diff options
author | Karol Wachowski <karol.wachowski@intel.com> | 2025-04-16 12:25:55 +0200 |
---|---|---|
committer | Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com> | 2025-04-25 09:49:11 +0200 |
commit | 0e7db503c5355ff9a7471d0a450bde8c069ef803 (patch) | |
tree | 779b001642a4e3613fd25bdc66a02ef755046976 /kernel/trace/trace_workqueue.c | |
parent | 3a2b7389feea9a7afd18d58cda59b7a989445f38 (diff) |
accel/ivpu: Implement heartbeat-based TDR mechanismHEADfor-linux-nextdrm-misc-next
Introduce a heartbeat-based Timeout Detection and Recovery (TDR) mechanism.
The enhancement aims to improve the reliability of device hang detection by
monitoring heartbeat updates.
Each progressing inference will update heartbeat counter allowing driver to
monitor its progression. Limit maximum number of reschedules when heartbeat
indicates progression to 30. This increases the maximum running time of
single inference to about 60 seconds.
The heartbeat mechanism provides a more robust method for detecting device
hangs, potentially reducing false positive recoveries due to long running
inferences.
Signed-off-by: Karol Wachowski <karol.wachowski@intel.com>
Signed-off-by: Maciej Falkowski <maciej.falkowski@linux.intel.com>
Reviewed-by: Jeff Hugo <jeff.hugo@oss.qualcomm.com>
Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Link: https://lore.kernel.org/r/20250416102555.384526-1-maciej.falkowski@linux.intel.com
Diffstat (limited to 'kernel/trace/trace_workqueue.c')
0 files changed, 0 insertions, 0 deletions