ZFS with Linux: An Open Plea

ZFS with Linux: An Open Plea

[David R. Litwin]

Before I go on, let me appologise. I don't really know what I hope to  
accomplish, beyond trying to garner thoughts (and support?) for the topic.

Essentially: I want to use Linux and ZFS. I don't particularly care about  
licences or any of the rest of that nonsense. The code is there; it merely  
needs to be made to work with Linux. Done and done -- provided I can find  
some one to do this for me (I'd do it myself, but I haven't the foggiest  
notion how to go about such a feat).

By the way, forget about this FUSE business. I don't know why they're  
bothering: It's not real, it's slow and, in general, silly.

What are the thoughts of the Linux community?

I appologise right now for my intrusion. I am a Linux-nobody; I freely  
admit it. I haven't even subscribed to this list (so do CC me) because I  
don't want to be over-whelmed with the list's glorious posts. But, part of  
Linux is it's being a community. If a member of this community (that is, a  
user of Linux) can't ask the others their
thoughts and opinions, then the community has failed in a large respect.  
Take this letter as you will.

-- 
—A watched bread-crumb never boils.
—My hover-craft is full of eels.
—[...]and that's the he and the she of it.

Re: ZFS with Linux: An Open Plea

[Neil Brown]

On Friday April 13, presently42@gmail.com wrote:
> Before I go on, let me appologise. I don't really know what I hope to  
> accomplish, beyond trying to garner thoughts (and support?) for the topic.
> 
> Essentially: I want to use Linux and ZFS. I don't particularly care about  
> licences

You may not care about licenses, but a lot of people do.  And they are
a real issue.

But I'm more interested in what you really want.
What, specifically, is there in ZFS that you want to use in Linux?
There is lots of interesting stuff in there, but which bit has caught
your attention?  It is possible that that functionality can be
incorporated into Linux without trying to clone or copy ZFS.

NeilBrown

Re: ZFS with Linux: An Open Plea

[Christoph Hellwig]

On Sat, Apr 14, 2007 at 09:43:29AM +1000, Neil Brown wrote:
> On Friday April 13, presently42@gmail.com wrote:
> > Before I go on, let me appologise. I don't really know what I hope to  
> > accomplish, beyond trying to garner thoughts (and support?) for the topic.
> > 
> > Essentially: I want to use Linux and ZFS. I don't particularly care about  
> > licences
> 
> You may not care about licenses, but a lot of people do.  And they are
> a real issue.
> 
> But I'm more interested in what you really want.
> What, specifically, is there in ZFS that you want to use in Linux?
> There is lots of interesting stuff in there, but which bit has caught
> your attention?  It is possible that that functionality can be
> incorporated into Linux without trying to clone or copy ZFS.

Linux definitly missed the hype value.  So everyone please start blogs
and do a of handwaving to get the mindspehere in web 2.0 back..

/me sighs

Re: ZFS with Linux: An Open Plea

[Mike Snitzer]

On 4/13/07, Neil Brown <neilb@suse.de> wrote:
> On Friday April 13, presently42@gmail.com wrote:
> > Before I go on, let me appologise. I don't really know what I hope to
> > accomplish, beyond trying to garner thoughts (and support?) for the topic.
> >
> > Essentially: I want to use Linux and ZFS. I don't particularly care about
> > licences
>
> You may not care about licenses, but a lot of people do.  And they are
> a real issue.
>
> But I'm more interested in what you really want.
> What, specifically, is there in ZFS that you want to use in Linux?
> There is lots of interesting stuff in there, but which bit has caught
> your attention?  It is possible that that functionality can be
> incorporated into Linux without trying to clone or copy ZFS.

ZFS does have some powerful features but much of it depends on their
broken layering of volume management.  Embedding the equivalent of LVM
into a filesystem _feels_ quite wrong.

That aside, the native snapshot capabilities of ZFS really stand out
for me.  The redirect on write semantics aren't exclusive to ZFS;
NetApp's WAFL employs the same.  But with both ZFS and WAFL they were
designed to do snapshots extremely well from the ground up.

Unfortunately in order for Linux to incorporate such a feature I'd
imagine a new filesystem would need to be developed with redirect on
write at its core.  Can't really see ext4 or any other existing Linux
filesystem grafting such a feature into it.  But even though I can't
see it; do others?


Begin non-technical patent related babble:
As you noted licenses are important, as are patents.  Interestingly
I've learned that Sun and NetApp's lawyers had it out over the
redirect on write capability of ZFS.  When the dust settled Sun had
enough patent protection to motivate a truce with NetApp.

The interesting side-effect is now ZFS is "open" and with that comes
redirect on write in a file system other than WAFL.  But ZFS's CDDL
conflicts with the GPL so I'm not too sure how Linux could hit the
ground running in this potentially patent mired area of filesystem
development.  The validity of NetApp having patented redirect on write
aside; does the conflict between CDDL and GPL _really_ matter?  Or did
the CDDL release of ZFS somehow undermine NetApp's WAFL patent?

Mike

Re: ZFS with Linux: An Open Plea

[Krzysztof Halasa]

Neil Brown <neilb@suse.de> writes:

> What, specifically, is there in ZFS that you want to use in Linux?
> There is lots of interesting stuff in there, but which bit has caught
> your attention?  It is possible that that functionality can be
> incorporated into Linux without trying to clone or copy ZFS.

Filesystem block hashes (checksums) and in-fs redundancy (using the
hashes to determine which copy of data is correct in case of
corruption). It would mean multi-device filesystem.
-- 
Krzysztof Halasa

Re: ZFS with Linux: An Open Plea

[Jan Engelhardt]

On Apr 14 2007 10:04, Mike Snitzer wrote:
>
> ZFS does have some powerful features but much of it depends on their
> broken layering of volume management.  Embedding the equivalent of LVM
> into a filesystem _feels_ quite wrong.
>
>[...]
>
> Unfortunately in order for Linux to incorporate such a feature I'd
> imagine a new filesystem would need to be developed with redirect on
> write at its core.  Can't really see ext4 or any other existing Linux
> filesystem grafting such a feature into it.  But even though I can't
> see it; do others?

FUSE-based filesystems. (That said, might wanna try through
"ZFS-on-fuse" fs).


Jan
-- 

Re: ZFS with Linux: An Open Plea

[Bill Huey]

On Sat, Apr 14, 2007 at 10:04:23AM -0400, Mike Snitzer wrote:
> ZFS does have some powerful features but much of it depends on their
> broken layering of volume management.  Embedding the equivalent of LVM
> into a filesystem _feels_ quite wrong.

They have a clustering concept in their volume management that isn't
expressable with something like LVM. That justifes their approach from
what I can see.
 
> That aside, the native snapshot capabilities of ZFS really stand out
> for me.  The redirect on write semantics aren't exclusive to ZFS;
> NetApp's WAFL employs the same.  But with both ZFS and WAFL they were
> designed to do snapshots extremely well from the ground up.

Write allocation for these kinds of system (especially when concerned
with mirroring) is non-trivial.

> Unfortunately in order for Linux to incorporate such a feature I'd
> imagine a new filesystem would need to be developed with redirect on
> write at its core.  Can't really see ext4 or any other existing Linux
> filesystem grafting such a feature into it.  But even though I can't
> see it; do others?

You also can't use the standard page cache to buffer all of the sophicated
semantics of these systems and have to create your own.

> I've learned that Sun and NetApp's lawyers had it out over the
> redirect on write capability of ZFS.  When the dust settled Sun had
> enough patent protection to motivate a truce with NetApp.

I think they are still talking and it's far from over the last I heard.
The creation of a new inode and decending indirect blocks is a fundamental
concept behind WAFL. Also ZFS tends to be a heavy weight as far as
metadata goes and quite possibly uneccessarily so which is likely to effect
performance for things related to keep a relevant block allocation map in
memory. ZFS is a complete pig compared to traditional file systems.

> The interesting side-effect is now ZFS is "open" and with that comes
> redirect on write in a file system other than WAFL.  But ZFS's CDDL
> conflicts with the GPL so I'm not too sure how Linux could hit the
> ground running in this potentially patent mired area of filesystem
> development.  The validity of NetApp having patented redirect on write
> aside; does the conflict between CDDL and GPL _really_ matter?  Or did
> the CDDL release of ZFS somehow undermine NetApp's WAFL patent?

That doesn't really matter. FUSE could be extended to handle this kind
of stuff and still have it be in userspace. The BSD get around including
Stephen Tweedy's (sp?) ext2 header file by making the user manually
compile it. That's not a problem for Linux folks that can download a
patch and compile a kernel.

FreeBSD already has a port of ZFS. Just for a kick, Google for that as
a possible basis for a Linux kernel port.

bill

Re: ZFS with Linux: An Open Plea

[Kasper Sandberg]

On Fri, 2007-04-13 at 19:18 -0400, David R. Litwin wrote:
> Before I go on, let me appologise. I don't really know what I hope to  
> accomplish, beyond trying to garner thoughts (and support?) for the topic.
> 
> Essentially: I want to use Linux and ZFS. I don't particularly care about  
> licences or any of the rest of that nonsense. The code is there; it merely  
> needs to be made to work with Linux. Done and done -- provided I can find  
> some one to do this for me (I'd do it myself, but I haven't the foggiest  
> notion how to go about such a feat).
> 
> By the way, forget about this FUSE business. I don't know why they're  
> bothering: It's not real, it's slow and, in general, silly.
This seems to me to be a rather uninformed, arrogant, and quite stupid
comment.

> 
> What are the thoughts of the Linux community?
> 
> I appologise right now for my intrusion. I am a Linux-nobody; I freely  
> admit it. I haven't even subscribed to this list (so do CC me) because I  
> don't want to be over-whelmed with the list's glorious posts. But, part of  
> Linux is it's being a community. If a member of this community (that is, a  
> user of Linux) can't ask the others their
> thoughts and opinions, then the community has failed in a large respect.  
> Take this letter as you will.
> 

Re: ZFS with Linux: An Open Plea

[Jesper Juhl]

On 14/04/07, David R. Litwin <presently42@gmail.com> wrote:
> Before I go on, let me appologise. I don't really know what I hope to
> accomplish, beyond trying to garner thoughts (and support?) for the topic.
>
> Essentially: I want to use Linux and ZFS. I don't particularly care about
> licences or any of the rest of that nonsense.

The license that protects the code we write is far from nonsense.

>The code is there; it merely
> needs to be made to work with Linux. Done and done -- provided I can find
> some one to do this for me (I'd do it myself, but I haven't the foggiest
> notion how to go about such a feat).
>
I suggest the first thing you do is contact the ZFS developers and
convince them to release their code under a license that's GPL
compatible, then we can start looking at a Linux port.

> By the way, forget about this FUSE business. I don't know why they're
> bothering: It's not real, it's slow and, in general, silly.
>
FUSE is nice for trying out new and interresting ideas in userspace -
it has its uses.

> What are the thoughts of the Linux community?
>
Can't tell you that, all I can tell you is my own oppinion.  I believe
ZFS for Linux would be interresting, if not for any other reason then
for compatibility. I'd personally like to see it - but, settle the
license issue first.


-- 
Jesper Juhl <jesper.juhl@gmail.com>
Don't top-post  http://www.catb.org/~esr/jargon/html/T/top-post.html
Plain text mails only, please      http://www.expita.com/nomime.html

Re: ZFS with Linux: An Open Plea

[David Chinner]

On Sat, Apr 14, 2007 at 08:56:40PM +0200, Krzysztof Halasa wrote:
> Neil Brown <neilb@suse.de> writes:
> 
> > What, specifically, is there in ZFS that you want to use in Linux?
> > There is lots of interesting stuff in there, but which bit has caught
> > your attention?  It is possible that that functionality can be
> > incorporated into Linux without trying to clone or copy ZFS.
> 
> Filesystem block hashes (checksums) and in-fs redundancy (using the
> hashes to determine which copy of data is correct in case of
> corruption). It would mean multi-device filesystem.

Yup - multidevice support in XFS is something I'm working on
at the moment. There's many nice features that multi-device
filesystems can take advantage of (different geomteries,
multiple journals, internal RAID, redundancy, partially
online/offline filesystems, partial filesystem repair, etc).

Cheers,

Dave.
-- 
Dave Chinner
Principal Engineer
SGI Australian Software Group

Re: ZFS with Linux: An Open Plea

[Tomasz Kłoczko]

[-- Attachment #1: Type: TEXT/PLAIN, Size: 2036 bytes --]

On Sat, 14 Apr 2007, Jan Engelhardt wrote:

>
> On Apr 14 2007 10:04, Mike Snitzer wrote:
>>
>> ZFS does have some powerful features but much of it depends on their
>> broken layering of volume management.  Embedding the equivalent of LVM
>> into a filesystem _feels_ quite wrong.
>>
>> [...]
>>
>> Unfortunately in order for Linux to incorporate such a feature I'd
>> imagine a new filesystem would need to be developed with redirect on
>> write at its core.  Can't really see ext4 or any other existing Linux
>> filesystem grafting such a feature into it.  But even though I can't
>> see it; do others?
>
> FUSE-based filesystems. (That said, might wanna try through
> "ZFS-on-fuse" fs).

FUSE implemtation uses too many context switches on each I/O so on the 
same hardware it will never will be so fast as on Linux, BSD and MOX (yes 
ZFS is now avalaible on all this OSes .. and few people says Windows 
implemtation is very close). Current FUSE implemntation can't be 
comparable in aspects of speed and probably never will be on using threads 
(very simmilar case to ALSA and mixing in user space .. in both cases it 
is broken by design). Also ZFS on Solaris uses few other system abilities 
for example it interract with PSH.

So FUSE ZFS is IMO only kind of academic demo implemtation only but never 
will be usefull/ready for production (plain waste of time). If Linux 
licensing will not be relaxed probaly we can forget about ZFS on Linux 
(licensing problems in this case are obly on Linux side .. <ironically>in 
this case ZFS licensing is more oppened than Linux licensing 
</ironically>).

kloczek
PS. IIRC implemting ZFS on FUSE was some kind of workaround for licensing 
issue but FUSE fill uses vfs layer and probaly still thinking about
licensing is actual.
-- 
-----------------------------------------------------------
*Ludzie nie mają problemów, tylko sobie sami je stwarzają*
-----------------------------------------------------------
Tomasz Kłoczko, sys adm @zie.pg.gda.pl|*e-mail: kloczek@rudy.mif.pg.gda.pl*

Re: ZFS with Linux: An Open Plea

[Tomasz Kłoczko]

[-- Attachment #1: Type: TEXT/PLAIN, Size: 1098 bytes --]

On Sat, 14 Apr 2007, Mike Snitzer wrote:
[..]
> ZFS does have some powerful features but much of it depends on their
> broken layering of volume management.  Embedding the equivalent of LVM
> into a filesystem _feels_ quite wrong.

