[MAPREDUCE-6066] Speculative attempts should not run on the same node as their original attempt

• Type: Bug
• Status: Resolved
• Priority: Major
• Resolution: Duplicate
• Affects Version/s: 2.5.0, 2.6.0
• Component/s: applicationmaster, scheduler
• Assignee: Unassigned
• Reporter: Todd Lipcon
• Created: 03/Sep/14 02:30
• Updated: 07/Jul/21 15:22
• Resolved: 07/Jul/21 15:22

Description

I'm seeing a behavior on trunk with fair scheduler enabled where a speculative reduce attempt is getting run on the same node as its original attempt. This doesn't make sense – the main reason for speculative execution is to deal with a slow node, so scheduling a second attempt on the same node would just make the problem worse if anything.

Issue Links

• is duplicated by: MAPREDUCE-7169 Speculative attempts should not run on the same node