08c53ca964
Every time a page is mapped into an area on fault, we have to allocate a mapping object for it. While the object_cache does have per-CPU depots, these depots only store a limited number of items, and once they run out the object_cache's lock must be acquired. So, to reduce lock contention on SMP systems, create a number of object caches corresponding to the nearest power of 2 that is equal or smaller than the count of CPUs. (We already allocate dozens of object caches for the block allocator no matter how many CPUs there are, so a few more depending on CPU count shouldn't impact memory use too much. Besides, the object_caches are wired into the low_resource system.) This significantly reduces lock contention on SMP systems. Same benchmark setup as yesterday (compile mime_db and relink HaikuDepot, VMware, -j4), before: real 0m16.981s user 0m14.357s sys 0m6.060s after: real 0m14.522s user 0m14.194s sys 0m4.337s And the page_mappings object_cache locks went from having 200,000+ waits and ~14 seconds waiting time (across all threads) down to ~900 (yes, that's not a typo) and ~0.05s wait time (though these numbers were captured in conjunction with the following commit.)
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:
- https://xref.landonf.org/ (OpenGrok, provided by Landon Fuller)
- https://git.haiku-os.org/ (git, provided by Haiku, Inc.)
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.