Hundret years ago some people told "people can fly depends on broken 
idea".

LVM was never defined strictly and no one says current LVM 
"definition/abstracion" is finished and complet .. try to think about this 
and never use phrases like "broken idea" when you have real proof for 
"people can fly" because you can simple look on sky or "embedding the 
equivalent of LVM into a filesystem _feels_ quite wrong" when you can
use real and working ZFS on some OSes .. specialy when this new 
"definition" of LVM provides better functionalities than current FS 
way of thinking about some OS aspects.

kloczek
-- 
-----------------------------------------------------------
*Ludzie nie mają problemów, tylko sobie sami je stwarzają*
-----------------------------------------------------------
Tomasz Kłoczko, sys adm @zie.pg.gda.pl|*e-mail: kloczek@rudy.mif.pg.gda.pl*

Re: ZFS with Linux: An Open Plea

[John Anthony Kazos Jr.]

> FUSE implemtation uses too many context switches on each I/O so on the same
> hardware it will never will be so fast as on Linux, BSD and MOX (yes ZFS is
> now avalaible on all this OSes .. and few people says Windows implemtation is
> very close). Current FUSE implemntation can't be comparable in aspects of
> speed and probably never will be on using threads (very simmilar case to ALSA
> and mixing in user space .. in both cases it is broken by design). Also ZFS on
> Solaris uses few other system abilities for example it interract with PSH.
> 
> So FUSE ZFS is IMO only kind of academic demo implemtation only but never will
> be usefull/ready for production (plain waste of time). If Linux licensing will
> not be relaxed probaly we can forget about ZFS on Linux (licensing problems in
> this case are obly on Linux side .. <ironically>in this case ZFS licensing is
> more oppened than Linux licensing </ironically>).
> 
> kloczek
> PS. IIRC implemting ZFS on FUSE was some kind of workaround for licensing
> issue but FUSE fill uses vfs layer and probaly still thinking about
> licensing is actual.

I'm just a lowly proto-hacker trying to get into kernel development, but 
even I know a few things, and I'm getting very tired of hearing FUSE 
slammed as stupid and the Linux licencing policy as foolish. I can sum 
things up in two short passages.

FUSE is intended for end-users, not critical server applications. 
End-users have plenty of processor to spare at lower-than-ever prices. So 
you have a simple and flexible end-user API that lets you do anything with 
anything in any way you want, all the time, without needing to (or even 
needing to be able to) alter your kernel. Win.

Linux licencing basically says, "If you want in on this good thing, you 
have to play by the rules. That means no cheating, no scamming, no 
profiting at the expense of others, and no getting on a high horse and 
proclaiming to the rest of the world that you are in control of their 
destinies. Play nice, kiddies." If you want to do something, you do it 
open and you do it Free, and if you don't want to, well...write your own 
kernel!

There is a wonderful quotation on the GNU site comparing agencies like 
Microsoft to crack dealers: They appear more open in theory in order to 
get people hooked, then trigger the beartrap around your foot. Linux has 
rules--hard, fast, and immutable--and they protect everybody from their 
own stupidities. Open-community development takes a whole lot longer, but 
you don't have to sell your soul to do it.

Re: ZFS with Linux: An Open Plea

[Tomasz Kłoczko]

[-- Attachment #1: Type: TEXT/PLAIN, Size: 3045 bytes --]

On Mon, 16 Apr 2007, Mike Snitzer wrote:
[..]
> The ZFS volume management piece could've easily been abstracted to be
> outside of the actual filesystem.

Sorry .. but can you poof this by show one example of this kind of 
problems ?

> In fact its more natural to maintain that separation.

Sorry but cause of developing ZFS was not braking classic/"natural" FS 
abstraction but try to solve things like limited I/O bandwich and 
statatistical number of errors on storing portion informations (it 
~constant but capacity of used storage divices grows) now avalaible 
storage devices and simplify managing hundrets or thousands phisical 
devices. From this point of view it is state of art.

> It allows people to have choices about how they manage the underlying 
> block layer rather than imposing one specialized solution.  Look at the 
> various technologies in Linux (LVM2, MD, Linux Multipath) to understand 
> the flexibility Linux provides for managing storage.

Except ext4 all this all this technologies not solves some problems which 
are plugged by ZFS. Also adding checksuming to ext3 (aka ext4) it is not 
all what profides ZFS way ..

> Not to mention the availability of commercial solutions from the various 
> storage vendors.

It is not matter comercial/non-commercial .. forget about this argument 
(don't practice this kind of FUDing).

ZFS was implemnted and is useable .. very useable like many commersial 
technologiess (do you remenber form where come NFS to Linux ?)
It is so useable it case many people are now ready for switch from Linux 
to Solaris.
Few days ago I'm swich two backup servers with few TB storage from Linux 
to Solaris .. only because client want use ZFS .. because ZFS is EXCELENT 
for this kind tasks (only because it allow save many thousands of 
<put_your_currency_name> because it allow better utilize the same storage) 
and trust me .. cases like this will be more .. much more and changing 
licensing Linux code will be MUCH more easier than reinventing wheel (wich 
will be reimplemnting ZFS under GPL).

Problem is not on technical area but on licensing and it is plain Linux 
word problem because neccessary in this case changes on CDDL side will 
make this code less oppended than now .. so you can (probably ?) forget 
about GPLing ZFS code (and ZFS it is not all what will good to have from 
Sol in Linux).
IMO current Linux licensing less is importand than bringing in possible 
simpler way things like ZFS to Linux. So best/simpler way will be start 
change Linux licensing for save all GPL goodies and allow interract with 
code on license like CDDL.
Licensing is for allow keep in best possible form Linux. If it can't do 
this in best possible way it must be change (must evolve .. like 
many othes things around).

kloczek
-- 
-----------------------------------------------------------
*Ludzie nie mają problemów, tylko sobie sami je stwarzają*
-----------------------------------------------------------
Tomasz Kłoczko, sys adm @zie.pg.gda.pl|*e-mail: kloczek@rudy.mif.pg.gda.pl*

Re: ZFS with Linux: An Open Plea

[Stefan Richter]

Tomasz Kłoczko wrote:
> Current FUSE implemntation can't be 
> comparable in aspects of speed and probably never will be on using threads

Did you measure this on a few hardwares and workloads?

> (very simmilar case to ALSA and mixing in user space ..

Audio is about guaranteed latency, not "speed".
-- 
Stefan Richter
-=====-=-=== -=-- -==-=
http://arcgraph.de/sr/

Re: ZFS with Linux: An Open Plea

[Tomasz Kłoczko]

[-- Attachment #1: Type: TEXT/PLAIN, Size: 1578 bytes --]

On Mon, 16 Apr 2007, Stefan Richter wrote:

> Tomasz Kłoczko wrote:
>> Current FUSE implemntation can't be
>> comparable in aspects of speed and probably never will be on using threads
>
> Did you measure this on a few hardwares and workloads?

Before asking firs you must try look on current ZFS on FUSE 
discuss phorums/docu .. like on: 
http://groups.google.com/group/zfs-fuse/feed/rss_v2_0_msgs.xml

ZFS on Solaris provides for many workloads better speed than any Linux 
technology on the same hardware but ZFS ond FUSE in current form provides 
lower speed than now avalaible Linux technologies.

Example http://groups.google.com/group/zfs-fuse/msg/5b10c69707a46c07:

"According to bonnie, I see 125 MB/s reads on ext3+RAID5, 65 MB/s on 
ZFS+RAID5 (using Linux's software RAID) and 20 MB/s on ZFS+raidz (using 
the same raw drives).  Writes are also proportionally slower.  The real 
performance hit with ZFS-FUSE was random accesses for lots of small files. 
The bonnie++ results showed something like 75 random seeks for ZFS vs 470 
for ext3 (..)"

On the same phorun you can find threads with discuss about utilize 
treading under FUSE.

>> (very simmilar case to ALSA and mixing in user space ..
>
> Audio is about guaranteed latency, not "speed".

You meam "guaranteed worser latency" ? excelent 8-)

kloczek
-- 
-----------------------------------------------------------
*Ludzie nie mają problemów, tylko sobie sami je stwarzają*
-----------------------------------------------------------
Tomasz Kłoczko, sys adm @zie.pg.gda.pl|*e-mail: kloczek@rudy.mif.pg.gda.pl*

Re: ZFS with Linux: An Open Plea

[Adrian Bunk]

On Mon, Apr 16, 2007 at 04:01:23PM +0200, Tomasz Kłoczko wrote:
>...
> Few days ago I'm swich two backup servers with few TB storage from Linux to 
> Solaris .. only because client want use ZFS .. because ZFS is EXCELENT for 
> this kind tasks (only because it allow save many thousands of 
> <put_your_currency_name> because it allow better utilize the same storage) 
> and trust me .. cases like this will be more .. much more and changing 
> licensing Linux code will be MUCH more easier than reinventing wheel (wich 
> will be reimplemnting ZFS under GPL).

This is a technical mailing list, so let's start with technical 
arguments:

Why did this client want to use ZFS?

Because his boss was convinced by a marketing guy that ZFS was the best 
invention since sliced bread?

Or due to technical limitations in what Linux currently offers 
resulting in ZFS bringing him direct advantages on these servers?

If the latter, what exactly?

> Problem is not on technical area but on licensing and it is plain Linux 
> word problem because neccessary in this case changes on CDDL side will make 
> this code less oppended than now .. so you can (probably ?) forget about 
> GPLing ZFS code (and ZFS it is not all what will good to have from Sol in 
> Linux).
> IMO current Linux licensing less is importand than bringing in possible 
> simpler way things like ZFS to Linux. So best/simpler way will be start 
> change Linux licensing for save all GPL goodies and allow interract with 
> code on license like CDDL.
> 
> Licensing is for allow keep in best possible form Linux. If it can't do 
> this in best possible way it must be change (must evolve .. like many othes 
> things around).

There are at about 10.000 people who contributed to the Linux kernel, 
some of them unreachable or even dead.

AFAIK the only way to relicense the Linux kernel that wouldn't be 
legally questionable in any jurisdiction would be to get each one of 
them to agree to the license change.

IOW, it's more or less practically impossible to relicense the kernel.

If the GPL is a problem for you, FreeBSD might be a good choice for you.

> kloczek

cu
Adrian

-- 

       "Is there not promise of rain?" Ling Tan asked suddenly out
        of the darkness. There had been need of rain for many days.
       "Only a promise," Lao Er said.
                                       Pearl S. Buck - Dragon Seed

Re: ZFS with Linux: An Open Plea

[Christoph Hellwig]

On Mon, Apr 16, 2007 at 04:20:41PM +0200, Tomasz K?oczko wrote:
> ZFS on Solaris provides for many workloads better speed than any Linux 
> technology on the same hardware but ZFS ond FUSE in current form provides 
> lower speed than now avalaible Linux technologies.

Numbers, please.  So far in all interesting benchmarks it actually
was slower.  But when they're faster than XFS somewhere I'd defintly
be interesting in looking at why this is true and if possible and
important enough fix it.

Re: ZFS with Linux: An Open Plea

[Tomasz Kłoczko]

[-- Attachment #1: Type: TEXT/PLAIN, Size: 4479 bytes --]

On Mon, 16 Apr 2007, Adrian Bunk wrote:

> On Mon, Apr 16, 2007 at 04:01:23PM +0200, Tomasz Kłoczko wrote:
>> ...
>> Few days ago I'm swich two backup servers with few TB storage from Linux to
>> Solaris .. only because client want use ZFS .. because ZFS is EXCELENT for
>> this kind tasks (only because it allow save many thousands of
>> <put_your_currency_name> because it allow better utilize the same storage)
>> and trust me .. cases like this will be more .. much more and changing
>> licensing Linux code will be MUCH more easier than reinventing wheel (wich
>> will be reimplemnting ZFS under GPL).
>
> This is a technical mailing list, so let's start with technical
> arguments:
>
> Why did this client want to use ZFS?

Because switching to Solaris was chipper than buying next faster FC/SCSI 
storage. Simple ?

> Because his boss was convinced by a marketing guy that ZFS was the best
> invention since sliced bread?

In this scenario ther is no place for "marketing guy" .. try again .. 
(maybe it can occure in US or Germany but trust me .. not in Poland 8-)

> Or due to technical limitations in what Linux currently offers
> resulting in ZFS bringing him direct advantages on these servers?

Yes .. it is Linux limitiations because it is very hard to provide 
simultanouse streams of backup data with threaded compression (using in 
this case pbzip2) with good CPUs utilization because most streams waits on 
I/Os and most of CPUs are not fully utilized. All this becase single stram 
of compressed data can't be easy dinamically switched to another (not 
busy) disk in JBOD. ZFS by two level allocation (on device and block 
level) will not wait for finish I/O but will try use another/not busy 
device in ZFS pool. This is *main* reason integrate in one layer VFS and 
LVM in case ZFS. By integrate this two layers you can make deciion where 
data will be written depending on *current* devices utilization. In all 
other "classic" ways you will break layered OS model .. so in ZFS case 
conclution like "we must integrate this two layers in one" it is not bug 
but feacture and was FUNDAMENTAL.

This is not all .. backup data must be safe in best possible form .. in 
time .. and it mean in this case that checksumming is NECCESSARY. Look .. 
ext4 for now only have plans for implemting checksuming 
(http://www.bullopensource.org/ext4/files/ext4.txt) and ATM on Linux there 
is no FS with this kind abilities .. so yes again: this was Linux 
technical limitation.

