[Gluster-devel] New Development Update - [1.4.X releases]
Daniel van Ham Colchete
daniel.colchete at gmail.com
Mon Jun 9 18:00:38 UTC 2008
That's great to hear. I'm getting back at using GlusterFS again. Yesterday
my web servers started using it again and we'll migrate our e-mail storage
to it within 6 weeks.
I'll start using the 1.4qa version this week with a new project here. The
new BDB storage is the answer to my prayers. I'm developing a spam
reputation system here, it will have to handle a few millions of requests
per day (~20 million/day), and every request reads and writes a few files (a
few per domain name plus a few per IP address). This new BDB storage fits
perfectly for me. So, I'm very excited with this new version.
1 - Will 1.4's unify still need the namespace cache?
2 - If so, can I use the BDB storage for the namespace cache?
3 - Thinking about the database problem I described above, I'll have to open
many many files per second. If unify will have to lookup() every server
every time it will not scale too much if I add more servers as I will be
limited by the lookup() capacity of my worst brick, right? So, talking
performance wise, have you thought about the hash scheduler I proposed 
some time ago that know where a file should be and only asks at right server
first? If the file is not found, ask the others.
Congratulations to all of you.
On Fri, Jun 6, 2008 at 6:24 PM, Amar S. Tumballi <amar at zresearch.com> wrote:
> As the topic says, I want to give you all a snapshot of whats coming in
> 1.4.x series and where is our main focus for the release.
> 1.4.x -
> * Performance of GlusterFS (reduced CPU and memory usage, protocol
> * Non blocking I/O - to give more responsiveness to GlusterFS, remove the
> issues faced due to timeout, freezing etc.
> * Few features to handle different verticals of storage requirements.
> We expect to get this branch to stability very soon (within a month or so),
> so we won't be having complains about small file performance and
> timeout/hang issues anymore (from 1.3.x branch). Hence your help in testing
> this out for your application, your configuration, and reporting bugs
> help us to get it to stability even faster.
> GlusterFS Team
> PS: Currently this release of qa is not tested on any other OS than
> GNU/Linux. I will write back as soon as we have a fix for each specific OS.
> Amar Tumballi
> Gluster/GlusterFS Hacker
> [bulde on #gluster/irc.gnu.org]
> http://www.zresearch.com - Commoditizing Super Storage!
> Gluster-devel mailing list
> Gluster-devel at nongnu.org
More information about the Gluster-devel