* [PATCH] drm/amdgpu: Increase hmm range get pages timeout
@ 2023-06-06 19:57 Philip Yang
2023-06-06 19:59 ` Russell, Kent
2023-06-06 22:53 ` [PATCH v2] " Philip Yang
0 siblings, 2 replies; 4+ messages in thread
From: Philip Yang @ 2023-06-06 19:57 UTC (permalink / raw)
To: amd-gfx; +Cc: Philip Yang, Felix.Kuehling
If hmm_range_fault returns -EBUSY, we should call hmm_range_fault again
to validate the remaining pages. On one system with NUMA auto balancing
enabled, hmm_range_fault takes 6 seconds for 1GB range because CPU
migrate the range one page at a time. To be safe, increase timeout value
to 1 second for 128MB range.
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c
index 2dadcfe43d03..f7efa582f3ed 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c
@@ -190,8 +190,8 @@ int amdgpu_hmm_range_get_pages(struct mmu_interval_notifier *notifier,
pr_debug("hmm range: start = 0x%lx, end = 0x%lx",
hmm_range->start, hmm_range->end);
- /* Assuming 512MB takes maxmium 1 second to fault page address */
- timeout = max((hmm_range->end - hmm_range->start) >> 29, 1UL);
+ /* Assuming 128MB takes maxmium 1 second to fault page address */
+ timeout = max((hmm_range->end - hmm_range->start) >> 27, 1UL);
timeout *= HMM_RANGE_DEFAULT_TIMEOUT;
timeout = jiffies + msecs_to_jiffies(timeout);
--
2.35.1
^ permalink raw reply related [flat|nested] 4+ messages in thread
* RE: [PATCH] drm/amdgpu: Increase hmm range get pages timeout
2023-06-06 19:57 [PATCH] drm/amdgpu: Increase hmm range get pages timeout Philip Yang
@ 2023-06-06 19:59 ` Russell, Kent
2023-06-06 22:53 ` [PATCH v2] " Philip Yang
1 sibling, 0 replies; 4+ messages in thread
From: Russell, Kent @ 2023-06-06 19:59 UTC (permalink / raw)
To: Yang, Philip, amd-gfx; +Cc: Yang, Philip, Kuehling, Felix
[AMD Official Use Only - General]
> -----Original Message-----
> From: amd-gfx <amd-gfx-bounces@lists.freedesktop.org> On Behalf Of Philip
> Yang
> Sent: Tuesday, June 6, 2023 3:57 PM
> To: amd-gfx@lists.freedesktop.org
> Cc: Yang, Philip <Philip.Yang@amd.com>; Kuehling, Felix
> <Felix.Kuehling@amd.com>
> Subject: [PATCH] drm/amdgpu: Increase hmm range get pages timeout
>
> If hmm_range_fault returns -EBUSY, we should call hmm_range_fault again
> to validate the remaining pages. On one system with NUMA auto balancing
> enabled, hmm_range_fault takes 6 seconds for 1GB range because CPU
> migrate the range one page at a time. To be safe, increase timeout value
> to 1 second for 128MB range.
>
> Signed-off-by: Philip Yang <Philip.Yang@amd.com>
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c | 4 ++--
> 1 file changed, 2 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c
> b/drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c
> index 2dadcfe43d03..f7efa582f3ed 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c
> @@ -190,8 +190,8 @@ int amdgpu_hmm_range_get_pages(struct
> mmu_interval_notifier *notifier,
> pr_debug("hmm range: start = 0x%lx, end = 0x%lx",
> hmm_range->start, hmm_range->end);
>
> - /* Assuming 512MB takes maxmium 1 second to fault page
> address */
> - timeout = max((hmm_range->end - hmm_range->start) >> 29,
> 1UL);
> + /* Assuming 128MB takes maxmium 1 second to fault page
> address */
Since we're changing the line anyways, can we fix maxmium->maximum ?