>> Problem is not on technical area but on licensing and it is plain Linux
>> word problem because neccessary in this case changes on CDDL side will make
>> this code less oppended than now .. so you can (probably ?) forget about
>> GPLing ZFS code (and ZFS it is not all what will good to have from Sol in
>> Linux).
>> IMO current Linux licensing less is importand than bringing in possible
>> simpler way things like ZFS to Linux. So best/simpler way will be start
>> change Linux licensing for save all GPL goodies and allow interract with
>> code on license like CDDL.
>>
>> Licensing is for allow keep in best possible form Linux. If it can't do
>> this in best possible way it must be change (must evolve .. like many othes
>> things around).
>
> There are at about 10.000 people who contributed to the Linux kernel,
> some of them unreachable or even dead.

Do you know who was Paracelsus ? He was medic hundriet years ago. They 
discover and verbalise some kind fundamental (?) law for medicine which 
can be used not only on medicine area. He sayd "kills not subtance but 
dose of substance". So anything can kill you/animal/project .. you can 
kill someon also using oxigen (not only low level of oxigen kills but also 
to much can kill). Try to think on how this law on how many diffret ways 
can be trasformed/appied to this kind of arguments. Look on how many 
developers migrate to another unices in last few years (count only two for 
simplicity like Solaris and MOX). Try looking for public forums statistics 
for example Linux vs. Solaris and after this try to answer on "is it 10k 
is it realy big number in this case or not ?" (IIRC google provides very 
good tools for anyone who want this kind answers).

kloczek
-- 
-----------------------------------------------------------
*Ludzie nie mają problemów, tylko sobie sami je stwarzają*
-----------------------------------------------------------
Tomasz Kłoczko, sys adm @zie.pg.gda.pl|*e-mail: kloczek@rudy.mif.pg.gda.pl*

Re: ZFS with Linux: An Open Plea

[Tomasz Kłoczko]

[-- Attachment #1: Type: TEXT/PLAIN, Size: 1393 bytes --]

On Mon, 16 Apr 2007, Christoph Hellwig wrote:

> On Mon, Apr 16, 2007 at 04:20:41PM +0200, Tomasz K?oczko wrote:
>> ZFS on Solaris provides for many workloads better speed than any Linux
>> technology on the same hardware but ZFS ond FUSE in current form provides
>> lower speed than now avalaible Linux technologies.
>
> Numbers, please.  So far in all interesting benchmarks it actually
> was slower.  But when they're faster than XFS somewhere I'd defintly
> be interesting in looking at why this is true and if possible and
> important enough fix it.

Google still is working but .. (from my bookmarks):

http://cmynhier.blogspot.com/2006/05/zfs-io-reordering-benchmark.html
http://cmynhier.blogspot.com/2006/05/zfs-benchmarking.html

also some other interestig numbers can be founnd on:
http://milek.blogspot.com/2006/08/hw-raid-vs-zfs-software-raid-part-ii.html

Probably more can be find on looking for zfs+benchmark on 
http://blogs.sun.com/

IMO real power ZFS shows on growing number if phisical devices so don't 
look so close on this kind of documents because usualy it was prepared on 
limited number of devices.

kloczek
-- 
-----------------------------------------------------------
*Ludzie nie mają problemów, tylko sobie sami je stwarzają*
-----------------------------------------------------------
Tomasz Kłoczko, sys adm @zie.pg.gda.pl|*e-mail: kloczek@rudy.mif.pg.gda.pl*

Re: ZFS with Linux: An Open Plea

[Christoph Hellwig]

On Mon, Apr 16, 2007 at 05:46:50PM +0200, Tomasz K?oczko wrote:
> Probably more can be find on looking for zfs+benchmark on 
> http://blogs.sun.com/

If I was searching for sun marketing material I'd have fun the way
to blogs.sun.com myself, thanks :)

Re: ZFS with Linux: An Open Plea

[Adrian Bunk]

On Mon, Apr 16, 2007 at 05:27:51PM +0200, Tomasz Kłoczko wrote:
> On Mon, 16 Apr 2007, Adrian Bunk wrote:
>
>> On Mon, Apr 16, 2007 at 04:01:23PM +0200, Tomasz Kłoczko wrote:
>>> ...
>>> Few days ago I'm swich two backup servers with few TB storage from Linux 
>>> to
>>> Solaris .. only because client want use ZFS .. because ZFS is EXCELENT 
>>> for
>>> this kind tasks (only because it allow save many thousands of
>>> <put_your_currency_name> because it allow better utilize the same 
>>> storage)
>>> and trust me .. cases like this will be more .. much more and changing
>>> licensing Linux code will be MUCH more easier than reinventing wheel 
>>> (wich
>>> will be reimplemnting ZFS under GPL).
>>
>> This is a technical mailing list, so let's start with technical
>> arguments:
>>
>> Why did this client want to use ZFS?
>
> Because switching to Solaris was chipper than buying next faster FC/SCSI 
> storage. Simple ?
>
>> Because his boss was convinced by a marketing guy that ZFS was the best
>> invention since sliced bread?
>
> In this scenario ther is no place for "marketing guy" .. try again .. 
> (maybe it can occure in US or Germany but trust me .. not in Poland 8-)
>
>> Or due to technical limitations in what Linux currently offers
>> resulting in ZFS bringing him direct advantages on these servers?
>
> Yes .. it is Linux limitiations because it is very hard to provide 
> simultanouse streams of backup data with threaded compression (using in 
> this case pbzip2) with good CPUs utilization because most streams waits on 
> I/Os and most of CPUs are not fully utilized. All this becase single stram 
> of compressed data can't be easy dinamically switched to another (not busy) 
> disk in JBOD. ZFS by two level allocation (on device and block level) will 
> not wait for finish I/O but will try use another/not busy device in ZFS 
> pool. This is *main* reason integrate in one layer VFS and LVM in case ZFS. 
> By integrate this two layers you can make deciion where data will be 
> written depending on *current* devices utilization. In all other "classic" 
> ways you will break layered OS model .. so in ZFS case conclution like "we 
> must integrate this two layers in one" it is not bug but feacture and was 
> FUNDAMENTAL.

You are having IO problems doing bzip2 ???

This sounds as if your application is doing something silly like e.g. 
using O_DIRECT or you are mounting your filesystems with "-o sync".

On my 1.8 GHz Athlon, it takes 2.5 minutes to compress a 250 MB kernel 
tar to 40 MB - and this is with the data cached in RAM, so no IO 
involved. That's 1.7 MB/s resp. 0.3 MB/s.

I'm even having problems to imagine IO problems with 4 or 8 CPU 
machines doing parallel bzip2 to a single disk - with any filesystem.

> This is not all .. backup data must be safe in best possible form .. in 
> time .. and it mean in this case that checksumming is NECCESSARY. Look .. 
> ext4 for now only have plans for implemting checksuming 
> (http://www.bullopensource.org/ext4/files/ext4.txt) and ATM on Linux there 
> is no FS with this kind abilities .. so yes again: this was Linux technical 
> limitation.

bzip2 already checksums all data, so why do you need a second checksum 
at the filesystem level for your backups?

>>> Problem is not on technical area but on licensing and it is plain Linux
>>> word problem because neccessary in this case changes on CDDL side will 
>>> make
>>> this code less oppended than now .. so you can (probably ?) forget about
>>> GPLing ZFS code (and ZFS it is not all what will good to have from Sol in
>>> Linux).
>>> IMO current Linux licensing less is importand than bringing in possible
>>> simpler way things like ZFS to Linux. So best/simpler way will be start
>>> change Linux licensing for save all GPL goodies and allow interract with
>>> code on license like CDDL.
>>>
>>> Licensing is for allow keep in best possible form Linux. If it can't do
>>> this in best possible way it must be change (must evolve .. like many 
>>> othes
>>> things around).
>>
>> There are at about 10.000 people who contributed to the Linux kernel,
>> some of them unreachable or even dead.
>
> Do you know who was Paracelsus ? He was medic hundriet years ago. They 
> discover and verbalise some kind fundamental (?) law for medicine which can 
> be used not only on medicine area. He sayd "kills not subtance but dose of 
> substance". So anything can kill you/animal/project .. you can kill someon 
> also using oxigen (not only low level of oxigen kills but also to much can 
> kill). Try to think on how this law on how many diffret ways can be 
> trasformed/appied to this kind of arguments. Look on how many developers 
> migrate to another unices in last few years (count only two for simplicity 
> like Solaris and MOX). Try looking for public forums statistics for example 
> Linux vs. Solaris and after this try to answer on "is it 10k is it realy 
> big number in this case or not ?" (IIRC google provides very good tools for 
> anyone who want this kind answers).

I don't need Google for this.

It's easy to extract from git that patches that were applied to the 
Linux kernel during the last 2 years contained 3196 unique 
Signed-off-by: lines.

Some people might have lines with different email addresses, but this 
still makes > 2000 contributors during the last 2 years alone. Plus all 
the other people who contributed during the first 14 years of Linux 
kernel development but didn't during the last 2 years.

You could argue whether there were really 10.000 people or "only"
5.000 people who contributed code to the Linux kernel, but 
that doesn't make a real difference.

> kloczek

cu
Adrian

-- 

       "Is there not promise of rain?" Ling Tan asked suddenly out
        of the darkness. There had been need of rain for many days.
       "Only a promise," Lao Er said.
                                       Pearl S. Buck - Dragon Seed

Re: ZFS with Linux: An Open Plea

[Stefan Richter]

Tomasz Kłoczko wrote:
> On Mon, 16 Apr 2007, Stefan Richter wrote:
>> Tomasz Kłoczko wrote:
>>> Current FUSE implemntation can't be
>>> comparable in aspects of speed and probably never will be on using
>>> threads
>>
>> Did you measure this on a few hardwares and workloads?
> 
> Before asking firs you must try look on current ZFS on FUSE discuss
> phorums/docu .. like on:
> http://groups.google.com/group/zfs-fuse/feed/rss_v2_0_msgs.xml
> 
> ZFS on Solaris provides for many workloads better speed than any Linux
> technology on the same hardware but ZFS ond FUSE in current form
> provides lower speed than now avalaible Linux technologies.

There isn't a lot of useful facts in this last sentence.

> Example http://groups.google.com/group/zfs-fuse/msg/5b10c69707a46c07:

That's much more like it...

> "According to bonnie, I see 125 MB/s reads on ext3+RAID5, 65 MB/s on
> ZFS+RAID5 (using Linux's software RAID) and 20 MB/s on ZFS+raidz (using
> the same raw drives).  Writes are also proportionally slower.  The real
> performance hit with ZFS-FUSE was random accesses for lots of small
> files. The bonnie++ results showed something like 75 random seeks for
> ZFS vs 470 for ext3 (..)"

...although the tester doesn't say a lot about the test setup (e.g. no
word on the used hardware).

Another thread in the forum links to
http://www.ntfs-3g.org/performance.html which shows that filesystems
implemented on top of FUSE may actually yield performance in the same
league as classic Linux filesystems.  However that page doesn't say
anything about the test method either, beyond that bonnie++ was used.

> On the same phorun you can find threads with discuss about utilize
> treading under FUSE.

Could you point out what you meant by "not comparable... on using
threads"?  (Who is using which threads for what purposes; what are the
pertaining issues?)  Then I might be able to find those forum posts
which explain why a FUSE fs can never work comparably well "with threads".

>>> (very simmilar case to ALSA and mixing in user space ..
>>
>> Audio is about guaranteed latency, not "speed".
> 
> You meam "guaranteed worser latency" ?

I meant that the central requirement on the design and implementation of
audio subsystems is an (ideally guaranteed) bounded maximum of
latencies; and that's exactly the major point where I heard that there
are problems with ALSA driver components in userspace.  You were talking
about throughput of storage systems, for which latencies of the software
part of the stack do not play such a central role.  Therefore your
comparison appeared off the mark to me.
-- 
Stefan Richter
-=====-=-=== -=-- =----
http://arcgraph.de/sr/

Re: ZFS with Linux: An Open Plea

[Diego Calleja]

El Mon, 16 Apr 2007 17:46:50 +0200 (CEST), Tomasz Kłoczko <kloczek@rudy.mif.pg.gda.pl> escribió:

> also some other interestig numbers can be founnd on:
> http://milek.blogspot.com/2006/08/hw-raid-vs-zfs-software-raid-part-ii.html

So software raid can be faster than HW raid. News at 11.

Re: ZFS with Linux: An Open Plea

[Bernd Eckenfels]

In article <4623BE2E.2020800@s5r6.in-berlin.de> you wrote:
> I meant that the central requirement on the design and implementation of
> audio subsystems is an (ideally guaranteed) bounded maximum of
> latencies; and that's exactly the major point where I heard that there
> are problems with ALSA driver components in userspace.  You were talking
> about throughput of storage systems, for which latencies of the software
> part of the stack do not play such a central role.  Therefore your
> comparison appeared off the mark to me.

Unfortunatelle Latency is critical for a number of critical applications
like databases or file based transaction systems (mail, news) - mainly the
users of fsync().

Gruss
Bernd

Re: ZFS with Linux: An Open Plea

[Lee Revell]

On 4/16/07, Bernd Eckenfels <ecki@lina.inka.de> wrote:
> In article <4623BE2E.2020800@s5r6.in-berlin.de> you wrote:
> > I meant that the central requirement on the design and implementation of
> > audio subsystems is an (ideally guaranteed) bounded maximum of
> > latencies; and that's exactly the major point where I heard that there
> > are problems with ALSA driver components in userspace.  You were talking
> > about throughput of storage systems, for which latencies of the software
> > part of the stack do not play such a central role.  Therefore your
> > comparison appeared off the mark to me.
>
> Unfortunatelle Latency is critical for a number of critical applications
> like databases or file based transaction systems (mail, news) - mainly the
> users of fsync().

Whether you mix audio in userspace or kernel does not impact latency -
you still need to schedule the application playing audio every N
milliseconds or there will be dropouts.  I don't see where audio
mixing issue has any relevance to this thread.

Lee

Re: ZFS with Linux: An Open Plea

[Jörn Engel]

On Mon, 16 April 2007 17:46:50 +0200, Tomasz Kłoczko wrote:
> On Mon, 16 Apr 2007, Christoph Hellwig wrote:
> 
> >Numbers, please.  So far in all interesting benchmarks it actually
> >was slower.  But when they're faster than XFS somewhere I'd defintly
> >be interesting in looking at why this is true and if possible and
> >important enough fix it.

