Commit Graph

3479 Commits

Author SHA1 Message Date
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
a73382f7bb * uninit_port_locked(): Fixed incorrect use of ConditionVariable::NotifyAll().
Fixes #5152.
* _get_port_message_info_etc(): Check whether the port still exists and is not
  closed and empty in the loop. Though actually it shouldn't be necessary
  (same in the other functions), since Wait() would return an error, if the
  port was closed/deleted. Well, paranoia... :-)


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34713 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-12-20 00:31:37 +00:00
Ingo Weinhold
7382f82116 Should have been part of an earlier commit: Initialize the IOSchedulerRoster.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34705 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-12-19 14:35:05 +00:00
Ingo Weinhold
f36ea5de1b Should have been part of the previous commit: Include directory for the I/O
scheduling event support.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34704 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-12-19 14:34:24 +00:00
Ingo Weinhold
189010cbc2 Added support for I/O scheduling events to the system profiler interface.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34703 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-12-19 14:33:29 +00:00
Ingo Weinhold
ca77afe75f * Implemented missing cleanup when an IOScheduler is destroyed. The threads
weren't terminated orderly.
* IOScheduler now stores its name and gets a unique ID.
* Added IOSchedulerRoster singleton which registers all IOSchedulers. It also
  provides a notification service. We generate interesting events for
  IOSchedulers, IORequests, and IOOperations.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34702 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-12-19 14:32:14 +00:00
Ingo Weinhold
410ba11f8c read_port_etc():
* Also check whether the port is closed after waiting.
* Don't increment read_count after waiting failed. That should have been the
  cause of #5119.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34687 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-12-17 12:21:05 +00:00
Ingo Weinhold
c3bc71d6e2 Removed superfluous ConditionVariableEntry::WaitStatus() checks. Wait() always
returns the correct value.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34686 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-12-17 11:06:16 +00:00
Ingo Weinhold
3ffeff0770 port_writev_etc(): Missing check whether the port has been closed after
waiting.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34685 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-12-17 10:51:05 +00:00
Axel Dörfler
7d592ec4d2 * Fixed the bug that led to #5119. There was a race condition in the read path
as soon as a second thread got into the game: if a thread was notified that
  a message is ready, another thread could call read_port() and steal it before
  the previous thread could claim it. The "Extensions" menu still doesn't seem
  to work, but I would guess that is unrelated.
* The threads of the test app never exited, as read_port() returns the number
  of bytes it read, not just a status.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34681 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-12-16 12:51:26 +00:00
Fredrik Holmqvist
118fa8936e Make sure settings isn't null. Not my finest day apparently.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34679 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-12-15 22:19:08 +00:00
Fredrik Holmqvist
0f6b7a8cad Unload driver settings as well.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34678 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-12-15 22:05:45 +00:00
Fredrik Holmqvist
d403ff624f Style fix:
* static variables should start with s.
 * function blocks should start on new line.



