Beta

Slashdot: News for Nerds

×

Welcome to the Slashdot Beta site -- learn more here. Use the link in the footer or click here to return to the Classic version of Slashdot.

Thank you!

Before you choose to head back to the Classic look of the site, we'd appreciate it if you share your thoughts on the Beta; your feedback is what drives our ongoing development.

Beta is different and we value you taking the time to try it out. Please take a look at the changes we've made in Beta and  learn more about it. Thanks for reading, and for making the site better!

Facebook VP Slams Intel's, AMD's Chip Performance Claims

timothy posted more than 5 years ago | from the more-than-half-of-you-less-than-half-as-well-as-you-deserve dept.

Intel 370

narramissic writes "In an interview on stage at GigaOm's Structure conference in San Francisco on Thursday, Jonathan Heiliger, Facebook's VP of technical operations, told Om Malik that the latest generations of server processors from Intel and AMD don't deliver the performance gains that 'they're touting in the press.' 'And we're, literally in real time right now, trying to figure out why that is,' Heiliger said. He also had some harsh words for server makers: 'You guys don't get it,' Heiliger said. 'To build servers for companies like Facebook, and Amazon, and other people who are operating fairly homogeneous applications, the servers have to be cheap, and they have to be super power-efficient.' Heiliger added that Google has done a great job designing and building its own servers for this kind of use."

cancel ×

370 comments

You're Computin' for a Shootin' Mister (5, Insightful)

eldavojohn (898314) | more than 5 years ago | (#28476905)

So let me get this straight, the Vice President of a web company is criticizing the hardware guys in two of the world's biggest chip makers?

You guys don't get it

Is it possible to take out a massive life insurance policy on Jonathan Heiliger?

To build servers for companies like Facebook, and Amazon, and other people who are operating fairly homogeneous applications, the servers have to be cheap, and they have to be super power-efficient.

I assure you, despite your misconception that the world revolves around you everyone has those requirements. From the people who build supercomputers right down to the netbook I am typing on while watching Gurren Lagann.

Can we get like a panel of hardware engineers to have a discussion with this guy and can I get some popcorn?

Re:You're Computin' for a Shootin' Mister (4, Informative)

Daengbo (523424) | more than 5 years ago | (#28476999)

Can we get like a panel of hardware engineers to have a discussion with this guy and can I get some popcorn?

Slashdotters might want to take a look at the details of the Google servers [cnet.com] to see what Heiliger is looking for. There's also a video tour. [youtube.com]

Re:You're Computin' for a Shootin' Mister (3, Insightful)

timmarhy (659436) | more than 5 years ago | (#28477127)

i don't know that i agree with some of googles design choices. do they account for details such as 10 small batteries are more expensive than 1 large battery of the same capacity?

and why have a PSU for each unit, why not just run 12v power rails to each server and do the ac/dc conversion on a larger transformer further down the line with larger batteries providng the back up for clusters of servers? after all no psu is cheaper than a psu with just the 5v taken out.

Re:You're Computin' for a Shootin' Mister (4, Informative)

fuzzyfuzzyfungus (1223518) | more than 5 years ago | (#28477179)

At low DC voltages, you can't really do long cable runs without either suffering substantial resistive losses or using cable so thick you could club a seal to death with it.

Re:You're Computin' for a Shootin' Mister (5, Funny)

Anonymous Coward | more than 5 years ago | (#28477381)

I vote for the seal clubbing thing.

Re:You're Computin' for a Shootin' Mister (3, Informative)

mabhatter654 (561290) | more than 5 years ago | (#28477439)

I think they run AC to the row or rack of servers, then they have just one super efficient PSU powering all the servers in a rack rather than 42 separate power supplies (plus UL enclosures, connectors, extension cords, etc, etc)

Essentially Google builds "rack-sized" blade centers... or at least catching up to what IBM and HP are doing but on a bigger scale, like full racks or multiple racks managed at once rather than just one chassis.

I do agree that chip makers aren't thinking "big enough" with things like their Blade lines.. Google wants to see reference specs that include options for bare motherboards to slide right into your basic 42 unit rack with IO, disk and power all pulled out to the raw basics so Google can decide how to manage the bits rather than having stock OEM boards with such limited options. Google wants to manage a "rack" as a single machine and optimize power and parts across 40 servers as one group, not 40 separate little systems.

Re:You're Computin' for a Shootin' Mister (5, Funny)

jamesh (87723) | more than 5 years ago | (#28477617)

cable so thick you could club a seal to death with it.

What's with everyone creating new units of measure? "We're going to need some 3 Seal Cable for this job!"

Re:You're Computin' for a Shootin' Mister (1)

timmarhy (659436) | more than 5 years ago | (#28477673)

i wouldn't suggest one single psu for a whole center, just one per rack. surely it would be cheaper then messing around mounting batteries to each server? for one thing it'd make the racks top heavy if the rack wasn't 100% full.

Re:You're Computin' for a Shootin' Mister (0)

Anonymous Coward | more than 5 years ago | (#28477399)

Thats what Blade Chassis are used for

Re:You're Computin' for a Shootin' Mister (5, Funny)

node 3 (115640) | more than 5 years ago | (#28477595)

i don't know that i agree with some of googles design choices

I'm sure they'll get right on that, random slashdot guy...

Re:You're Computin' for a Shootin' Mister (-1, Troll)

timmarhy (659436) | more than 5 years ago | (#28477643)

i don't give 2 shits if they don't, why are you so offended is the question?

Re:You're Computin' for a Shootin' Mister (2, Insightful)

Frosty Piss (770223) | more than 5 years ago | (#28477081)

You've basically agreed with him. Whats your bitch? I don't get it.

