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!

Reiser4 Benchmarks

michael posted more than 11 years ago | from the little-things-mean-a-lot dept.

Linux 414

unmadindu writes "Hans Reiser has benchmarked Reiser4 against ext3 and Reiserfs 3. Reiser4 turns out to be way faster than V3, and for ext3, why don't you check out the results yourself ? Hans Reiser states, "these benchmarks mean to me that our performance is now good enough to ship V4 to users", and he will be probably sending in a patch within the next couple of weeks to be included in the 2.6/2.5 kernel."

cancel ×

414 comments

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

What the shit fuck? (-1)

Fecal Troll Matter (445929) | more than 11 years ago | (#6540236)

THis fp sucks.

The straight truth about the GNAA (-1, Troll)

Anonymous Coward | more than 11 years ago | (#6540392)

The GNAA is a small loose knit group of trolls whose sole purpose is to post retarded shit to various websites. Membership of the group is really irrelevant, but they do have guidelines, which are really just part of their elaborate "troll". Basically, you gotta be a nigger, gay, or both, blah blah. Post an fp for the group and your ub3r l33t, bs ,bs . ...

The cold hard facts about the GNAA
There's nothing gay or black about the GNAA. In fact, the GNAA doesnt have a single gay or black member at all, and most likely never will.

IRC Chat log
(Nws4Turds) pocide
(Nws4Turds) i m teh luv j00!
(koft) yo, st0p b3ing teh gay
(koft) gh3y is teh sux0r
(pocide) i luv u 2 Nws4Turds !, lets felch!
(Nws4Turds) y3s!
(Nws4Turds) pocide
(koft) ph3lch is teh sux0r
(Nws4Turds) i like teh ph3lch
(koft) thats nasty, yall are gay niggers if i ever saw gay niggers
(Nws4Turds) i'm a gay nigger
(koft) stop being t3h gh3y.
(Nws4Turds) actually, i'm a straight honkey

And at this point, Nws4Turds ebraces his heterosexuality, coming out of a "reverse closet" for a brief moment, exposing his inner self. He then feels the need to expound on this idea.
(Nws4Turds) i had sex this morning
(Nws4Turds) it felt good
(Nws4Turds) she came twice

After these statements i was threatened!
(pocide) k0ft: do not even attempt to fr0st
(pocide) not only will YFI but you'd be testin my gangsta and you don't wanna do that, oh no

Following our conversation, my ids picked up a portscan from 24.174.81.26, the address from a user in the channel known as "penisbird".
(pocide) I see your running IIS and exchange. your machine is going down the deep dark anus hole of goatse!
(koft) Damn, i didnt realize that apache and sendmail were part of IIS and exchange... You guys are leeter that i immagined...

Truth: GNAA is a group of wanna be script kiddies who troll on lame message boards like 'Slashdot'
Truth: All GNAA members are white
Truth: None of the GNAA members are gay
Truth: All GNAA members live with their mothers

Don't take my word for it though, check out the lameness for yourself. efnet #GNAA

Reliability (5, Interesting)

prestwich (123353) | more than 11 years ago | (#6540251)

My one concern is reliability and recovery from failure; I've had a few cases where my belief in ReiserFS has been questioned; however I can't get Ext3 to build on larger than 500GB arrays.

At this point I'd happily choose based on reliability/recoverability/stability not raw speed.

Re:Reliability (5, Insightful)

globalar (669767) | more than 11 years ago | (#6540343)

Exactly. RAM, CPU, and storage space are ever increasing. Now we need better ways to organize data, access it, protect it, and back it up.

The fact of the matter is, it is easier to make a fast system than a stable, reliable one.

Re:Reliability (5, Informative)

SaDan (81097) | more than 11 years ago | (#6540368)

ReiserFS has worked pretty good on 1.2TB RAID-5 array I helped build. We're running RedHat 7.2 on a box with a Promise SX6000 RAID controller.

The drivers are crap, and the box dies about every week or so. Haven't lost a single file yet, and we're at 91% filesystem useage (millions of files).

The / filesystem is ext3. It's about 20gigs, and has had to have files restored several times.

I have a lot of confidence in ReiserFS, after seeing the incredible amount of abuse on this one particular machine. I have run ReiserFS for quite a while now (ever since it was part of the kernel) for all of my home systems, and have never had a single issue with those filesystems.

Looking forward to what ReiserFS4 will bring.

Re:Reliability (0)

Anonymous Coward | more than 11 years ago | (#6540371)

If these file systems only break on large sizes like 500 GB, then I have nothing to worry =) I have and endless supply of 3 GB drives =) ReiserFS has been reliable on small drivers, and also, I have always seen ReiserFS's speed as an advantage.

Re:Reliability (5, Interesting)

cvd6262 (180823) | more than 11 years ago | (#6540434)

We had a massive failure of our primary database server while I was out of the country. (Trust me, nothing puts a damper on your day more than having one of your techs call you at midnight from 7,000 miles away.) I blame Reiser. Not because it caused the outage (it was hardware), but because it was so good, it made us a bit lax.

We're just a small grant lab at a university, so it's not like this was a corporate system or anything, and there had been hardware problems before. Given that most of the people are not techies, they did not know how to ssh in and shutdown -r now, so they would just hit the reset button whenever they thought something was wrong and I wasn't around.

Anyway, because of Reiser's journalling, the system would come right back up after a forced reboot. I think that the guys in the lab cut the power a couple of times to many and the hard drive just gave out.

By the way, I just had a tech install a new drive, and Debian base with ssh. I knew the password he would use for root, and I was able to rebuild the entire system and restored 250,000 records in half a day.... From North Africa.

Try that with a non-*nix.

Re:Reliability (5, Funny)

FyRE666 (263011) | more than 11 years ago | (#6540506)

Given that most of the people are not techies, they did not know how to ssh in and shutdown -r now, so they would just hit the reset button whenever they thought something was wrong and I wasn't around.

