inet_timewait_death_row dccp_death_row = {
         .sysctl_max_tw_buckets = NR_FILE * 2,
-        .period         = DCCP_TIMEWAIT_LEN / INET_TWDR_TWKILL_SLOTS,
-        .death_lock     = __SPIN_LOCK_UNLOCKED(dccp_death_row.death_lock),
         .hashinfo       = &dccp_hashinfo,
-        .tw_timer       = TIMER_INITIALIZER(inet_twdr_hangman, 0,
-                                            (unsigned long)&dccp_death_row),
-        .twkill_work    = __WORK_INITIALIZER(dccp_death_row.twkill_work,
-                                             inet_twdr_twkill_work),
-/* Short-time timewait calendar */
-
-        .twcal_hand     = -1,
-        .twcal_timer    = TIMER_INITIALIZER(inet_twdr_twcal_tick, 0,
-                                            (unsigned long)&dccp_death_row),
 };
 
 EXPORT_SYMBOL_GPL(dccp_death_row);
 
 void dccp_time_wait(struct sock *sk, int state, int timeo)
 {
-        struct inet_timewait_sock *tw = NULL;
+        struct inet_timewait_sock *tw;
 
-        if (dccp_death_row.tw_count < dccp_death_row.sysctl_max_tw_buckets)
-                tw = inet_twsk_alloc(sk, state);
+        tw = inet_twsk_alloc(sk, &dccp_death_row, state);
 
         if (tw != NULL) {
                 const struct inet_connection_sock *icsk = inet_csk(sk);
@@ -71,8 +59,7 @@ void dccp_time_wait(struct sock *sk, int state, int timeo)
                 if (state == DCCP_TIME_WAIT)
                         timeo = DCCP_TIMEWAIT_LEN;
 
-                inet_twsk_schedule(tw, &dccp_death_row, timeo,
-                                   DCCP_TIMEWAIT_LEN);
+                inet_twsk_schedule(tw, timeo);
                 inet_twsk_put(tw);
         } else {
                 /* Sorry, if we're out of memory, just CLOSE this