<!DOCTYPE html><html><head> <meta http-equiv="Content-Type" content="text/html; charset=utf-8"> </head> <body> Am 27.10.23 um 09:39 schrieb Boris Brezillon: <blockquote type="cite" cite="mid:20231027093943.3f0ae992@collabora.com"> <pre class="moz-quote-pre" wrap="">On Fri, 27 Oct 2023 09:35:01 +0200 Christian König <a class="moz-txt-link-rfc2396E" href="mailto:christian.koenig@amd.com"><christian.koenig@amd.com></a> wrote: </pre> <blockquote type="cite"> <pre class="moz-quote-pre" wrap="">Am 27.10.23 um 09:32 schrieb Boris Brezillon: </pre> <blockquote type="cite"> <pre class="moz-quote-pre" wrap="">On Fri, 27 Oct 2023 09:22:12 +0200 Christian König <a class="moz-txt-link-rfc2396E" href="mailto:christian.koenig@amd.com"><christian.koenig@amd.com></a> wrote: </pre> <blockquote type="cite"> <blockquote type="cite"> <pre class="moz-quote-pre" wrap="">+ + /** + * @update_job_credits: Called once the scheduler is considering this + * job for execution. + * + * Drivers may use this to update the job's submission credits, which is + * useful to e.g. deduct the number of native fences which have been + * signaled meanwhile. + * + * The callback must either return the new number of submission credits + * for the given job, or zero if no update is required. + * + * This callback is optional. + */ + u32 (*update_job_credits)(struct drm_sched_job *sched_job); </pre> </blockquote> <pre class="moz-quote-pre" wrap="">Why do we need an extra callback for this? Just document that prepare_job() is allowed to reduce the number of credits the job might need. </pre> </blockquote> <pre class="moz-quote-pre" wrap="">->prepare_job() is called only once if the returned fence is NULL, but we need this credit-update to happen every time a job is considered for execution by the scheduler. </pre> </blockquote> <pre class="moz-quote-pre" wrap=""> But the job is only considered for execution once. How do you see that this is called multiple times? </pre> </blockquote> <pre class="moz-quote-pre" wrap=""> Nope, it's not. If drm_sched_can_queue() returns false, the scheduler will go look for another entity that has a job ready for execution, and get back to this entity later, and test drm_sched_can_queue() again. Basically, any time drm_sched_can_queue() is called, the job credits update should happen, so we have an accurate view of how many credits this job needs.</pre> </blockquote> Well, that is the handling which I already rejected because it creates unfairness between processes. When you consider the credits needed *before* scheduling jobs with a lower credit count are always preferred over jobs with a higher credit count. What you can do is to look at the credits of a job *after* it was picked up for scheduling so that you can scheduler more jobs. Regards, Christian. </body> </html>