System Management by Exception: Availability cluster

Tuesday, October 16, 2012

Availability vs. Capacity

Continuing the previous posts about "Battle between "Gut-feeling" and Engineering." ....

Engineer 2: Igor - if you would like to find further extensions of your equation, you might check out Volume 1 of "Breaking the Availability Barrier," which I co-authored and which is available on Amazon. Also, check out several papers I published in the Availability Digest in the Geek Corner (http://www.availabilitydigest.com/articles.htm). A subscription is free.

Igor Trubin: Yes, I have already looked briefly at your book and referenced it in my blog, Very good book and I plan to read that all.

UPDATE: After reading one of suggested above papers ( "Calculating Availability - Redundant Systems" Some useful rules come out of the derivation of the availability equation.) I was able to show to my client that the following more general cluster (system) availability formula proves that for three-node cluster (n=3) the one spare node (s=1) configuration could provide approximately the same cluster availability as in the case of two spare nodes (s=2) but Capacity usage could be a critical factor as seen below.

That could be a way to save money by allocating less capacity with the same number but more reliable nodes.

Igor Trubin

Igor Trubin began his engineering career in 1979 as an IBM/370 systems engineer. He earned a Ph.D. in Robotics from St. Petersburg Technical University in 1986 and spent 12 years there as a professor teaching CAD/CAM and Robotics. He has published and presented more than 60 technical papers and conference presentations in robotics, artificial intelligence, IT performance, capacity management, anomaly detection, and FinOps. After moving to the U.S. in 1999, Igor worked at Capital One, IBM, and SunTrust Bank in senior engineering, architecture, and management roles. His 2002 CMG paper on exception detection received a Best Paper Award. He later developed Perfomalist.com, based on his original methods for anomaly, change-point, and trend detection, and created the online course “Performance Anomaly Detection.” At Capital One, he led development of cloud capacity-management and FinOps solutions, including the award-winning OptiCloud application. He has served on the CMG Board of Directors since 2015. Now semi-retired, Igor focuses on research, writing, and consulting. His current work expands his concept of the “Area of Normal Functioning” (ANF) from technical systems to human, orga

Wednesday, September 12, 2012

The Right Number of Cluster Redundancy to Achieve the Availability Goal. Trubin's Law #4!

...Still playing with the availability algebra exercise, that I started in my other post: How to Calculate Availability of Clustered Infrastructure for Multi-Tier Application

I have built the following two charts to see how the same availability goal can be achieved by different number of redundancy.

That of course possible if the less redundant configuration has more available individual components.

By the way, interesting that if the component availability has one 9's (90.00%), then increasing redundancy on +1 gives the additional one 9's for the cluster availability.

So, the equation

has the following solution: A=0.9 for any integer n within the interval (0,∞)

It is probably the known law in the availability algebra. If not let's call that Trubin's law #4! ;)
________
This Saga of 9's continuous in the next post:

Cluster Availability 9's Equation