#
83321094 |
|
06-Oct-2022 |
Matthew Brost <matthew.brost@intel.com> |
drm/i915/guc: Delay disabling guc_id scheduling for better hysteresis Add a delay, configurable via debugfs (default 34ms), to disable scheduling of a context after the pin count goes to zero. Disable scheduling is a costly operation as it requires synchronizing with the GuC. So the idea is that a delay allows the user to resubmit something before doing this operation. This delay is only done if the context isn't closed and less than a given threshold (default is 3/4) of the guc_ids are in use. Alan Previn: Matt Brost first introduced this patch back in Oct 2021. However no real world workload with measured performance impact was available to prove the intended results. Today, this series is being republished in response to a real world workload that benefited greatly from it along with measured performance improvement. Workload description: 36 containers were created on a DG2 device where each container was performing a combination of 720p 3d game rendering and 30fps video encoding. The workload density was configured in a way that guaranteed each container to ALWAYS be able to render and encode no less than 30fps with a predefined maximum render + encode latency time. That means the totality of all 36 containers and their workloads were not saturating the engines to their max (in order to maintain just enough headrooom to meet the min fps and max latencies of incoming container submissions). Problem statement: It was observed that the CPU core processing the i915 soft IRQ work was experiencing severe load. Using tracelogs and an instrumentation patch to count specific i915 IRQ events, it was confirmed that the majority of the CPU cycles were caused by the gen11_other_irq_handler() -> guc_irq_handler() code path. The vast majority of the cycles was determined to be processing a specific G2H IRQ: i.e. INTEL_GUC_ACTION_SCHED_CONTEXT_MODE_DONE. These IRQs are sent by GuC in response to i915 KMD sending H2G requests: INTEL_GUC_ACTION_SCHED_CONTEXT_MODE_SET. Those H2G requests are sent whenever a context goes idle so that we can unpin the context from GuC. The high CPU utilization % symptom was limiting density scaling. Root Cause Analysis: Because the incoming execution buffers were spread across 36 different containers (each with multiple contexts) but the system in totality was NOT saturated to the max, it was assumed that each context was constantly idling between submissions. This was causing a thrashing of unpinning contexts from GuC at one moment, followed quickly by repinning them due to incoming workload the very next moment. These event-pairs were being triggered across multiple contexts per container, across all containers at the rate of > 30 times per sec per context. Metrics: When running this workload without this patch, we measured an average of ~69K INTEL_GUC_ACTION_SCHED_CONTEXT_MODE_DONE events every 10 seconds or ~10 million times over ~25+ mins. With this patch, the count reduced to ~480 every 10 seconds or about ~28K over ~10 mins. The improvement observed is ~99% for the average counts per 10 seconds. Design awareness: Selftest impact. As temporary WA disable this feature for the selftests. Selftests are very timing sensitive and any change in timing can cause failure. A follow up patch will fixup the selftests to understand this delay. Design awareness: Race between guc_request_alloc and guc_context_close. If a context close is issued while there is a request submission in flight and a delayed schedule disable is pending, guc_context_close and guc_request_alloc will race to cancel the delayed disable. To close the race, make sure that guc_request_alloc waits for guc_context_close to finish running before checking any state. Design awareness: GT Reset event. If a gt reset is triggered, as preparation steps, add an additional step to ensure all contexts that have a pending delay-disable-schedule task be flushed of it. Move them directly into the closed state after cancelling the worker. This is okay because the existing flow flushes all yet-to-arrive G2H's dropping them anyway. Signed-off-by: Matthew Brost <matthew.brost@intel.com> Signed-off-by: Alan Previn <alan.previn.teres.alexis@intel.com> Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com> Reviewed-by: John Harrison <John.C.Harrison@Intel.com> Signed-off-by: John Harrison <John.C.Harrison@Intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20221006225121.826257-2-alan.previn.teres.alexis@intel.com
