Improve slow path performance for allocation #143
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Change remote to count down 0, so fast path does not need a constant. Use signed value so that branch does not depend on addition.
The fast path of remote_dealloc is sufficiently compact that it can be inlined.
Turn the internal structure into tail calls, to improve fast path. Should be no algorithmic changes.
Break lazy initialisation into two functions, so it is easier to codegen fast paths.
Make the backup path a bit faster. Only algorithmic change is to delay checking for first allocation. Otherwise, should be unchanged.
The fisrt operation a new thread takes is special. It results in allocating an allocator, and swinging it into the TLS. This makes this a very special path, that is rarely tested. This test generates a lot of threads to cover the first alloc and dealloc operations.
Large alloc stats aren't necessarily balanced on a thread, this changes to tracking individual pushs and pops, rather than the net effect (with an unsigned value).
Each allocator has a bump ptr for each size class. This is no longer slab local. Slabs that haven't been fully allocated no longer need to be in the DLL for this sizeclass.
This change reduces the branching in the case of finding a new free list. Using a non-empty cyclic list enables branch free add, and a single branch in remove to detect the empty case.
Use needs initialisation as makes more sense for other scenarios.
mjp41
force-pushed
the
alloc_slow_optimise
branch
from
f098f39
to
8a8a2f6
Compare
davidchisnall
approved these changes
Mar 16, 2020
davidchisnall
approved these changes
Mar 16, 2020
|
Any idea why the pipeline "Microsoft.snmalloc" is not firing? |
This reverts commit a857b92.
|
This PR addresses #66 |
|
A segfault during linking? |
|
@SchrodingerZhu this is in the self-host test. So we are LD_PRELOADing the snmalloc we just built, and it is crashing. This is one of the harder tests to debug, but also provides us a good piece of coverage of the code. This change is pretty big, so I wanted to go above the standard CI level, hence why it has been hanging around for a week or so. I was going to run a lot of benchmarks through it, but haven't had the time yet. With the changes to CI I guess we have hit an issue independently. |
The GlobalPlaceholder allocator is now a zero init block of memory. This removes various issues for when things are initialised. It is made read-only to we detect write to it on some platforms.
mjp41
force-pushed
the
alloc_slow_optimise
branch
from
f2da4ff
to
65bb8c1
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Make separate bump allocator ptr per thread and size class.
bump allocation.
Refactor code to
The general form of allocation is now
There are special cases interleaved into this
The first occurs between 1 and 2, and the second occurs between, 3 and 4.