A Look At Microsoft's 'Mini Internet' For Testing IE 241
MrSeb writes "With the grandiose bluster that only an aging juggernaut can pull off, Microsoft has detailed the Internet Explorer Performance Lab and its extraordinary efforts to ensure IE9 is competitive and IE10 is the fastest browser in the world. Here are a few bullet points: 128 test computers, 20,000 tests per day, over 850 metrics analyzed, 480GB of runtime data per day, and a granularity of just 100 nanoseconds. The data is reported to 11 server-class (16-core, 16GB of RAM) computers, and the data is stored on a 24-core, 64GB SQL server. The 'mini internet' has content servers, DNS servers, and network emulators (to model various different latencies, throughputs, packet loss)."
Could use the real internet eh! (Score:4, Interesting)
Why not just use the real internet?
Re:Could use the real internet eh! (Score:5, Informative)
They wanted to account for any kind of lag, so by having it all in house and disconnected from even their internal network, they have control over all variables so everything is equal.
They did this post on their blog yesterday http://blogs.msdn.com/b/b8/ [msdn.com]
Re:Could use the real internet eh! (Score:4, Interesting)
They wanted to account for any kind of lag, so by having it all in house and disconnected from even their internal network, they have control over all variables so everything is equal.
They did this post on their blog yesterday http://blogs.msdn.com/b/b8/ [msdn.com]
They care about it so they created a genuine imitation of the real thing.
Honestly, I'd go at some of the pages I have to each day, which are ludicrous in their use of content and scripting - web developers just pick up and drop widgets all over the place, never a look toward what impact it has on the page being interpreted or used on the receiving end. I know I've got a bad one when I hear the processor fan kick in for a stinkin' web page!!!
Re:Could use the real internet eh! (Score:4, Informative)
they never do say what kind of sites, just that they are sanitized and are real world web pages... but if you are comparing IE to itself or Chrome or FF, whatever site you use should be similar in speeds, except for ones that detect clients and do different things...
"Content servers are web servers that stand in for the millions of web hosts on the Internet. Each content server hosts real world web pages that have been captured locally. The captured pages go through a process we refer to as sanitization, where we tweak portions of the web content to ensure reproducible determinism. For example, JavaScript Date functions or Math.Random() calls will be replaced with a static value. Additionally, the dynamic URLs created by ad frameworks are locked to the URL that was first used by the framework.
After sanitization, content is served similarly to static content through an ISAPI filter that maps a hash of the URL to the content, allowing instantaneous lookup. Each web server is a 16-core machine with 16GB of RAM to minimize variability and ensure that content is in memory (no disk access required).
Content servers can also host dynamic web apps like Outlook Web Access or Office Web Apps. In these cases, the application server and any multi-tier dependencies are hosted on dedicated servers in the lab, just like real world environments."
Re: (Score:2)
Re: (Score:2)
Re: (Score:2)
Re: (Score:2)
Catch-22 if IE10 loads those pages faster than anyone else:
Microsoft will be ridiculed for finishing the task too quickly.
Re: (Score:2)
Re:Could use the real internet eh! (Score:5, Insightful)
Rule #2 of IT that should never be broken [earthlink.net]: Never let a web designer design your web page.
Giving free reign to a web designer to design a web site is like giving a two year-old a Faberge egg.
Re:Could use the real internet eh! (Score:5, Insightful)
Re:Could use the real internet eh! (Score:5, Insightful)
You have to figure out what the variables that you have problems with in real world usage, before you can start optimising your product to account for them.
There has to be iterative cycles of real world, then fake internet testing to really make it work well.
It would also help if you were able to test your competition alogn the same lines.
I additionally wonder if they are accouting for all of the different behavious of all of the various webservers out there. If they are only testing agianst iis, well, that's not very good.
Re: (Score:2)
Re: (Score:3)
Well duh ! That is one the major reason you create that kind of lab in the first place: you found something in the real world then you craft a similar scenario in the lab and make that part of either your test case, or benchmark. Obviously part of the crafting the scenario is to make sure that it behaves the same as in the real world. Other uses include debugging, analysis of edge cases (i.e. stuff difficult to find the real world, or stuff that does not yet exist)
Considering the renewed competition on t
Re:Could use the real internet eh! (Score:4, Insightful)
Probably an evolving tick-tock setup between real and test.
