[HN Gopher] Markov Chains for Queueing Systems
___________________________________________________________________
Markov Chains for Queueing Systems
Author : kqr
Score : 34 points
Date : 2022-08-01 19:03 UTC (3 hours ago)
(HTM) web link (two-wrongs.com)
(TXT) w3m dump (two-wrongs.com)
| jschveibinz wrote:
| "Capacity planning" is the general term used in systems analysis
| and design. Here is another article of interest on the topic:
|
| https://www.helpsystems.com/blog/why-you-need-queuing-theory...
| zokier wrote:
| I know its not main point of the article, but the "Bigger Holding
| Space" results are surprising to me. The idle time barely changes
| at all, and even the response time change is very moderate (<10%
| increase), while rejection rate drops three orders of
| magnitude(!). I suppose this is somehow an artifact on the
| particular distributions chosen in the example? Also intuitively
| tail-end latency (like p99) would suffer more when you add
| queues, I guess figuring that out analytically is more
| difficult..
| kqr wrote:
| Author here: TL;DR of this exercise would be
|
| "If what you need is a fast system, don't start with a slow
| system and try to load balance or queue your way out of your
| problems. Design a fast system from the start."
| erichocean wrote:
| Have you read _The Power of Two Choices in Randomized Load
| Balancing_?[0]
|
| [0]
| https://www.eecs.harvard.edu/~michaelm/postscripts/tpds2001....
___________________________________________________________________
(page generated 2022-08-01 23:01 UTC)