Commit Graph

44 Commits

Author SHA1 Message Date
Alex Smith
4be4fc6b1f More 64-bit compilation/safety fixes. 2012-06-15 16:04:20 +01:00
Fredrik Holmqvist
78af90d494 Fix codestyle violation:
Multiline statements after if should always be in a code block.
No functional change.
2012-05-14 21:05:12 +02:00
Yongcong Du
44c3c03412 scheduler: Don't setup the quantumTimer for idle thread
Let's say the timer is waken up when its hook is called. This patch
reduces ~41% wakeups during idle

Signed-off-by: Fredrik Holmqvist <fredrik.holmqvist@gmail.com>
2012-05-13 19:06:47 +02:00
Ingo Weinhold
24df65921b Merged signals-merge branch into trunk with the following changes:
* Reorganized the kernel locking related to threads and teams.
* We now discriminate correctly between process and thread signals. Signal
  handlers have been moved to teams. Fixes #5679.
* Implemented real-time signal support, including signal queuing, SA_SIGINFO
  support, sigqueue(), sigwaitinfo(), sigtimedwait(), waitid(), and the addition
  of the real-time signal range. Closes #1935 and #2695.
* Gave SIGBUS a separate signal number. Fixes #6704.
* Implemented <time.h> clock and timer support, and fixed/completed alarm() and
  [set]itimer(). Closes #5682.
* Implemented support for thread cancellation. Closes #5686.
* Moved send_signal() from <signal.h> to <OS.h>. Fixes #7554.
* Lots over smaller more or less related changes.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@42116 a95241bf-73f2-0310-859d-f6bbb57e9c96
2011-06-12 00:00:23 +00:00
Ingo Weinhold
4535495d80 Merged the signals branch into trunk, with these changes:
* The team and thread kernel structures have been renamed to Team and Thread
  respectively and moved into the new BKernel namespace.
* Several (kernel add-on) sources have been converted from C to C++ since
  private kernel headers are included that are no longer C compatible.

Changes after merging:
* Fixed gcc 2 build (warnings mainly in the scary firewire bus manager).


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@40196 a95241bf-73f2-0310-859d-f6bbb57e9c96
2011-01-10 21:54:38 +00:00
Axel Dörfler
3e86abbd71 * Added an extra check as requested by CID 1567, but also added a comment why
this (and other checks) should not be necessary in the first place.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@38229 a95241bf-73f2-0310-859d-f6bbb57e9c96
2010-08-18 11:39:39 +00:00
Ingo Weinhold
f651548ee6 scheduler_reschedule_no_op(): panic() when the calling thread is not
continuing to run. This must not happen since the thread is the boot CPU's
idle thread performing the early kernel initialization (before the scheduler
is started).


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@36560 a95241bf-73f2-0310-859d-f6bbb57e9c96
2010-04-30 19:40:20 +00:00
Ingo Weinhold
28d05e026f Make scheduler_reschedule() an no-op until we're ready to start the
scheduler. This avoids the need to use the send_signal_etc() work-around for
resume_thread() during the early kernel initialization. Might fix #5851.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@36530 a95241bf-73f2-0310-859d-f6bbb57e9c96
2010-04-29 15:10:37 +00:00
Axel Dörfler
ee0d2be9e4 bonefish+axeld:
* Implemented a tiny bit more sophisticated version of
  estimate_max_scheduling_latency() that uses a syscall that lets the scheduler
  decide.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@36170 a95241bf-73f2-0310-859d-f6bbb57e9c96
2010-04-11 20:40:58 +00:00
Ingo Weinhold
022cdb9ce3 Fixed build with scheduler tracing enabled.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34714 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-12-20 00:32:08 +00:00
Ingo Weinhold
0338371f26 * All scheduler implementations:
- enqueue_in_run_queue() no longer returns whether rescheduling is supposed
    to happen. Instead is sets cpu_ent::invoke_scheduler on the current CPU.
  - reschedule() does now handle cpu_ent::invoke_scheduler_if_idle(). No need
    to let all callers do that.
* thread_unblock[_locked]() no longer return whether rescheduling is supposed
  to happen.
* Got rid of the B_INVOKE_SCHEDULER handling. The interrupt hooks really
  can't know, when it makes sense to reschedule or not.
* Introduced scheduler_reschedule_if_necessary[_locked]() functions for
  checking+invoking the scheduler.
* Some semaphore functions (e.g. delete_sem()) invoke the scheduler now, if
  they wake up anything with greater priority.
  I've also tried to add scheduler invocations in the condition variable and
  mutex/rw_lock code, but that actually has a negative impact on performance,
  probably because it causes too much ping-ponging between threads when
  multiple locking primitives are involved.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34657 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-12-13 21:18:27 +00:00
Axel Dörfler
adf9b14ed6 * Applied r34634 to the simple SMP scheduler as well (Rene was right, I just
overlooked it).


