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).
them in the include path. This fixes recent breakage of the syscons
LKMs and general brokenness of the include paths (headers under
/usr/include were used in many cases).
things fixed in here, including the '-ko' vs. -A problem with
remote cvs which caused all files with -ko to be resent each time
(which is damn painful over a modem, I can tell you). It also found a
heap of stray empty directories that should have been pruned with the -P
flag to cvs update but were not for some reason.
It also has the fully integrated rcs and diff, so no more fork/exec
overheads for rcs,ci,patch,diff,etc. This means that it parses the control
data in the rcs files only once rather than twice or more.
If the 'cvs diff' vs. Index thing is going to be fixed for future patch
compatability, this is the place to do it.
volume value for the disc. It is now possible to specify additional arguments
(audio, volume, media) to print only a subset of the full status.
This is particularly useful with drives which stop playing when asked to
return the catalog number.
-i Do not overwrite files.
-s Do not strip output pathname to base filename. By default uuencode
deletes any prefix ending with the last slash '/' for security
purpose.
6x86MX CPU is enabled (BIOS should not disable it), some BIOS disables
it via CCR4. In this case, cpu variable becomes CPU_486 and
identblue() is called. Because Cyrix 6x86MX has MSR and doesn't have
MSR1002, wrmsr instruction generates general protection fault.
Tested by: Simon Coggins <chaos@ultra.net.au>
