How we used RabbitMQ in wrong way at a scale
In LINE, we are building/operating multiple large OpenStack Clusters for 2 years.
Recently the scale of biggest cluster in our cloud exceed 700 hypervisors, and started to experience RabbitMQ related outage and learned what we should have done. We believe RabbitMQ operation for OpenStack is one of the most difficulties and paint points of OpenStack Operators. In this talk, we will share what we faced and how we solved based of our failure story.
What can I expect to learn?
* Introduce configuration/metrics/architecture we have to consider for large scale OpenStack Cluster
* Introduce oslo.messaging patches which help large cluster
* Introduce our activity about rpc statistics to help user identify problem and tuning
Monday, November 4, 3:00pm-3:40pm (7:00am - 7:40am UTC)
Difficulty Level: Beginner
Tags:
Arch / Ops
OpenStack
Senior Software engineer
Yuki Nishiwaki is working as a Senior Software Engineer at LINE Corporation. He is leading the Private Cloud Platform team which is in charge of developing/operating Managed Kubernetes Service and OpenStack Cluster on a large scale in LINE.
Prior to LINE Corp, He have been working at Cloud technology R&D team in NTT Communications for about 4 years. He had worked on OpenStack related works... FULL PROFILE
Software Engineer
In Line Corp, he is working as a Software Engineer as a member of Private Cloud Platform team which is in charge of developing/operating Managed Kubernetes Service and
OpenStack Cluster on a large scale in LINE.
* * *
Prior to LINE Corp, He was working in NTT DATA as a Software Engineer mainly focusing on OpenStack upstream contribution.
Worked on mainly NUMA, HA and API layer features. FULL PROFILE
Download App
