Hi Simon - what does your cluster topology look like? Are your hadoop services running in containers, VMs, bare metal? How much ram do your slaves and master have, and is there any swap space on those machines?
Off the cuff, it sounds like one or more of your machines is running out of memory, but more details about your environment would help to know for sure.
Hi Simon - what does your cluster topology look like? Are your hadoop services running in containers, VMs, bare metal? How much ram do your slaves and master have, and is there any swap space on those machines?
Off the cuff, it sounds like one or more of your machines is running out of memory, but more details about your environment would help to know for sure.