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 : The New QLogic (ANCR) -- Ignore unavailable to you. Want to Upgrade?

To: George Dawson who wrote (25137)	12/8/1999 6:56:00 PM
From: George Dawson	Read Replies (2) \| Respond to of 29386

One further thought on the issue of GE vs. FC and NAS vs. SANs. You can analyze the situation from the perspective of the rate limiting connection or so-called bottleneck. I think we have a lot of current information from the past several years that is is at the max. distance from the processor, namely disk read/writes. I see SCSI and FC RAID as a way around that, basically writing to many disks instead of one. The bottleneck will still be at the level of the RAID controller or the FCAL bus connecting a finite level of loops. At the level of the of this loop, it is contention between disks that appears to be a limiting factor rather than disk throughput. This limits the number of disks per FC array. At this level the question is: 1. The limits of FCAL loops per bus, I know they can do at least two but can they do more? 2. What will the characteristics of the disk drives arrays be with 2 gig FC rather than 1 gig? Specifically will they still be limited by contention? Is it even feasible to consider clustering disks off 2 gig FCAL or will the disk arrays remain 1 gig while 2 gig is in the fabric? In addition to the practical issues of real LAN average and peak traffic, I think these bottleneck factor need to be considered when thinking of storage in the future. George D.