Quoting Joonas Lahtinen (2019-02-07 16:01:31) > Quoting Chris Wilson (2019-02-07 09:18:22) > > Apply backpressure to hogs that emit requests faster than the GPU can > > process them by waiting for their ring to be less than half-full before > > proceeding with taking the struct_mutex. > > > > This is a gross hack to apply throttling backpressure, the long term > > goal is to remove the struct_mutex contention so that each client > > naturally waits, preferably in an asynchronous, nonblocking fashion > > (pipelined operations for the win), for their own resources and never > > blocks another client within the driver at least. (Realtime priority > > goals would extend to ensuring that resource contention favours high > > priority clients as well.) > > > > This patch only limits excessive request production and does not attempt > > to throttle clients that block waiting for eviction (either global GTT or > > system memory) or any other global resources, see above for the long term > > goal. > > Code checks out. > > Some Testcase: links and some relative perf numbers might be in place. Fixes an arbitrary test case written with exactly this problem in mind ;) Performance stress tests show no impact, which soothes my conscience as my biggest worry was upsetting those microbenchmarks that try to measure driver overhead. -Chris _______________________________________________ Intel-gfx mailing list Intel-gfx@xxxxxxxxxxxxxxxxxxxxx https://lists.freedesktop.org/mailman/listinfo/intel-gfx
