Improved connection establishment performance by doing local port lookups via

a hashed port list. In the new scheme, in_pcblookup() goes away and is
replaced by a new routine, in_pcblookup_local() for doing the local port
check. Note that this implementation is space inefficient in that the PCB
struct is now too large to fit into 128 bytes. I might deal with this in the
future by using the new zone allocator, but I wanted these changes to be
extensively tested in their current form first.

Also:
1) Fixed off-by-one errors in the port lookup loops in in_pcbbind().
2) Got rid of some unneeded rehashing. Adding a new routine, in_pcbinshash()
   to do the initialial hash insertion.
3) Renamed in_pcblookuphash() to in_pcblookup_hash() for easier readability.
4) Added a new routine, in_pcbremlists() to remove the PCB from the various
   hash lists.
5) Added/deleted comments where appropriate.
6) Removed unnecessary splnet() locking. In general, the PCB functions should
   be called at splnet()...there are unfortunately a few exceptions, however.
7) Reorganized a few structs for better cache line behavior.
8) Killed my TCP_ACK_HACK kludge. It may come back in a different form in
   the future, however.

These changes have been tested on wcarchive for more than a month. In tests
done here, connection establishment overhead is reduced by more than 50
times, thus getting rid of one of the major networking scalability problems.

Still to do: make tcp_fastimo/tcp_slowtimo scale well for systems with a
large number of connections. tcp_fastimo is easy; tcp_slowtimo is difficult.

WARNING: Anything that knows about inpcb and tcpcb structs will have to be
         recompiled; at the very least, this includes netstat(1).

1 files changed, 5 insertions, 5 deletions

diff --git a/sys/netinet/tcp_timewait.c b/sys/netinet/tcp_timewait.c
index 962dc47..b0bdac2 100644
--- a/sys/netinet/tcp_timewait.c
+++ b/sys/netinet/tcp_timewait.c
@@ -31,7 +31,7 @@
  * SUCH DAMAGE.
  *
  *	@(#)tcp_subr.c	8.2 (Berkeley) 5/24/95
- *	$Id: tcp_subr.c,v 1.40 1997/12/19 03:36:14 julian Exp $
+ *	$Id: tcp_subr.c,v 1.41 1998/01/25 04:23:32 eivind Exp $
  */
 
 #include "opt_compat.h"
@@ -87,11 +87,10 @@ static void	tcp_cleartaocache __P((void));
 static void	tcp_notify __P((struct inpcb *, int));
 
 /*
- * Target size of TCP PCB hash table. Will be rounded down to a prime
- * number.
+ * Target size of TCP PCB hash tables. Must be a power of two.
  */
 #ifndef TCBHASHSIZE
-#define TCBHASHSIZE	128
+#define TCBHASHSIZE	512
 #endif
 
 /*
@@ -107,6 +106,7 @@ tcp_init()
 	LIST_INIT(&tcb);
 	tcbinfo.listhead = &tcb;
 	tcbinfo.hashbase = hashinit(TCBHASHSIZE, M_PCB, &tcbinfo.hashmask);
+	tcbinfo.porthashbase = hashinit(TCBHASHSIZE, M_PCB, &tcbinfo.porthashmask);
 	if (max_protohdr < sizeof(struct tcpiphdr))
 		max_protohdr = sizeof(struct tcpiphdr);
 	if (max_linkhdr + sizeof(struct tcpiphdr) > MHLEN)
@@ -417,8 +417,8 @@ tcp_close(tp)
 	}
 	if (tp->t_template)
 		(void) m_free(dtom(tp->t_template));
+	inp->inp_ppcb = NULL;
 	free(tp, M_PCB);
-	inp->inp_ppcb = 0;
 	soisdisconnected(so);
 	in_pcbdetach(inp);
 	tcpstat.tcps_closed++;