From: Matthew Brost <matthew.brost@intel.com>
To: "Thomas Hellström" <thomas.hellstrom@linux.intel.com>
Cc: igt-dev@lists.freedesktop.org, intel-xe@lists.freedesktop.org
Subject: Re: [igt-dev] [PATCH i-g-t v2] tests/xe/xe_noexec_ping_pong: Add a test to expose unnecessary rebinds
Date: Thu, 16 Mar 2023 15:29:38 +0000 [thread overview]
Message-ID: <ZBM14me9pLBqchXH@DUT025-TGLU.fm.intel.com> (raw)
In-Reply-To: <20230316094723.63713-1-thomas.hellstrom@linux.intel.com>
On Thu, Mar 16, 2023 at 10:47:23AM +0100, Thomas Hellström wrote:
> This test creates compute vms, binds a couple of bos and an engine each,
> thus redying it for execution. However, VRAM memory is over-
> committed and while there is still nothing to execute, an eviction
> will trigger the VM's rebind worker to rebind the evicted bo, which
> will in turn trigger another eviction and so on.
>
> Since we don't have eviction stats yet we need to watch "top" for
> the rebind kworkers using a lot of CPU while the test idles.
>
> The correct driver behaviour should be not to rebind anything unless
> there is work queued on one of the VM's compute engines.
>
> v2:
> - Use the ALIGN macro for aligning
> - Reduce the idle pause duration to 10s. (Matthew Brost)
> - Add an IGT_TEST_DESCRIPTION()
> - Explicity use gt0 for testing.
> - Skip if no VRAM available.
>
> Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
> ---
> tests/meson.build | 1 +
> tests/xe/xe_noexec_ping_pong.c | 106 +++++++++++++++++++++++++++++++++
> 2 files changed, 107 insertions(+)
> create mode 100644 tests/xe/xe_noexec_ping_pong.c
>
> diff --git a/tests/meson.build b/tests/meson.build
> index 632e36e0..2e62ff23 100644
> --- a/tests/meson.build
> +++ b/tests/meson.build
> @@ -256,6 +256,7 @@ xe_progs = [
> 'xe_huc_copy',
> 'xe_mmap',
> 'xe_mmio',
> + 'xe_noexec_ping_pong',
> 'xe_pm',
> 'xe_prime_self_import',
> 'xe_query',
> diff --git a/tests/xe/xe_noexec_ping_pong.c b/tests/xe/xe_noexec_ping_pong.c
> new file mode 100644
> index 00000000..dc14f8cf
> --- /dev/null
> +++ b/tests/xe/xe_noexec_ping_pong.c
> @@ -0,0 +1,106 @@
> +// SPDX-License-Identifier: MIT
> +/*
> + * Copyright © 2023 Intel Corporation
> + */
> +
> +#include <unistd.h>
> +
> +#include "drmtest.h"
> +#include "igt.h"
> +
> +#include "xe/xe_ioctl.h"
> +#include "xe/xe_query.h"
> +
> +#define NUM_VMS 10
> +#define NUM_BOS 1
> +#define SECONDS_TO_WAIT 10
> +
> +/**
> + * TEST: Expose compute VM's unnecessary rebinds
> + * Category: Software building block
> + * Sub-category: compute
> + * Test category: functionality test
> + */
> +
> +/*
> + * This test creates compute vms, binds a couple of bos and an engine each,
> + * thus redying it for execution. However, VRAM memory is over-
> + * committed and while there is still nothing to execute, an eviction
> + * will trigger the VM's rebind worker to rebind the evicted bo, which
> + * will in turn trigger another eviction and so on.
> + *
> + * Since we don't have eviction stats yet we need to watch "top" for
> + * the rebind kworkers using a lot of CPU while the test idles.
> + *
> + * The correct driver behaviour should be not to rebind anything unless
> + * there is worked queued on one of the VM's compute engines.
