[MESOS-10033] Design per-task cgroup isolation

• Type: Task
• Status: Resolved
• Priority: Major
• Resolution: Done
• Fix Version/s: 1.10.0
• Labels: foundations
• Epic Link: Resource Limits/Requests
• Sprint: Studio 4: RI-23 64
• Story Points: 5
• Assignee: Andrei Budnik
• Reporter: Greg Mann
• Created: 20/Nov/19 15:57
• Updated: 21/Jan/20 15:22
• Resolved: 31/Dec/19 14:36

Description

To provide container resource isolation which more closely matches the isolation implied by the Mesos nested container API, we should limit CPU and memory on a per-task basis. The current Mesos containerizer implementation limits CPU and memory at the level of the executor only, which means that tasks within a task group can burst above their CPU or memory resources. Instead, we should apply these limits using per-task cgroups.