Posted by
CmdrTaco
on from the now-thats-a-lotta-pr0n dept.
Delta-9 writes "Here is a writeup on how to combine 6 200GB IDE drives into a small tower and hack together some firewire controllers to give you one giant 1.2TB firewire drive." Very cool project, both technically and aesthetically.
..actually there are quite cheap external boxes for usual hard drives including a firewire plughole. Cheap, finished - it works out of the box.
Ok, why get it easy if it can be done complicated as well..
isn't there a question out there on this??
by
peragrin
·
· Score: 2, Interesting
hey guys isn't this an article already here. or maybe he should of waited an hour????
http://ask.slashdot.org/article.pl?sid=03/09/23/20 41246&mode=thread&tid=137&tid=188&tid= 198
-- i thought once I was found, but it was only a dream.
Forgive my hardware ignorance but...
by
Kethinov
·
· Score: 4, Interesting
if you use firewire controllers to give you one giant 1.2TB firewire drive, doesn't that essentially make 6 hard drives pretend to be one? (AKA the OS doesn't realize it's many) And if just ONE of those drives failed, aren't you shit out of luck with your data?
Again, forgive my hardware ignorance if I'm way off.
-- You're right, I wouldn't steal a car. But if it were possible, I sure as hell would download one!
Wouldn't it make more sense to build a SATA RAID array? Using the 3Ware 8 channel SATA controller and a bunch of big ass Maxtor SATA drives you can get more storage for probably less cost and complication.
It would be cool if the OS saw it as 1 huge 1.2GB drive, but that would be a hell of a hack to make it display as unified piece of media.
I would imagine he has the drives striped in software to appear as one large drive. This is pretty easy to do with Windows, OS X, and pretty much any semi-modern un*x.
Hardly newsworthy
by
Anonymous Coward
·
· Score: 2, Interesting
Fore everyones information, this 'project' is nothing new or special. I will not metion its name, but connected to the better servers of a 'top' P2P application are dozens if not hunreds of people with shares (ie. storage solutions) of comparable and rarely even greater capacity. On some servers, they won't even let you in if you have less than a hundred gigabytes of shared 'infomation'...
2c
Re:Thank God
by
Anonymous Coward
·
· Score: 1, Interesting
Why not gigabit ethernet? That much space is clearly best either for scientific (cluster) or multiuser situations.
I tried this on Linux with some problems.
by
Rolman
·
· Score: 4, Interesting
I tried this on Linux and got terrible performance at the first try, I got a 23MB/s RAID-0 when each HDD is capable of 26MB/s by itself (everything according to Bonnie++ and hdparm). I didn't know what to blame, the bus, the cables, the Linux SCSI layer, or the whole IEEE1394 support on Linux. Windows was noticeably faster with up to 28MB/s.
Then I made some more research and it turned out the problem was caused by the sbp2 kernel module. This module had some good fine-tuning parameters (sbp2_max_sectors, sbp2_max_outstanding_cmds and spb2_max_cmds_per_lun) up to 2.4.20, but these got ditched in 2.4.21 in the name of a "better way of handling these parameters". I understand the logic behind this move, but the tweakable granularity should have been kept.
Using 2.4.20, I managed to get better performance by tweaking these parameters, then modified sbp2.c on 2.4.22 to reflect the changes. However, I haven't been able to get the 35MB/s this guy got so easily on MacOS X, I'm currently stuck at 29.22MB/s maximum and it's painfully slow to test all combinations of those variable parameters on the sbp2 module.
I just wish there was some document which could explain more about the relationship between these parameters for people not actually involved on the linux1394 project. The comments on sbp2.c are not helpful beyond this point.
By the way, I'm using two Oxford-based bridges to connect two 8MB cache Matrox HDDs, and I'm using Bonnie++ and hdparm for testing. YMMV but the least I can say is Linux RAID support on Firewire still has a long way to go.
-- - Otaku no naka no otaku, otaking da!!!
appearantely nothing
by
Anonymous Coward
·
· Score: 1, Interesting
People put those in PC's all the time which are probably much more sensitive to noise than my simple system. Keep in mind that the drives themselves are fully enclosed in grounded metal. So the only exposure risk is to the FW controllers. They don't seem to care.
To verify integrity I wrote a 1TB file of pseudorandom data using PRBS23 and then read it back and verified the data integrity with no errors. As a side note, it takes about a day to do this over firewire, although some delays were because my powerbook's cpu is too slow to decode the data at full bus speed.
