[Date Prev][Date Next]   [Thread Prev][Thread Next]   [Thread Index] [Date Index] [Author Index]

[Linux-cluster] Advice on suitability



Hi

 

I have been finding a fair bit of configuration info iro clustering, cluster suite and gfs/2 but not quite seeing the more conceptual stuff with pretty diagrams that would help me grasp whether its applicable to my needs so I hope you can help with unscrambling my confusion.

 

Currently I have 25 odd servers each running LAMP and qmail etc. Throughput on each ranges from 1 – 10 mbits/s. Each currently works off raid 1 mirrored disks and all are relatively low powered machines. Total storage usage for all 25 machines is about 4Tb. I want to virtualize the whole lot (I am leaning towards KVM). My motivations are 1) reduce power usage in rack and 2) build in as much redundancy as I can.

 

My thoughts have been to have 3 “front end” physical host machines with a rough 50/50 split of the current 25 odd servers into VMs on these physical hosts. I will then have redundancy across 3 machines so that if machine 1 dies, the vms are moved to machine 2 or 3 pending fix of machine 1. Then I want to create two “back end” storage servers which are replicated and provide redundant storage to the front ends in a primary/secondary way such that the front ends can failover to either available storage server. I am anticipating having only VM host booting off machine1-3 and using the back end storage servers for booting the vms and storing their data. Each storage server will have 6 x 2Tb sata disks set up as a 6Tb raid1 array although I have been reading that more spindles is better so maybe I need more disks for optimal performance. Front ends and back ends would have multiple bonded Gig e ports to a dedicated switch which I think should provide enough bandwidth and the net facing NICs running off a separate switch.

 

I have looked at openfiler and open-e for storage platforms which are options but then followed some RHEL links to Cluster Suite, GFS2 and the HA add ons and it began to look like another option for presenting a redundant, automated-failover storage platform to the VMs using commodity hardware rather than proprietary SAN kit.

 

So I am trying to work out if I am on the right track with Cluster Suite/GFS/ etc and if so, what are the elements I need to meet my objective and will it actually work and provide the throughput I need or are 25 web/mail servers doing constant reads/writes going to mean its all too slow. I also saw some warnings about mysql usage on the cluster which looked troubling. Any real world experiences, pointers or advice would be great.

 

Thanks and regards

Ashley


[Date Prev][Date Next]   [Thread Prev][Thread Next]   [Thread Index] [Date Index] [Author Index]