Cisco blades - or: I´m not really impressed

Quicksearch

Disclaimer

The individual owning this blog works for Oracle in Germany. The opinions expressed here are his own, are not necessarily reviewed in advance by anyone but the individual author, and neither Oracle nor any other party necessarily agrees with them.

Navigation

< Compression on the 7000 | Storagemojo about Fishworks >

Cisco blades - or: I´m not really impressed

Monday, March 16. 2009

The big Cisco announced they entry to the server market. I expected something big. Well ... i´m not impressed. The informations are a little bit sparse at the moment, but i will write down my thoughts about it:

As expected the concept circles around their Nexus line of switches for combined FCoE and IP traffic.
The cisco website states on product page that
"Cisco UCS 5100 Series Blade Server Chassis supports up to eight blade servers and up to two fabric extenders in a 6RU enclosure without the need for additional management modules."
This translates into 4 fullsize slots and 8 halfsize slots. for blades. This is considerable less dense than a Sun 6000 chassis with 10 respectively 12 slots on 10 rackunits.
The blade system is even less dense than using 1 RU pizzaboxes. 1,25 inches for a single server as long you don´t choose the halfsize blades.
The infos are a little bit sparse, but it looks like you can choose any kind of I/O for the blades ... as long it´s Ethernet ... no Infiniband, no FC, no SAS.
Several points are unclear at the moment ... processor density for example, I/O capabilties, or the memory extender technology that Cisco mentions in a whitepaper

I hope there will be more information soon, but at the moment this fails at impressing me. I´m not really sure that just some Nehalem Blades with Ethernet, an Ethernet switch and reselling some software (they announced VMware, Windows and Redhat partnerships) is enough to convince the people of buying servers from their networking vendor.

Posted by Joerg Moellenkamp in English, The IT Business at 21:24 | Comments (2) | Trackback (1)

Defined tags for this entry: sun

Related entries by tags:

View as PDF: This entry | This month | Full blog

Trackbacks

Trackback specific URI for this entry

PingBack

Weblog: blog.koehntopp.de
Tracked: Mar 25, 16:34

Comments

Display comments as (Linear | Threaded)

From what I understand, Cisco didn't try to make their blades as small as possible, but rather tried to get them to accommodate as much RAM as possible, so that each blade can run a large number of guest operating systems in a virtualized environment.
Rumors speak of 384 GBytes of RAM per (full size) blade. Conceivably, a Cisco blade will also cost more than your average HP/IBM/SUN blade.

#1 Greg on 2009-03-18 01:28 (Reply)

The memory point is especially interesting for for me ... they use Nehalems, thus they have to live with the limits of the IMC of the Nehalems. 384 GB clearly breaks this limits, thus they have to use a different technology. I´m interested, how they do that without introducing additional latency.

#1.1 Joerg M. (Homepage) on 2009-03-18 06:14 (Reply)

Add Comment

Name
Email
Homepage
In reply to
Comment	E-Mail addresses will not be displayed and will only be used for E-Mail notifications. To prevent automated Bots from commentspamming, please enter the string you see in the image below in the appropriate input box. Your comment will only be submitted if the strings match. Please ensure that your browser supports and accepts cookies, or your comment cannot be verified correctly. Enter the string from the spam-prevention image above: Standard emoticons like :-) and ;-) are converted to images. Enclosing asterisks marks text as bold (word), underscore are made via _word_.
	Remember Information? Subscribe to this entry