Christoph, could you show some numbers as well?  While I usually trust
your opinion, I have yet to see any substantial argument against ZFS
from your side.

> http://cmynhier.blogspot.com/2006/05/zfs-io-reordering-benchmark.html

http://blogs.sun.com/bill/#zfs_vs_the_benchmark

If you read closely you may notice that ZFS had relatively little to do
with read performance under heavy write load.  ZFS simply has "some fancy
I/O scheduling code" that in particular deals with deadlines.  The Linux
equivalent appears to be CONFIG_IOSCHED_DEADLINE.  But the quoted
benchmark does not mention which scheduler was used for Linux.

So unless the benchmark is redone and properly documented, its numbers
are fairly worthless.  Bummer.

> http://cmynhier.blogspot.com/2006/05/zfs-benchmarking.html

"The company I work for would probably balk if I put that script here"

No publically available benchmark.  So even if a third party wanted to,
it couldn't recreate the benchmark.  Again, fairly worthless.


So by my count, neither side has showed any worthwile numbers.  Whether
ZFS performance is better or worse is anyone's guess.

Jörn

-- 
Simplicity is prerequisite for reliability.
-- Edsger W. Dijkstra

Re: ZFS with Linux: An Open Plea

[Stefan Richter]

Bernd Eckenfels wrote:
> In article <4623BE2E.2020800@s5r6.in-berlin.de> you wrote:
>> I meant that the central requirement on the design and implementation of
>> audio subsystems is an (ideally guaranteed) bounded maximum of
>> latencies;
[...]
>> You were talking about throughput of storage systems, for which latencies
>> of the software part of the stack do not play such a central role.
[...]
> Unfortunatelle Latency is critical for a number of critical applications
> like databases or file based transaction systems (mail, news) - mainly the
> users of fsync().

Yes, I know that; and there may even be mass storage systems with actual
realtime requirements.  Note though that latencies in FUSE-based
filesystems due to (what do I know) context switches and possibly CPU
scheduling latencies are not necessarily relevant to the overall
latencies in applications which you mentioned.

Anyway, that's not at all what the original poster alluded to when he
made vague statements about FUSE vs. kernelspace filesystems, finishing
in the odd comparison with ALSA.

(Please try not to delete Ccs.)
-- 
Stefan Richter
-=====-=-=== -=-- =----
http://arcgraph.de/sr/

Re: ZFS with Linux: An Open Plea

[Tomasz Kłoczko]

[-- Attachment #1: Type: TEXT/PLAIN, Size: 2403 bytes --]

On Mon, 16 Apr 2007, Diego Calleja wrote:

> El Mon, 16 Apr 2007 17:46:50 +0200 (CEST), Tomasz Kłoczko <kloczek@rudy.mif.pg.gda.pl> escribió:
>
>> also some other interestig numbers can be founnd on:
>> http://milek.blogspot.com/2006/08/hw-raid-vs-zfs-software-raid-part-ii.html
>
> So software raid can be faster than HW raid. News at 11.

Of cources it can be true in most cases (probably for some more advanced 
RAID controlers). Few weeks ago I perform some basic test on Dell 2950 
with 8x73GB SAS disk .. just as for kill time (waiting for access to some 
bigger box ;). This small iron box have inside RAID controller (Dell uses 
in this box LSI Logic SAS MegaRAID based ctrl). Anykind combinations on 
controler level RAID was slower than using this as plain JBOD with LVM or 
MD+LVM. Diffrence between HW and soft RAID was not so big (1-6% depending 
on configuration) but allways HW produces worser results (don't ask me 
why). Finaly I decide using this disk as four RAID1 luns only because 
under Linux I can't read each phisical disk SMART data and protecting this 
by RAID on controller level and collecting SNMP traps from DRAC card was 
kind of worakaround for this (in my case it will be better constanlty 
monitor disk healt and collesting some SMART data for observe trends on 
for example zabbix graphs for try predict some faults using triggers). On 
top of this was configured diffrent types of volumes on LVM level (some 
with stripping some without, some with bigger some with smaller chunk 
size).

But .. in case ZFS diffrences can be better visable.
Q: why ?
A: because most of HW RAID controlers (nevermind is it small/simple 
internal HW controler for DAS sotorage or advances in storage processor in 
dedicated FC array) are _optimized_ for classic FS workloads but .. ZFS 
uses bunch of devices in completly diffrent way/characteristics. If you 
will see flashing LEDs on box with disk first time configurad for classic 
RAID<any_level> (nevermind soft or hw) and on second time configured for 
ZFS you will see kind of organoleptic diffrence.
And yes .. ZFS may be kind of problem for some HW vendors ;)

kloczek
-- 
-----------------------------------------------------------
*Ludzie nie mają problemów, tylko sobie sami je stwarzają*
-----------------------------------------------------------
Tomasz Kłoczko, sys adm @zie.pg.gda.pl|*e-mail: kloczek@rudy.mif.pg.gda.pl*

Re: ZFS with Linux: An Open Plea

[Bernd Eckenfels]

In article <75b66ecd0704161226t40fdb322xfc174dbf3d097bb0@mail.gmail.com> you wrote:
>> Unfortunatelle Latency is critical for a number of critical applications
>> like databases or file based transaction systems (mail, news) - mainly the
>> users of fsync().
> 
> Whether you mix audio in userspace or kernel does not impact latency -
> you still need to schedule the application playing audio every N
> milliseconds or there will be dropouts.  I don't see where audio
> mixing issue has any relevance to this thread.

Well, I was not talking about Audio - I was saying that there are a class of
applications which need low latency on commits (fsync or rename).

And for the audio mixer, the problem is that you have multiple reschedules
and data ping pong if you do user mode mixing - i guess.

Anyway.. not important. I still think filesystem servers can be a good
thing. And I really hope we will find some interesting numbers on ZFS
advantages...

Gruss
Bernd

Re: ZFS with Linux: An Open Plea

[Lennart Sorensen]

On Mon, Apr 16, 2007 at 10:18:45PM +0200, Tomasz K?oczko wrote:
> Of cources it can be true in most cases (probably for some more advanced 
> RAID controlers). Few weeks ago I perform some basic test on Dell 2950 
> with 8x73GB SAS disk .. just as for kill time (waiting for access to some 
> bigger box ;). This small iron box have inside RAID controller (Dell uses 
> in this box LSI Logic SAS MegaRAID based ctrl). Anykind combinations on 
> controler level RAID was slower than using this as plain JBOD with LVM or 
> MD+LVM. Diffrence between HW and soft RAID was not so big (1-6% depending 
> on configuration) but allways HW produces worser results (don't ask me 
> why). Finaly I decide using this disk as four RAID1 luns only because 
> under Linux I can't read each phisical disk SMART data and protecting this 
> by RAID on controller level and collecting SNMP traps from DRAC card was 
> kind of worakaround for this (in my case it will be better constanlty 
> monitor disk healt and collesting some SMART data for observe trends on 
> for example zabbix graphs for try predict some faults using triggers). On 
> top of this was configured diffrent types of volumes on LVM level (some 
> with stripping some without, some with bigger some with smaller chunk 
> size).

Does it matter that google's recent report on disk failures indicated
that SMART never predicted anything useful as far as they could tell?
Certainly none of my drive failures ever had SMART make any kind of
indication that anything was wrong.

I think the main benefit of MD raid, is that it is portable, doesn't
lock you into a specific piece of hardware, and you can span multiple
controllers, and it is likely easier to have bugs in MD raid fixed that
in some raid controller's firmware if any were to be found.  Performance
advantages are a bonus of course.

--
Len Sorensen

Re: ZFS with Linux: An Open Plea

[Jeff Garzik]

Lennart Sorensen wrote:
> On Mon, Apr 16, 2007 at 10:18:45PM +0200, Tomasz K?oczko wrote:
>> Of cources it can be true in most cases (probably for some more advanced 
>> RAID controlers). Few weeks ago I perform some basic test on Dell 2950 
>> with 8x73GB SAS disk .. just as for kill time (waiting for access to some 
>> bigger box ;). This small iron box have inside RAID controller (Dell uses 
>> in this box LSI Logic SAS MegaRAID based ctrl). Anykind combinations on 
>> controler level RAID was slower than using this as plain JBOD with LVM or 
>> MD+LVM. Diffrence between HW and soft RAID was not so big (1-6% depending 
>> on configuration) but allways HW produces worser results (don't ask me 
>> why). Finaly I decide using this disk as four RAID1 luns only because 
>> under Linux I can't read each phisical disk SMART data and protecting this 
>> by RAID on controller level and collecting SNMP traps from DRAC card was 
>> kind of worakaround for this (in my case it will be better constanlty 
>> monitor disk healt and collesting some SMART data for observe trends on 
>> for example zabbix graphs for try predict some faults using triggers). On 
>> top of this was configured diffrent types of volumes on LVM level (some 
>> with stripping some without, some with bigger some with smaller chunk 
>> size).
> 
> Does it matter that google's recent report on disk failures indicated
> that SMART never predicted anything useful as far as they could tell?
> Certainly none of my drive failures ever had SMART make any kind of
> indication that anything was wrong.
> 
> I think the main benefit of MD raid, is that it is portable, doesn't
> lock you into a specific piece of hardware, and you can span multiple
> controllers, and it is likely easier to have bugs in MD raid fixed that
> in some raid controller's firmware if any were to be found.  Performance
> advantages are a bonus of course.

SMART largely depends on how you use it.  Simply polling the current 
status will not give you all the benefits SMART provides.  On the 
dedicated servers that I rent, running the extended test ('-t long') 
often finds problems before you start losing data, or deal with a drive 
death.  Certainly not a huge sample size, but it backs up what I hear in 
the field.  Running the SMART tests on a weekly basis seems most 
effective, though you'll want to stagger the tests if running in a RAID set.

	Jeff

Re: ZFS with Linux: An Open Plea

[Valerie Henson]

On Wed, Apr 18, 2007 at 01:25:19PM -0400, Lennart Sorensen wrote:
> 
> Does it matter that google's recent report on disk failures indicated
> that SMART never predicted anything useful as far as they could tell?
> Certainly none of my drive failures ever had SMART make any kind of
> indication that anything was wrong.

I saw that talk, and that's not what I got out of it.  They found that
SMART error reports _did_ correlate with drive failure.  See page 8
of:

http://www.usenix.org/events/fast07/tech/full_papers/pinheiro/pinheiro.pdf

(If you're not a USENIX member, you may be able to find a free
download copy elsewhere.)

However, they found that the correlation was not strong enough to make
it economically feasible to replace disks reporting SMART failures,
since something like 70% of disks were still working a year after the
first failure report.  Also, they found that some disks failed without
any SMART error reports.

Now, Google keeps multiple copies (3 in GoogleFS, last I heard) of
data, so for them, "economically feasible" means something different
than for my personal laptop hard drive.  I have twice had my laptop
hard drive start spitting SMART errors and then die within a week.  It
is economically quite sensible for me to replace my laptop drive once
it has an error, since I don't carry around 3 laptops everywhere I go.

-VAL

Re: ZFS with Linux: An Open Plea

[Matt Mackall]

On Thu, Apr 26, 2007 at 10:21:02PM -0700, Valerie Henson wrote:
> On Wed, Apr 18, 2007 at 01:25:19PM -0400, Lennart Sorensen wrote:
> > 
> > Does it matter that google's recent report on disk failures indicated
> > that SMART never predicted anything useful as far as they could tell?
> > Certainly none of my drive failures ever had SMART make any kind of
> > indication that anything was wrong.
> 
> I saw that talk, and that's not what I got out of it.  They found that
> SMART error reports _did_ correlate with drive failure.

In fact, a certain small set of SMART indicators were a very good sign
that a drive would fail.

> However, they found that the correlation was not strong enough to make
> it economically feasible to replace disks reporting SMART failures,
> since something like 70% of disks were still working a year after the
> first failure report.  Also, they found that some disks failed without
> any SMART error reports.

Indeed, SMART registered no counts at all for most failures, so on the
whole, it can't be said that SMART can predict failures.

So: not a good idea to base your backup scheme on SMART warnings, but
not entirely useless.

-- 
Mathematics is the supreme nostalgia of our time.

Re: ZFS with Linux: An Open Plea

[Tomasz Kłoczko]

[-- Attachment #1: Type: TEXT/PLAIN, Size: 610 bytes --]

On Fri, 13 Apr 2007, David R. Litwin wrote:
[..]

I'm just found something new in filtered folder by "ZFS" word in RSS feed 
from blogs.sun.com and on firs look it may be some continuation of this 
thread:

http://blogs.sun.com/darren/entry/zfs_under_gplv2_already_exists

I'm not check completly this .. so don't beat me if it is not true :)

kloczek
-- 
-----------------------------------------------------------
*Ludzie nie mają problemów, tylko sobie sami je stwarzają*
-----------------------------------------------------------
Tomasz Kłoczko, sys adm @zie.pg.gda.pl|*e-mail: kloczek@rudy.mif.pg.gda.pl*

Re: ZFS with Linux: An Open Plea

[Alan Cox]

On Wed, 2 May 2007 17:03:22 +0200 (CEST)
Tomasz Kłoczko <kloczek@rudy.mif.pg.gda.pl> wrote:

> On Fri, 13 Apr 2007, David R. Litwin wrote:
> [..]
> 
> I'm just found something new in filtered folder by "ZFS" word in RSS feed 
> from blogs.sun.com and on firs look it may be some continuation of this 
> thread:
> 
> http://blogs.sun.com/darren/entry/zfs_under_gplv2_already_exists
> 
> I'm not check completly this .. so don't beat me if it is not true :)

Useful if accurate as the GPLv2 and Sun origin means youa re clear for
any patents Sun used in that code but maybe not for any in the pure CDDL
bits. Definitely positive.

Re: ZFS with Linux: An Open Plea

[Theodore Tso]

On Wed, May 02, 2007 at 04:42:47PM +0100, Alan Cox wrote:
> > I'm just found something new in filtered folder by "ZFS" word in RSS feed 
> > from blogs.sun.com and on firs look it may be some continuation of this 
> > thread:
> > 
> > http://blogs.sun.com/darren/entry/zfs_under_gplv2_already_exists
> > 
> > I'm not check completly this .. so don't beat me if it is not true :)
> 
> Useful if accurate as the GPLv2 and Sun origin means youa re clear for
> any patents Sun used in that code but maybe not for any in the pure CDDL
> bits. Definitely positive.

