Garrett Wollman 233e8c18e8 A number of performance-reducing flaws fixed based on comments ... from Larry Peterson &co. at Arizona: - Header prediction for ACKs did not exclude Fast Retransmit/Recovery. - srtt calculation tended to get ``stuck'' and could never decrease when below 8. It still can't, but the scaling factors are adjusted so that this artifact does not cause as bad an effect on the RTO value as it used to. The paper also points out the incr/8 error that has been long since fixed, and the problems with ACKing frequency resulting from the use of options which I suspect to be fixed already as well (as part of the T/TCP work). Obtained from: Brakmo & Peterson, ``Performance Problems in BSD4.4 TCP''		1996-03-22 18:09:21 +00:00
..
alpha	Update the linux_sendsig() handler to the new type of the 4th	1996-03-17 14:31:58 +00:00
amd64	Add vx0 device to GENERIC. Yes, I know that this bloats GENERIC, but	1996-03-20 10:42:56 +00:00
compat/linux	Fixed unsigned longs that should have been vm_offset_t.	1996-03-19 15:03:00 +00:00
compile	Stop cvs up -P from removing empty compile directories.	1994-08-25 16:20:16 +00:00
conf	Add fe0 to the LINT and GENERIC files (hmmm - looks like my rcvs setup't	1996-03-17 08:39:51 +00:00
ddb	For Lite2: proc LIST changes.	1996-03-11 05:55:56 +00:00
dev	Ported to 2.2-current. Uses [bc]devsw_add(), and is also now a proper	1996-03-21 04:13:25 +00:00
fs	Fix the problem that unmounting filesystems that are backed by a VMIO	1996-03-19 05:13:22 +00:00
geom	Ported to 2.2-current. Uses [bc]devsw_add(), and is also now a proper	1996-03-21 04:13:25 +00:00
gnu	Removed vestigial support for the obsolete FIFO option. In ext2fs	1996-02-25 20:12:36 +00:00
i386	Disable SCSI parity checking until we figure out why the aic78X0 generates	1996-03-22 16:26:26 +00:00
isa	Fix the isa_device table (lkm): id_irq and id_maddr must be 0.	1996-03-16 01:08:04 +00:00
isofs/cd9660	Provide a better handling of partially corrupted directory entries.	1996-03-14 21:44:32 +00:00
kern	Fixed unsigned longs that should have been vm_offset_t.	1996-03-19 15:03:00 +00:00
libkern	Import 4.4BSD-Lite2 onto the vendor branch, note that in the kernel, all	1996-03-11 19:22:56 +00:00
miscfs	Fix the problem that unmounting filesystems that are backed by a VMIO	1996-03-19 05:13:22 +00:00
modules	Add joy to the SUBDIR list.	1996-03-16 01:43:26 +00:00
msdosfs	Fix a bunch of spelling errors in the comment fields of	1996-01-30 23:02:38 +00:00
net	Move or add #include <queue.h> in preparation for upcoming struct socket	1996-03-11 15:13:58 +00:00
netinet	A number of performance-reducing flaws fixed based on comments	1996-03-22 18:09:21 +00:00
netipx	Move or add #include <queue.h> in preparation for upcoming struct socket	1996-03-11 15:13:58 +00:00
netns	finish killing off netns. (For some reason, CVS `undeleted' these	1996-02-13 18:19:17 +00:00
nfs	Import 4.4BSD-Lite2 onto the vendor branch, note that in the kernel, all	1996-03-11 19:34:14 +00:00
nfsclient	Kill XNS.	1996-02-13 18:16:31 +00:00
nfsserver	Kill XNS.	1996-02-13 18:16:31 +00:00
pc98/pc98	Fix a bunch of spelling errors in the comment fields of	1996-01-30 23:02:38 +00:00
pccard	Removed un-used code.	1996-02-21 23:31:03 +00:00
pci	Fixed unsigned longs that should have been vm_offset_t.	1996-03-19 15:03:00 +00:00
powerpc/include	Add commands for ptrace get/set registers.. (Same numbers as NetBSD)	1996-01-24 18:51:48 +00:00
rpc	Fix a bunch of spelling errors in the comment fields	1996-01-30 23:33:04 +00:00
scsi	Fixed some missing int32 -> int32_t	1996-03-10 18:17:54 +00:00
sys	Actually implement SA_RESETHAND - some of the sigaction code recognised it	1996-03-15 08:01:33 +00:00
tools	Another mega commit to staticize things.	1995-12-14 09:55:16 +00:00
ufs	Import 4.4BSD-Lite2 onto the vendor branch, note that in the kernel, all	1996-03-11 19:47:21 +00:00
vm	Fix the problem that unmounting filesystems that are backed by a VMIO	1996-03-19 05:13:22 +00:00
Makefile	Removed almost all traces of libkern.a. The objects that were in	1995-12-26 13:58:31 +00:00