This change fixes a bug where nsync waiter objects would leak. It'd mean
that long-running programs like runitd would run out of file descriptors
on NetBSD where waiter objects have ksem file descriptors. On other OSes
this bug is mostly harmless since the worst that can happen with a futex
is to leak a little bit of ram. The bug was caused because tib_nsync was
sneaking back in after the finalization code had cleared it. This change
refactors the thread exiting code to handle nsync teardown appropriately
and in making this change I found another issue, which is that user code
which is buggy, and tries to exit without joining joinable threads which
haven't been detached, would result in a deadlock. That doesn't sound so
bad, except the main thread is a joinable thread. So this deadlock would
be triggered in ways that put libc at fault. So we now auto-join threads
and libc will log a warning to --strace when that happens for any thread
This change doubles the performance of thread spawning. That's thanks to
our new stack manager, which allows us to avoid zeroing stacks. It gives
us 15µs spawns rather than 30µs spawns on Linux. Also, pthread_exit() is
faster now, since it doesn't need to acquire the pthread GIL. On NetBSD,
that helps us avoid allocating too many semaphores. Even if that happens
we're now able to survive semaphores running out and even memory running
out, when allocating *NSYNC waiter objects. I found a lot more rare bugs
in the POSIX threads runtime that could cause things to crash, if you've
got dozens of threads all spawning and joining dozens of threads. I want
cosmo to be world class production worthy for 2025 so happy holidays all
This change reduces o/tiny/examples/life from 44kb to 24kb in size since
it avoids linking mmap() when unnecessary. This is important, to helping
cosmo not completely lose touch with its roots.
We now have a C++ red-black tree implementation that implements standard
template library compatible APIs while compiling 10x faster than libcxx.
It's not as beautiful as the red-black tree implementation in Plinko but
this will get the job done and the test proves it upholds all invariants
This change also restores CheckForMemoryLeaks() support and fixes a real
actual bug I discovered with Doug Lea's dlmalloc_inspect_all() function.
If pthread_create() is linked into the binary, then the cosmo runtime
will create an independent dlmalloc arena for each core. Whenever the
malloc() function is used it will index `g_heaps[sched_getcpu() / 2]`
to find the arena with the greatest hyperthread / numa locality. This
may be configured via an environment variable. For example if you say
`export COSMOPOLITAN_HEAP_COUNT=1` then you can restore the old ways.
Your process may be configured to have anywhere between 1 - 128 heaps
We need this revision because it makes multithreaded C++ applications
faster. For example, an HTTP server I'm working on that makes extreme
use of the STL went from 16k to 2000k requests per second, after this
change was made. To understand why, try out the malloc_test benchmark
which calls malloc() + realloc() in a loop across many threads, which
sees a a 250x improvement in process clock time and 200x on wall time
The tradeoff is this adds ~25ns of latency to individual malloc calls
compared to MODE=tiny, once the cosmo runtime has transitioned into a
fully multi-threaded state. If you don't need malloc() to be scalable
then cosmo provides many options for you. For starters the heap count
variable above can be set to put the process back in single heap mode
plus you can go even faster still, if you include tinymalloc.inc like
many of the programs in tool/build/.. are already doing since that'll
shave tens of kb off your binary footprint too. Theres also MODE=tiny
which is configured to use just 1 plain old dlmalloc arena by default
Another tradeoff is we need more memory now (except in MODE=tiny), to
track the provenance of memory allocation. This is so allocations can
be freely shared across threads, and because OSes can reschedule code
to different CPUs at any time.
This change adds a TLS freelist for small dynamic memory allocations.
Cosmopolitan's TIB is now 512 bytes in size. Single-threaded malloc()
performance isn't impacted by this, until pthread_create() is called.
Single-threaded programs may also want to consider using:
#include "libc/mem/tinymalloc.inc"
Which will shave 30k off the executable size and sometimes go faster.
Renaming gc() to _gc() was a mistake since the better thing to do is put
it behind the _COSMO_SOURCE macro. We need this change because I haven't
wanted to use my amazing garbage collector ever since we renamed it. You
now need to define _COSMO_SOURCE yourself when using amalgamation header
and cosmocc users need to pass the -mcosmo flag to get the gc() function
Some other issues relating to cancelation have been fixed along the way.
We're also now putting cosmocc in a folder named `.cosmocc` so it can be
more safely excluded by grep --exclude-dir=.cosmocc --exclude-dir=o etc.
