Beta
×

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

Thank you!

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

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

Linux 2.2 and 2.4 VM Systems Compared

CmdrTaco posted more than 12 years ago | from the hey-look-someone-did-actual-tests dept.

Linux 225

Derek Glidden writes "I got sick of trying to figure out from other people's reports whether or not the 2.4 kernel VM system was broken or not, so I decided to run my own tests, write them up and post them online. The short conclusion is that the 2.4 VM rocks when compared with 2.2, but there's more to it than just that."

cancel ×

225 comments

Sorry! There are no comments related to the filter you selected.

Which 2.4 VM ???? (0)

CDWert (450988) | more than 12 years ago | (#2513249)

Whick 2.4 VM rocks ?

The latest , if so you are correct, the -ac seems to pretty much Suck though.

Re:Which 2.4 VM ???? (-1)

Anonymous Pancake (458864) | more than 12 years ago | (#2513263)

This is a pretty bad FP, faggot

Re:Which 2.4 VM ???? (0)

Anonymous Coward | more than 12 years ago | (#2513265)

The both rock compared to 2.2, that's his point in the article.

RTA ???? (0)

Anonymous Coward | more than 12 years ago | (#2513276)

"You'll notice that again, 2.4.13 squeaks by 2.4.12-ac6 in terms of compile times"

Re:Which 2.4 VM ???? (-1, Troll)

Anonymous Coward | more than 12 years ago | (#2513285)

The writing is on the wall.
*VM is dying.

Re:Which 2.4 VM ???? (5, Informative)

Alan Cox (27532) | more than 12 years ago | (#2513305)

As of 2.4.14pre the Andrea/Marcelo VM is definitely doing better on most workloads. Where the Riel one has advantages the right way is going to be to build on the Andrea VM.

The 2.4.14pre VM also seems to be taking the harder brutalisation test sets pretty well - something the Andrea VM didnt do in 2.4.10-13

Care to tell us who gave you the DMCA legal advice (-1, Flamebait)

glrotate (300695) | more than 12 years ago | (#2513322)

Since you refuse to on the kernel list most people are assuming you just made that up? Did RedHat give it to you? If so RedHat seems to have incompetent counsel and I'll be looking to dump my stock.

Re:Care to tell us who gave you the DMCA legal adv (-1, Offtopic)

Anonymous Coward | more than 12 years ago | (#2513426)

It's not incompetant -- it's paranoid. It's intentionally paranoid to draw attention to a political issue that AC cares about.

Can you imagine... (-1, Redundant)

Anonymous Coward | more than 12 years ago | (#2513342)

Can you imagine a beowulf cluster of Alan Cox's?

Thank you.

Whats it like (-1)

ArchieBunker (132337) | more than 12 years ago | (#2513358)

to be a goat fucker like RMS? do you share goats?

Re:Which 2.4 VM ???? (1)

cpeterso (19082) | more than 12 years ago | (#2513742)


And didn't Linus add Rik's new VM during the Linux 2.4.0-pre code freeze? Linus has no concept of release management. He should follow FreeBSD a while, where they actually have a beta releases, release candidates, and separate branches for stable and development releases. Thank goodness for Alan Cox's voice of reason to balance Linus.

*BSD-is-dying-posting is dying. (-1, Offtopic)

Anonymous Coward | more than 12 years ago | (#2513332)

Yet another crippling bombshell hit the beleaguered *BSD-is-dying-posting community when last month IDC confirmed that *BSD-is-dying-posting accounts for less than a fraction of 1 percent of all troll posting. Coming on the heels of the latest Netcraft survey which plainly states that *BSD-is-dying-posting has lost more trolling share, this news serves to reinforce what we've known all along. *BSD-is-dying-posting is collapsing in complete disarray, as further exemplified by failing dead last in the recent Sys Admin comprehensive networking test.

You don't need to be a Kreskin [good.site] to predict *BSD-is-dying-posting's future. The hand writing is on the wall: *BSD-is-dying-posting faces a bleak future. In fact there won't be any future at all for *BSD-is-dying-posting because *BSD-is-dying-posting is dying. Things are looking very bad for *BSD-is-dying-posting. As many of us are already aware, *BSD-is-dying-posting continues to lose trolling share. Red ink flows like a river of blood. *BSD-is-dying-posting is the most endangered recurrent troll postings of them all.

Let's keep to the facts and look at the numbers.
*BSD-is-dying-posting leader Benny "Stupid Trolling Retard" McGoatfucker states that there are 7000 *BSD-is-dying-posters. How many *BSD-is-dying-posters are there? Let's see. The number of *BSD-is-dying-posting versus Imagine-a-Beowulf-cluster posts on Usenet is roughly in ratio of 5 to 1. Therefore there are about 7000/5 = 1400 *BSD-is-dying-posting users. Goatse.cx-link posts on Usenet are about half of the volume of *BSD-is-dying posts. Therefore there are about 700 posters of Goatse.cx links. A recent article put *BSD-is-dying-posting at about 80 percent of the idiotic trolling posts. Therefore there are (7000+1400+700)*4 = 36400 *BSD-is-dying-posters. This is consistent with the number of *BSD-is-dying Usenet posts.

Due to the troubles of Walnut Creek, abysmal sales and so on, *BSD-is-dying-posting went out of business and was taken over by Klerck who post other idiotic trolls. Now Klerck is also dead, his smelling corpse turned over to another charnel house.

All major surveys show that *BSD-is-dying-posting has steadily declined in trolling share.
*BSD-is-dying-posting is very sick and its long term survival prospects are very dim. If *BSD-is-dying-posting is to survive at all it will be among no life redneck retards. *BSD-is-dying-posting continues to decay. Nothing short of a miracle could save it at this point in time. For all practical purposes, *BSD-is-dying-posting is dead.