|
#
54c204c5 |
|
19-Aug-2022 |
Matthew Auld <matthew.auld@intel.com> |
Revert "drm/i915/guc: Add delay to disable scheduling after pin count goes to zero" This reverts commit 6a079903847cce1dd06345127d2a32f26d2cd9c6. Everything in CI using GuC is now timing out[1], and killing the machine with this change (perhaps a deadlock?). CI was recently on fire due to some changes coming in from -rc1, so likely the pre-merge CI results for this series were invalid? For now just revert, unless GuC experts already have a fix in mind. [1] https://intel-gfx-ci.01.org/tree/drm-tip/index.html? Signed-off-by: Matthew Auld <matthew.auld@intel.com> Cc: Matthew Brost <matthew.brost@intel.com> Cc: Alan Previn <alan.previn.teres.alexis@intel.com> Cc: John Harrison <John.C.Harrison@Intel.com> Reviewed-by: John Harrison <John.C.Harrison@Intel.com> Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20220819123904.913750-1-matthew.auld@intel.com
|
#
6a079903 |
|
16-Aug-2022 |
Matthew Brost <matthew.brost@intel.com> |
drm/i915/guc: Add delay to disable scheduling after pin count goes to zero Add a delay, configurable via debugfs (default 34ms), to disable scheduling of a context after the pin count goes to zero. Disable scheduling is a costly operation as it requires synchronizing with the GuC. So the idea is that a delay allows the user to resubmit something before doing this operation. This delay is only done if the context isn't closed and less than a given threshold (default is 3/4) of the guc_ids are in use. As temporary WA disable this feature for the selftests. Selftests are very timing sensitive and any change in timing can cause failure. A follow up patch will fixup the selftests to understand this delay. Alan Previn: Matt Brost first introduced this series back in Oct 2021. However no real world workload with measured performance impact was available to prove the intended results. Today, this series is being republished in response to a real world workload that benefited greatly from it along with measured performance improvement. Workload description: 36 containers were created on a DG2 device where each container was performing a combination of 720p 3d game rendering and 30fps video encoding. The workload density was configured in a way that guaranteed each container to ALWAYS be able to render and encode no less than 30fps with a predefined maximum render + encode latency time. That means the totality of all 36 containers and their workloads were not saturating the engines to their max (in order to maintain just enough headrooom to meet the min fps and max latencies of incoming container submissions). Problem statement: It was observed that the CPU core processing the i915 soft IRQ work was experiencing severe load. Using tracelogs and an instrumentation patch to count specific i915 IRQ events, it was confirmed that the majority of the CPU cycles were caused by the gen11_other_irq_handler() -> guc_irq_handler() code path. The vast majority of the cycles was determined to be processing a specific G2H IRQ: i.e. INTEL_GUC_ACTION_SCHED_CONTEXT_MODE_DONE. These IRQs are sent by GuC in response to i915 KMD sending H2G requests: INTEL_GUC_ACTION_SCHED_CONTEXT_MODE_SET. Those H2G requests are sent whenever a context goes idle so that we can unpin the context from GuC. The high CPU utilization % symptom was limiting density scaling. Root Cause Analysis: Because the incoming execution buffers were spread across 36 different containers (each with multiple contexts) but the system in totality was NOT saturated to the max, it was assumed that each context was constantly idling between submissions. This was causing a thrashing of unpinning contexts from GuC at one moment, followed quickly by repinning them due to incoming workload the very next moment. These event-pairs were being triggered across multiple contexts per container, across all containers at the rate of > 30 times per sec per context. Metrics: When running this workload without