Well, except remember that they only made sources available so that
GRUB could boot OpenSolaris.  Grub only requires read-only access to
the filesystem, and what was made available under GPLv2 was only a
distinct subset of the full ZFS sources.

						- Ted

Re: ZFS with Linux: An Open Plea

[Manoj Joseph]

Alan Cox wrote:
>> Please do see:
>> http://www.opensolaris.org/os/about/faq/licensing_faq/#patents
> 
> 
> Which appears to agree with everything I said not what you are claiming.
> 
> The patent license is strictly tied to their implementation and its
> derivatives under the CDDL, so specifically acts to exclude Linux.

I thought you said "incompatible with other OS products". I believe 
there are other OS products it is quite compatible with. The ports of 
ZFS seem to confirm this.

That it is compatible with the Linux kernel was not what I was arguing. :)

-Manoj

Re: ZFS with Linux: An Open Plea

[Alan Cox]

> Please do see:
> http://www.opensolaris.org/os/about/faq/licensing_faq/#patents


Which appears to agree with everything I said not what you are claiming.

The patent license is strictly tied to their implementation and its
derivatives under the CDDL, so specifically acts to exclude Linux.

Alan

Re: ZFS with Linux: An Open Plea

[Manoj Joseph]

Alan Cox wrote:

> The real test of whether Sun were serious about ZFS being anywhere but
> Solaris is what they do to license it - they've patented everything they
> can, and made the code available only under licenses incompatible with
> other OS products. Their intent is quite clear, and quite sad.

Please do see:
http://www.opensolaris.org/os/about/faq/licensing_faq/#patents

ZFS has been ported to some of those 'other OS products'. :)

My two cents...

-Manoj

Re: ZFS with Linux: An Open Plea

[Daniel Hazelton]

On Tuesday 17 April 2007 18:12:17 David Lang wrote:
> On Tue, 17 Apr 2007, Daniel Hazelton wrote:
> > On Tuesday 17 April 2007 15:58:09 Tomasz Kłoczko wrote:
> >> On Tue, 17 Apr 2007, Daniel Hazelton wrote:
> >> [..]
> >>
> >>>> Why on discussion about switching to GPL v3 Linux code this argument
> >>>> was allways taken as "piece of cake". Why in case switching to another
> >>>> license which will allow use CDDL code just it is most importand contr
> >>>> argument ?
> >>>>
> >>>> kloczek
> >>>
> >>> Because *EVERY* version of the GPL contains the "or any later version
> >>> of this license" clause (except, now, the version being used with the
> >>> Linux kernel)
> >>
> >> So after around commented swiching to GPL v3 it will be possible to
> >> start work on GLP v3.5 which will allow easy reuse CDDL code under Linux
> >> .. good to know :o)
> >
> > Nope. Note that I said "Except the Linux Kernel".
> >
> > After the discussions that took place back around the time of the release
> > of the first draft of GPLv3 it was decided to lock Linux to *ONLY* GPLv2
>
> actually the GPLv2 only predates the GPLv3 draft by several years
>
> there are quite a few other projects that are also GPLv2 only
>
> > So the Linux kernel will *never* be able to have a version of the GPL
> > other than the current one applied. This change might have occurred
> > without the knowledge or agreement of the FSF, who maintain the GPL, but
> > since it was done with the complete agreement of all the current
> > developers - and assumed agreement of any who contributed and are no
> > longer able to consent (since their code was originally released under
> > GPLv2) - it should stand. After all, the form of the license that applies
> > to the kernel is shipped with the kernels sources.
>
> the 'or later' version is not part of the GPLv2 license itself, it's a burb
> that the FSF suggests that people use so that they (the FSF) can
> retroactivly change the license of the code that other people create.
>
> The dispute over the GPLv3 is if these retroactive chagnes aer to the
> benifit or detriment of the people who created the code.
>
> > In fact, from the copy in the latest Git:
> > NOTE! This copyright does *not* cover user programs that use kernel
> > services by normal system calls - this is merely considered normal use
> > of the kernel, and does *not* fall under the heading of "derived work".
> > Also note that the GPL below is copyrighted by the Free Software
> > Foundation, but the instance of code that it refers to (the Linux
> > kernel) is copyrighted by me and others who actually wrote it.
> >
> > Also note that the only valid version of the GPL as far as the kernel
> > is concerned is _this_ particular version of the license (ie v2, not
> > v2.2 or v3.x or whatever), unless explicitly otherwise stated.
> >
> >                        Linus Torvalds
> > -----------------
>
> take a look at the date that this went into the kernel

Yeah, I did afterwards. Perhaps it was because of the discussion that occurred 
then that I remember it.

> >> How many years it will take ? two, three ? more ? (it will be
> >> good to know how long we must wait on ZFS under Linux .. I don't belive
> >> in rewriting ZFS code time and make it so useable on production as *now*
> >> it is possible under Solaris/*BSD/MOX and passing all pointless arguing
> >> will take shorter time) .. or maybe never because some people says
> >> something like "Linux is in GPL cage".
> >
> > Linux is not in any cage - Solaris and ZFS, because of the CDDL, sit
> > inside the cage. I, personally, will *NEVER* release code meant to be
> > "open source" under a license that makes demands like those of the user.
>
> and similarly, many people will not release code under a license that lets
> other people change the terms years later.

Agreed. This is something that I would never do. 

DRH

>
> David Lang

Re: ZFS with Linux: An Open Plea

[Roland Dreier]

 > After the discussions that took place back around the time of the release of 
 > the first draft of GPLv3 it was decided to lock Linux to *ONLY* GPLv2

This is not accurate.  As far back as I can easily check, the kernel's
COPYING file has said:

 Also note that the only valid version of the GPL as far as the kernel
 is concerned is _this_ particular version of the license (ie v2, not
 v2.2 or v3.x or whatever), unless explicitly otherwise stated.

To be really precise, there was a trivial rewording of this sometime
around Feb 2002 to make it clearer, but the point is that the kernel
has been GPL v2 only long before the GPL v3 process started.

 - R.

Re: ZFS with Linux: An Open Plea

[Daniel Hazelton]

On Tuesday 17 April 2007 15:58:09 Tomasz Kłoczko wrote:
> On Tue, 17 Apr 2007, Daniel Hazelton wrote:
> [..]
>
> >> Why on discussion about switching to GPL v3 Linux code this argument was
> >> allways taken as "piece of cake". Why in case switching to another
> >> license which will allow use CDDL code just it is most importand contr
> >> argument ?
> >>
> >> kloczek
> >
> > Because *EVERY* version of the GPL contains the "or any later version of
> > this license" clause (except, now, the version being used with the Linux
> > kernel)
>
> So after around commented swiching to GPL v3 it will be possible to start
> work on GLP v3.5 which will allow easy reuse CDDL code under Linux .. good
> to know :o)

Nope. Note that I said "Except the Linux Kernel".

After the discussions that took place back around the time of the release of 
the first draft of GPLv3 it was decided to lock Linux to *ONLY* GPLv2

So the Linux kernel will *never* be able to have a version of the GPL other 
than the current one applied. This change might have occurred without the 
knowledge or agreement of the FSF, who maintain the GPL, but since it was 
done with the complete agreement of all the current developers - and assumed 
agreement of any who contributed and are no longer able to consent (since 
their code was originally released under GPLv2) - it should stand. After all, 
the form of the license that applies to the kernel is shipped with the 
kernels sources.

In fact, from the copy in the latest Git:
 NOTE! This copyright does *not* cover user programs that use kernel
 services by normal system calls - this is merely considered normal use
 of the kernel, and does *not* fall under the heading of "derived work".
 Also note that the GPL below is copyrighted by the Free Software
 Foundation, but the instance of code that it refers to (the Linux
 kernel) is copyrighted by me and others who actually wrote it.

 Also note that the only valid version of the GPL as far as the kernel
 is concerned is _this_ particular version of the license (ie v2, not
 v2.2 or v3.x or whatever), unless explicitly otherwise stated.

                        Linus Torvalds
-----------------

So the Linux kernel, unless things change some years in the future, will never 
have a license completely compatible with the CDDL. (and the CDDL isn't 
really a "Free Software" license in the GPL vein because it makes demands 
such as retention of the header blocks and reserves Sun (or whoever is 
releasing code under the CDDL) the right to revoke the implicit patent grant 
the license offers.)

> How many years it will take ? two, three ? more ? (it will be
> good to know how long we must wait on ZFS under Linux .. I don't belive in
> rewriting ZFS code time and make it so useable on production as *now* it
> is possible under Solaris/*BSD/MOX and passing all pointless arguing will
> take shorter time) .. or maybe never because some people says
> something like "Linux is in GPL cage".

Linux is not in any cage - Solaris and ZFS, because of the CDDL, sit inside 
the cage. I, personally, will *NEVER* release code meant to be "open source" 
under a license that makes demands like those of the user.

DRH

Re: ZFS with Linux: An Open Plea

[David Lang]

[-- Attachment #1: Type: TEXT/PLAIN, Size: 3551 bytes --]

On Tue, 17 Apr 2007, Daniel Hazelton wrote:

> 
> On Tuesday 17 April 2007 15:58:09 Tomasz Kłoczko wrote:
>> On Tue, 17 Apr 2007, Daniel Hazelton wrote:
>> [..]
>>
>>>> Why on discussion about switching to GPL v3 Linux code this argument was
>>>> allways taken as "piece of cake". Why in case switching to another
>>>> license which will allow use CDDL code just it is most importand contr
>>>> argument ?
>>>>
>>>> kloczek
>>>
>>> Because *EVERY* version of the GPL contains the "or any later version of
>>> this license" clause (except, now, the version being used with the Linux
>>> kernel)
>>
>> So after around commented swiching to GPL v3 it will be possible to start
>> work on GLP v3.5 which will allow easy reuse CDDL code under Linux .. good
>> to know :o)
>
> Nope. Note that I said "Except the Linux Kernel".
>
> After the discussions that took place back around the time of the release of
> the first draft of GPLv3 it was decided to lock Linux to *ONLY* GPLv2

actually the GPLv2 only predates the GPLv3 draft by several years

there are quite a few other projects that are also GPLv2 only

> So the Linux kernel will *never* be able to have a version of the GPL other
> than the current one applied. This change might have occurred without the
> knowledge or agreement of the FSF, who maintain the GPL, but since it was
> done with the complete agreement of all the current developers - and assumed
> agreement of any who contributed and are no longer able to consent (since
> their code was originally released under GPLv2) - it should stand. After all,
> the form of the license that applies to the kernel is shipped with the
> kernels sources.

the 'or later' version is not part of the GPLv2 license itself, it's a burb that 
the FSF suggests that people use so that they (the FSF) can retroactivly change 
the license of the code that other people create.

The dispute over the GPLv3 is if these retroactive chagnes aer to the benifit or 
detriment of the people who created the code.

> In fact, from the copy in the latest Git:
> NOTE! This copyright does *not* cover user programs that use kernel
> services by normal system calls - this is merely considered normal use
> of the kernel, and does *not* fall under the heading of "derived work".
> Also note that the GPL below is copyrighted by the Free Software
> Foundation, but the instance of code that it refers to (the Linux
> kernel) is copyrighted by me and others who actually wrote it.
>
> Also note that the only valid version of the GPL as far as the kernel
> is concerned is _this_ particular version of the license (ie v2, not
> v2.2 or v3.x or whatever), unless explicitly otherwise stated.
>
>                        Linus Torvalds
> -----------------

take a look at the date that this went into the kernel

>> How many years it will take ? two, three ? more ? (it will be
>> good to know how long we must wait on ZFS under Linux .. I don't belive in
>> rewriting ZFS code time and make it so useable on production as *now* it
>> is possible under Solaris/*BSD/MOX and passing all pointless arguing will
>> take shorter time) .. or maybe never because some people says
>> something like "Linux is in GPL cage".
>
> Linux is not in any cage - Solaris and ZFS, because of the CDDL, sit inside
> the cage. I, personally, will *NEVER* release code meant to be "open source"
> under a license that makes demands like those of the user.

and similarly, many people will not release code under a license that lets other 
people change the terms years later.

David Lang

Re: ZFS with Linux: An Open Plea

[Ricardo Correia]

Ricardo Correia wrote:
> That FAQ entry is outdated, ZFS can recover from metadata corruption on
> non-replicated pools for a long time already.

Just a clarification, ZFS not only detects metadata corruption through
the use of checksums but, since it keeps 2-3 copies of each metadata
block on-disk (even on non-replicated pools), it also rewrites the
corrupted blocks, effectively repairing the corruption.

All of this is done transparently to the user but, of course, it's
possible to see a report of checksum failures.

Re: ZFS with Linux: An Open Plea

[Tomasz Kłoczko]

[-- Attachment #1: Type: TEXT/PLAIN, Size: 2140 bytes --]

On Tue, 17 Apr 2007, Daniel Hazelton wrote:
[..]
>> Why on discussion about switching to GPL v3 Linux code this argument was
>> allways taken as "piece of cake". Why in case switching to another license
>> which will allow use CDDL code just it is most importand contr argument ?
>>
>> kloczek
>
> Because *EVERY* version of the GPL contains the "or any later version of this
> license" clause (except, now, the version being used with the Linux kernel)

So after around commented swiching to GPL v3 it will be possible to start 
work on GLP v3.5 which will allow easy reuse CDDL code under Linux .. good 
to know :o)
How many years it will take ? two, three ? more ? (it will be 
good to know how long we must wait on ZFS under Linux .. I don't belive in 
rewriting ZFS code time and make it so useable on production as *now* it 
is possible under Solaris/*BSD/MOX and passing all pointless arguing will 
take shorter time) .. or maybe never because some people says 
something like "Linux is in GPL cage".

Hmm .. transforming KProbes/systemtap to someting useable as DTrace was 
started more than two years ago and I don't see end of base work (sill on 
start). Make ALSA so useable as OSS it was next three trashed years 
(because some developers stays on position "mixing audio in kernel space 
is dangerous") and also not finished in many points. LVM still isnt't 
Veritas. I don't see OpenVZ to tries be so useable and easy for managa as 
Solaris zoning (why OpenVZ people can't use the same commands syntax for 
manage zones as under Solaris .. command syntax is not patented :). Also 
.. moment .. moment .. for what I'm waiting if I can install and use 
Solaris/*BSD/MOX *NOW* ??? Why still contribute any code to project which 
seems must die ? (Is is realy true that some beeings which can't evolve in 
changeing enviroment will not survive .. ?)

