“the process of institutionalizing a new technology will change the institution” — ViewYonder » Poor IT hygiene is a barrier to technology adoption
“Recently Mike Stonebraker wrote an influential paper titled One Size Fits All: An Idea Whose Time Has Come and Gone. In this paper, Mike argued that the existing commercial RDBMS offerings do not meet the needs of many important market segments. In a presentation with the same title, Stonebraker argues that StreamBase special purpose stream processing system beat the RDBMS solutions in benchmarks by 27x, that Vertica, a special purpose data warehousing product beat the RDBMS incumbents by never less than 30x, and H-Store (now VoltDB), a special purpose transaction processing system, beat the standard RDBMS offerings by a full 82x.” — Perspectives - One Size Does Not Fit All
“This conclusion may be surprising — people notice a half second delay? — but we had a similar experience at Amazon.com. In A/B tests, we tried delaying the page in increments of 100 milliseconds and found that even very small delays would result in substantial and costly drops in revenue.” — Perspectives - The Cost of Latency
“Excellent set of distributed systems rules of thumb:
o L1 cache reference 0.5 ns
o Branch mispredict 5 ns
o L2 cache reference 7 ns
o Mutex lock/unlock 25 ns
o Main memory reference 100 ns
o Compress 1K bytes with Zippy 3,000 ns
o Send 2K bytes over 1 Gbps network 20,000 ns
o Read 1 MB sequentially from memory 250,000 ns
o Round trip within same datacenter 500,000 ns
o Disk seek 10,000,000 ns
o Read 1 MB sequentially from disk 20,000,000 ns
o Send packet CA->Netherlands->CA 150,000,000 ns”
— Jeff Dean: Design Lessons and Advice from Building Large Scale Distributed Systems
“
A few NSPs quietly mentioned that Google has already been offering to sell bandwidth on their part of the cable in the wholesale market. This puts some NSPs between a rock and a hard competitive place — with one of their biggest customers!
This creates an intriguing dilemma for Google, according to a financial markets expert I chatted with at the Capacity show. Google’s P/E valuation has been driven by its reputation for disruptive technologies since the beginning of Google-time. Although it’s unlikely, if they also start operating as a telecom utility (offering bandwidth and all sorts of cellular technology/services), that could change. P/E values for NSPs, wireless equipment manufacturers and wireless operators are rather modest to say the least. So even if Google has spectacular success selling bandwidth, I can’t imagine it would contribute to even a modest change in their P/E expectations.
” — IP Backbone: Hard sell, not so much - Renesys Blog“
The reason I assert you will end up with break-even or a loss is because if you start to accurately identify the additional expenditures necessary to maintain and operate that investment, then costs start to dramatically increase relative to this single expenditure. To offset these costs, a business would need on the order of a 25% costs reduction or increase in profits to have a “return”. As I noted above, TCO and ROI are notional concepts designed to be manipulated by those with budgets to justify expenditures. I have yet to see one CIO actually go back and reconcile the initial ROI estimates against the original assertion past year one.
[…]
The metric I recommend is total service cost (TSC). Basically stated as a formula, TSC is:
(Cost of Infrastructure + Cost of Operations + Cost of Software + Cost of Risk) – Billed Usage = TSC
[…]
At this point, you’ve laid out very little capital to get started, your development costs were kept relatively low and you’re service is being managed by your Cloud provider. This sounds resoundingly like the story many startups delivering Cloud-based services are prescribing as success. However, because you highly leveraged with a significant number of dependencies on external agencies, your cost of risk is significantly higher than if you has hosted it in a co-located facility with less compute capacity and used your own employees, which maintains knowledge internally to your company, which causes you to set a higher price point for your unit of billing, which results in slower uptake in sales.
” — A Better Metric for Analyzing the Value of the Cloud — CIOUpdate.comBlades Made Simple · Making blade servers simple -
A blog about blades, heavy on networking info, fairly technical, across most major vendors (incl. cisco ucs).
“It depends. I love the concept of the Cisco UCS platform. Servers are seen as processors and memory – building blocks that are centrally managed. Easy to scale, easy to size. However, is it for the average datacenter who only needs 5 servers with high I/O? Probably not. I see the Cisco UCS as a great platform for datacenters with more than 14 servers needing high I/O bandwidth (like a virtualization server or database server.) If your datacenter doesn’t need that type of scalability, then perhaps going with IBM’s BladeCenter solution is the choice for you. Going the IBM route gives you flexibility to choose from multiple processor types and gives you the ability to scale into a unified solution in the future. While ideal for scalability, the IBM solution is currently more complex and potentially more expensive than the Cisco UCS solution. ” — Blades Made Simple · Cisco UCS vs IBM BladeCenter H
Dilbert comic strip for 11/18/2009 from the official Dilbert comic strips archive.