Commit Graph

200801 Commits

Author SHA1 Message Date
nonaka
28846998b3 Reduce kernel size.
Tested on SL-C1000.

Fix PR/44898.
2011-05-05 09:07:59 +00:00
nonaka
9d698592f1 Don't check device numbers. 2011-05-05 08:46:12 +00:00
mrg
a8b7159c16 convert stripelocks to kmutex. 2011-05-05 08:21:29 +00:00
mrg
c4fdb0522f RF_BROADCAST_COND() is no more. 2011-05-05 08:21:09 +00:00
wiz
93cfe89ec0 Add missing preposition. 2011-05-05 07:36:44 +00:00
mrg
710e439b0e convert access_suspend_mutex to a kmutex/cv. 2011-05-05 07:12:58 +00:00
mrg
ec1c557b57 convert the diskqueue mutex into a kmutex 2011-05-05 06:04:09 +00:00
jruoho
19742b4964 Fix lead paragraph. 2011-05-05 05:58:14 +00:00
jruoho
f9b73fbc67 Follow the real tree with the test directory structure. 2011-05-05 05:39:10 +00:00
jruoho
083337961f Fix some glitches (a human doing machine's work). 2011-05-05 05:28:52 +00:00
jruoho
5cdd3dcf2a Follow the real tree with the test directory structure. 2011-05-05 05:24:44 +00:00
tsutsui
d797bedab3 Fix buffer overrun in readdisklabel(9) (and writedisklabel(9))
that causes unexpected panic during installation and
DIAGNOSTIC pool assertions.
Also fix bp->b_flags in writedisklabel(9) error path.

The problem was reported from Y.Sugahara during XM6i development,
and this fix is confirmed on both X68030 (by me) and XM6i (by Sugahara).

XXX: broken dkbad support (which makes struct cpu_disklabel larger
XXX: than 512 bytes) should be removed...
2011-05-05 04:38:20 +00:00
mrg
50fe584a38 finish porting mcpair users to kmutex, and fix a couple of declarations
in rf_netbsdkintf.c.  fixes i386/conf/ALL build.
2011-05-05 04:20:51 +00:00
macallan
bcb7f01345 add support for (ancient) Mach64 CX and GX, while there make sure the visible
vram area starts at the same offset as the area we're going to draw into -
zero that is.
from David Riley
2011-05-04 23:36:21 +00:00
wiz
9e66d3e091 Remove trailing whitespace. 2011-05-04 21:24:59 +00:00
christos
fc29dd21ad Document what I wrote for PR/40115 2011-05-04 21:14:56 +00:00
sjg
48587910e0 Add .MAKE.META.BAILIWICK - to identify the scope of make's control.
meta_oodate: if a file that was written or linked within our bailiwick,
but outside of .OBJDIR is missing, add it to missingFiles.
If we get to the end of the .meta file without seeing it [re]moved,
then consider the target out-of-date.
2011-05-04 20:38:31 +00:00
tsutsui
08bc844a54 Don't call mfp_init() in mfp_attach().
It's already called from early mfp_config_console() via config_console()
and reinitializing MFP could sometimes cause silent hang.
2011-05-04 12:27:03 +00:00
tsutsui
17739fce78 WARNSfy to avoid further botch. 2011-05-04 11:44:25 +00:00
macallan
1abcfa381e add access functions for the Instruction Cache Throttling Control register
found in 750 and newer CPUs
2011-05-04 04:33:37 +00:00
pgoyette
38b438f332 Use %zx for _both_ size_t formats! 2011-05-04 03:43:30 +00:00
dyoung
c1922724a7 Invalidate the vestigital PCB at the top of in6_pcblookup_connect() to
fix the bug where incoming TCPv6 connections were reset.
2011-05-04 01:45:48 +00:00
dyoung
fe23a102a6 On second thought, make a more conservative change: use %zx instead of
%x for size_t.
2011-05-04 01:31:40 +00:00
dyoung
6392073d00 Use %zu format for size_t instead of %x. 2011-05-04 01:30:01 +00:00
dyoung
7957556091 Always try to open kmem, do not always set use_sysctl to 1, and do not
fail if opening kmem fails unless !use_sysctl.  Fixes netstat(1) options
such as -s.
2011-05-04 01:13:35 +00:00
dyoung
7135b6c6f4 Access the kvm_t using get_kvmd(), only. 2011-05-04 01:11:29 +00:00
dyoung
fea546afcb Don't use type qualifier 'register'. 2011-05-04 00:55:19 +00:00
dyoung
6866464399 Remove #ifdef INET6 throughout. 2011-05-03 23:57:41 +00:00
dyoung
7f40ffb8aa Do not display expired or reclaimed vestigial TIME_WAIT entries. 2011-05-03 23:36:26 +00:00
jym
0471a19395 Use fls64() only for types strictly bigger than 4 bytes.
ok christos@. Will ask for a pull-up, using 64 bits ops even for 4-bytes
int's is plain overkill.
2011-05-03 21:36:59 +00:00
dyoung
c2e43be1c5 Reduces the resources demanded by TCP sessions in TIME_WAIT-state using
methods called Vestigial Time-Wait (VTW) and Maximum Segment Lifetime
Truncation (MSLT).