Re:You're Computin' for a Shootin' Mister (0)

Anonymous Coward | more than 5 years ago | (#28477541)

He did not "agree with him".

The point is subtle:

Yes, the requirements mentioned in the summary are ones that are important to everyone.
No, Heiliger does not understand this, and seems to believe the requirements are specific to Facebook and Google-like sites.

But: Yes, the hardware manufacturers are actually already aware of these requirements, but aren't meeting them.

WTF? (1, Insightful)

Spit (23158) | more than 5 years ago | (#28476921)

Maybe the dude should have benchmarked before committing. How does he scope his projects, with brochures?

Re:WTF? (-1, Troll)

Anonymous Coward | more than 5 years ago | (#28477039)

Probably the fact that only those fuckin' gamers and other masturbating cockney desktop yuppies are driving the exaggerated claims of Intel and AMD chips. Do you notice the performance gain from a 4, 534, 654 Niggawatt chip to a 5, 135, 345 Niggawatt one?

Me either.

Re:WTF? (5, Insightful)

Zebai (979227) | more than 5 years ago | (#28477069)

I agree I think this was writing his own resignation with this crap. The guy is basically telling everyone that he is incapable of finding an acceptable solution for his company and blaming intel and amd because he has committed a great deal of money on something that he didn't plan well enough to know exactly what the long term costs vs performance was. In the very article he says to not be cheap, but in many more words than necessary, probably to try to disguise what he is saying like most politicians, that they were not only too cheap, but made bad decisions on what to be cheap with. Its as if he's already in a public office, hes telling everyone he screwed up, why he screwed up, and trying to make it look like hes teaching everyone lesson to make his mistake to be less of a disaster.

Re:WTF? (4, Interesting)

Spit (23158) | more than 5 years ago | (#28477331)

Looks like that to me; he scoped for cheap and cheerful and was bit on the ass when he realised that sometimes you get what you pay for. Like what's the point in having quad-core server CPU without the high-bandwidth buses of server-grade hardware.

In the concurrent DNS/Kaminsky thread, I saw a reference that facebook's DNS TTL is low. A quick investigation reveals that they have a 30 second TTL and are using DNS round-robin for their load balancing.

He's nothing but a blame-shifting cretin.

Re:WTF? (4, Insightful)

cryogenix (811497) | more than 5 years ago | (#28477361)

I think we read different articles. He's not saying he didn't plan well enough, he's saying that Intel and AMD promise that Gen Y processor is 35% faster than Gen X processor, and he's not seeing anywhere near 35% in real world performance. The 35% is a made up number but it doesn't matter what the number is that they claim. He's probably correct. Manufacturers pull this stuff all the time. Look at the recent articles on battery life claims on notebook's. AMD came out and called BS on the whole thing and basically said if you guys don't stop lying through your teeth, the FTC is going to regulate us. From the perspective you are taking, that would mean we have to call AMD incompetent for not understanding how batteries work and not properly selecting them.

Manufacturers ALWAYS overstate claims in computer related products. CRT actual inches vs viewable inches (thank you lcd's for finally being honest... about inches anyway.. brightness and contrast however....) Computer speaker wattage being 1/2 or 1/4 of what's claimed. Power supply efficiency or wattage not measuring up to claims... you name it. He's calling out what he see's to be bogus claims based on a real world experiences in a demanding environment, the type of environment where one is always looking for better performance. I think we should get some more information before declaring him to be the problem as I'm sure he has a whole team of people that are working on this issue.

What I'd like to see from him is some numbers. On this Intel (or AMD) rig, we get so many operations per hour/minute/whatever. On this new Intel (or AMD) rig which they claim is 20% faster than the previous rig, we're only seeing this number of operations per hour which amounts to only a 7% gain, thus we're seeing 13% less than they are claiming. Again, numbers made up for examples sake. I'd also be very interested in what a typical rig of theirs looks like... X Processor, Y Ram, what type of storage system is it connected to, etc. I think such numbers are vital to understanding the issues at hand. We all know that vendors will run the benchmarks that makes their stuff look the best, and that is often not reflective of real world performance. If I was Intel/AMD I'd be chiming in right about now and opening a dialog with Facebook and looking to see what the issues are. Facebook is a big customer with huge name recognition and you want to be able to use them as an example of your solution delivering the promised performance for your marketing. I'm going to assume (I know I know) that they are already working with the server vendor to try and see what's going on here.

Re:WTF? (2, Interesting)

MidnightBrewer (97195) | more than 5 years ago | (#28477475)

How can you be blamed for finding an acceptable solution when there simply isn't one available? He is a software developer, not a hardware one. Not everybody can just go out and design their own servers like Google does. He's saying he's been tripped up by the fact that the server manufacturers aren't delivering on their promises; hardly something he should be blamed for. Your attempts to read more into his comment about "not being cheap" and compare it to the false words of a politician seems like a pretty big stretch.

If you read the entire article, he not only doesn't say that his decisions have led to disasters, but instead says that his infrastructure development decisions have led to very smooth transitions, even when Facebook rolls out big, new features like the customized home page URLs. He is only voicing his disappointment in saying that the servers aren't living up to the hype, and that he is still looking for a better solution.

I will say that his comment to not be cheap seems to be in direct conflict with the rest of his argument, since his criticism over AMD and Intel revolves around the fact that they need to be cheaper. Seems a bit counter-intuitive.

