A bit of Ozzie slang to leaven the limey stuff? Nice. Keep it coming.
Amazon Web Services (AWS) says magnetic disks cannot handle modern NoSQL-powered applications, which have such high throughputs and generate such weirdly bursty traffic that spinning rust looks and feels as slow and awkward as tape. Chief Technology Officer Werner Vogels says as much on his blog: “Magnetic disks are rapidly …
From my perspective, storage is "online" (local memory ... fast ... a workstation), "nearline" (tape/disk available over the network, without human intervention ... sometimes slowish) & "offline" (tape that isn't physically available to the Memorex robot and needs human intervention ...). But then I come from a real hardware background.
“Magnetic disks are rapidly starting to exhibit tape-like properties and with modern workloads being increasingly random, they are becoming less and less suitable as a storage system.”
It's not modern workloads, it's the size of hard disks. As a hard disk gets bigger the amount of data accessed over a given time period, as a % of the total disk, either drops to where the access patterns look like archive storage or stays the same and hits the IOPS limit of the hard disk.
In fact HDDs are a fantastic storage system, just not so good at random access high IOPS storage.
As to if modern workloads are any different from previous workloads in terms of data access patterns, it's more of a case of how well the database is designed by the developer than the type of database itself.
All in all a pretty poor way to introduce a very useful addition to the EC2 family.
No I think it's a perfect way to introduce it.
All those cloud services are used by people who don't understand hardware, and are ready to pay to not understand it and have a running service.
Now what they call "modern workloads" is mostly the kind of bullshit startup pitchers love and are indeed going to buy, since who except a startup would want to pay 20 times the hardware costs just to be "in da cloud baby".
Nothing modern, nothing even huge there, just amazon waking up and selling ssd-equipped stuff. good to know but at 125K over 5 years they can stuff it down someone else's throat.
I'm currently planning the refresh of our Colo servers, we'll either replace the tin or move to the "cloud".. after much research, I can honestly say its cheaper and more reliable to simply replace the tin. And in actual fact I'm looking at getting a Nutanix ESX cluster, which not only offer ridiculous levels of IOps, but will also be safer from my perspective!
Biting the hand that feeds IT © 1998–2019