MSLT and VTW were contributed by Coyote Point Systems, Inc.

Even after a TCP session enters the TIME_WAIT state, its corresponding
socket and protocol control blocks (PCBs) stick around until the TCP
Maximum Segment Lifetime (MSL) expires.  On a host whose workload
necessarily creates and closes down many TCP sockets, the sockets & PCBs
for TCP sessions in TIME_WAIT state amount to many megabytes of dead
weight in RAM.

Maximum Segment Lifetimes Truncation (MSLT) assigns each TCP session to
a class based on the nearness of the peer.  Corresponding to each class
is an MSL, and a session uses the MSL of its class.  The classes are
loopback (local host equals remote host), local (local host and remote
host are on the same link/subnet), and remote (local host and remote
host communicate via one or more gateways).  Classes corresponding to
nearer peers have lower MSLs by default: 2 seconds for loopback, 10
seconds for local, 60 seconds for remote.  Loopback and local sessions
expire more quickly when MSLT is used.

Vestigial Time-Wait (VTW) replaces a TIME_WAIT session's PCB/socket
dead weight with a compact representation of the session, called a
"vestigial PCB".  VTW data structures are designed to be very fast and
memory-efficient: for fast insertion and lookup of vestigial PCBs,
the PCBs are stored in a hash table that is designed to minimize the
number of cacheline visits per lookup/insertion.  The memory both
for vestigial PCBs and for elements of the PCB hashtable come from
fixed-size pools, and linked data structures exploit this to conserve
memory by representing references with a narrow index/offset from the
start of a pool instead of a pointer.  When space for new vestigial PCBs
runs out, VTW makes room by discarding old vestigial PCBs, oldest first.
VTW cooperates with MSLT.

It may help to think of VTW as a "FIN cache" by analogy to the SYN
cache.

A 2.8-GHz Pentium 4 running a test workload that creates TIME_WAIT
sessions as fast as it can is approximately 17% idle when VTW is active
versus 0% idle when VTW is inactive.  It has 103 megabytes more free RAM
when VTW is active (approximately 64k vestigial PCBs are created) than
when it is inactive.
2011-05-03 18:28:44 +00:00
dyoung
ac162b774b *_drain() routines may be called with locks held, so instead of doing
any work in *_drain(), set a drain-needed flag.  Do the work in the
fasttimo handler.

Contributed by Coyote Point Systems, Inc.
2011-05-03 17:44:30 +00:00
jruoho
6372875351 Fix PR bin/22230. 2011-05-03 16:25:19 +00:00
jruoho
4811a79682 Link {daily, monthly, weekly}.conf.5 to {daily, monthly, weekly}.5 and move
things around a little. Part of fixing PR bin/22230.
2011-05-03 16:12:23 +00:00
dyoung
8e054749e4 arp_drain() may be called with locks held, so instead of doing any work
in arp_drain(), set a drain-needed flag.  Do the work in the fasttimo
handler.

Contributed by Coyote Point Systems, Inc.
2011-05-03 16:00:29 +00:00
jruoho
cb861154c1 Add a test case for PR bin/26453. 2011-05-03 15:13:50 +00:00
jruoho
ae3433a79c Fix same copy-paste error here. (Why atf(7) does not warn about these?) 2011-05-03 14:26:11 +00:00
jruoho
15dd14fca5 Fix build failure reported by pgoyette@. 2011-05-03 14:11:51 +00:00
manu
38ecbcf429 Fixes for the advlock method. It can now sustain pkgsrc/devel/locktests
with glusterfs as backend
2011-05-03 13:19:50 +00:00
manu
7f87f63c56 Call advlock method if supplied 2011-05-03 13:16:47 +00:00
manu
f8934bcc9b Fix build (libperfuse is still not built by default, but time is coming) 2011-05-03 13:14:09 +00:00
jruoho
ab0275b298 Clarify the comment on how to disable password authentication (i.e. the
combination of PasswordAuthentication=no and UsePam=yes still allow password
authentication). Fixes PR bin/32313 from Curt Sampson.
2011-05-03 13:04:00 +00:00
jruoho
1a3a1673c8 Fix copy-paste error. 2011-05-03 12:54:48 +00:00
wiz
daf04c06a3 Remove \*[q] -- not necessary, just use plain double quotes instead. 2011-05-03 09:36:24 +00:00
tsutsui
50d317854b TAB/space cosmetics. 2011-05-03 09:15:20 +00:00
jruoho
7b594ad6a4 Identify AMD Family 11h. From PR bin/41188 by FUKAUMI Naoki. 2011-05-03 09:06:22 +00:00
jruoho
6e1e04d65f Add a test for PR bin/41880. 2011-05-03 08:36:15 +00:00
mrg
15d13d88fa convert the pssTable mutex into a kmutex/cv. 2011-05-03 08:18:43 +00:00
jruoho
765b090a54 A test for non-critical/low PR bin/42179. 2011-05-03 07:56:42 +00:00
jruoho
1f57069f96 Verify that PR bin/42628 is no longer an issue. 2011-05-03 07:23:19 +00:00