Slashdot Mirror
Debugging Microsoft.com
teslatug writes "Channel 9 has an interesting video interview with Chris St.Amand and Jeff Stucky who test and debug Microsoft.com. They reveal some of the big problems they used to face such as recycling processes every 5 minutes due to memory leaks and 32 bit limitations, and being unable to push more than 10 Mbits of data to their datacenters due to Windows' networking stack limitations."
WMV? You serious?
How the hell am I supposed to watch that?
The summary is missing the fact that many of their problems went away after upgrading to an early 64 bit version of Vista with its improved networking stack.
Help Brendan pay off his student loans
The next post will be about debugging slashdot.
I think the term is, "Pissing into the wind"....
week, month, lunar orbit, eon, pound ...?
Why don't they just migrate to Apache on OpenBSD? :)
Oh, right...
Perhaps... but not all of us receive the amount of traffic that they do.
Help Brendan pay off his student loans
1. mplayer
2. xine
Not that tough, really, now is it?
The secret to creativity is knowing how to hide your sources. -- Albert Einstein
call me when he's done, because he obviously is not finished yet... :P
...Until the slashdotting?
Wow, didn't see that one coming.
I suppose that, transitively, it is due to a limitation in an archaic version of the BSD stack.
"Strangers have the best candy" -Me
Hey, Microsoft has to eat their own dogfood if they want to keep some modicum of credibility no matter how bad the food tastes...
Is anybody really suprised here? What they didn't tell us is that there's a top-secret Debian redundancy server running behind it just in case all hell breaks loose. Nothing to see here, move along.
( I
Did anyone notice the desk? What kind of soda cans are those on his desk? I thought they were Hansens, but it does not look like any I have ever seen.
M
Wow.
Is that not one of the most ironic things you've ever heard? The limitations of the operating system made by the same company holding back another division? Shock and awe.
Christ, they may as well run Max OSX Server. Dolt.
Having worked on a small-ish e-commerce site in the past, recycling IIS is normal. Go ask turboTax how many windows servers they had and how often they used to recycle IIS. That's all pretty normal.
The limitations discussed in the video of the Windows TCP stack are not limited to Windows. These are limitations imposed by a to-the-spec implementation of TCP. TCP is 30+ years old, and it wasn't designed for the kinds of networks it runs on today.
The new TCP stack in Vista effectively implements TCP is such a way that it removes these limitations while preserving compatibility with old stack implementations.
Windows had PROBLEMS?! OMG. Call the Press! Shock. Horror. Oh the horror. That has never happened before!
And hey. If they gotta use unreleased technology to get acceptable quality what about people like us, ey?
I love humanity, it is people I hate
Interviewer: "Hey dude."
Chris St.Amand "What up bro"
Interviewer: "So like what happened when you worked on microsoft.com? Oh but first...Did you get all the chicks at the bars when you mentioned your job or what?"
Chris St.Amand "Oh totally. I'd just say, 'what up babe. I work on the microsoft.com web portal' and she'd degfrag my harddrive all night."
Interviewer: "Sweet. So what was your biggest hurrdle writing all that HTML? After all that's a complicated langaguage to master."
Chris St.Amand "It'd definelty have to be that F'ing page not found shit. You don't know how many times I'd go to microsoft.com after doing a big update and it'd just say four-oh something and the page just wouldn't show up. You know we tried to put up a 420 page not found but got in trouble with our boss."
Interviewer: "Yea totally! That would have been cool. Oh ummm let's see here. So what other problems did you have?"
Chris St.Amand: "Not being able to use FreeBSD to serve that shit. When I first heard I actually had to use Microsoft I was completely like, 'Not cool Bill. Not F'ing cool, Bill.'
Interviewer: "Any thing else? Like was it hard to get up every day in the morning knowing that your existence was updating microsoft.com HTML?"
Chris St.Amand: "Yea I tried sucicide a number of times. But then I discovered that I could just completely make up new HTML tags and that was a lot of fun."
Interviewer: "Make up HTML?"
Chris St.Amand: "Oh yea, we're microsoft. When I first started they told me that no other browsers exist other then that big blue F'ing E and that no other operating systems exist. And that I could do whatever I wanted to do. So I just started making up *ALL KINDS* of crazy ass HTML.
Interviewer: "Cool dude. You rock. Anything else you want to mention?"
Chris St.Amand: "Yea you know all that crazy F'ed up HTML that all of our products output? You know without indention and messed up question marks everywhere? That was me. I was all hung over the day I added that. And that's about it."
Interviewer: Thanks Chris, I'm sure you'll go down in infamancy for such a piece of F'ing shit web page and end up in some lame ass 'Don't write web pages like this' hall of fame.
Chris St.Amand: "Peace out and remeber to eat your greens not smoke 'em!"
They had those bushleague limits while their bosses were telling corporate customers to throw away Unix for their network operations. With all the inhouse advantages (money, expertise, source code) of running Microsoft's own systems. What serious enterprise defects do you think MS astroturf is covering up these days? No wonder so many corporations have switched to Linux. Not only does the OS work better, and you get the source code to fix it when it doesn't, but it isn't backed by a giant spin machine pretending it isn't a toy.
And no, TrollMods, this poll doesn't count as that: I'm not on any Linux marketing payroll, and what I say is actually true.
--
make install -not war
http://wm.microsoft.com/ms/msnse/0511/25766/micro
While I usually RTFA (unlike most slashbots) I think we can all agree that at 40 minutes maybe 1/2 a percent of
/me waits for the transcript
And yea, I saw the cans, but the bit-rate of that video is so low, I have no clue what they were. Maybe that red one on the left is a coke or dr. pepper?
