Sassy to scuzzy to sass. (I/O with Mark & Hal).Mark: There wasn't much meat on the bone at the Server I/O (Input/Output) The transfer of data between the CPU and a peripheral device. Every transfer is an output from one device and an input to another. See PC input/output. I/O - Input/Output Conference in January. Hal: Everyone's on a diet these days, what with the economy in the tank. Mark: True, but it doesn't seem to have stemmed the tide of new players coming into the storage space. Hal: Such as...? Mark: Z-Force put together something so intuitively obvious that one had to wonder why nobody'd done it before: an NAS (1) See network access server. (2) (Network Attached Storage) A specialized file server that connects to the network. A NAS device contains a slimmed-down operating system and a file system and processes only I/O requests by supporting the popular array. Hal: Wait a second. Isn't that just a glorified glo·ri·fy tr.v. glo·ri·fied, glo·ri·fy·ing, glo·ri·fies 1. To give glory, honor, or high praise to; exalt. 2. Snap appliance? Mark: Nope. Z-Force's entry includes switching technology. You know that, in order to go from server to storage in a SAN, you go through a SAN switch. So, to create a NAS array, Z-Force uses something similar to a RAID controller A disk controller card that supports one or more RAID configurations. Originally only for SCSI drives, RAID controllers have become very popular for PATA and SATA drives. See RAID. . Of course, the new Snap appliance was on display, too. Hal: Tell me about that. Mark: Snap is a recent spinoff from Ouantum- Hal: Which we covered last year. Mark: Yes. They've taken over all of its NAS appliance business. And with any kind of luck, they'll pick up some of the business that Maxtor has since abandoned, too. Hal: That sounds pretty routine--one company feeding from the trough after another has left. There must have been something truly exciting at the conference. Mark: For me, the hottest announcements were the developments in Serial-Attached SCSI SCSI in full Small Computer System Interface Once common standard for connecting peripheral devices (disks, modems, printers, etc.) to small and medium-sized computers. SCSI has given way to faster standards, such as Firewire and USB. . Hal: I'm not so sanguine about SCSI as I used to be. As you know, the popularity of HDDs using ATA (1) (AT Attachment) The specification for IDE drives. See IDE. (2) See analog telephone adapter. ATA - Advanced Technology Attachment is enormous and growing. ATA is less expensive, and the performance is high enough for most installations and most apps. Mark: Yes. But now what we're seeing is a progression from "sassy sas·sy 1 adj. sas·si·er, sas·si·est 1. Rude and disrespectful; impudent. 2. Lively and spirited; jaunty. 3. Stylish; chic: a sassy little hat. " to "skuzzy" to "sass." Hal: Very funny! Better explain that. Mark: Surely we all remember our history lessons! First there was Al Shugart's protocol: the Shugart Associates Systems Interface, or SASI (Shugart Associates Systems Interface) A peripheral interface developed by Shugart in 1981 that evolved into the ANSI SCSI standard in 1986. It was renamed SCSI because ANSI does not allow corporate names in its standards. See SCSI. , for short. Then came the industry-standard Small Computer Systems Interface, which is SCSI. Well, now there's Serial-Attached SCSI or just plain SAS (1) (SAS Institute Inc., Cary, NC, www.sas.com) A software company that specializes in data warehousing and decision support software based on the SAS System. Founded in 1976, SAS is one of the world's largest privately held software companies. See SAS System. . Hal: We'll remember it now! How does it work? Mark: Under the Serial-Attached SCSI approach, which includes a re-working of the connector technology, it should be possible for an integrator to select between high-performance SCSI drives and lower-performance serial ATA drives, while still basing the entire array on traditional SCSI connectivity. Hal: So, does that mean users wouldn't have to change physical connectors to change source drives? Mark: Yes. Hal: Then, I'm confused. Wouldn't that add cost and unnecessary complexity to the array? Why not just stick with one flavor of connectivity or the other? Go for economy with ATA. Or go for performance with SCSI--especially now that there's iSCSI available. Which reminds me: Addison-Wesley's just published a new book on that subject, by 35-year IBM (International Business Machines Corporation, Armonk, NY, www.ibm.com) The world's largest computer company. IBM's product lines include the S/390 mainframes (zSeries), AS/400 midrange business systems (iSeries), RS/6000 workstations and servers (pSeries), Intel-based servers (xSeries) veteran John Hufferd. It's called iSCSI: the Universal Storage Connection. I'd question the use of a headline word like "universal," in any storage context, but the book itself is a solid, well-presented handbook for anyone who's got to be up on the subject. Mark: Well, in resolving the conflict between ATA and SCSI, the idea of SAS is the old-fashioned one: Let the customer decide! Hal: So, what about the complexity? Isn't it inevitable? And how does SAS address it? Mark: That very question came up often, at the conference. Hal: Ibet it did! Mark: The issues involved in managing complexity were common threads running through practically every session that wasn't vendor-specific. Hal: And was there a consensus? Mark: Most of the presenters agreed that storage software isn't yet capable of coping with the complexity: That the state-of-the-art is still not up to the task. Hal: No surprise, there. But isn't this what "virtualization An umbrella term for enhancing a computer's ability to do work. Following are the ways virtualization is used. Hardware Virtualization Partitioning the computer's memory into separate and isolated "virtual machines" simulates multiple machines within one physical computer. " is supposed to overcome? Mark: It turns out that "virtualization" is only part of the solution. It masks the complexity from the user with a layer of abstraction See abstraction layer. . Hal: So, let me get this straight: It overcomes complexity by adding another layer of complexity. Mark: I said it wasn't the whole answer! Hal: So, does anybody have what radio commentator Paul Harvey calls "the rest of the story?" Mark: No. It's still unresolved. Remember the old saying: The solution is in the search? Hal: I think it's still in the soup. And it's not yet "duck soup." Mark: Let's see if our readers have a fresh ingredient to toss in. If you think virtualization will carry the day, email me at: mark_ferelli@wwpi.com Hal: And if you think we've still got a long way to go before complexity turns into simplicity, email me at: hal_glatzer@wwpi.com |
|
||||||||||||||||

Printer friendly
Cite/link
Email
Feedback
Reader Opinion