gluster-devel
[Top][All Lists]
Advanced

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

[Gluster-devel] RE: problem with DHT


From: David Braginsky
Subject: [Gluster-devel] RE: problem with DHT
Date: Tue, 13 Jan 2009 14:56:31 -0800

Even stranger, I create 1000 dirs in /mnt/glfs. They all appear in /glfs on 
every node. However, when I do ls /mnt/glfs I only see about 100. 

> -----Original Message-----
> From: David Braginsky
> Sent: Tuesday, January 13, 2009 2:20 PM
> To: 'address@hidden'
> Subject: problem with DHT
> 
> I set up a DHT over AFR on top of 360 machines. Every 4 machines form
> an AFR cluster, then the DHT is defined on top of those clusters.
> 
> Each machine defines a storage endpoint:
> 
> ----- SERVER.CONF -----
> volume posix
>   type storage/posix
>   option directory /glfs
> end-volume
> 
> volume brick
>   type features/locks
>   subvolumes posix
> end-volume
> 
> volume server
>   type protocol/server
>   option transport-type tcp
>   option listen-port 6996
> 
>   option auth.addr.brick.allow *
>   subvolumes brick
> end-volume
> 
> ----- CLIENT.CONF -----
> 
> volume multifeed001
>   type protocol/client
>   option transport-type tcp
>   option remote-host multifeed001
>   option remote-subvolume brick
> end-volume
> .
> .
> .
> (1 per host)
> .
> volume rep-0
>   type cluster/afr
>   subvolumes multifeed001 multifeed091 multifeed181 multifeed271
> end-volume
> .
> .
> .
> (1 per cluster, 90 total)
> .
> .
> .
> volume dht
>   type cluster/dht
>   subvolumes rep-0 rep-1 rep-2 rep-3 rep-4 rep-5 rep-6 rep-7 rep-8 rep-
> 9 rep-10 rep-11 rep-12 rep-13 rep-14 rep-15 rep-16 rep-17 rep-18 rep-19
> rep-20 rep-21 rep-22 rep-23 rep-24 rep-25 rep-26 rep-27 rep-28 rep-29
> rep-30 rep-31 rep-32 rep-33 rep-34 rep-35 rep-36 rep-37 rep-38 rep-39
> rep-40 rep-41 rep-42 rep-43 rep-44 rep-45 rep-46 rep-47 rep-48 rep-49
> rep-50 rep-51 rep-52 rep-53 rep-54 rep-55 rep-56 rep-57 rep-58 rep-59
> rep-60 rep-61 rep-62 rep-63 rep-64 rep-65 rep-66 rep-67 rep-68 rep-69
> rep-70 rep-71 rep-72 rep-73 rep-74 rep-75 rep-76 rep-77 rep-78 rep-79
> rep-80 rep-81 rep-82 rep-83 rep-84 rep-85 rep-86 rep-87 rep-88 rep-89
> end-volume
> 
> I mount the fs by doing glusterfs -f client.conf /mnt/glfs
> 
> I then created a bunch of test files in /mnt/glfs and they showed up in
> the backend dir on every node. Am I misunderstanding how DHT should
> work?




reply via email to

[Prev in Thread] Current Thread [Next in Thread]