Step1. Performance Test App against real world
Step2. Document Real world issues
Step3. Create test environment to run your issue cases against
Step4. Optimize app against test environment
Step5. Goto Step1, adding any new cases
Steps 1 and 2 can happen independent of 3 and 4. Step5 is just to make the logic seem serial.
Re: (Score:2, Insightful)
they don't want all those fancy test clients to be picking up the latest in drive-by syphilis; even microsoft knows better than to go on the real internet with explorer.
Re:Could use the real internet eh! (Score:4, Insightful)
Re:Could use the real internet eh! (Score:5, Funny)
Yes, there must be some conspiracy! Microsoft couldn't possibly want to make a good browser! They must have ulterior motives!
Re:Could use the real internet eh! (Score:5, Insightful)
So, what's going to make anyone use a Microsoft browser? They've been losing market share for ages because their browsers suck. How do they get people back? Make a good browser. Your argument might mean something if Microsoft sold IE as a standalone product, but they don't. It costs nothing (in terms of cash coming straight out of your pocket) to switch browsers, and users are notoriously not fond of switching. Since you can't count on your competitors' products to be lousy, you can only compete by making yours better. The browser market is about as Darwinistic as a software market could be.
Re: (Score:2)
IE 9 is actually not bad.I am surprised how well they did it!
Re: (Score:2)
That's what I hear, but there's also what I said about people not liking to switch. :)
I'll stick with Chrome until I hear something is much, much better, or Chrome gets much, much worse. Same thing happened when I originally used Netscape (turned to shit around version 4.5), then IE (turned to shit around version 6), then Firefox (I forget when it went to hell, but then I jumped to Chrome.)
Re: (Score:2)
Indeed. I've used it (briefly) but just didn't care for it over and above Chrome. I do, however, use Opera Mini on my Android phone.
Re: (Score:2)
As noted in other posts, Microsoft wouldn't be able to predict the behavior of the general Internet, and therefore not have repeatable results. The results only need to be repeatable by Microsoft for their own testing. It's not like they are trying to prove a scientific theory here, they're trying to improve a product through aggregate testing and quantitative measurements. Hard to make good quantitative measurements when there are variables you can't easily account for, hence their own private, custom-desi
Re: (Score:2)
Re: (Score:3)
And still... (Score:4, Insightful)
Re:And still... (Score:5, Funny)
The only thing Firefox does fast anymore is update.
Re: (Score:3)
Oh snap!
Yeah, that's why I ditched Firefox years ago for Chrome. Got sick of FF freezing/crashing all the time, as well as its performance just getting worse and worse over time.
Re: (Score:2)
And Chrome has built in sycning of *everything*. An natively supports Greasemonkey scripts without an extension. And auto-updates in a cleaner fashion than Firefox. And is blazing fast at rendering.
Re: (Score:3)
All true. Although I have a friend who uses Opera, and she was aghast at the way Chrome renders a white screen before it starts rendering the full page. She said under Opera, the full page just shows up all at once with no weird white screen first. I'm not sure but I think Opera's renderer might be a little faster than Chrome's.
Re: (Score:2)
Funny, I'm aghast at requiring everything to be downloaded and rendered before it's displayed. That gives the illusion of nothing being done, and subtly irks me.
Re: (Score:2)
I feel the same way, myself. I'd rather the browser render whatever it has available at that moment rather than wait for the whole page (unless it has to because the page is compressed or something.)
Re:And still... (Score:4, Insightful)
Firefox hasn't become any slower. What's happened is that everything else become so much faster. There used to be a "pregnant pause" when entering a domain, I remember when 30 seconds to load a page was the norm, over 56k.
Now, I expect the results from a google search to appear as I type, interactively. This isn't just an improvement, it's a whole 'nother animal at that level of performance.
Firefox isn't slow at all. (Score:5, Insightful)
While slashdot mocks the computer industry marketing for describing computers using a single metric, you seem to be quite happy with that when it comes to browser performance.
An example: Chrome (v8 engine) has this reputation for amazing speed, but IE9 absolutely grinds Chrome into the dust when it comes to simply repositioning elements on screen; something which today's web apps spend a lot of their time doing. You can feel it too if you know what you're looking for. I don't follow IEs development as closely as Chrome or Firefox, but IE must be hardware accelerating these translations.
I fully expect Google to focus on performance cases which help their specific apps. Again, a conflict of interest, akin to Microsoft pre-caching masses of junk, so that Office can appear to start up much faster than the competition.
