[Intel-gfx] [PATCH v4 06/38] drm/i915: Re-instate request->uniq because it is extremely useful
John.C.Harrison at Intel.com
Tue Jan 12 03:16:42 PST 2016
On 11/01/2016 22:04, Chris Wilson wrote:
> On Mon, Jan 11, 2016 at 06:42:35PM +0000, John.C.Harrison at Intel.com wrote:
>> From: John Harrison <John.C.Harrison at Intel.com>
>> The seqno value cannot always be used when debugging issues via trace
>> points. This is because it can be reset back to start, especially
>> during TDR type tests. Also, when the scheduler arrives the seqno is
>> only valid while a given request is executing on the hardware. While
>> the request is simply queued waiting for submission, it's seqno value
>> will be zero (meaning invalid).
> Even with per-context seqno that can be assigned before execution as we
> know that requests within a context cannot be reordered?
Firstly, we do not have per-context seqno values at the moment. However,
even if we did that would make a per request unique value even more
useful as the only way to identify a given request then would be through
a context pointer and seqno pair which would make scanning through debug
traces even worse.
More information about the Intel-gfx