I've found users doing that to my servers before now. I find that hitting them on the nose with a rolled up newspaper and shouting "No! Bad monkey!" in a stern voice tends to stop this behaviour...

It's really good that filesystems are maturing too (2, Insightful)

192939495969798999 (58312) | more than 11 years ago | (#6540252)

With all of the focus on the latest hardware and graphics, it's good to know that improvements are being made across the board like this. It gives me faith that Moore's law is a long way from failing!

Re:It's really good that filesystems are maturing (1)

smitty_one_each (243267) | more than 11 years ago | (#6540382)

Insightful? [intel.com]
Moore observed an exponential growth in the number of transistors per integrated circuit and predicted that this trend would continue.

I can see where your stated "faith that Moore's law is a long way from failing" is "kind of" in keeping with Moore's law...

Re:It's really good that filesystems are maturing (1)

numonic (640947) | more than 11 years ago | (#6540455)

Not only that, but this 'Han' guy has even achieved getting his 'Reiser' to promote his FS' performance on Slashdot.

Silly apostrophes...

Conversion? (4, Interesting)

avalys (221114) | more than 11 years ago | (#6540255)

Does anyone know if there will be a conversion utility available - i.e, to convert ReiserFS v3 partitions to v4?

Re:Conversion? (3, Informative)

mlg9000 (515199) | more than 11 years ago | (#6540280)

ReiserFS v4 is backward compatible with v3. So if there isn't a conversion tool yet (don't know) you'll still be able use your v3 filesystems along side any new v4 filesystems you might add.

Re:Conversion? (0)

Anonymous Coward | more than 11 years ago | (#6540430)

Try 'cp -Rp'

Re:Conversion? (0)

Anonymous Coward | more than 11 years ago | (#6540324)

They are a LOT different so I really doubt it. It would take way too much work to make it worth it.

ok (1)

HanzoSan (251665) | more than 11 years ago | (#6540258)

how can I install this into Redhat9?

Re:ok (3, Interesting)

ElGuapoGolf (600734) | more than 11 years ago | (#6540308)

You'll probably have to compile it in yourself for now.

RH probably will include it in the future, but probably won't give you the option to install on it without jumping thru major hoops.

RH seems to suffer from a big case of "not-invented-here-itis", and RH users sometimes suffer for it. Not having ReiserFS is one way in which they do.

Re:ok (4, Informative)

silvaran (214334) | more than 11 years ago | (#6540367)

I'm not sure about the exact reasons why they don't support various other filesystems. The default bootup sequence of a RH system uses an initial ramdisk, and actually scans each partition available to find out where they should be mounted (they created nash, NAno SHell, which is just simple support for shell commands as well as fs label scanning). That's why you see the LABEL=/ in your /etc/fstab on a RH system. ResiserFS didn't support filesystem labels until 3.6, so using this setup could mess things up (with 3.5 or older), and justifies your point about having to "jump through hoops" to get reiserfs working. The simplest way I found to move to reiserfs was to change all the LABEL=??? specifications to actual device files, boot from a recovery disk, move everything around while reformatting the partitions as another filesystem, then finally rebooting.

Re:ok (3, Informative)

Anonymous Coward | more than 11 years ago | (#6540445)

that may be true for existing systems, but in the case of running an install from cd, instead of taking the default, add either "reiserfs" or "reiser" (don't remember which - think the "fs" one) to the boot options at the prompt when booting from the cd. it then adds reiserfs to the list of filesysems you can choose to format new filesystems with in the partitioning tool. pre-existing reiser filesystems will be handled correctly if you don't format them.

rh supports reiser just fine - they simply hide the option, probably because they feel ext3 is a safer choice.

Re:ok (1)

AllUsernamesAreGone (688381) | more than 11 years ago | (#6540341)

Simple - install Mandrake.

Re:ok (-1, Troll)

Anonymous Coward | more than 11 years ago | (#6540486)

> how can I install this into Redhat9?
>

Who the fuck cares?

If you want to *DESTORY* your filesystem by
and *ALL* you data all means install/use the
Reiser BullShit filesystems.

Just don't run crying to people who refuse to
have anything to do with the crap Reiser spews
when you get burned by it.

>

Re:ok (0)

Anonymous Coward | more than 11 years ago | (#6540493)

re: how can I install this into Redhat9?

It's been a while, but I have rhl9 running on reiserfs 3.6.

During the graphical install, choose the partitions that you wish to install the stuff on. before you begin, ctrl-alt-F? out and reformat those partitions into reiserfs's. Then install as usual. The install automatically detects the partition type and creates the appropriate initrd image for you.

Don't trust ReiserFS! (-1, Troll)

Anonymous Coward | more than 11 years ago | (#6540268)

I once used ReiserFS since then never trusted it anymore. ReiserFS looses data, corrupts the filesystem, causes no good things. And if something goes wrong then your binary data in first view looks ok but usually is filled with trash. Even files that are not touched, read, written during 'the bad condition' will be trashed.

If you want to use some serious FileSystem for Linux then continue using EXT2/EXT3 or switch to XFS. everything else is simply a risk.

You may think that I may some standart troll or something but then you should ask yourself why there was a need to rewrite ReiserFS at all. Because there was a requirement to get rid of all these known issues.

Re:Don't trust ReiserFS! (1)

Raagshinnah (670749) | more than 11 years ago | (#6540288)

"Because there was a requirement to get rid of all these known issues" then you're admitting that they're gone, so why the hell are you bitching about it? something was wrong, it was fixed. wow...that makes it...bad...guess ill change my 60gb partition to ext2 cause of that!

Re:Don't trust ReiserFS! (-1, Troll)

Anonymous Coward | more than 11 years ago | (#6540396)

Well they re-wrote it to get rid of these known issues. But who can prove that they are really gone ? So it's better to warn the people rather than have them trap into some shitty gay FileSystem.

Re:Don't trust ReiserFS! (0)

Anonymous Coward | more than 11 years ago | (#6540535)

Yes, praise the Lord Jeebus Almighty for our good, wholesome, heterosexual FileSystems! Hallelujah!

wait! (5, Insightful)

BigBadDude (683684) | more than 11 years ago | (#6540269)


hey, I can live with an unstable gnome or Kicq, but a beta filesystem?? no thanks dude!

Re:wait! (0)

Anonymous Coward | more than 11 years ago | (#6540283)

come one!

it works just fine if you backup your data every 2736 seconds

Re:wait! (2)

justsomebody (525308) | more than 11 years ago | (#6540322)

you could if you have spare machine:)

As it goes for me I can do that with no pain. Seeing what r4 provides migrating my things to r4 would be good. But first place for beta fs is spare machine that is just used to crash test this filesystem.

Re:wait! (2, Informative)

quasi_steller (539538) | more than 11 years ago | (#6540327)

Yep. Testing a beta filesystem is something you do on a spare machine that you are not using at the moment. It would be really cool to help test ReiserFS out, but I only have one machine and can't risk losing all of my work!

Re:wait! (0)

Anonymous Coward | more than 11 years ago | (#6540342)

Well then, don't test it. Wait for a stable release. I don't see what the problem is.

Reiser4? Competition? (4, Insightful)

GreyWolf3000 (468618) | more than 11 years ago | (#6540270)

After reiser4, what filesystems are actually decent competition for it? It'd be nice for OSS to claim not only the best web server (apache), best kernel, and best filesystem.

Re:Reiser4? Competition? (5, Funny)

1s44c (552956) | more than 11 years ago | (#6540333)

After reiser4, what filesystems are actually decent competition for it? It'd be nice for OSS to claim not only the best web server (apache), best kernel, and best filesystem.
--

Sick of gentoo zealots throwing plugs in completely unrelated topics? Me too!


Not to mention the best software installation system ( portage ).

Re:Reiser4? Competition? (0)

Anonymous Coward | more than 11 years ago | (#6540337)

Not to troll, but "best" kernel is almost impossible to measure. If you believe Linux is the be-all and end-all of kernels, it's a good sign you know very little about how kernels work.

Re:Reiser4? Competition? (0)

Anonymous Coward | more than 11 years ago | (#6540362)

Besides ext3, there is JFS developed by IBM and XFS developed by SGI. However these are more aimed towards servers.

Re:Reiser4? Competition? (2, Informative)

Doktor Memory (237313) | more than 11 years ago | (#6540406)

Reiser's competition is, in order: SGI XFS and IBM JFS. Oh, and I guess VxFS.

Re:Reiser4? Competition? (1)

mrvis (462390) | more than 11 years ago | (#6540476)

Honestly, when I used BFS it was pure tits.

>It was fast (I don't have numbers, just experience)
>It never lost data
It handled crashes (or pulling the plug accidentally as was more common) without a hiccup
>You could search for things and find them in 1/100th of the time it takes Windows to find things
>All that metadata was cool even though I never got around to using it much.

It's sad that BFS is at least 5 years old and I think it's better than anything else out there.

Honest Portability Question (5, Interesting)

jstockdale (258118) | more than 11 years ago | (#6540275)

I am curious as to whether there are any projects to port Reiser4 to *BSD, particularly FreeBSD 5.x. Does anyone have any thoughts on how difficult a port might be? Can somone more versed in filesystems on *nix enlighten me as to the implimentation differences?

*BSD is dying (-1, Troll)

Anonymous Coward | more than 11 years ago | (#6540316)

It is official -- Netcraft is now confirming: *BSD is dying

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

FreeBSD is the most endangered of them all, having lost 93% of its core developers. The sudden and unpleasant departures of long time FreeBSD developers Jordan Hubbard and Mike Smith only serve to underscore the point more clearly. There can no longer be any doubt: FreeBSD is dying.

Let's keep to the facts and look at the numbers.

OpenBSD leader Theo states that there are 7000 users of OpenBSD. How many users of NetBSD are there? Let's see. The number of OpenBSD versus NetBSD posts on Usenet is roughly in ratio of 5 to 1. Therefore there are about 7000/5 = 1400 NetBSD users. BSD/OS posts on Usenet are about half of the volume of NetBSD posts. Therefore there are about 700 users of BSD/OS. A recent article put FreeBSD at about 80 percent of the *BSD market. Therefore there are (7000+1400+700)*4 = 36400 FreeBSD users. This is consistent with the number of FreeBSD Usenet posts.

Due to the troubles of Walnut Creek, abysmal sales and so on, FreeBSD went out of business and was taken over by BSDI who sell another troubled OS. Now BSDI is also dead, its corpse turned over to yet another charnel house.

All major surveys show that *BSD has steadily declined in market share. *BSD is very sick and its long term survival prospects are very dim. If *BSD is to survive at all it will be among OS dilettante dabblers. *BSD continues to decay. Nothing short of a miracle could save it at this point in time. For all practical purposes, *BSD is dead.

Fact: *BSD is dying

Re:*BSD is dying (0)

Anonymous Coward | more than 11 years ago | (#6540494)

Netcraft says there are 2 million websites using freebsd.

Could you do the math for that too.

Re:*BSD is dying (-1, Flamebait)

Anonymous Coward | more than 11 years ago | (#6540507)

I hope somebody goes postal (or Columbine) over you, and people like you. Have fun.

Re:Honest Portability Question (1, Informative)

Kaladis Nefarian (655671) | more than 11 years ago | (#6540357)

None that I know of. However if you're just looking for a journalled filesystem for BSD, there is an effort to port JFS to FreeBSD, however their page has "moved". Used to be here [sourceforge.net] .

Re:Honest Portability Question (0)

Anonymous Coward | more than 11 years ago | (#6540359)

Well, the powers who be in BSD think that any sort of journaling is a crude band-aid slapped on by foolish Linux users and their UFS 'Soft Updates' are the cure for the worlds' ills, so they won't be helping you.

Re:Honest Portability Question (1)

Just Some Guy (3352) | more than 11 years ago | (#6540499)

One of the ex-powers who be just forked his own BSD. Feel free to do the same if it's important to you.

Re:Honest Portability Question (0)

Anonymous Coward | more than 11 years ago | (#6540436)

Pretty difficult, seeing as how ResierFS is GPL'd and thus can't be included with any of the BSD kernels.

The Paul Reiser filesystem... (2, Funny)

Anonymous Coward | more than 11 years ago | (#6540278)

...is mostly funny, but is too much of a company filesystem to trust completely.

Computer's names translation (5, Informative)

vadim_t (324782) | more than 11 years ago | (#6540289)

In case anybody cares, "strelka" means "arrow", and "belca" means "squirrel"

Wonder what naming system they're using. I use names from Alice in Wonderland.

Re:Computer's names translation (5, Informative)

kliklik (322798) | more than 11 years ago | (#6540369)

Strelka and Belka are the names of the dogs that were sent into space.

Quote from first google search result: "Belka("Squirrel")and Strelka("Little Arrow") were launched into space on board Sputnik 5 on August 19, 1960. They were accompanied on their historic flight by 40 mice, 2 rats and a number of plants. Belka and Strelka were safely recovered after spending a day in orbit. Strelka eventually gave birth to a litter of 6 healthy puppies, one of which was given to President Kennedy as a gift."

Re:Computer's names translation (0)

Anonymous Coward | more than 11 years ago | (#6540508)

Maybe Hans will switch to astronauts' names once they run out of animals. You know, Gagarin, Aldrin, Armstrong... once they run out of the oldtimers, they can just start calling the machines toast1, toast2, toast3...

Re:Computer's names translation (1)

AntiOrganic (650691) | more than 11 years ago | (#6540523)

So what means "moose"?

So how much better is this really? (2, Insightful)

Man In Black (11263) | more than 11 years ago | (#6540293)

All these numbers are nice, but I can't make heads or tails of them. Since these are times, I assume lower numbers are better? If so, they why are they usually in red in the report?

Would this increase the speed of a normal system by any noticable amount? Is it worth my time to switch over my EXT3 filesystem to reiser4? Are there programs that can perform the filesystem change for me?

Re:So how much better is this really? (3, Informative)

gumpish (682245) | more than 11 years ago | (#6540385)

Since these are times, I assume lower numbers are better? If so, they why are they usually in red in the report?

The columns marked B/A and C/A are the performance ratios of ext3 data journaling and ext3 to reiserV4 respectively. A ratio greater than 1 means more time was needed for the operation than reiserV4 while a ratio less than 1 means faster performance.

Re:So how much better is this really? (1)

|<amikaze (155975) | more than 11 years ago | (#6540559)

Ahh... Thank you very much :). That had me pretty confused too.

Re:So how much better is this really? (0)

Anonymous Coward | more than 11 years ago | (#6540398)

Notice the convention they are using
They start with a single quantity (A) and devide the second quantity by it (ie B/A)
so if you see a score over 1 then that result is actually slower than the original, less than 1 shows a (100-*value*) percent increase in performance

I don't understand the statistics (4, Insightful)

0x0d0a (568518) | more than 11 years ago | (#6540298)

The statistics on that page are measured in seconds, no? So larger numbers are worse.

The comparisons are done with [foreign filesystem] divided by reiser4.

One would think that numbers greater than one, where the foreign filesystem has a long running time and reiser4 a short one, would be the ones that benefit reiser4.

Yet the numbers *less* than one are green, where Hans says reiser4 is considered better.

What's going on?

(Incidently, after having a friend lose a filesystem to buggy reiser code, I'm a bit inclined to wait until people have *seriously* hammered on this).

Re:I don't understand the statistics (1)

BabyDave (575083) | more than 11 years ago | (#6540351)

Part way through the document, he switches to ReiserV4/ReiserV3, in which case numbers less than one are better.

Oh, and while I remember:

I'm red/green colour-blind you insensitive clod!

Re:I don't understand the statistics (3, Informative)

silvaran (214334) | more than 11 years ago | (#6540401)

A. reiser4
B. ext3 data journalling
C. ext3


That's how the filesystems are lettered. In the column headers, you see this:

A B/A C/A

So it looks like the first column is the actual time for reiser4 (A), the second column is the ratio between ext3-j (B) and reiser4 (A) which is B divided by A, and the third is ext3 divided by reiser4. So if the number is > 1 (red), it means reiser4 took less time and might be "better". If the number is 0 (green) it means reiser took MORE time.

I think.

Re:I don't understand the statistics (1)

Feztaa (633745) | more than 11 years ago | (#6540582)

That's what I thought, too, but what's with the color choices? Normally, red means bad and green means good. But in this case, it's the opposite.

Or am I missing something?

Bugs (4, Insightful)

Kaladis Nefarian (655671) | more than 11 years ago | (#6540306)

While great, this announcement/benchmark/statement does not mean that ReiserFS V4 is ready for production use, just that it is fast. It needs a lot more bug testing before then, so don't rush out and mass-convert to V4 just yet! See here [google.com] for the full thread, rather than just the first post...

Re:Bugs (1)

Anonymous Coward | more than 11 years ago | (#6540361)

Thanks! You truly are a master of the obvious [sphosting.com] !

Ummm... (-1, Flamebait)

Anonymous Coward | more than 11 years ago | (#6540314)

Is it just me are these numbers meaninless?

Summary:
(BAD)Reiser takes considerable more CPU time.

(NEGLIGABLE)Everything else is a little slower but without them telling me what the measurements for their time numbers it's moot.

picoseconds? milliseconds? Who knows?

What kind of machine? What the hell is a "belka/strelka"? Are these the names of the machines?

Why only 256MB of RAM?

Come on, the test was probably run on a Pentium 133. Why should I assume otherwise?

I'll continue to use ext3 until I see some real stats. These might be it but I need more info than what they gave. :(

Re:Ummm... (0)

Anonymous Coward | more than 11 years ago | (#6540346)

In addition what apps is he running in the background? Is this while he's ripping and encoding CDs?

Comparison (0)

Anonymous Coward | more than 11 years ago | (#6540321)

How does this compare against say AIX or HPUX's implementation of journaled filesystems?

Re:Comparison (3, Funny)

Anonymous Coward | more than 11 years ago | (#6540348)

Like "Three Dogs Playing Poker" to the Mona Lisa.

Which to choose for DBs? (4, Interesting)

Openadvocate (573093) | more than 11 years ago | (#6540329)

I realise that it is a bit early to adopt V4, but stable issues aside, which filesystem would YOU choose to for database volumes for fx. Oracle or MySQL?

Re:Which to choose for DBs? (0, Insightful)

Anonymous Coward | more than 11 years ago | (#6540393)

Why the hell would you want to place Oracle data files on a journalled filesystem? Get a clue!

Re:Which to choose for DBs? (1)

GameMaster (148118) | more than 11 years ago | (#6540553)

You know, I think he might have actually been asking the question because he didn't know the answer. I know this might be a shock to you, but some people may not have learned the exact same things as you have and that doesn't make them deserve your attitude.

Why is this "Insightful"? Its a one line comment with a derogatory statement and no actual content.

Re:Which to choose for DBs? (0, Offtopic)

OneEyedApe (610059) | more than 11 years ago | (#6540604)

This, good sir, is "random moderation" in action.

Re:Which to choose for DBs? (0)

Anonymous Coward | more than 11 years ago | (#6540599)

So how about explaining why you don't want to place oracle data on top of a journalled filesystem? Or anybody else for that matter. (I've never heard this before, but I'm not a dba either.)

Re:Which to choose for DBs? (0)

Anonymous Coward | more than 11 years ago | (#6540489)

I have used both ext3 and Reiser3.6 for heavily hit Oracle databases. No problems to report with either.

XFS? (4, Interesting)

leoboiko (462141) | more than 11 years ago | (#6540352)

How does it compare against everyone's favorite, XFS?

Re:It may be interesting to know... (2, Informative)

botzi (673768) | more than 11 years ago | (#6540470)

..but however remember that both have different strong points:

XFS is especially good in dealing with large(and when I say large I mean *LARGE*) files, and IIRC, the all idea behind the Reiser filesystem is to deal with small data objects.

Anyway, it'd be interesting to see such a benchmark as XFS has the reputation of one of the best(the best???) fs to be used with high hard-disk I/O-s and even higher system loads.....

Re:XFS? (2, Insightful)

lvdrproject (626577) | more than 11 years ago | (#6540478)

Yeah, really. Currently i'm a big XFS fan, but i've heard a lot of great things about Reiser. That said, i'm not going to switch over to Reiser until i see some good information that suggests that it's worth it. What the advantages are, what the disadvantages are, what happens if you do this or that, numbers about speed or whatever, et cetera, et cetera. I've seen a few good comparisons, but they're either all numbers, or all conjecture. :/

I'd also like to see it compared to JFS and maybe ext2 (if not just for reference).

but will it make it (4, Interesting)

DemiKnute (237008) | more than 11 years ago | (#6540358)

So he's submitting it to 2.6, but what are the chances it'll get submitted? Isn't this what caused all of Reiser's bitching a couple of years ago? He waited to long to get RFS into the kernel and ran into the feature freeze, and then pitched a hissy fit.

Filesystems for the laptop user? (4, Interesting)

niko9 (315647) | more than 11 years ago | (#6540370)

Anybody know what, if any, features are being added for the laptop user? Last time a checked, journaled filesystems, like ext3, were generally a no-no if you wanted you battery to last.

Maybe a filesystem just for laptop/tablet pc users?

Re:Filesystems for the laptop user? (0)

Anonymous Coward | more than 11 years ago | (#6540529)

Anybody know what, if any, features are being added for the laptop user? Last time a checked, journaled filesystems, like ext3, were generally a no-no if you wanted you battery to last.

ext3 can store it journal outside of the filesystem
("mke2fs -O journal_dev [external-journal]", or "tune2fs -J device=[external-journal]"). If you put the journal on external solid-state media, your hard drive could spin down even while the journal is being used (I don't know how this would affect reliability).

Reiser4 has wandering logs, which will result in less disk seeking, and should help battery life (at least slightly).

Encryption will be a good feature for laptops. It's not in reiser4 yet, but a plugin has been talked about.

unfair - but true for me at least in the past (3, Funny)

fiddlesticks (457600) | more than 11 years ago | (#6540372)

DELETE (time in secs to perform action)

40.13(R4) 0.797 (ext3 journal) 0.837 (ext3)

woo-hoo! now it corrupts my data even quicker :(

Re:unfair - but true for me at least in the past (0)

Anonymous Coward | more than 11 years ago | (#6540439)

Eh... corruption inferrs that the data is still there but wrong. Deleting means it isn't there. So Reiser FS would probably be better at those "rm -rf" moments.

Re:unfair - but true for me at least in the past (0)

Anonymous Coward | more than 11 years ago | (#6540495)

Actually, worse.

Re:unfair - but true for me at least in the past (1)

khuber (5664) | more than 11 years ago | (#6540446)

By quicker you must mean slower.

Re:unfair - but true for me at least in the past (1)

khuber (5664) | more than 11 years ago | (#6540460)

Oh nevermind, I've gone insane again.

Which is best? (3, Interesting)

Dodge This (654497) | more than 11 years ago | (#6540373)

OK so there seems to have been a lot of Reiser flaming going on here, so what would people recommend? Taking into account Speed, Reliability and Compatability.

I know a lot of people will pull their hair out when they hear this, but: Speed is my primary concern. On long compiles of new programs or kernels for example the speed difference on a good FS can be important. I'm not saying that I'm willing to have a FS that corrupts every last file and directory, only that given two FSs which both have seemingly similar stability I would prefer the speed boost.

I have tried one or two of the FSs but I haven't used them for any length of time to be able to compare one against another.

I'm going to disagree with you (1)

lamontg (121211) | more than 11 years ago | (#6540527)

When you have a thousand machines, if you're constantly losing filesystems then you spend way too much SA time rebuilding them.

of course if you've got a cluster of 100 machines that are all doing the same things and you can even make the app go 5% faster by a different filesystem, that can be a saving of $20,000 or so.

"but you won't need to fsck" (2, Informative)

Anonymous Coward | more than 11 years ago | (#6540381)

In this [helsinki.fi] note, Hans Reiser clearly states his position: you trade off filesystem metadata performance against data integrity.

Once you realize that this maintains your filesystem structure but turns your files into Swiss cheese (this happened to me several times) you'll switch to ext3 or XFS.

Since reiserfs continuously rebalances the block tree, files that are only open for reading can be trashed by having a block exchanged with the last file written before a crash.

Hans is recklessly pursuing optimization of one aspect of filesystem performance. I honestly believe DARPA should reconsider funding his current track of work.

Re:"but you won't need to fsck" (1)

IamTheRealMike (537420) | more than 11 years ago | (#6540598)

Once you realize that this maintains your filesystem structure but turns your files into Swiss cheese (this happened to me several times) you'll switch to ext3 or XFS.

That note just says what is common knowledge already, that if you want an actual crash proof system you need data journalling. I know very, very few people who use this, because it effectively means writing everything twice, which kills performance. That doesn't reflect upon ReiserFS at all, many filing systems don't support data journalling because it is actually quite a niche feature.

It's also wrong to assume that data journalling == no problems in the event of a crash. That's not the way it works.

Hans is recklessly pursuing optimization of one aspect of filesystem performance. I honestly believe DARPA should reconsider funding his current track of work.

I think you should wait and see how it actually behaves in the real world, before slamming him or his work (as an anonymous cowards, I might add).

Nullo! (-1, Troll)

Anonymous Coward | more than 11 years ago | (#6540402)

The room was packed full of naked 14 year old boys. All of them had a number and were waiting their turn. After the boys had stripped naked and had put their clothing into lockers, they walked into the next room. In this room were a bunch of male nurses, who, unbeknownst to the boy, were in fact eunuchs. The nurses took the boys' vital signs to make sure that they were all fit and able to use the Machine. Once they were sure the boy could handle it, a nurse would use a spray-type injector to give each boy a shot. Within 30 seconds the boy's penis would become rock hard. The boy would not loose his erection until the drug began to wear off 8 to 9 hours later.

Once the boy had received his shot he would be taken into the next room to take a number and wait for his number to be called to go into the Machine Room.

As the boy waits, he will notice that the room he is in is rather hot. This room is kept at a higher temp so a boy's balls will become hot and hang lower in the scrotum.

Cody Miller had pulled the number 14. He thought that was kind of cool seeing that he was 14 years old. Just like the old style military draft, Cody had to register on his 14th birthday. 8 out of 10 boys all over the world would get picked to use the Machine, to help keep the birth rate down. Cody thought he was going to make it and not get called, but his luck ran out the day before his 15th birthday.

If he had made his 15th birthday, he would not of been called to use the Machine unless he committed a high crime and sentenced to use the Machine as part of his punishment.

Cody had arrived just after the clinic had opened up and he walked in. A eunuch volunteer talked with Cody and told him what was going to happen to him that day and what he needed to do. Cody, just like 99% of all boys, already knew what was going to happen and how it happened. He had spent the night at Keith's house. Keith was his very best friend who had to use the Machine just 2 days after his own 14th birthday. Keith had let Cody watch the DVD recording of his use of the Machine.

The one thing that Keith did not know was that Cody had sneaked into the bathroom after bedtime and jerked off to a powerful orgasm while thinking of what he had watched on the wide screen TV. Now that is was his turn to use the Machine, Cody was not turned on at all. As a matter of fact he was on the edge of tears. When Cody had taken his ticket with the number 14 on it, he had looked up to see that they were working on boy number 89.

Cody had sat for a while in one of the chairs and had checked out the other 14 year old boys that were in the waiting room with him. Cody was thankful that all of the boys had a hard penis, because Cody knew he would of had a hard cock even without the shot, checking out all the hot looking boys.

Once about every 10 to 15 minutes a nice-sounding voice would call the next number and a door would slide open. The boy with the called number would walk through the door and the door would slide closed faster than it had opened.

As his number got closer to being called, Cody got more jittery. Finally, he could not sit any longer and he walked all around the room. The number 13 was called and Cody saw a very cute blond boy stand up. The blond boy had a bead of pre-cum hanging off of the tip of his 7-inch long, uncut dick and it leaked down his shaft and dripped off of his balls, landing on his foot as he walked to the open door. Cody stood there knowing he only had a short time left and had to put extra into his mental state to keep from crying.

The voice then said Cody's number and the door slid open. It took several seconds for Cody to get his feet to move. He walked into the next room and felt the wind of the door closing on his bare butt cheeks.

A eunuch technician was waiting for Cody. He took Cody's number and led him to a small booth. He had Cody sit down on a seat, and then used a hand to guide Cody's low hanging balls into a hole in the seat. He then guided Cody's hard 5-inch penis into a different hole. Once the dick and balls were in their holes, the tech pulled a small lever.

Cody felt some kind of band squeeze tightly around the base of his penis and close to his body around his balls. The tech told Cody to give the other lever a pull to start the Machine.

Cody reached out and stared at his hand. It was shaking. He stared at it.

The technician watched him, tapping his foot.

Then he swallowed hard and pulled.

He then watched a screen of the inside of the Machine. He saw a wheel with 19 black, 19 red, and 2 green spaces on it, start to spin. At the same time a slick tube closed softly onto his penis and started to masturbate him.