EOT .. sorry

kloczek
-- 
-----------------------------------------------------------
*Ludzie nie mają problemów, tylko sobie sami je stwarzają*
-----------------------------------------------------------
Tomasz Kłoczko, sys adm @zie.pg.gda.pl|*e-mail: kloczek@rudy.mif.pg.gda.pl*

Re: ZFS with Linux: An Open Plea

[Ricardo Correia]

Florian Weimer wrote:
> <http://opensolaris.org/os/community/zfs/faq/#zfspanic>
> 
> I keep hoping that this FAQ entry is outdated, but the date on that
> page is rather current. 8-/

That FAQ entry is outdated, ZFS can recover from metadata corruption on
non-replicated pools for a long time already.

Background scrubbing and the ability to see a list of corrupted files
has also been available for a long time (even longer than the above).

Re: ZFS with Linux: An Open Plea

[Florian Weimer]

* Theodore Tso:

> we can continue trying to innovate around better filesystem and LVM
> storage technologies, as opposed to trying to chase the ZFS tail
> lights.

Indeed.  Here's a gem from the official ZFS FAQ:

| What can I do if ZFS panics on every boot?
| 
|     ZFS is designed to survive arbitrary hardware failures through the
|     use of redundancy (mirroring or RAID-Z). Unfortunately, certain
|     failures in non-replicated configurations can cause ZFS to panic
|     when trying to load the pool. This is a bug, and will be fixed in
|     the near future (along with several other nifty features like
|     background scrubbing and the ability to see a list of corrupted
|     files). In the meantime, if you find yourself in the situation
|     where you cannot boot due to a corrupt pool, do the followng:
| 
|        1. boot using '-m milestone=none'
|        2. # mount -o remount /
|        3. # rm /etc/zfs/zpool.cache
|        4. # reboot
| 
|     This will remove all knowledge of pools from your system. You will
|     have to re-create your pool and restore from backup.

<http://opensolaris.org/os/community/zfs/faq/#zfspanic>

I keep hoping that this FAQ entry is outdated, but the date on that
page is rather current. 8-/

Re: ZFS with Linux: An Open Plea

[Theodore Tso]

On Tue, Apr 17, 2007 at 12:22:19PM -0400, Daniel Hazelton wrote:
> Nope. You've just ignored it when it was explained *why* the existing ZFS code 
> cannot be simply be ported to Linux. If you really need ZFS on linux, might I 
> suggest that you port the code on your own and maintain whatever patches are 
> needed to use it? As it stands ZFS *might* show up in Linux as a from-scratch 
> implementation, although I stress the "might" because there are patents 
> involved.

Given that Sun has reportedly filed a huge number of patents covering
ZFS and has refused to make them available for anything other than
Solaris --- and there are senior Sun programmers who have on record
stated that one of the reasons why Sun picked the CDDL was precisely
because it was incompatible with GPL and Sun fears Linux ---- I
wouldn't bet on Sun being willing to making a patent license available
to a hypothetical alternate implementation of the ZFS format for
Linux.

Again, this is is Sun's fault, and it's because they fear Linux, and
it may have something to do with the fact that the vast majority of
their Opteron boxes get Linux installed instead of Solaris.  The
bottom line is that people who would like ZFS need to understand that
the code is Copyright by Sun, and there are almost certainly patents
owned by Sun, and if they choose licenses that are explicitly designed
to be incompatible with Linux, we should respect Sun's deep-seated
fear of Linux, and we can continue trying to innovate around better
filesystem and LVM storage technologies, as opposed to trying to chase
the ZFS tail lights.

Of course, this is all open source.  If someone wants to work on
reimplementing ZFS from scratch, either in userspace or in the kernel,
certainly the Linux community won't stop them.  Given the patent
issues Linus might not feel comfortable including it in the mainline
sources without a promise from Sun that they won't sue the pants off
of him and The Linux Foundation, but again, that's Sun's decision, and
no one else can help you there.

						- Ted

Re: ZFS with Linux: An Open Plea

[Alistair John Strachan]

On Tuesday 17 April 2007 15:48, Alan Cox wrote:
> > So who is responsible for potential changing Linux code licensing for
> > allow if not incorporate CDDL code correct interraction without breaking
> > some law ?
>
> Every single contributor, individually. Which won't happen.
>
> The real test of whether Sun were serious about ZFS being anywhere but
> Solaris is what they do to license it - they've patented everything they
> can, and made the code available only under licenses incompatible with
> other OS products. Their intent is quite clear, and quite sad.

This isn't universally true. Look at Java, for example, which Sun recently 
released parts of under an open source license -- not the CDDL, not a 
CDDL/xxx dual license, the GPL proper.

Indeed, Sun already have products that are dual licensed CDDL/GPL, for example 
the J2EE product.

> If Sun want ZFS to get used all over the place in free software then I'd
> have expected at the very least to see them throw out a copy of the code,
> docs and patent grant in a form that could be used, even if it came with
> no other assistance of any kind.

I couldn't speculate on the rationale, but it does seem that Sun's choice to 
use _only_ the CDDL with certain software (like ZFS) is deliberate.

-- 
Cheers,
Alistair.

Final year Computer Science undergraduate.
1F2 55 South Clerk Street, Edinburgh, UK.

Re: ZFS with Linux: An Open Plea

[Daniel Hazelton]

On Tuesday 17 April 2007 11:46:38 Tomasz Kłoczko wrote:
> On Tue, 17 Apr 2007, Matthew Garrett wrote:
> > On Tue, Apr 17, 2007 at 03:47:32PM +0200, Tomasz Kłoczko wrote:
> >> Realy can't or don't want (?)
> >> So who is responsible for potential changing Linux code licensing for
> >> allow if not incorporate CDDL code correct interraction without breaking
> >> some law ?
> >
> > Everyone who holds any copyright over any of the code in Linux, which is
> > several thousand people. You'd probably need permission from all of
> > them. Good luck!
>
> Why on discussion about switching to GPL v3 Linux code this argument was
> allways taken as "piece of cake". Why in case switching to another license
> which will allow use CDDL code just it is most importand contr argument ?
>
> kloczek

Because *EVERY* version of the GPL contains the "or any later version of this 
license" clause (except, now, the version being used with the Linux kernel)

DRH

Re: ZFS with Linux: An Open Plea

[Daniel Hazelton]

On Tuesday 17 April 2007 09:47:32 Tomasz Kłoczko wrote:
> On Tue, 17 Apr 2007, Theodore Tso wrote:
> [..]
>
> > Well, that was totally useless answer from the ZFS developers.  What
> > he should have told you is to contact Sun management, since they are
> > the only ones who can decide whether or not to release ZFS under a GPL
> > license, and more importantly, to give a patent license for any
> > patents they may have filed in the course of developing ZFS.  This is
> > not anything Linux developers can help you with.
>
> Realy can't or don't want (?)

As it has been explained to you before it is "can't"

> So who is responsible for potential changing Linux code licensing for
> allow if not incorporate CDDL code correct interraction without breaking
> some law ?

If I've parsed this query correctly the answer is: Linux is licensed under the 
GPL and because a number of people that have contributed code to it can no 
longer agree to a change in the license because they have died this cannot be 
changed. That was explained quite clearly in several mails as well.

> And/or what Linux can loose on follow this king changes ?
> And/or why Linux code licensing can't evolve ? Seems when Linux code was
> licensed noone was thinking about case like interraction with code under
> license like CDDL so why now it can be corrected and still many people try
> to think like "anything arond Linux must evolve .. but not Linux" (?)

When Linux was licensed under the GPL there was only *ONE* real choice for 
licensing it. Linus released the code under the GPL and there it has 
remained, with Linus leading development. If Linux had *NOT* been released 
under the GPL it would not be as popular or as powerful as it is - and that 
is not an opinion but a statement of fact.

> Why this can't be fixes ?

See the previous statement and several previous mails in this thread. Linux is 
licensed under the GPL, it is the *only* license agreed to by everyone that 
has contributed code. If I remember the statistics, there have been something 
like 10,000 different people that have contributed code. Since each 
contributor holds the copyright on their code they are the *ONLY* people that 
could change the license on it. Anyone attempting to change the license 
without agreement from *everyone* that has contributed code to the kernel 
they are in violation of US and international copyright laws.

> If in this ponit in Linux "evniroment" can't be chaged .. sorry but is it
> not kind of hipocritics ?

Nope. You've just ignored it when it was explained *why* the existing ZFS code 
cannot be simply be ported to Linux. If you really need ZFS on linux, might I 
suggest that you port the code on your own and maintain whatever patches are 
needed to use it? As it stands ZFS *might* show up in Linux as a from-scratch 
implementation, although I stress the "might" because there are patents 
involved.

DRH

(Now please, drop the subject - IMNSHO it is never going to happen)

Re: ZFS with Linux: An Open Plea

[John Anthony Kazos Jr.]

> > That's not evolution; it's de-evolution. Linux morphing to some sort of
> > mentally-damaged pseudo-proprietary licence would be like switching back
> > to a feudal society where 50 was considered unbelievably ancient.
> 
> CDDL is OSI aproved. Did you realy want to say by above something like "CDDL
> is pseudo-proprietary licence" ? Are you still taking about (and only) CDDL ?

>From what I have read, CDDL is treading the veeeerrrrrry thin line between 
an actual Free license and an actual proprietary licence. Just look at the 
nonsense Mozilla Co. has gotten itself worked up about (and judging by how 
much Firefox/Iceweasel crashes on me, being like IE is quite appropriate 
in licencing too). And (if I have not been misinformed), CDDL is inspired 
by Mozilla's licence.

The FSF has something to say.
http://www.gnu.org/licenses/license-list.html#SoftwareLicenses
So yes, CDDL is, to me, "pseudo-"proprietary, and it would be very easy 
for them to slip up and whoops! Didn't we tell you? You can do everything 
but -that-. But of course it's still free...yeah...

> > I'm sure Linus did think very closely about the interaction of his code
> > with proprietary licences. He thought about it, snickered for a few
> > moments, and made the right decision.
> 
> I don't want see problmes on border with propretary licenses at all but I see
> (and still want to talk only about) problem on on some class licenses which
> provides more oppened (and not closed) code.

The GPL is more about protection than openness. Someone can write code, 
throw it on the internet with no licence at all, and it's exactly as 
"open" as it is under the GPL. You can do anything you want with it in any 
way, just like under the GPL. What the GPL does is protect the code and 
its writer from being snapped up by somebody else, and in any way 
restricted: It makes sure the code STAYS open, and makes sure you are 
always free to do as you like with it.

Re: ZFS with Linux: An Open Plea

[Mike Snitzer]

On 4/17/07, Alan Cox <alan@lxorguk.ukuu.org.uk> wrote:
> > So who is responsible for potential changing Linux code licensing for
> > allow if not incorporate CDDL code correct interraction without breaking
> > some law ?
>
> Every single contributor, individually. Which won't happen.
>
> The real test of whether Sun were serious about ZFS being anywhere but
> Solaris is what they do to license it - they've patented everything they
> can, and made the code available only under licenses incompatible with
> other OS products. Their intent is quite clear, and quite sad.
>
> Compare it to what the old Sun company did with NFS, which is now a
> standard used everywhere.
>
> If Sun want ZFS to get used all over the place in free software then I'd
> have expected at the very least to see them throw out a copy of the code,
> docs and patent grant in a form that could be used, even if it came with
> no other assistance of any kind. Now would be a great time to do that,
> but I can't see it happening, instead they'll miss the boat just as
> microsoft did with Office XML (three years ago they'd have sailed it
> through ISO to the sound of fanfairs)

Maybe Ian Murdock could weigh in on this given his new position at Sun. Ian?

BTW, congrats on the new gig...

Re: ZFS with Linux: An Open Plea

[Alan Cox]

> Why on discussion about switching to GPL v3 Linux code this argument was 
> allways taken as "piece of cake". Why in case switching to another license 

What planet do you come from I wonder ?

On Earth (where most of us usually reside) the consensus of the kernel
developers and the legal people they talked to was that GPLv2 to GPLv3
would be very very hard to do if not impossible for the kernel.

Alan

Re: ZFS with Linux: An Open Plea

[Tomasz Kłoczko]

[-- Attachment #1: Type: TEXT/PLAIN, Size: 965 bytes --]

On Tue, 17 Apr 2007, Matthew Garrett wrote:

> On Tue, Apr 17, 2007 at 03:47:32PM +0200, Tomasz Kłoczko wrote:
>> Realy can't or don't want (?)
>> So who is responsible for potential changing Linux code licensing for
>> allow if not incorporate CDDL code correct interraction without breaking
>> some law ?
>
> Everyone who holds any copyright over any of the code in Linux, which is
> several thousand people. You'd probably need permission from all of
> them. Good luck!

Why on discussion about switching to GPL v3 Linux code this argument was 
allways taken as "piece of cake". Why in case switching to another license 
which will allow use CDDL code just it is most importand contr argument ?

kloczek
-- 
-----------------------------------------------------------
*Ludzie nie mają problemów, tylko sobie sami je stwarzają*
-----------------------------------------------------------
Tomasz Kłoczko, sys adm @zie.pg.gda.pl|*e-mail: kloczek@rudy.mif.pg.gda.pl*

Re: ZFS with Linux: An Open Plea

[Tomasz Kłoczko]

[-- Attachment #1: Type: TEXT/PLAIN, Size: 1415 bytes --]

On Tue, 17 Apr 2007, John Anthony Kazos Jr. wrote:

>> And/or why Linux code licensing can't evolve ? Seems when Linux code was
>> licensed noone was thinking about case like interraction with code under
>> license like CDDL so why now it can be corrected and still many people try to
>> think like "anything arond Linux must evolve .. but not Linux" (?)
>> Why this can't be fixes ?
>
> That's not evolution; it's de-evolution. Linux morphing to some sort of
> mentally-damaged pseudo-proprietary licence would be like switching back
> to a feudal society where 50 was considered unbelievably ancient.

