Re: archive

1999-12-23 Thread Stephen C. Tweedie

Hi,

On Wed, 22 Dec 1999 11:08:37 -0800, "sadri" [EMAIL PROTECTED] said:

 Is there an archive of the emails posted in this list(linux-fsdevel)?
 thanks 

Searching for "linux-fsdevel archive" on www.google.com found several.

--Stephen



Re: (reiserfs) Re: RFC: Re: journal ports for 2.3?

1999-12-23 Thread Hans Reiser

Stephen's remarks seem right to me.

Hans


--
Get Linux (http://www.kernel.org) plus ReiserFS
 (http://devlinux.org/namesys).  If you sell an OS or
internet appliance, buy a port of ReiserFS!  If you
need customizations and industrial grade support, we sell them.





Re: (reiserfs) Re: RFC: Re: journal ports for 2.3?

1999-12-23 Thread Hans Reiser

"Benjamin C.R. LaHaise" wrote:

 I completly agree to change mark_buffer_dirty() to call balance_dirty()

  before returning. But if you add the balance_dirty() calls all over the
  right places all should be _just_ fine as far I can tell.

 I don't agree, both for the reasons above and because doing a
 balance_dirty in mark_buffer_dirty tends to result in stalls in the
 *wrong* place, because it tends to stall in the middle of an operation,
 not before it has begun.  You end up stalling on metadata operations that
 shouldn't stall.  The stall thresholds for data vs metadata have to be
 different in order to make the system 'feel' right.  This is easily
 accomplished by trying to "allocate" the dirty buffers before you actually
 dirty them (by checking if there's enough slack in the dirty buffer
 margins before doing the operation).

 -ben

If reiserfs had good SMP, you could stall it anywhere, and the code could handle
that.  But we don't, and I bet others also don't, and we won't have it for some
time even though we are working on it.

Hans

--
Get Linux (http://www.kernel.org) plus ReiserFS
 (http://devlinux.org/namesys).  If you sell an OS or
internet appliance, buy a port of ReiserFS!  If you
need customizations and industrial grade support, we sell them.





Re: (reiserfs) Re: RFC: Re: journal ports for 2.3?

1999-12-23 Thread Jeff Garzik

On Thu, 23 Dec 1999, Hans Reiser wrote:
 All I'm going to ask is that if mark_buffer_dirty gets changed again, whoever
 changes it please let us know this time.  The last two times it was changed
 we weren't informed, and the first time it happened it took a long time to
 figure it out.

Can't you figure this sort of thing out on your own?  Generally if you
want to stay updated on something, you are the one who needs to do the
legwork.  And grep'ing patches ain't that hard

Jeff






Object Based Storage and File System Snapshots: alpha release

1999-12-23 Thread Peter J. Braam

Object based storage  File System Snapshots: alpha release
---

Stelias Computing is pleased to announce the first public release of
its object based storage software.  At this time we are releasing a
driver and a file system which together access Ext2 formatted disks,
and a module for file system snapshots.  This is alpha quality, kernel
software, for use with Linux 2.3.31 kernels.  Please exercise
caution. It is Open Source, runs on Linux only at this time and can be
obtained from http://www.lustre.org.

Object based storage breaks with the block device paradigm and
instroduces "smart" drives that handle objects like inodes. We expect
that our work as well as that of others in this arena, will lead to a
suite of advanced storage management software and to a new cluster
file system.  The cluster file system is named the Lustre file system
(Linux CLUSTRE), and will be forthcoming during the next year. 

We have built a simulated object based disk, using Ext2 disk format.
To exploit such drives, a file system is the most obvious choice.  An
object based file system that writes directories in Ext2 format is
included.  When used with the Ext2 object based disk driver, it
reads/writes Ext2 file systems and fsck is available for recovery. Our
file system has been used with other object based disk drivers - as
long as the protocol is correctly implemented it should work.

The power of this architecture lies in the fact that modules can be
placed between the file system and the object based driver. For
example, modules for aggregation (RAID), file system snapshots,
hierarchical storage management, encryption/compression find a natural
place between the file system and object based storage driver.  We
expect to release more modules in the future, but at this time an
experimental driver is included that can make snapshots (read only
clones) of Ext2 file systems.  There is a utility that can delete
snapshots and change a file system back to the state of a historical
snapshot.  The snapshot architecture found here is very different from
bot the Network Appliances approach and the AFS/Coda approach.

Please tell us what you think of this project, and of your experiences
with the software - you might be able to influence further work.  If
you want to contribute to this software, please contact us so that we
can tell you where we are heading.  We expect to release more software
frequently now - subscribe to the obd-announce mailing list if you
want to be informed.

Stelias wishes to thank many for support, advice and stimulating
discussions on this topic.

Peter J. Braam  - [EMAIL PROTECTED] / [EMAIL PROTECTED]
Michael J. Callahan - [EMAIL PROTECTED] 
Andreas Dilger  - [EMAIL PROTECTED]

Stelias Computing Inc.