[Gluster-users] Gluster FS replication

[Joe Julian]

On 10/21/2012 02:18 PM, Israel Shirk wrote:
> Haris, try the NFS mount.  Gluster typically triggers healing through 
> the client, so if you skip the client, nothing heals.
Not true anymore. With 3.3 there's a self-heal daemon that will handle 
the heals. You do risk reading stale data if you don't read through the 
client though.
> The native Gluster client tends to be really @#$@#$@# stupid.  It'll 
> send reads to Singapore while you're in Virginia (and there are bricks 
> 0.2ms away),
False. The client will read from the first-to-respond. Yes, if Singapore 
is responding faster than Virginia you might want to figure out why 
Virginia is so overloaded that it's taking more than 200ms to respond, 
but really that shouldn't be the case.
> then when healing is needed it will take a bunch of time to do that, 
> all the while it's blocking your application or web server, which 
> under heavy loads will cause your entire application to buckle.
False. 3.3 uses granular locking which won't block your application.
> The NFS client is dumb, which in my mind is a lot better - it'll just 
> do what you tell it to do and allow you to compensate for connectivity 
> issues yourself using something like Linux-HA.
The "NFS client" is probably more apt than you meant. It is both 
GlusterFS client and NFS server, and it connects to the bricks and 
performs reads and self-heal in exactly the same way as the fuse client.
>
> You have to keep in mind when using gluster that 99% of the people 
> using it are running their tests on a single server (see the recent 
> notes about how testing patches are only performed on a single server),
False. There are many more testers than that, most of which are outside 
of the development team.
> and most applications don't distribute or mirror to bricks more than a 
> few hundred yards away.  Their idea of geo-replication is that you 
> send your writes to the other side of the world (which may or may not 
> be up at the moment), then twiddle your thumbs for a while and hope it 
> gets back to you.  So, that said, it's possible to get it to work, and 
> it's almost better than lsyncd, but it'll still make you cry periodically.
>
> Ok, back to happy time :)
>
>     Hi everyone,
>
>     I am using Gluster in replication mode.
>     Have 3 bricks on 3 different physical servers connected with WAN. This
>     makes writing but also reading files from Gluster mounted volume
>     very slow.
>     To remedy this I have made my web application read Gluster files from
>     the brick directly (I make a readonly bind mount of the brick), but
>     write to the Gluster FS mounted volume so that the files will
>     instantly
>     replicate on all 3 servers. At least, "instant replication" is what I
>     envision GLuster will do for me :)
>
>     My problem is that files sometimes do not replicate to all 3 servers
>     instantly. There are certainly short network outages which may prevent
>     instant replication and I have situations like this:
>
>     ssh web1-prod ls -l
>     /home/gluster/r/production/zdrava.tv/web/uploads/24/playlist/38/19_10_2012_18.js
>     <http://zdrava.tv/web/uploads/24/playlist/38/19_10_2012_18.js>
>     -rw-r--r-- 1 apache apache 75901 Oct 19 18:00
>     /home/gluster/r/production/zdrava.tv/web/uploads/24/playlist/38/19_10_2012_18.js
>     <http://zdrava.tv/web/uploads/24/playlist/38/19_10_2012_18.js>
>     web2-prod.
>     ssh web2-prod ls -l
>     /home/gluster/r/production/zdrava.tv/web/uploads/24/playlist/38/19_10_2012_18.js
>     <http://zdrava.tv/web/uploads/24/playlist/38/19_10_2012_18.js>
>     -rw-r--r-- 1 apache apache 0 Oct 19 18:00
>     /home/gluster/r/production/zdrava.tv/web/uploads/24/playlist/38/19_10_2012_18.js
>     <http://zdrava.tv/web/uploads/24/playlist/38/19_10_2012_18.js>
>     web3-prod.
>     ssh web3-prod ls -l
>     /home/gluster/r/production/zdrava.tv/web/uploads/24/playlist/38/19_10_2012_18.js
>     <http://zdrava.tv/web/uploads/24/playlist/38/19_10_2012_18.js>
>     -rw-r--r--. 1 apache apache 75901 Oct 19 18:00
>     /home/gluster/r/production/zdrava.tv/web/uploads/24/playlist/38/19_10_2012_18.js
>     <http://zdrava.tv/web/uploads/24/playlist/38/19_10_2012_18.js>
>
>     Where the file on web2 server brick has a size of 0. So serving this
>     file from web2 makes my application make errors..
>
>     I have had a brain-split situation couple of times and resolved
>     manually. The above kind of situation is not a brain-split and
>     resolves
>     and (re-)replicates completly with a simple "ls -l" on the file in
>     question from any of the servers.
>
>     My question is:
>     I suppose that the problem here is incomplete replication for the file
>     in question due to temporary network problems.
>     How to insure the complete replication immediatly after the
>     network has
>     been restored?
>
>
>     kind regards
>     Haris Zukanovic
>
>     --
>     --
>     Haris Zukanovic
>
>
>
> _______________________________________________
> Gluster-users mailing list
> Gluster-users at gluster.org
> http://supercolony.gluster.org/mailman/listinfo/gluster-users

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://supercolony.gluster.org/pipermail/gluster-users/attachments/20121022/d52251a1/attachment.html>