Starfish is a clustered file storage system that keeps very large amounts of data safe and accessible – even in the face of massive hard drive and storage node failures. More specifically, Starfish is a highly-available, fully decentralized, clustered storage file system. It provides a distributed POSIX-compliant storage device that can be mounted like any other drive under Linux or Mac OS X. The resulting fault-tolerant storage network can store files and directories, like a normal file system – but unlike a normal file system, it can handle multiple catastrophic disk and machine failures.
The storage network automatically provides file mirroring, disaster recovery, and high-availability in the event of multiple storage or metadata node failures. Like the starfish, this file system can be damaged severely, continue to function, and regrow itself over time.
There is much more information on the official website including software packages, HOWTOs, FAQs and source code:
What about rising free Starfish filesystem space limit to 3 – 5 Tb? 1 Tb right now means 3 cheap disks which are quickly filled with digital photos or family video clips (see how much space takes raw format from cameras nowadays…)
I was considering using Starfish for my home LAN file servers but then noticed 1 Tb limit… Times are changing! 1 Tb has nothing to do with “very large amounts” now. Come on, 400 Gb SATA disks are about $140 now. Are 3 such disks so “very large” that Starfish can not be used by a private persons home LAN for them…?
P.S. Your “protection code” is very hard to read for a human being.
So Im confused. What is the state of Starfish today?
I see on one page it says files are mirrored, so if you lost one server lets say, you could rebuild from other copies.
But another page said mirroring was not implemented yet?
So what usefulness is Starfish right now today?
Im wondering if it can be used in a mail server/web server data farm, ie 3 data servers with a 1 terabyte drive that has a copy of the data on all 3 servers so you could lose 2 and still have your data?
There is a pretty detailed answer to your question on the Starfish mailing list:
Status of Starfish
Harijs, to answer your question – we are sticking with a 1TB limit for Starfish file systems. We are talking about licensing Starfish free for non-commercial use. This would mean that you could build clusters that are as big as you want, as long as it is for non-commercial purposes.
Currently, we aren’t getting many requests to lift the 1TB limit. Yours has been the only one to date.
>Currently, we aren’t getting many requests to
> lift the 1TB limit
here`s another request lifting that limit.
i`m looking for a distributed filesystem and starfish looks very promising, i`d happily using it for an internal cd-rom server.
but i can have several terabytes as local storage cheaper for now and until starfish isn´t cheaper than that, it`s no option for me.
you should at least change that limit to 2 or 5TB – 10 nodes is quite ok!
btw – i`d happily being a tester for beta version(s)
regards
Roland
I’d too ask for 1tb limit to be lifted. I already have 1tb on another filesystem and was looking for something with fault tolerance to expand. Is this limit enforced in some way ?
This document will explain what the dfs is and how to set it up in Windows 2003 Server.
http://www.msproficient.com/2008/dfs/