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34641 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-12-12 15:02:30 +00:00
Rene Gollent
5c7993bfab Small cleanup: As the cpu_ent struct now tracks the running thread directly, the affine scheduler can use that instead of keeping track internally.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34638 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-12-12 00:01:33 +00:00
Ingo Weinhold
e36d79e9dc CPU selection in enqueue_in_run_queue():
* Moved the CPU selection conde into a separate function.
* Re-added the support for disabling CPUs, which I accidentally removed.
* Got rid of idle CPU tracking. We don't need it anymore -- we iterate
  through all CPUs and check the priority of the running thread.
* Added a kind of round-robin component to the CPU selection loop, so that
  we pick CPUs more evenly. And indeed, the ProcessController display is
  less skewed, now. There doesn't seem to be a measurable performance gain,
  though.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34637 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-12-11 23:28:28 +00:00
Ingo Weinhold
b4be7c9021 * Added cpu_ent::running_thread which is maintained by the schedulers.
* simple_smp scheduler: Rewrote the interesting part of
  enqueue_in_run_queue(). It always selects a target CPU for the inserted
  thread, now. If no CPU is idle, the CPU running the thread with the lowest
  priority is chosen. If the thread running on the target CPU has a lower
  priority than the inserted one, it will be asked to reschedule. If that's
  the current CPU, we'll return the correct value (wasn't done before at
  all).
  These changes help reducing latencies. On my machine in an idle system
  playing music DebugAnalyzer shows maximum latencies of about 1 us. I still
  find that a bit much, but it's several orders of magnitude better than
  before. The -j8 Haiku image build time dropped about 10%.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34635 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-12-11 19:06:57 +00:00
Axel Dörfler
edc69377fa * Changed the simple scheduler's next thread selection in the same way as the
affine scheduler to avoid possible latency issues.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34634 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-12-11 17:40:15 +00:00
Ingo Weinhold
ec1dcae8cd We have to use dprintf_no_syslog() in the scheduler, as all code is executed
with the threads spinlock held.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34629 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-12-11 10:25:56 +00:00
Ingo Weinhold
3533b6597d * Reintroduced the SMP_MSG_RESCHEDULE_IF_IDLE ICI message. This time
implemented by means of an additional member in cpu_ent.
* Removed thread::keep_scheduled and the related functions. The feature
  wasn't used yet and wouldn't have worked as implemented anyway.
* Resurrected an older, SMP aware version of our simple scheduler and made it
  the default instead of the affine scheduler. The latter is in no state to
  be used yet. It causes enormous latencies (I've seen up to 0.1s) even when
  six or seven CPUs were idle at the same time, totally killing parallelism.
  That's also the reason why a -j8 build was slower than a -j2. This is no
  longer the case. On my machine the -j2 build takes about 10% less time now
  and the -j8 build saves another 20%. The latter is not particularly
  impressive (compared with Linux), but that seems to be due to lock
  contention.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34615 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-12-10 11:54:38 +00:00
Axel Dörfler
7249de5e61 * Changed the affine scheduler to have more or less the same characteristics
as the BeOS scheduler. This makes MediaPlayer playback much better, as high
  priority threads could lose their quantum to a worker thread twice in a row
  with 4% probability before.
* I did not yet change the simple scheduler as well yet; maybe this isn't the
  final one either.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33965 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-11-09 19:00:42 +00:00
Michael Lotz
861b223cf2 * Strip down scheduler_simple. Anything related to multiple CPU handling has
been removed. That includes CPU disabling and thread pinning, as that becomes
  pointless with only one CPU.
* Return a proper reschedule hint on enqueing a thread, based on the priority
  of the current thread vs. the enqueued one.
* Enable dynamic scheduler selection. With one CPU the simple scheduler will
  be used, otherwise affine is selected.
* Removed the scheduler type define as we now always auto-select it.
* Some cleanup.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@32573 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-08-21 16:10:27 +00:00
Rene Gollent
009ccc2962 anevilyak+mmlr:
* scheduler_enqueue_in_runqueue() now allows the scheduler to return a hint as to whether a reschedule is desirable or not. This is used in a few other places in order to relegate scheduling decisions entirely to the scheduler rather than the priority hacks previously used. There are probably other places in the kernel that could now make use of that information to more intelligently call reschedule() though.
* Switch over the default scheduler to scheduler_affine().



