Jetson xavier nx camera IMX477

  • Our kit is combined by Jetson Xavier NX, Leetop carrier board A205E, Leetop CSI pinboard c.1705.m and 6 cameras Arducam B0251 (IMX477)
  • Our situation is:
    • At aspect ratio 16:9 and 3840X2160 (8.3MP) resolution. The system operated 6 cameras (simultaneously) at maximum 20FPS. CPU usage: 35% per 6 core, GPU usage: 20-80%, VIC (image processor) usage: 75%
    • At aspect ratio 4:3 and 12MP resolution, the system managed to operate 6 cameras (simultaneously) at maximum 2-3 FPS
    • At aspect ratio 4:3 and 3MP resolution the system managed to operate 6 cameras at maximum 2-3 FPS
  • We are looking for:
    • Aspect ratio 4:3
    • resolution 12MP
    • 30 FPS
      • Can it be increased to 60 FPS?
    • 6 simultaneous streams from Arducam B0251 (IMX477) cameras

The information about resource usage that INCLUDES our image postprocessing and AI algorithms.
If we are talking about resources usage in case if we are only getting stream from cameras ( 3840 x 2160, 20 fps, 6 cameras in parallel ) without any postprocessing then numbers are different: CPU: 20%, GPU 0%, VIC 0%, memory bandwidth usage 10% (data obtained by tegrastats during 6 cameras streaming).

If I increase the frame rate to 21 (just +1) I start getting messages from argus API about dropped frames.
The overclocking you suggested didn’t help, again +1 frame per second causes dropping frames.

We are getting streams via Libargus camera API that is part of Nvidia MMAPI Jetson Linux API Reference: Libargus Camera API | NVIDIA Docs

Here is some extra information:

output of v4l2-ctl -d /dev/video0 --list-formats-ext is

ioctl: VIDIOC_ENUM_FMT
	Type: Video Capture

	[0]: 'RG10' (10-bit Bayer RGRG/GBGB)
		Size: Discrete 3840x2160
			Interval: Discrete 0.033s (30.000 fps)
		Size: Discrete 1920x1080
			Interval: Discrete 0.017s (60.000 fps)
		Size: Discrete 4032x3040
			Interval: Discrete 0.033s (30.000 fps)
		Size: Discrete 2028x1520
			Interval: Discrete 0.017s (60.000 fps)

I use API method to get internal frame count and then I expect it monotonically increasing
const Ext::IInternalFrameCount *iInternalFrameCount = interface_cast(metadata);

if I miss frame count it means frame was dropped.

Mode 0 3840x2160 (16:9)

  1. mode 0, 20fps * 6 cams = OK
  2. mode 0, 30fps * 4 cams - OK
  3. mode 0, 25fps * 5 cams - OK
  4. mode 0, 25fps * 6 cams - dropping frames
  5. mode 0, 30fps * 5 cams - dropping frames
  6. mode 0, 21fps * 6 cams - dropping frames

Mode 2 4032x3040 (4:3) we are interested in

The mode has strange issue with setting fps, if I set 10fps I actually gets 15fps, if I set 15->21, 18->26, 19->28, it seems it has multiplication 1.5.

If I set 20fps (actually I expect to have 30 according to rule above) the camera stream stuck with message:

SCF: Error InvalidState: Timeout waiting on frame start sensor guid 0, capture sequence ID = 3 (in src/services/capture/FusaCaptureViCsiHw.cpp, function waitCsiFrameStart(), line 507)
SCF: Error InvalidState:  (propagating from src/common/Utils.cpp, function workerThread(), line 114)
SCF: Error InvalidState: Worker thread ViCsiHw frameStart failed (in src/common/Utils.cpp, function workerThread(), line 133)
SCF: Error Timeout:  (propagating from src/services/capture/FusaCaptureViCsiHw.cpp, function waitCsiFrameEnd(), line 593)
SCF: Error Timeout:  (propagating from src/common/Utils.cpp, function workerThread(), line 114)
SCF: Error Timeout: Worker thread ViCsiHw frameComplete failed (in src/common/Utils.cpp, function workerThread(), line 133)
SCF: Error Timeout:  (propagating from src/services/capture/CaptureServiceEvent.cpp, function wait(), line 59)
Error: Camera HwEvents wait, this may indicate a hardware timeout occured,abort current/incoming cc

In kern.log I see:

Nov 24 11:17:53 nvidia-desktop kernel: [ 91.255030] [RCE] ERROR: camera-ip/vi5/vi5.c:745 [vi5_handle_eof] "General error queue is out of sync with frame queue. ts=115311592000 sof_ts=115311957696 gerror_code=2 gerror_data=2400060 notify_bits=120000"

If I run 6 cameras with 20fps(30 fps) in mode 2 I get:
SCF: Error IoctlFailed: (propagating from src/services/capture/FusaCaptureViCsiHw.cpp, function abort(), line 656)

and in kernel.log:

Nov 24 11:20:53 nvidia-desktop kernel: [  271.250342] [RCE] ERROR: camera-ip/vi5/vi5.c:745 [vi5_handle_eof] "General error queue is out of sync with frame queue. ts=295336937472 sof_ts=295337303136 gerror_code=2 gerror_data=400060 notify_bits=120000"
Nov 24 11:20:53 nvidia-desktop kernel: [  271.642291] [RCE] BUG: camera-ip/vi5/vi5.c:415 [vi5_check_falcon_failure] "VI FALCON FAILURE: 0x40000000"
Nov 24 11:20:53 nvidia-desktop kernel: [  271.709781] tegra186-cam-rtcpu bc00000.rtcpu: Alert: Camera RTCPU gone bad! restoring it immediately!!
Nov 24 11:20:54 nvidia-desktop kernel: [  272.642280] tegra194-vi5 15c10000.vi: capture control message timed out
Nov 24 11:20:54 nvidia-desktop kernel: [  272.642479] tegra194-vi5 15c10000.vi: vi capture reset failed
Nov 24 11:20:54 nvidia-desktop kernel: [  272.643185] tegra194-vi5 15c10000.vi: vi_capture_reset: control failed, errno 1
Nov 24 11:20:54 nvidia-desktop kernel: [  272.643365] tegra194-vi5 15c10000.vi: vi capture reset failed
Nov 24 11:20:54 nvidia-desktop kernel: [  272.643837] tegra194-vi5 15c10000.vi: vi_capture_reset: control failed, errno 1
Nov 24 11:20:54 nvidia-desktop kernel: [  272.644018] tegra194-vi5 15c10000.vi: vi capture reset failed
Nov 24 11:20:54 nvidia-desktop kernel: [  272.647990] ------------[ cut here ]------------
Nov 24 11:20:54 nvidia-desktop kernel: [  272.648208] channel context at 0 is busy
Nov 24 11:20:54 nvidia-desktop kernel: [  272.648278] WARNING: CPU: 0 PID: 2906 at /black_hd/jp5.0.2_r35.1_ga/kernel/nvidia/drivers/platform/tegra/rtcpu/capture-ivc.c:176 tegra_capture_ivc_notify_chan_id+0x188/0x1b0
Nov 24 11:20:54 nvidia-desktop kernel: [  272.648708] Modules linked in: fuse(E) xt_conntrack(E) xt_MASQUERADE(E) nf_conntrack_netlink(E) nfnetlink(E) xt_addrtype(E) iptable_filter(E) iptable_nat(E) nf_nat(E) nf_conntrack(E) nf_defrag_ipv6(E) nf_defrag_ipv4(E) libcrc32c(E) br_netfilter(E) lzo_rle(E) lzo_compress(E) zram(E) bnep(E) overlay(E) snd_soc_tegra210_ope(E) snd_soc_tegra186_asrc(E) snd_soc_tegra186_arad(E) snd_soc_tegra210_mvc(E) snd_soc_tegra186_dspk(E) snd_soc_tegra210_iqc(E) snd_soc_tegra210_afc(E) snd_soc_tegra210_admaif(E) snd_soc_tegra210_dmic(E) snd_soc_tegra210_mixer(E) snd_soc_tegra210_amx(E) snd_soc_tegra210_adx(E) snd_soc_tegra_pcm(E) snd_soc_tegra210_i2s(E) snd_soc_tegra210_sfc(E) ofpart(E) cmdlinepart(E) qspi_mtd(E) mtd(E) input_leds(E) rtk_btusb(E) btusb(E) btrtl(E) btbcm(E) btintel(E) aes_ce_blk(E) crypto_simd(E) cryptd(E) aes_ce_cipher(E) ghash_ce(E) sha2_ce(E) sha256_arm64(E) sha1_ce(E) snd_soc_spdif_tx(E) snd_soc_tegra_machine_driver(E) leds_gpio(E) max77620_thermal(E) snd_soc_tegra210_adsp(E)
