gluster-devel
[Top][All Lists]
Advanced

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

Re: [Gluster-devel] Crawling and indexing hardware


From: gordan
Subject: Re: [Gluster-devel] Crawling and indexing hardware
Date: Fri, 9 May 2008 12:24:35 +0100 (BST)
User-agent: Alpine 1.10 (LRH 962 2008-03-14)

On Fri, 9 May 2008, Marcus Herou wrote:

OK cool. Glad to hear that it works like I thought initially.

But what does "connected" mean ? Can GlusterFS really be disconnected ?

In theory, yes, it can function disconnected, but there is no clever reconciliation of split-brain changes, and in some cases it can cause massive data loss. We've discussed this over the past few days on a couple of threads that are still floating about.

I guess you are talking about snippets in client/server configs. Could you
elaborate a little on the difference of connected vs disconnected to open my
eyes a little ?

There is no configuration difference - it comes down to whether all of your nodes are up and connected to the network or not.

Gordan




reply via email to

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