o Backout rev. 1.125 of in_pcb.c. It appeared to behave extremely

  bad under high load. For example with 40k sockets and 25k tcptw
  entries, connect() syscall can run for seconds. Debugging showed
  that it iterates the cycle millions times and purges thousands of
  tcptw entries at a time.
  Besides practical unusability this change is architecturally
  wrong. First, in_pcblookup_local() is used in connect() and bind()
  syscalls. No stale entries purging shouldn't be done here. Second,
  it is a layering violation.
o Return back the tcptw purging cycle to tcp_timer_2msl_tw(),
  that was removed in rev. 1.78 by rwatson. The commit log of this
  revision tells nothing about the reason cycle was removed. Now
  we need this cycle, since major cleaner of stale tcptw structures
  is removed.
o Disable probably necessary, but now unused
  tcp_twrecycleable() function.

Reviewed by:	ru

1 files changed, 12 insertions, 7 deletions

diff --git a/sys/netinet/tcp_timer.c b/sys/netinet/tcp_timer.c
index 5c105b4..ca0bd36 100644
--- a/sys/netinet/tcp_timer.c
+++ b/sys/netinet/tcp_timer.c
@@ -288,15 +288,20 @@ tcp_timer_2msl_tw(int reuse)
 	int i;
 
 	INP_INFO_WLOCK_ASSERT(&tcbinfo);
-	for (i = 0; i < 2; i++) {
+	for (i = 0; i < TWLIST_NLISTS; i++) {
 		twl = tw_2msl_list[i];
 		tw_tail = &twl->tw_tail;
-		tw = LIST_FIRST(&twl->tw_list);
-		if (tw == tw_tail || (!reuse && tw->tw_time > ticks))
-			continue;
-		INP_LOCK(tw->tw_inpcb);
-		tcp_twclose(tw, reuse);
-		return (reuse ? tw : NULL);
+
+		for (;;) {
+			tw = LIST_FIRST(&twl->tw_list);
+			if (tw == tw_tail || (!reuse && tw->tw_time > ticks))
+				break;
+			INP_LOCK(tw->tw_inpcb);
+			tcp_twclose(tw, reuse);
+			if (reuse)
+				return (tw);
+		}
+
 	}
 	return (NULL);
 }