Nov 24 11:20:54 nvidia-desktop kernel: [  272.649015]  snd_soc_tegra_utils(E) snd_soc_simple_card_utils(E) tegra_bpmp_thermal(E) r8168(E) tegra210_adma(E) nvadsp(E) userspace_alert(E) snd_soc_tegra210_ahub(E) snd_hda_codec_hdmi(E) snd_hda_tegra(E) snd_hda_codec(E) snd_soc_rt5640(E) r8169(E) snd_hda_core(E) snd_soc_rl6231(E) realtek(E) spi_tegra210_qspi(E) spi_tegra114(E) loop(E) binfmt_misc(E) ina3221(E) pwm_fan(E) nvgpu(E) nvmap(E) ramoops(E) reed_solomon(E) ip_tables(E) x_tables(E)
Nov 24 11:20:54 nvidia-desktop kernel: [  272.649150] CPU: 0 PID: 2906 Comm: CaptureSchedule Tainted: G           OE     5.10.104-tegra #2
Nov 24 11:20:54 nvidia-desktop kernel: [  272.649156] Hardware name: Unknown NVIDIA Jetson Xavier NX Developer Kit/NVIDIA Jetson Xavier NX Developer Kit, BIOS 1.0-d7fb19b 08/10/2022
Nov 24 11:20:54 nvidia-desktop kernel: [  272.649167] pstate: 40400009 (nZcv daif +PAN -UAO -TCO BTYPE=--)
Nov 24 11:20:54 nvidia-desktop kernel: [  272.649177] pc : tegra_capture_ivc_notify_chan_id+0x188/0x1b0
Nov 24 11:20:54 nvidia-desktop kernel: [  272.649185] lr : tegra_capture_ivc_notify_chan_id+0x188/0x1b0
Nov 24 11:20:54 nvidia-desktop kernel: [  272.649190] sp : ffff800023c2bb00
Nov 24 11:20:54 nvidia-desktop kernel: [  272.649203] x29: ffff800023c2bb00 x28: ffff44fdba5ad700 
Nov 24 11:20:54 nvidia-desktop kernel: [  272.649227] x27: 0000000000000043 x26: ffff44fd83e00400 
Nov 24 11:20:54 nvidia-desktop kernel: [  272.649248] x25: ffff44fd99079a38 x24: ffff450097210088 
Nov 24 11:20:54 nvidia-desktop kernel: [  272.649270] x23: 0000000000000050 x22: ffff450097210080 
Nov 24 11:20:54 nvidia-desktop kernel: [  272.649291] x21: ffff450097210a80 x20: 0000000000000000 
Nov 24 11:20:54 nvidia-desktop kernel: [  272.649312] x19: 0000000000000050 x18: 0000000000000000 
Nov 24 11:20:54 nvidia-desktop kernel: [  272.649334] x17: 0000000000000000 x16: 0000000000000000 
Nov 24 11:20:54 nvidia-desktop kernel: [  272.649355] x15: ffff44fdba5adc70 x14: ffffffffffffffff 
Nov 24 11:20:54 nvidia-desktop kernel: [  272.649409] x13: ffffc2427785ade8 x12: ffffc2427785aa1b 
Nov 24 11:20:54 nvidia-desktop kernel: [  272.649423] x11: 0000000000000000 x10: 0000000000000a80 
Nov 24 11:20:54 nvidia-desktop kernel: [  272.649436] x9 : ffff800023c2bb00 x8 : 2073692030207461 
Nov 24 11:20:54 nvidia-desktop kernel: [  272.649449] x7 : 20747865746e6f63 x6 : c0000000ffffefff 
Nov 24 11:20:54 nvidia-desktop kernel: [  272.649462] x5 : ffff4500bfd9d958 x4 : ffffc24277557968 
Nov 24 11:20:54 nvidia-desktop kernel: [  272.649475] x3 : 0000000000000001 x2 : ffff4500bfd9d960 
Nov 24 11:20:54 nvidia-desktop kernel: [  272.649509] x1 : 902dda3e38321500 x0 : 0000000000000000 
Nov 24 11:20:54 nvidia-desktop kernel: [  272.649522] Call trace:
Nov 24 11:20:54 nvidia-desktop kernel: [  272.649531]  tegra_capture_ivc_notify_chan_id+0x188/0x1b0
Nov 24 11:20:54 nvidia-desktop kernel: [  272.649540]  vi_capture_setup+0x35c/0x670
Nov 24 11:20:54 nvidia-desktop kernel: [  272.649547]  vi_channel_ioctl+0x35c/0x8c0
Nov 24 11:20:54 nvidia-desktop kernel: [  272.649564]  __arm64_sys_ioctl+0xa8/0xf0
Nov 24 11:20:54 nvidia-desktop kernel: [  272.649620]  el0_svc_common.constprop.0+0x7c/0x1c0
Nov 24 11:20:54 nvidia-desktop kernel: [  272.649628]  do_el0_svc+0x34/0xa0
Nov 24 11:20:54 nvidia-desktop kernel: [  272.649639]  el0_svc+0x1c/0x30