Re:WTF? (1, Informative)

whoever57 (658626) | more than 5 years ago | (#28477335)

I have some sympathy for this guy. Some years ago, I built a fileserver using the best SATA RAID (hardware RAID) cards I could find (~$300) from major manufacturers and enterprise disks (specified for use in RAID systems)

Performance absolutely sucked. The cards were fast enough it I tried to read/write single large files, but when reading/writing large numbers of small files, they were very slow. The first manufacturer's card was appallingly slow. I replaced it with another manufacturer's card and performance was merely slow.

I followed all the manufacturer's recommendations, I communicated with one manufacturer on a Linux RAID mailing list, but was never able to get anything remotely like acceptable performance. For compariso, later I built a fileserver around an old (sub 1GHz) PC, using software RAID and was able to get at least the same performance.

I was only building one machine, so I did not have the luxury of benchmarking it.

Re:WTF? (1, Insightful)

afidel (530433) | more than 5 years ago | (#28477403)

Wow, you found out that 7200rpm SATA disks suck for small random I/O? That's surely a shocker! Oh wait, it's not and the least bit of research would tell you that. It's the same thing with Facebook, they expect to get awesome performance/dollar out of interpreted code and are blaming the hardware when it doesn't magically come true.

Re:WTF? (2, Interesting)

Spit (23158) | more than 5 years ago | (#28477523)

You can better identify your bottlenecks by benchmarking. Facebook's scalability is likely not as cpu-bound as predicted, thus the dude's angst on discovering that CPU upgrades weren't a silver bullet.

In your case, you haven't looked past the RAID configuration for the root-cause of your performance issues. Without benchmarking you don't really know if it was an issue with: the filesystem, the block size, stripe size, or a caching tunable.

Systems architecture isn't as easy as PC builders would have you believe.

Hm... (3, Insightful)

Darkness404 (1287218) | more than 5 years ago | (#28476941)

To build servers for companies like Facebook, and Amazon, and other people who are operating fairly homogeneous applications, the servers have to be cheap, and they have to be super power-efficient.

Hm, lets see... perhaps because Facebook and Amazon are niche markets? The average server isn't going to even need all the computing horsepower and the power efficiency is simply a drop in the bucket for most companies electrical bills. The average server is going to be much more I/O intensive than CPU intensive unless you do cluster computing or render a lot of stuff. The average server such as a web server or a file server doesn't use that much CPU and usually you are running 1-3 servers, not the hundreds that Facebook or Amazon would run.

And really, why is a VP complaining about this stuff? That he can't either afford custom solutions or spend the money buying more servers?

Re:Hm... (0, Troll)

VinylRecords (1292374) | more than 5 years ago | (#28476995)

Hm, lets see... perhaps because Facebook and Amazon are niche markets?

Niche market? Considering over 100 million people are logging into Facebook every day and Amazon is massive online retail entity I would hardly call them niche.

Some info on Facebook:
- More than 200 million active users
- More than 100 million users log on to Facebook at least once each day

http://www.facebook.com/press/info.php?statistics [facebook.com]
http://www.alexa.com/topsites [alexa.com]

Facebook is the fourth most popular website according to Alexa and Amazon is at 34. Niche? Really?

Re:Hm... (2, Insightful)

Darkness404 (1287218) | more than 5 years ago | (#28477025)

Niche as in, only a few companies (~100) are going to need the same solutions. On the other hand the vast majority of servers will be for much, much, much less intense use. Then you have the problem that really Facebook isn't super profitable, Amazon is but they seem to be doing decent with their servers and have the spare cash to simply upgrade them. I mean, other than a few websites who needs a "perfect" server?

Re:Hm... (0, Redundant)

JackieBrown (987087) | more than 5 years ago | (#28477177)

You need to read his post again if you think that is what darkness meant

Re:Hm... (2, Informative)

Quothz (683368) | more than 5 years ago | (#28477185)

Hm, lets see... perhaps because Facebook and Amazon are niche markets?

-Maybe-. Even if they are a niche market, they're a big enough one to hold the attention of the big chipmakers.

A traditional business model might use large orders, especially advance orders, to offset or defray the cost of setting up a production line or facility, and get most of the profit from smaller sales. Or they may choose only to do production runs for large, inherently profitable orders. Even in a firing-from-the-hip model, large customers cost less per unit in marketing and sales than do smaller ones, very much so when compared to the general public. And of course there's plenty of wiggle room between extremes. So depending on the diversity of the market and the choice of business model, big customers range from important to desirable. Naturally, in a niche market large customers have a greater importance, since smaller sales are fewer.

Presumably, AMD and Intel are selling servers to the likes of Amazon and Facebook 'cause they think it's profitable. If it is a niche market, keeping those guys happy is paramount to profitability.

(I don't think the server farm market is really a niche, tho'. But I dunno; I don't keep up with such things.)

And really, why is a VP complaining about this stuff? That he can't either afford custom solutions or spend the money buying more servers?

Well, because we asked. Well, not "we" as such, but someone asked him and he answered. It sounds like he was answering honestly and openly. I've no problem with that.

Re:Hm... (0)

Anonymous Coward | more than 5 years ago | (#28477587)

Well, because we asked. Well, not "we" as such, but someone asked him and he answered. It sounds like he was answering honestly and openly. I've no problem with that.

Nice business plan -- trash the only two outfits who can get you what you want.

Flies, honey, vinegar.

Re:Hm... (1)

vux984 (928602) | more than 5 years ago | (#28477211)

That he can't either afford custom solutions or spend the money buying more servers?

Tell me again what Facebook's revenue model is...??

Surely that's obvious (3, Informative)

grahamsz (150076) | more than 5 years ago | (#28477447)

They collect a large amount of data on people and mine that for marketing information to turn around and target those same users.

It's the same model as google.

