[bun] incorrect/huge worker-to-main latency

[twoeths]

Describe the bug

this is on a bun node subscribing to all subnets, some message latency is negative, some is significantly higher than NodeJS

same type of node using NodeJS

Expected behavior

message latency should be comparable to NodeJS

Steps to reproduce

No response

Additional context

No response

Operating system

Linux

Lodestar version or commit hash

unstable

[twoeths]

there is also big scrape duration

and weird event lag issues