Nov 24 11:20:54 nvidia-desktop kernel: [  272.649649]  el0_sync_handler+0xa8/0xb0
Nov 24 11:20:54 nvidia-desktop kernel: [  272.649657]  el0_sync+0x16c/0x180
Nov 24 11:20:54 nvidia-desktop kernel: [  272.649664] ---[ end trace 1db75e38656c2dd0 ]---
Nov 24 11:20:54 nvidia-desktop kernel: [  272.649824] tegra194-vi5 15c10000.vi: failed to update control callback
Nov 24 11:20:54 nvidia-desktop kernel: [  272.650117] tegra194-vi5 15c10000.vi: vi capture setup failed
Nov 24 11:20:54 nvidia-desktop kernel: [  272.651388] tegra194-isp5 13e10000.host1x:isp@14800000: isp_capture_ivc_control_callback: unknown capture isp control resp
Nov 24 11:20:55 nvidia-desktop kernel: [  273.666252] tegra194-vi5 15c10000.vi: capture control message timed out
Nov 24 11:20:55 nvidia-desktop kernel: [  273.666539] tegra194-isp5 13e10000.host1x:isp@14800000: isp_capture_ivc_control_callback: unknown capture isp control resp
Nov 24 11:20:56 nvidia-desktop kernel: [  274.690238] tegra194-vi5 15c10000.vi: capture control message timed out
Nov 24 11:20:56 nvidia-desktop kernel: [  274.690431] tegra194-vi5 15c10000.vi: csi_stream_release: failed to disable nvcsi tpg on stream 2 virtual channel 0
Nov 24 11:20:56 nvidia-desktop kernel: [  274.691362] tegra194-isp5 13e10000.host1x:isp@14800000: isp_capture_ivc_control_callback: unknown capture isp control resp
Nov 24 11:20:57 nvidia-desktop kernel: [  275.714232] tegra194-vi5 15c10000.vi: capture control message timed out
Nov 24 11:20:57 nvidia-desktop kernel: [  275.714421] tegra194-vi5 15c10000.vi: vi_capture_release: release channel IVC failed
Nov 24 11:20:57 nvidia-desktop kernel: [  275.714699] ------------[ cut here ]------------
Nov 24 11:20:57 nvidia-desktop kernel: [  275.714723] WARNING: CPU: 0 PID: 2906 at /black_hd/jp5.0.2_r35.1_ga/kernel/nvidia/drivers/media/platform/tegra/camera/fusa-capture/capture-vi.c:960 vi_capture_release+0x2a8/0x2d0
Nov 24 11:20:57 nvidia-desktop kernel: [  275.715038] Modules linked in: fuse(E) xt_conntrack(E) xt_MASQUERADE(E) nf_conntrack_netlink(E) nfnetlink(E) xt_addrtype(E) iptable_filter(E) iptable_nat(E) nf_nat(E) nf_conntrack(E) nf_defrag_ipv6(E) nf_defrag_ipv4(E) libcrc32c(E) br_netfilter(E) lzo_rle(E) lzo_compress(E) zram(E) bnep(E) overlay(E) snd_soc_tegra210_ope(E) snd_soc_tegra186_asrc(E) snd_soc_tegra186_arad(E) snd_soc_tegra210_mvc(E) snd_soc_tegra186_dspk(E) snd_soc_tegra210_iqc(E) snd_soc_tegra210_afc(E) snd_soc_tegra210_admaif(E) snd_soc_tegra210_dmic(E) snd_soc_tegra210_mixer(E) snd_soc_tegra210_amx(E) snd_soc_tegra210_adx(E) snd_soc_tegra_pcm(E) snd_soc_tegra210_i2s(E) snd_soc_tegra210_sfc(E) ofpart(E) cmdlinepart(E) qspi_mtd(E) mtd(E) input_leds(E) rtk_btusb(E) btusb(E) btrtl(E) btbcm(E) btintel(E) aes_ce_blk(E) crypto_simd(E) cryptd(E) aes_ce_cipher(E) ghash_ce(E) sha2_ce(E) sha256_arm64(E) sha1_ce(E) snd_soc_spdif_tx(E) snd_soc_tegra_machine_driver(E) leds_gpio(E) max77620_thermal(E) snd_soc_tegra210_adsp(E)
Nov 24 11:20:57 nvidia-desktop kernel: [  275.715283]  snd_soc_tegra_utils(E) snd_soc_simple_card_utils(E) tegra_bpmp_thermal(E) r8168(E) tegra210_adma(E) nvadsp(E) userspace_alert(E) snd_soc_tegra210_ahub(E) snd_hda_codec_hdmi(E) snd_hda_tegra(E) snd_hda_codec(E) snd_soc_rt5640(E) r8169(E) snd_hda_core(E) snd_soc_rl6231(E) realtek(E) spi_tegra210_qspi(E) spi_tegra114(E) loop(E) binfmt_misc(E) ina3221(E) pwm_fan(E) nvgpu(E) nvmap(E) ramoops(E) reed_solomon(E) ip_tables(E) x_tables(E)