Re:Hm... (5, Informative)

HockeyPuck (141947) | more than 5 years ago | (#28477411)

The average server is going to be much more I/O intensive than CPU intensive unless you do cluster computing or render a lot of stuff.

As someone who designs and deploys large storage environments for a living, I call BS. While the current generation of HBAs are 8Gb FibreChannel, I would say that the "average server" (as you put it) could happily live on a 1Gb HBA. Recall that almost all servers, or atleast those you care about, have DUAL HBA connections to their respective storage. So that's actually 2Gb of storage connectivity. Sure there are servers which have multiple HBAs, or use a higher utilization of the HBAs, such as database servers or backup/media servers. Most servers today are deployed with dual 4Gb HBAs as the 8Gb SFPs/optics are still quite pricey, and you cannot, in all seriousness, purchase 1 or 2Gb FC HBAs.

Even as we deploy VMware based servers, the VMware servers themselves tend to be more memory/cpu strapped than IO.

It would be very rare, or almost impossible for a server to be driving linerate HBAs, with still plenty of headroom left in the CPU. Even basic test tools like IOmeter require significant CPU usage to drive an HBA to capacity. And that is when it's writing/reading all zeros. It's doesn't actually need to do anything with the data. As would be the case if a database server was requesting 2Gb/s from a disk array, and then had to join/sort/add/whatever the tables retrieved.

 

Re:Hm... (0)

Anonymous Coward | more than 5 years ago | (#28477467)

I assume the masses of PHP scripts they have to run aren't CPU intensive? And rather large SQL databases...

Re:Hm... (1)

mabhatter654 (561290) | more than 5 years ago | (#28477535)

they may be "niche" but data centers are the top multiple unit customers, buying thousands of the exact same configurations from OEMS .... they've surpassed the "enterprise cube farm" desktops buy a good margin in that data centers buy the MOST expensive server CPU they can where Enterprises are buying the cheapest desktops they can... Data center customers and Gamers are the only ones that NEED new CPUS every six months... nobody else really cares as they're out buying no-profit Atom based netbooks now.

YouTube... (0)

Anonymous Coward | more than 5 years ago | (#28476943)

YouTube has been constantly crashing and showing server errors more frequently over the last month. I'm not sure how much more bandwidth that YouTube demands over Facebook or Amazon (if it does) but whatever issues with servers and reliability that the Facebook team is having with Intel and AMD might be even worse over at YouTube.

Anyone experiencing major outages and slow movement and loading times over at YouTube recently? Can't say I've had a problem with Amazon or Facebook other than intended outages for updates or repairs in the last month.

Facebook's application is poorly coded (3, Insightful)

jsimon12 (207119) | more than 5 years ago | (#28476965)

I have heard from some reliable sources that Facebook and Twitter's backend applications are poorly written.

Are Intel and AMD's claims overblown, sure what hardware manufacter doesn't cherry pick performance claims.

But I don't care what sort of hardware you through at crap code you are always going to get crap performance.

Re:Facebook's application is poorly coded (1)

lothos (10657) | more than 5 years ago | (#28477019)

The facebook code was leaked a year ago:

  Facebook users on Monday were left contemplating the security of private details stored on the social-networking site after part of its source code was leaked onto the Internet.

The site on Monday acknowledged that a section of its code had been copied and published on a blog, but stressed that none of the personal details of its 52 million users had been compromised.

Over the weekend, a blog called Facebook Secrets published details of part of Facebook's source code, the set of commands which determine the way the site appears when it is viewed by users.

Re:Facebook's application is poorly coded (3, Insightful)

royallthefourth (1564389) | more than 5 years ago | (#28477085)

Crap code on faster computer is still going to be faster than it was on a slower computer. He's not saying anything about how efficient their software is, just that buying new processors didn't get him the performance delta that it was supposed to. More advanced hardware should deliver a performance benefit no matter what is running on it.

Re:Facebook's application is poorly coded (2, Insightful)

corychristison (951993) | more than 5 years ago | (#28477123)

More advanced hardware should deliver a performance benefit no matter what is running on it.

Not if your code is not tuned for this new "advanced hardware". Surely there are new compile flags to consider, and if you are not tuning your code for the new processor features it could very well be slower than before.

Re:Facebook's application is poorly coded (1)

royallthefourth (1564389) | more than 5 years ago | (#28477223)

More advanced hardware should deliver a performance benefit no matter what is running on it.

Not if your code is not tuned for this new "advanced hardware". Surely there are new compile flags to consider, and if you are not tuning your code for the new processor features it could very well be slower than before.

Facebook is written in PHP; there are no compile flags.

Re:Facebook's application is poorly coded (5, Informative)

hidden (135234) | more than 5 years ago | (#28477323)

Facebook is written in PHP; there are no compile flags.

apache and the php engine have plenty of compile flags. not to mention whatever the database is.

Re:Facebook's application is poorly coded (0)

Anonymous Coward | more than 5 years ago | (#28477329)

Ya don't think, maybe this makes compile flags even more important for the base PHP lib?

Re:Facebook's application is poorly coded (0)

Anonymous Coward | more than 5 years ago | (#28477187)

Crap code on faster computer is still going to be faster than it was on a slower computer

That is only partially true. But what if they have algs in there that are O(N^N)? Say N is the number of users? And they are adding 1000 new users per day?

So as they add more users the 'better' hardware does NOTHING for them. It sounds like Intel or AMD reps promised them the moon and they bought the story. I would say perhaps he was sold a bill of goods. But guess what without metrics to back it up. Like how does it run with HIS software I would say he didnt do his job.

I would also say a bad alg on better hardware will eventually perform just as bad once you add more users. They are trying to throw more hardware at the problem without understanding the problem. Or perhaps they do but are unwilling/unable to change something?

