When it comes to blades vs. traditional servers, it comes down to your internal readiness level and budget in my opinion

First off: blades require a larger upfront investment in general, as the chassis is generally the largest cost (depending on the modules you put in the chassis). They also usually require more buy-in and a higher level of participation from your SAN and network team than you typically would require in a typical physical server deployment.

One other thing that you should be aware of when looking at blades is that they can be made as fault tolerant as a traditional rack server. For example, in my environment we mandate that all servers must have more than one NIC (counting the onboards as one) and we must have two HBAs in every server. Well the HP blades typically only have 2-3 mezzanine slots per blade, depending on the form factor. So that means that if you have a need for additonal NICs and a SAN connection, you will need to rely on one dual HBA to provide this connectivity. This may or may not be an issue for your SAN team, but it's a good thing to know upfront. When I was discussing this with HP, they raised and excellent point - you will always have a single point of failure at some level, usually it ends up being the system board. The mean time between failure is extremely high on the mezzanine cards in use on the blades, so while you are extending out the single point of failure beyond the system board to the mezzanine cards, it is not significantly higher risk.

I also wouldn't deploy your whole environment in a single chassis...chassis failures are incredibly rare according to HP, but you would definitely hate to one of the few that have experienced one.

Now on the converse, once you have deployed them, and learned them - they are much more convenient and flexible that traditional rack servers. They save a great amount of power (50% in our environment), and they have some great advantages such as the Onboard Administrator that makes configuring your ILOs and network settings amazingly simple.

I think there is an increasing benefit to high density virtualization, so if you have the option you may want to consider a small number of larger servers as opposed to a large number of smaller servers. in addition to ease of management, there are now huge licensing benefits in the Windows environment. You can read more about this in my blog http://virtuallycrazy.blogspot.com/2008/07/high-density-virtualization.html

One other link : HP just announced a blade targeted around high density virtualization. http://h18004.www1.hp.com/products/servers/proliant-bl/c-class/495c-g5/compariso n.html

I hope this was helpful.

I guess I'll represent the other side of the coin, lol.

After a lot of research, meetings, and arguments, we went with rack servers for our primary cluster. The reason for doing so was Jason eluded to with single points of failure. We were having a hard time convincing administration that virtualization was the route to follow for our server infrastructure. So a single failure ANYWHERE within the system was not acceptable. Having rack servers also gave us flexibility with peripherals such as NIC's and HBA's. We went with HP DL380 G5's. They have dual quad core Xeon's, so you do catch a break with VMWare's "odd" per socket licensing. We had 32 GB of RAM installed along with 2 additional 2 port NIC's for a total of 6 network links. We also used 2 single port HBA's (FC-2142SR). All this was put into an APC rack with redundant PDU's that are plugged into 3 phase / 5 wire curcuits that span 2 separate UPS's. We used a EMC CX3-40 SAN with redundant paths to the hosts, as well as redundant fabric switches and redundant processors. The servers, outfitted with full carepacks and licensed came in at roughly $12k per. We started with four in our primary cluster. The G5's are also HP's latest attempt at going green, so the processors are energy efficient and they have switching power supplies that have the ability to throttle themselves according to current demands in the server.

With all this in place, we have eliminated all single points of failure out to the desktops, or heaven forbid, a bomb taking out the data center.

Hope this gives you the other half of the scenerio!

Thanks,

Tim

I hope I didn't come off as anti-blade. The blades are great if you have the budget flexibility and the operational readiness.

It shouldn't take long - start with this Proven Practice: Document Template

Cheers!

Steve

German (or Germán):

Blades are a great choice for many things.... but not for Virtualization. First: Blades are no cheap!!!. More money for CPU's, RAM and others. Blades requires a large inversion in infrastructure (addecuate racks, cooling and heat dissipation). Second: Virtualization, specially VMware ESX, requires flexibility, versatility and brute power. Blades are compact and small... not flexibles. Blades are no flexibles: You can not load into a blade alll I/O that you can want, for exmaple; expansion is expesive and propietary (look the prices of a blade switch!!), and normally, at the end, you look exatly the same numbers of cables than traditional servers. Power: For years, I'm trying someboy convince me that a server that works at 15 or 20 celcius degrees up than other offers the same performance!!!.

Other aspect, and not less important, is heat: If you plan to massively populate your datacenter with blades, prepare to redesing it!!!: Better cooling, Heat extraction..... Blades are like Hell's kitchen!!!

If you want to eliminate cables, think in infiniband or datacenter Ethernet, but not in blades. Take in mind that the first "Blade Taliban", HP, has presented a "big node" Proliant DL785 G5, with up 8 AMD quad core....

I prefer Big nodes (currently I'm using SUN x4600 with un 8 AMD quad core in a 4U form factor) and I obtain more power in a rack than if it was blade Populated. I can install up to 10 x4600 in each rack (a total of 80 CPU/ 320 cores) per 48U rack... HP do not recommend to install more than 2 chasis per rack (16 blades per chassis, 2 CPU per blade = 64 CPU = 256 cores)

I hope it was helpfull...

I would say that c3000 chassis has curtain points to remember:

• - If you are not going to a addition mezzanine card for network in our blade servers than you will be not able to use a Network level redundancy in your C3000. This is by design; because we also faced a similar at one of our customer site.
• - If you are not planning to have more than 3 to 4 servers than it would be good for you to go with a DL servers.
• - Even a startup process of your SAN switch, Network Switch is very important if you are using it with SAN storage.