Filesystem Journaling Update II - July 2005

Emiel Kollof coolvibe at hackerheaven.org
Wed Jul 6 01:52:03 PDT 2005


On Wednesday 06 July 2005 05:32, Matthew Dillon wrote:
> :Matthew Dillon wrote:
> :>     .....This is about
> :>     a 7% performance penalty, which is quite reasonable considering what
> :>     you get for the trouble....

[snip]

> :IOW, could this same journalling mechanism be used in FBSD or NBSD
> :with a bit of hackery?  Or not.

[explanation snip]

>     I don't think any of the other BSDs could adopt our journaling layer
>     without also adopting most of the VFS work I've done over the last year
>     and a half.  It would be a huge job.  Without the namecache and API
>     work it would not be possible to tag the journaling records properly or
>     guarentee transactional consistency or even feed the VFS operations 
>     through the new layer safely.  In short: you won't ever see this in any 
>     of the other BSDs. 

What about the client side? I mean, if you journal on a socket, and that 
socket is connected to some other BSD machine, surely that other box could 
run a daemon that has raw access to some disk to facilitate the journalling? 
If the client side is all userland, it could be possible, yes? Imagine having 
DFBSD journal to some other box that has heaps and heaps of disk. Heck, 
imagine having a whole cluster of DFBSD boxen stream their journals to some 
large SAN :)

Cheers,
Emiel
-- 
This Fortue Examined By INSPECTOR NO. 2-14
Attachment:
pgp00001.pgp
-------------- next part --------------
A non-text attachment was scrubbed...
Name: pgp00001.pgp
Type: application/octet-stream
Size: 187 bytes
Desc: "Description: PGP signature"
URL: <http://lists.dragonflybsd.org/pipermail/kernel/attachments/20050706/d2fc56e4/attachment-0020.obj>


More information about the Kernel mailing list