Nov 24 11:20:57 nvidia-desktop kernel: [  275.715449] CPU: 0 PID: 2906 Comm: CaptureSchedule Tainted: G        W  OE     5.10.104-tegra #2
Nov 24 11:20:57 nvidia-desktop kernel: [  275.715456] Hardware name: Unknown NVIDIA Jetson Xavier NX Developer Kit/NVIDIA Jetson Xavier NX Developer Kit, BIOS 1.0-d7fb19b 08/10/2022
Nov 24 11:20:57 nvidia-desktop kernel: [  275.715469] pstate: 40400009 (nZcv daif +PAN -UAO -TCO BTYPE=--)
Nov 24 11:20:57 nvidia-desktop kernel: [  275.715480] pc : vi_capture_release+0x2a8/0x2d0
Nov 24 11:20:57 nvidia-desktop kernel: [  275.715488] lr : vi_capture_release+0x2a8/0x2d0
Nov 24 11:20:57 nvidia-desktop kernel: [  275.715523] sp : ffff800023c2bb80
Nov 24 11:20:57 nvidia-desktop kernel: [  275.715532] x29: ffff800023c2bb80 x28: ffff44fdba5ad700 
Nov 24 11:20:57 nvidia-desktop kernel: [  275.715553] x27: 0000000000000000 x26: 0000000000000000 
Nov 24 11:20:57 nvidia-desktop kernel: [  275.715568] x25: 0000000000000000 x24: ffff44fdba5ad700 
Nov 24 11:20:57 nvidia-desktop kernel: [  275.715586] x23: 00000000ffffff92 x22: ffff44fd99079a00 
Nov 24 11:20:57 nvidia-desktop kernel: [  275.715600] x21: 000000000000ffff x20: 0000000000000001 
Nov 24 11:20:57 nvidia-desktop kernel: [  275.715640] x19: ffff44fd83e00400 x18: 0000000000000010 
Nov 24 11:20:57 nvidia-desktop kernel: [  275.715657] x17: 0000000000000000 x16: 0000000000000000 
Nov 24 11:20:57 nvidia-desktop kernel: [  275.715671] x15: ffff44fdba5adc70 x14: 633531203569762d 
Nov 24 11:20:57 nvidia-desktop kernel: [  275.715687] x13: 3439316172676574 x12: 7061635f6976203a 
Nov 24 11:20:57 nvidia-desktop kernel: [  275.715701] x11: 69762e3030303031 x10: 6572203a65736165 
Nov 24 11:20:57 nvidia-desktop kernel: [  275.715715] x9 : 6c65725f65727574 x8 : 5649206c656e6e61 
Nov 24 11:20:57 nvidia-desktop kernel: [  275.715729] x7 : 686320657361656c x6 : c0000000ffffefff 
Nov 24 11:20:57 nvidia-desktop kernel: [  275.715743] x5 : ffff4500bfd9d958 x4 : ffffc24277557968 
Nov 24 11:20:57 nvidia-desktop kernel: [  275.715758] x3 : 0000000000000001 x2 : 902dda3e38321500 
Nov 24 11:20:57 nvidia-desktop kernel: [  275.715775] x1 : 902dda3e38321500 x0 : 0000000000000000 
Nov 24 11:20:57 nvidia-desktop kernel: [  275.715791] Call trace:
Nov 24 11:20:57 nvidia-desktop kernel: [  275.715802]  vi_capture_release+0x2a8/0x2d0
Nov 24 11:20:57 nvidia-desktop kernel: [  275.715810]  vi_capture_shutdown+0x64/0xf0
Nov 24 11:20:57 nvidia-desktop kernel: [  275.715819]  vi_channel_close_ex+0x2c/0x80
Nov 24 11:20:57 nvidia-desktop kernel: [  275.715827]  vi_channel_release+0x2c/0x40
Nov 24 11:20:57 nvidia-desktop kernel: [  275.715838]  __fput+0x7c/0x230
Nov 24 11:20:57 nvidia-desktop kernel: [  275.715847]  ____fput+0x20/0x30
Nov 24 11:20:57 nvidia-desktop kernel: [  275.715858]  task_work_run+0x88/0x140
Nov 24 11:20:57 nvidia-desktop kernel: [  275.715870]  do_notify_resume+0x234/0x9f0
Nov 24 11:20:57 nvidia-desktop kernel: [  275.715879]  work_pending+0xc/0x384
Nov 24 11:20:57 nvidia-desktop kernel: [  275.715886] ---[ end trace 1db75e38656c2dd1 ]---