Can you imagine... (-1, Offtopic)

Anonymous Coward | more than 12 years ago | (#2513268)

Can you imagine a beowulf cluster of linux 2.2 and 2.4 virtual memories?

Thank you.

Better but bad (2, Insightful)

Chocky2 (99588) | more than 12 years ago | (#2513282)

2.4 VM is, IMO, a significant improvement over the 2.2 VM, but completely rewriting something as important as VM management is intrinsicaly risky and it's difficult to predict with even the slightest confidence many of the consequences of such a change. This sort of thing should be left for major revisions.

Nigger VM (-1, Flamebait)

Anonymous Coward | more than 12 years ago | (#2513290)

i'm using teh 2.4 nigger vm. and it works like a slave!


cmdrtaco is waiting for jonkatz to come fuck his asshole and then let him suck his dick and eat his own shit off of it. that is one sick faggot. /. news for niggers. faggots that don't matter.

Re:Nigger VM (-1, Troll)

Anonymous Coward | more than 12 years ago | (#2513301)

can you imagine a beowulf cluster of niggers fucking cmdrtaco's asshole? well you don't just have to imagine it anymore because they just finished shooting "cmdrtaco's nigger gang bang and bukake extravaganza" . be the first to rent this gay ass movie and get to fuck cmdrtaco just like jonkatz does every night.

Re:Nigger VM (-1)

Trollificus (253741) | more than 12 years ago | (#2513434)

With posts like this being the dominant, it's no wonder the proposed /. subscription model will never succeed.
Keep up the good work.

Linux is for terrorists! (-1, Troll)

Anonymous Coward | more than 12 years ago | (#2513296)

Viva le Windows! Linux is for commies and terrorists!

Re:Linux is for terrorists! (-1, Flamebait)

Anonymous Coward | more than 12 years ago | (#2513405)

[OffTopic] Let me see if I have this straight. A non-Arab-looking teenager is barred from two UNITED AIRLINES flight for carrying a Hary Potter book. But two carloads of Arabs, in possession of maps and info about US nuclear power plants and the Alaska pipeline are stopped and released? I wonder if the cops gave them directions to Three Mile Island?

Old News (-1, Troll)

Anonymous Coward | more than 12 years ago | (#2513299)

Did anyone else notice that this stuff
was all done in January, 2001?

BSoD (3, Insightful)

parc (25467) | more than 12 years ago | (#2513300)

From the article:

These were pretty uninteresting - just sitting there watching the kernel compile. Except that at one point, while running the 2.4.13 kernel, the hard drive started grinding away with the drive light pegged on continuously, the display became extremely sluggish and quickly froze up entirely, and about ten minutes later, the hard drive light went off but the machine remained unresponsive, requiring a hard reboot. I don't think this was related to anything I was doing as I wasn't actually doing a compile run at the time - probably just a random occurance, but worth mentioning.

So the machine essentially BSoD'd, but it's not interesting?

Re:BSoD (1, Informative)

Anonymous Coward | more than 12 years ago | (#2513319)

BSODs happen right away. They don't put you through that kind of torture. Also, they give you a nice stack trace for informational purposes.

If that had been a coredump, it probably could have been helpful, but since they don't even have a kernel debugger for Linux yet, these kinds of occurrences are just brushed away as "random occurance"s.

Re:BSoD (0)

Anonymous Coward | more than 12 years ago | (#2513349)

No, we _have_ a kernel debugger, but it's not being included with the kernel for some ... annoying reasons. Cough.

Re:BSoD (2)

pe1rxq (141710) | more than 12 years ago | (#2513487)

You would be surprised what you can do with the call trace of an oops and a list of kernel symbols.
No need for a debugger in the kernel.

Jeroen

Re:BSoD (0, Redundant)

Anonymous Coward | more than 12 years ago | (#2513360)

> So the machine essentially BSoD'd, but it's not
> interesting?

Indeed. It might be "interesting" for Amazon and Google, to name at least two. The Google bug is currently being debugged on LKML.

Re:BSoD (-1, Flamebait)

Anonymous Coward | more than 12 years ago | (#2513363)

one time i got a NSOD (nigger screen of death). it was horrible. the error message was in jive. it was almost impossible to read it, "sheeet, you done preformed an illegal operation. best be rebooting ya shit right now."

another time, i got a FSOD (faggot screen of death). that was bloodly awful. it was all brown and white and red. talked about one file 'rear ending' another file.

i guess the worst was a FNSOD (faggot nigger screen of death). oh shit!

Shit bitch, I ain't playin! (-1, Troll)

Anonymous Coward | more than 12 years ago | (#2513379)

Get yo mutha fukin shit rebooted. I ain't gunna ax yous again.

Re:Shit bitch, I ain't playin! (-1, Flamebait)

Anonymous Coward | more than 12 years ago | (#2513418)

Derek Glidden scribbles "I gots sick uh tryin' t'figure out fum oda' sucka's's repo'ts wheda' o' not da damn 2.4 kernel VM system wuz bugger'd o' not, so's I decided t'run mah' own tests, scribble dem down and post dem online. De sho't conclusion be dat da damn 2.4 VM rocks when compared wid 2.2, but dere's mo'e t'it dan plum dat. Man!"

The one major difference (5, Insightful)

matty (3385) | more than 12 years ago | (#2513469)

...is that Linux's warts are fully out in the open for all to see. Microsoft would never admit to such failings openly, even though anyone who has used Windows extensively is painfully aware of them.

