freebsd-skq/sys at b003da79386de11c47119f4e4e4424dba4d3e9a7 - freebsd-skq - Quacker.org Git Repositories

d/freebsd-skq

History

David E. O'Brien b003da7938 Give a more reasonable CPU time to the threads which are using scheduler

activation (i.e., applications are using libpthread).  This is because
SCHED_ULE sometimes puts P_SA processes into ksq_next unnecessarily.
Which doesn't give fair amount of CPU time to processes which are
using scheduler-activation-based threads when other (semi-)CPU-intensive,
non-P_SA processes are running.

Further work will no doubt be done by jeffr at a later date.

Submitted by:	Taku YAMAMOTO <taku@cent.saitama-u.ac.jp>
Reviewed by:	rwatson, freebsd-current@

2004-03-21 18:53:29 +00:00

..

- Add uiomove_fromphys() implementations to alpha and ia64. These only

2004-03-20 21:06:20 +00:00

- Add uiomove_fromphys() implementations to alpha and ia64. These only

2004-03-20 21:06:20 +00:00

Introduce the cpumask_t type. The purpose of the type is to create a

2004-03-20 20:41:40 +00:00

MFi386: revision 1.29.

2004-03-14 09:43:15 +00:00

Compare the *number* of patterns to zero, not the *pointer* to the

2004-02-28 12:59:56 +00:00

Device megapatch 5/6:

2004-02-21 21:32:15 +00:00

Change (yet again, sorry!) the path of the 32 bit ld-elf.so.1.

2004-03-21 01:22:24 +00:00

Compile the kernel with -O2 on ia64 by default.

2004-03-21 05:10:34 +00:00

Check in files off the vendor branch as well as files with local patches.

2004-03-18 17:46:27 +00:00

Fix a reentrancy issue in md5_calc().

2004-01-27 18:57:21 +00:00

Give DDB a "watchdog" command which disables all watchdogs.

2004-02-29 09:55:32 +00:00

Fix $FreeBSD$.

2004-03-21 18:16:49 +00:00

Don't reject FAT file systems with a number of "Heads" greater than

2004-03-14 23:28:12 +00:00

Move "is consumer attached?" check before G_VALID_PROVIDER() check,

2004-03-18 07:17:10 +00:00

Properly vector all bwrite() and BUF_WRITE() calls through the same path

2004-03-11 18:02:36 +00:00

Convert callers to the new bus_alloc_resource_any(9) API.

2004-03-17 17:50:55 +00:00

Introduce the cpumask_t type. The purpose of the type is to create a

2004-03-20 20:41:40 +00:00

In breakpoint(), use a different immediate to make sure we can

2004-03-21 01:41:29 +00:00

Convert callers to the new bus_alloc_resource_any(9) API.

2004-03-17 17:50:55 +00:00

Remove unused second arg to vfinddev().

2004-03-11 16:33:11 +00:00

Give a more reasonable CPU time to the threads which are using scheduler

2004-03-21 18:53:29 +00:00

These are changes to allow to use the Intel C/C++ compiler (lang/icc)

2004-03-12 21:45:33 +00:00

Add uart_subr.c

2004-03-20 22:41:52 +00:00

- Correct variable name.

2004-03-21 17:27:41 +00:00

Add explicit dependency on "ether", since we use ether_ifattach().

2004-03-16 19:25:55 +00:00

Spell "(struct foo *)0" as "NULL".

2004-03-21 03:28:08 +00:00

These are changes to allow to use the Intel C/C++ compiler (lang/icc)

2004-03-12 21:45:33 +00:00

Make the vaule of PTT_RELAY_SID match the RFC. This should help PPPoE

2004-03-18 12:34:14 +00:00

- Fix indentation lost by 'diff -b'.

2004-03-21 18:51:26 +00:00

Move the AH algorithm list from a static local function variable to

2004-03-10 04:56:54 +00:00

Fix type in a sysctl. It used to be: net.key.prefered_oldsa

2004-02-16 17:09:53 +00:00

Rename dup_sockaddr() to sodupsockaddr() for consistency with other

2004-03-01 03:14:23 +00:00

avoid duplicate free.

2004-01-25 17:18:12 +00:00

Rename dup_sockaddr() to sodupsockaddr() for consistency with other

2004-03-01 03:14:23 +00:00

Make the process_exit eventhandler run without Giant. Add Giant hooks

2004-03-14 02:06:28 +00:00

Rename dup_sockaddr() to sodupsockaddr() for consistency with other

2004-03-01 03:14:23 +00:00

…

Properly vector all bwrite() and BUF_WRITE() calls through the same path

2004-03-11 18:02:36 +00:00

Add a comment with an explanation why we don't report EPIPE errors on

2004-03-17 21:10:20 +00:00

Calculate NFS timeouts in units of 10ms, not 5ms. This matches the default

2004-03-14 06:21:56 +00:00

kthread_exit() no longer requires Giant, so don't force callers to acquire

2004-03-05 22:42:17 +00:00

Convert callers to the new bus_alloc_resource_any(9) API.

2004-03-17 17:50:55 +00:00

Convert callers to the new bus_alloc_resource_any(9) API.

2004-03-17 17:50:55 +00:00

solid reports that it is buggy *and* that it slows down transmit

2004-03-19 23:20:23 +00:00

The sem_timedwait() and ksem_timedwait() functions both

2004-02-03 22:27:03 +00:00

Introduce the cpumask_t type. The purpose of the type is to create a

2004-03-20 20:41:40 +00:00

Calculate NFS timeouts in units of 10ms, not 5ms. This matches the default

2004-03-14 06:21:56 +00:00

Define BPFD_LOCK_ASSERT() to assert the BPF descriptor lock.

2004-02-29 15:33:56 +00:00

Introduce the cpumask_t type. The purpose of the type is to create a

2004-03-20 20:41:40 +00:00

Introduce the cpumask_t type. The purpose of the type is to create a

2004-03-20 20:41:40 +00:00

Attempt to clean up the emu10k1-alsa.h stuff so that config doesn't

2004-02-05 22:51:16 +00:00

Avoid doing bawrite to initialize inode block while holding cylinder

2004-03-16 22:06:32 +00:00

When mmap-ing a file from a noexec mount, be sure not to grant the right

2004-03-18 20:58:51 +00:00

Makefile

Replaced outdated comment.

2004-01-17 03:28:27 +00:00