From: "Christian König" <christian.koenig-5C7GfCeVMHo@public.gmane.org>
To: "Michel Dänzer" <michel-otUistvHUpPR7s880joybQ@public.gmane.org>,
sunnanyong <sunnanyong-hv44wF8Li93QT0dZR+AlfA@public.gmane.org>
Cc: "Baixin (BX)" <baixin1-hv44wF8Li93QT0dZR+AlfA@public.gmane.org>,
"amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org"
<amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org>
Subject: Re: GTT memory usage overflow
Date: Fri, 13 Jul 2018 09:47:00 +0200 [thread overview]
Message-ID: <5e684ce7-9382-e84f-bc4c-e41245cf9412@amd.com> (raw)
In-Reply-To: <c588a557-1488-9d86-f6c9-d584bdeba16c-otUistvHUpPR7s880joybQ@public.gmane.org>
Am 13.07.2018 um 09:40 schrieb Michel Dänzer:
> On 2018-07-13 09:00 AM, Christian König wrote:
>> Hi,
>>
>> no that is certainly not normal.
>>
>> We temporary allow the kernel to allocate more pages than available when
>> we bind stuff into the GART, but that shouldn't have this effect.
> mgr->available can happen to be negative when amdgpu_gtt_mgr_debug is
> called, can't it? I.e. we should clamp it to 0 there as well, same as in
> amdgpu_gtt_mgr_usage (or maybe just use that for both values in
> amdgpu_gtt_mgr_debug).
Yeah, but that happens only temporary while binding things into GART.
You must be really really lucky if you can see that in debugfs and from
the description it sounds more like the reporter sees negative values
all the time.
I really wonder how that could happen.
Christian.
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
prev parent reply other threads:[~2018-07-13 7:47 UTC|newest]
Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-07-12 15:50 GTT memory usage overflow sunnanyong
[not found] ` <EB021AE3BDDC1742A899855D00BABEB001075B42-0LhPdUyVHB9548jd+VSckwK1hpo4iccwjNknBlVQO8k@public.gmane.org>
2018-07-13 7:00 ` Christian König
[not found] ` <9564a854-21ff-1ca3-34d9-cf9baaa18a8c-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
2018-07-13 7:40 ` Michel Dänzer
[not found] ` <c588a557-1488-9d86-f6c9-d584bdeba16c-otUistvHUpPR7s880joybQ@public.gmane.org>
2018-07-13 7:47 ` Christian König [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=5e684ce7-9382-e84f-bc4c-e41245cf9412@amd.com \
--to=christian.koenig-5c7gfcevmho@public.gmane.org \
--cc=amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org \
--cc=baixin1-hv44wF8Li93QT0dZR+AlfA@public.gmane.org \
--cc=michel-otUistvHUpPR7s880joybQ@public.gmane.org \
--cc=sunnanyong-hv44wF8Li93QT0dZR+AlfA@public.gmane.org \
/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