And it's been my experience that you don't hear, "Linux never crashes" that much anymore. At least I don't say it anymore, whereas I used to. I would still say that a properly configured Linux box is more stable than any Windows box, but I've had my share of lockups. (on the desktop anyway. You'll notice my server has been up for 140+ days. The last reboot was when the power supply died [it's a patched together P166] which interrupted 243 days uptime)

All the mailing lists are public, and all of Linux's problems are there for anyone to see. This allows people to make truly informed decisions about which version of Linux to use, or whether to even use it at all. (Yes, of course these things are also true of *BSD) The current issues are why I still run 2.2.19 on my servers, since none of them get anywhere near enough load to need the newer VM's. "Stable" is definitely a relative term.

Re:BSoD (2, Informative)

sbrown123 (229895) | more than 12 years ago | (#2513470)

Actually, its probably something very simple: EnergySaver. Computer went into sleep mode which I have seen lock Linux up before.

Re:BSoD (-1, Troll)

Anonymous Coward | more than 12 years ago | (#2513643)

So in other words, Linux hates the earth and the stupid dork "developers" responsible for that travesty of an OS are even more useless than originally speculated. A bunch of whining, pompous niggerboys.

Re:BSoD (1)

Adrian Voinea (216087) | more than 12 years ago | (#2513475)

Please mod this down, the guy is stupid. The article says:

These were pretty uninteresting [...]Except that at one point[...]

That means that the guys says that the BSoD(as you like to call it) was interesting.

Re:BSoD (2)

Puk (80503) | more than 12 years ago | (#2513494)

Um... what?

These were pretty uninteresting - just sitting there watching the kernel compile. Except that at one point, ...

So the machine essentially BSoD'd, but it's not interesting?

It seems to me he said that they were uninteresting, except when it BSODed -- which was interesting.

-Puk

Windows users... (1)

Roadmaster (96317) | more than 12 years ago | (#2513530)

Windows users don't find BSOD's interesting. They happen all day long. Why should we? :)


Seriously, even I have seen Linux die.. it would have been interesting if it kept happening, but it clearly states it was a one-time event.

Re:BSoD (0)

Anonymous Coward | more than 12 years ago | (#2513601)

This wasn't a random occurence either; in fact, that particular bug is the only thing stopping me from dropping Windows entirely. It's kind of sad to see that arguments and ego's regarding kernel development are actually forcing me into using an operating system I'd rather not, simply because the kernel that supports everything I need is too buggy to use at the moment.

Re:BSoD (1)

EllF (205050) | more than 12 years ago | (#2513754)

the nice part about the kernel is that you don't have to use the latest version of it. alan cox maintains his own tree which runs a different version of the VM (for now, at least); the 2.2 kernels are also still available.

for the record, i've been running 2.4 since 2.4.1, and i've *never*, on three seperate machines, had a crash. i can't say that about windows. if the reason you aren't switching is because you think a linux-2.4 system will be less stable than your windows boxen, you might be running on a mistaken assumption.

if you don't want to read the article (5, Informative)

b-side.org (533194) | more than 12 years ago | (#2513304)

it goes like this -

the 2.2 VM 'feels' better for single-user use (which i disagree with) but falls down under 'heavy' load. (which, as i've pushed 2.2 to load avgs above 250, i also disagree with)

but, anyways, that's what he's saying. i found 2.4 to be much nicer in the one userland task that frequently shows off the VM - mp3 decoding under load. 2.4 never, ever skips, 2.2, with or without ESD, skipped frequently.

YMMGV.

YMMVGV (2, Interesting)

Tailhook (98486) | more than 12 years ago | (#2513568)

Your observations run counter to the continuous stream of reports of high latency in 2.4 found in the linux kernel mailing list. Specifically, skipping mp3 playing is the canonical report. 2.2 is often cited as being the less latent of the two.

I don't claim you're wrong. I point this out only to illustrate the subjectivity and lack of real data involved in these anecdotal reports. At the very least, the author has attempted to produce hard data on the matter.

Linus obviously thought poorly enough to of original 2.4 VM to space the mess.

Idunno... (-1, Offtopic)

journalistguy (398433) | more than 12 years ago | (#2513311)

I can't seem to get AOL to install on either of them.

Most recent is 2.4.14-pre7, with many VM updates (5, Informative)

Azog (20907) | more than 12 years ago | (#2513313)

If anyone out there has been having problems with 2.4 vm's (and there have been some problems) you should give 2.4.14-pre7 a try. Things have been moving fast on this front for a while now, but Linus thinks it's pretty much there now.

In his words, "In fact, I'd _really_ like to know of any VM loads that show bad behaviour. If you have a pet peeve about the VM, now is the time to speak up. Because otherwise I think I'm done.

This is an experimental patch to 2.4.13, and you shouldn't run it on an important machine, but the VM by all accounts is much improved.

Even Alan Cox (who has been maintaining the older Rik Van Riel version of the VM in his -ac patches) agrees that the new VM is faster and simpler, and he plans to switch to it as soon as it is reliable enough to pass his stress testing. (which should be really soon, it seems.)

(Yes, I spend an hour a day reading the kernel mailing list.)

Check out Linux Weekly News and Kernel Traffic (5, Interesting)

cpeterso (19082) | more than 12 years ago | (#2513695)

(Yes, I spend an hour a day reading the kernel mailing list.)

I'm too lazy to read LKML, but I am interested in the happenings of the Linux kernel development. I highly recommend Linux Weekly News' [lwn.net] kernel news (updated every Thursday) and Kernel Traffic [zork.net] , an in depth summary of the week's LKML happenings (usually updated every Sunday or Monday).

VM problems in early 2.4? (2)

cdipierr (4045) | more than 12 years ago | (#2513317)

Anyone have a link to the problems aluded to in the article with early 2.4 kernels? I've got a machine at work that swaps quite a lot and is running 2.4.2 ... I know it's due for an upgrade, but I'd like to know a little more specifically what was wrong back then...Thanks.

