mirror of
https://github.com/fluencelabs/musl
synced 2025-04-24 23:02:14 +00:00
this bug probably would have gone unnoticed since it's only used in the fallback code for systems where priority-inheritance locking fails. unfortunately this approach results in one spurious wake syscall on the final unlock, when there are no waiters remaining. the alternative (possibly better) would be to use broadcast wakes instead of reflagging the waiter unconditionally, and let each waiter reflag itself; this saves one syscall at the expense of invoking the "thundering herd" effect (worse performance degredation) when there are many waiters. ideally we would be able to update all of our locks to use an array of two ints rather than a single int, and use a separate counter system like proper mutexes use; then we could avoid all spurious wake calls without resorting to broadcasts. however, it's not clear to me that priority inheritance futexes support this usage. the kernel sets the waiters flag for them (just like we're doing now) and i can't tell if it's safe to bypass the kernel when unlocking just because we know (from private data, the waiter count) that there are no waiters. this is something that could be explored in the future.
musl libc - a new standard library to power a new generation of Linux-based devices. musl is lightweight, fast, simple, free, and strives to be correct in the sense of standards-conformance and safety. musl is an alternative to glibc, eglibc, uClibc, dietlibc, and klibc. For reasons why one might prefer musl, please see the FAQ and libc comparison chart on the project website, http://www.etalabs.net/musl/ For installation instructions, see the INSTALL file. Please refer to the COPYRIGHT file for details on the copyright status of code included in musl, and the COPYING file for the license (LGPL) under which the library as a whole is distributed. Greetings! As of the 0.8.0 release, musl is in _beta_ status. While some interfaces remain incomplete or yet to be implemented, the ABI is intended to be stable at this point, and serious efforts have been made, using three separate test frameworks, to verify the correctness of the implementation. Many major system-level and user-level programs are known to work with musl, either out-of-the-box or with minor patches to address portability errors. Included with this package is a gcc wrapper script (musl-gcc) which allows you to build musl-linked programs using an existing gcc 4.x toolchain on the host. There are also now at least two mini distributions (in the form of build scripts) which provide a self-hosting musl-based toolchain and system root: Sabotage Linux and Bootstrap Linux. These are much better options than the wrapper script if you wish to use dynamic linking or build packages with many library dependencies. The musl project is actively seeking contributors, mostly in the areas of porting, testing, and application compatibility improvement. For bug reports, support requests, or to get involved in development, please visit #musl on Freenode IRC or subscribe to the musl mailing list by sending a blank email to musl-subscribe AT lists DOT openwall DOT com. Thank you for using musl. Cheers, Rich Felker / dalias
Description
Languages
C
92%
Assembly
4.2%
JavaScript
1.5%
C++
1%
Awk
0.4%
Other
0.9%