At least in neovim, `│vi:` is not recognized as a modeline because it
has no preceding whitespace. After fixing this, opening a file yields
an error because `net` is not an option. (`noet`, however, is.)
We now have an `#include <cxxabi.h>` header which defines all the APIs
Cosmopolitan's implemented so far. The `cosmocc` README.md file is now
greatly expanded with documentation.
- We now serialize the file descriptor table when spawning / executing
processes on Windows. This means you can now inherit more stuff than
just standard i/o. It's needed by bash, which duplicates the console
to file descriptor #255. We also now do a better job serializing the
environment variables, so you're less likely to encounter E2BIG when
using your bash shell. We also no longer coerce environ to uppercase
- execve() on Windows now remotely controls its parent process to make
them spawn a replacement for itself. Then it'll be able to terminate
immediately once the spawn succeeds, without having to linger around
for the lifetime as a shell process for proxying the exit code. When
process worker thread running in the parent sees the child die, it's
given a handle to the new child, to replace it in the process table.
- execve() and posix_spawn() on Windows will now provide CreateProcess
an explicit handle list. This allows us to remove handle locks which
enables better fork/spawn concurrency, with seriously correct thread
safety. Other codebases like Go use the same technique. On the other
hand fork() still favors the conventional WIN32 inheritence approach
which can be a little bit messy, but is *controlled* by guaranteeing
perfectly clean slates at both the spawning and execution boundaries
- sigset_t is now 64 bits. Having it be 128 bits was a mistake because
there's no reason to use that and it's only supported by FreeBSD. By
using the system word size, signal mask manipulation on Windows goes
very fast. Furthermore @asyncsignalsafe funcs have been rewritten on
Windows to take advantage of signal masking, now that it's much more
pleasant to use.
- All the overlapped i/o code on Windows has been rewritten for pretty
good signal and cancelation safety. We're now able to ensure overlap
data structures are cleaned up so long as you don't longjmp() out of
out of a signal handler that interrupted an i/o operation. Latencies
are also improved thanks to the removal of lots of "busy wait" code.
Waits should be optimal for everything except poll(), which shall be
the last and final demon we slay in the win32 i/o horror show.
- getrusage() on Windows is now able to report RUSAGE_CHILDREN as well
as RUSAGE_SELF, thanks to aggregation in the process manager thread.
Thanks to @autumnjolitz (in #876) the Cosmopolitan codebase is now
acquainted with Apple's outstanding ulock system calls which offer
something much closer to futexes than Grand Central Dispatch which
wasn't quite as good, since its wait function can't be interrupted
by signals (therefore necessitating a busy loop) and it also needs
semaphore objects to be created and freed. Even though ulock is an
internal Apple API, strictly speaking, the benefits of futexes are
so great that it's worth the risk for now especially since we have
the GCD implementation still as a quick escape hatch if it changes
Here's why this change is important for x86 XNU users. Cosmo has a
suboptimal polyfill when the operating system doesn't offer an API
that let's us implement futexes properly. Sadly we had to use that
on X86 XNU until now. The polyfill works using clock_nanosleep, to
poll the futex in a busy loop with exponential backoff. On XNU x86
clock_nanosleep suffers from us not being able to use a fast clock
gettime implementation, which had a compounding effect that's made
the polyfill function even more poorly. On X86 XNU we also need to
polyfill sched_yield() using select(), which made things even more
troublesome. Now that we have futexes we don't have any busy loops
anymore for both condition variables and thread joining so optimal
performance is attained. To demonstrate, consider these benchmarks
Before:
$ ./lockscale_test.com -b
consumed 38.8377 seconds real time and
0.087131 seconds cpu time
After:
$ ./lockscale_test.com -b
consumed 0.007955 seconds real time and
0.011515 seconds cpu time
Fixes#876
- This change fixes a bug that allowed unbuffered printf() output (to
streams like stderr) to be truncated. This regression was introduced
some time between now and the last release.
- POSIX specifies all functions as thread safe by default. This change
works towards cleaning up our use of the @threadsafe / @threadunsafe
documentation annotations to reflect that. The goal is (1) to use
@threadunsafe to document functions which POSIX say needn't be thread
safe, and (2) use @threadsafe to document functions that we chose to
implement as thread safe even though POSIX didn't mandate it.
- Tidy up the clock_gettime() implementation. We're now trying out a
cleaner approach to system call support that aims to maintain the
Linux errno convention as long as possible. This also fixes bugs that
existed previously, where the vDSO errno wasn't being translated
properly. The gettimeofday() system call is now a wrapper for
clock_gettime(), which reduces bloat in apps that use both.
