Dishwasha - Slashdot User

Submission + - Which OSS Clustered Filesystem should I use?

Submitted by

Dishwasha

on Monday October 31, 2011 @03:09AM

Dishwasha writes: "For over a decade I have had arrays of 10-20 disks providing larger than normal storage at home. I have suffered twice through complete loss of data once due to accidentally not re-enabling the notification on my hardware RAID and having an array power supply fail and the RAID controller was unable to recover half of the entire array. Now, I run RAID-10 manually verifying that each mirrored pair is properly distributed across each enclosure. I would like to upgrade the hardware but am currently severely tied to the current RAID hardware and would like to take a more hardware agnostic approach by utilizing a cluster filesystem. I currently have 8TB of data (16TB raw storage) and am very paranoid about data loss.

My research has yielded 3 possible solutions. Luster, GlusterFS, and Ceph.

Lustre is well accepted and used in 7 of the top 10 supercomputers in the world, but it has been sullied by the buy-off of Sun to Oracle. Fortunately the creator seems to have Lustre back under control via his company Whamcloud, but I am still reticent to pick something once affiliated with Oracle and it also appears that the solution may be a bit more complex than I need. Right now I would like to reduce my hardware requirements to 2 servers total with an equal number of disks to serve as both filesystem cluster servers and KVM hosts.

GlusterFS seems to be gaining a lot of momentum now having backing from Red Hat. It is much less complex and supports distributed replication and directly exporting volumes through CIFS, but doesn't quite have the same endorsement as Lustre.

Ceph seems the smallest of the three projects, but has an interesting striping and replication block-level driver called Rados.

I really would like a clustered filesystem with distributed, replicated, and striped capabilities. If possible, I would like to control the number of replications at a file level. The cluster filesystem should work well with hosting virtual machines in a high-available fashion thereby supporting guest migrations. And lastly it should require as minimal hardware as possible with the possibility of upgrading and scaling without taking down data.

Has anybody here on Slashdot had any experience with one or more of these clustered file systems? Are there any bandwidth and/or latency comparisons between them? Has anyone experienced a failure and can share their experience with the ease of recovery? Does anyone have any recommendations and why?"

Submission + - Improve cell phone reception indoors

Submitted by Dishwasha on Tuesday May 31, 2011 @09:51AM

Dishwasha writes: I just bought a snazzy new 4G CDMA cell phone that works great, but inside my house the reception is spotty. As soon as I walk outside I've got plenty of bars. What is the best and what is the cheapest way to extend the signal in to my house?

Submission + - Best April Fool's joke

Submitted by Dishwasha on Wednesday April 01, 2009 @10:10AM

Dishwasha writes: If you really want to pull off a good April Fool's joke, post an article on the front page apologizing that due to major glitch in the system, all the UIDs for all /. users had to be reset and were done so randomly. If ya'll could do some tricks to spoof people's UIDs, that would make it totally awesome.

Submission + - NAS/SAN Redundancy

Submitted by

Dishwasha

on Tuesday July 01, 2008 @07:45AM

Dishwasha writes: "There seems to be a lot of chatter about NAS and SAN storage and there is a lot of consensus on using FreeNAS or OpenFiler, a multi-drive controller, and a redundant RAID level, but what insight does the /. community have on providing greater live redundancy than just the disks and power supplies? Using RAID-10, you can effectively stripe across controllers for controller redundancy, but is there any redundant controller solutions for RAID-5/6 without doing RAID-51/61 (RAID-5 hardware, RAID-1 software) and duplicating a lot of disks? More enterprise-level equipment has two data paths to the physical drives themselves as well as redundant storage processors, is there anything like this available on the open market? How about platform? The AMD Opteron platform allows for dedicated RAM per-processor, but is there any hardware or software that will safely migrate process-0 to a second processor and keep the system operational? The Linux Hotplug CPU project seems to be accomplishing this; has anyone safely used this on an x86/x64 platform? What hardware did you use and were you able to achieve full redundancy during a processor failure?"

Submission + - Redundant commodity hardware for Linux SANs

Submitted by

Dishwasha

on Thursday June 19, 2008 @12:58PM

Dishwasha writes: "The capabilities offered by The iSCSI Enterprise Target Project and LVM2 really make commodity SAN solutions for clustering or remote raw storage a possibility. iSCSI or Fiberchannel SAN equipment has typically been very expensive and most of the lower cost equipment has minimal expansion flexibility that you would typically get from a high dollar EMC solution. I see one of the bars to entry is hardware redundancy not at the disk level, but at the processing level. Even the lower end Dell/EMC CX3 and AX100/150 solutions have redundant storage processors and in some cases, backplane redundancy to the disks. Is there any commodity i386/x64 hardware out there that provides CPU redundancy rather than just multi-processing? If so, does anybody have any experience using this with Linux Hotplug CPU Support? At least some of the commercial hardware SAN solutions require a full outage for service on a storage processor, but allowing for hot CPU, RAM, backplane, and controller would definately be a plus if anyone has any experience with getting these components redundant on the i386/x64 platform."

Submission + - BMI madness

Submitted by Dishwasha on Thursday March 01, 2007 @07:19PM

Dishwasha writes: I have several customers that have recently received a notice from the Broadcast Music Incorporated (BMI) that they were in violation of the music rights which BMI owns. They were sited that they had "Music on Hold; TVs in Public Waiting Rooms, in Therapy Sessions, In Fitness Centers, in Operating Rooms, and in Patient Rooms." Apparently none of these applied except for having a TV in waiting rooms and patient rooms. BMI is demanding my customers to sign an agreement for a "Health Care Multiple Use License". More recently one of my customers is a hospital in a town consisting of a population of less than 800 and they have been directly invoiced by the BMI for the use of TVs in public waiting areas.

Is there any legal advice, articles, or documentation the community can offer me that I can share with my customers? Does BMI hold any legal right to claim fees on publicly broadcasted material that is receiving royalties through advertisement that is not being charged by the accused to their customers nor directly generating any revenue or profit, but is simply accessed via a common device used to gain access to public services (i.e. Broadcasted Television) and not being duplicated in any illegal fashion?

Slashdot Top Deals