|
|
About ::
TODO ::
Blog ::
RSS ::
Old blog ::
Projects ::
GIT ::
Gallery ::
Notes
Wed, 27 Jun 2007
Distributed storing dilemma.
I have a qustion about the way data should be organized in distributed storage.
There are two possible ways:
- sequential data is stored lineary - first storage is filled until it is full, then
next one and so on. Of course error recovery codes usage requires another
storages to be used, but amount of CRC data is usually noticebly smaller than
amount of actual data.
- sequential data is distributed among several storages according to some algorithm (like round-robin).
The former allows to increase random access speed, the latter - sequential access.
Getting into account that even 1Gbit network has about two times faster bulk
transfer speed than modern disks, priority of this issue increases.
Likely round-ribin writing is a good candidate for first implementation.
/devel/dst :: Link / Comments (0)
Please solve this captcha to be allowed to post (need to reload in a minute): 56 - 78
|