> + */
> +static void test_ping_pong(int fd, struct drm_xe_engine_class_instance *eci)
> +{
> + size_t vram_size = xe_vram_size(fd, 0);
> + size_t align = xe_get_default_alignment(fd);
> + size_t bo_size = vram_size / NUM_VMS / NUM_BOS;
> + uint32_t vm[NUM_VMS];
> + uint32_t bo[NUM_VMS][NUM_BOS];
> + uint32_t engines[NUM_VMS];
> + unsigned int i, j;
> +
> + igt_skip_on(!bo_size);
> +
> + /* Align and make sure we overcommit vram with at least 10% */
> + bo_size = ALIGN(bo_size + bo_size / 10, align);
> +
> + /*
> + * This should not start ping-ponging memory between system and
> + * VRAM. For now look at top to determine. TODO: Look at eviction
> + * stats.
> + */
> + for (i = 0; i < NUM_VMS; ++i) {
> + struct drm_xe_ext_engine_set_property ext = {
> + .base.next_extension = 0,
> + .base.name = XE_ENGINE_EXTENSION_SET_PROPERTY,
> + .property = XE_ENGINE_SET_PROPERTY_COMPUTE_MODE,
> + .value = 1,
> + };
> +
> + vm[i] = xe_vm_create(fd, DRM_XE_VM_CREATE_COMPUTE_MODE, 0);
> + for (j = 0; j < NUM_BOS; ++j) {
> + igt_debug("Creating bo size %lu for vm %u\n",
> + (unsigned long) bo_size,
> + (unsigned int) vm[i]);
> +
> + bo[i][j] = xe_bo_create_flags(fd, vm[i], bo_size,
> + vram_memory(fd, 0));
> + xe_vm_bind(fd, vm[i], bo[i][j], 0, 0x40000 + j*bo_size,
> + bo_size, NULL, 0);
> + }
> + engines[i] = xe_engine_create(fd, vm[i], eci,
> + to_user_pointer(&ext));
> + }
> +
> + igt_info("Now sleeping for %ds.\n", SECONDS_TO_WAIT);
> + igt_info("Watch \"top\" for high-cpu kworkers!\n");
> + sleep(SECONDS_TO_WAIT);
> +
> + for (i = 0; i < NUM_VMS; ++i) {
> + xe_engine_destroy(fd, engines[i]);
> + for (j = 0; j < NUM_BOS; ++j)
> + gem_close(fd, bo[i][j]);
> + xe_vm_destroy(fd, vm[i]);
> + }
> +}
> +
> +static int fd;
> +
> +IGT_TEST_DESCRIPTION("Expose compute VM's unnecessary rebinds");
> +igt_simple_main
> +{
> +
> + fd = drm_open_driver(DRIVER_XE);
> + xe_device_get(fd);
> +
> + test_ping_pong(fd, xe_hw_engine(fd, 0));
> +
> + xe_device_put(fd);
> + close(fd);
> +}
> --
> 2.39.2
>
prev parent reply other threads:[~2023-03-16 15:29 UTC|newest]
Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-03-16 9:47 [igt-dev] [PATCH i-g-t v2] tests/xe/xe_noexec_ping_pong: Add a test to expose unnecessary rebinds Thomas Hellström
2023-03-16 11:13 ` [igt-dev] ✓ Fi.CI.BAT: success for tests/xe/xe_noexec_ping_pong: Add a test to expose unnecessary rebinds (rev2) Patchwork
2023-03-16 13:58 ` [igt-dev] ✓ Fi.CI.IGT: " Patchwork
2023-03-16 15:29 ` Matthew Brost [this message]
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=ZBM14me9pLBqchXH@DUT025-TGLU.fm.intel.com \
--to=matthew.brost@intel.com \
--cc=igt-dev@lists.freedesktop.org \
--cc=intel-xe@lists.freedesktop.org \
--cc=thomas.hellstrom@linux.intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox