Skip to content

c-kzg verifyCellKzgProofBatch high process_heap_bytes #7930

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
twoeths opened this issue Jun 6, 2025 · 2 comments
Open

c-kzg verifyCellKzgProofBatch high process_heap_bytes #7930

twoeths opened this issue Jun 6, 2025 · 2 comments
Labels
meta-bug Issues that identify a bug and require a fix.

Comments

@twoeths
Copy link
Contributor

twoeths commented Jun 6, 2025

Describe the bug

Got different behavior of nodes regarding process_heap_bytes

  • node 0 - MIN_DATA_COLUMN_SIDECAR_BATCH_SIZE = 4: it's >= 45GB and keeps growing
Image

here we batch ~4 messages per ckzg.verifyCellKzgProofBatch() call

Image
  • node 1 - MIN_DATA_COLUMN_SIDECAR_BATCH_SIZE = 16: it started with 3.3GB then grew to ~16GB then ~47GB in the end
Image

here we batch ~10 messages per ckzg.verifyCellKzgProofBatch() call

Image
  • node 2 - MIN_DATA_COLUMN_SIDECAR_BATCH_SIZE = 32: it stayed at < 3GB then jumped to ~35GB in the end
Image

here we batch ~13.5 messages per ckzg.verifyCellKzgProofBatch() call

Image
  • node 3 - MIN_DATA_COLUMN_SIDECAR_BATCH_SIZE = 64, it's ~3GB for ~6h then started to jumped to 4.7GB
Image

here we batch ~15 messages per ckzg.verifyCellKzgProofBatch() call

Image

Expected behavior

it should not grow over time, ideally should be ~<= 13GB, similar to a mainnet node subscribing to all subnets

Steps to reproduce

No response

Additional context

No response

Operating system

Linux

Lodestar version or commit hash

te/validate_data_column_sidecar_in_batch

@twoeths twoeths added the meta-bug Issues that identify a bug and require a fix. label Jun 6, 2025
@twoeths
Copy link
Contributor Author

twoeths commented Jun 7, 2025

  • node 0 rss / process_heap_bytes increased to 72.5GB
Image
  • same to node 1 and node 2
Image
  • node 3 spiked to ~52.5GB then dropped back down to ~17GB
Image

@twoeths
Copy link
Contributor Author

twoeths commented Jun 7, 2025

it also happens on peerDAS so it's an issue of c-kgz verifyCellKzgProofBatch itself

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
meta-bug Issues that identify a bug and require a fix.
Projects
None yet
Development

No branches or pull requests

1 participant