New-age Transactional Systems - Not Your Grandpa's OLTP
John Hugg discusses high volume transaction processing applications with high and low frequency profiles, and how VoltDB can be used for that purpose.
The content has been bookmarked!
There was an error bookmarking this content! Please retry.
Posted by Johan Strandler on Aug 28, 2007
The Millicomputer and MilliCluster hardware is developed as "Open Hardware", which means that the hardware design won't be owned by a single vendor. The Millicomputer is using LInux as the operating system and the hardware is based on a Freescale i.MX31 System-on-a-chip component using microSDHC flash memory. While the Millicomputer doesn't require much power by itself, external ethernet connections do. In order to save power, Cockcroft introduces the concept of "Enterprise MilliCluster", which allows 14 Millicomputers to be load balanced behind one Twin 1GB Ethernet external interface ethernet port by connecting by connecting them through a USB switch using Linux USBNet transport. The form factor to such a MilliCluster makes it possible to put 8 clusters plus a power unit on a single 1U rack, which consumes less than 160W - probably much less.
By comparing a MilliCluster based 1U server with Suns x4100 Operon and T1000 Niagara servers Cockcroft says:
"For the same 1U package size and similar cost per package power is much less than a Niagara, less than half of an Opteron system. Total RAM capacity is similar, the raw CPU GHz is double, worst case GHz per Watt is six times better than Opteron, three times better than Niagara. Flash storage is 1000x faster for both random and sequential IOPS.
Applications suitable to run on Millicomputers include:
Although in very early development, Millicomputing appears to be quite a paradigm shift; could this be the enterprise hardware platform of the (greener) future?Applications that can be broken into small chunks, small scale or horizontally scalable web workloads, legacy applications that used to run on 5 year old machines, graphical video caves and storage I/O intensive applications are the best candidates to run on Millicomputers."
John Hugg discusses high volume transaction processing applications with high and low frequency profiles, and how VoltDB can be used for that purpose.
Kevlin Henney examines code samples to see what can be learned from them starting from the premise that one won’t write great code unless he knows how to read it.
Jason Ayers share the observations he made watching a team of developers collaborating in real time on the same code base, pushing XP, pair programming and continuous integration to their extremes.
Michael Snoyman presents Yesod, a web framework written in Haskell and containing a web server, templating, ORM, libraries (templating, gravatar, etc.).
Richard Kreuter and Kyle Banker on how to avoid classical RDBMS transactional systems by using compensation mechanisms, transactional messaging or transactional procedures.
Attila Szegedi talks about performance tuning Java and Scala programs at Twitter: how to approach GC problems, the importance of asynchronous I/O, when to use MySQL/Cassandra/Redis, and much more.
One category of risk that project teams need to ensure they address is business value failure – delivering a product that fails to provide value for the business investor.
InfoQ spoke to the authors of Software Systems Architecture on a couple of new topics, the System Context viewpoint and Agile, which have been added to the second edition.
No comments
Watch Thread Reply