Windows is only sending low-memory notifications when the machine
is reaching low-memory. So running a 32bit process on 64bit machine
can easily exhaust address space before machine gets close to
low-memory.
The low-memory notification was getting into an infinite loop. This
fixes the loop termination, and provides a test for platforms which
support low-memory notification.
* Removing option as not supported by CI
Will migrate CI forward and readd.
* Made failure for clang-format errors.
* Improved handling of errors during CI.
* Prevent failures escaping.
* Clang-format fix
* Remove stderr
* Update azure-pipelines.yml
Co-Authored-By: Paul Liétar <plietar@users.noreply.github.com>
Co-authored-by: Paul Liétar <plietar@users.noreply.github.com>
The performance on Windows was significantly regressed by the
notify_using during the bump allocation. This change removes that.
It appears that the pages are already committed by
the large allocator.
Fixes a few places where Clang complains about Windows specific code,
and also uses macros supported by Clang on Windows. A few places
separating platform and compiler specific code, as MSVC and WIN32 were
used interchangably previously.
* add rust support
* move aligned_size to sizeclass.h
* add static qualifier
* adjust CMakeLists.txt, may broke CI tests
* fix msvc's complaining on c++17
* use SNMALLOC_FAST_PATH as the decorator of aligned_size
* adapt new alignment algorithm and add related test
Co-authored-by: mjp41 <mattpark@microsoft.com>
* fix test cases for msvc
* add extra test for size == 0
* treat memory block of same sizeclass as the same
* fix formatting problem
* remove extra declarations
Co-authored-by: Matthew Parkinson <mjp41@users.noreply.github.com>
For languages like Verona or Rust, the deallocation calls know the
size of the object originally requested. This change optimises that
code path to create a much better fast path.
Previous implementation of aligned_alloc met the specification, but was
not particularly useful. This uses the same implementation for
alligned_alloc and memalign.
For architectures that can't manipulate pointers like integers, don't
try XORing them like this. It's not ideal -- perhaps we should have
"else" branches to these tests.
`load` does not load (`read` and `compare_exchange` do) so give it a
different name. For the cases where `ptr` was previously the pointer we
were guarding, rename it to `raw`.
If the test happens as uintptr_t on CHERI, then we attempt to construct
a capability and use a capability-based test rather than an
integer-based one, and things go south.
posix_memalign requires that the alignment parameter be a multiple of
sizeof(uintptr_t), but the test begins with alignments as small as
sizeof(size_t). While those are very likely the same value out in the
wild right now, they're not on CHERI.
Begin the test loop at sizeof(uintptr_t) and add a test that a request
for a reasonable amount of memory but with an alignment of
sizeof(uintptr_t)/2 fails with EINVAL.
There are two things calling themselves pagemaps:
- the src/mem/pagemap.h objects of that name
- the SuperslabMap object gets called a PageMap inside the Allocator
Rename the latter to chunkmap, with appropriate case and snake,
everywhere, and pull it out to its own file (chunkmap.h).
The default implementation of a chunkmap is a purely static object, but
we nevertheless instantiate it per allocator, so that other
implementations can use stateful instances when interposing on the
mutation methods. Note that the "get" method, however, must remain
static to support the interface required by Allocator objects.