CDDL is OSI aproved. Did you realy want to say by above something like 
"CDDL is pseudo-proprietary licence" ? Are you still taking about (and 
only) CDDL ?

> I'm sure Linus did think very closely about the interaction of his code
> with proprietary licences. He thought about it, snickered for a few
> moments, and made the right decision.

I don't want see problmes on border with propretary licenses at all but I 
see (and still want to talk only about) problem on on some class licenses 
which provides more oppened (and not closed) code.

kloczek
-- 
-----------------------------------------------------------
*Ludzie nie mają problemów, tylko sobie sami je stwarzają*
-----------------------------------------------------------
Tomasz Kłoczko, sys adm @zie.pg.gda.pl|*e-mail: kloczek@rudy.mif.pg.gda.pl*

Re: ZFS with Linux: An Open Plea

[Alan Cox]

> What I meant in saying the CDDL is less restrictive than the GPL is that
> the CDDL can be freely used in conjunction with code under other

The CDDL is more restrictive in numerous ways, and in the Solaris case
has an obnoxious requirement to use the US joke courts for any legal
decisions (which means the license is I'm pretty sure not even valid in
some parts of the world).

Re: ZFS with Linux: An Open Plea

[Ricardo Correia]

Xavier Bestel wrote:
>> That is not quite true. They made ZFS available under the CDDL, which is
>> an OSI-approved open-source license that is *less* restrictive than the
>> GPL. The CDDL doesn't prevent anyone from using the ZFS code in
>> combination with code under other licenses.
> 
> You are wrong. Please read e.g.
> <http://www.gnu.org/licenses/license-list.html#GPLIncompatibleLicenses>
> (maybe there are better analysis somewhere, but I don't know where).

What I meant in saying the CDDL is less restrictive than the GPL is that
the CDDL can be freely used in conjunction with code under other
licenses, as long as the files licensed under CDDL keep the license
notice, whereas the GPL requires that derived works also have to be
licensed under the GPL, which is not possible in many cases (such as
this one).

Re: ZFS with Linux: An Open Plea

[Michal Schmidt]

linux-os (Dick Johnson) skrev:
> if you never look at somebody else's'
> implementation details, you certainly should not be violating a patent.

Oh, it would be a beautiful world in which this was true!

Michal

Re: ZFS with Linux: An Open Plea

[Xavier Bestel]

On Tue, 2007-04-17 at 16:06 +0100, Ricardo Correia wrote:
> Alan Cox wrote:
> > The real test of whether Sun were serious about ZFS being anywhere but
> > Solaris is what they do to license it - they've patented everything they
> > can, and made the code available only under licenses incompatible with
> > other OS products. Their intent is quite clear, and quite sad.
> 
> That is not quite true. They made ZFS available under the CDDL, which is
> an OSI-approved open-source license that is *less* restrictive than the
> GPL. The CDDL doesn't prevent anyone from using the ZFS code in
> combination with code under other licenses.

You are wrong. Please read e.g.
<http://www.gnu.org/licenses/license-list.html#GPLIncompatibleLicenses>
(maybe there are better analysis somewhere, but I don't know where).

	Xav

Re: ZFS with Linux: An Open Plea

[linux-os (Dick Johnson)]

On Tue, 17 Apr 2007, Xavier Bestel wrote:

> On Tue, 2007-04-17 at 10:59 -0400, linux-os (Dick Johnson) wrote:
>> So, what needs to be done is simply find out the specifications of
>> the file-system.
>
> I didn't know that was that simple, great !
> So, what do we wait ? (I love that abusive "we")
>
> 	Xav

Well BSD already announced that they ported the file-system. "We" is
not meant to be abusive, simply instructive as in "we the people."

Cheers,
Dick Johnson
Penguin : Linux version 2.6.16.24 on an i686 machine (5592.59 BogoMips).
New book: http://www.AbominableFirebug.com/
_
\x1a\x04

****************************************************************
The information transmitted in this message is confidential and may be privileged.  Any review, retransmission, dissemination, or other use of this information by persons or entities other than the intended recipient is prohibited.  If you are not the intended recipient, please notify Analogic Corporation immediately - by replying to this message or by sending an email to DeliveryErrors@analogic.com - and destroy all copies of this information, including any attachments, without reading or disclosing them.

Thank you.

Re: ZFS with Linux: An Open Plea

[Xavier Bestel]

On Tue, 2007-04-17 at 10:59 -0400, linux-os (Dick Johnson) wrote:
> So, what needs to be done is simply find out the specifications of
> the file-system.

I didn't know that was that simple, great !
So, what do we wait ? (I love that abusive "we")

	Xav

Re: ZFS with Linux: An Open Plea

[Ricardo Correia]

Alan Cox wrote:
> The real test of whether Sun were serious about ZFS being anywhere but
> Solaris is what they do to license it - they've patented everything they
> can, and made the code available only under licenses incompatible with
> other OS products. Their intent is quite clear, and quite sad.

That is not quite true. They made ZFS available under the CDDL, which is
an OSI-approved open-source license that is *less* restrictive than the
GPL. The CDDL doesn't prevent anyone from using the ZFS code in
combination with code under other licenses.

The proof of that is that ZFS has already been ported to FreeBSD and
it's being ported to the Mac OS X kernel.

The main problem with ZFS on Linux is that most people consider that the
GPL doesn't allow non-GPL kernel modules.

Re: ZFS with Linux: An Open Plea

[linux-os (Dick Johnson)]

On Tue, 17 Apr 2007, Theodore Tso wrote:

> On Tue, Apr 17, 2007 at 02:54:32AM -0400, David R. Litwin wrote:
>>> The license that protects the code we write is far from nonsense.
>>
>> I know. In the end, this is the reason this topic is being discussed.
>>
>> I suggest the first thing you do is contact the ZFS developers and
>> convince them to release their code under a license that's GPL
>> compatible, then we can start looking at a Linux port.
>>
>> I began by contacting them. One of the devs there told me to contact the
>> Linux devs.
>
> Well, that was totally useless answer from the ZFS developers.  What
> he should have told you is to contact Sun management, since they are
> the only ones who can decide whether or not to release ZFS under a GPL
> license, and more importantly, to give a patent license for any
> patents they may have filed in the course of developing ZFS.  This is
> not anything Linux developers can help you with.
>
> 						- Ted

Copyright law protects an implementation, not a specification. If
there is a specification for a particular file-system, then certainly
one can create a compatible one without violating any copyrights. Patents
protect algorithms and other implementation details. Certainly, there
are at least a hundred ways of performing the same function using
a programming language, and if you never look at somebody else's'
implementation details, you certainly should not be violating a patent.

So, what needs to be done is simply find out the specifications of
the file-system. From the specifications, one writes compatible code.
To protect "IP," you might have to give it a different name than "ZFS,"
but you certain should be able to write code that handles ZFS format
files. The patent (pending) seems to work around the little/big endian
issue. So, there is probably something in a header somewhere that resolves
this --big deal, machines that are incompatible will have to suffer
byte-swapping overhead. There are also 64-bit checksums for some reason.
I guess they have bad hardware and needed a work-around. The 128-bit
file-size follows the, "if a little is good, more must be better..."
logic that became prevalent in industry once sales persons and accountants
took over engineering.

Cheers,
Dick Johnson
Penguin : Linux version 2.6.16.24 on an i686 machine (5592.59 BogoMips).
New book: http://www.AbominableFirebug.com/
_
\x1a\x04

****************************************************************
The information transmitted in this message is confidential and may be privileged.  Any review, retransmission, dissemination, or other use of this information by persons or entities other than the intended recipient is prohibited.  If you are not the intended recipient, please notify Analogic Corporation immediately - by replying to this message or by sending an email to DeliveryErrors@analogic.com - and destroy all copies of this information, including any attachments, without reading or disclosing them.

Thank you.

Re: ZFS with Linux: An Open Plea

[Alan Cox]

> So who is responsible for potential changing Linux code licensing for 
> allow if not incorporate CDDL code correct interraction without breaking 
> some law ?

Every single contributor, individually. Which won't happen.

The real test of whether Sun were serious about ZFS being anywhere but
Solaris is what they do to license it - they've patented everything they
can, and made the code available only under licenses incompatible with
other OS products. Their intent is quite clear, and quite sad.

Compare it to what the old Sun company did with NFS, which is now a
standard used everywhere.

If Sun want ZFS to get used all over the place in free software then I'd
have expected at the very least to see them throw out a copy of the code,
docs and patent grant in a form that could be used, even if it came with
no other assistance of any kind. Now would be a great time to do that,
but I can't see it happening, instead they'll miss the boat just as
microsoft did with Office XML (three years ago they'd have sailed it
through ISO to the sound of fanfairs)

Alan

Re: ZFS with Linux: An Open Plea

[Diego Calleja]

El Tue, 17 Apr 2007 15:47:32 +0200 (CEST), Tomasz Kłoczko <kloczek@rudy.mif.pg.gda.pl> escribió:

> Realy can't or don't want (?)

Relicensing the whole kernel under the CDDL just to be able to get ZFS is
not going to happen (I bet that rewriting ZFS is easier than relicensing a
large piece of software with thousand of different copyrigth owners ;)

Either Sun relicenses Solaris under a GPL-compatible license (which may
happen, as Sun's CEO has said they may relicense it under the GPL3), or
Linux won't get ZFS except using the FUSE backend. If you miss ZFS, you
always can use solaris. 

Re: ZFS with Linux: An Open Plea

[John Anthony Kazos Jr.]

> And/or why Linux code licensing can't evolve ? Seems when Linux code was
> licensed noone was thinking about case like interraction with code under
> license like CDDL so why now it can be corrected and still many people try to
> think like "anything arond Linux must evolve .. but not Linux" (?)
> Why this can't be fixes ?

That's not evolution; it's de-evolution. Linux morphing to some sort of 
mentally-damaged pseudo-proprietary licence would be like switching back 
to a feudal society where 50 was considered unbelievably ancient.

I'm sure Linus did think very closely about the interaction of his code 
with proprietary licences. He thought about it, snickered for a few 
moments, and made the right decision.

Re: ZFS with Linux: An Open Plea

[Alan Cox]

On Sun, 15 Apr 2007 16:44:57 +0400
Nikita Danilov <nikita@clusterfs.com> wrote:

> Ignatich writes:
>  > You might want to look at this discussion:
>  > http://mail.opensolaris.org/pipermail/zfs-discuss/2007-April/027041.html
> 
> Licenses involved cover file system _code_, rather than storage format
> that is openly specified. Just stand up and implement driver for zfs
> format from scratch under whatever license you want. This is exactly how
> Linux supports "foreign" file systems (ntfs, fat, etc.).

That leaves all the patents Sun have filed to prevent anyone doing so.

Re: ZFS with Linux: An Open Plea

[Erik Mouw]

[-- Attachment #1: Type: text/plain, Size: 2330 bytes --]

On Tue, Apr 17, 2007 at 03:47:32PM +0200, Tomasz K?oczko wrote:
> On Tue, 17 Apr 2007, Theodore Tso wrote:
> [..]
> >Well, that was totally useless answer from the ZFS developers.  What
> >he should have told you is to contact Sun management, since they are
> >the only ones who can decide whether or not to release ZFS under a GPL
> >license, and more importantly, to give a patent license for any
> >patents they may have filed in the course of developing ZFS.  This is
> >not anything Linux developers can help you with.
> 
> Realy can't or don't want (?)
> So who is responsible for potential changing Linux code licensing for 
> allow if not incorporate CDDL code correct interraction without breaking 
> some law ?

All Linux contributors (i.e: copyright owners) are. If you want to
change the kernel license, you have all contributors to agree. Like
somebody else in this thread already said: some of them can't be
reached anymore, some of them are even dead.

For Sun it would be much easier: there might be many contributors to
ZFS, but all of them are employed by Sun and hence Sun owns the
copyright and has the choice of license.

> And/or what Linux can loose on follow this king changes ?

A lot. Like an even playing field for all contributors.

> And/or why Linux code licensing can't evolve ? Seems when Linux code was 
> licensed noone was thinking about case like interraction with code under 
> license like CDDL so why now it can be corrected and still many people try 
> to think like "anything arond Linux must evolve .. but not Linux" (?)

The Linux kernel was licensed under GPLv2 way before Sun even thought
about CDDL. You can't blame Linus for choosing a license that was
incompatible with to be written future licenses.

> Why this can't be fixes ?

Because so far we haven't found a way to ask dead copyright owners to
think about relicensing their code. And even if we had, that still
doesn't mean they would actually agree with relicensing their code.

> If in this ponit in Linux "evniroment" can't be chaged .. sorry but is it 
> not kind of hipocritics ?

Nothing hypocritical about it, just undoable.


Erik

-- 
They're all fools. Don't worry. Darwin may be slow, but he'll
eventually get them. -- Matthew Lammers in alt.sysadmin.recovery

[-- Attachment #2: Digital signature --]
[-- Type: application/pgp-signature, Size: 189 bytes --]

Re: ZFS with Linux: An Open Plea

[Matthew Garrett]

On Tue, Apr 17, 2007 at 03:47:32PM +0200, Tomasz Kłoczko wrote:
> Realy can't or don't want (?)
> So who is responsible for potential changing Linux code licensing for 
> allow if not incorporate CDDL code correct interraction without breaking 
> some law ?

Everyone who holds any copyright over any of the code in Linux, which is 
several thousand people. You'd probably need permission from all of 
them. Good luck!

-- 
Matthew Garrett | mjg59@srcf.ucam.org

Re: ZFS with Linux: An Open Plea

[Tomasz Kłoczko]

[-- Attachment #1: Type: TEXT/PLAIN, Size: 1384 bytes --]

On Tue, 17 Apr 2007, Theodore Tso wrote:
[..]
> Well, that was totally useless answer from the ZFS developers.  What
> he should have told you is to contact Sun management, since they are
> the only ones who can decide whether or not to release ZFS under a GPL
> license, and more importantly, to give a patent license for any
> patents they may have filed in the course of developing ZFS.  This is
> not anything Linux developers can help you with.

