Score:0

GCP - GPU staging time reduction

cn flag

I have an application that requires the smallest boot-time/TTL possible with GPUs attached to a VM in GCP CE. To keep cost down, my infrastructure is dependent on starting and stopping instances as demand increases/decreases.

I have tried multiple different distros, clear linux, minimal installs of Fedora, minimalised Debian, reductions to kernel and userspace - systemd-analyze says my boot-time is 3s, but when I start the instance on GCP it takes 30s in staging to label the instance as running. This only occurs when the gpu is attached to the VM and when removed the VM starts within seconds. This is consistent across all distros and bootimages.

Is there any packages or documentation I am missing to speed up this staging-time with a GPU attached or is this a limitation with GCP's internal staging of GPU instances?

I'd much appreciate any help or advice.

If you're also experiencing this issue and would like to track its progress, I created a issue report: https://issuetracker.google.com/issues/200575905

mangohost

Post an answer

Most people don’t grasp that asking a lot of questions unlocks learning and improves interpersonal bonding. In Alison’s studies, for example, though people could accurately recall how many questions had been asked in their conversations, they didn’t intuit the link between questions and liking. Across four studies, in which participants were engaged in conversations themselves or read transcripts of others’ conversations, people tended not to realize that question asking would influence—or had influenced—the level of amity between the conversationalists.