git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@32554 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-08-21 04:11:40 +00:00
Michael Lotz
152132f08a mmlr+anevilyak:
* Keep track of the currently running threads.
* Make use of that info to decide if a thread that becomes ready should preempt
  the running thread.
* If we should preempt we send the target CPU a reschedule message.
* This preemption strategy makes keeping track of idle CPUs by means of a bitmap
  superflous and it is therefore removed.
* Right now only other CPUs are preempted though, not the current one.
* Add missing initialization of the quantum tracking code.
* Do not extend the quantum of the idle thread based quantum tracking as we want
  it to not run longer than necessary. Once the preemption works completely
  adding a quantum timer for the idle thread will become unnecessary though.
* Fix thread stealing code, it did missed the last thread in the run queue.
* When stealing, try to steal the highest priority thread that is currently
  waiting by taking priorities into account when finding the target run queue.
* Simplify stealing code a bit as well.
* Minor cleanups.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@32503 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-08-19 03:19:17 +00:00
Michael Lotz
100487755f We explicitly remove the thread from the (priority sorted) run queue to
re-insert it at a new place, but by only setting the priority and not the
next_priority field, the thread would actually be enqueued at the same priority
level as before. Didn't cause any real damage, guess it was just an oversight.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@32494 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-08-18 13:19:12 +00:00
Rene Gollent
f940f1e99c Initialize variable.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@32485 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-08-17 23:28:58 +00:00
Rene Gollent
494fe97976 Cleanups and some changes to avoid looping to compute the quantum average as suggested by Axel.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@32484 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-08-17 23:26:22 +00:00
Michael Lotz
699bf40942 Add scheduling notifications to scheduler_affine.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@32463 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-08-17 14:51:07 +00:00
Ingo Weinhold
6a1f462e72 * arch_debug_get_interrupt_pc() does now optionally return whether the iframe
is a syscall iframe.
* User debugger support: Don't to call BreakpointManager::PrepareToContinue(),
  if the thread returns from a syscall. We don't want to skip breakpoints in
  that case.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@31223 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-06-24 11:49:35 +00:00
Ingo Weinhold
227fe7d34a * Scheduler/wait object listener:
- Moved scheduler listening interface to <listeners.h> and added more
    convenient to use templatized notification functions.
  - Added a listener mechanism for the wait objects (semaphores, condition
    variables, mutex, rw_lock).
* system profiler:
  - Hopefully fixed locking issues related to notifying the profiler thread
    for good. We still had an inconsistent locking order, since the scheduler
    notification callbacks are invoked with the thread lock held and have to
    acquire the object lock then, while the other callbacks acquired the object
    lock first and as a side effect of ConditionVariable::NotifyOne() acquired
    the thread lock. Now we make sure the object lock is the innermost lock.
  - Track the number of dropped events due to a full buffer.
    _user_system_profiler_next_buffer() returns this count now.
  - When scheduling profiling events are requested also listen to wait objects
    and generate the respective profiling events. We send those events lazily
    and cache the infos to avoid resending an event for the same wait object.
  - When starting profiling we do now generate "thread scheduled" events for
    the already running threads.
  - _user_system_profiler_start(): Check whether the parameters pointer is a
    userland address at all.
  - The system_profiler_team_added event does now also contain the team's name.
* Added a sem_get_name_unsafe() returning a semaphore's name. It is "unsafe",
  since the caller has to ensure that the semaphore exists and continues to
  exist as long as the returned name is used.
* Adjusted the "profile" and "scheduling_recorder" according to the system
  profiling changes. The latter prints the number of dropped events, now.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@30345 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-04-23 13:47:52 +00:00
Ingo Weinhold
4a559f388b simple_enqueue_in_run_queue(): Between having found the insertion point and
manipulating the queue is a particularly unsuitable place for calling the
listeners, as they wouldn't be allowed to e.g. unblock threads, since that
would screw the run queue.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@30338 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-04-22 22:03:56 +00:00
Ingo Weinhold
79257a4ad6 Added a listener mechanism to the scheduler (ATM only for scheduler_simple).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@30242 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-04-18 17:24:58 +00:00
Ingo Weinhold
53e1017720 bonefish + mmlr:
* We started the "main2" thread too late. Since the scheduler was already
  started on all CPUs, the idle thread could wait (for a mutex) while
  spawing the "main2" thread. This violated the assumption in the scheduler
  that all idle threads would always be ready or running. We now create the
  thread while the kernel runs still single-threaded.
* scheduler_start() is now invoked with interrupts still disabled. We enable
  them after the function returns. This prevents scheduler_reschedule() from
  potentially being invoked before scheduler_start().


