Skip to content
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

Connection overflow #692

Closed
alexvanin opened this issue Jul 13, 2021 · 1 comment · Fixed by #694
Closed

Connection overflow #692

alexvanin opened this issue Jul 13, 2021 · 1 comment · Fixed by #694
Assignees
Labels
bug Something isn't working
Milestone

Comments

@alexvanin
Copy link
Contributor

It seems that neofs-node v0.22.2 does not reuse existing connections and creates new one on each request. At one time there is no enough ulimit to open new connection and we see errors like in #676.

Here the example from one of our storage nodes couple hours after restart.

# ls -l /proc/9758/fd | grep socket  | wc -l
568
# lsof -i -a -p 9758 | grep 199.247.0.222 | wc -l
199

I guess we need to look at client cache. Probably it is related to group address support.

@alexvanin
Copy link
Contributor Author

How to debug it in neofs-dev-env.

  1. Find pid of the storage node
$ docker inspect -f '{{.State.Pid}}' s01
788785
  1. See open connections in lsof, e.g.
sudo nsenter -t 788785 -n lsof -i -a -p 788785 2>&1 | grep -- '->s0'

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working
Projects
None yet
Development

Successfully merging a pull request may close this issue.

1 participant