It must suck to be a Windows developer. So you already have an entire legion of misguided folk hating your work for no reason (on top of the people hating your work for legitimate reasons), and then a company comes along spreading clear misinformation about Windows’ memory usage, based on that company’s performance monitoring software. To make matters worse, when said company is called out on its errors, it decides to publish the usage information of an Ars Technica editor’s computer. As such, it is advisable to uninstall the software in question.
Craig Barth is the CTO of Devil Mountain Software, which is a company making performance monitoring software for Windows. Users can opt to share this information with the company so they can gather data on what’s going on with users’ Windows machines. Barth published a blog post a few days ago, in which it was claimed that “8 in 10 Windows 7 systems monitored by the exo.performance.network are running alarmingly low on physical memory”.
When I stumbled upon this news via another site (can’t recall which, it was two days ago), I thought to myself that either these guys have uncovered a massive bug in Windows 7 that no one else has yet encountered, or they are just reading the “free” memory statistic in Windows 7 and be done with it.
Both options seemed highly unlikely to me; Windows 7 has been out for ages, and if some random company can uncover such a massive problem through 3rd party software, than Microsoft most certainly would’ve uncovered it using their far more sophisticated and more detailed analytics info you can opt-in to send to Redmond. Option 2 seemed even more unlikely; you’d have to be hilariously ignorant to base memory consumption figures in Windows on the “free memory” statistic.
Just in case we have newcomers here at OSNews, or people unfamiliar with Windows: Windows has something called SuperFetch, a technology that learns what programs you use and when you use them, and then uses that information to pre-load them into memory so that they launch faster. The more you use your computer, the faster your programs will load up – that is, if you don’t load it with other crap overtime like spyware or whatever.
SuperFetch can indeed speed up booting your computer and launching applications as several benchmarks have proven, but a consequence of this is that you simply cannot rely on the “free” memory statistic – in fact, you should add up “cached” and “free”, because there is no penalty for using cached memory; it frees up instantly when called upon, as if it were free memory. That’s why, in Windows 7, Microsoft has changed the value from “cached” to “available”. Technically less accurate than “cached”, but I can understand why they went for “available”.
It’s mostly a philosophical debate though: should a computer cache as much stuff as possible, or leave your RAM sticks entirely void of any data?
In any case, SuperFetch is pretty basic Windows stuff, and you’d think someone called CTO would know this – especially if you’re the CTO of a company making performance monitoring software. Apparently, to my sincere astonishment, he didn’t, causing the confusion cited earlier.
And now the fun begins: Ars Technica’s Peter Bright decided to test the software in question, and he indeed confirmed what many already suspected: they simply don’t account for caching, leading to the crazy figures. In response to Bright’s thorough debunking, the company decided to – get this – publish the usage information of Peter Bright’s computer. Yes, you’re reading that right.
“I presume the company reserves the right to do whatever it likes with the data it collects. I didn’t bother reading the EULA,” Bright writes in the Ars comment section, “I do agree that it was a little surprising, but I can’t say I care.”
Barth’s “rebuttal” further confirms that he seems to thoroughly misunderstand the issue at hand. He’s claiming the company’s software looks at a variety of metrics to come to its conclusions, but none of these metrics take caching into account. The Committed Bytes metric, for instance, is the amount of bytes in memory with stuff in it – whether those bytes are cached (and thus, available) or not is of no concern to this metric.
So, let me give all of you a piece of advice. If you’re running Windows, please check your installed programs list for the XPnet performance monitoring tool. If you have it, you run the risk of having your usage data publicised on the web, linked to your personal data such as your name. As such, it is strongly advisable to uninstall this tool, and stay the heck away from any software related to it.
Eh, all this controversy really does is give them lots of free clicks and a pagerank boost.
My thoughts exactly. Had there really been this big an issue with memory leaks we would have seen it back in the beta days. I for one have yet to see my system use more than half of my 4gigs of ram and even then that was running several ram intensive apps.
I had to weigh that, obviously, but the fact that they publish their users’ information, linked with users’ real names is enough of a problem to have it mentioned here.
Then don’t link their name to their site. Link words like “bastards,” “assholes,” and the like to their site.
