News for hackers. Stuff that matters.

A comment on Performance variation in ‘identical’ processors. Parent comment

Re:Performance variation in ‘identical’ processors by judge2020 on Sunday January 05, 2020 @10:45PM (#21966264)
don't think this would work on GCP since they regularly preform 'live migrations' https://cloud.google.com/compute/docs/instances/live-migrati...
[ Parent | on HN ]
Re:Performance variation in ‘identical’ processors by eru on Sunday January 05, 2020 @11:49PM (#21966523)
I think they don't live-migrate pre-emptible instances: https://cloud.google.com/compute/docs/instances/live-migrati...
[ Parent | on HN ]
Re:Performance variation in ‘identical’ processors by dilyevsky on Monday January 06, 2020 @03:20AM (#21967505)
They just preempt them when they need to migrate.
[ Parent | on HN ]
Re:Performance variation in ‘identical’ processors by eru on Monday January 06, 2020 @03:23AM (#21967518)
Yes. So at least you explicitly know when you are getting new physical computers, so you can run your selection process again.
[ Parent | on HN ]