Realy can't or don't want (?)
So who is responsible for potential changing Linux code licensing for 
allow if not incorporate CDDL code correct interraction without breaking 
some law ?
And/or what Linux can loose on follow this king changes ?
And/or why Linux code licensing can't evolve ? Seems when Linux code was 
licensed noone was thinking about case like interraction with code under 
license like CDDL so why now it can be corrected and still many people try 
to think like "anything arond Linux must evolve .. but not Linux" (?)
Why this can't be fixes ?

If in this ponit in Linux "evniroment" can't be chaged .. sorry but is it 
not kind of hipocritics ?

kloczek
-- 
-----------------------------------------------------------
*Ludzie nie mają problemów, tylko sobie sami je stwarzają*
-----------------------------------------------------------
Tomasz Kłoczko, sys adm @zie.pg.gda.pl|*e-mail: kloczek@rudy.mif.pg.gda.pl*

Re: ZFS with Linux: An Open Plea

[Theodore Tso]

On Tue, Apr 17, 2007 at 02:54:32AM -0400, David R. Litwin wrote:
> > The license that protects the code we write is far from nonsense.
> 
> I know. In the end, this is the reason this topic is being discussed.
> 
> I suggest the first thing you do is contact the ZFS developers and
> convince them to release their code under a license that's GPL
> compatible, then we can start looking at a Linux port.
> 
> I began by contacting them. One of the devs there told me to contact the  
> Linux devs.

Well, that was totally useless answer from the ZFS developers.  What
he should have told you is to contact Sun management, since they are
the only ones who can decide whether or not to release ZFS under a GPL
license, and more importantly, to give a patent license for any
patents they may have filed in the course of developing ZFS.  This is
not anything Linux developers can help you with.

						- Ted

Re: ZFS with Linux: An Open Plea

[David R. Litwin]

On 17/04/07,  Miklos Szeredi <miklos@szeredi.hu> wrote:

> Yes, but it is not really for the end-user. To paraphrase another, it is
> mostly academic.

Oh?  I thought those ~10,000 downloads of SSHFS and ~200,000 downloads
of NTFS-3G were end users.(*)

Maybe I was wrong though.  Thanks for the clarification.

The clarification has not been made: As I have said before, I speak only  
of ZFS on FUSE.

--
—A watched bread-crumb never boils.
—My hover-craft is full of eels.
—[...]and that's the he and the she of it.

Re: ZFS with Linux: An Open Plea

[Miklos Szeredi]

> > FUSE is nice for trying out new and interresting ideas in userspace -
> > it has its uses.
> 
> Yes, but it is not really for the end-user. To paraphrase another, it is  
> mostly academic.

Oh?  I thought those ~10,000 downloads of SSHFS and ~200,000 downloads
of NTFS-3G were end users.(*)

Maybe I was wrong though.  Thanks for the clarification.

Miklos

(*) Numbers obviously don't include packaged installations

Re: ZFS with Linux: An Open Plea

[David R. Litwin]

On 15/04/07,  Jesper Juhl <jesper.juhl@gmail.com> wrote:
On 14/04/07, David R. Litwin <presently42@gmail.com> wrote:
> Before I go on, let me appologise. I don't really know what I hope to
> accomplish, beyond trying to garner thoughts (and support?) for the  
> topic.
>
> Essentially: I want to use Linux and ZFS. I don't particularly care about
> licences or any of the rest of that nonsense.

The license that protects the code we write is far from nonsense.

I know. In the end, this is the reason this topic is being discussed.

I suggest the first thing you do is contact the ZFS developers and
convince them to release their code under a license that's GPL
compatible, then we can start looking at a Linux port.

I began by contacting them. One of the devs there told me to contact the  
Linux devs.

> FUSE is nice for trying out new and interresting ideas in userspace -
> it has its uses.

Yes, but it is not really for the end-user. To paraphrase another, it is  
mostly academic.

> What are the thoughts of the Linux community?
>
> Can't tell you that, all I can tell you is my own oppinion.

You make up a member of the Linux community.

> I believe
> ZFS for Linux would be interresting, if not for any other reason then
> for compatibility.

For the greater glory of Linux? :-)

> I'd personally like to see it - but, settle the
> license issue first.

And we've come full circle: The liconsinc issue.

--
Jesper Juhl <jesper.juhl@gmail.com>
Don't top-post  http://www.catb.org/~esr/jargon/html/T/top-post.html
Plain text mails only, please      http://www.expita.com/nomime.html



--
—A watched bread-crumb never boils.
—My hover-craft is full of eels.
—[...]and that's the he and the she of it.

Re: ZFS with Linux: An Open Plea

[David Chinner]

On Sun, Apr 15, 2007 at 08:50:25PM -0400, Rik van Riel wrote:
> David R. Litwin wrote:
> 
> >>4: ZFS has a HUGE capacity. I don't have 30 exobytes, but I might some
> >>day....
> >
> >ext4 will probably cope with that.  XFS definitely has very high
> >limits though I admit I don't know what they are.
> >
> >XFS is also a few exobytes.
> 
> The fsck for none of these filesystems will be able to deal with
> a filesystem that big.  Unless, of course, you have a few weeks
> to wait for fsck to complete.

Which is why I want to be able to partially offline a chunk of
a filesystem and repair it while the rest is still online.....

> Backup and restore are similar problems.  When part of the filesystem
> is lost, you don't want to have to wait for a full restore.
> 
> Sounds simple?  Well, the hard part is figuring out exactly which
> part of the filesystem you need to restore...
> 
> I don't see ZFS, ext4 or XFS addressing these issues.

XFS has these sorts of issues directly in our cross-hairs.

The major scaling problem XFS has right now is to do with
how long repair/backup/restore take when you have hundreds
of terabytes of storage.

> IMHO chunkfs could provide a much more promising approach.

Agreed, that's one method of compartmentalising the problem.....

Cheers,

Dave.
-- 
Dave Chinner
Principal Engineer
SGI Australian Software Group

Re: ZFS with Linux: An Open Plea

[Rik van Riel]

David R. Litwin wrote:

>> 4: ZFS has a HUGE capacity. I don't have 30 exobytes, but I might some
>> day....
> 
> ext4 will probably cope with that.  XFS definitely has very high
> limits though I admit I don't know what they are.
> 
> XFS is also a few exobytes.

The fsck for none of these filesystems will be able to deal with
a filesystem that big.  Unless, of course, you have a few weeks
to wait for fsck to complete.

Backup and restore are similar problems.  When part of the filesystem
is lost, you don't want to have to wait for a full restore.

Sounds simple?  Well, the hard part is figuring out exactly which
part of the filesystem you need to restore...

I don't see ZFS, ext4 or XFS addressing these issues.

IMHO chunkfs could provide a much more promising approach.

-- 
Politics is the struggle between those who want to make their country
the best in the world, and those who believe it already is.  Each group
calls the other unpatriotic.

Re: ZFS with Linux: An Open Plea

[Kasper Sandberg]

On Sun, 2007-04-15 at 04:57 -0400, David R. Litwin wrote:
> On 15/04/07,  Kasper Sandberg <lkml@metanurb.dk> wrote:
> On Fri, 2007-04-13 at 19:18 -0400, David R. Litwin wrote:
> 
> > By the way, forget about this FUSE business. I don't know why they're
> > bothering: It's not real, it's slow and, in general, silly.
> This seems to me to be a rather uninformed, arrogant, and quite stupid
> comment.
> 
> Thank you, sir, for calling my comment stupid. Perhaps you are one of  
> those FUSE folk. In that case, I would love for you to enlighten
> me as to why any one would bother attempting to port a file system when it  
> is known that not only is it much slower than the slowest
> currently available to Linux, but also does not provide much of the  
> functionality of the original product.
Well first off, i dont believe anyone has ever prooved that an fuse
filesystem on linux is inheritly much slower than the slowest filesystem
on linux, in fact i believe this to be very far from the truth, and even
if you are not able to squeeze the last bits of efficiency out, i doubt
that its gonna be the cpu overhead that will kill your IO performance.
ZFS-on-FUSE may not have all the features now, it may not ever get them,
but its far from pointless, but whats even more pointless and silly, is
you blindly acknowledging that you are uninformed and seeking
information (which is okay enough), but at the same time calls stuff
silly and unreal.

> 
> As to uninformed, well, yes, I am uninformed; hence my request for you to  
> inform me. And arrogant? I sure am.
> 
> Cheers.
> 
> --
> —A watched bread-crumb never boils.
> —My hover-craft is full of eels.
> —[...]and that's the he and the she of it.
> -
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at  http://www.tux.org/lkml/
> 

Re: ZFS with Linux: An Open Plea

[Nikita Danilov]

Ignatich writes:
 > You might want to look at this discussion:
 > http://mail.opensolaris.org/pipermail/zfs-discuss/2007-April/027041.html

Licenses involved cover file system _code_, rather than storage format
that is openly specified. Just stand up and implement driver for zfs
format from scratch under whatever license you want. This is exactly how
Linux supports "foreign" file systems (ntfs, fat, etc.).

Nikita.

Re: ZFS with Linux: An Open Plea

[David R. Litwin]

On 15/04/07,  Kasper Sandberg <lkml@metanurb.dk> wrote:
On Fri, 2007-04-13 at 19:18 -0400, David R. Litwin wrote:

> By the way, forget about this FUSE business. I don't know why they're
> bothering: It's not real, it's slow and, in general, silly.
This seems to me to be a rather uninformed, arrogant, and quite stupid
comment.

Thank you, sir, for calling my comment stupid. Perhaps you are one of  
those FUSE folk. In that case, I would love for you to enlighten
me as to why any one would bother attempting to port a file system when it  
is known that not only is it much slower than the slowest
currently available to Linux, but also does not provide much of the  
functionality of the original product.

As to uninformed, well, yes, I am uninformed; hence my request for you to  
inform me. And arrogant? I sure am.

Cheers.

--
—A watched bread-crumb never boils.
—My hover-craft is full of eels.
—[...]and that's the he and the she of it.

Re: ZFS with Linux: An Open Plea

[David R. Litwin]

On 14/04/07, Neil Brown <neilb@suse.de> wrote:

It is generally expected that email conversations started on-list will
remain on-list, unless there is a special reason to take it off
list... though maybe it was an accident on your part.

It very much was. I'm not used to not being subscribed to a mailing list.

Example of odd commands?
    mkfs -j /dev/whatever
usually does me.  Admittedly it might be nice to avoid the -j, but
that doesn't seem like a bit issue.

Fair enough.

> 2: ZFS provides near-platter speeds. A hard-drive should not be
> hampered performance-wise by it's file system.

That is claimed of XFS too.

Really? I must have missed that one.... Any way, I use XFS so this news  
makes me like it even more.

Immediate backups to tape?  seems unlikely.
Or are you talking about online snapshots.  I believe LVM supports
those.  Maybe the commands there are odd...

O fine, be that way with your commands. :-) As I said, though, I'm not an  
expert. Merely a Linux-user. You know far more about this sort of thing  
than I ever shall.

> 4: ZFS has a HUGE capacity. I don't have 30 exobytes, but I might some
> day....

ext4 will probably cope with that.  XFS definitely has very high
limits though I admit I don't know what they are.

XFS is also a few exobytes.

> 5: ZFS has little over-head. I don't want my file system to take up
> space; that's for the data to do.

I doubt space-overhead is a substantial differentiator between
filesystems.  All filesystems need to use space for metadata.  They
might report it in different ways.

Again, I'm simply reporting what I've heard. Well, read.

>
>   It is possible that that functionality can be
> > incorporated into Linux without trying to clone or copy ZFS.
>
>
> I don't deny this in the least. But, there's good code sitting,waiting  
> to be used. Why bother starting from scratch or trying to
> re-do what is already done?

Imagine someone wanting some cheap furniture and going to a 'garage
sale' at a light-house.  All this nice second-hand furniture, but you
can tell it won't fit in your house as it all has rounded edges...

It is a bit like that with software.  It might have great features and
functionality, but that doesn't mean it will fit.

XFS is a prime example.  It was ported to Linux by creating a fairly
substantial comparability interface so that code written for IRIX
would work in Linux.  That layer makes it a lot harder for other
people to maintain the software (I know, I've tried to understand it
and never got very far).

I've heard of the horrors of XFS's code. But, is there really that much  
work to be done to port ZFS to Linux? This is one area for which I have no  
information, as no one has tried (save the FUSEy folk) due to Lisences. To  
inform me!
- Hide quoted text -

-- 
—A watched bread-crumb never boils.
—My hover-craft is full of eels.
—[...]and that's the he and the she of it.

Re: ZFS with Linux: An Open Plea

[Ignatich]

You might want to look at this discussion:
http://mail.opensolaris.org/pipermail/zfs-discuss/2007-April/027041.html

Let me quote my last letter:
The problem is not with CDDL, GPL is the problem. ATI and nVidia do 
provide binary modules with GPL "adapters", but I don't think legality 
of this approach was proven in court. I see no parties interested in 
proving that it is not legal (Intel perhaps?), but Sun is another story. 
They are not interested in ZFS port for Linux, because Solaris and Linux 
are real competitors, and if winds change may decide to take legal 
action. Also, such port can never be included in mainline for obvious 
reasons and I really want to see storage system such as ZFS as "default" 
for Linux in future. To sum all of this I see a number of possible 
solutions for this situation:

1. Sun dual licenses ZFS as GPLv2 and thus gives green light for 
ZFS-Linux port. Personally I doubt that this will happen.

2. Linux changes it's license. The chance is near zero.

3. US and EU courts clearly state that it is legal to use non-GPL kernel 
modules in Linux.

4. GPL ZFS reimplementation project is started. I prefer that way until 
1), 2) or 3) happen.

I know Sun opened most if not all ZFS related patents for OpenSolaris 
community. So I repeat questions I asked in my first mail:

1. Are those patents limited to CDDL/OpenSolaris code or can by used in 
GPL/Linux too?

2. If GPL code can't use those patented algorithms, will you please 
provide list of ZFS-related patents? RAID-Z and LZJB are most obvious 
technologies which may be patent protected.
<end>

So far I've got no response from Sun. According to Jeff Bonwick's blog 
Sun issued 56 patents on ZFS, but I have no idea what they patented. 
Sorry, binary compatible ZFS reimplementation with GPL license might not 
be legal. If you know something about this or can help to get ZFS 
related patent list please send me a mail.

Sincerely yours, Max V. Yudin