Um, Randall is a liar and he got fired for it … should give pause as far as his credibility:
http://www.infoworld.com/d/adventures-in-it/unfortunate-ending-357
Isn’t this the same website/metric that posted that Vista SP1 was twice as slow as XP about two years ago? It seems like they enjoy being some sort of paparazzi..
Edited 2010-02-19 21:36 UTC
Eeeekm, NASTY of them to publish an individual’s information! Foo foo foo. As if their blatant lack of understanding of the Windows memory system wasn’t bad enough already.
The slashdot article has a bunch of decent comments (wow, that’s gotta be a first
) – http://tech.slashdot.org/story/10/02/18/0429258/86-of-Windows-7-PCs…
Total Scum Company.
Probably started by a trust funder.
I don’t care about superfetch, nor i care about FUD.. all i care is that i have to reboot my computer Windows 7 4Gb computer every 2 days bc if i don’t do it.. its barely usable and its bc windows is using all my memory and all i hear is my hd working like a donkey (swapping memory i presume).
How do you know it is the fault of the OS and not something you have installed? What have you looked at so far?
Edited 2010-02-20 00:31 UTC
Lol my first experience with windows7 was that its keep coming out of sleep mode. It turned out that the ethernet card wake it up, no idea why would that happen without wol but after I turned the function off the machine is still coming back from sleep mode for 5sec then turns off at the middle of the night, great os
It has a bunch of useless shit service like superfetch ,network location determinator* just turn them the hell off and your mem wont disapper randomly. My box uses 20% of 8gb.
You’ve got to be kidding me. I think you need to really look into what is eating your RAM. You have big issues, and it’s not from Windows 7.
My 4gb computer is in and out of sleep with matlab and stuff, and have been for weeks, without any hint of a slowdown. Windows 7 is not what’s causing this for you.
Guys, guys, this dude is clearly a troll… Registered today, only one comment. Mod down, and be done with it
.
nah, i’m a usual read of osnews but never had the need to register and disagree on a news before..
and is not something that i installed because i did check that, i once reinstalled windows and only installing 2 driver(ethernet and vidcard) + firefox + EDA soft i work with.
So, the only thing i can think of is that the ethernet or nvidia driver has some memory leak that is eating my memory but if not, i blame windows 7.
Thanks for the laugh, Thom.
This article brightened my night, I had to go and read the exo.blog responses, hilarious!
And it was thoroughly debunked. Takes a lot of hutzpa (sp) for someone to report the exact same FUD about 7.
Not if it’s true (and I’m not saying that it is).
Thank you for playing.
What I find more enlightening is this post from a user called warrens on Arstechnica link:
When you take into account the fact that Randall Kennedy and his cohorts have been wrong so many times – why the hell would anyone take what he says seriously? he has all the credibility of the mad man standing on the corner screaming, ‘the end of the world is near! repent! repent!’. It would be linking to an article by Dvorak and expecting a deep thinking article.
Edited 2010-02-20 03:30 UTC
Cosmologically speaking, the end of the world IS near. Let’s say the Sun lasts another 10 billion years before it toasts the Earth, possibly sucking it in by creating friction with its outer atmosphere and slowing the Earth’s orbit until the Earth spirals in to its death… the entire UNIVERSE in most scenarios will last many many many more billions of years before going dark or what-have-you. So… in terms of the lifespan of the Earth, it is true: the end of the world is near.
Well to be honest, *if* you were using a PCI video card, *or* you were using Linux with an X Windows driver without acceleration, like the “nv” driver, then running a lower resolution and bit depth does help performance.
Superfetch is interesting. I know that have throttled it for Win7 so it can work better with netbooks.
But I actually preferred how it worked in Vista since I have at least 3GB RAM.
Does anyone know if Superfetch can be adjusted to work like in Vista?
No, but generally Superfetch in Win7 is more effective than it was in Vista, despite the fact that it may prefetch less data in some scenarios:
http://blogs.technet.com/markrussinovich/archive/2008/07/21/3092070…
I think the story here has nothing to do with technology as much as pure incompetence on the part of people running this business, and how they are able to still be a business. How? How do some of these manage to even keep their jobs at a time when there is an abundance of highly skilled people already out of work. I imagine quite a few are scratching their heads wondering why they can’t find employment, but idiots like this are working as CIO?
Why would anyone even consider using this software in the first place is beyond me, especially now.I think this probably is some trust fund created business run by someone who probably thinks turning off their monitor is the same as shutting down their PC.
