Slashdot Mirror
ZFS, the Last Word in File Systems?
guigouz writes "Sun is carrying a feature story about its new ZFS File System - ZFS, the dynamic new file system in Sun's Solaris 10 Operating System (Solaris OS), will make you forget everything you thought you knew about file systems. ZFS will be available on all Solaris 10 OS-supported platforms, and all existing applications will run with it. Moreover, ZFS complements Sun's storage management portfolio, including the Sun StorEdge QFS software, which is ideal for sharing business data."
From the article:
Unlimited scalability
As the world's first 128-bit file system, ZFS offers 16 billion billion times the capacity of 32- or 64-bit systems.
Microsoft immediately countered by saying WinFS will now support "twelveteen million billion times" as much storage as Sun's ZFS, and is "a bazillion times" more secure.
When reached for comment, Sun CEO Scott McNealy replied "neener neener". Microsoft CEO Steve Ballmer responded by putting gum in Sun President Jonathan Schwartz's hair.
And it looks like it's going to be opensourced along with most of Solaris 10!
Presumably a 32 bit machine will be able to handle a 128 bit file system, in the same way as Solaris 10 is currently destined for (at most) 64 bits.
Of course ZFS is the last word in file systems. I mean, what can come after zed?
"Have you ever thought about just turning off the TV, sitting down with your kids, and hitting them?"
It never *is* the last word in file systems.
1) Even Sun has succumbed to recursive acronyms, now.
2) Is it just me, or is the post surprisingly bereft of unique details? I mean, integration with all existing applications is rather assumed, given that it's a file system and all...
It's only an insult if it's not true.
is that even a word? i really hate marketing people
Logically, the next question is if ZFS' 128 bits is enough. According to Bonwick, it has to be. "Populating 128-bit file systems would exceed the quantum limits of earth-based storage. You couldn't fill a 128-bit storage pool without boiling the oceans."
So, what was the point of creating a 128-bit filesystem?
-1, Marketing Hype.
*Yawn*
... it took them long enough.
Perhaps they had to rewrite an LVM from scratch in order to opensource it?
This is truly great, so will this be part of it being open sourced the Sun OS?
Having a global pool does lessen maintenance/support, but what method are they using to place data on the disks?
Frequently accessed data needs to be spread out on all the disks for the fastest access, so does that mean Sun has FS files/tables that track usage and repositions data based on that?
IBM has ZFS on their z/OS Unix Systems Services (POSIX interfaces on z/OS) component. ZFS was developed to provide improvements over the HFS (Hierarchical File System) that they ship with the OS.
what they dont tell you is it runs linux!!! (sorry, it just seemed funny i'm going to post anon lol)
Nah, the ultimate filesystem has to be xyzzyfs! Your data magically appears... :-)
Enable 3D printed prosthetics!
File Systems work particularly well in certain application environments. A good example being ReiserFS. The only way this could be the last word is if somehow it was the best for all the current known ways in which computing can be applied and that no more will be found. This would be like being a FileSystem yes man. At this point I get modded down.... Which is more or less just like one of the current candidates for President.
We heard earlier that solaris 10 will be open source.
I wonder if that means that this filesystem can be included in other kernels.
Sagans?
Best Slashdot Co
I'm really happy with UFS2/SU, and have been more than happy with the original UFS in general since 1994 when I first started off with NetBSD.
But, with ZFS, maybe we finally have found a FS with replacing it with. I sure look forward to trying Solaris 10, though I'm sure that I will find that SunOS has a better feal to it, like always.
Maybe DragonflyBSD will be the one to do this, FreeBSD is generally more restrictive to radical changes; for good reasons, you don't get that stability without reason.
"ZFS, the Last Word in File Systems?"
The last word in file systems is "systems". And stop asking file systems these questions, you fool.
War is one of the most horrible things a human can be exposed to. And one of the worlds largest industries.
If it's the last word, why are we even talking about it?
and
Compared to AIX or HP-UX, 28 steps is shockingly bad, both have had much simpler logical volume management for several versions now (AIX for 5 years or more? certainly as long as I have used it). The existing Solaris 9 logical volume infrastructure is years behind the competition, this is bringing it up to date, but not putting it far ahead.
Ewan
COME ON! It may be a slow day, but how is this news? There's only one link, and it's to Sun's marketing info.
Can someone please provide a link to some technical details other than it being 128-bit? What does this file system actually do that is even remotely special? What's under the covers? And, more importantly, does it actually work as described?
-1,Uninformative
But of course you'll still have to have your boot image within the first 1024 cylinders.
Does this mean the absolutely awful Disksuite/Solaris Volume Manager is finally, mercifully, dead, too?
I'll do a dance of utter joy if so. Disksuite is 10 pounds of shit in a 5 pound bag.
- A.P.
"Remember when the U.S. had a drug problem, and then we declared a War On Drugs, and now you can't buy drugs anymore?"
Kneel Before Zod!
Art Schools Dietzilla
Well, there is another way for it to be the last word in Filesystems ... but with the Apocalypse delayed until 2032 we would have to have some damned lazy coders.
It is more productive to voice thoughtful opinions (reply) than to judge (moderate) others.
Who else instantly thought of, "640 K ought to be enough for anybody", uttered by the chief architect of twenty years of chaos?
Until now it does sound just like raid, but:
I guess I just don't get it; I know they are talking about logical corruption and not a physical failure, but this is kind of like raid with somethink like SMART, or isn't it?