Re:Facebook's application is poorly coded (-1, Troll)

RightSaidFred99 (874576) | more than 5 years ago | (#28477373)

No, the facebook guy is just stupid, that's all. There are plenty of other performance bottlenecks in a system. Hard drive performance is currently the biggest one. This asshole is like a gamer who updates from a 2.2GHz processor to a next-gen 3.0Ghz faster per clock CPU then complains when Crysis doesn't run any faster.

Yeah, stupid, Crysis isn't faster because your $150 graphics card was the bottleneck.

Re:Facebook's application is poorly coded (3, Insightful)

evanbd (210358) | more than 5 years ago | (#28477167)

Developers have been known to trade off performance for development ease. Frequently the result is crap code. Yes, it performs like crap on both sets of processors. But if the application is CPU-limited (rather than IO or memory or...), then throwing faster CPUs at it ought to make it proportionally faster, no? Obviously they thought the previous performance was acceptable, is it unreasonable to think that buying CPUs marketed as 50% faster should give a 50% performance increase? Clearly crap code will still run like crap, but you ought to be able to throw more CPU power at it and get 150% of crap performance.

Re:Facebook's application is poorly coded (0)

Anonymous Coward | more than 5 years ago | (#28477569)

Developers have been known to trade off performance for development ease.

[cough] java [cough]

Depends on 'headroom' of other subsystems. (2, Informative)

Kadin2048 (468275) | more than 5 years ago | (#28477571)

Not necessarily, no.

It's all about how CPU limited the workload is.

You might be running a program that's CPU limited on one processor, then upgrade the processor and discover that it's suddenly discover that instead of being CPU-bound, now you're memory-bound. Or I/O bound. Or whatever.

Point is, just because you've hit the wall in terms of CPU doesn't mean you'll get a 50% improvement with a 50% increase in CPU ... you'll only get that if all the rest of the server's systems have 50% overhead to spare. And in most cases they don't. One of them will hit the performance wall before you return to being CPU-bound with the shiny new processor.

There are exceptions to this -- renderfarms, for instance, or some distributed HPC stuff -- where you really can reasonably expect to get 50% more performance out of 50% more CPU, but they're exceptions not the rule.

Re:Facebook's application is poorly coded (4, Interesting)

Necroman (61604) | more than 5 years ago | (#28477337)

One of the server techs from Twitter was at SXSW 2 years and gave some details about how their backend servers worked. If I remember correctly (there were 4 sites on the panel, so I may be confusing them with someone else), the original code was written in Ruby on Rails which did not scale well to the multi-server systems that they had setup. They have spent a lot of time improving their code over the years, but from what I could tell, their initial implementation wasn't the most thought out thing in the world.

Re:Facebook's application is poorly coded (0)

Anonymous Coward | more than 5 years ago | (#28477531)

...

But I don't care what sort of hardware you through at crap code you are always going to get crap performance.

A wise man once said: A computer's performance is 10% hardware, 90% software

Well I suppose... (3, Funny)

cptnapalm (120276) | more than 5 years ago | (#28476967)

Well, I suppose that if he does not like the offerings from Intel and AMD, they could always go with...

Uh..

Oh.

Re:Well I suppose... (5, Informative)

the linux geek (799780) | more than 5 years ago | (#28477041)

Let's see... IBM, Sun, Fujitsu, Itanium (yeah, its still Intel, but has great performance)... All of these can offer equivalent or much better performance at these kinds of applications than what they're using. Don't bitch if you're not willing to consider the alternatives.

Re:Well I suppose... (1)

WilliamBaughman (1312511) | more than 5 years ago | (#28477175)

[...] Itanium (yeah, its still Intel, but has great performance) [...]

Does a VLIW processor with lots of cache really do well (in terms of transactions per Watt) compared to a non-VLIW processor for hosting web apps? My understanding was that Itanium chips were made on older processes because of their large die size, they need the lowest possible defect rate to get good yields. That hurts their performance / power. Also, I don't know if having a large amount of cache is cost effective for hosting web apps unless you're hosting the same content again and again, at least compared to having lots of RAM and fast memory access. Using power and transistors on cache doesn't seem like a good idea to me when you're serving that much data for random access requests. Also, I don't see how Instruction level parallelism would work for a web app that's as customizable as Facebook, because each user request will require a slightly different response. I'd be interested in seeing Fujitsu chips enter the fray, I forgot to mention them in my post.

Re:Well I suppose... (1)

the linux geek (799780) | more than 5 years ago | (#28477355)

I was actually just throwing that in as an alternative. At my company, we use Itanic for machines in our compiler farm, running the Intel C Compiler. It gets excellent performance for this purpose; it does quite well on moderately parallel tasks and okay for floating point. I can't speak for how well it does for anything web-facing though. Out of the four I mentioned (POWER6, SPARC T1/T2, SPARC VIIIFX), its probably the worst-suited for this specific type of task. Of course, anything beats the shit that is x86.

Re:Well I suppose... (3, Interesting)

Trixter (9555) | more than 5 years ago | (#28477393)

I was just going to say that. If Facebook et al are not looking at the Sun coolthreads servers, they're idiots. A T5240 would deliver a whopping 128 hardware threads per 1u of rackspace.

Re:Well I suppose... (0)

Anonymous Coward | more than 5 years ago | (#28477697)

All those Niagara hardware threads is good for throughput. Not performance. Sun sucks big time on performance. To bump up performance they had this whole Rock line of processors but they canned the whole thing.