git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34668 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-12-15 17:00:03 +00:00
Fredrik Holmqvist
5e972c0f3d Implemented TODO about not loading symbols at boot.
This saves ~0.5s of boot time here, but I suspect it might be better for CD.
Enabled loadSymbols in kernel settings so the behavior should be the same as before this change.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34666 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-12-15 15:55:16 +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
Ingo Weinhold
89e87505cf Improved panic() message.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34656 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-12-13 21:03:48 +00:00
Ingo Weinhold
2f7eb9b546 Fixed a stupid race condition between IORequest finishing and
IORequest::Wait(). Wait() immediately returned when IsFinished() returned
true, but this is the case as soon as the last IOOperation has finished. The
I/O scheduler is not done with the request at this point, though, since it
will still be sitting in at least one of three doubly linked lists. Since the
usual procedure to issue synchronous I/O requests is to create an IORequest
on the stack, pass it to the I/O scheduler, and Wait() on it, Wait()
returning early might cause the IORequest object to be destroyed while it is
still in use, leading to invalid memory access in the I/O scheduler,
corruption of its list structures, as well as later corruption of the issuing
thread's stack.
Related tickets:
* #4431: The request issuing thread returned and already deleted the area the
  request was writing to before NotifyFinished() was called.
* #3048, #4883: Caused by the on stack IORequest being overwritten with other
  data while being handled by the I/O scheduler thread.
* #4517: Hard to say, but I've seen a such a problem too, after a thread
  scheduling related change. An explanation would be a list structure
  corruption in the I/O scheduler causing an infinite loop with disabled
  interrupts.
* #2845, #3428, #3429: The block notifier/writer is I/O heavy and as such
  quite likely to run into the stack corruption issue.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34655 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-12-13 19:28:33 +00:00
Jérôme Duval
d0c1951713 added fmin, fma, fmax from glibc (ticket #5114).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34652 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-12-13 14:22:13 +00:00
Axel Dörfler
a195cce7b5 * Added a bit more missing info about user_threads.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34647 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-12-12 19:08:04 +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
Ingo Weinhold
10b4833178 When any of the executed timer hooks return B_INVOKE_SCHEDULER, let
timer_interrupt() return B_INVOKE_SCHEDULER. The scheduler itself uses a
timer hook and relies on scheduler_reschedule() to be called. Will make this
even more reliable in the next commit.
This might fix #3535.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34614 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-12-10 11:29:38 +00:00
Axel Dörfler
2388f50c53 * The io_handler::handled_count was increased unconditionally, but in some cases
not at all.
* Tried to improve the readability of the "ints" command output.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34613 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-12-10 11:14:46 +00:00
Axel Dörfler
33c82a30c0 * While reading in a block, the block is now marked busy, and the cache
unlocked, allowing for more parallel access.
* Writing is still done synchronously, though.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34611 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-12-10 10:29:37 +00:00
Axel Dörfler
1339ccf411 * Enforce that the caller of transfer_area() owns the area - this fixes some
mean crashes with the media_server version I just checked in.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34556 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-12-08 15:28:44 +00:00
Ingo Weinhold
d8d4b902cb * The system profiler scheduling event structures sport nanotime_ts now.
* Adjusted the DebugAnalyzer to handle nanosecond times.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34546 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-12-07 22:56:29 +00:00
Ingo Weinhold
b2a2d5c065 The usual files forgotten to commit. The generic system_time_nsecs()
implementation.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34545 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-12-07 22:53:53 +00:00
Ingo Weinhold
34a48c70ef Added type nanotime_t (an int64 storing a nanoseconds value) and function
system_time_nsecs(), returning the system time in nanoseconds. The function
is only really implemented for x86. For the other architectures
system_time() * 1000 is returned.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34543 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-12-07 21:43:19 +00:00
Ingo Weinhold
db905187d5 Implemented a class uint128 with the basic arithmetic operations and
replaced the previous, somewhat complicated and inexact method of
computing the TSC conversion factor using it.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34542 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-12-07 21:37:56 +00:00
Ingo Weinhold
522c2f19d4 * Added a simple mechanism to wait for events to VMCache. WaitForPageEvents()
waits for certain events on a given page, NotifyPageEvents() wakes up
  waiting threads respectively.
* Used the new feature instead of condition variables for waiting on busy
  pages. We save publishing and unpublishing of a condition variable whenever
  a page is marked busy. There's only something to do, if there's at least
  one thread waiting in the list of the respective cache. The general
  assumption is that this is only rarely the case and even if it happens,
  there should be only very few threads.
* Added an apparently missing notification in cache_io(). At least I didn't
  see the reason for it not being there.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34537 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-12-07 15:42:08 +00:00
Ingo Weinhold
be7328a9f6 Moved VMCache related definitions to <vm/VMCache.h>.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34535 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-12-07 14:14:21 +00:00
Ingo Weinhold
bcfdfff497 Added 64 bit TODO. We'll probably have to change the interface (cookie type)
of get_next_area_info() and others.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34533 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-12-07 12:26:26 +00:00
Ingo Weinhold
40cd019ea0 * Renamed VMAddressSpace::ResizeArea{Head,Tail}() to ShrinkArea{Head,Tail}()
to clarify that they never enlarge the area.
* Reimplemented VMKernelAddressSpace. It is somewhat inspired by Bonwick's
  vmem resource allocator (though we have different requirements):
  - We consider the complete address space to be divided into contiguous
    ranges of type free, reserved, or area, each range being represented by
    a VMKernelAddressRange object.
  - The range objects are managed in an AVL tree and a doubly linked list
    (the latter only for faster iteration) sorted by address. This provides
    O(log(n)) lookup, insertion and removal.
  - For each power of two size we maintain a list of free ranges of at least
    that size. Thus for the most common case of B_ANY*_ADDRESS area
    allocation, we find a free range in constant time (the rest of the
    processing being O(log(n))) with a rather good fit. This should also
    help avoiding address space fragmentation.
  While the new implementation should be faster, particularly with an
  increasing number of areas, I couldn't measure any difference in the -j2
  haiku build. From a cursory test the -j8 build hasn't tangibly benefitted
  either.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34528 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-12-06 17:18:04 +00:00
Ingo Weinhold
fe30b74fde Fix for stack traces in the early boot process: The thread might not have
its stack top/bottom assigned yet.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34527 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-12-06 16:01:21 +00:00
Ingo Weinhold
a54549a8cd * AVLTree:
- Renamed to AVLTreeBase and moved it into its own header/source file.
  - Renamed FindClose() to FindClosest().
  - Added CheckTree() method for debugging purposes. It checks the validity
    of the tree.
* Added a templatized class AVLTree which doesn't offer a map-like interface
  like AVLTreeMap, but rather one similar to BOpenHashMap and SplayTree. It
  is more convenient to use, if one wants to store objects that already
  contain the key.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34526 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-12-06 15:59:37 +00:00
Ingo Weinhold
08d9b6d462 Obvious copy and paste left-over. Totally missed it as I've been testing
the wrong image for quite a while. :-/


