Slashdot Mirror
Where are the High-Capacity SCSI Drives?
An anonymous reader asks: "Storage technology has really exploded in recent years, giving us ATA drives up to and exceeding 200-250 GB per drive. Why is it that SCSI drive technology has remained stagnant? I can't find a SCSI drive exceeding about a 146 GB capacity. Instead, businesses (and some individuals) wanting greater storage capacities are required to buy more drives which takes up more space, generates more heat, provides more points of failure, uses more electricity, etc. Why is this so?"
Everyone is going serial. USB, SAS, Serial ATA, etc. Time to invest in Kellogs.
Oops, wrong "cerial".
(sorry for the pun, couldn't help it).
Comment forecast: Bits of genius surrounded by a sea of mediocrity.
Yeah, I was thinking IDE and a standard 33mhz 32bit PCI bus. Your right, SCSI goes up the 320 and the bus can handle it if you use PCI-X, PCI express, 66mhz PCI, 64bit PCI, etc. Nice catch.
Comment forecast: Bits of genius surrounded by a sea of mediocrity.
I always find comments like this amusing. It's just not true.
Not long ago I had to set up a several terabyte array (around 4 TB) using SCSI drives. We were constantly replacing the damn things. And this was supposedly quality hardware from Sun. Now, with as many drives as we had, there were bound to be failures. Eventually the failure rate stablized at about 1 or 2 drives per month. A rate which continues to this day, some 3 years later.
Previous to that array I had helped set up a similar system using PC components and IDE drives. The array was actually nearly twice as big at around 7 TB but cost less than the SCSI array. Guess what? In the last 3 years only 1 drive has failed. One drive.
Which one is more realible?
Fuck SCSI.
You make good arguments, but reliability and storage capacities are only two of the issues involved.
The largest benefit is performance. Gamers invest so much in their system bus, cpu, and memory, but disk i/o is 5 orders of magnitude slower. if performance is key, a small investment in SCSI improves disk intensive apps considerably.
1. IDE requires CPU cycles. SCSI buses have embedded ICs that handle queuing of data and such, freeing the CPU to perform other tasks.
2. IDE channels are shared. Most IDE ribbons allow for two devices, but one device can talk on the channel at a time, much like CSMA/CD, whereas SCSI allows you to daisy-chain 7 or more devices to simultaeneously talk on the same channel.
3. IDE is not bidirectional. similar to (2), this causes read/writes to wait.
one reason that you didn't mention, that falls under reliability is SCA. this interface combines signalling, power input and data i/o, which enables hot-swappable SCSI drives, critical to any non-appliance or diskless system that requires high availability.
I'm very curious which Sun array this is, and which drives you are using.
I've worked in the Sun market for well over a decade, and I haven't seen failure rates like you're describing since the old Seagate 2.9G 5-1/4" full-height drives they used to have in their "Mass Storage" cabinets (the ones that looked exactly like a SPARCcenter 2000)... and that was only after the drives were out of production for a few YEARS (all replacements were refurbs).
My guess is you have serious environmental issues... heat/humidity due to a non-datacenter environment (do you have raised-floor-cooling? is it under 70F?), or non-isolated air (is the A/C air-handler the same one used for the rest of the building?), or you have non-isolated power and have regular spikes (in Miami maybe?).
You need a _true_ UPS system, not an SPS labeled as a UPS.
- Preferences: Solaris 10 (servers), Ubuntu (desktops), Solaris 11 (personal servers) -
Some SATA RAID controllers do support the advanced features offered by high-end SCSI RAID controllers, it's just that it seems strange to spend $700 on a controller for $1000 in disks, vs. spending $500 on a controller for $4000 in disks. Most recent server boards support 133MHz PCI-X, so bandwidth to SCSI devices is not an issue. The difference is speed and quality. Still though, if you don't need the absolute fastest array (ours is about 610MB/sec read, 300MB/sec write, RAID-10 striped within, mirrored across channels), SATA is a good solution. We use 6 15k U320 SCSI disks for our primary database system (54GB total array size), and 12 7.2k 250GB SATA disks for our document imaging system (2TB, RAID-5 with hot spares). Sustained transfers from either array are practically identical, but the access times to the SCSI array is much lower (though this is partly due to differences between RAID levels, as having a RAID-10 array means that the closest stripe to the data can get priority). Either storage method easily outperforms Gb Ethernet, so the only real difference is the access times for processes performed on the local machines (such as index and data lookups for a database), and aside from a few ms difference in query time, which is usually much smaller than the running time for the query, a remote user can't tell the difference.
--That's the point of being root, you can do anything you want, even if it's stupid.
My company was offering 180GB SCSI drives in one of our RAID products, but we had to stop due to reliability issues. There was a huge difference in reliability between the 180GB and 146GB drives (which we still offer).
Under capitalism man exploits man. Under communism it's the other way around.
"You forget the important fact that as the drive DENSITY increases, so does the amount of data read per revolution of the platters"
The _evidence_ of actual transfer rates is more important that your "important fact".
This might be helpful. Select WB99 transfer rate - Begin.
If you have evidence of significantly faster single drives do let me know.
Were the IDE and SCSI drives rotating at the same speed?
--Phillip
Can you say BIRTH TAX
storage review says about 64MB/s on the outside of the platter for the best performing 15K RPM drive (which is a 74GB drive not a 140GB one). So, to swamp an U320 bus with sustained transfers you will need at least 6 drives, not the 3 that some people keep spouting around here. So if you need 6 drives to saturate the bus, why have a few high capacity drives when more drives gives you lower latency and gets you to max sustained transfer.
There are 4 boxes to use in the defense of liberty: soap, ballot, jury, ammo. Use in that order. Starting now.
I've read of companies that bought a bunch of SCSI drives and then set them up to only use half their normal capacity, by throwing away half the cylinders. This reduced the average access time of the drives. I'm not sure if they reconfigured the drives in-house or if the manufacturer did it for them.
Mea navis aericumbens anguillis abundat