this patch, we measured an average of ~69K INTEL_GUC_ACTION_SCHED_CONTEXT_MODE_DONE events every 10 seconds or ~10 million times over ~25+ mins. With this patch, the count reduced to ~480 every 10 seconds or about ~28K over ~10 mins. The improvement observed is ~99% for the average counts per 10 seconds. Signed-off-by: Matthew Brost <matthew.brost@intel.com> Signed-off-by: Alan Previn <alan.previn.teres.alexis@intel.com> Reviewed-by: John Harrison <John.C.Harrison@Intel.com> Signed-off-by: John Harrison <John.C.Harrison@Intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20220817020511.2180747-3-alan.previn.teres.alexis@intel.com
|
#
022f324c |
|
17-Sep-2021 |
Lucas De Marchi <lucas.demarchi@intel.com> |
drm/i915: rename debugfs_gt files We shouldn't be using debugfs_ namespace for this functionality. Rename debugfs_gt.[ch] to intel_gt_debugfs.[ch] and then make functions, defines and structs follow suit. While at it and since we are renaming the header, sort the includes alphabetically. Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com> Acked-by: Jani Nikula <jani.nikula@intel.com> Reviewed-by: Matt Roper <matthew.d.roper@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20210918025754.1254705-1-lucas.demarchi@intel.com
|
#
f1928ac2 |
|
30-Jul-2021 |
Vinay Belgaumkar <vinay.belgaumkar@intel.com> |
drm/i915/guc/slpc: Add debugfs for SLPC info This prints out relevant SLPC info from the SLPC shared structure. We will send a H2G message which forces SLPC to update the shared data structure with latest information before reading it. v2: Address review comments (Michal W) v3: Remove unnecessary tasks from slpc_info (Michal W) v4: Rename function to intel_guc_slpc_print_info() (Michal W) v5: checkpatch() Reviewed-by: Michal Wajdeczko <michal.wajdeczko@intel.com> Signed-off-by: Vinay Belgaumkar <vinay.belgaumkar@intel.com> Signed-off-by: Sundaresan Sujaritha <sujaritha.sundaresan@intel.com> Signed-off-by: John Harrison <John.C.Harrison@Intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20210730202119.23810-10-vinay.belgaumkar@intel.com
|
#
731c2ad5 |
|
26-Jul-2021 |
John Harrison <John.C.Harrison@Intel.com> |
drm/i915/guc: Include scheduling policies in the debugfs state dump Added the scheduling policy parameters to the 'guc_info' debugfs state dump. Signed-off-by: John Harrison <John.C.Harrison@Intel.com> Signed-off-by: Matthew Brost <matthew.brost@intel.com> Reviewed-by: Matthew Brost <matthew.brost@intel.com> Signed-off-by: John Harrison <John.C.Harrison@Intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20210727002348.97202-23-matthew.brost@intel.com
|
#
28ff6520 |
|
21-Jul-2021 |
Matthew Brost <matthew.brost@intel.com> |
drm/i915/guc: Update GuC debugfs to support new GuC Update GuC debugfs to support the new GuC structures. v2: (John Harrison) - Remove intel_lrc_reg.h include from i915_debugfs.c (Michal) - Rename GuC debugfs functions Signed-off-by: John Harrison <John.C.Harrison@Intel.com> Signed-off-by: Matthew Brost <matthew.brost@intel.com> Reviewed-by: John Harrison <John.C.Harrison@Intel.com> Signed-off-by: John Harrison <John.C.Harrison@Intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20210721215101.139794-17-matthew.brost@intel.com
|
#
293a5548 |
|
26-Mar-2020 |
Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com> |
drm/i915/uc: Move uC debugfs to its own folder under GT uC is a component of the GT, so it makes sense for the uC debugfs files to be in the GT folder. A subfolder has been used to keep the same structure we have for the code. v2: use intel_* prefix (Jani), rebase on new gt_debugfs_register_files, fix permissions for writable debugfs files. v3: Rename files (Michal), remove blank line (Jani), fix sparse warns. Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com> Cc: Andi Shyti <andi.shyti@intel.com> Cc: Michal Wajdeczko <michal.wajdeczko@intel.com> Cc: John Harrison <John.C.Harrison@Intel.com> Cc: Matthew Brost <matthew.brost@intel.com> Cc: Tony Ye <tony.ye@intel.com> Cc: Jani Nikula <jani.nikula@linux.intel.com> Reviewed-by: Andi Shyti <andi.shyti@intel.com> #v2 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Link: https://patchwork.freedesktop.org/patch/msgid/20200326181121.16869-6-daniele.ceraolospurio@intel.com
|