and device rebooted.

May need consider VI bandwidth.
NX vi max clock is about 460Mhz and VI able process 460Mhz*8PPC = 3.68Gbps

Also try boost the clocks to confirm.

sudo su
echo 1 > /sys/kernel/debug/bpmp/debug/clk/vi/mrq_rate_locked
echo 1 > /sys/kernel/debug/bpmp/debug/clk/isp/mrq_rate_locked
echo 1 > /sys/kernel/debug/bpmp/debug/clk/nvcsi/mrq_rate_locked
echo 1 > /sys/kernel/debug/bpmp/debug/clk/emc/mrq_rate_locked
cat /sys/kernel/debug/bpmp/debug/clk/vi/max_rate |tee /sys/kernel/debug/bpmp/debug/clk/vi/rate
cat /sys/kernel/debug/bpmp/debug/clk/isp/max_rate | tee /sys/kernel/debug/bpmp/debug/clk/isp/rate
cat /sys/kernel/debug/bpmp/debug/clk/nvcsi/max_rate | tee /sys/kernel/debug/bpmp/debug/clk/nvcsi/rate
cat /sys/kernel/debug/bpmp/debug/clk/emc/max_rate | tee /sys/kernel/debug/bpmp/debug/clk/emc/rate

I tried overclocking and it didn’t help to raise even +1 fps. This is one of the reasons I think there is some issue with software (driver) and not a limitation of hardware. Another reason is: okay we have 20fps*6cams for 3840x2160 (8MP), so if it’s some hardware bandwidth limitation I expect to have at least 13fps * 6 cameras for 4032x3040 (12MP), but maximum I get is 2-3fps for 6 cameras simultaneously for 12MP.

From my calculate

3.68Gbps/(3840x2160x10bitx 6) ~= 7 fps

We already reached 20fps*6 cameras in 3840x2160 resolution mode
The question is how to get the same fps with 4032x3040 resolution.
What can you suggest?

Boost the clocks if didn’t help that tell the HW bandwidth unable support it.

So you don’t think it’s software (driver) issue? What concern me is why we are able to reach 125fps (25fps5 cameras) in 3840x2160 mode, and only up to ~= 20 fps (2-3fps6cameras ) in 4032x3040.

Have a check the CPU usage if full loading for your case.

Thanks

Please see the 2nd msg in this thread.

What’s command to verify the frame rate?
What’s the BSP version?

Could you probe the MIPI signal to confirm the output frame interval and the MIPI clocks