[Fuck Beta]
o0t!
When did they release Vista as a stable release? What kind of ignorance is that to use a beta product in such a critical site for Microsoft.
Is windows really limited to 10mb/s due to the network implementation? Now I am really glad I convince people to use Linux, we have one server pushing 480Mbits/s or so using Lighttpd.
They should be redesigned.
That's a big problem of software made by companys:
1 - The company's cashflow is based arround selling new versions of the software
2 - They can't sell to it's customers improvements that they customers can't see
3 - There is a fixed time that can go by beetween one release and the next one
4 - Resources are limited
Because of this, a major redesign is something that won't be profitable, because only the advanced users will note the changes, but 99% of their customers won't, so the software won't sell well. Bug fixes also won't sell, because they are also unvisible to the naked eye of the majority of the userbase, and also customers expect those changes to be free.
So, some companys only can expect revenue from a given software once a year, and they have to invest into that software, a given set of limited resources over, say, 6 months, when they have to freeze the featureset so they can start debugging. Seeing which things sell, they will obviously focus their atention on: New Features, and a nicer GUI.
OTH, a project that doesn't have a company running it, can just get out lots of upgrades, when needed, and focus their time on making the software better, even if some of the changes made to the software won't be seen by most of it's users.
With software prices dropping, and Free Software proving to be a better option, the budget of software companys will be even more limited, and we won't see this situation changing anytime soon.
WTF am I doing replying to an AC at 5 A.M on a Friday night?
Love the shirt, MS loves the Montreal Canadiens. I also liked the fact they plugged firefox. Go firefox and/or Montreal Canadiens!
That reminds me one of the windows 95 presentations, when the scanner was connected by USB to the computer :D
These guys would love to use apache and squid, they know that it is the best way to do the job. But they can't ! They have to run this on shitty microsoft sofware, whatever is the cost !
They must be paid a lot to look these good
I'm pretty sure there is some firefox hidden on that computer and many debian and apple boxes hidden under the desk
It's good to hear this from inside microsft, i wonder how it got throw the censorship we could expect from this company
I which they could keep their URLs (on microsoft.com) fixed. That way links to the site won't alaways be broken. Its not that hard.
Slightly off topic, but the new Windows TCP stack will be implementing their new Compound TCP stack, aka, CTCP. More information can be read here:
a spx?type=Technical%20Report&id=940
http://research.microsoft.com/research/pubs/view.
Am I the only one who looked at the title and thought: "debug microsoft.com? Who still uses .com files any more?"
Yup, thought so. I suck.
They reveal some of the big problems they used to face such as recycling processes every 5 minutes due to memory leaks and 32 bit limitations, and being unable to push more than 10 Mbits of data to their datacenters due to Windows' networking stack limitations."
Micro$oft needs 64 bit so it can leak more memory faster and stay running. Or at least this is how I read this.
As for 10mbs, maybe they should put a Linux/BSD/UNIX cache in front of those servers like MSNBC did to get through the last olympics.
Well do you think want to give us Linux users the satisfaction of seeing Microsoft employees admitting faults in their software?
OK OK I couldn't resist.
I'll never do this again.
You're confused. Just because you can push 480Mb/s doesn't mean you're getting 480Mb/s throughput on any given connection. Suppose you had 1Gb/s on two connections seperated by 5000 miles. You really think you're going got get 1Gb/s? You think you're going to get 500Mb/s? 100Mb/s? The inherant latency delays in the protocol make it impossible to get anywhere near optimum bandwidth.
Sure, you can push 480Mb/s to 100 4.8Mb/s connections, but you're not going to push 480Mb/s to one. THAT is what they're talking about.
If you need web hosting, you could do worse than here
According to microsoft, the MSN messenger service (which serves to around 70 million people) used to run on 250 32-bit servers, and now it runs on just 25 or something like that... (apparently one of the big reasons was the limit on the number of tcp connections).
It's quite amazing to think that a service as huge as messenger can run on just 25 servers!
The AACS key is NOT 0xF606EEFD628B1CA427BEA93A9CA9773F
Win 98, not 95 =)
I was watching the video full screen (I'm 23:40 into it now) and I started getting dizzy with all the movement in the camera. Whoooa! We're moving toward the screen again!
Also, it would be nice if they went over the interview plan before hand, so we wouldn't have to listen to them ask if they can show different tools, and so we wouldn't have to watch them switch the refresh rate, etc.
The 10mb/sec number was over a high capacity WAN link from Redmond to San Francisco with a 30ms latency. The new 64-bit OS and IP stack supposedly increased thoughput to 800mb/sec! I'm guessing window size limitations in the 32-bit stack were constraining throughput? I've personally seen over 200mb/sec between 32-bit Windows machines on gigabit Ethernet links. (Likely the limitations of the disk subsystem rather than the NIC/IP stack in my case.)
This may enlighten you.
Quoting:
...and yet, AGAINST ALL ODDS, microsoft.com kept working. How's that for some unexplained mystery shit?
Actually, they already do quite a bit. http://searchdns.netcraft.com/?host=.microsoft.com &position=limited&lookup=Search. Yes, this does means that it's been confirmed by Netcraft.
Grammar Lesson: you're is a contraction of "you are"; your means you possess something; yore means days gone by.
Wow. Just wow.
I look at Solaris (err, OpenSolaris) and how it can now push a 10Gb/s interface at line speed (or close to it) and MS has struggled up until recently to get satisfactory speeds above 10Mbit/s ?
Yet another "how do users/admins accept this as OK" thought going through my head re: Windows internals.
You realize that that article talks about issues that had been long since solved by 1996, and list the solutions to them? In the case of the particular quote, the TCP Window Scale Option.
The following is just hearsay, as I've never actually worked for MS. But a couple of engineer buddies I used to work with did some subcontracting for MS, and they said they deployed a whole lot of internal-facing *nix servers during that period. I tend to believe it, because the MS security guys who taught some seminars I attended wouldn't confirm or deny that they used any Linux internally. If they could have denied it in clean conscience, wouldn't they have done so emphatically?
Working in a DevOps shop is like playing in a band made up entirely of keytarists.
What are the server specs? Altavista was running on 8 Digital high-end servers, Google runs on several thousand PC-class servers.
So MS is trying to embrace and extend TCP now?
I wonder how much of this is just to win benchmarking contests with Linux (look at how much faster this all Vista network runs versus this all Linux network)
I guess as long as it is fully documented and truly open if it is a benefit Linux will implement it as well. But if it is fully open for GPL implementation, MS probably won't release all the info until after Vista is out, knowing that it will take 2-3 years for it to get written, get accepted into -mm, get accepted into the real kernel, make it into Fedora, get into the next major rev of Redhat and then finally be used in benchmarking contests between Windows and Linux....sometime in 2010!
I'm not so sure. Back when OS X 10.3 was current during late 2004, I was transferring some files from an older OS X box to an iBook and compared to transfer rates between the older OS X box and a Windows Server 2003 box, the iBook had something like 35-50% better throughput than from the Windows box. This was for a very large transfer of around 1GB (100baseT).
Give me a break. Microsoft uses Akamai to do DNS load balancing.
100% of Microsoft.com runs on Windows.
Hmm, nearly-direct link to a 145-megabyte video file on the /. front page, posted right as the geeks of the world are getting home from work. What are you, crazy? Are you trying to Slashdot Microsoft?
Don't answer that.
"In a 32-bit world, you're a 2-bit user. You've got your own newsgroup, alt.total.loser." -Weird Al
Yep. I've seen much higher transfer rates on OS X since OS X Server 1.2 when compared to OS 8.5-9.2 and Windows.
Side by side I've FTP'ed at 30-60% faster with OS X and Linux against Windows and OS 9
In other words, TCP is a protocol, not an algorithm.
So ... if Vista has some fabulous new algorithms for implementing TCP, then why can't other OSes be patched to benefit from those algorithms also? OR, if Vista is implementing something other than TCP, then how can it be (fully) backwards compatible?
Seems like the word "compatibility" might need to be scrutinized here.
Human being (n.): A genetically human, genetically distinct, functioning organism.
Microsoft has more traffic than Slashdot?
Surely.
But you know that does not really solve the problem. Window Scale just allows you to "adjust" your window further than the 64Kb. Also a packet loss with a large window has some dramatic consequences, and to address that is not easy.
Second large windows degrade what we call "fair queuing" mechanisms: splitting bandwidth over multiple TCP/SWP connections. Large windows cause a lot of congestion.
I am not a Windows user myself:
[ 16.784315] TCP reno registered
[ 16.784454] TCP westwood registered
[ 16.784487] TCP highspeed registered
[ 16.784515] TCP hybla registered
[ 16.784542] TCP htcp registered
[ 16.784570] TCP vegas registered
[ 16.784597] TCP scalable registered
I've all those TCP "flavours" available. Some are good for high-speed links, some for high-latency, some for low-congestion and so on.
There are some other issues around that may arise if you have some other "active" node in between the endpoints (such as routers). But you know that.
This is why I love AAL5 (ATM)
You might know this. Why is MacOS so slow at ping? Try it sometime, ping flood a linux box, and you'll probably clear 20,000 pings/sec on a normal system (though some versions of linux are slow too). Ping -f a mac and you might get a couple hundred packets back.
This is true with OS9 and a lot of OSX boxes it seems.
I've had enough abrasive sigs. Kittens are cute and fuzzy.
Check out this google query, that's all I know. I'd bet they are high quality x86-64 PC's...
The AACS key is NOT 0xF606EEFD628B1CA427BEA93A9CA9773F
Yep, then they replaced the 8-bit 3COM 3C501 NIC and they were flyin'
AT&ROFLMAO
207.46.18.10 (or ..16.70)
It traceroutes through MSN address space (po34.bay-6nf-mcs-3a.ntwk.msn.net (64.4.63.86) is the ending hop)
You're confused.
No, he's not.
Just because you can push 480Mb/s doesn't mean you're getting 480Mb/s throughput on any given connection.
Yes it does - it means that he's getting 480Mb/s to the outside world. Whether that is to one client on the same local link, or split between 1000 clients across the globe, it's still 480Mb/s.
Suppose you had 1Gb/s on two connections seperated by 5000 miles. You really think you're going got get 1Gb/s?
Yes. By definition. That's what 1Gb/s means. Latency and bandwidth are orthogonal.
The inherant latency delays in the protocol make it impossible to get anywhere near optimum bandwidth.
Latency and bandwith are orthogonal. If you could get 1Gb/s to Mars, it's *still* 1Gb/s, even though the latency would be measured in seconds (or possibly minutes.)
As they say, never underestimate the bandwith of a station wagon full of backup tapes hurtling down the highway.
Thank you for the insight. It was a joke.
Grammar Lesson: you're is a contraction of "you are"; your means you possess something; yore means days gone by.
Bandwidth vs Latency.
/proc/sys/net/ipv4/icmp_ratelimit
:)
Take a truck. A huge one. Fill it up with recorded DVD's and send it over a hundred miles distance.
You'll have huge bandwidth.
But wait, somehow a DVD got lost in transit. What now ?
You have to phone back and have a taxi to pick it up and deliver the missing DVD.
As you need the last DVD, you'll have to wait. Your bandwidth decreases.
It's pretty much costly for you to do so if you miss a DVD.
So you decide to take only a hundred DVD's per truck and using multiple smaller trucks. But somehow none is missing this time, so you spent a lot of money for the extra trucks.
This issue is somehow similiar to Heisenberg's Uncertainty Principle. You cannot get maximum bandwidth and minimum latency.
Linux can respond faster if it has to. OS/X doesn't do that because it does not want to.
It can also respond slower:
$ cat
250
Tune it as you wish.
Yes, I had some beers today, and what?
No, no, no... they can saturate a 10MB/s connection easily. What they had problems with was database connections over a long distance (a problem with TCP, not windows)... which they rectified (using a concept called CTCP), check this paper out: http://research.microsoft.com/research/pubs/view.a spx?type=Technical%20Report&id=940
-everphilski-
You could scan through all of my old posts for background if you like, but back when NT 4.0 was brand new, I helped to save a failing ISP (for at least the next 6 months or so) by setting up a new mail server to replace the one that was failing ever 2 to 10 minutes. I used a machine with less than half the power and resources of the machine already running... and loaded slackware. I think the kernel was jsut over 1.00 at the time.
...I guess I've repeated enough digs on microsoft for one posting...
Yeah, "old technology" couldn't do anything better than new stuff like NT right? Come to think of it, there's not a LOT of difference between XP's kernel and NT's from what I understand... a few bug fixes here and there... but basically, it uses the same vulnerable messaging scheme and drivers running at ring-0 and all that.
You realize that that article talks about issues that had been long since solved by 1996, and list the solutions to them? In the case of the particular quote, the TCP Window Scale Option.
The problem has been solved (or improved anyway) a few times! Zmodem used the same solution to essentially the same problem.
After having this video playing in the background for awhile, one interview question caught my ear:
"So is your security getting better?..."
Aside, its funny to hear them concede that they're actually having to adjust for other browsers visiting their home page.
"Use standard-compliant code? Heresy!..."
It's very true, I know some of the hotmail engineers who were helping with the handover. The Microserfies just couldn't do anything right :)
The original Hotmail platform was all something-BSD. FreeBSD I think.
oh come on, how can you blame Windows networking stack.. Microsoft.com is the biggest most visited website..the story poster is a anti microsoft crack head...
"I'd rather be a lightning rod than a seismometer." -Ken Kesey
Just out of curiosity...
I've not had much experience with Apache. How easy is it to use Apache, but make the client think they're connecting to IIS?
This sig rocks the casbah.
Latency and bandwidth are not orthogonal when you have flow control. Try looking up 'bandwidth delay product' and tcp windowing. To achieve 1gbp/s to mars you need to buffer all that data in case of packet loss. Available memory will throttle your throughput.
A quick web search says round trip times to mars are between 10-50 minutes. Say 60 minutes * 60 seconds = 360 gigabits of window space to achieve full line rate. Now consider some minor packet loss and even with SACK you're buffering an unreasonable amount of data.
Annoying that the parent got modded up with bad information and this post will likely be passed over.
The round trip time to Mars varies between about 10 and 40 minutes, depending on the relative positions of the Earth and Mars.
Slashdot has turned from "Microsoft sucks" to waxing poetically about how Microsoft used to suck.
How times change...
What? I fail to see what this has to do with bandwidth delay product.
Thanks for the tip on the icmp_ratelimit though, that's probably the culprit.
I've had enough abrasive sigs. Kittens are cute and fuzzy.
No, it used to be "eat their own dogfood" - now its "drink the nice purple flavour-aid - or I'll fucking bury you!"
It was one of there secondary sites, something like blah.microsoft.com. The ISP was supposed to be hosting it on a colo NT box as part of an outsourced hosting contract. Well the site crashed constantly and the support team got sick of the late night pager calls and moved it over to a BSDI box with Apache and spoofed the server headers to read IIS, never told the M$ guys.
One big reason for the reduction in necessary applicances to serve the web traffic is the increase in network speeds, that now let home users download many megabytes of patches in only a few minutes rather than the continuous hours it took before. Another reason is web proxies, that cache the bundles en route and redistribute it from local proxy servers. Another is that few Windows clients have microsoft.com as their home page anymore: services like Yahoo automatically reset the user's home pages to something more useful, which takes load off those servers.
Given all that, a reduction in the number of servers needed is not shocking.
Ok, even if the Mars example breaks down... intra-earth, the point still holds.
Anyhow, the 38 minute video has not been slashdotted yet.
However, that one guy definately looks like he hasn't washed his hair in a week. (No not the bald guy).
In general, when I download stuff from MSFT (usually big, bloated stuff) it does saturate my 4Mbs cable link - sometimes even more than advertised!
This issue is a bit more complicated than you think.
sysctl -a | grep icmplim
This showed the setting for my 10.4 box
You're totally not understanding where the bottleneck is. The issue isn't if it's possible to push 480Mb/s out of one machine, or if it's possible to push it over a link rated at 480Mb/s. The issue is if it's possible to do it *using the original TCP standard*.
Each end of a TCP connection allocates a receive buffer. The available empty space in this buffer is mentioned as part of the header on every packet. A TCP implementation allowed to continue sending packets to the other machine as long as there is space in the buffer. If machine A says it has an 8 KB buffer, then machine B can send 8 KB without worrying. If machine B receives an ACK packet saying that there is free buffer space from machine A before it sends 8 KB, then it can keep on sending data. However, if 8 KB is sent before machine B hears anything from machine A, machine B is required to completely stop sending data until it receives an ACK indicating free buffer space.
The buffer size specified in the TCP header is a 16 byte number. This worked fine on slower networks, but according to the article it peaks around 10Mb/s. It becomes an issue of latency. Once you receive a packet, you need to be able to get an acknowledgement packet to the other machine before it can send out 64KB of data (counting the packet you just received). If you can't, the other machine stops sending data until it hears from you.
Sometime in the 90's when the problem first became an issue, a solution was developed. A new TCP option was created that indicated the buffer size in the TCP header was to be multiplied by a number specified during the initialization of the connection to get the true buffer size. Apparently MS only implemented this recently.
And they still manage to have a service outage for at least a few minutes to a few hours a month. AIM and Yahoo! don't seem to do that to me.
Administration, software issues, whatever. MSN isn't that amazing, especially compared to the other services.
My blog. Good stuff (when I remember to update it). Read it.
:)
... half of a FSB running at 1GHz.
Either you have high bandwidth you you have low latency, TCP speaking.
But pings are ICMP, not TCP, so that does not directly apply.
Ping slowdown (slow rate) in OS/X its probably a rate limit. To prevent DoS attacks.
I bet OS/X fails horribly transferring files over noisy links, or in high congestion situations, but nowadays we don't use those noisy links anymore (we do congestion tho) so that makes some sense.
No one has spoken yet about ECN. That can play a major role too in window scaling.
My point is simple: what you get is what you tune your OS for. I know Linux/BSD can be fine-tuned. I believe M$ Windows can too, but I'm not sure.
Still my first post was only to enlighten what TCP and sliding window protocols were all about. Some more issues arise when dealing with high bandwidth transfers, such as interrupt congestion at CPU bus, DMA, layer-2 aware NIC cards, and so on...
For example, 10Gbit cards are here, but that makes at 64bit a speed of 312Mb between peripheral/memory and memory/cpu. Pretty high. At 32bit/transfer makes 624Mb/sec
I remember "freezing" NT4 just by flooding it over a 100Mbps link with IGRP packets. The mouse froze completely.
... Google runs on several thousand PC-class servers.
;-)
Yeah, but Google's servers aren't just passing bits around, they store a copy of the whole (freely accessible) web.
-- "I never gave these stories much credence." - HAL 9000
Oh crap. I'm 100 in world wide web years... :(
He points out sooooo many short comings of windows. When he was talking about memory, he basically says that they needed 64bit so that they can just throw more memory at thier problems.
I was thinking the other day that hardware makers should be a little scared about OSS as well. I mean, now that you can run a nice GUI on hardware that is 4 years old without issues, how are they going to sell newer and faster?
I don't think he washed his hair that day. A true geek.
Note To Mods; I didn't read ANY comments, so be kind.
Too bad gaim was reporting connection errors for the past hour on AIM for me.
all everyones problems went away when they switched to winxp ?
Sorry i though everyones problems went away when they switched to winme?
Sorry i though everyones problems went away when they switched to win98
Sorry i though everyones problems went away when they switched to win95.
all i seem to hear before a new windows release is how xxxx is stable now xxxx starts up in only 4 seconds xxxx doesnt have this problem xxxx doesnt have that problem.
Windows has had commercial server software for how long ?
and its just fixing a stack limitation when ?
except for the fact that you're a fagot. queerz0rz
Are these guys sitting in their office playing Quake? If not why can't MS get them a flat panel?
Penny - plain text accounting
That's a minor change. It's kind of obvious too: take two congestion control protocols that work OK, and blend them into a hybrid. People have been doing this sort of thing for ages.
Linux offers several choices, configurable at run time if you like to play with settings. The default is great for almost everyone though, so not many people play with the settings.
Probably they also implemented TCP Window scaling. Everybody does this now.
If you watch the system log on an OS X machine that's getting ping flooded, you'll note that it starts printing "Limiting icmp ping response from (large number) to 250 packets per second". It's entirely intentional.
TANSTAAFI: There Ain't No Such Thing As A Free iPod.
gaim isn't AIM. I'm talking about using the real, Windows-based MSN client that tells me "Service is unavailable, try again later". Go astroturf elsewhere.
My blog. Good stuff (when I remember to update it). Read it.
I'm watching this right now and....
THESE GUYS ARE IDIOTS!!!!
If this is the best face M$ can show of it's staff, than open source has nothing to worry about.
The cans are used in Scientology to rid you of Body Thetans and Engrams. Regular use of the cans will help you to become Clear, or at least attain a higher rank in the organization while going into debt.
So that explains Microsoft's success. Wow.
Heh, if you had to pay those MSFT licensing fees, I'm sure you'd find a way to reduce the number of Windows Servers you used too. ;)
This is only impressive if we have a figure from a competing IM service to compare it to. For example, does anyone know what Yahoo Messenger's server farm looks like?
25? How about one server, and with several more applications tossed in for good measure? Yup, runs Linux reeeaaaalllly well. :)
It gracefully "cycles" your process so you have your memory leaks. If only other apps were coded for memory leaks.
I think you underestimate just how much I just dont care.
Microsoft--and the two staffers shown in this video--deserve strong praise for the *unedited* candor, the self-depricating humor, and the absense of spin on this video.
:-)
Maybe I've missed the comments, but what no one seems to mention here is that these guys--clearly both geeks at heart (in a good way)--really are peeling back a lot of the layers of MS's site. The candor about their security problems, the 2gb memory issues, and a variety of other things was refreshing.
Heck, they even mention firefox.
Good work all. Good work.
Running 'Nix is like owning a Lightsaber. It's "a more elegant weapon for a more civilized time."
This story was just made for slashdot. Can a more perfect story have come along? It has everything, a Microsoft insider, Microsoft bashing, a direct video download for easy slashdotting, plenty of fuel for trolls, and even caffeinated beverages.
Its exactly what we want to hear. Its like preaching to a group of fundies that God loves them for hating gays. Oooh, put a cork in it, we can only have one flamewar at a time.
-d
"Here Lies Philip J. Fry, named for his uncle, to carry on his spirit"
Seems fair (or ironic) since he *was* replying to a post with bad information that got modded up.
Slashdot gets worse every day... Pipedot: News for nerds, without the corporate slant
No, but it would be if it ran on Linux!!!
Now before I get modded down, I be to remind whoever might read this that what I am saying is FACT. - bogaboga
I like how 10:14-10:18 zooms in right on Chris's keyboard as he types his password. Just using Windows Media Player on cntl+shift+s takes a lot of the guess work out of the password.
Especially with a little help from our friends from UC-Berkley.
Also, I like 12:32, "so we'll avoid showing ip address... haha we'll have to cut that part out..." like the large 207.46.16.30 address looking at us in the face and then seconds later the 3 ip addresses in clear view on the right.
"So we have terminal server access to all the servers in the data center, right.". Right, well I wonder how may of those servers, whose IP addresses we just saw, are attached to Chris's login and password?
Ready, aim, proxy.
Hey look no pointless curley braces or semicolons... just like Python
*IF* you have 30ms+ latency on the link, as they explicitly said in the video.
Slashdot gets worse every day... Pipedot: News for nerds, without the corporate slant
If you're talking about a purely asynchronous protocol, maybe. Here on planet Earth not so much.
Now before I get modded down, I be to remind whoever might read this that what I am saying is FACT. - bogaboga
I guess Microsoft hasn't invented UDP yet.
"Go astroturf elsewhere." are you implying he was hired by microsoft?
There's a thing called cost-benefit analysis.
If the cost of redesigning is greater than the benefit then it's not worth doing.
Apparently it's better right now to patch.
Let the market decide.
If a redesign is really a lot better then someone will do it an they will make a big profit.
Yay for free market.
At around 10:25 in the video Chris St. Amand, who runs Microsoft's website and data center, types in his password, which the camera recorded. And the video is hosted off of Microsoft's website...although I don't know how long that'll still be operational.
If you think that AIM never goes down, you have no idea what you're talking about. I've had AIM shit out on me MANY, MANY times, and yes, this is with the actual AIM client. It'll kick me off, and I won't be able to sign in for a few minutes, sometimes it'll get stuck at verifying login/password and just sit there until it times out, etc.
AIM has its server problems too.
Also, not everyone who disagrees with you is an astroturfer. As hard as it may be to believe, some people might ACTUALLY have different experiences and opinions as you.
wow, this video has been compressed to timestamp sizes.
it shows as a 1.25*1 inch window on my monitor, and sounds worse than a cell phone conversation.
in this day and age, I expected it to be at least 4 times bigger. this is ridiculous...
Donald 'Duck' Dunn: We had a band powerful enough to turn goat piss into gasoline.
iChat wasn't able to connect for around an hour today either. Completely gone, nada, nothing, zilch.
All those services go down from time to time, heck, I pay how much for it again.... Oh yeah, nothing.
If you want to e-mail me, use my PGP Key.
So because AIM simply refuses to connect instead of giving you the useful info that the service is down (and thus don't bother trying to troubleshoot your computer/network) means that it never goes down?
I laughed... but specing out machines just to find out that licensing will cost 1/3rd of hardware is a bit much. It's like a horrible, horrible tax.
Some big-ass Solaris boxes there. Front-end is Windows, though. This will soon change, due mainly to competitive pressure (storage, mostly). Once the new Hotmail is deployed (the AJAXified version), the backend will run Windows, too.
The most popular approaches to the problem of the fat pipes is multiple TCP sessions and streaming over UDP. In case of streaming over UDP retransmission requests can arrive after the transaction of some large block completed. In many UDP based protocols destination sends only NACks. etc.
The area is very interesting and i expect will gain more attention in the future. it looks unlikely that network delay will be (can be ?) cured, but pipes are definitely getting fatter.
There are certainly many models other than strict flow control that can cope with packet loss but all of these also restrict bandwidth. Also, we were talking about TCP. The point being, you're going to have to do _something_ that will reduce your throughput from the theoretical maximum.
;-)
Even in your scheme the data must be available if the redundency protocol fails. Anyway, with these latencies you're really only going to do bulk file transfer so even normal tcp works with sack and a sufficiently large window if you can page your window in from disk. It certainly would be smart to build some redundancy in to the protocol but I wasn't exactly going for designing a martian transmission control protocol in a slashdot article where most people can't tell their asses from their elbows.