Cody could not believe the great feeling the Machine was giving his dick. The tube on his dick was warm and slippery as it slid up and down his shaft. A feather like object was raised up and started to tickle his balls. Cody was moaning from the great feelings he was having when he felt a small slick object enter his ass. The mini dildo started to push in and out of Cody's ass, and it added to the good feelings the Machine was giving him.

Cody enjoyed the sexual feelings coursing through his body, but was fighting his approaching orgasm. He thought of the pain that was soon to be coming. He knew that his sperm would choose his type of castration.

He remembered reading that if his first blast of semen hit a red space he would be loose his testicles. If the semen landed on black, he would loose his penis, and if it hit one of the two green spaces he would loose both penis and balls - a full nullo.

Another feather was now tickling one ball, while the first feather tickled the other one. The tube over his penis, warmed up a bit more, had started to vibrate. Cody felt his balls try to pull up, but the band kept them down. The orgasm was fast approaching and he could not fight it any longer. He felt the glands inside his body contract and expel fluids. These fluids mixed together to make semen.

Another contraction and a bead of clear fluid came out of the tip of his penis and clung to the tip.

Cody yelled out in orgasmic bliss, as there was an even harder and more powerful contraction. This one caused his penis to lift upwards in a jerking motion, and a large white rope of teen cum shot out of his piss slit.

His eyes became wide as everything went into slow motion. He watched the cum blob leave his penis and squirt towards the spinning colored wheel. It seemed to hang in the air for a bit, then travel on, towards the wheel ... slowly.

Cody's heart stopped beating for one beat when he thought his cum was about to land on one of the green spaces. His dick gave another twitch and launched another cum rope, just as the first spurt landed on a red space.

Several things happened at once when his sperm landed on the wheel:

The first being a third spurt of cum launched out of Cody's cock. The second thing to happen was the band that was around his penis was cut off and fell free with a stinging pain. Then the band around his balls became extremely and painfully tight.

A fourth spurt was leaving the piss hole at the tip of Cody's hard penis just as a super heated and sharp blade sliced his balls off right below were the band was located. He screamed in pain as the knife cut away his jewels, his teen body pumping harder in its last real ejaculation of sperm-laden cum.

Cody sat there for another minute before the tech came back and helped him to stand up. He gave Cody a shot to help him with the pain and then helped him back to the locker room so he could get dressed again.

After Cody was dressed he left the locker room and stopped in an office to talk to a man about his new ID card. The man took his picture and made a new ID card for Cody. When he gave the card back to Cody, he also handed Cody a small bottle of pain pills.

As Cody walked home, he thought of calling Keith so they could talk about what happened to them, and Keith could tell Cody what it was like to have his penis sliced off during orgasm.

The End

ReiserFS == BrokenFS (1, Informative)

Anonymous Coward | more than 11 years ago | (#6540405)

I once used ReiserFS since then never trusted it anymore. ReiserFS looses data, corrupts the filesystem, causes no good things. And if something goes wrong then your binary data in first view looks ok but usually is filled with trash. Even files that are not touched, read, written during 'the bad condition' will be trashed.

If you want to use some serious FileSystem for Linux then continue using EXT2/EXT3 or switch to XFS. everything else is simply a risk.

You may think that I may some standart troll or something but then you should ask yourself why there was a need to rewrite ReiserFS at all. Because there was a requirement to get rid of all these known issues.

About reiser4 (5, Informative)

Fefe (6964) | more than 11 years ago | (#6540411)

I attended Hans' presentation at Linuxtag.

Basically, reiser4 is optimized for the case where you unpack a large tarball, say the Linux kernel, and have enough memory to hold it all in cache, which is true for most of us these days. reiser4 will then choose the optimal disk layout for these files and flush them to disk.

Hans also has aspects of a log structured file system in reiser4, which means you don't write to the file, you write to a log file which basically encompasses the whole disk. The up side is that you mostly write linearly, the down side is that the files get badly fragmented if they are updated at all. Most files are not updated, just written once at installation of the package. The files that are updated frequently tend to be source code from CVS, which are small enough to fit in memory completely and have reiser4 choose an optimal disk layout again.

The case where this model completely sucks is the case where you update many portions of a large file. For example, running an SQL database with files on a reiser4 file system as backend, or maybe a DNS server with DDNS, or a berkeley db backend for Postfix or qmail to keep the SMTP AUTH users or something. Also, log files will probably be badly fragmented.

Hans proposes to have something like a transparent defragmenter running in the background, which he calls "repacker". This would run in the kernel space, as part of the file system, and defragment badly fragmented files that are accessed frequently. This would solve most of the down sides of his approach, but this repacker is not finished yet.

My personal view of reiser4 is: it looks like it is optimized to perform well in benchmarks. It tries to be fastest for updating databases, but buys the performance by being slower when reading the data afterwards. The critical question is whether the repacker can alleviate these concerns, and as long as it is not finished, reiser4 is basically out of the question except for a little testing here and there. I reckon reiser4 would be a great filesystem for keeping your mozilla and gcc CVS checkout handy. But until the repacker is done, I will not even use it for testing, because the repacker really is the crucial component that makes or breaks this.

By the way: my previous experiences with reiserfs were less than stellar. Some people call it shredderfs instead. The main complaint with reiserfs is and always was that the fsck is not nearly as trustworthy or stable as the one from ext2/ext3. So even if I use reiserfs at all, it's only for data I can afford to lose completely, like my CVS checkouts or the squid cache directories or something like that.

The benchmarks do look good though, and I am glad that at least someone is still trying major innovations in this area. Since most Unix vendors or divisions are no longer profit centers, file system innovations have largely stalled or moved to specialized companies who regard them as proprietary (Veritas) instead of releasing them as free software like IBM and SGI did.

