Silicon Investor (SI) -- The First Internet Community

STOCKTALK

We've detected that you're using an ad content blocking browser plug-in or feature. Ads provide a critical source of revenue to the continued operation of Silicon Investor. We ask that you disable ad blocking while on Silicon Investor in the best interests of our community. If you are not using an ad blocker but are still receiving this message, make sure your browser's tracking protection is set to the 'standard' level.

Technology Stocks : Frank Coluccio Technology Forum - ASAP -- Ignore unavailable to you. Want to Upgrade?

To: Frank A. Coluccio who wrote (690)	12/12/1999 11:10:00 PM
From: ftth	Read Replies (1) \| Respond to of 1782

Hi Frank, I'm still catching up on many of the interesting recent topics. Metadata and Bandwidth exchanges are on the list for further review. re: >> I also think there's a place for GbE for storage area networks (SANs) and network-attached storage (NASs) over much greater distances than previously possible, although, here, FC is quite formidable, still, with no signs that its popularity is going anywhere but up, as well. I've heard of the push for NAS using GbE, as a solution for some of the more basic SAN functions, but hadn't heard of any work being done on the SAN front, as a replacement for FC. Have you heard of some? I suppose the momentum of the FC alliances and industry groups can't be ignored, since the participating members in FCIA(www.fibrechannel.com [not a typo]) and SNIA(www.snia.org) essentially set what gets developed and integrated as a packaged advanced storage solution. These now number over a hundred company-members. That's a big boulder to stop. GbE would seem to have a slim chance of making any serious inroads (re: SANs) (no matter how much 'sense' it makes at the lower levels, for the base SAN functions) when you look at the participants (who happen also to be developing the SAN solutions, and have vested interests in preserving FC's place, i.e. the storage management software vendors, the SAN system solution integrators (especially), the FC hub and switch vendors, the HBA vendors, the test equipment vendors, and the FC-SCSI router vendors.) These packaged solutions will be tested for interoperability, and allow one-stop shopping for hardware, software/system management, and integration--or so the claim goes. They have to, though, so I think this will happen. The GbE folks are pretty much absent from these forums. This all assumes that these alliances and industry groups will actually move forward; we'll know the answer to that soon enough, but they appear to have strengthened in the past 6 months. The partnerships where combined NAS/SAN solutions are being addressed (e.g. BRCD and NTAP; LGTO and ASPX; others working on NAS/SAN gateways) are--I believe--only looking at FC on the SAN side. These partnerships in particular are important in showing that SAN's are not going to be just a transitional step, since even the NAS leaders recognize that NAS simply does not cover all the advanced storage cases SAN covers (some of these limitations can be attributed to Ethernet, but removing that eliminates the GbE-NAS strong points on the basic SAN functions where NAS can replicate the task). As for the claimed price advantage of GbE/NAS, as I've seen in several interviews with IT folks, it's a mistake to look just at the fixed, up front hardware costs (e.g. FC HBA [host bus adapter] vs GbE HBA) because they are but a fraction of the total long term cost of the project. It has to be viewed as an end-to-end system cost--software, hardware, system management, operations, and staffing. They don't confirm or deny that a first-generation SAN solution is cheaper (probably because it isn't yet), but these are certainly valid points since all the press comparisons tend to look at it from the most basic, visible hardware pieces. As for the speed argument of GbE vs FC, over time I think it's a wash. They'll both go up. FC may have a slight edge in some cases now due to lower overhead and larger data blocks (re: 800Mb v. GbE) and chains of blocks. Distance...maybe a slight edge to FC at present; the long distance GbE that matches FC are proprietary. Both will increase over time. Multi-Protocol is solely in FC's court; this is important for simultaneous support of multiple, diverse storage media. Any corrections or comments welcomed.