32-bit DLLs work fine on 64-bit x86 Linux. You have to compile MPlayer as a 32-bit program, of course, but you're still running it on a 64-bit processor, and a 64-bit Linux OS.
how about stop bitchin about stupid players? VLC is good enought and have WM codecs
no one noticed the bulshit about 10mbits to datacenter wich is not true. shame on you linux users. stop bitchin about windows and microsoft and get a life . you have your own OS of choice and it is good to focus on it only.
I imagine that the price tag, the exposure to malware (one of the big reasons I don't use MS products myself), and possibly the lack of PPC and/or 64-bit versions of MS-Windows and/or the codecs might have something to do with it.
What your assertion basically amounts to is: "He should run x86/32 and use an illegal copy of MS-Windows rather than run a Free (and probably free) OS and player on the hardware of his choice."
Let's put this in modern, everyday terms. Imagine Sony's media companies releasing only DVDs that work only on Sony players. I own a Panasonic player. You're telling me that I should buy a Sony player at whatever price Sony asks rather than whining about Sony's exclusivity?
It's kind of like signing a temperance pledge because practically everybody else in my community has VD, and subsequently being told that if I want to watch a movie I have to have sex in the back row of it. Am I a whiner because I refuse?
And how about you?
Got time? Spend some of it coding or testing
quality is dacaying. I think this post will be marked as a flamebait however I don't care. I'm noticing that apart of "first posts", stupid posts that pretend to be funny and so on, slashdot is becoming unreadable ...
No, I regularly hit 100 mbps, and know people who have gigabit (but, due to hard drive speed or other factors, seem to top out around 600 mbps). So that is definitely not a limitation in windows.
"73% of quotes on the Internet are made up" -Ben Franklin
I do believe MS is also using a Linux partner to distribute the content, can't recall the name but all very large sites us this technique.
People seem to forget how fast a system can run if you don't have a massive GUI running Office on top of it. This goes for departmental file server (no, you don't need a dual 3Ghz XEON to server files to 10 users) as well as for efficient internet apps.
All MSN does is keep a connection open (no doubt using non-blocking I/O, not a thread per connection!), take in some bytes, look up the connection for the recipient(s) and stick it in their OS level TCP/IP buffers.
This obviously isn't entirely trivial, but is shouldn't come as a surprise that a team of Ivy league CS PhDs can make this work on just 25 modern servers with a good TCP/IP stack.
And obviously, not nearly all of those 70 million users are signed in at the same time.
why do you care about microsoft.com and the video that discusses it?
AIM and yahoo combined must have about 10% of the total traffic of MSN Messenger.
http://www.vnunet.com/networkitweek/news/2052597/s olaris-calls-hotmail-shots-microsoft
(to verify parent's link)
tcp aside, as just basic ftp command line, or ftp GUI.
A mac ftp single data connection, couldnt max out 3.5 megbytes/sec to a unix box or the xbox.
Xbox to xbox , does 10+ MEGbytes/sec easy
Linux to xbox (lftp) , 10.5meg/sec too.
What TF, is wrong with the mac... why is it soo roooted. Even back in 1997, OS7 was still doing 350KB/sec on ftp to an Irix box.
Liberty freedom are no1, not dicks in suits.
AIM did it yesterday. System-wide boot on at least the East Coast.
They really *should* upgrade to 100 or 1000 Mbit ethernet cards.
Oh wait... you're talking about Windows?
They look like hell!
Who the hell modded this informative?
The search at rpm.pbone.net in the parent post returns "Your search MPlayer-w32codecs-1.0pre7try2-15.sparc.rpm did not match any entry in database.". Further searches at rpm.pbone.net and Google do not return any hits for this rpm.
Did you see the Coke Can at his desk, that's how m$ are paying for all the bandwidth.........Product Placement. :-)
s hire/2005/11/328667.html
http://www.indymedia.org.uk/en/regions/nottingham
Microsoft is the only place I've every worked that hired other engineers remove the ongoing responsibility of performance and debug from development engineers. They should require that a developer has to maintain whatever they work on for at least a year after release.
The numbers mentioned are for the MSN MESSENGER service only!
The AACS key is NOT 0xF606EEFD628B1CA427BEA93A9CA9773F
To achieve 1gbp/s to mars you need to buffer all that data in case of packet loss. Available memory will throttle your throughput.
Well, by the time we have a 1Gb/s link to Mars, every computer will have a minumum of 128GB RAM, so this isn't really an issue.
The thing is that besides me underestimating the distance to Mars (sorry, and thanks for the correction), I'm right. Bandwidth and latency are orthogonal except in extreme cases (extremely high speed over extremely long distance.)
As another poster pointed out, with a 30 bit receive window and 100ms latency, it's possible to get 5Gb/s - well under the 480Mb/s that was posted here.
The problem you describe was solved in the 1990's. The fact that MS only recently got around to implementing it is beside the point.
You're thinking about akamai (content distribution network), but that's not relevant on this particular discussion since we're just talking about the MSN Messenger service, not the whole msn/microsoft site(s).
The AACS key is NOT 0xF606EEFD628B1CA427BEA93A9CA9773F
Pardon me if I think you're lying through your teeth. How could they not notice that they're no longer connecting to a Windows server? They would still have to connect via FTP or something other protocol, did you spoof those too? Not just that, how did you manage to fake the whole directory tree? If they connect to upload files, they'd notice it was a unix system by the file hierarchy and the fact that ASP DIDN'T WORK ANYMORE. Yes, there are some *nix ASP products, but they don't work that well. They'd definitely notice something was wrong the second they tried changing something on the website.
When you are being filmed, take your chewing gum out!
