From: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
To: Chris Wilson <chris@chris-wilson.co.uk>, intel-gfx@lists.freedesktop.org
Subject: Re: [PATCH 2/2] drm/i915: Include completed status in request tracepoints
Date: Tue, 1 May 2018 15:41:51 +0100 [thread overview]
Message-ID: <4842e6bf-29c6-ab26-5221-e14809879ef6@linux.intel.com> (raw)
In-Reply-To: <20180501134114.29216-2-chris@chris-wilson.co.uk>
On 01/05/2018 14:41, Chris Wilson wrote:
> Include a bool to show whether the request is complete in every
> tracepoint. This especially helps when tracing the flow of requests
> through the HW.
>
> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
> ---
> drivers/gpu/drm/i915/i915_trace.h | 6 ++++--
> 1 file changed, 4 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h
> index 408827bf5d96..0122a22d6613 100644
> --- a/drivers/gpu/drm/i915/i915_trace.h
> +++ b/drivers/gpu/drm/i915/i915_trace.h
> @@ -647,6 +647,7 @@ DECLARE_EVENT_CLASS(i915_request,
> __field(u32, ctx)
> __field(u32, seqno)
> __field(u32, global)
> + __field(u32, completed)
> ),
>
> TP_fast_assign(
> @@ -656,11 +657,12 @@ DECLARE_EVENT_CLASS(i915_request,
> __entry->ctx = rq->fence.context;
> __entry->seqno = rq->fence.seqno;
> __entry->global = rq->global_seqno;
> + __entry->completed = i915_request_completed(rq);
> ),
>
> - TP_printk("dev=%u, hw_id=%u, ring=%u, ctx=%u, seqno=%u, global=%u",
> + TP_printk("dev=%u, hw_id=%u, ring=%u, ctx=%u, seqno=%u, global=%u, completed?=%d",
> __entry->dev, __entry->hw_id, __entry->ring, __entry->ctx,
> - __entry->seqno, __entry->global)
> + __entry->seqno, __entry->global, __entry->completed)
> );
>
> DEFINE_EVENT(i915_request, i915_request_add,
>
Wouldn't i915_request_hw class be more interesting for things like the
preemption bug?
And you mentioned you would like to see priority in there as well?
I am just thinking is completed status to all is not an overkill. Well,
only from the angle of manually looking at the traces it may be too
noisy. Not sure yet.
Regards,
Tvrtko
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
next prev parent reply other threads:[~2018-05-01 14:41 UTC|newest]
Thread overview: 10+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-05-01 13:41 [PATCH 1/2] drm/i915/execlists: Emit i915_trace_request_out for preemption Chris Wilson
2018-05-01 13:41 ` [PATCH 2/2] drm/i915: Include completed status in request tracepoints Chris Wilson
2018-05-01 14:41 ` Tvrtko Ursulin [this message]
2018-05-01 14:46 ` Chris Wilson
2018-05-01 14:58 ` [PATCH v2] drm/i915: Include completed status in HW " Chris Wilson
2018-05-01 15:25 ` Tvrtko Ursulin
2018-05-01 14:02 ` ✓ Fi.CI.BAT: success for series starting with [1/2] drm/i915/execlists: Emit i915_trace_request_out for preemption Patchwork
2018-05-01 14:37 ` [PATCH 1/2] " Tvrtko Ursulin
2018-05-01 15:05 ` ✓ Fi.CI.IGT: success for series starting with [1/2] " Patchwork
2018-05-01 15:06 ` ✗ Fi.CI.BAT: failure for series starting with [1/2] drm/i915/execlists: Emit i915_trace_request_out for preemption (rev2) Patchwork
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=4842e6bf-29c6-ab26-5221-e14809879ef6@linux.intel.com \
--to=tvrtko.ursulin@linux.intel.com \
--cc=chris@chris-wilson.co.uk \
--cc=intel-gfx@lists.freedesktop.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 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.