On Tue, Feb 21, 2017 at 10:10:09AM +0000, Tvrtko Ursulin wrote: > > On 21/02/2017 09:50, Chris Wilson wrote: > >Hmm. How should we handle global changing value in the course of the > >wait? > > How would you do that? It will get logged at the end of the wait and > ctx/ring/seqno can be used as an unique identifier to match the two > ends. I was wondering what value global had in the early tracepoint. It tells us if the wait begins before the request was executed. Then at the end, you can see if it was interrupted by seeing if global changed. It will definitely help in the trivial cases of reading through the logs and tieing the waits to the execution - I just forsee some confusion occasionally :) -Chris -- Chris Wilson, Intel Open Source Technology Centre _______________________________________________ Intel-gfx mailing list Intel-gfx@xxxxxxxxxxxxxxxxxxxxx https://lists.freedesktop.org/mailman/listinfo/intel-gfx