And what kinds of corruption can there be? Journaling filesystems already work well for write errors and such, or so I thought.
I know the architecture seems innovative and different (at least for me), but is there really new functionality?
Sorry if I seem ignorant this time. I don't know if I was able to get my point across; the things this filesystem does, wouldn't they be better left on a different layer?
O make me a mask
One HUNDRED BILLION DOLLARS!
puts pinky in mouth
-- n
I don't know about the "last" word in file systems, but they won't be anything but klugey simulations of antiquated paper cabinets until their first word is "SELECT". Will someone finally replace the hierarchical inode database with relational tables, and a SQL API? Throw in a traditional file/directory API mapped to SQL statements, and the world will beat a path/filespec to your door.
--
make install -not war
Such a feature would rock, because it would be possible to make things like installers completely atomic: interrupt the installer process and the whole thing rolls back.
Use 'slashdot stuff' in the subject line in any email you send me if you want to get past the spam filter.
... ZFS will also make you forget everything you knew about English grammar.
"We've rethought everything and rearchitected it," says Jeff Bonwick
Rearchitected? WTF? Howsaboot "Redesigned?"
I'm still wrapping my brain around "adaptive endian-ness" as well.
--QTone
Obligatory Plug - Please check out my online novel
Great. A link to the marketting release. Wonderful.
So, what we now know is this is the greatest thing since sliced bread. According to sun that is.
Mod me down with all of your hatred and your journey towards the dark side will be complete!
Looks like Sun went out and redid their filesystem based on the performance characteristics of machines today, instead of machines of yesteryear.
Some highllights, for those that don't (or won't) RTA:
* Data integrity. Apparently it uses file checksums to error-correct files, so files will never be corrupted. About time someone did this.
* Snapshots, like netapp?
* Transactional nature/copy-on-write
* Auto-striping
* Really, Really Large volume support
All of this leads to speed and reliability. There's a lot of other stuff (varying blocks sizes, write queueing, stride stuff which I haven't heard about in years), but all of it leads to above.
Oh, and they simplified their admin too.
It's hard to make a filesystem look exciting. Most of the time it just works, until it fails. The data checksum stuff looks interesting, in that they built error correction into the FS (like CDs and RAID but better hopefully).
It might also do away with the idea of "space free on a volume," since the marketing implies that each FS grows/shrinks dynamically, pulling storage out of the pool as needed.
Any users want to chime in?
Looks to me like nothing more than an excuse to put up a patent tollboth for anyone who wants to implement ZFS.
"Sun's patent-pending "adaptive endian-ness" technology"
ok, that aside. First 128bit file system, and get this: transactional object model
I think this means it is optimistic but they figure it has blazing fast performance, who am I to argue. Fed up with killing this indexing garbage on the work machine, bloody microsoft, disabled it and everything and every full moon it seems to come out and graze on my HDD platter.
From the MS article : This perfect storm is comprised of three forces joining together: hardware advancements, leaps in the amount of digitally born data, and the explosion of schemas and standards in information management.
Then I started to suspect they would rant about moores law and sure e-bloody-nough
Everyone knows Moore's law--the number of transistors on a chip doubles every 18 months. What a lot of people forget is that network bandwidth and storage technologies are growing at an even faster pace than Moore's law would suggest.
That is like saying, everyone knows the number 9 bus comes at half 3 on wednesdays, but noone expects 3 taxis sat there doing nothing at half past 3 on a tuesday.
Can we put this madness to rest? Ok back to the articles.
erm... lost track now....
#hostfile 0.0.0.0 primidi.com 0.0.0.0 www.primidi.com 0.0.0.0 radio.weblogs.com
Never need more than a 128 bit filesystem? My arse... and I'll never need more than 640k of system memory. Just because 128 bit filesystems allow an utter crapload of data doesn't negate the fact that 256 bit filesystems would allow a super utter crapload of data...
"In fact, Solaris Kernel engineers Bill Moore and Matt Ahrens have subjected ZFS to more than a million forced, violent crashes in the course of their testing."
:)
Damn! These guys are even worse programmers than I am!
No, the German ß (s+z ligature) looks too much like a Greek lowercase letter beta, implying that the software is only of beta quality.
It would take over 500 years to fill a 64 bit filesystem written at 1GB/sec (and of course 500 years to read it back again). 64 bits is already an impossibly large figure. There's absolutely nothing special or clever whatsoever about doubling the size of your pointers aside from using up more disk space for all the metadata.
64 bits is enough for today's filesystems in much the same way that 256 bit AES is enough for today's encryption - there are far bigger things that will require complete system changes than that so called "limit". I suspect a better filesystem will come along well before those 500 years are up... I agree with grandparent:
-1, Marketing Hype.
Wasn't it supposed to be sometime in January, 2038?
I was going to respond to the article, but I forgot everything I know about file systems.
You have enemies? Good. That means you've stood up for something, sometime in your life. --Winston Churchill
"Patent Pending".
//Information does not want to be free; it wants to breed.
Though it before xyzzyfs, it is the last because it automatically generates and collects porn. Most geeks would never get past it.
Fight Spammers!
It sounds as if this will really take a bite out of using Linux as a SAN solution. I'm currently looking at different SAN options, and with Solaris 10 going open-source too, this really sounds like a HUGE deal for enterprise. Maybe Sun will make a comeback...