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@29914 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-04-04 23:54:01 +00:00
Rene Gollent
14df3c2bed Various tweaks - 1) while enqueued, keep track of which run queue a thread is in on the scheduler data structure, and use this information so that set_thread_priority doesn't have to search every CPU to find the thread. Also slightly tweak the enqueue and steal operations to take advantage of some of the stats we're now tracking, and experiment with variable quantum sizes for low priority CPU bound threads. Still lots of work to do with respect to balancing and/or affinity though.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@29857 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-04-02 03:13:55 +00:00
Rene Gollent
4cabb4a077 Integer precision is good enough for us here. Thanks Axel.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@29796 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-03-29 21:44:44 +00:00
Rene Gollent
6ad5d4edc0 dump_run_queue() now outputs the average quantum usage for threads as well. Not quite formatted properly due to what appear to be limitations in kprintf's handling of float format specifiers. Need to investigate.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@29789 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-03-29 18:11:28 +00:00
Rene Gollent
bd037e94a0 Track the number of threads in each CPU's runqueue.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@29786 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-03-29 17:14:52 +00:00
Rene Gollent
6c990aa4af Start tracking thread timeslice usage. Not actually used for any determinations just yet, but will be.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@29785 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-03-29 17:08:10 +00:00
Rene Gollent
dc707c28aa Small cleanup, no functional change.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@29784 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-03-29 16:53:38 +00:00
Rene Gollent
a27b5524c8 Fix code style violation (thanks Axel! ;-)
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@29733 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-03-26 15:26:15 +00:00
Rene Gollent
0296b82ae6 Add several extra scheduler hook functions to allow the scheduler(s) to maintain private housekeeping data on the thread structs. These hooks are called on thread creation/destruction and when prepping a thread for use. Review welcome.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@29721 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-03-26 00:58:20 +00:00
Rene Gollent
24fde47c7a Introduce an experimental new scheduler intended to work fundamentally the same as our existing one, but with various optimizations to better handle the SMP case:
1) We now maintain a runqueue per CPU, rather than a single global shared queue. Idle threads are segregated into their own queue for simplicity.
2) Enqueueing threads is now somewhat more intelligent - if the thread is pinned, it is always enqueued onto that core. Otherwise we enqueue it on whichever CPU it previously ran, unless it either hasn't run before, or that core has been disabled via ProcessController. If so, we try to enqueue it on whichever core has been the most idle recently.
3) The above allow various simplifications to thread scheduling. Pinned threads and/or disabled cores are now no longer special cases that need to be dealt with. If a CPU has no threads ready, it looks for another one to steal a thread from, though that part still needs some tuning along with enqueueing for load balancing purposes.

The chief aim here is better load balancing and support for soft affinity. However, at the moment the overall behavior still exhibits some regressions compared to the old scheduler, so it's disabled by default. If you wish to experiment/debug with it, instructions for enabling it can be found in scheduler.cpp. Much thanks to Ingo, Axel and everyone who's helped with either code review/advice or testing so far.



git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@29643 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-03-22 00:39:51 +00:00
Rene Gollent
3f71e54926 If a CPU is disabled, continue serving any threads still pinned. Otherwise disabling a CPU in ProcessController at an inopportune time will result in a total system deadlock. Might explain part of the problem in ticket #3535.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@29484 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-03-12 22:11:17 +00:00
Ingo Weinhold
53892c92a0 * Replaced scheduler_remove_from_run_queue() by
scheduler_set_thread_priority(). Setting the thread priority was the
  only situation in which it was used.
* Renamed scheduler.cpp to scheduler_simple.cpp.
* The scheduler functions are no longer called directly. Instead there's
  an operation vector now, which is initialized at kernel init time.
  This allows for picking the most suitable scheduler for the machine
  (e.g. a non-SMP scheduler on a non-SMP machine).


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28262 a95241bf-73f2-0310-859d-f6bbb57e9c96
2008-10-21 12:37:13 +00:00
Ingo Weinhold
1d1eb06e15 "lastTime" wasn't updated correctly when the thread was unscheduled.
"scheduler" would therefore print incorrect latencies.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28254 a95241bf-73f2-0310-859d-f6bbb57e9c96
2008-10-20 23:12:06 +00:00
Ingo Weinhold
768036bb6e Moved scheduler.cpp into new subdirectory scheduler/. Moved the
scheduler tracing and scheduler analysis code into separate source
files.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28253 a95241bf-73f2-0310-859d-f6bbb57e9c96
2008-10-20 22:57:40 +00:00