On 4/21/2013 4:23 PM, Furkan KAMACI wrote: > When I read documentation about Hbase it says RAID is not recommended for > many cases. When we talk about SolrCloud (and consider that if a machine > goes down there is a failure system via replicas) and when we think about > the purposes of different RAID disks: > > do they true -> > using RAID systems for: > > * *fault tolerance*: does not make sense because there is already a > mechanism at SolrCloud and instead of using my disks for such kind of RAID > purpose I can use that disk at somewhere else for a replica? > > * *read and write performance:* I should select a RAID version for > considering about a good performance of read/write. > > All in all maybe I should consider about Non-RAID drive architectures as > like JBOD? > > What do you guys think about not considering RAID versions which has good > fault tolerance but considering read/write performance and maybe > considering about Non-RAID drive architectures?
I never build a server without at least RAID1. I figure the cost of an extra disk is more than worth the time and hassle involved in the initial setup of the server, so that I don't have to reinstall everything when a disk fails. If you have a lot of servers in your SolrCloud cluster and you've worked out a way to build a new one extremely quickly, then JBOD might be a good solution. The I/O performance of an individual server will not be as high as it would be with RAID10, but you may see good performance from the cluster as a whole, especially if each node has plenty of RAM. Aside from cost, the main reason that I have not seriously investigated SSD drives is because I have not come across a solution for any level of RAID (even RAID1) with SSDs that exposes TRIM to the operating system. Without reliable TRIM support, an SSD solution is not viable for a long-term setup. Thanks, Shawn
