Great article for beginners, with some good comparisons, tables and examples. However...
I work in storage ops and I've never heard of the "hot" and "cold" applied to latency in the way you describe
"hot" and "cold" I've only heard applied to
a) DR sites in varying states of readiness
b) storage that is basically online or offline
c) cache hit rates in a database table or network proxy
(which I think you mention in passing in the article)
I also don't quite follow why the article is entitled "Explain Distributed Storage" when it exclusively talks about single partition storage. Sounds like the storage is all in one place - so not distributed!
Thanks for the feedback. Your right that it wasn't made clear, and the concept hot & cold is applicable in a server setup. I have renamed the title accordingly and added the following lines in the article
Such mix of hot and cold storage can be done on both a single server, or (as per this series) on a much larger scale across multiple servers, or even multiple nations. Where one can take advantage of much cheaper servers in Germany or Frankfurt, where electricity and cooling are cheaper.
As for latency, admittingly its rarer as it happens mainly in HPC (High Performance Computing) on time-sensitive data. Where it has a mix of both large data set too big to fit into RAM, and fast CPU's crunching data in a non-sequential format.
Especially those weather prediction supercomputers, who only guesses it right half the time.
Though these days it becomes less of an issue with GPU based workloads (which is a topic on its own)
For further actions, you may consider blocking this person and/or reporting abuse
We're a place where coders share, stay up-to-date and grow their careers.
Great article for beginners, with some good comparisons, tables and examples. However...
I work in storage ops and I've never heard of the "hot" and "cold" applied to latency in the way you describe
"hot" and "cold" I've only heard applied to
a) DR sites in varying states of readiness
b) storage that is basically online or offline
c) cache hit rates in a database table or network proxy
(which I think you mention in passing in the article)
I also don't quite follow why the article is entitled "Explain Distributed Storage" when it exclusively talks about single partition storage. Sounds like the storage is all in one place - so not distributed!
btw that Katy Perry vid is ridiculous :)
Thanks for the feedback. Your right that it wasn't made clear, and the concept hot & cold is applicable in a server setup. I have renamed the title accordingly and added the following lines in the article
As for latency, admittingly its rarer as it happens mainly in HPC (High Performance Computing) on time-sensitive data. Where it has a mix of both large data set too big to fit into RAM, and fast CPU's crunching data in a non-sequential format.
Especially those weather prediction supercomputers, who only guesses it right half the time.
Though these days it becomes less of an issue with GPU based workloads (which is a topic on its own)