Archive for February, 2010

Erfahrungen mit Netcup

Posted by mark on February 25, 2010 under Private Observations, Technology

The following blog post is about a German hosting provider, and written in German.

Netcup vermietet keine virtuellen Server, sondern “logische Serverpartitionen“. Eine an sich völlig stabile und eprobte Technik aus der Zeit der Mainframes, an der es bis auf Kleinigkeiten nichts auszusetzen gibt. Wenn man denn soetwas wollte.

Der Unterschied zeigt sich, Read more »

Gentoo on a linux-vserver partition with wrong initstyle

Posted by mark on February 25, 2010 under Technology

Recently I’ve rented a server partition from a German provider which turned out to be a linux-vserver partition. About five or six years ago I have experimented with linux-vserver myself, still have headaches when it comes to its security implications…

Unfortunately the provider has not offered any Gentoo images. Despite that and by the means of the rescue shell, I have installed Gentoo on it. Here is how: Read more »

Tags: , ,

distributed key/value stores shootout (part 1)

Posted by mark on February 7, 2010 under Technology

For a project of mine I have been looking today on key/value stores. Redis, Tokyo Cabinet and Memcache are the popular ones, but I have been interested in benchmarking the distributed species of its kind (“DKVS”). Those are needed in high scalable systems as replacement for traditional databases, which happen not to scale well.

These are the criteria which the DKVS must meet:

  1. distribute data amongst one to four nodes (and the more the better)
  2. nodes must be able to be added on-the-fly,
  3. … and removed on-the-fly
  4. data has to be held redundantly, even after removal of a node
  5. data access has to be transparent, i.e. every node shall be equal
  6. scale with additional nodes – for every additional node there should be an increase of GET and SET operations per second up to the maximum dictated by the hardware and network

Read more »

Tags: , , ,

Redis benchmarks on Amazon EC2 and Rackspace Cloudservers

Posted by mark on February 3, 2010 under Technology

Amazon and Rackspace both provide virtualized servers billed per hour. That makes deploying scalable applications, especially with distributed key/value stores, very handy: You could launch new servers just as load, customer count or requests increase.

Today I’ve run the Redis benchmark on the SheevaPlug, Amazon EC2 and Rackspace Cloudservers to see where a small Redis database will perform the best. Read more »

Tags: , , , , ,