Questions[blade-server](server)

I pulled up the datasheet but there's only "Acoustics Sound Power Measured" and I can't make any sense of it. It's got numbers like (page 15):

Power in Watts: >= 300W

Servers/Rack Mount BA: 7.0

I'm trying to figure out if we can realistically install these servers (4) in the closet in our office. Our existing server is installed in there but it's a tower, not a blade. I have essentially no experience with this sort of thing and I'm being asked to help.

Scenario: Brand new Dell M610 blades.

Connected to the network with a 10GE uplink into a Dell PowerConnect M6220 blade switch.

DHCP server evidently working, as everything else boots / gets addresses fine.

TFTP server working fine.

Can't seem to get a DHCP address from the server.

Is there something on a blade chassis level interfering? Will I need to set up something special on the chassis? On the switch? On the blade?

• Portfast = Enabled.
• IP Helper = Points at our DHCP server (BUT! Shouldn't be needed, everything is somewhere on 192.168.0.0/16)
• DHCP Relay = Enabled
• DHCP Snooping = Disabled

Now What?

I'm currently in the middle of a process to specify and design a new server environment for graphics and video rendering.

We know we want to use blades, and we're pretty sure of our vendor decisions.

We've got one massive problem, and that's power.
At the moment, we're looking at getting more 3 phase power into the building. One idea that I've heard of, is using 48v DC to power the servers and networking equipment.

Questions are these:

1. What are the advantages of using 48V DC over 230VAC or 415VAC 3phase. (We're in the UK.)
2. Do all of the decent (Dell, HP, IBM, Cisco)/most servers and network vendors support 48V DC power supplies?
3. Can we expect this to be more expensive in hardware costs?
4. Will this actually be more power efficient than using single/threephase, if all a PSU is gonna do is downcovert to +/- 12v/5v/3.3v.
5. Can we expect lower cooling demands because of lower amount of powerloss in downconversion from 230v.

We're planning to host our website for the first time for ourselves. We have currently have a linode of 8 gigs and the memory is going up to 90% most of the time. So I want to move my website to my own server with huge RAM. So this will be first time to manage any physical hardware of a server.

So I came across IBM's BladeCenter, found them interesting. So can I just buy the blade and run it? Or do I have to buy the chassis for sure? Also, do I need to buy an UPS? So how hard is it to setup? How about the hard drives? Can I setup them easily? Please advice.

My team of developers has suggested a server structure for an upcoming project we are developing. Our structure is "logical", meaning that the various logical components of the application (it is a distributed one) relies on different servers. Some components are more critical than others and will be subjected to more load.

Our proposal was to have 1 server per component but the hardware guys suggested to replace the various machines with a single, bigger one with virtual servers. They're gonna use Blade Servers.

Now, I'm not an expert at all, but my question to the guys was: so if we need, for example, 3 2GHz CPU / 2GB RAM machines and you give me 1 machine with 3 2GHz CPUs and 6 GB of RAM it is the same? They told me it is.

Is this accurate? What are the advantages or disadvantages of both the solutions? What are the generally accepted best practices? Could you point out some URL reference dealing with the problem?

EDIT:

Some more info. The (internet / intranet) application is already layered. We have some servers on the DMZ that will expose pages to the internet and the databases are on their own machines. What we want to split (and they want to join) are some webservers that mainly expose webservices. One is a DAL that communicates with the database layer, one is our Single Sign On / User Profile application that gets called once per page and one is a clone of what seen on the Internet to be used on our lan.