Augustin Cavalier 02077ffc42 kernel/condition_variable: Atomicize ConditionVariableEntry and drop the lock.
Before 2019, the entire ConditionVariable system was "giant"-locked:
that is, there was a single global lock that all ConditionVariable
and ConditionVariableEntry operations had to pass through. This of
course was not very performant on multicore systems and when
ConditionVariables see significant use, so I reworked it then to have
more granular locking.

Those patches took a number of attempts to get right, as having two
objects in separate threads that can each access the other not turn
into a deadlock or use-after-free is not easy to say the least,
and the ultimate solution I came up with erased most of the performance
gains I initially saw on the first (partially broken) patchsets.

So I have wanted to revisit this and see if there was a better way
even since then. Recently there have been a few reports of
ConditionVariable-related panics (apparently double unlocks),
notably #16894, and so that was reason enough to actually revisit
this code and see if a better solution could be found.

Well, I think I have come up with one: after this commit, Entries
no longer have their own lock, and instead accesses to Entry members
are almost always atomic; and there is now a case where we spin inside
Variable::_NotifyLocked as well as one in Entry::_RemoveFromVariable.

This leads to somewhat simpler code (no more lock/unlock dance in Notify),
though it is significantly more difficult to understand the nuances of it,
so I have left a sizable number of comments explaining the intricacies
of the new logic.

Note: I initially tried 1000 for "tries", but on a few instances I did see
the panic hit, strangely. I don't think the code that is waited on can
be reasonably reduced any further, so I have just increased the limit to
10000 (which is still well below what spinlocks use.) Hopefully this suffices.

Quick benchmark, x86, compiling HaikuDepot and the mime_db in VMware, 2 cores:
before:
real    0m23.627s
user    0m25.152s
sys     0m7.319s

after:
real    0m23.962s
user    0m25.229s
sys     0m7.330s

Though I occasionally I saw sys times as low as 7.171s, so this seems
to be at least not a regression if not a definitive improvement.

Change-Id: Id042947976885cd5c1433cc4290bdf41b01ed10e
Reviewed-on: https://review.haiku-os.org/c/haiku/+/4727
Tested-by: Commit checker robot <no-reply+buildbot@haiku-os.org>
Reviewed-by: Alex von Gluck IV <kallisti5@unixzen.com>
2021-11-30 02:18:27 +00:00
2021-11-04 16:15:34 +00:00

Haiku

Homepage | Mailing Lists | IRC Channels | Issue Tracker | API docs

Haiku is an open-source operating system that specifically targets personal computing. Inspired by the BeOS, Haiku is fast, simple to use, easy to learn and yet very powerful.

Goals

  • Sensible defaults with minimal configuration required.
  • Clean, clear, concise code.
  • Unified desktop environment.

Trying Haiku

Haiku provides pre-built nightly images and release images. Haiku is compatible with a large variety of hardware, but in case you don't want to "take the plunge" and install Haiku on bare metal, you can install it on a virtual machine (VM) instead. If you've never used a VM before, you can follow one of the "Emulating Haiku" guides.

Compiling Haiku

See ReadMe.Compiling.

Contributing

Haiku is a meritocratic open source project with a large variety of tasks. Even if you can't write code, you can still help! Haiku needs designers, (technical) writers, translators, testers... Get involved and help out!

Contributing code

If you're submitting a patch to us, please make sure you're following the patch submitting guidelines.

If you're having trouble finding something in the source tree, you can use one of our web-based source code browsers:

Contributing documentation

The main piece of documentation that still needs work are the API docs (found in the tree at docs/user). Just find an undocumented class, write documentation for it, and submit a patch.

Contributing translations

See wiki:i18n.

Contributing software ports

See HaikuPorts.

Contributing to our infrastructure

See Infrastructure.

Description
The Haiku operating system
Readme 550 MiB
Languages
C++ 52.2%
C 46.6%
Assembly 0.4%
HTML 0.3%
Python 0.1%