CAB
free ipod and free gmail!
Then why didn't IBM call its improved HFS "HFS Plus"? No wait, that would collide with Apple's HFS and HFS Plus, used in Mac OS.
It would appear that there can be only twenty-six distinct file systems. Then Microsoft went and innovated NTFS with Four-Letter-Word File System Technology, which actually was just a copy of IBM's HPFS, the first to introduce File System Named After a Competitor Technology.
You organize a 128bit file system with a database.
Why bother with folders as a root? You can create a folder hierarchy *with* a database too.
GPL Deconstructed
So what are the chances that someone could accidentally wipe the shared data pool for an entire company and how hard is recovery on a volume striped across a few hundred hard drives?
This article is shocking. I'm used to much less hype and far more technical details from Sun. Software patents and bullshit are not what I expect when I follow a link to them.
I don't like any of this.
Friends don't help friends install M$ junk.
when we had 1 bit filing systems, that being dead or alive, and 2 bit whores. I guess you yun folk just loved picking things to be bits. Now how the hell do I get back to 'Pals of the Saddle' dot com?
"Look Lois, the two symbols of the Republican Party: an elephant, and a fat white guy who is threatened by change."
how about ZZ(top)FS? if you need more storage, they can grow more!
No? Well the folks in Texas may get it...no?
CB
free ipod and free gmail!
we can:
/dev/hda
./opt/ut2k4/ut2k4
emerge zfs-utils
mkfs.zfs
?
A woman trying to grab smoke. :-) Sort of like trying to get solid details about the filesystem when everything was handled by the marketing droids.
Hmmm...as late as June 1 it was being referred to as DFS, the Dynamic File System. Not good enough for marketing, as it was too generic a term. Now it is ZFS -- the LAST WORD in filesystems. Ugh!
What happens when IBM decideds to let Sun's marketing droids know that ZFS is IBM's zSeries File System for OS/390 machines? How about that it also was a "dfs" in the way of "Distributed File System"?
Sun now want to take on Veritas, whose existance came into being pretty much to deal with the crappy Sun volume management.
All in all, Solaris 10 looks promising. Even more so that a good chunk of it will be open sourced.
Learning HOW to think is more important than learning WHAT to think.
When I saw that SUN was going to release solaris under an open source liscensce I was very impressed. Now that I have read about ZFS the advantages seem even more compelling.
Given that solaris has many primitives that linux lacks, for instance I understand that solaris has advanced file system primitives that linux lacks. Should the open source community decide to develop solaris instead of linux? Or at least split efforts equally between the two? Or should we concentrate on porting things like ZFS?
If you liked this thought maybe you would find my blog nice too:
It's a 128-bit filesystem, so doesn't that make it the last 8 words?
"No matter where you go, there you are." -- Buckaroo Banzai
ZFS achieves its impressive performance through a number of techniques:
* Dynamic striping across all devices to maximize throughput
* Copy-on-write design makes most disk writes sequential
* Multiple block sizes, automatically chosen to match workload
* Explicit I/O priority with deadline scheduling
* Globally optimal I/O sorting and aggregation
* Multiple independent prefetch streams with automatic length and stride detection
* Unlimited, instantaneous read/write snapshots
* Parallel, constant-time directory operations
ZFS has some similarities to NetApp's WAFL in that it uses "copy on write".
One of the fun things with ZFS is that it automatically stripes across all the storage in your pool. Disk size doesn't matter - it's all used. This even works across SCSI and IDE.
One of the important things is that volume management isn't a seperate feature. Effectively, all the current limitations of volume managers are blown away:
Just as it dramatically eases the suffering of system administrators, ZFS offers relief for your company's bottom line. Because ZFS is built on top of virtual storage pools (unlike traditional file systems that require a separate volume manager), creating and deleting file systems is much less complex. Not only does this eliminate the need to pay for volume manager licenses and allow for single support contracts, it lowers administration costs and increases storage utilization.
ZFS appears to applications as a standard POSIX file system--no porting is required. But to administrators, it presents a pooled storage model that eliminates the antique concept of volumes, as well as all of the related partition management, provisioning, and file system sizing problems. Thousands--even millions--of file systems can all draw from ZFS' common storage pool, each one consuming only as much space as it needs. The combined I/O bandwidth of all of the devices in that storage pool is always available to each file system.
This is also part of the stuff making admin and configuration far far simpler. The thing I like is that it should be far harder to go wrong with ZFS (not available in Solaris Express yet so I haven't seen this for myself).
The very high degree of reliability as standard is very welcome too:
Data can be corrupted in a number of ways, such as a system error or an unexpected power outage, but ZFS removes this fear of the unknown. ZFS prevents data corruption by keeping data self-consistent at all times. All operations are transactional. This not only maintains consistency but also removes almost all of the constraints on I/O order and allows changes to succeed or fail as a whole.
All operations are also copy-on-write. Live data is never overwritten. ZFS writes data to a new block before changing the data pointers and committing the write. Copy-on-write provides several benefits:
* Always-valid on-disk state
* Consistent, reliable backups
* Data rollback to known point in time
"We validate the entire I/O stack, start to finish, no guesswork involved. It's all provable data integrity," says Bonwick.
Administrators will never again have to run laborious recovery procedures, such as fsck, even if the system is shut down in an unclean fashion. In fact, Solaris Kernel engineers Bill Moore and Matt Ahrens have subjected ZFS to more than a million forced, violent crashes in the course of their testing. Not once has ZFS lost data integrity or leaked a single block.
