Ordina DockerOps

Transcript

1. NOMAD Mans Matulewicz
2. Infra Engineer @ Ordina @ ING Twitter: @Mans_M Github: @MansM mans@mansm.io
3. What is Nomad? § Distributed § Optimistically concurrent § Scheduler
4. Nomad setup
5. What is a scheduler? In short: A scheduler maps sets of work to a set of resources
6. Schedulers around us
7. Why do you want a scheduler? § Higher resource utilization − Bin packing − Over-subscription − Job queueing
8. Scheduling § You decide what to run § Nomad decides where and how to run − But you can force Nomad’s hands by using constraints (examples coming up)
9. Workloads Nomad can schedule § Docker containers § Rkt containers § Java § Isolated exec (chroot) § Raw exec § Qemu VM’s
10. Job types § Service § Batch § System
11. Evaluation enqueue
12. Evaluation dequeue
13. Plan generation
14. Plan execution
15. Nomad scheduling
16. Jobs § nomad run jobfile.nomad job “name” { group “name” { task “name” { driver resources } } }
17. Jobs Note: for a single task, you don’t need to create a taskgroup, as the group is created implicitly.
18. Jobs - Constraints § Force Nomad’s hand on a scheduling location § Can be on job, taskgroup and/or task level § Hostname, kernel.version, os.name, os.version, platform.aws.ami-id, platform.aws.instance-type, arch, driver.docker.version, etc
19. Jobs - Service Discovery • Consul needs to be installed on client machines • No need for in-container Consul agents • Nomad will register and deregister nodes/services
20. Service Discovery § Container provides a service § Container runs service on unknown port § Consul-template queries Consul server for values and reloads nginx with new config file
21. Jobs - Restart container
22. Jobs - Restarts § Sorry Bryan § Note: batch jobs have slightly different defaults!
23. Jobs - Scaling
24. Jobs - Updates
25. Jobs - Periodic
26. Local development § Make sure docker env vars are set if you want docker driver active § Fingerprinter of Mac instead of Docker host
27. Resources (Docker) § CPU − Based on shares − Will only kick in when Nomad client machine is under load § Memory − Based on total virtual memory, no swapping − Hard limit, app can crash or terminate when using more than specified! § Diskspace − Amount of GB’s that is required (including logs) § IO (Network planned for later releases)
28. How to install Nomad § Install Nomad servers § Connect the Nomad servers to each other § Install the Nomad clients and connect them to the servers § Run the workloads!
29. Unofficial roadmap § 0.4 − Persistent volumes − Multiple network cards − Enhancements to logging (Source: 0.3.0 release notes (current)) − ACL’s (Source: GitHub issue #589) § 0.5 − Vault (Source: Jim Benson ( Hashicorp solution eng @ Hashicorp meetup AMS March) § Hashicorp has not released an official roadmap
30. What I don’t like about Nomad § No UI
31. Demo setup
32. Demo
33. Questions § I might even have some answers § (and otherwise the guys after me)