Bug 219895

Summary:	amdgpu spamming log [drm] scheduler comp_1.0.1 is not ready, skipping and becoming slow
Product:	Drivers	Reporter:	Kasper Sandberg (kontakt)
Component:	Video(DRI - non Intel)	Assignee:	drivers_video-dri
Status:	RESOLVED ANSWERED
Severity:	normal
Priority:	P3
Hardware:	AMD
OS:	Linux
Kernel Version:		Subsystem:
Regression:	No	Bisected commit-id:

Description Kasper Sandberg 2025-03-19 00:38:51 UTC

somewhere between 6.9.8 and 6.12.9 (also impacts 6.12.12, 6.12.19) it began spamming the kernel messages like this:

[267433.487654] [drm] scheduler comp_1.0.5 is not ready, skipping
[267433.487786] [drm] scheduler comp_1.0.1 is not ready, skipping
[267433.487789] [drm] scheduler comp_1.0.5 is not ready, skipping
[267433.487968] [drm] scheduler comp_1.0.1 is not ready, skipping
[267433.487972] [drm] scheduler comp_1.0.5 is not ready, skipping
[267433.488084] [drm] scheduler comp_1.0.1 is not ready, skipping
[267433.488087] [drm] scheduler comp_1.0.5 is not ready, skipping
[267433.497154] [drm] scheduler comp_1.0.1 is not ready, skipping
[267433.497161] [drm] scheduler comp_1.0.5 is not ready, skipping


(and many many more).

sometimes it also spews this:
[267875.110412] amdgpu 0000:07:00.0: [drm:amdgpu_ring_test_helper [amdgpu]] *ERROR* ring comp_1.0.1 test failed (-110)
[267875.362692] amdgpu 0000:07:00.0: [drm:amdgpu_ring_test_helper [amdgpu]] *ERROR* ring comp_1.0.2 test failed (-110)
[267875.614312] amdgpu 0000:07:00.0: [drm:amdgpu_ring_test_helper [amdgpu]] *ERROR* ring comp_1.0.5 test failed (-110)
[267875.735280] [drm] UVD and UVD ENC initialized successfully.
[267875.836243] [drm] VCE initialized successfully.
[267945.115839] [drm] PCIE GART of 256M enabled (table at 0x000000F400300000).
[267945.433091] amdgpu 0000:07:00.0: [drm:amdgpu_ring_test_helper [amdgpu]] *ERROR* ring comp_1.0.1 test failed (-110)
[267945.685998] amdgpu 0000:07:00.0: [drm:amdgpu_ring_test_helper [amdgpu]] *ERROR* ring comp_1.0.2 test failed (-110)
[267945.939166] amdgpu 0000:07:00.0: [drm:amdgpu_ring_test_helper [amdgpu]] *ERROR* ring comp_1.0.5 test failed (-110)
[267946.059710] [drm] UVD and UVD ENC initialized successfully.
[267946.160672] [drm] VCE initialized successfully.
[268008.569244] [drm] PCIE GART of 256M enabled (table at 0x000000F400300000).
[268008.882686] amdgpu 0000:07:00.0: [drm:amdgpu_ring_test_helper [amdgpu]] *ERROR* ring comp_1.0.1 test failed (-110)
[268009.134521] amdgpu 0000:07:00.0: [drm:amdgpu_ring_test_helper [amdgpu]] *ERROR* ring comp_1.0.2 test failed (-110)
[268009.387366] amdgpu 0000:07:00.0: [drm:amdgpu_ring_test_helper [amdgpu]] *ERROR* ring comp_1.0.5 test failed (-110)
[268009.508038] [drm] UVD and UVD ENC initialized successfully.
[268009.609004] [drm] VCE initialized successfully.
[268060.742711] [drm] PCIE GART of 256M enabled (table at 0x000000F400300000).
[268061.059056] amdgpu 0000:07:00.0: [drm:amdgpu_ring_test_helper [amdgpu]] *ERROR* ring comp_1.0.1 test failed (-110)
[268061.309970] amdgpu 0000:07:00.0: [drm:amdgpu_ring_test_helper [amdgpu]] *ERROR* ring comp_1.0.2 test failed (-110)
[268061.562294] amdgpu 0000:07:00.0: [drm:amdgpu_ring_test_helper [amdgpu]] *ERROR* ring comp_1.0.5 test failed (-110)
[268061.682610] [drm] UVD and UVD ENC initialized successfully.
[268061.783565] [drm] VCE initialized successfully.
[268462.577338] [drm] PCIE GART of 256M enabled (table at 0x000000F400300000).
[268462.894749] amdgpu 0000:07:00.0: [drm:amdgpu_ring_test_helper [amdgpu]] *ERROR* ring comp_1.0.1 test failed (-110)
[268463.148701] amdgpu 0000:07:00.0: [drm:amdgpu_ring_test_helper [amdgpu]] *ERROR* ring comp_1.0.2 test failed (-110)
[268463.402591] amdgpu 0000:07:00.0: [drm:amdgpu_ring_test_helper [amdgpu]] *ERROR* ring comp_1.0.5 test failed (-110)
[268463.523318] [drm] UVD and UVD ENC initialized successfully.
[268463.624279] [drm] VCE initialized successfully.
[268546.092832] [drm] PCIE GART of 256M enabled (table at 0x000000F400300000).
[268546.409437] amdgpu 0000:07:00.0: [drm:amdgpu_ring_test_helper [amdgpu]] *ERROR* ring comp_1.0.1 test failed (-110)
[268546.662004] amdgpu 0000:07:00.0: [drm:amdgpu_ring_test_helper [amdgpu]] *ERROR* ring comp_1.0.2 test failed (-110)
[268546.912911] amdgpu 0000:07:00.0: [drm:amdgpu_ring_test_helper [amdgpu]] *ERROR* ring comp_1.0.5 test failed (-110)
[268547.033655] [drm] UVD and UVD ENC initialized successfully.


allthough thats far from all the time.

old installation used linux-firmware-20240909 with kernel 6.9.8, and newer where it fails tried with linux-firmware-20250109 and linux-firmware-20250211 on 6.12.9+6.12.12+6.12.19.

the system has two gpus, one:
07:00.0 VGA compatible controller: Advanced Micro Devices, Inc. [AMD/ATI] Baffin [Radeon RX 550 640SP / RX 560/560X] (rev cf)

which is the offending, and is a 560, and another (in case its relevant, non-offending):
0a:00.0 VGA compatible controller: Advanced Micro Devices, Inc. [AMD/ATI] Navi 22 [Radeon RX 6700/6700 XT/6750 XT / 6800M/6850M XT] (rev c1)

it seems to mostly be triggered when a monitor powers off, but once thats happened, it seems to keep spamming quite regularly, sometimes stopping, sometimes not.

Comment 1 Kasper Sandberg 2025-03-19 00:41:13 UTC

I should note that when its in this state, its also slow to read the sensor readings using lmsensors, the following block:

amdgpu-pci-0700
Adapter: PCI adapter
vddgfx:        1.10 V  
fan1:             N/A  (min =    0 RPM, max = 3500 RPM)
edge:         +27.0°C  (crit = +94.0°C, hyst = -273.1°C)
PPT:           9.23 W  (cap =  48.00 W)
pwm1:            128%
sclk:         562 MHz 
mclk:         300 MHz 

usually goes so fast that it returns instantly, but when its throwing these errors, it takes ~1sec

Comment 2 Artem S. Tashkinov 2025-03-20 08:34:00 UTC

Please report here instead:

https://gitlab.freedesktop.org/drm/amd/-/issues