For more technical info see Matt Ahrens's and Val Henson's blogs - since they're among the engineers who worked on it.
at (deleted, it seems there are some things you can't say on /. You can figure it out but somehow it's not so funny that way.)
You may need better than a 128 bit file system for your Matrioshka Brain, but even that's not sure.
And your 640k quote is dubious. Here's a real quote that you can wow the punters with instead:
"There is no reason for any individual to have a computer in their home." - Ken Olsen, President of Digital, 1977.
That is to say:
- Solaris will still recognize the hardware it always ran on.
- The kernel will keep on hiding low-level details to the applications.
Badabing. Thank you...I hadn't the slightest objection to his spending his time planning massacres for the bourgeoisie... (P.G. Wodehouse)
The codename for the first generation of Novells current filesystem was ZFS. Why? because it was supposed to be "the last, or final word" in file systems.
Novell now Novell Storage System (I think it used to be NetWare Storage System).
Apart from the obvious fact that SUN didnt manage to be very original in naming their filesystem, its noteworthy that Novell is porting their ZFS - now NSS - to Linux. It'll be part of Novell Open Enterprise Server - on both Linux and NetWare kernels.
From the top of my mind, here are some features of NSS that SUN needs to exceed to qualify for a new "final word..":
- Background compression
- Fast on-demand decompression
- Transactions
- Pluggable Name spaces
- Pluggable protocols (ie. http, nfs, etc)
- Advanced Access control model with inheritance, rights filters, etc. integrated with directory service (duh!)
- Quotas on user, group, directory level
- 64-bit (ok, SUN obviously got that one)
- mini-volumes
- journaled
- etc.
oh well, I wont bother continuing, but its worth looking out for NSS. Hopefully Novell will open source it and not make it exclusive to their distros.
For that matter, is anyone sure a 128 bit FS is even needed? 2^64 is an extraordinarily big number - a few years back, when I was a BeOS fanatic, I read an essay estimating the total amount of data generated by the human race in all of history, and concluding that all of it could be put into a 64-bit FS like BeFS without coming anywhere close to the theoretical storage capacity (i.e. using something like a millionth or a billionth of the potential space, don't remember the details). We are very, very far away from having any storage device that cannot be indexed with 64 bits. It may well be true that a device that outstrips the abilities of a 128 bit FS is a physical impossibility. For comparison, I remember hearing that IPv6 (a 128-bit scheme) could provide 5,000 distinct IP addresses for every atom on the surface of the earth.
Actually it was Al Gore. Right before he starting inventing the Internet.
Right now there are a lot of file systems that do somehing not all that different than what Sun is proposing. The project I am on is evaluating them as we speak for a center wide filesystem. I've had the fun (no sarcasm, honestly) of setting up a number of different onces and helping to run benchmarks and tests against each. All of them have strengths. Every single one of them has some nasty weaknesses.
If you are looking for an open source based cluster file system, Lustre is what you want. It's supported by LLNL, PNNL, and the main writers at ClusterFS Inc. It's a network based cluster FS. We've been using it over GigE. However, we've found that there needs to be a ratio of 3:1 for data server:clients for a ratio. Wehave only used one metadata server. Failover isn't the greatest. Quotas don't exist. it also makes kernel mods (some good and bad) to do a mild fork of the linux kernel (they put them into the newer kernels every so often). It only runs on Linux. Getting it to run on anything else looks...scary.
GPFS runs on AIX and Linux. Even sharing the same storage. It runs and is pretty stable. it has the option to run in a SAN mode or network based FS. In the latter form, it even does local discovery of disks via labels so that if a client can see the disks locally it will read and write to them via FC rather than to the server. It, however, is a balkanized mess. It requires a lot more work to bring up and run: there is an awful lot of software to configure to get it to run (re: RSCT. If you haven't had the joys of HATS and HAGS, count yourself very, very lucky).
ADIC's StorNext software is another option. This one is good if you are interested in ease of installation, maintanence, and very, very fast speeds (damn near line speed on Fibre channel). I have set this one up for sharing disks in less than two hours from first install to getting numerous assorted nodes of different OS's to play together (Solaris, AIX, Linux). It freakin on virtually everything from Crays to Linux to Windows. It's issues seem to be scaling (right now doesn't go past 256 clients) and it has some nontrivial locking issues (righting to the same block from multiple clients, and parallel I/O to the same file from multiple clients if you change the file size).
There are some others that are not as mature. Among them are Ibrix, Panasas, GFS, and IBM's SANFS. All of them are interesting or promising. Only SANF looks like it runs on more than Linux though at this point. Our requirements for the project I am on are to share the same FS and storage instance among disparate client OSes simultaneously. This might not be the same for others though and these might be worth a look. Lustre dodges this because its open source and they're interested in porting.
Do you know why the road less traveled by is littered with the bones of the unwary?
The last word in file systems is "systems".
Thank you.
Please read my Canon EOS tech blog at http://www.everyothershot.com
/* typedef int size_t */ /* 128-bit unsigned integer */
typedef unsigned long long long int size_t;
=)
True. However, it is more ambiguous than "million million million", as absent minded Brits might interpret it as a "million million million million".
Or would you rather they say 6.0 × 10^18?
Yes.
Most people can't imagine that.
Most people can't imagine it anyway, whether you call it "six billion billion", "6.0 x 10^18", "6 x 2^60", or "1.27 x e^43". Or understand any number higher than the number of dollars they carry in their wallet, for that matter. Anyone who needs to make any decisions in life based on this ZMS number ought to be able to understand it any of those ways (although getting help from a calculator for the last one or even two is understandable). Of course, many people manage things they can't understand. This is life.
//Information does not want to be free; it wants to breed.
As someone who's been involved with performance/stress optimizations I can tell you that for each situation you can carefully put together two types of tests: one which proves that there's a problem, another that proves the problem doesn't exist.
The proof is in the pudding. Let Sun release it and administrators use it for a year or two, then we'll see if it's good enough. Right now I'm having doubts it's as good as they want you to believe.
He just subtracted one from infinity, which as anyone can tell you gives you 16 billion billion.
"There is more worth loving than we have strength to love." - Brian Jay Stanley
Two words:
"Patent burdened"
Logically, the next question is if ZFS' 128 bits is enough. According to Bonwick, it has to be. "Populating 128-bit file systems would exceed the quantum limits of earth-based storage. You couldn't fill a 128-bit storage pool without boiling the oceans."
Well...I never really like the oceans anyways. They were always so wet.
.. if you speak with a German accent. Chip H.
What a useless writeup.
ZFS, the dynamic new file system in Sun's Solaris 10 Operating System (Solaris OS), will make you forget everything you thought you knew about file systems.
Don't forget, everything is possible with the Zombo File System!
It is not so hard to do adaptation to endianness. I built a filesystem to handle UFS that way circa 1995. It looked at the magic numbers at the start of various structures and either swapped bytes or not, to get the right values. I imagine what Sun is doing is basically exactly that, just stuck at a fairly low level in the fs code, but allowing access to structures written on either endianness. Thus an inode written initially on x86 would be swapped on read and write (except complete rewrite, where it could be left native) if handled on Sparc or other big-endian iron, and vice versa. Not bad engineering but how the devil USPTO could consider it patentable at this late date is a mystery to me. An integer written from memory to a device is going to be different on disk depending on endian-ness. That is just the way things work. What I just described is the clear and simple solution, and the fact that the magic numbers are all devised so it works argues that others thought of the issue long before I did.
Shouldn't Luke be telling Anakin to tell Amidala "I am your density."
There is some interesting information in Matthew Ahrens's blog.
And some Val Henson papers here and here.
Read Epic the first RPG novel.
DEC/Compaq/HP/Doesn't matter now! provided this view of data storage years ago with AdvFS on Tru64. You had a bunch of disks, created a volume, then created as many filesets as needed. Any fileset could use any (or all) of the storage space in the volume.
For the record, 2^128 yields 3.402e38 and the mass of mother Earth is 5.974e27 grams (according to google). For the earthbound human to create the harddrives needed to fill this filesystem, we would have to contribute around 1e-11 grams (0.00000000001) to every bit or byte needed. So, anybody who wants to proved Sun wrong and call 128bits the same as 640k, get digging. I'll check up on you every century or so to see how the project is going.
There aren't any letters after "Z" that I know of.
ZFS, the Last Word in File Systems?
Of course it's the last word. It starts with "Z"!
Oh wait, I suppose ZZFS could be the last word
Or maybe ZZZZZZZZZZFS
"Sun's PATENT-PENDING "adaptive endian-ness" technology, which is unique to ZFS..."
Richard Steven Hack - This sig is TOO GODDAMN SHORT TO DO ANYTHING USEFUL WITH! MORONS!
Half of the magic is already in FAT32 when your data magically disappears* - it obviously just needs an upgrade! :)
* yes, i know this is actually just by a power failure
If anyone wants to read more details on the "Zettabyte File System" they can view the white papers on ZFS self-tuning and QOS as they contain far more detail than the marketing article given.
Logically, the next question is if ZFS' 128 bits is enough. According to Bonwick, it has to be. "Populating 128-bit file systems would exceed the quantum limits of earth-based storage. You couldn't fill a 128-bit storage pool without boiling the oceans."
Hey, forget North Korea and Iran! It's these Sun guys we need to worry about!
For instance, those solved by LVM; you can plug in additional discs and they appear as part of the same volume, and they seem to be claiming they do this better than the competition. And there seem to be some other clever stuff (copy-on-write, error recovery). Based on the article (which is useless) they seem to be trying to do similar things in terms of very clever journaling file systems, but I can't see who's best without some facts.
Oh yes, If you happen to be running Solaris 10, it's available while Reiser4 isn't. (If you happen to be running Linux, this isn't true)
In soviet russia stale jokes recycle you!
Says he needs a new wallet...
..oh wait, he does.
If Bill Gates had a nickel for every time Windows crashed...
It takes 40+ muscles to frown, but only four to extend your arm and bitchslap the motherfucker
...AAFS?
Zed : Bring out the Gimp.
Maynard : But the Gimp's sleeping.
Zed : Well, I guess you're gonna have to go wake him up now, won't you?
"Leo Fender was in a 'state of grace' when he designed the Stratocaster." -- Paul Reed Smith
This means that not only will I be able to store 16 billion billion times more Libraries of Congress, I will be able to read/write them soooooo much faster than I am now...