If you run a business, you can choose who gets to work there. I guess the question is why they are still in business given the caliber of their employees.
The source of their confusion is this:
It is common knowledge that this counter (Memory\Committed Bytes), more than any other, provides the most accurate picture of physical memory use under Windows
Actually, committed bytes is one of the worst possible metrics for physical memory usage. You can have a system that is completely out of physical memory, yet has plenty of available commit, and vice versa. As other people mentioned, Available Memory is a much better counter to use when you are interested in physical memory usage.
By the way, Tom’s version of what Committed Bytes are is also not quite correct:
The Committed Bytes metric, for instance, is the amount of bytes in memory with stuff in it
Initially, when a page of virtual memory is committed there is no “stuff” in it. Physical storage for the page will be allocated only when it is accessed for the first time. Until then the page doesn’t really exist anywhere – all you did by committing it is essentially tell the memory manager “I may decide to write some data to this page later; please make sure you’ll have enough RAM or pagefile space to store this data in case I actually decide to write it.”
This may seem like nitpicking but it’s important to understand that when you see for example 1 GB of commit charge in task manager it doesn’t mean there’s 1 GB of stuff sitting in the RAM and/or pagefile. It means that if every committed page in the system was written to, you’d have 1 GB of data that would have to be backed by either physical memory or the pagefile.
Thanks for the clarification; that’s indeed an important aspect (and certainly not nitpicking as you think
).
BTW, I want to point out the MS-induced trend of using “\” instead of “/” in English prose. I suppose I can suck it up and deal with the fact that they use “\” as a path separator (still irks me, but I’ll deal). But I can’t abide by people who now think that a “\” is really just another way of writing “/”. It’s not. It’s wrong and it’s gotta stop.
The backslash in “Memory\Committed Bytes” is in fact a path separator. It’s part of the naming convention for performance counters in Windows:
C:\> typeperf /q Memory
…
\Memory\Committed Bytes
Ahh. Okay, that’s acceptable, I suppose. I have, however, seen it used in non-path situations, and that is quite annoying.
asshole bastards exo performance network blog xpnet http://www.xpnet.com
lol!
We’ve posted a number of blog entries rebutting the various arguments against our findings. Please visit our blog site for more information.
<a href=”http://exo-blog.blogspot.com“>exo-blog.blogspot.com
I am pissed off that MS is forcing me to reinstall perfectly working Win7 RC which has absolutely nothing wrong. It has been rock solid platform for almost a year already (install date 9. May 2009) and if MS would not make my computer to reboot every 2 hours starting from the 1st March 2010, then I would happily continue using that nice RC. Unfortunately have to go and get legit copy, I guess.
Edited 2010-02-21 11:54 UTC
You were specifically warned this would happen when downloading/installing the RC, why are you complaining?
Did you seriously expect a change of heart from MS and for them to suddenly start giving away a 200$ OS package for free? Why?
Wow, you’re pissed off that Microsoft isn’t going to give you Windows 7 for free? You’ve certainly got a strong sense of entitlement don’t you?
I am pissed off, that I am _forced_ to reinstall perfectly working system. I understand, that RC is not upgradeable, but the fact, that I am not allowed to use good operating system for ever, pisses me off. Well I got it for free but then again it is not RTM, and I am happy with it.
So basically this is the first time I have to reinstall windows against my will
Havn’t happend so before. Always had to reinstall because there were problems, but now I dont have any and still need to reinstall. Most recent legit windows I have, is Vista, should I go back… Vista works most of the time..
Who, precisely, are you pissed off at? Microsoft, for enforcing the terms of the free preview they gave you? Or yourself, for mistaking it for something other than a time-limited preview? Because you must have known when you installed it that this was going to happen…
What is he, 14 years old? What a tool. Buy the software if you want to use it.
Edited 2010-02-22 15:46 UTC
Well, they could have at least made it to where you could register the trial version with a real license, so you just don’t have to do the reinstall.
It isn’t a “trial version.” It was a pre-release beta/RC build. The pre-release terms were quite clear.
Nobody would want to run a pre-release build anyway. Not only is it incomplete and *known* to contain bugs, but it isn’t subject to support, security updates, or even driver/application support.
