Main And I/O Cooling Modules
Cooling is a key factor when running the MFSYS25. About 80% of the MFSYS25 front panel is perforated, so if you put your hand in front of the running chassis, you can feel the amount of air drawn in from different parts of the panel. There are three main sources for this induction.
In the rear of the main chassis are two hot-swappable main cooling modules that are used to pull air through the heavily perforated front panels in front of the compute modules. These large modules sit in a vertical arrangement so that each main cooling module is positioned to cover either the top three compute modules or the bottom three.
As the fans spin, air rushes over each of the compute modules’ voltage regulator, CPU, and memory banks before exiting through the main cooling module. Each of these two larger cooling devices consists of two 4.5" fans in a 1+1 redundancy configuration and sits in a tandem position. Each fan then plugs into a small circuit board inside the module housing, which in turn plugs into the MFSYS25 midplane.
As mentioned before, each of the main cooling modules cools down three of the six compute modules, so if there is a problem with a faulty fan, it should be replaced immediately. The user manual states that hot-swappable cooling devices should be replaced within a minute, especially if the MFSYS25 is fully populated with six compute modules.
The smaller I/O cooling module sits on the front of the main chassis, just below the storage enclosure. Inside this smaller module are six 1.5" fans that run in a 3+3 redundancy configuration. The I/O module pulls in air from the front of the chassis and directs the flow to the back, which cools the I/O devices in the rear of the system. Like the other two cooling modules, the I/O cooling module is hot-swappable as well.
One interesting observation I made during this evaluation was the behavior of the entire cooling system when one of the three modules was pulled out. When the chassis loses a cooling component, the remaining two devices go into high gear. From the increase of air flow, it would seem that the chassis is compensating for the missing device. However, neither the MFSYS25/MFSYS35’s user guide nor the technical product specification manual mentions this behavior, while an email from an Intel representative said that this is normal behavior.
I found out that in case of a cooling device failure that the remaining main cooling module will continue to run at 100% activity and can run in this state for a while. On the other hand, if there was a problem with the sole I/O cooling module, then an immediate replacement would be necessary.
I couldn’t wait to test the overall heat coming out of the MFSYS25 at different compute module configurations. After bringing up all three compute modules (one at a time), I sequentially shut them down until I was just running the chassis by itself. The startup and shutdown of the compute modules were completed in 15-minute intervals.
I started with just the chassis and the disk drives powered on. Note that the compute modules were in their bays the whole time, but no command to start them up was issued until later.
I then powered on the compute modules in 15 minute intervals. By interval 4, you can see that the amount of heat coming out of the main cooling modules increases dramatically.
As might be expected, when power consumption increased and after I added more compute modules to the chassis, there was a significant increase in heat, not only from the newly powered-up components, but from the power supply modules as well. There’s at least a 19 degrees Fahrenheit heat increase coming from the cooling modules as they pull the hot air away from the three compute modules. If I had loaded the chassis with three more compute modules, then I’m sure the line representing the main cooling modules would be close to the power module’s temperatures. At interval 5, I started shutting down the compute modules at 15 minute intervals. This “shutdown” test produced an almost mirror-image of the system as everything was booting up during the first half. Note that temperature coming from the compute modules’ front panel only went up and down by three degrees. This just means that the CPUs near the front of the compute modules were probably being well ventilated by the flow of fresh air coming from the front of the chassis.
Latest Servers News
- 24/05 – HP Announces Plans to Lay off 27,000 in Next Two Years
- 18/05 – Supermicro Highlights its Latest X9 SuperServers at GTC 2012
- 17/05 – Microsoft Proposes Personal Honeypots to Fend Off Hackers
- 04/05 – How Scientists Plan to Stop Nasty Side-Channel Attacks
- 27/04 – Apple Promises 100 Percent Green Data Center
And the point of this is...?
How much did intel pay for this advert?
Im not too sure if the readers of TomsHardware UK would be much interested in a Intel 24-Core, 14-Drive Modular Server
I agree, its just a big dirty advert!!
Very interesting .. I take it you guys dont really work with servers that much .. ??
I bet it wont even play CRYSIS!!!
Why do people only care about articles based on games?
If the topic of an article doesn't interest you don't read it. Nobody is forcing you. Do you call your radio station or tv channel to tell them that the program they have on doesn't interest you?
God !!! I'm surrounded by morons !!!
Well i wud if they broadcast porn on a family show just cos its relevant to the dad..
God!! i am surrounded by geeks!!
Aye it won't play Crysis because its a SERVER! Hehe. To be honest I thought it would be funny to try and install Diablo 2 on a Server 2003 system. It kinda went TILT and gave me the finger.
Joking aside, I quite like this sort of geeky stuff as I work with networks everyday. Good to keep up with what's new and what to blow my budget on.
Its a nice bit of kit for sure, that setup with virtualisation would probably half the size of many companies server rooms. However it only makes sense if your going to fill the sysem with the maximum of servers and hard disks and need the capacity.Its perfect for a building
a powerfull server cluster.
obvious advert is obvious
however advert does go in depth and while it may not play crysis at full spec (what the hell will?) it does shine the noble light yet again out of intels a$$ to show that yet again they are trying to corner every market they can
as this is a ardware and occasional software site im not suprised this article is here a little less advert and a bit more under the hood and more in detail what we can do to it would be nice but meh
u pay for what u get and last time i checked im not paying for this site (just my interwebs bill)
Toms have always been intel biased, it sucks
It's nice to see some server reviews once in a while... don't listen to those gaming worshipers, to them virtualization doesn't compute because it cannot run Crysis.
Intel does some pretty good servers, it's sad that some of us have to search hard for proper reviews
You guys are like someone who watches the car reviews program and says 'I'm going to complain to the broadcaster, I don't like cars.'
I don't see that reviewing something from Intel shows 'intel bias' unless you can say how they've managed to tilt the playing field in Intel's favour.
Historically, Intel architecture has dictated that multi-core solutions connect via the FSB, limiting CPU-CPU bandwidth. AMD's solution was streets ahead (and competitively priced) and even now, it would take a lot of convincing for me to go back to Intel. I'm sure each person has their own reasons for choosing a particular setup, however.
Given that toms has never reviewed a server product such as this one ever before(and that there has been such products available through multiple products for many years); that this article makes no attempt to make a quality or critical review by using real world benchmarks, extensive and varied testing; there is no real attempt to compare this product to many other simillarily configured systems and finally that the reviwer seems content to offer nothing more than superfical and trite crtitism such as "this remote access server product has no power button"- I think its more than fair for the readers of toms to asume that intel had a hand in suggesting this review for marketing.
What a nice change to find a hardware site talking about new Industry HARDWARE, rather than just new gaming ware.
It's just a shame that some of the readers commenting on here think that they know all about hardware because they've built or overclocked a system at home, least of all those that then start throwing around insults directed at TOMS because it's not applicable to them.
But IBM BladeCenter QS22 Still much stronger .
see Roadrunner Supercomputer in wikipedia .
and NASA test it and found the 'Cell C' are 8 times faster then 'Xeon5150'.that's Cell C
and 'IBM PowerXCell 8i' use new article "40nm" in the
BladeCenter QS22 server .and it have two 'PowerXCell 8i' this mean at less 16 times faster the Intel crap Xeon .
X86 are really out the range now "they use it basically in late 70s to save the money on the DRAM because 1M cost that days about $5,000.!
Awesome review, am atm searching for some modular stable solution for our client, something like this should be enough fail-safe to provide 99% stability.
to trolls talking crap about shitty reviews:
go to your mommy ask for money for a gaming machine and go play crysis 2, scrubs.