"We're absolutely trying to make disk storage more like memory, and often use that analogy in our presentations. For example, when you add DIMMS to your computer, you don't run some 'dimmconfig' program or worry about how the new memory will be allocated to various applications; the computer just does the right thing. Applications don't have to worry about where their memory comes from. Likewise with ZFS, when you add new disks to the system, their space is available to any ZFS filesystems, without the need for any further configuration. In most scenarios it's fairly straightforward for the software to make the unequivocably best choices about how to use the storage. If you want to tell the system more about how you want the storage used, you'll be able to do that too (eg. this data should be mirrored but that not; it's more important for this data to be accessed quickly but that can be slower). We hope that with relatively modern hardware, all but the most complicated and demanding configurations will be handled adequately without any administrator intervention." read more
The /. fortune when I read this article.
Everyone keeps ranting about how 128 bits is unreliastic and we will never need the space.
It is quite obvious Sun is working on Human Teleportatoin, and needs the 128 bits to be able to addresss the quantum superpositions of all of the particles in a human body.
(http://www.britneyspears.ac/lasers.htm)
Cool, Anonymous Cowards have their own TLD now.
Your hybrid is not saving the environment. Its purpose is to make you feel good about buying something.
All I ask is, where the hell do they get these kind of figures?
For more information, please consult the National Department of Arbitrary Statistics.
What I'd like to know is by how much this increases floating point and double-precision resolution. Can anybody comment on this?
It's easy to talk about the number of integers possible - because they're a power of 2. But what are we talking about in terms of floating point? Same range, greater resolution? Same resolution, greater range? Or both? Which would be more important?
Anyone?
Find a job you like and you will never work a day in your life.
Not on the default input method in Windows, Linux, and Mac OS as configured for U.S. English. American customers constitute a huge chunk of system vendors' sales. Few Americans know how to type foreign characters, so how would they know what to put into Google?
And not on Slashdot. Slashdot's Slashcode installation completely strips out all Unicode characters except for a select few. Without Slashdot traffic, who will know of a file system? And without customers, what's the point of developing and supporting a file system?
Cosmos. Also a book.
I loved that show when I was in jr high, but when I went back and checked it out it felt a bit dated, but still fascinating.
Personally I wonder what advantage "boiling the oceans" would give to anyone trying to fill the 128-bit storage pool.
The world's largest steam bath?
Microsoft is to software what Budweiser is to beer.
Historically IBM has assumed a "so what?" attitude when it was pointed out to them that they didn't comform to the rest of the world's standards. Take ... counting bit positions from left to right.
In graphics systems, I can see how this would make sense. The 1-, 4-, and 16-color display modes of the CGA, EGA, VGA, and various Mac display adapters, as well as display systems of many video game consoles, assigned bits within a byte such that the high order bit is on the left. The only display hardware systems I can think of that assign bits to pixels from right to left are Apple II (not the IIGS SHR modes), the Virtual Boy, the Game Boy Advance, and the PlayStation 1.
"you couldn't fill a 128-bit file system unless you boiled the oceans"
Uh, bunky? Burning all the oil and boiling the oceans are opposite classes of thermodynamic processes.
One is exothermic and will help you fill a filesystem. The other is endothermic and will require burning your filesystem to accomplish.
So now I really wonder if this thing doesn't conk out at like 4 GB (or even 2!) due to some similar stupidity in the driver stack...
Speaking of numbers no one can pronounce....
Why not just go all the way to 256 and address EVERY PROTON IN THE UNIVERSE.
With about 10^79 protons in the observable universe, one could address them all with 2^256 possible addresses.
Mad Software: Rantings on Developing So
With the only exception that GFS was targeted at clusters where the common ops are append and seq read, and rarely others. GFS performs mirroring, snapshots, COW and data checksums (and that is just what I remember for the public paper, probably does some more).
That's what -they- said anyway ... it's just a trick to fake you into feeling safe until the end.
It is more productive to voice thoughtful opinions (reply) than to judge (moderate) others.
You'd have to boil some water in a pan before some Linux or ReiserFS programmer comes along and makes this filesystem a moot point.
This article doesn't say anything about the things that most users and OS/applications care about. What about extended meta-data? What about better indices?
Let me guess, the 128bit fs takes up so much room, that I cant fit extra meta-data on the filesystem.
I've wanted to say this about Linux vs. Sun for a while: The main strength that Linux has is that UFS is a dog, and developers are writing filesystems for Linux that do AMAZING things - libferris anyone? ReiserFS is still my favorite, I use it all over the place.
With Sun, you dont get the innovation that you get from Linux, because they dont let at the innards of their filesystem interface. Sure veritas is cool - but that's ONE out of say 5 or 10 available for Linux.
The one thing that is cool in the article is the storage reservation capability. That would be a nice feature to have.
"ZFS, the dynamic new file system in Sun's Solaris 10 Operating System (Solaris OS), will make you forget everything you thought you knew about file systems."
What is a....."file-system"?
One of the key feature of ZFS is that you can create a file system over a pool of storage. Nothing stops you from building a distributed storage pool of 18.3 million desktop drives (they don't have to be locally connected). You could apply the same concept as SETI@HOME and allow end users with excessive storage space to lend them. Didn't someone talk about a peer to peer backup system a while ago?
And com'n, don't be so against hypes. Not all numbers are evil. And the overhead to process some extra bits are miniscule. The space and time required are in logarithmic time to the size of the number set. E.g., 128-bit is some billions billion times the size of 64-bit, but only takes 2 times more to store and process. And this time is already small compared to the actual I/O time, and the space compared to combined storage space.
I once had a signature.
I'll see you a [fs and raise you a ~fs!
While I'll admit it's hard for me to imagine a file system without limits, but we should all acknowledge that a limit is still a limit no matter how far off that limit may be at the moment.
Perhaps by the time that unimaginably large limit becomes too small to be useful, perhaps we won't be using this crude "binary" system any more anyway.
I was going to try to explain some of the material, but you've done a better job than I could have. Sun will be releasing complete technical details soon. Solaris 10 shipping date is year end. I wasn't clear as to whether the full implemention of ZSH will make the first cut.
There are a million filesystems better than UFS that Sun could have easily squeezed into Solaris 9. For years, consumers have been screaming for reiser and other filesystems as the default. The standard filesystem will always be UFS no matter what their marketing push. Until I see c0t0d0 as ZFS, I won't believe a thing.
Solaris! Woo hoo, whats next, new video abilities being added to Be?
As subversion has shown, with a db based file system, a version controlled file system can be developed intuitively and effectively.
I hope that sun's new FS is `ready to go` if users would like to add such features that are built into the FS.
Yet another hierarchical DB as a filesystem?
This is dumb. It is high time we should have a truly RDBMS (*not* SQL!) as *the* storage engine for all systems, with POSIX as a compatibility option.
Leandro Guimarães Faria Corcete DUTRA
DA, DBA, SysAdmin, Data Modeller
GNU Project, Debian GNU/Lin
Oh god, another file system.
Let's lock all the file system developers in a room for a few days and let the fight it out. The last one standing wins.
emerge ZFS ?
Si vis pacem, para bellum! For evil to succeed good men need only do nothing!
this is obviously the One World Filesystem in its infancy
after this comes (natch) the One World Government!
don't be reduced to an inode! fight!
Architecture is a step preceding Design.
But then, I have yet to convince my colleagues of this distinction.
Needless to say, most of our apps suck when they go into the maintenance phase (about one third into development).
Still, this does sound like a tick-in-a-box comparison thing for FUDing people about scalability. "So you're thinking about buying OS xxx. I hope you know it only has a 64bit FS. Think of the future. Buy ours with a shiny 128bit FS".
Engineering is the art of compromise.
If it's the trivial "receiver makes it right" technique (endian architecture identified in packet so swapping is required only in dissimilar cases), it would be especially ironic since the prior art is (at a minimum) from the 1980s when it was used by the OSF RPC design - back when the Unix world was divided into Sun/AT&T vs. nearly everyone else.
The pools, that's cool. But I wouldn't expect anything less from Sun anyways.
I hope so, but you can't tell from Sun's announcement.
Friends don't help friends install M$ junk.
Twitter, you're a petulant cock-gobbling sycophant to Linux Torvaldyos! Quit taking DP from ESR and RMS's feculent cocks and why don't you try to stop sucking quite so much? Get out of your parents' basement and see the real world - maybe then you'll see how pathetic you sound, with your neverending stream of bullshit about how Microsoft is stalking you. Wasn't it you who said that Microsoft believes your insane ranting is actually a threat to them, so they PAY PEOPLE to reply to you on Slashdot? No sir, I don't get any money. I do it for the love. Someone has to go up against your paranoid whining. So get back in your cage and shut the fuck up already.
Twitter, you're a petulant cock-gobbling sycophant to Linux Torvaldyos! Quit taking DP from ESR's and RMS's feculent cocks and why don't you try to stop sucking quite so much? Get out of your parents' basement and see the real world - maybe then you'll see how pathetic you sound, with your neverending stream of bullshit about how Microsoft is stalking you. Wasn't it you who said that Microsoft believes your insane ranting is actually a threat to them, so they PAY PEOPLE to reply to you on Slashdot? No sir, I don't get any money. I do it for the love. Someone has to go up against your paranoid whining. So get back in your cage and shut the fuck up already.
Not only did the submitter's summary not really tell you anything at all about ZFS, except that it's Sun's new filing system (why should we care? what's different? etc), and basically read like a content-free press release, but slashdot posters filled up the entire first page of comments bitching about the meaning of 'billion', UK vs US numbers, the population of India, blah blah, anything really except talking about the damn filing system.
And no, as my UID will attest, I am not new here. I just behave as if I am :-).
What does the Z stand for? and why wouldn't I wan't RFS or BFS or almost anything else? and 16billion billion is definatly a known limit so in order to make this truely unlimited we'd need to recode it to know about qbits, and make it's max_write_size= i.oo+Ioo|i...++oo| ? But first of all DYAM that's a LOT of porn.
ISTR that it goes
1 == one
1e3 == one thousand
1e6 == one million
1e9 == one billion
1e12 == one trillion
1e15 == one quadrillion
1e18 == one quintillion
1e21 == one sextillion
There are, I think, some other numbers between those; but they've never really seemed that important.
I guess today is a passable day to die.
3) What does ZFS offer over AdvFS?
Granted, Solaris hasn't been EOL'd and Tru64 has, but I fail to see anything meaningful [0] that ZFS does that AdvFS doesn't.
[0] dtrace is a seperate thing, although I supose ZFS has hooks for it. The 128 bit filesystem is just excessive.
Yes [gigle] the last word [stifled laugh] in filesystems [uproarious laughter]... No really, there is not ever (in the forseeable future) going to be a last word in file systems. Sure this is nice, but hey, it is part of Solarus, which has a market share so small that not even the Earth Simulator can hold it in memory.
