Cebit 2011: Some Quick Server Related Impressions
by Johan De Gelas on March 14, 2011 9:21 AM EST- Posted in
- IT Computing
- CeBIT
- Cloud Computing
- Trade Shows
Supermicro is a true innovator when it comes to form factors. Two years ago Supermicro invented the Twin² a 2U chassis with four servers. The 4 server nodes were fed by two shared redundant 1200W PSUs. When we heard about the Twin³, we became very curious.
The Twin³ contains 4 hotpluggable units just like the Twin². However, each unit contains two separate motherboards, and as a result there are 8 servers inside this 2U node. The Twin³ is not aimed at the same market as the Twin². The Twin² offers high processing power in a dense, high available chassis.
The Twin³ , also known under the less sexy name Superserver 2015TA-HTRF, is based on the dual-core Intel Atom D525 1.8 GHz. Each node also supports 4 GB of non-ECC DDR3-800 SO-DIMMs, dual Gigabit Ethernet LAN, 2 USB ports, IPMI 2.0 with virtual media over LAN support, and 3x 2.5” SATA hot-swap HDDs. With 4 GB of RAM and a dual-core Atom, we can hardly speak of the Twin³ as a speed daemon.
It is not completely clear to me which market is targeted. According to Supermicro, there are server markets where very low power in idle is important and where little processing power is required. I would personally solve that problem by consolidating all those low intensive workloads on a decently powerful virtualized host with tons of RAM so that you can keep the total amount of servers low. But we have to give this server the benefit of the doubt.
The system also includes (1+1) redundant 720W Gold Level power supplies with PMBus, and four high quality fans. In reality it will be hard to push this system into consuming more than 400W.
17 Comments
View All Comments
Gami - Monday, March 14, 2011 - link
Damn, I wish I was Limited to 1 TB of RAM right now.AlExAkE - Tuesday, March 15, 2011 - link
hahaha u wish u had such a problem hah? :) xxaxa I'd take my 4GB to the corner and stay there without saying anything...vol7ron - Tuesday, March 15, 2011 - link
I can hardly imagine what you would need that much RAM in a PC for. Servers I understand, PCs not so much.Gami - Tuesday, March 15, 2011 - link
for VM Hosts servers,after getting pass the first problem of storage space...
the next problem is normally not enough Real Memory.
4 CPUs with 24 Cores in total, can handle a lot of VMs, but you normally run out of storage space first (which can actually be resolved), but Memory, you've basically hit a Brick wall..
vbrisebo - Wednesday, March 16, 2011 - link
Companies like V3sys.com use the Fusion-io cards to break past those barriers. They can run 50 to 100 VM's on one server as the Fusion-io card can serve as both storage and RAM for the VMs.oneoho - Tuesday, March 15, 2011 - link
werd, 1TB of ram? holy shiet think of the VMs!Griswold - Monday, March 14, 2011 - link
You spent only a few hours at the largest IT fair there is and come to the conclusion its becoming less international every year just because the few booths you visited mostly presented you with german material?Did you go there during the press days or public opening?
JMC2000 - Monday, March 14, 2011 - link
"The HTX slot offers a low latency 6.4 GB/s interface. Together with these kind of "NUMA connected" cards, it is easier to build a very low latency HPC cluster.However, it seems that the HTX slot is at the end of its lifetime. The upcoming Xeons seem to come with a PCI-express 3.0 controller integrated, so they should be able to offer a low latency interface of up to 12.8 GB/s, or twice as much."
I was just looking at the HTX specs/whitepapers, and HTX 3.0 has an aggregate bandwidth of 20.8GB/sec or 10.4GB/sec in each direction. Are you sure it is just a HTX 1.0/2.0 slot or is it HTX 3.0? All 6000-series Opterons support up to 3.2GHz or 6.4GT/s.
mino - Monday, March 14, 2011 - link
Plus a lower latency on top of it.PCIe is not really a HTX competitor. That hypothetical QPI slot is.
MySchizoBuddy - Monday, March 14, 2011 - link
When will we see Tegra 2 based Server.