These two have about 30 minutes left in their careers before the rent-a-cops escort them to the front door.
Are you joking? No one in the United States ever uses MSN. I have never been asked for my MSN email, but people swap AIM names like phone numbers. I am aware MSN is more popular abroad, but I think the IM penetration in the US is quite high.
I'm not surprised that there are people like this there.
The problems at microsoft that lead to things like the IE-hole-of-the-month-club have nothing to do with the competence or otherwise of the people working there. You could put Linus, RMS, and another fifty of the top OSS developers there and (if they didn't quit) they'd end up producing the same quality of product.
The problem is that windows has some fundamentally bad designs baked into it. Design flaws that they won't (and probably by now can't) change. Some deliberately created for short-term advantage, like the IE/ActiveX farce, that would break too many applications for them to properly fix now.
Interesting. It's the opposite in the UK. I've never had the need to use AIM or Yahoo, but I've got nearly 100 messenger contacts. In fact Messenger is something that you must have installed on some projects I've been on.
From the openbsd mplayer port's Makefile:
ONLY_FOR_ARCHS= amd64 i386 powerpc sparc64 arm
As it was explained repeatedly now, its just the win32 binary codecs are i386 only.
TCP windowing is not the solution. It's a hack. If everyone started using high TCP Windows, retransmission would cripple the network. Of course you could counter that with fully error correcting protocols, but then you reduce bandwidth again as parity information increases. you also increase the load on the CPU and/or network processors.
It's like saying "I can hold my breath for 10 minutes under water if I meditation and chemicals to slow my heart rate", but that doesn't help someone who needs to move around and do things while underwater.
You need a solution that works for everything, without putting too much load on the infrastructure.
If you need web hosting, you could do worse than here
That's the best definition of a corporation that I've ever heard. You've just gained a new friend :)
You still don't know what you're talking about. That's not 30 bits of buffer, that's a 30bit window size. That's a 1 gigabyte buffer. Even if you had 128 gigabyte of ram, which I don't know how you've arrived at that, you probably don't want to use almost half of it for one transfer.
You don't seem to know what the problem or the solution is so I'm not sure how you know when it was solved by anyone including microsoft.
They were using ASP that widely way back then?
See?, this is why capitalism doesn't work, and this is what i was pointing out ... what you are saying, is a HORRIBLE way to think, but you consider it OK.
The purpose of Software development is to DEVELOPE new and better sfotware that is usefull to human kind. But, it's not profitable, so, let's just produce crappy software and earn lots of money, yay for free market!. Hey, public education is not profitable, let's just have a few expensive schools, and make lots of money out of it, so, who cares if only a few can get education, we will be rich, yay for free market!. Hey, you know what?, why don't use start producing weapons and sell them to both the USA and Irak?, that way the war will last forever, and we will be rich!, ok, lots will die, but, you know, let the market decide!.
Yay for free market.
You sir, are really dusgusting.
WTF am I doing replying to an AC at 5 A.M on a Friday night?
If something not profitable then why would people want to do it?
Perfectly designed software has its place (ATM's for instance) but at some point it's not profitable (Video Games and Microsoft Operating Systems apparently).
Most public education ends up being not profitable. That's because of the way it's run not because it couldn't provide the education for less than the amount being paid.
What about colleges?
People are willing to pay for education. Education could be profitable. Lots of private schools make profits. Few people run schools out of the goodness of their hearts.
There is plenty of competition and profit in education. Why do you think people look at so many colleges searching for the one that is right for them.
Public education is not profitable because there is no drive for it to be profitable. If a public high-school profits then where does the money go? Maybe to pay for the roof of the town hall, or if they are lucky, back to the tax payers next year.
Private schools aren't expensive schools. People pay a lot yes but clearly the education from the school is more valuable than dollars given to the school.
It costs the tax payers in my town 13k per student per year for public schooling. If every kid got a 13k voucher then plenty of schools would pop up offering great education for the price. Yes school owners and teachers would make lots of money but the kids would get better education because there is better competition.
Right now competition is difficult because it involves moving between towns. The public schools practically have a monopoly.
How many Ivy League schools are public schools?
That's how many government controlled ivy league software companies there would be.
Back to your earlier post:
So called problems:
1 - The company's cashflow is based arround selling new versions of the software
Yes. If a new version is just the same as the last one but much more stable then maybe people will buy it. Depends on the marketing and word of mouth. Maybe some people will prefer the cheaper older version that crashed more often the same as some people buy a cheaper used car that breaks more often. There is nothing wrong with that in my opinion.
2 - They can't sell to it's customers improvements that they customers can't see
I cant see the interest rate on a loan any more than I can see the stability and reliability of a program I use. Customers buy lower interest rates all the time.
3 - There is a fixed time that can go by beetween one release and the next one
There is? Microsoft doesn't update Minesweeper very often. When is the next fixed release on that software?
4 - Resources are limited
They are? I've never heard of a company hiring new people and buying more machines. What limit?
What a stupid capitalist bastard you are ...
Look, certain things should be done as good as possible BECAUSE that's good to human kind. I DON'T GIVE A FUCK if someone in your stupid capitalist system can profit from it or not.
People should recieve the best education possible. People should do their work the best they can. Software should be as good as it can get. And this are just examples, the rule is: The human race have had lots of political, economical and social systems, but the objective all the time is to IMPROVE our life quality, to learn, to be better as a society. If your stupid capitalist system gets in the middle of that, FUCK CAPITALISM.
WTF am I doing replying to an AC at 5 A.M on a Friday night?
lol