Re:About reiser4 (0)

Anonymous Coward | more than 11 years ago | (#6540560)

Thanks for your well-written, thought-out post. Everyone else seems to express their one-sided opinion, but you've presented a balanced and fact-based comment.

Re:About reiser4 (0)

Anonymous Coward | more than 11 years ago | (#6540583)

>The benchmarks do look good though, and I am glad that at least someone is still trying major innovations in this area. Since most Unix vendors or divisions are no longer profit centers, file system innovations have largely stalled or moved to specialized companies who regard them as proprietary (Veritas) instead of releasing them as free software like IBM and SGI did.
>
>

You sir, are an utter and complete *MORON*

Re:About reiser4 (0)

Anonymous Coward | more than 11 years ago | (#6540602)

If this is true, then it is uber-funny.

"Hans proposes to have something like a transparent defragmenter running in the background, which he calls "repacker". This would run in the kernel space, as part of the file system, and defragment badly fragmented files that are accessed frequently. This would solve most of the down sides of his approach, but this repacker is not finished yet."

First, let's add some extra shit in kernel space.

Second, the 'defragmenter' of those log-structured fs are always the problem. Looks great on the paper, looks a bit worse when coding, and eat I/O at production.

What I find funny is that LSFs were supposed to be the "file system for the 90's" (in late 80's) http://citeseer.nj.nec.com/rosenblum91design.html. There was a LSF in stock FreeBSD (dropped because it wasn't really better than true and tried FFS with soft update at the end). "Plus ca change, plus c'est la meme chose"...

As the original LFS conceptor admit themselves, LFS is great in micro-benchmark. No wonder reiser4 is great at benchmark, and wait for other problems to be fixed by the cleaner. Yeah...

One major positive point about FS with 'cleaners/garbage collectors' is that they are usually easy to enlarge shrink. This can be a real plus when dealing with raid paritions...

ext2? (3, Interesting)

Coneasfast (690509) | more than 11 years ago | (#6540412)

I know ext2 isn't a journal fs, but it would still be interesting to see a direct comparison again reiser4.

Warning (-1, Flamebait)

Anonymous Coward | more than 11 years ago | (#6540428)

WARNING!!!!!!

ReiserFilesystem trashes your data!

WARNING!!!!!!

Re:Warning (1)

rdean400 (322321) | more than 11 years ago | (#6540544)

I've been running ReiserFS for 36 months without issue. Can't say the same for JFS, XFS, ext2, or ext3.

Re:Warning (0)

Anonymous Coward | more than 11 years ago | (#6540603)

That may be true, but your statement would still be true even if you never tried any of the other filesystems...

If I'm reading these right.... (4, Insightful)

Anonymous Coward | more than 11 years ago | (#6540433)

It's still not time to swap it for ext3 for general use.

The first table with the mixed file sizes is the most compelling. The fact that reiser4's Create and Copy times are less than a third of the ext3s in real_time is impressive.

But the fact that the CPU consumption on Read is double that for R4 as it is for ext3 is a serious problem. On a 1.3 Ghz machine saturating a generic UDMA 100 60G bus on RH 9.0 it's about 10% of the CPU, so the home user might not care. For a system capable of delivering serious data (like a 4 drive, 15k rpm SCSI RAID array @~3 times the read throughput) going from 30% CPU to 60% CPU usage is a definite problem. Even with a 2.6 Ghz cpu it would still move from chewing up 15% to 30%. I know these numbers don't scale exactly, but they could in fact scale ugly depending on how much CPU is dedicated to communicating with the hardware and how much is in fiddling with the filesystem. My production boxes spend > 80% of their disk activity reading, so I'm not yet inspired to go out and spend the time running benchmarks on highperf. systems just yet.

Nevertheless, I always admire it when a new version of software comes out and it's noticeably faster than the old

Real comparison? (3, Insightful)

Quixote (154172) | more than 11 years ago | (#6540440)

I'd like to see someone (i.e., not me) do a comparison of ReiserV4 with other heavy hitters like XFS [sgi.com] and JFS [ibm.com]

That would be interesting.

In other news... (4, Interesting)

wirelessbuzzers (552513) | more than 11 years ago | (#6540512)

Apple benchmarked their new G6 processor against the latest 10 GHz Pentium V. They say that despite its lower clock speed, it runs their suite of PhotoShop 8 filters almost four time faster than the Pentium.

Seriously, Hans Reiser is benchmarking his own file system, and he's using benchmarks that make his system look good. Like the SpriteLFS, his filesystem has a log structure for sequential writing, which makes it look really good in tests like he performed where you write the files once.

Compare a database load, where you write small chunks of big files all the time. Without the repacker (like the cleaner in LFS), the disk becomes horribly fragmented. With the repacker, you have to include the slowdown of this background process defragging your hard disk. Ick.

I'll trust his benchmarks when he presents a final, stable release, with the repacker on, and tests it under workloads such as would be encountered on a server. I might use it on my homebox even if it sucks on a server, but it would be nice to know that he considers his structure's impact on other workloads.

linus (2, Interesting)

austad (22163) | more than 11 years ago | (#6540516)

Didn't linus say no more new features at this point? Didn't Reiser try this same damn thing last time, fighting with the kernel people to get his stuff in after the feature freeze?

ReiserFS recovery tools? (0)

Anonymous Coward | more than 11 years ago | (#6540526)

ReiserFS is very fast at writing large numbers sub-blocksize files, granted, but has anyone out there ever gotten its filesystem recovery tools to run 1) faster than ~1 hour/GB/1000BogoMIPS and 2) without crashing near the very end? In other words, in the (ostensibly unlikely) event that ReiserFS screws up and you do have to check its consistency, is there any way to do it? My experience has been to the contrary several times now, and I end up having to rebuild the entire FS. Fortunately I'm fanatical about keeping backups, so I can afford to do this; I certainly wouldn't recommend it to anyone who wants to maintain filesystem integrity, but the speed is breathtaking.
Load More Comments
Slashdot Login

Need an Account?

Forgot your password?