haiku/src/system/kernel
Pawel Dziepak c08ed2db65 scheduler: Try to keep thread on the same logical CPU
Some SMT implementations (e.g. recent AMD microarchitectures) have
separate L1d cache for each SMT thread (which AMD decides to call "cores").
This means that we shouldn't move threads to another logical processor too
often even if it belongs to the same core. We aren't very strict about
this as it would complicate load balancing, but we try to reduce unnecessary
migrations.
2013-12-20 03:36:01 +01:00
..
arch x86[_64]: Support assigning MSI IRQs to arbitrary CPU 2013-12-20 01:07:08 +01:00
cache Merge branch 'master' into x86_64 2012-11-18 14:02:07 +00:00
debug kernel: Use SMP_MAX_CPUS instead of B_MAX_CPU_COUNT 2013-12-06 19:53:56 +01:00
device_manager kernel: Remove gSchedulerLock 2013-11-08 02:41:26 +01:00
disk_device_manager Merge branch 'master' into package-management 2013-05-05 15:03:26 +02:00
fs Remove remaining unnecessary 'volatile' qualifiers 2013-11-06 00:03:07 +01:00
lib ARM: kernel: fix timer resolution and implement basic timekeeping. 2013-09-17 14:42:05 +02:00
locks kernel, drivers: Fix gcc2 build 2013-11-29 03:47:38 +01:00
messaging Clean up the mess added in hrev43461 and solve it differently. 2011-12-10 23:20:18 +01:00
platform Whitespace cleanup 2013-09-17 13:51:38 +02:00
posix kernel/posix: Do not use thread_block_locked() 2013-11-07 02:06:42 +01:00
scheduler scheduler: Try to keep thread on the same logical CPU 2013-12-20 03:36:01 +01:00
slab Add support for pthread_attr_get/setguardsize() 2012-12-28 18:02:58 +00:00
util kernel/util: Bitmap: Silence warning 2013-12-06 03:10:50 +01:00
vm kernel, libroot: Add more memory info in system_info 2013-12-16 04:53:46 +01:00
boot_item.cpp * Changed get_boot_item() API: it now also can retrieve the size of the boot 2008-03-30 11:01:41 +00:00
boot_splash.cpp Move the boot images conditional selection in one place, to remove 2010-10-11 12:54:21 +00:00
commpage.cpp vm: place commpage and team data near the top of user address space 2013-04-04 15:27:24 +02:00
condition_variable.cpp kernel: Remove gSchedulerLock 2013-11-08 02:41:26 +01:00
cpu.cpp kernel: Protect cpu_ent::active_time with sequential lock 2013-12-20 01:31:32 +01:00
DPC.cpp kernel: DPC: remove schedulerLocked argument 2013-11-04 23:51:18 +01:00
elf.cpp elf: restore correct region protection after relocation 2013-04-16 03:44:38 +02:00
guarded_heap.cpp Fix the page need calculation, it was possibly off by one. 2011-12-07 00:09:31 +01:00
heap.cpp kernel: Use SMP_MAX_CPUS instead of B_MAX_CPU_COUNT 2013-12-06 19:53:56 +01:00
image.cpp kernel: Remove Thread::next_state 2013-11-29 19:31:10 +01:00
int.cpp x86[_64]: Support assigning MSI IRQs to arbitrary CPU 2013-12-20 01:07:08 +01:00
Jamfile scheduler: Code refactoring 2013-12-05 22:47:30 +01:00
kernel_c++_structs.cpp Attempt at allowing to use C++ structures in C only code: We use the 2009-12-02 10:56:10 +00:00
kernel_daemon.cpp Replaced no longer necessary send_signal_etc() work-arounds for 2010-04-29 15:23:29 +00:00
kernel_versions Merged signals-merge branch into trunk with the following changes: 2011-06-12 00:00:23 +00:00
kernel.rdef patch by Artur Wyszynski (aljen): 2008-03-18 10:11:58 +00:00
linkhack.c
listeners.cpp Added WaitObjectListener destructor. Hopefully fixes the gcc 2 build. 2009-04-23 14:53:18 +00:00
low_resource_manager.cpp First round of 64-bit safety fixes in the kernel. 2012-06-13 17:42:46 +01:00
main.cpp kernel: smp_cpu_rendezvous(): Use counter instead of bitmap 2013-12-05 23:10:04 +01:00
module.cpp Merge branch 'master' into package-management 2013-05-05 15:03:26 +02:00
Notifications.cpp Rework DefaultNotificationService registration. 2013-04-22 18:42:21 -04:00
port.cpp kernel: Remove gSchedulerLock 2013-11-08 02:41:26 +01:00
real_time_clock.cpp Changed {,u}int64 to be long rather than long long on x86_64. 2012-06-28 12:36:45 +01:00
sem.cpp kernel: Remove gSchedulerLock 2013-11-08 02:41:26 +01:00
shutdown.cpp Introduce a gSystemShutdown flag to be able to check if system is shutting down. ACPI Embedded Controller now uses polling when it is set to true. 2010-09-08 19:19:49 +00:00
signal.cpp kernel: Remove Thread::next_state 2013-11-29 19:31:10 +01:00
smp.cpp kernel: Protect cpu_ent::active_time with sequential lock 2013-12-20 01:31:32 +01:00
syscalls.cpp Merged signals-merge branch into trunk with the following changes: 2011-06-12 00:00:23 +00:00
system_info.cpp kernel: Fix topology node count being decreased twice per node 2013-12-19 20:24:34 +01:00
team.cpp kernel: Remove Thread::next_state 2013-11-29 19:31:10 +01:00
TeamThreadTables.h Merged signals-merge branch into trunk with the following changes: 2011-06-12 00:00:23 +00:00
thread.cpp kernel: Use SMP_MAX_CPUS instead of B_MAX_CPU_COUNT 2013-12-06 19:53:56 +01:00
timer.cpp kernel: Use SMP_MAX_CPUS instead of B_MAX_CPU_COUNT 2013-12-06 19:53:56 +01:00
UserEvent.cpp kernel: Change Thread::team_lock to rw_spinlock 2013-11-07 04:20:59 +01:00
usergroup.cpp kernel: Do not use gSchedulerLock when accesing UID and GID 2013-10-30 02:57:45 +01:00
UserTimer.cpp kernel: Rework cpuidle module 2013-11-25 23:50:27 +01:00
wait_for_objects.cpp _user_wait_for_objects(): Don't copy the infos back to userland when an error 2010-03-25 15:57:38 +00:00