What is typical contention ratio for cloud instances on a hardware?
I recently ran into a problem with a cloud instance hosted with one of the big guys, which shall be nameless. I saw intermittent 30%+ packet loss for a day or so before creating a ticket.
After some convincing that I'm not an idiot (they kept blaming my firewall config as the cause of the problem), the ticket was escalated to the right person and the instance was then moved to another hardware. All is now good.
(The official response I received was that other instance on the same hardware was "outbounding" which, from what I understand, is basically hogging all the bandwidth.)
What kind of contention ratio one can expect from a premium cloud hosting?
I paid extra for this instance to be on a gige port. It wasn't event hitting 20mbps and another instance was able to kill my connection. Say, for a host on a 10gige link, am I unreasonable to expect ~10x gige instances on it?
Assuming each VM has a max of 1Gbps, and the hypervisor has a 10Gbps uplink, no single VM should be able to saturate the link, at all.
Leading provider of enterprise SSD cloud platforms with 15 clouds in 3 regions
Dublin, London, Amsterdam, Vienna, Frankfurt, New York, Chicago, Dallas, Los Angeles, Toronto, Singapore, Jakarta, Hong Kong, Sydney