Re:Well I suppose... (1)

RightSaidFred99 (874576) | more than 5 years ago | (#28477421)

None of these offer much better performance. None. Please find me a general purpose (even niche) processor with higher performance than a high end Xeon across a variety of loads. Power? Nope. Anything from Sun? Nope. When Nehalem comes out it will not be possible to buy a general purpose CPU for anything up to 8 sockets (64 cores).

Re:Well I suppose... (1)

RightSaidFred99 (874576) | more than 5 years ago | (#28477423)

I meant when Nehalem-EX comes out - Nehalem is of course out.

Re:Well I suppose... (0)

Anonymous Coward | more than 5 years ago | (#28477517)

Yes http://tech.slashdot.org/article.pl?sid=08/04/10/1152205 Power6

http://www.tpc.org/tpcc/results/tpcc_perf_results.asp

http://www-03.ibm.com/systems/power/hardware/benchmarks/

Re:Well I suppose... (2, Informative)

fishbowl (7759) | more than 5 years ago | (#28477565)

>None of these offer much better performance. None.

There are IBM and Sun systems that are in an entirely different league, in terms of IO and memory bandwidth, than any Intel- or AMD-flavored system.

Re:Well I suppose... (0, Flamebait)

the linux geek (799780) | more than 5 years ago | (#28477663)

POWER6 absolutely ass-rapes Nehalem. Period. 4.7GHz (clocked up to 6GHz internally), faster per-cycle than any x86 processor currently on the market.

Re:Well I suppose... (1)

WilliamBaughman (1312511) | more than 5 years ago | (#28477077)

Well, Sun's Niagara 2 processor seems pretty good at number of network I/O operations per Watt. And if he doesn't like that, he can try IBM's Power6, although I hear it's better for floating-point than integer (relative to Intel and AMD's offerings.) If he doesn't like that, he can sell his company to Google and ask them to build servers for him.

Sun.... (2, Insightful)

Fallen Kell (165468) | more than 5 years ago | (#28477079)

Its the next logical solution... Those T5440 servers with 256 processing threads are MONSTERS in terms of handling simultaneous connections which make them very good web servers, database servers, and file servers, all of which means they are very good for a company who's product is a website.

Re:Sun.... (0)

Anonymous Coward | more than 5 years ago | (#28477199)

Sun?.... you are crazy to go with sun and there platform now.. its all dead now..

Re:Sun.... (2, Funny)

Temkin (112574) | more than 5 years ago | (#28477267)

Sun?.... you are crazy to go with sun and there platform now.. its all dead now..

Larry? Is that you?

Re:Sun.... (2, Interesting)

Fallen Kell (165468) | more than 5 years ago | (#28477371)

Not really. What is dead is Rock. Coolthreads are here to stay, especially now that Oracle bought them. Niagra Falls is the fastest single server Oracle server currently in existence. Oracle is going to continue to build on that platform, with most speculation being that they are going to release a "black box" Oracle solution, which will simply be a drop in place, connect power and network, and turn the key solution, eliminating the need for the company that purchases said solution to have system admins who have had enough Oracle training to know how to properly setup a server to run the database. Oracle will then sell "support" for the systems on a tiered basis. It will most likely be based on the same platform as the Sun Unified Storage System line, like the 7410, even available with Oracle RAC as an option.

Re:Well I suppose... (1)

NervousNerd (1190935) | more than 5 years ago | (#28477169)

I heard that Cyrix CPU's had bitching performance.

Re:Well I suppose... (3, Informative)

kzieli (1355557) | more than 5 years ago | (#28477207)

There's actually 2 seperate points here
  1. the latest CPU's don't seem to be any better in practice then the previous model.
  2. Server OEM's are not delivering power efficient servers.

the two points are somewhat independent of each other. The second I suspect is due to their being a lack of any standard for power efficent servers. Google did it by running single voltage power supplies. A standard around something like this would be useful, and not just for servers I suspect.

ARM? (1)

sznupi (719324) | more than 5 years ago | (#28477625)

I wonder when we'll see servers with CPUs based on (many...) ARM cores.

Yes, they are an order of magnitude slower, but three orders of magnitude more power efficient. For the same CPU performance you'd probably be around two orders of magnitude more power efficient (for CPUs at least). If your app runs on a large farm already...

Well which is it? (0)

Anonymous Coward | more than 5 years ago | (#28476973)

Do you want your servers to be cheap or do you want them to be good?

Take that... (-1, Offtopic)

actionbastard (1206160) | more than 5 years ago | (#28476975)

bitches.

ARM to the rescue? (1)

bogaboga (793279) | more than 5 years ago | (#28476977)

"...To build servers for companies like Facebook, and Amazon, and other people who are operating fairly homogeneous applications, the servers have to be cheap, and they have to be super power-efficient..."

Sounds like ARM processors are being described here. Whether they can deliver is another subject in itself. On this front, I have my doubts on ARM's ability to deliver. That's my bias.

Re:ARM to the rescue? (0)

Anonymous Coward | more than 5 years ago | (#28477171)

What part of it do you doubt? That they're cheap? (They are) That they're super power efficient? (They are) That they can deliver? (ARM licenses out to dozens of other companies for actual production, so they're available in mass quantities)

Re:ARM to the rescue? (1)

digitalunity (19107) | more than 5 years ago | (#28477563)

As the AC noted, ARM's are available, cheap and power efficient. What they are not, however, is very powerful.

They have their uses, but interpreting large amounts of crappy scripts is not one of ARM's strong points.

Something about his arguement doesn't work (5, Insightful)

joeflies (529536) | more than 5 years ago | (#28476989)

1) Facebook & Amazon need cheap, power efficient systems
2) Intel and AMD aren't measuring up with processors to power these systems
3) However, Google has systems appropriate for this use (presumably using Intel or AMD processors)

If that's his argument, then it would seem that the real conclusion is that Facebook can't build systems as good as Google's, even though they are using the same processor technology.