Re: (Score:3)
so that Office can appear to start up much faster than the competition
Ah yes, "the competition"... hmm, who exactly is that these days? Yeah, please don't say Libre/OpenOffice.
I'm not at all saying MSOffice is good, because in a lot of ways it's terrible, but honestly thinking there is real competition now is a bit outrageous.
Re: (Score:2)
Still can't print with the latest issue of Open Office on OSX. Forums online tell us its a feature, or a bad driver (not using a driver all other apps print flawlessly) but definitely not a bug.
I guess the feature they are referring to is you can export to PDF and print.
Re:And still... (Score:5, Insightful)
And when all we care about is the fastest browser - in nanoseconds! - will we begin to forget the truly important criteria for choosing a browser?
Or better still, by the time IE is on par with Chrome the actual browser will be irrelevant because mobile platforms - in which IE has little share - will do to traditional computers what Cromagnons did to Neanderthals. The next generation will use integrated devices, unaware they were using a browser, and with little or no need for even a choice.
Re: (Score:3)
The next generation will use integrated devices, unaware they were using a browser, and with little or no need for even a choice.
And little or no understanding of how it works or how to use it as anything other than yet another few-to-many information channel they can listen to or watch, but can't talk back to in any real sense. And you're right that that's the direction it's going, but some of us aren't thrilled about that..
Re: (Score:2)
Milliseconds, (maybe not so much nanoseconds) DO matter inside an animation loop.
Oh, unless you were happy with Flash?
Re: (Score:2)
last words (Score:2)
"As you can see, my young apprentice, your friends have failed. Now witness the firepower of this fully ARMED and OPERATIONAL battle station! "
not a true real-world test (Score:2, Informative)
until they add some zombied computers and malware control servers.
oh, wait.. these are windows test systems. never mind. some kind soul probably already added them
But will it run Linux? (Score:5, Interesting)
I couldn't resist. But with all the work and effort and resources going into this, how is it that operations a tiny fraction of this can generate fast, reliable and standards complaint browsers better than MSIE?
Microsoft, the problem isn't that you're not spending enough money. It's that you're not doing it right.
Re:But will it run Linux? (Score:4, Insightful)
I couldn't resist. But with all the work and effort and resources going into this, how is it that operations a tiny fraction of this can generate fast, reliable and standards complaint browsers better than MSIE?
Microsoft, the problem isn't that you're not spending enough money. It's that you're not doing it right.
I'm not familiar with IE 8 and 9, but in the past the issue was many years and revisions of code reuse and accumulation of cruft, an insane amount of backwards compatibility and some poor initial design choices combined to make each new version bigger, slower and buggier. I imagine this combines to make developing and especially testing any new release a massive undertaking.
To be fair, I would argue that Firefox is starting that downward spiral now. Each new version is slower and has a bigger footprint. Personally, I've switched to Chrome, but when Chrome inevitably starts lagging, I'll be on the lookout for the next completely new browser. Not merely because it's new, but because it's less likely to have years of bad decisions weighing it down.
The problem in Microsoft's case is that they seem incapable of dumping what they have and doing a complete rewrite. There may be marketing reasons for this, granted, but if they made a clean break it'd be better for them in the long run.
Re: (Score:3)
It's really tempting to think that way, but actually doing a clean re-write is usually a complete mistake. I'd say Mac OSX is one of the only successfull examples of this (and that largely because their previous versions were so horribly outdated it was unbelievable).
Joel has a great article on this from a while back:
http://www.joelonsoftware.com/articles/fog0000000069.html [joelonsoftware.com]
Re: (Score:2)
Right, but back in 2000, I don't think we had the appreciation of accumulated browser cruft that we have today.
I'd argue that Internet Explorer has fallen into the class of "so horribly outdated it's unbelieveable".
Re: (Score:2)
Well, yes. The whole internet thing was still on the steep end of the curve back then.
Re: (Score:2)
Well, also, that was eleven years ago...
Re: (Score:3)
To be fair, I would argue that Firefox is starting that downward spiral now. Each new version is slower and has a bigger footprint.
As opposed to Chrome, which (on my machine, at least) has an even larger footprint?
Re: (Score:2)
I think the difference is that Chrome spawns separate processes instead of one big-ol-thang like Firefox. My computers seem to like multiple relatively large processes more than one gigantic process, even if the sum of the parts is greater than the whole.
I switched to Chrome too! (Score:2)
Re: (Score:2)
"Vastly different" is not the same as "a complete rewrite". If it's like the ribbon in MS Office, being vastly different could actually be a disadvantage.
Re: (Score:2)
Re: (Score:2)
0.0000000000001 is infinitely more than zero. big whoop.
Re: (Score:2)
Good point. Microsoft's worst enemy is their former selves.
Re: (Score:2, Interesting)
yes
http://bellard.org/jslinux/
Re: (Score:2)
But with all the work and effort and resources going into this, how is it that operations a tiny fraction of this can generate fast, reliable and standards complaint browsers better than MSIE?
And with more features, too!
It's 2012 and IE9 still doesn't have a built-in spellchecker for text areas! Among many other must-have features that are suspiciously absent.
Re: (Score:3, Interesting)
It's 2012 and IE9 still doesn't have a built-in spellchecker for text areas!
If IE had a spell checker you'd call it bloat. When it's still 2012 and browsers running on Windows 8 won't need to worry about it because it'll be built into the OS, would that relieve your frustration?
Re: (Score:2)
What will be built into the OS? IE or a spellchecker?
The spellchecker.
Re: (Score:2)
Re: (Score:2)
To be fair, IE10 includes spell checking (and auto correct), though only preview versions have been released. The final version of IE9 was released in March of last year. I'm curious, what other "must-have features" are absent from IE10 (or IE9, for that matter)?
I'm used to people disliking IE for how it was years ago and not giving it a fair chance today--and of course Microsoft hate is popular here (TFS opens with the "grandiose bluster" of an "aging juggernaut"--thanks so much for excellent and fair repo
Try it on Slashdot (Score:2)
These massive pages are a real benchmark for any browser. Or Google .. they seem to be logging every page I go to now. Or eBay with all that horrible bloat. Or Facebook, which is seriously clunky with to many competing scripts. ...
If it's their own little internet they should be using some of the most bloated, unresponsive web sites on the internet to test on. I don't think when IE10 comes out I'll be surfing their own tiny little internet.
Re: (Score:2)
Ring, ring (Score:2)
Congrats (Score:2)
HHGttG (Score:4, Funny)
TFA Forgot (Score:2)
What could possibly go wrong? (Score:2)
All that power... (Score:2)
...and they still can't see why users hate their software.
Mini Internet? (Score:4, Funny)
If it's a mini-Internet (Score:2)
Then technically 40% of its traffic is pure Pr0n.
Re: (Score:2)
Now we know ... (Score:2)
... why we need IPv6. ;-)
Is this mini Internet IPv6? (Score:2)
One thing I'm wondering - given how in Windows 7 and beyond, MS seems to be making IPv6 the default home networking protocol, any idea whether this mini internet they are experimenting w/ is an IPv6 internet, or an IPv4 intranet (likely w/ private addresses?)
Seems to me that that's what they should be doing. That way, they don't have to duplicate their efforts later to verify IPv6 compatibility.
How many ... (Score:2)
Bad Code Metric? (Score:2)
I am all for this testing, but in practice I think it will lack one very important metric that Microsoft can not measure. How well IE10 works with a site riddled with poorly written code.
Re: (Score:2)
oh don't worry, they use pages captured from the web after all.
my worry is, will they also test it against the standards? you know, like they should be doing :O
and personally, I'd rather have browsers that support the standards and that's it, than browser vendors having to maintain (and browsers having to contain) huge amounts of special case code, which in turn prolongs sloppy website authorship. I know very well it won't happen, but I would love to have such a browser. you know, a hardcore strict edition
1/10,000 of a millisecond (Score:5, Funny)
Re:Granularity of 100 nanoseconds (Score:5, Funny)
Granularity of 100 nanoseconds: What does that mean?
That's as small as they could get the bits, pounding on them with Steve's chair.
Re:Granularity of 100 nanoseconds (Score:4, Insightful)
It means the runtime data they have collected is stored in a 100ns interval.
Re:Granularity of 100 nanoseconds (Score:5, Informative)
No, it means that Windows has a 100ns granularity on it's timestamps.
http://msdn.microsoft.com/en-us/library/windows/desktop/ms724284(v=vs.85).aspx [microsoft.com]
Re:IE Crap (Score:5, Funny)
Fixed that for ya.
Re:IE Crap (Score:5, Insightful)
Correctly according to whom? Neither CSS3 nor HTML5 are completed standards and various portions remain in flux. Of the more mature bits IE9 and IE10 implement quite a bit of it and do so quite comprehensively.