Makes me feel better... (2)

green pizza (159161) | more than 12 years ago | (#2513318)

... about running 2.2.19 (on RedHat 6.2) on my dual PII server. Guess it's about time to upgrade, though. RedHat 7.2 is looking nice.

How is bigmem support coming along? Is 2.4 still having problems with (32-bit) systems sporting more than 2 GB of ram?

Re:Makes me feel better... (0)

Anonymous Coward | more than 12 years ago | (#2513361)

Yep time to upgrade that 2.2.19 to 2.2.20 which came out today after being stuck in -pre for a year. Have fun!

Re:Makes me feel better... (1)

solve for x (531526) | more than 12 years ago | (#2513402)

How is bigmem support coming along? Is 2.4 still having problems with (32-bit) systems sporting more than 2GB of ram?

I don't belive 32bit machines can address more than 2gb of ram, that's one of the reasons there are 64bit machines. At work we have an SGI Octane2 that does HDTV work, it has 6gb installed and can support 8gb. It's a 64bit machine and runs IRIX64 v.6.5.13, a 64bit OS.

Re:Makes me feel better... (1)

Chandon Seldon (43083) | more than 12 years ago | (#2513442)

There are hacks to get 32 bit machines to support more than 2 gig of ram. Linux 2.4 seems to support up to 4gb.

Re:Makes me feel better... (2)

the_2nd_coming (444906) | more than 12 years ago | (#2513464)

a 64 bit machine should be able to address much much more memory than 8GB, I don't have a calculator infront of me but 2^64 is arounf a TB or 2 if I remember.

Re:Makes me feel better... (1)

solve for x (531526) | more than 12 years ago | (#2513744)

a 64 bit machine should be able to address much much more memory than 8GB, I don't have a calculator infront of me but 2^64 is arounf a TB or 2 if I remember.

AFIK, the Octane2 only supports 8gb of ram. Which I guess is ok since it only has support for 1-2 cpus.

I would imagine that a 64bit machine and os can address at least 1tb, as the Origin 3000 can handle 1tb (1024gb) of ram per single image.

Re:Makes me feel better... (3, Informative)

Arrgh (9406) | more than 12 years ago | (#2513789)

<niggle>Actually, 2^64 bytes is 1.84467E+19 bytes, or approx. 18.4 exabytes</niggle>

Re:Makes me feel better... (1)

worldwideweber (116531) | more than 12 years ago | (#2513472)

Just a note...

RedHat 7.2 ships with a modified linux 2.4.7,
so you will not get the AVM (Andrea's VM).

Also RH7.2 kernel still has the local root ptrace vulnerability, so you will need to upgrade to kernel-2.4.9 right away. RPMS are available at the usual places.

Then you can feel good...

why does slashdot temporarily ban people (-1, Offtopic)

Anonymous Coward | more than 12 years ago | (#2513333)

...who make only TWO low-moderated posts in a few minutes. What is that about? One thing is stopping DoS attacks from people who make, say, 10 or more rubbish posts in 5 minutes, but isn't there something off about silencing people who don't think like the majority?

I guess even Slashdot only likes free speech when the speech agrees with it (its regulars, whatever). Ah well, bunch of hypocrites.

Re:why does slashdot temporarily ban people (-1)

Dead Fart Warrior (525970) | more than 12 years ago | (#2513359)

CORRECT!

Hard-core nazi censoring from the people that bring you YRO!

I just got out of my ban and am timing when I return to it.

Re:why does slashdot temporarily ban people (-1, Offtopic)

Anonymous Coward | more than 12 years ago | (#2513371)

Liberals tend to be that way. Conservatives too, now that I think about it.

Wish I had that kind of time... (-1, Troll)

Anonymous Coward | more than 12 years ago | (#2513334)

to waste on useless stuff. I'd probably do more outside stuff than play with a freakin computer though. I don't have to worry, thank god I have a job. Especially in these tough times.

Somebody help me out here (5, Interesting)

rho (6063) | more than 12 years ago | (#2513337)

Quite often I get the feeling that Linux and BSD are doing quite a bit of "me-too"-isms in an attempt to catch up with the mainstream OSes--including MS, Apple and commercial Unixen.

I read this story and wonder if I should still be getting the same feeling -- isn't a VM subsystem mostly a solved problem? Or am I reading this wrong, and this is merely tweaking and specialization?

Since I'm no Alan Cox (I'm closer to Alan Thicke), I can't see the truth of the matter, but I get the feeling that we're doing a lot of walking in a tight circle on the path, while others have already left the forest.

Re:Somebody help me out here (3, Interesting)

DataPath (1111) | more than 12 years ago | (#2513367)

It's hard to say if the VM subsystem has been completely reworked in the MS operating systems. It's all closed source. But I think it's a fair guess that NT and 9x had completely different VM subsystems, and in addition, that the Win2k VM subsystem is likely a complete rework of the NT 4 VM. I guess it's something that happens from time to time... someone thinks of a different way of doing things that changes how everything works together, and it makes something faster, something slower.

Re:Somebody help me out here (1)

rho (6063) | more than 12 years ago | (#2513382)

That makes sense, but it still sounds to me that the bickering between Rik and Andrea's VM is more fundamental.