Re:Something about his arguement doesn't work (2, Insightful)

joeflies (529536) | more than 5 years ago | (#28477051)

In addition, there seems to be something else wrong with his arguement

"To build servers for companies like Facebook, and Amazon, and other people who are operating fairly homogeneous applications, the servers have to be cheap"

Which he later follows up with the following insight

"There's a pretty simple answer for scaling infrastructure. It's, 'Don't be cheap,'"

so which one is it?

Re:Something about his arguement doesn't work (2, Informative)

blackraven14250 (902843) | more than 5 years ago | (#28477309)

Server Cheapness != Data Center Cheapness

Re:Something about his arguement doesn't work (1)

Gazzonyx (982402) | more than 5 years ago | (#28477313)

I'd assume that the context of 'cheap' is different in both instances. On one hand, you want cheap per unit servers; OTOH, you want to buy many cheap units to be able to scale.
Of course, that's just my interpretation...

Re:Something about his arguement doesn't work (1)

ushering05401 (1086795) | more than 5 years ago | (#28477365)

so which one is it?

Dunno, but I'm not gonna match wits with this guy when death is one the line.

Re:Something about his arguement doesn't work (1)

Hurricane78 (562437) | more than 5 years ago | (#28477529)

Both. Stupid people oversimplify. In this case, he did not mean cheap. He meant... damn, there is no English word for "preiswert". Essentially it is, when you get a good value for your money.
He meant that you should buy much (don't be cheap) with little money (the servers have to be cheap).

Of course, with that level of differentiation of thoughts, it's no wonder that he got problems. ^^

Re:Something about his arguement doesn't work (0)

Anonymous Coward | more than 5 years ago | (#28477613)

Word your looking for is thrifty.

Would you expect otherwise (4, Funny)

Chuck Chunder (21021) | more than 5 years ago | (#28477675)

If that's his argument, then it would seem that the real conclusion is that Facebook can't build systems as good as Google's

Google's core business is intelligence.
Facebooks core business is stupidity.

PHP (3, Interesting)

Anonymous Coward | more than 5 years ago | (#28477011)

And we're, literally in real time right now, trying to figure out why that is,' Heiliger said.

It's because your shitty website doesn't have a single line of compiled code. PHP only goes so far.

Re:PHP (4, Interesting)

afidel (530433) | more than 5 years ago | (#28477151)

Yeah, this. Most of us don't have too much trouble wringing performance out of x64 processors when we need to. He wants a miracle of hardware he can throw at poor code which is NOT what Google asks for. Google simply want to wring every last flop/dollar (TCO) out of their systems which is slightly more than most of us need (the cost of engineering Google type solutions is more than 99.9+% of shops could reap through improved efficiency).

Re:PHP (2, Insightful)

MightyMartian (840721) | more than 5 years ago | (#28477425)

Exactly. All these interpreted languages, even with some special tricks, will have serious scalability issues. At some point you have to look at the application and ask some serious questions.

Re:PHP (1)

digitalunity (19107) | more than 5 years ago | (#28477607)

Exactly. They should start small. Focus on performance profiling, find the most expensive parts of their code and reimplement those in a compiled language.

If they're using Zend and still can't get the performance they need, they just need to accept that PHP's flexibility and rapid development friendliness come at a price-runtime speed.

Re:PHP (0)

Anonymous Coward | more than 5 years ago | (#28477489)

You're a tool if you think they aren't using the Zend optimizer or APC keep the compiled byte-code cached. In the end, it's the same as running Java on a JVM.

I wonder if he's not thinking about scaling enough (1)

filesiteguy (695431) | more than 5 years ago | (#28477107)

Honestly, I think that his arguments fall flat. Though I like FB as much as anybody, and I feel for someone dealing with massive performance needs - I only have a paltry 30 servers running my main application - I wonder if he's being realistic.

There's a pretty simple answer for scaling infrastructure. It's, 'Don't be cheap,'" Heiliger said. He added that Facebook does drive hard bargains with its hardware and software infrastructure suppliers, and is careful not to overbuy.

I remember reading about how Amazon does it. They have clusters of servers running whatever OS suits the particular person having written the portion of code being used and will blow through something like 100 dead servers a day. IIRC, when you load a page from Amazon you get content delivered by 20+ servers onto one web page.

Maybe he just needs to scale out.

Or - I just noticed an unused AS390 in the server room today. Apparently the Z890 that replaced it is also going to be replaced by a new z9 machine. He could bundle some apps on the z890 or the 390.

I wonder if you can run .net or Java under OS/390 or MVS...

Re:I wonder if he's not thinking about scaling eno (1)

BBCWatcher (900486) | more than 5 years ago | (#28477317)

Facebook uses PHP, and yes you can, on both z/OS [ibm.com] and Linux. Probably on z/TPF, too. And Facebook wouldn't be the first Internet company to buy a mainframe [ibm.com] .

Re:I wonder if he's not thinking about scaling eno (1)

dirtyhippie (259852) | more than 5 years ago | (#28477441)

Java? Yes, absolutely. Not sure about .net tho.

Re:I wonder if he's not thinking about scaling eno (0)

Anonymous Coward | more than 5 years ago | (#28477457)

I wonder if you can run .net or Java under OS/390 or MVS...

Yes, actually, though we've been calling it z/OS for about 10 years now, and it's an hybrid mix of MVS and Unix.
Java definitely. Not sure if there's a .NET engine yet - might need to run Linux for z-Series in an LPAR or under z/VM to get a .NET framework

Sounds like a bunch of excuses to me (4, Insightful)

stox (131684) | more than 5 years ago | (#28477115)

Assuming that a solution was properly engineered, this should not have been a surprise.