1) It’s very refreshing to see people DEFENDING Windows for a change. Usually when this type of **** hits the *nix freetards come pouring out of the woodwork. Funny though because this is the same thing that happened when Vista was introduced; Many linux users went “well it’s about time they caught up on the idea of using available memory for caching”
2) I wonder how these ignorant dipshits at Devil Mountain would react to your average *nix server… Like say, my Debian one.
top – 08:44:10 up 269 days, 21:40, 1 user, load average: 0.20, 0.52, 0.59
Tasks: 111 total, 2 running, 109 sleeping, 0 stopped, 0 zombie
Cpu(s): 12.3%us, 0.2%sy, 0.0%ni, 85.9%id, 1.7%wa, 0.0%hi, 0.0%si, 0.0%st
Mem: 1996448k total, 1728400k used, 268048k free, 111808k buffers
Swap: 5847620k total, 6740k used, 5840880k free, 1121320k cached
Oh noes, it only has 268 megs of it’s 2 gigs free… Oh wait, 90% of that memory use is PHP (APC) and mySQL cache…
Just goes to prove you don’t have to know the first thing about Operating Systems to slap together some script kiddy metrics tracking crapplet in visual basic, then market it to the type of people who think you can get serious technical advice in Forbes magazine.
These guys and their software are only one step removed from the bastards who make those fake anti-virus popups, ranking right up there with the ‘registry cleaners’ the majority of which usually do more harm than good. (there are what, two legitimate ones and the rest are malware?)
Yeah, my machine’s the same. Just 70Mb listed as free, out of 8Gb total – about half of that memory use is cache…
This topic has almost nothing to do with Free Software. There are only two points in common that I can even remotely see.
The first point is that there is a Linux utility that will do the same task as SuperFetch, with the same benefits and consequences of running it.
http://en.wikipedia.org/wiki/Preload_%28software%29
So Linux/FOSS software is actually LIKE Windows (or at least Superfetch in Windows) in this respect. Exactly the same observation of performance gains, and the same misguided criticism, could be made of Linux/preload as is being made of Windows/Superfetch. The only real difference is that preload is not normally part of the default installation.
The second point of commonality is right up your street, deathshadow. You are a prime example of a practitioner of this practice … that practice being mentioned at the start of Thom’s second sentence in the introduction:
Happens quite a lot. There is no shortage of misguided folk about.
Other than these two points, there is no involvement of Linux/FOSS in this topic at all.
Edited 2010-02-22 00:49 UTC
According to Slashdot, this incident wasn’t a case of being misguided, but rather a case of fraud.
http://news.slashdot.org/story/10/02/21/2329249/Windows-7-Memory-Us…
http://infoworld.com/d/adventures-in-it/unfortunate-ending-357
SuperFetch is not there to speed up the booting of your computer. Logically, it can’t because it is there to load things from disk into memory, which is slow. The reason why it does it is to make subsequent loading of system and application files faster, so the longer you run it the faster things will be – in theory anyway.
However, the benefits of potentially loading a lot of application files into (and out of, since you don’t have as much memory as you do disk space) cache dynamically is rather debatable. The disk eventually becomes the bottleneck whatever you do.
It turns out Devil Mountain’s CTO Barth was actually a psuedonym for Infoworld’s Randall C. Kennedy, who’s been fired as a consequence of this revelation. Details here:
http://blogs.zdnet.com/BTL/?p=31024
I loved following this as it is a train wreck in the making. Something I have long despised is brought out into the open, that is the complete lack of journalists in the tech industry, an industry filled with hacks, morons, shills, and other miscellaneous twits. Why, it is just one step behind sports journalism.
Anyone here remember the controversy that has popped up several times now with game developers vs. game review sites? Better give that game a good review or they pull their ads.
It will be a very long time before any of these journalistic endeavors come even close to winning a Pulitzer so to speak. As it appears now, Infoworld was fully aware of Kennedy’s outside adventure. Infoworld should have disclosed this completely, yet they did not and thus have absolutely zero credibility as a magazine. How could you trust anything written by anyone there?
p.s. My Windows 7 media machine reports 0 free memory…should I buy more now? I wonder who Randall C. Kennedy would advise me to buy memory from…a company he owns stock in I bet.
Sadly, most sports journalists are probably better writers. Makes me long for the days of BYTE Magazine.