(which means little, since I only understand one word in three in a technical comparison between the two)

Re:Somebody help me out here (3, Funny)

DataPath (1111) | more than 12 years ago | (#2513422)

Well, things changed enough between the 2.2 series kernels and the 2.4 series kernels that a change in the way of thinking MIGHT make things better. Someone came up with a different way of doing things... The debate between which VM could be compared to the Vi vs. Emacs debate. The "which is better" debate isn't always an objective thing. You can't simply say Emacs is better or Vi is better. The question becomes "what direction do we want to take the kernel." No only that, but Linus was butting in a bit on Alan's territory, which added some heat to the debate. In the middle of a stable tree isn't necessarily the best place to add a completely new VM subsystem. Linus thought it was important enough to add now. Linus'll do anything to squeeze out a few more points on the Infinite Loops Per Second benchmark.

Re:Somebody help me out here (-1)

Guns n' Roses Troll (207208) | more than 12 years ago | (#2513561)

Hey, that's a good uid. If you give me your password, I'll trade you a "slightly experienced" towel I use to wipe myself with after I jerk off.

Re:Somebody help me out here (4, Informative)

Anonymous Coward | more than 12 years ago | (#2513394)

Making a VM subsystem is easy enough. Making a very high performance one that works well in as many cases as possible is not so easy - most OSes have a myriad of tweakable parameters (including Linux /proc/ files and mysterious NT registry keys, for example) to handle all the different special cases - but it's still a bit of a black art, since bizarre things like what sectors on the HD hold the swapped-out memory can make a big difference (personally I have a separate swap harddrive, but that's because I'm running nasty finite element analysis problems).

Also, the VM underlies a host of other bits of the OS, and as they change, so the VM has to change to accomodate them - for example, Linux's zero-copy unix domain sockets, or Linux's VFS layer.

In short, no, VM design is not 100% solved.

Re:Somebody help me out here (4, Interesting)

Ami Ganguli (921) | more than 12 years ago | (#2513409)

Another factor is probably the tremendous range of hardware and workloads that Linux tries to handle. I don't think any other OS attempts to work well on watches and mainframes (and everything inbetween) while using the same code base.

Re:Somebody help me out here (0)

Anonymous Coward | more than 12 years ago | (#2513554)

Actually, the VM subsystem is pretty much gone on watches. Who ever heard of a watch swapping?

Re:Somebody help me out here (2, Interesting)

rho (6063) | more than 12 years ago | (#2513534)

Also, the VM underlies a host of other bits of the OS, and as they change, so the VM has to change to accomodate them - for example, Linux's zero-copy unix domain sockets, or Linux's VFS layer. In short, no, VM design is not 100% solved.

That's interesting. I'm operating on my simplistic, naive notion that a VM is "the hard drive, where you dump pages when you're short on RAM or they get really stale". Thus, in my simple little world, the VM subsystem is affected the most by tweaks to the scheduler that swaps out pages. Is that where the major differences between the two VM schemes lie?

If so, wouldn't it be a worthwhile effort to modularize that part out? (suddenly I see kernel hackers turning white as a sheet, gripping their chair arms in a fit of white-knuckled fear and loathing)

I'm just a twink asking dumb questions...

Re:Somebody help me out here (1)

astrashe (7452) | more than 12 years ago | (#2513404)

I'd like to second this post.

I have a vague sense that BSD and Solaris stand up better than linux under heavy loads, but I'm not sure why, if it's the VM, the scheduler, or the way the various systems interact.

But the thing that I don't understand is the controversy surrounding the VM. I can understand controversey about whether to change horses in the middle of 2.4 -- it seems like there would be legitimate arguments on both sides.

But isn't an optimal VM design something that's been clarified by research, or at least by the experiences of those who have built other kernels?

I guess what I don't understand is why there would be a gap between Solaris and Linux, or BSD and Linux. Can't Linux just do it the BSD way? Is it an inertia thing, a matter of not wanting to break things?

To ask the question another way, my big pet peeve with Windows 2K is that copying a big file (100's of megs) locks up the system. Solaris doesn't do that, Linux doesn't do that. Why does NT do it? Can't they look at the code in the Linux kernel and do something similar? I can't believe that the NT developers don't think it's a problem, I can't believe that they're not very smart guys. So what's the problem?

BSD's missing some things that are hard to do without -- their java support isn't as good, and they don't have the device drivers that Linux has. It seems like it would be easier for linux to pick up what it lacks that BSD has, than the other way around.

Re:Somebody help me out here (0)

Anonymous Coward | more than 12 years ago | (#2513430)

What device is supported in Linux that isn't in FreeBSD? Let's not forget who had working PCMCIA and USB in releases _years_ before Linux.

Re:Somebody help me out here (0)

Anonymous Coward | more than 12 years ago | (#2513485)

any real hardware like quad processor boxes isnt supported in BSD. its a toy OS. even network cards like Xircom and 3COMs give problems in BSD. and 3C990 ethernet cards arent supported at all.

Copying Large Files - Re:Somebody help me out here (1)

TechnoLust (528463) | more than 12 years ago | (#2513501)

Win2k locks up when you copy large files? I haven't seen this problem. I have a P4 system with 256 MB RAM, I have Win2k and Mandrake 8.0 dual boot. I have the ISOs for Mandrake on the Win2k partition and I copied them to another folder with no problem. These are 650 MB files. I believe that when you copy a file 2k reads a chunk and then writes it, then repeats. I wouldn't make sense to try to copy the entire contents into memory then write it. Besides there may not be enough concurrent sectors to store it, so it would have to break it into chuncks anyway. Anyway, I think if this were a widespread problem we would have seen a patch a while back. just my opinion.

Re:Copying Large Files - Re:Somebody help me out h (2)

throx (42621) | more than 12 years ago | (#2513677)

I believe that when you copy a file 2k reads a chunk and then writes it, then repeats.

I'm pretty sure it mmaps the files and does a memcpy(). Would make the most sense because it then just results in direct access to the cache manager's buffers.