Hmmm.. you'd need some aluminium bar-stock, a small die-casting setup, watchmakers lathe and an ultra-clean glovebox for assembly. And of course sacrificial drives to grab the platters and heads out of. You'd need to redesign the driver board and remember to feed extra power to the motor to counter all the extra mass. And while you're at it, why not cap the whole thing off with a perspex window and internal LEDs.
Slashdot Mirror
..actually there are quite cheap external boxes for usual hard drives including a firewire plughole. Cheap, finished - it works out of the box.
Ok, why get it easy if it can be done complicated as well..
hey guys isn't this an article already here. or maybe he should of waited an hour???? http://ask.slashdot.org/article.pl?sid=03/09/23/20 41246&mode=thread&tid=137&tid=188&tid= 198
i thought once I was found, but it was only a dream.
if you use firewire controllers to give you one giant 1.2TB firewire drive, doesn't that essentially make 6 hard drives pretend to be one? (AKA the OS doesn't realize it's many) And if just ONE of those drives failed, aren't you shit out of luck with your data?
Again, forgive my hardware ignorance if I'm way off.
You're right, I wouldn't steal a car. But if it were possible, I sure as hell would download one!
Wouldn't it make more sense to build a SATA RAID array? Using the 3Ware 8 channel SATA controller and a bunch of big ass Maxtor SATA drives you can get more storage for probably less cost and complication.
No sig for you. YOU GET NO SIG!
It would be cool if the OS saw it as 1 huge 1.2GB drive, but that would be a hell of a hack to make it display as unified piece of media.
I would imagine he has the drives striped in software to appear as one large drive. This is pretty easy to do with Windows, OS X, and pretty much any semi-modern un*x.
Here's a guy who striped 5 floppy drives to make a floppy RAID... he's my hero:
http://ohlssonvox.8k.com/fdd_raid.htm
Fore everyones information, this 'project' is nothing new or special. I will not metion its name, but connected to the better servers of a 'top' P2P application are dozens if not hunreds of people with shares (ie. storage solutions) of comparable and rarely even greater capacity.
On some servers, they won't even let you in if you have less than a hundred gigabytes of shared 'infomation'...
2c
Why not gigabit ethernet? That much space is clearly best either for scientific (cluster) or multiuser situations.
I tried this on Linux and got terrible performance at the first try, I got a 23MB/s RAID-0 when each HDD is capable of 26MB/s by itself (everything according to Bonnie++ and hdparm). I didn't know what to blame, the bus, the cables, the Linux SCSI layer, or the whole IEEE1394 support on Linux. Windows was noticeably faster with up to 28MB/s.
Then I made some more research and it turned out the problem was caused by the sbp2 kernel module. This module had some good fine-tuning parameters (sbp2_max_sectors, sbp2_max_outstanding_cmds and spb2_max_cmds_per_lun) up to 2.4.20, but these got ditched in 2.4.21 in the name of a "better way of handling these parameters". I understand the logic behind this move, but the tweakable granularity should have been kept.
Using 2.4.20, I managed to get better performance by tweaking these parameters, then modified sbp2.c on 2.4.22 to reflect the changes. However, I haven't been able to get the 35MB/s this guy got so easily on MacOS X, I'm currently stuck at 29.22MB/s maximum and it's painfully slow to test all combinations of those variable parameters on the sbp2 module.
I just wish there was some document which could explain more about the relationship between these parameters for people not actually involved on the linux1394 project. The comments on sbp2.c are not helpful beyond this point.
By the way, I'm using two Oxford-based bridges to connect two 8MB cache Matrox HDDs, and I'm using Bonnie++ and hdparm for testing. YMMV but the least I can say is Linux RAID support on Firewire still has a long way to go.
- Otaku no naka no otaku, otaking da!!!
People put those in PC's all the time which are probably much more sensitive to noise than my simple system. Keep in mind that the drives themselves are fully enclosed in grounded metal. So the only exposure risk is to the FW controllers. They don't seem to care.
To verify integrity I wrote a 1TB file of pseudorandom data using PRBS23 and then read it back and verified the data integrity with no errors. As a side note, it takes about a day to do this over firewire, although some delays were because my powerbook's cpu is too slow to decode the data at full bus speed.
Bobby Kinstle
Hmmm.. you'd need some aluminium bar-stock, a small die-casting setup, watchmakers lathe and an ultra-clean glovebox for assembly. And of course sacrificial drives to grab the platters and heads out of. You'd need to redesign the driver board and remember to feed extra power to the motor to counter all the extra mass.
And while you're at it, why not cap the whole thing off with a perspex window and internal LEDs.