Cheap. power efficient, performance. Pick two.

Re:Sounds like a bunch of excuses to me (0)

Anonymous Coward | more than 5 years ago | (#28477665)

You don't have to pick two. It is perfectly possible to change the way you look at the problem and arrive at something which is cheaper, more power efficient and is faster.

Google designed their own server systems. The fact they rolled their own resulted in it being cheaper. The fact they distributed the UPS meant it was more efficient, and they didn't sacrifice anything in CPU to get it.

This "pick two" meme is BS, and has been since it came out. It's only "pick two" if you assume you can't change the rules.

A Familiar Tune from Facebook (3, Interesting)

1sockchuck (826398) | more than 5 years ago | (#28477189)

This is becoming an annual event for Heiliger, who also complained about server vendors [datacenterknowledge.com] at GigaOm's Structure 08 conference last year. Facebook used to buy a lot of cloud-optimized gear from Rackable/SGI, but no longer appears on the list of their largest customers. Makes you wonder if they're not going to follow Google's lead and build their own servers.

Having a Bad Day? (1)

FranTaylor (164577) | more than 5 years ago | (#28477245)

He woke up on the wrong side of the bed, and then he had to sign the check for the electric bill.

He's just grumpy.

Rub a lamp, Heiliger (4, Insightful)

SeaFox (739806) | more than 5 years ago | (#28477305)

'You guys don't get it,' Heiliger said. 'To build servers for companies like Facebook, and Amazon, and other people who are operating fairly homogeneous applications, the servers have to be cheap, and they have to be super power-efficient.'

NEWSFLASH! Customer are tightwads.

Performance/Reliability/Price.

Pick any two, Heiliger.

The Technical VP of Facebook????? (1)

Schnoogs (1087081) | more than 5 years ago | (#28477383)

Let me file his opinion with my next door neighbor the plumber.

so what about google then? (2, Insightful)

Klintus Fang (988910) | more than 5 years ago | (#28477451)

I'm bemused that he implies the problems with his servers are due to Intel and AMD no delivering with their chips, yet at the same time he admires google for how good a job they do in building out their machines.

he must be aware that google uses Intel and AMD chips.

his reasoning just doesn't square.

And yet... (5, Interesting)

Junta (36770) | more than 5 years ago | (#28477487)

Every major server vendor has jumped on the bandwagon of 'look how efficient we are, and 'cheap'. Three years ago, by and large the tier ones wouldn't bother designing systems without forcing even the cheap design to have parts included to facilitate purchase of redundant add-ons (i.e. power distribution cards designed for dual power supplies regardless of one being bought or not). They would always put a high end storage controller on the planar. They would always make their 'entry' platform be burdened with expensive components to make it easier to option it up.

Now, we have tons of 'internet scale', or 'cloud', or whatever buzzword you feel like. They tend to stress energy efficiency, low cost components, with sales and management strategies targeted at thousands of servers (i.e. IBM iDataplex, HP SL6000). Basically, precisely what he prescribes, though probably not as 'cheap' as he wants. The incentive he gives is that the vendors should have zero margin, which is not particularly compelling for companies to work toward. Google's situation works because they brought it in-house and thus have fewer middle-men. Honestly, from all the rumours I hear, it's the logical thing to do when your server consumption is larger than some respectable computer companies' entire production. If he thinks the volume of servers is high enough to pull a google, by all means do it. Otherwise, be prepared for people not jump at the chance to give their designs to him at zero margin.

Of course, if he is calling them out on performance per-watt by avoiding non-x86 solutions, including ARM, that might be a fair criticism. However, I think company forays into 'exotic' architectures have not panned out in the market recently. Sun's niagra, despite all the worthy praise, couldn't attract a mass-market required to subsidize it for those who benefited most from it. Last year, IBM seemed to be saying Cell architecture would light the world on fire, but have been a lot quieter about it now. The message their buisness leaders have probably taken in is that while these things have their target market, that market isn't worth the expense of developing products that are refused by the larger market and focus instead on leveraging commonly accepted building blocks to do as best they can for that niche, even if it means skipping the 'perfect' solution. Sure, IBM still sells plenty of POWER, but I haven't heard that be *particularly* praised on the performance/watt category like I hear a lot for Niagra, Cell, and ARM. And if not for POWER's legacy, it probably would be still born in the market today. The PA-RISC->Itanium decision for HP probably sank their HP-UX product line faster than banking on legacy of PA-RISC installs, and it seems IBM won't make that mistake, but at the same time I don't hear much about *new* POWER customers.

Strange... (4, Informative)

spire3661 (1038968) | more than 5 years ago | (#28477581)

Since when do we listen to manufacturer's claims? You take the new hardware, stress test it with your custom software, record results, plan servers accordingly. How hard is it really to commission a server design that meets your needs and then QA some prototypes?

co34 (-1, Redundant)

Anonymous Coward | more than 5 years ago | (#28477699)

From a techn1cal
Load More Comments
Slashdot Account

Need an Account?

Forgot your password?

Don't worry, we never post anything without your permission.

Submission Text Formatting Tips

We support a small subset of HTML, namely these tags:

  • b
  • i
  • p
  • br
  • a
  • ol
  • ul
  • li
  • dl
  • dt
  • dd
  • em
  • strong
  • tt
  • blockquote
  • div
  • quote
  • ecode

"ecode" can be used for code snippets, for example:

<ecode>    while(1) { do_something(); } </ecode>
Create a Slashdot Account

Loading...