From lots of testing, using mmap'd files is about twice as fast as using read/write on Win2k.

big file lockup (2)

jon_c (100593) | more than 12 years ago | (#2513611)

I remember reading about a problem with sblive and via chipsets having timing problems, at one point this caused file corruption as well!

Until SP2 (I believe) Win2k did not natively support ATA100 drives, so many boards either provided their own, or in the case of ATA-RAID controls the drivers we're shown to the system as SCSI. In my experience the native ATA-100 or 3rd party ATA-100 drivers do not perform as well as their SCSI counterparts. long shortly short, if you have a ATA-RAID disk, use the SCSI driver provided from the manufacture... Also if it's a HighPoint(tm) controller don't use the latest version of their drivers, they're is an issue with it where the mouse jumps and the sound card skips.

If you do have a via board, you may want to check out viahardware.com, they have some excellent FAQ's as well as all the latest drivers.

At any rate I am 99% sure it has something to do with your hardware, bios or drivers not Win2k specifically.

late,
-Jon

Re:big file lockup (1)

astrashe (7452) | more than 12 years ago | (#2513660)

I have a Dell that came with W2K preinstalled. I've patched it, but I haven't done any major tweaking. So I've always assumed it was reasonably well configured.

Maybe I'm doing something stupid...

Copying files on Win2k (2)

throx (42621) | more than 12 years ago | (#2513650)

To ask the question another way, my big pet peeve with Windows 2K is that copying a big file (100's of megs) locks up the system.

Interesting. I've copied files around that are several gigabytes in size and suffered no ill effects.

What were you using to copy the files? Command line, Explorer? Define 'locks up the system'?

Re:Somebody help me out here (2, Interesting)

iabervon (1971) | more than 12 years ago | (#2513489)

There's really no way to tell if the Windows VM is bad and is just being left as is, or is being changed, or is good, because you obviously can't run some other VM under the same load (even if you switch between Windows versions, it's a different load because you've got different system implementations and such).

The design of a VM system also depends a lot on the rest of the system: the best VM is one that always has a page swapped in when you need it, and always has it in an acceptable part of memory. But which page is going to be needed next depends on what sorts of programs you're running, and tons of other factors. The VM system is trying to guess these, and there are some known heuristics for guessing, but there's no right solution for VMs in general.

Apple has had a very different scheduling algorithm, which makes the problem totally different, and much easier: the applications not in front can be swapped out.

I believe that, for a commercial UNIX, if you need swap, then you didn't put in enough RAM. If you could buy the system in the first place, you can afford more RAM. If the OS doesn't support enough RAM, get a version that does.

Re:Somebody help me out here (2)

rho (6063) | more than 12 years ago | (#2513597)

I believe that, for a commercial UNIX, if you need swap, then you didn't put in enough RAM. If you could buy the system in the first place, you can afford more RAM. If the OS doesn't support enough RAM, get a version that does.

This I agree with. It was different 5-10 years ago, when 128 megs of RAM would buy you a pretty nice Honda. Now that you get RAM with your Happy Meals, it's quite different.

Following your logic, a VM will mostly be used in a workstation or desktop situation -- server applications aren't a real focal point. The scheduling is fundamentally different between a workstation (say, a hacker's main axe from which he runs Emacs and gdb, or a 3D animator's bench that runs nothing but Maya) and a desktop that is likely to have 4 or 5 apps open at once with constant switching between them.

Isn't this another argument for modularity of the VM, or at least the scheduler? Or am I missing something more fundamental?

Would also be interesting... (2)

forgoil (104808) | more than 12 years ago | (#2513344)

to know how XPs kernel would do, and how the different *BSDs, QNX, whatever you have under your sleave.

Heck, know what would be the best? A pluggable kernel system, where anyone could switch WM. Hmm, hurd? Anyways, it's nice to see 2.4 making progress, but we all kinda guessed that.

After all, if we know what is "best", then people could try to break that and become even better. And who could loose from that?;)

Re:Would also be interesting... (2, Informative)

haruharaharu (443975) | more than 12 years ago | (#2513375)

Heck, know what would be the best? A pluggable kernel system, where anyone could switch WM.

That's been suggested for Linux before, and the general feeling was that that would be so complicated (the memory manager changes touched most files in the kernel) and hard to test, that it would basically be a nightmare.

Re:Would also be interesting... (1)

ethereal (13958) | more than 12 years ago | (#2513455)

That's not flamebait, it's practically from the lips of Alan Cox himself. But don't let that interrupt your rush to mis-moderate...

Re:Would also be interesting... (3, Insightful)

TheAwfulTruth (325623) | more than 12 years ago | (#2513512)

Heh, If I ever said anything like this at work I'd get a "Are you afraid to code" out of my boss...

Systems are getting more complex and demands on them get more complex. People have to plan harder and think harder to keep up. It's time to step up to the plate or go home. Years ago Linux didn't need a VM that worked with 4 way SMP and 2 Gig of ram. Today it does.

Claiming that modularity is (I'm paraphrasing) "too hard" comes off more as a cop-out than a reason. If it's hard, do a better job at it. I don't think anyone is claiming that the VM should only take a weekend to do... They just want it done and done right. The argument FOR modularity put forth above is a solid one. Whatever planning/archeteting/coding/testing and debugging that takes. Just do it[tm].

Re:Would also be interesting... (0)

Anonymous Coward | more than 12 years ago | (#2513380)

Why is this +2? It makes about as much sense as a jonkatz story. Guy must be moderating up his own posts with a duplicate account (like all good karma whores)

Re:Would also be interesting... (0)

Anonymous Coward | more than 12 years ago | (#2513398)

dude he's a Troll with +2 to Post

Did someone think otherwise? (5, Informative)

Anonymous Coward | more than 12 years ago | (#2513376)

I don't think most people really thought the 2.4 VM was a worse performer than 2.2, especially under normal load, and in recent kernels even under high loads.

However, one thing that was not evaluated in this writeup at all was stability, especially on big boxes (as in SMP and >1GB) and heavy workloads. This is where neither VM really seems to be able to hang in there.

I admin seven such boxes that all have 2 or 4 CPUs, and 2 of 4GB of RAM, and during heavy jobs get hit pretty hard. These things run 100% rock solid with 2.2.19, I've achieved uptimes of greated than six months on all boxes simultaneaously. Basically, reboots are for kernel upgraded, nothing more.

With 2.4.x, I'm happy to get a few weeks, and sometimes much less. The machine practically always dies during heavy VM load. It has kept me from upgrading to 2.4 for several months now.

The real kicker, when 2.4 is running correctly, my jobs run as much as 35-50% faster than with 2.2, especially on the 4 CPU server, so I really wish the VM was stable enough to allow me to move.

Anyway, I'm sure it will get there sometime.

BTW, before people write about how they're 2.4 boxes have super long uptimes let me say that I too have some 2.4 based systems that have been up since 2.4.2 was released, but these machines are either single CPU, or SMP but with 512MB of RAM. 2.4 seems to run quite well in this case.

Re:Did someone think otherwise? (2, Interesting)

MentlFlos (7345) | more than 12 years ago | (#2513495)

I have two dual boxes with 1g each in them and they seem to take whatever I throw at them. I have yet to have any panics or what-not. (So you know what kind of loads I'm talking about, one box runs 3 CS servers with 3 HLTV proxies and the other runs mysql, apache (slash), hlstats for the servers and is my desktop box. Both run DNS and RC5 and have 2.4.10 or greater). Nothing too bad, but not idle either). I have no complaints about the kernels yet.

Now getting ext3 in the tree is something I would like :)

Re:Did someone think otherwise? (1, Interesting)

Anonymous Coward | more than 12 years ago | (#2513502)

hmm..i have hard lockups like the guy described with 2.2.19 on a single CPU 733MHz P-III system with 256MB of RAM and 2 Gigs of swap. im running vmware with 5 OSes running simultaneously under high loads and it typically locks up after 3-4 weeks.

Re:Did someone think otherwise? (1, Offtopic)

the_2nd_coming (444906) | more than 12 years ago | (#2513535)

I don't think most people really thought the 2.4 VM was a worse performer than 2.2, especially under normal load, and in recent kernels even under high loads.

well, I would like to say I hate the 2.4 VM. my Suse box was chuging along, and not doing anything at all, I go to the store realy quick to grab some stuff for my wife and when I return the machine is grinding like mad. I had no processes running no application up but the box was slow as hell. the light on the HDD would not turn off at all. I had to do a hard boot even after I tried to kill X since the action was taking forever.

I have used linux for 3 years now and I have never had to hard boot it, at least not in a situation where I didn't mess up the box :-)
3 years and one hard boot is pretty good, but it should not happen at all. I truly think that the 2.4 VM sucks and I am realy hoping that the 2.4.14pre7 VM is the goldenchild......please Linus, for 2.5 make sure the VM works before you put out 2.6, even if it takes you 2 years....oh wait :-)

Re:Did someone think otherwise? (0)

Anonymous Coward | more than 12 years ago | (#2513590)

You should notify either Linus or the LinuxKernelMailingList asap! See
http://slashdot.org/comments.pl?sid=23322&cid=2513 313 [slashdot.org]

why not more than one? (4, Insightful)

Karmageddon (186836) | more than 12 years ago | (#2513385)

when I learned computer science--which I admit was a long time ago, but that means the "gurus" have all had plenty of time to catch up--they taught us that if you obeyed the principles of modularity that you could have more than one implementation of something and use what was appropriate for the particulars of a given situation....

...so why does linux have 1 VM? it seems that 2 of them exist, and the BSD's have more... guys, "gimme a hunk" and "page fault" aren't exactly rocket science anymore, particularly with hardware support... the fact that there is room to make a big deal out of this is the problem, not the VMs.

Linux is not that modular (3, Informative)

Carnage4Life (106069) | more than 12 years ago | (#2513449)

so why does linux have 1 VM? it seems that 2 of them exist, and the BSD's have more... guys, "gimme a hunk" and "page fault" aren't exactly rocket science anymore, particularly with hardware support... the fact that there is room to make a big deal out of this is the problem, not the VMs.

If Linux was a microkernel I'm pretty sure this would be possible but from what I've seen of the Linux kernel code and from some discussions on the linux kernel mailing list [zork.net] , the virtual memory code is too entrenched in various parts of the code to be #ifdefed around with any sort of ease.

Re:why not more than one? (1, Insightful)

Anonymous Coward | more than 12 years ago | (#2513471)

Good Linux VM article (2, Redundant)

MrResistor (120588) | more than 12 years ago | (#2513389)

Here [byte.com] is an excellent article I found linked on rootprompt [rootprompt.org] yesterday that goes into considerable detail about the 2.4 VM (or VMs, as the case may be).

Re:Good Linux VM article (0)

Anonymous Coward | more than 12 years ago | (#2513421)

an excellent article I found linked on rootprompt yesterday

So you're not an avid slashdot [slashdot.org] reader it seems. Shame on you.

We know (3, Informative)

wiredog (43288) | more than 12 years ago | (#2513478)

The link is in this article. [slashdot.org]

VM Trouble and Linux 2.5 (2, Insightful)

PineHall (206441) | more than 12 years ago | (#2513415)

I am glad to see the 2.4 VMs doing so well. I assume that Linus is not at all satisfied with the VM code and that is the reason the 2.5 branch is not started. Hopefully it will start soon when the VM trouble is solved!