Kent
> + timeout = max((hmm_range->end - hmm_range->start) >> 27,
> 1UL);
> timeout *= HMM_RANGE_DEFAULT_TIMEOUT;
> timeout = jiffies + msecs_to_jiffies(timeout);
>
> --
> 2.35.1
^ permalink raw reply [flat|nested] 4+ messages in thread
* [PATCH v2] drm/amdgpu: Increase hmm range get pages timeout
2023-06-06 19:57 [PATCH] drm/amdgpu: Increase hmm range get pages timeout Philip Yang
2023-06-06 19:59 ` Russell, Kent
@ 2023-06-06 22:53 ` Philip Yang
2023-06-07 13:22 ` Felix Kuehling
1 sibling, 1 reply; 4+ messages in thread
From: Philip Yang @ 2023-06-06 22:53 UTC (permalink / raw)
To: amd-gfx; +Cc: Philip Yang, Felix.Kuehling
If hmm_range_fault returns -EBUSY, we should call hmm_range_fault again
to validate the remaining pages. On one system with NUMA auto balancing
enabled, hmm_range_fault takes 6 seconds for 1GB range because CPU
migrate the range one page at a time. To be safe, increase timeout value
to 1 second for 128MB range.
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c
index 2dadcfe43d03..081267161d40 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c
@@ -190,8 +190,8 @@ int amdgpu_hmm_range_get_pages(struct mmu_interval_notifier *notifier,
pr_debug("hmm range: start = 0x%lx, end = 0x%lx",
hmm_range->start, hmm_range->end);
- /* Assuming 512MB takes maxmium 1 second to fault page address */
- timeout = max((hmm_range->end - hmm_range->start) >> 29, 1UL);
+ /* Assuming 128MB takes maximum 1 second to fault page address */
+ timeout = max((hmm_range->end - hmm_range->start) >> 27, 1UL);
timeout *= HMM_RANGE_DEFAULT_TIMEOUT;
timeout = jiffies + msecs_to_jiffies(timeout);
--
2.35.1
^ permalink raw reply related [flat|nested] 4+ messages in thread
* Re: [PATCH v2] drm/amdgpu: Increase hmm range get pages timeout
2023-06-06 22:53 ` [PATCH v2] " Philip Yang
@ 2023-06-07 13:22 ` Felix Kuehling
0 siblings, 0 replies; 4+ messages in thread
From: Felix Kuehling @ 2023-06-07 13:22 UTC (permalink / raw)
To: Philip Yang, amd-gfx
Am 2023-06-06 um 18:53 schrieb Philip Yang:
> If hmm_range_fault returns -EBUSY, we should call hmm_range_fault again
> to validate the remaining pages. On one system with NUMA auto balancing
> enabled, hmm_range_fault takes 6 seconds for 1GB range because CPU
> migrate the range one page at a time. To be safe, increase timeout value
> to 1 second for 128MB range.
>
> Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c | 4 ++--
> 1 file changed, 2 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c
> index 2dadcfe43d03..081267161d40 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c
> @@ -190,8 +190,8 @@ int amdgpu_hmm_range_get_pages(struct mmu_interval_notifier *notifier,
> pr_debug("hmm range: start = 0x%lx, end = 0x%lx",
> hmm_range->start, hmm_range->end);
>
> - /* Assuming 512MB takes maxmium 1 second to fault page address */
> - timeout = max((hmm_range->end - hmm_range->start) >> 29, 1UL);
> + /* Assuming 128MB takes maximum 1 second to fault page address */
> + timeout = max((hmm_range->end - hmm_range->start) >> 27, 1UL);
> timeout *= HMM_RANGE_DEFAULT_TIMEOUT;
> timeout = jiffies + msecs_to_jiffies(timeout);
>
^ permalink raw reply [flat|nested] 4+ messages in thread
end of thread, other threads:[~2023-06-07 13:23 UTC | newest]
Thread overview: 4+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2023-06-06 19:57 [PATCH] drm/amdgpu: Increase hmm range get pages timeout Philip Yang
2023-06-06 19:59 ` Russell, Kent
2023-06-06 22:53 ` [PATCH v2] " Philip Yang
2023-06-07 13:22 ` Felix Kuehling
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.