Gigabyte is 10^9 bytes. This is the freaking definition of "Giga".[br] (2^30) that you are thinking about is 1 Gibibyte.[br] Get your facts straight before spewing. If everybody is using kilobyte to mean 1024 it does not make that right. kilo is 1000, kibi is 1024. That's it, end of story.
<^>_<(ô ô)>_<^>
These days I can do it sober!
This is the year 2004. There aren't that may bytes in the whole world! You might as well give us a filesystem that stores a Gajillion Bazillion bytes! Ha, ha, ha, ha!
You can find some more technical information about ZFS in my weblog. Check out the comments to my first entry about ZFS, there are a few juicy details there and I'll do my best to answer any questions posted to my blog.
Disclaimer: I work on ZFS at Sun.
Ah good, Sun has finally got the idea of a good LVM rather than disksuite or go and buy Veritas.
On the other hand, what's this Silent Date Corruption they are on about? Makes me worry about the existing Solaris filesystems.
Hopefully a decent LVM for Linux will happen soon, IBM's AIX LVM is quite simple to use and would have been very nice to have been included in the Linux Kernel, just install the OS, it makes all the filesystems you require, quite small and then just grow as need be. The implementation of LVM at the moment for Linux is poor, partition this bit and then this, and then make an LVM partition and partition that... /P
dearest /. reader, I would like to bestow upon you a http link for your consumption. I found it in my parent post.
The secret hidden article link with the accused spelling mistake
Now to address the issue of your spelling mistake, first to quote something out of context:
"Most data that people work with today is born digitally."
Yes, you could say that is bourne digitally, this would mean produced, and yes, it is technically correct.
"For example, rather than starting to write this article on a piece of paper, I started writing it using my laptop with Microsoft Word."
Ok looking closer born and borne can have the same usage, if your personify the context, in this case the living document of the article, then it can be said to have be born of something.
Like a bud beer, my files have a timestamp. a born on date.
I think this is what the person was saying. Although I am hesitant to provide any support for this article myself, as I think thier article was borne out of a cycle to hype up WinFS whihc most people don;t know what it is, or that they need it or don't need it, to enforce yet another upgrade cycle, limiting the life expectancy of a product that should continue to have updates and patches and remain servicable, not be engineered to be self deprecating.
Anon, I fear I have wandered from the path of the conversation.
"***Egad, I'm gonna lose karma here but fuggit...***"
Who gives a shit. This is the kind of thing you tag your post with hoping a mod would take this defiantly and mod you up just for the sake of it. I don't someone with mod points cares about this post, and I don't think anyone else but you will read it.
Also looking at your post history, I can say you have a nice even putting green of post scores, so no worries there.
Man, that is the most fuzzy post I've ever ready! WTF is your point??
Reading my post, I think I mentioned I lost my point long before, having been distracted by the outright idiocy of M$ (l33t!) quoting Moores law on an article so hopelessly geared towards getting a PHB another checkbox on his agenda for the next meeting to show he is doing some work.
Unless of course I misread your post and you are on the edge of you seat waiting with baited breath, which is held, in anticipation to hear what it was I was actually getting at. In my post. That is.
"please tell me how Microsoft's grazing on your platter"
Microsoft is the name I gave to my pet goat, because he is ugly and smells, so I have to open windows. Gee I just made that one up, but I am quite proud of it.
OK, jesting aside, I was talking about the indexing service which despite my efforts to the contrary decides to start up as I am running nmake and chews the fat with ntfs (gee posts about file systems and I slipped two in there! I am getting good at this flame thingy)
That's sorted (google for microsoft indexing service) I hope.
"without reference"
You want harvard or british standard? Else wait until I publish the errata on my homepage.
"(making me believe you read it off a 37733t h4xx0rz forum)"
I made you believe that? 3773t? I think you mean 37337 (a nice port number to visit). And by hfourxxzerorz forum, if you mean MSDN, then yes you are right.
"has *anything* to do with it?"
Well you are right there, is was kinda OT! fsck me, I hadn't gone and commented I could have modded myself down.
Thank you for playing flame warz, I'll let you tot up the score. (I would proof this longish post but it ain't worth the effort - it was midly amusing to write though!)
#hostfile 0.0.0.0 primidi.com 0.0.0.0 www.primidi.com 0.0.0.0 radio.weblogs.com
If that's too much typing for you,(without the ";" put there by Slashdot) yields: http://www.namesys.com/benchmarks.html
Why for the life of mine would we want a global filesystem?
I think you are like one of those people saying "let conquer the stars and travel to other planets" when they have not realized the enormity of the numbers involved.
SIt down and make some maths, what you are suggesting is completely ludicrous.
IANAL but write like a drunk one.
Please note that there is a Solaris discussion forum for x86 as well as other Solaris topics at:
http://forum.sun.com/forum.jsp?forum=11
the basic gates in BiCMOS technology all include an implicit inversion: NOT, NAND, NORs... buffers, ANDs, and ORs can only be built indirectly, generally by sticking an inverter on the output.
It doesn't take a genius to turn ANDs feeding into an OR into NANDs feeding into a NAND. So why can't a netlist compiler just automate this, sticking the "not" bubbles on gates in the most efficient way?
It was not a flaimbait. It was a statement of fact.
<^>_<(ô ô)>_<^>