- The recently-introduced improvements to the execute bit on Windows has
had bugs fixed. access(X_OK) on a directory on Windows now succeeds.
fstat() will now perform the MZ/#! ReadFile() operation correctly.
- Windows.h is no longer included in libc/isystem/, because it confused
PCRE's build system into thinking Cosmopolitan is a WIN32 platform.
Cosmo's Windows.h polyfill was never even really that good, since it
only defines a subset of the subset of WIN32 APIs that Cosmo defines.
- The setlongerjmp() / longerjmp() APIs are removed. While they're nice
APIs that are superior to the standardized setjmp / longjmp functions,
they weren't superior enough to not be dead code in the monorepo. If
you use these APIs, please file an issue and they'll be restored.
- The .com appending magic has now been removed from APE Loader.
- Every unit test now passes on Apple Silicon. The final piece of this
puzzle was porting our POSIX threads cancelation support, since that
works differently on ARM64 XNU vs. AMD64. Our semaphore support on
Apple Silicon is also superior now compared to AMD64, thanks to the
grand central dispatch library which lets *NSYNC locks go faster.
- The Cosmopolitan runtime is now more stable, particularly on Windows.
To do this, thread local storage is mandatory at all runtime levels,
and the innermost packages of the C library is no longer being built
using ASAN. TLS is being bootstrapped with a 128-byte TIB during the
process startup phase, and then later on the runtime re-allocates it
either statically or dynamically to support code using _Thread_local.
fork() and execve() now do a better job cooperating with threads. We
can now check how much stack memory is left in the process or thread
when functions like kprintf() / execve() etc. call alloca(), so that
ENOMEM can be raised, reduce a buffer size, or just print a warning.
- POSIX signal emulation is now implemented the same way kernels do it
with pthread_kill() and raise(). Any thread can interrupt any other
thread, regardless of what it's doing. If it's blocked on read/write
then the killer thread will cancel its i/o operation so that EINTR can
be returned in the mark thread immediately. If it's doing a tight CPU
bound operation, then that's also interrupted by the signal delivery.
Signal delivery works now by suspending a thread and pushing context
data structures onto its stack, and redirecting its execution to a
trampoline function, which calls SetThreadContext(GetCurrentThread())
when it's done.
- We're now doing a better job managing locks and handles. On NetBSD we
now close semaphore file descriptors in forked children. Semaphores on
Windows can now be canceled immediately, which means mutexes/condition
variables will now go faster. Apple Silicon semaphores can be canceled
too. We're now using Apple's pthread_yield() funciton. Apple _nocancel
syscalls are now used on XNU when appropriate to ensure pthread_cancel
requests aren't lost. The MbedTLS library has been updated to support
POSIX thread cancelations. See tool/build/runitd.c for an example of
how it can be used for production multi-threaded tls servers. Handles
on Windows now leak less often across processes. All i/o operations on
Windows are now overlapped, which means file pointers can no longer be
inherited across dup() and fork() for the time being.
- We now spawn a thread on Windows to deliver SIGCHLD and wakeup wait4()
which means, for example, that posix_spawn() now goes 3x faster. POSIX
spawn is also now more correct. Like Musl, it's now able to report the
failure code of execve() via a pipe although our approach favors using
shared memory to do that on systems that have a true vfork() function.
- We now spawn a thread to deliver SIGALRM to threads when setitimer()
is used. This enables the most precise wakeups the OS makes possible.
- The Cosmopolitan runtime now uses less memory. On NetBSD for example,
it turned out the kernel would actually commit the PT_GNU_STACK size
which caused RSS to be 6mb for every process. Now it's down to ~4kb.
On Apple Silicon, we reduce the mandatory upstream thread size to the
smallest possible size to reduce the memory overhead of Cosmo threads.
The examples directory has a program called greenbean which can spawn
a web server on Linux with 10,000 worker threads and have the memory
usage of the process be ~77mb. The 1024 byte overhead of POSIX-style
thread-local storage is now optional; it won't be allocated until the
pthread_setspecific/getspecific functions are called. On Windows, the
threads that get spawned which are internal to the libc implementation
use reserve rather than commit memory, which shaves a few hundred kb.
- sigaltstack() is now supported on Windows, however it's currently not
able to be used to handle stack overflows, since crash signals are
still generated by WIN32. However the crash handler will still switch
to the alt stack, which is helpful in environments with tiny threads.
