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: Mike Fredericks who wrote (15841)	4/22/1998 12:33:00 AM
From: George Dawson	Respond to of 29386

Mike, For a better idea of how this switch will work in a Bull clustering application - refer to the link in a previous post: Message 4110738 This is how the 1/4 speed switch performs in an SGI cluster at UMn. The relevant excerpt: "Fibre Channel All of the machines in this cluster use Ancor FCS 250 VME/64 Adapters. These adapters meet the ANSI X3T11 Fibre Channel Standard. The adapters are connected together with an Ancor CXT 250 16 Port Switch. We have seen speeds as high as 19 megabytes per second between nodes using direct channel I/O. We even saw one machine do 38 megabytes per second when it was equipped with two fibre channel adapters." A rule of thumb used by Pfister in his book on clusters is that the internode bandwidth should at least equal the aggregate bandwidth of each node or the throughput will suffer. We need similar performance facts on the MKII posted by an independent lab. George D.