Ray 2.32.0 logging issue

Ray Libraries (Data, Train, Tune, Serve)
1

I used “logging.getLogger(“ray.data”).setLevel(logging.CRITICAL)” to suppress most of the logging messages and works well with ray 2.31.0 and earlier version. For 2.32.0, it does not work anymore. I’ve got a large number of the following message coming out. Does one need other command to suppress these messages?

  ✔️  Dataset execution finished in 2.08 seconds: 100%|█████████████████| 1/1 [00:02<00:00,  2.08s/it]]
  - Write: 0 active, 0 queued, [cpu: 0.0, objects: 183.0B]: 100%|███████| 1/1 [00:02<00:00,  2.08s/it]
  ✔️  Dataset execution finished in 0.01 seconds: 100%|█████████████████| 1/1 [00:00<00:00, 78.19it/s]]
  - Write: 0 active, 0 queued, [cpu: 0.0, objects: 183.0B]: 100%|███████| 1/1 [00:00<00:00, 73.92it/s]
  ✔️  Dataset execution finished in 0.01 seconds: 100%|█████████████████| 1/1 [00:00<00:00, 79.34it/s]]
  - Write: 0 active, 0 queued, [cpu: 0.0, objects: 183.0B]: 100%|███████| 1/1 [00:00<00:00, 75.41it/s]
  ✔️  Dataset execution finished in 0.01 seconds: 100%|█████████████████| 1/1 [00:00<00:00, 78.35it/s]]
  - Write: 0 active, 0 queued, [cpu: 0.0, objects: 183.0B]: 100%|███████| 1/1 [00:00<00:00, 73.74it/s]
  ✔️  Dataset execution finished in 0.01 seconds: 100%|█████████████████| 1/1 [00:00<00:00, 78.74it/s]]
  - Write: 0 active, 0 queued, [cpu: 0.0, objects: 183.0B]: 100%|███████| 1/1 [00:00<00:00, 73.28it/s]
  ✔️  Dataset execution finished in 0.02 seconds: 100%|█████████████████| 1/1 [00:00<00:00, 44.50it/s]]
  - Write: 0 active, 0 queued, [cpu: 0.0, objects: 0.0B]: 100%|█████████| 1/1 [00:00<00:00, 43.16it/s]
  ✔️  Dataset execution finished in 0.01 seconds: 100%|█████████████████| 1/1 [00:00<00:00, 78.46it/s]]
2

hey @wxie2013 - someone else (maybe it was you?) also reported this on Ray Slack. I’m beginning to think this is a bug; can you please cut a GH issue and link it here and the Ray Core team will investigate.

3

Hi @Sam_Chan, it’s probably me. ray.train has a different logging issue that can’t be silenced with all loggers set to be critical. Can you please be more specific on how to cut a GH issue and link it here?

1 Like
4

Go to the Ray Github and click Issues > New Issue > Bug.

5

Thanks. The bug report has been submitted

1 Like