Jakub Sokołowski c474a3311d
logs.nimbus: leave memory for Lucene, use 32 GB heap
https://github.com/status-im/infra-nimbus/issues/96

"The moral of the story is this: even when you have memory to spare, try
to avoid crossing the 32 GB heap boundary. It wastes memory, reduces CPU
performance, and makes the GC struggle with large heaps."

https://www.elastic.co/guide/en/elasticsearch/guide/current/heap-sizing.html#compressed_oops
https://www.elastic.co/guide/en/elasticsearch/guide/current/heap-sizing.html#_give_less_than_half_your_memory_to_lucene

Signed-off-by: Jakub Sokołowski <jakub@status.im>
2022-06-01 12:28:48 +02:00
2022-05-24 18:21:09 +02:00
2022-05-05 16:36:24 +02:00

Description

This repo defines Nimbus cluster infrastructure.

Endpoints

These are Beacon API endpoints intended for community testing.

Endpoint Host
http://unstable.mainnet.beacon-api.nimbus.team/ metal-01.he-eu-hel1.nimbus.mainnet
http://testing.mainnet.beacon-api.nimbus.team/ metal-02.he-eu-hel1.nimbus.mainnet
http://unstable.prater.beacon-api.nimbus.team/ metal-01.he-eu-hel1.nimbus.prater
http://testing.prater.beacon-api.nimbus.team/ metal-02.he-eu-hel1.nimbus.prater
http://unstable.kiln.beacon-api.nimbus.team/ metal-01.he-eu-hel1.nimbus.kiln

These nodes have no validators attached.

Dashboards

There's a dedicated Kibana dashboard for Nimbus fleet logs: https://nimbus-logs.infra.status.im/

There are explorers available for various testnets:

Repo Usage

For how to use this repo read the Infra Repo Usage doc.

Description
Infrastructure for Nimbus cluster
https://nimbus.team
Readme
Languages
Python 62.3%
HCL 23.6%
Shell 6.8%
Makefile 3.4%
Nix 2.1%
Other 1.8%