This is all well and good (4, Interesting)

duffbeer703 (177751) | more than 12 years ago | (#2513460)

But the fact remains is that this VM holy war should have been resolved in the 2.3 series of kernels.

The number of major problems and architectural changes that are being made to the supposedly 'stable' branch of Linux kernel is really run amok.

I'm sure there's plenty of outrages to come as bad bugs are found in the volume manager and other new elements of 2.4

Re:This is all well and good (1, Insightful)

Anonymous Coward | more than 12 years ago | (#2513598)

Unfortunately, it wasn't resolved. It's only getting close now because Linus made the "outrageous" move of introducing a new one in the middle of a stable cycle. Whether you agreed with that move or not, it's working out brilliantly. Hopefully after this stabilizes a bit, LVM and devfs, both rat's nests of bugs, can be the subjects of the next holy war.

Mod up please!! (0)

Anonymous Coward | more than 12 years ago | (#2513612)

But the fact remains is that this VM holy war should have been resolved in the 2.3 series of kernels.


Hear! Hear! Linux releases are seriously lacking in professionalism.

The Unreal Tournament test (3, Interesting)

Miles (79172) | more than 12 years ago | (#2513538)

Just a possibly interesting data point. I played Unreal Tournament with 2.4.12-ac5 and 2.4.10 (both from Debian). 2.4.10 always seems to work fine for extended periods of Lan play (as both a client and server), whereas the 2.4.12-ac5 choked after a few games--the swap ended up being nearly all used up.
Of course, this was hardly a scientific test, but I think I'll stick to something proven for now.

2.4.13 VM (5, Informative)

sfe_software (220870) | more than 12 years ago | (#2513567)

I can't speak for the differences between the two VM layers in the most recent versions of each, but I went from 2.4.7-2 (RH Roswell Beta stock kernel) to 2.4.13 (+ext3 patch), and I've noticed a serious improvement.

My notebook has 192 megs and 256 meg swap partition. I run Mozilla constantly (which seems to constantly grow in memory usage as the days pass). Prior to the upgrade (2.4.7-2, recompiled without the debugging options RH had on by default), swapping was ungodly slow. Switching between Mozilla and an xterm would literally take a few seconds waiting for the window to draw on the screen. Even switching between tabs in Moz was slow.

Since going to 2.4.13 with ext3 patch, I've noticed a serious improvement in this behavior. Under the same conditions (between 20 and 50 megs swap usage), switching between windows is quite fast. I don't know if it's faster at swapping per se, or if it's just swapping different things (eg, more intelligently deciding what to swap out), but for me it "seems" much faster for day-to-day usage.

I haven't yet tested in a server environment... but for desktop usage, 2.4.13 rocks. Can't wait for 2.4.14, to see if any noticable improvements are added...

Though it will be a non-issue once I add another 128 megs to this machine, it's nice to see such great VM performance under (relatively) low memory conditions.

What a load of BS (0)

Anonymous Coward | more than 12 years ago | (#2513679)

A switch between mozilla and an xterm took SECONDS with 192 MB of RAM?

Next time tell us you had 100+ mozilla windows open.

Re:What a load of BS (3, Informative)

sfe_software (220870) | more than 12 years ago | (#2513792)

I didn't want to get too detailed, but I always have quite a lot of things running. 100 Moz windows? Not quite, but I typically keep anywhere between 5 and 20 open at a given time...

And, anyone who uses Mozilla constantly knows that it doesn't seem to free memory, ever... it grows and grows. The "tabs" feature is great (so technically it's just the one "window" open) but unfortunately closing a tab does not free any memory. I rarely restart Moz because I'd have to then re-open all the pages I had going, etc...

Trust me, run Mozilla for a few days straight, you'll see quite a bit of memory usage (it's at 80 megs right now).

Then there's LICQ (11 megs for such a tiny lil program), KMail (10 megs), 5 terminals, BitchX, Nautilis (using 12 megs, I suppose just showing the desktop)... the list goes on.

So yes, I'm typically using the full 192 megs plus a bit of swap after running for a while, and the new kernel has, IMHO, improved performance under these conditions.

VM ? Bah... (0)

kraf (450958) | more than 12 years ago | (#2513645)

Just buy more memory kids, it's cheap.
I have half a gig and no swap, and everything runs fine and dandy :)

BIOS settings (1, Interesting)

Anonymous Coward | more than 12 years ago | (#2513767)

One thing that is almost impossible to account for in these sorts of "benchmarks" is whether or not the BIOS chipset parameters are properly set. In particular, such settings as RAS, CAS, cache timing, and so on can be critical to stability. I have seen self-appointed know-it-alls post web sites on how to "tweak" the BIOS for ulitmate performance. Usually this involves setting system timing on the very edge with no margin for changes in load and environmental conditions. And usually these so-called "gurus" are not trying to achieve a stable system; they are trying to get the best FPS running Quake or whatnot.

I remember having problems with the 2.2 Linux kernel on occasion. Eventually after much trial and error I went into the BIOS and adjusted the system timing to be a bit slower, allowing system control lines more time to stabalize. My problems went away. Adjusting the BIOS is a black art, and it is often beyond even the best engineers, given that the sparse documentation is usually written in some unfathonable Asian "dialect" of English.

While this comparison of VM systems may be somewhat useful, I have yet to see a study done on a statistically significant sample. I would like to see several hundred different machines compared and have those results analyized. Only then do I believe that truly meaningful conclusions can be reached.

Load More Comments
Slashdot Login

Need an Account?

Forgot your password?