[PATCH] tests/xe: Add system_allocator test
Matthew Brost
matthew.brost at intel.com
Wed Apr 16 18:36:28 UTC 2025
On Wed, Apr 16, 2025 at 07:09:40PM +0200, Thomas Hellström wrote:
> Hi, Matt,
>
> On Tue, 2025-04-15 at 19:20 -0700, Matthew Brost wrote:
> > Test various uses of system allocator in single thread, multiple
> > threads, and multiple processes.
> >
> > Features tested:
> > - Malloc with various size
> > - Mmap with various sizes and flags including file backed mappings
> > - Mixing BO allocations with system allocator
> > - Various page sizes
> > - Dynamically freeing / unmapping memory
> > - Sharing VM across threads
> > - Faults racing on different hardware engines / GTs / Tiles
> > - GPU faults and CPU faults racing
> > - CPU faults on multiple threads racing
> > - CPU faults on multiple process racing
> > - GPU faults of memory not faulted in by CPU
> > - Partial unmap of allocations
> > - Attempting to unmap system allocations when GPU has mappings
> > - Eviction of both system allocations and BOs
> > - Forking child processes and reading data from VRAM
> > - mremap data in VRAM
> > - Protection changes
> > - Multiple faults per execbuf
> >
> > Running on LNL, BMG, PVC 1 tile, and PVC 2 tile.
> >
> > v2:
> > - Rebase
> > - Fix memory allocation to not interfear with malloc (Thomas)
> >
> > Signed-off-by: Matthew Brost <matthew.brost at intel.com>
>
> Did you have a chance to look at the memory (or rather virtual
> adddress) leaks on the tests as well?
> With the old version it would exceed 1GB after some time, which I
> believe caused some slowdown.
>
I have not looked at that - rather just fixed mmaping mallocs which
would eventually cause the test to fail with -ENOSPC (e.g. if just ran
xe_exec_system_alloc eventually everything started to fail whereas now I
can run xe_exec_system_alloc to completion).
I wonder if the way I changed memory allocation fixed the leaks, let me
try running under valgrind and see if anything pops.
Matt
> Unfortunately the igt library funcs also leaks memory so running the
> test under valgrind was a bit noisy, but helped to some extent.
>
> /Thomas
>
More information about the igt-dev
mailing list