- Test binaries are now smaller. Many of the mandatory dependencies of
the test runner have been removed. This ensures many programs can do a
better job only linking the the thing they're testing. This caused the
test binaries for LIBC_FMT for example, to decrease from 200kb to 50kb
- long double is no longer used in the implementation details of libc,
except in the APIs that define it. The old code that used long double
for time (instead of struct timespec) has now been thoroughly removed.
- ShowCrashReports() is now much tinier in MODE=tiny. Instead of doing
backtraces itself, it'll just print a command you can run on the shell
using our new `cosmoaddr2line` program to view the backtrace.
- Crash report signal handling now works in a much better way. Instead
of terminating the process, it now relies on SA_RESETHAND so that the
default SIG_IGN behavior can terminate the process if necessary.
- Our pledge() functionality has now been fully ported to AARCH64 Linux.
This change ports APE Loader to Linux AARCH64, so that Raspberry Pi
users can run programs like redbean, without the executable needing
to modify itself. Progress has also slipped into this change on the
issue of making progress better conforming to user expectations and
industry standards regarding which symbols we're allowed to declare
The *NSYNC linked list API is good enough that it deserves to be part of
the C libray, so this change writes an improved version of it which uses
that offsetof() trick from the Linux Kernel. We vendor all of the *NSYNC
tests in third_party which helped confirm the needed refactoring is safe
This change also deletes more old code that didn't pan out. My goal here
is to work towards a vision where the Cosmopolitan core libraries become
less experimental and more focused on curation. This better reflects the
current level of quality we've managed to achieve.
This change integrates e58abc1110b335a3341e8ad5821ad8e3880d9bb2 from
https://github.com/ahgamut/musl-cross-make/ which fixes the issues we
were having with our C language extension for symbolic constants. This
change also performs some code cleanup and bug fixes to getaddrinfo().
It's now possible to compile projects like ncurses, readline and python
without needing to patch anything upstream, except maybe a line or two.
Pretty soon it should be possible to build a Linux distro on Cosmo.
This change adds a double linked list of threads, so that pthread_exit()
will know when it should call exit() from an orphaned child. This change
also improves ftrace and strace logging.
- ASAN memory morgue is now lockless
- Make C11 atomics header more portable
- Rewrote pthread keys support to be lockless
- Simplify Python's unicode table unpacking code
- Make crash report write(2) closer to being atomic
- Make it possible to strace/ftrace a single thread
- ASAN now checks nul-terminated strings fast and properly
- Windows fork() now restores TLS memory of calling thread
This change addresses various open source compatibility issues, so that
we pass 313/411 of the tests in https://github.com/jart/libc-test where
earlier today we were passing about 30/411 of them, due to header toil.
Please note that Glibc only passes 341/411 so 313 today is pretty good!
- Make the conformance of libc/isystem/ headers nearly perfect
- Import more of the remaining math library routines from Musl
- Fix inconsistencies with type signatures of calls like umask
- Write tests for getpriority/setpriority which work great now
- conform to `struct sockaddr *` on remaining socket functions
- Import a bunch of uninteresting stdlib functions e.g. rand48
- Introduce readdir_r, scandir, pthread_kill, sigsetjmp, etc..
Follow the instructions in our `tool/scripts/cosmocc` toolchain to run
these tests yourself. You use `make CC=cosmocc` on the test repository
- fix rare thread exit race condition on openbsd
- pthread_getattr_np() now supplies detached status
- child threads may now pthread_join() the main thread
- introduce sigandset(), sigorset(), and sigisemptyset()
- introduce pthread_cleanup_push() and pthread_cleanup_pop()
This makes breaking changes to add underscores to many non-standard
function names provided by the c library. MODE=tiny is now tinier and
we now use smaller locks that are better for tiny apps in this mode.
Some headers have been renamed to be in the same folder as the build
package, so it'll be easier to know which build dependency is needed.
Certain old misguided interfaces have been removed. Intel intrinsics
headers are now listed in libc/isystem (but not in the amalgamation)
to help further improve open source compatibility. Header complexity
has also been reduced. Lastly, more shell scripts are now available.
The organization of the source files is now much more rational.
Old experiments that didn't work out are now deleted. Naming of
things like files is now more intuitive.
- You can now use _gc(malloc()) in multithreaded programs
- This change fixes a bug where fork() on NT disabled TLS
- Fixed TLS code morphing on XNU/NT, for R8-R15 registers
