Scaling infrastructure beyond containers

@wendigo

Mateusz „Serafin” Gajewski • AWS UG Meetup

Scaling infrastructure beyond containers

@wendigo

Agenda

• Evolution of infrastructure at Allegro,

• Why Apache Mesos™?

• Apache Mesos key concepts,

• Future of datacenter and cloud computing?

@wendigo

History of scaling infrastructure @ Allegro

@wendigo

Infrastructure 1.0

@wendigo

Job allocation problem

@wendigo

Web Scale Resource management

100s dots 100s dots

@wendigo

Infrastructure 2.0

1000s dots another 1000s dots

@wendigo

Infrastructure 2.1

1000s dots another 1000s dots

@wendigo

Challenges

• cloud not used as cloud ;),

• high cost of virtualization,

• effective resource utilization,

• microservice architecture,

• spread of new technologies,

• heterogenous resources,

• scalability, fault tolerance & HA,

• performance isolation,

• data processing at scale

@wendigo

Beyond cloud computing

@wendigo

Holly Grail of TCO

@wendigo

Infrastructure 3.0

A Platform for Fine-Grained Resource Sharing in the Data Center

@wendigo

Scheduling

@wendigo

Cluster scheduling

@wendigo

Mesos architecture

@wendigo

Mesos frameworks

@wendigo

Offers

@wendigo

Execution isolation

@wendigo

External Containerizers

@wendigo

Mesos HA

• master election/failover with ZooKeeper,

• master maintains soft-state,

• framework state reconciliation,

• slave checkpointing,

• slave recovery,

• framework checkpointing

@wendigo

Beyond offers

• offer filters (constraints),

• static (pre-startup) reservations,

• dynamic (post-startup) reservations,

• oversubscription,

• persistent volumes,

• pluggable allocator scheduling policy (fair, priority based)

@wendigo

Mesos frameworks

@wendigo

Mesos recap

• „programming against the datacenter",

• distributed datacenter kernel,

• two-level multi-resource scheduler,

• scalable, highly-available & fault-tolerant,

• performance isolation with containers,

• exposes homogeneous resources,

• elastic, dynamic partitioning,

• high resource utilization

@wendigo

Future Datacenter

@wendigo

IaaC

@wendigo

Efficient utilization

@wendigo

Google’s Omega

source: Omega: flexible, scalable schedulers for large compute clusters

Questions?

http://meetup.com/allegro.tech http://allegro.tech

@AllegroTechBlog

Work with us