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34494 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-12-04 21:32:00 +00:00
Ingo Weinhold
2c1886aeae * Added VMArea subclasses VM{Kernel,User}Area and moved the address space list
link to them.
* VM{Kernel,User}AddressSpace manage the respective VMArea subclass now, and
  VMAddressSpace has grown factory methods {Create,Delete}Area.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34493 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-12-04 17:07:16 +00:00
Ingo Weinhold
e2518ddbb1 Made VMAddressSpace an abstract base class and moved the area management into
new derived classes VM{Kernel,User}AddressSpace. Currently those are
identical, but that will change.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34492 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-12-04 14:45:08 +00:00
Ingo Weinhold
38a97b2c36 Moved all knowledge of reserved areas from vm.cpp to VMAddressSpace. It's a
pure address space feature, so it should be handled there.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34491 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-12-04 13:33:25 +00:00
Ingo Weinhold
f69032f22b * Added VMAddressSpace::ResizeArea{Head,Tail}() to adjust an area's base
and size.
* Made VMArea::Set{Base,Size}() private and made VMAddressSpace a friend.
  In vm.cpp the new VMAddressSpace::ResizeArea{Head,Tail}() are used
  instead.
Finally all address space changes happen in VMAddressSpace only. *phew*
Now it's ready to be thoroughly butchered. :-)


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34467 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-12-03 15:21:18 +00:00
Ingo Weinhold
bbd97b4bb4 Made the VMArea fields base and size private and added accessors instead.
This makes it more explicit where the fields are modified.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34464 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-12-03 14:18:24 +00:00
Colin Günther
af983c175d Coding style cleanups. Thanks axeld.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34462 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-12-03 13:05:39 +00:00
Ingo Weinhold
35d940014e * Changed the address space area list to doubly linked. The reason is to
simplify migration of the area management, but as a side effect, it also
  makes area deletion O(1) (instead of O(n), n == number of areas in the
  address space).
* Moved more area management functionality from vm.cpp to VMAddressSpace and
  VMArea structure creation to VMArea. Made the list and list link members
  itself private.
* VMAddressSpace tracks its amount of free space, now. This also replaces
  the previous mechanism to do that only for the kernel address space. It
  was broken anyway, since delete_area() subtracted the area size instead of
  adding it.
* vm_free_unused_boot_loader_range():
  - lastEnd could be set to a value < start, which could cause memory
    outside of the given range to be unmapped. Haven't checked whether this
    could happen in practice -- if so, it would be seriously unhealthy.
  - The range between the end of the last area in the range and the end of
    the range would never be freed.
  - Fixed potential integer overflows when computing addresses.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34459 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-12-03 12:41:11 +00:00
Colin Günther
1581b764e0 * Adding static Notify{One,All} functions. This allows a cleaner implementation
of the condition variable and synchronization subsystem of the freebsd compat
  layer which will be committed next.
* Also there was a discussion about adding these functions on the commit
  mailing list. The mail in http://www.freelists.org/post/haiku-commits/r34395-in-haikutrunksrclibscompatfreebsd-network-compatsys,3
  is a good sum up of it (need to scroll somewhat down, though).


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34458 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-12-03 12:24:17 +00:00
Ingo Weinhold
def9898c9b Moved the three address space locker classes into a separate pair of
header/source files.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34451 a95241bf-73f2-0310-859d-f6bbb57e9c96
2009-12-02 20:16:31 +00:00