MS is also one of very few organizations that is very actively involved with the W3C Test Suite by submitting test cases for each portion of the standard under various circumstances to demonstrate correct behaviors. What Google and Mozilla do instead is slap together a partial implementation and call it a day. More than once has their implementations been found to be not only incomplete but also incorrect.
Stop relying on scores given by non-authoritative tests demonstrating exceedingly limited and selective interpretations of non-standardized functionality. Oh, and HTML5 Video does NOT specify a codec, in fact it was designed to handle many simultaneous codecs, including h.264, which is explicitly referenced in the draft.
Re: (Score:3)
IE is crap, but not for that reason. IE9 is missing some very-nice-to-have bits of HTML5 just because it was released so long ago.
As for CSS3, yes it's deficient in some areas, but there is a trick to get around many of them: SVG
Unless you have to support IE8 (LOL poor you), then the users will never notice the smoke and mirrors.
With JavaScript polyfills, it's possible to take advantage of the latest and greatest in IE9 with minimal effort.
Re: (Score:3)
Well, sometimes blaming tools is an excuse, other times you have no choice but to speak up and say, this isn't a pool stick, its a baseball bat.
Re: (Score:3, Interesting)
the building windows 8 blogs are actually pretty good, as long as you know that it's going to be pumping up how cool windows 8 will be, and question what is in the cool-aid you are drinking, it's worth a read now and then. They give background information on decisions they are making and why some things are the way they are as well as where they plan to take them.
Re:Was /. been bought or what? (Score:5, Funny)
What we really need is another Bitcoin story!
Re: (Score:3)
Re: (Score:3)
I was just going to comment on the abundance of nuclear-related stories that have been running on /. of late - and I'm a nuclear supporter. I wouldn't be complaining though, just making an observation.
Why not? (Score:5, Insightful)
MSDN blogs are often very technically detailed, written by people who know this stuff from the inside, and if it's about a topic that's of general computing interest then it seems that's a good thing. And the blog in question is chock full of some really good detailed stuff about how they're doing performance testing, reasons why the lab is architected the way it is, detailed graphics on how they measure performance, how they analyze it...on and on.
Frankly, this seems more akin to old Slashdot than a lot of the nonsense we see here today. (That story the other day about a girl sent home from school because her lunch wasn't healthy, and then quickly called into question over what happened? Really? What was that topic even doing on Slashdot in the first place?) Whatever you think about Microsoft, having this extremely detailed look into how one of the world's biggest software vendors (or are they the biggest now?) goes about performance testing, and how they ensure consistent results, should be really, really interesting to anyone involved in IT.
Re: (Score:2, Offtopic)
From wikipedia:
The origins of the site now known as Slashdot date back to July 1997 when Rob "CmdrTaco" Malda started a personal website called Chips & Dips, which featured a single "rant" each day about something that interested him – typically something to do with Linux or open-source software.
(...)
On June 29, 1999, the site was sold to Linux megasite Andover.net for $1.5 million in cash and $7 million in Andover stock at the IPO price. Part of the deal was contingent upon the continued employment of Rob Malda and Jeff Bates and on "the achievement of certain milestones". With the acquisition of Slashdot, Andover.net could now advertise itself as "the leading Linux/Open Source destination on the Internet".[4][5] Andover.net eventually merged with VA Linux on February 3, 2000,[6] which changed its name to SourceForge, Inc. on May 24, 2007, and became Geeknet, Inc. on November 4, 2009.[7]
Emphasis mine.
If people really want to know more about windows, there is MSDN and other million dedicated websites already. So yeah, blame on wanting old slashdot back.
Re: (Score:3)
You're holding it wrong.
Re: (Score:3)
no no... those are what COMPILE the results...
They have a wide range of high end to low end PCs running the tests down to a 1.6ghz netbook with a Atom N270 processor.
Yea, but look at how FAST it does that! (Score:2)
By the way, does the current IE still assume a fixed width per letter when rendering buttons, so that buttons-with-very-long-texts-on-them render with extra space to the left and right?
Re: (Score:2)
Mozilla's doing it the cheap way: They let users do it.
Re: (Score:2)
Re: (Score:2)
Re: (Score:2)
Re: (Score:2)
It's also really really hard to shake the idea that microsoft really doesn't care about HTML5 or any other emerging web standards.
You mean making HTML5 a first class layout option for native Windows 8 apps isn't persuasive?
Re: (Score:2)