livepeer / livepeer/go-livepeer

CUDA_ERROR_UNKNOWN Transcoding errors for EU orchestrators

Open
#2,363 5 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

area: transcoding need: investigation
Dominant language
Go
Stars
586
Forks
226
Avg merge
1d 17h
Merged PRs (30d)
19

Description

**Describe the bug**
Me and a few other O's are getting lots of
```
Apr 13 10:02:04 koios livepeer[184664]: I0413 10:02:04.836866 184664 ot_rpc.go:140] Transcoding taskId=43790 url=https://93.119.2.215:8935/stream/af77db10/494.tempfile
Apr 13 10:02:05 koios livepeer[184664]: [h264_cuvid @ 0x7ff66cd9e780] ctx->cvdl->cuvidParseVideoData(ctx->cuparser, &cupkt) failed -> CUDA_ERROR_UNKNOWN: unknown error
Apr 13 10:02:05 koios livepeer[184664]: ERROR: decoder.c:64] Error sending packet to decoder : Generic error in an external library
Apr 13 10:02:05 koios livepeer[184664]: ERROR: transcoder.c:236] Could not decode; stopping : Generic error in an external library
Apr 13 10:02:05 koios livepeer[184664]: E0413 10:02:05.024776 184664 ffmpeg.go:609] Transcoder Return : Generic error in an external library
Apr 13 10:02:05 koios livepeer[184664]: E0413 10:02:05.024865 184664 ot_rpc.go:193] manifestID=fb0acd4d-b9b6-4d44-ba21-0e67ac467440 seqNo=494 orchSessionID=af77db10 taskId=43790 Transcoding done for taskId=43790 url=https://93.119.2.215:8935/stream/af77db10/494.tempfile dur=136.829413ms err="Generic error in an external library"
Apr 13 10:02:05 koios livepeer[184664]: E0413 10:02:05.024882 184664 ot_rpc.go:248] manifestID=fb0acd4d-b9b6-4d44-ba21-0e67ac467440 seqNo=494 orchSessionID=af77db10 taskId=43790 Unable to transcode err="Generic error in an external library"
```
It doesn't seem to drop the stream itself, and only seems to happen for EU orchestrators (https://discord.com/channels/423160867534929930/932724294230900776/962928882665783306)

**To Reproduce**
Have an active Orchestrator in the EU region

**Expected behavior**
To transcode the segments without error

**Desktop:**
- OS: Arch Linux (Also on Ubuntu 20)
- Livepeer 0.5.29
- Driver Version: 510.60.02
- CUDA Version: 11.6

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with the reported errors in decoder.c:64, transcoder.c:236, and the callers logged from ot_rpc.go:140 and ffmpeg.go:609. Compare transcoding behavior for EU orchestrators under the stated OS, driver, and CUDA versions, then verify that segments transcode without CUDA_ERROR_UNKNOWN.

Written by the indexing model from the issue text.

Assessment

Tech stack
arch-linux, linux, ubuntu
Domain
audio-video-rtc
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.