Re: [Moosefs-users] Lost all metadata on master w/ full disk

[Steve <st...@bo...>]

ahhhhh yes wasn't thinking of the conversion to master more just security of
the data utilising existing services and hardware.



 

 

 

 

 

-------Original Message------- 

 

From: Travis Hein 

Date: 10/11/2011 21:00:48 

To: moo...@li... 

Subject: Re: [Moosefs-users] Lost all metadata on master w/ full disk 

 

I think the metalogger was added in in 1.5.x, before that it kind of did not
exist. So there would be some backwards compatibility considerations to just
embed it. 

 

But I think more so the motivation of the meta logger is to have the meta
files similar to that of the master server, where in theory the meta logger
node could be converted into a master server, e.g. all chunk servers and
mfsmount clients used a DNS record to indirect the master server, this DNS
record could be updated to point to the metalogger instance that is to be
promoted to become the new master server. So when losing the master,
renaming the changelog_ml.* files to just changelog.* on the metalogger
instance, and running mfsmetarestore, booting up the mfsmaster, and
continuing. 

 

In this sense, the consideration for this metalogger machine to have a
similar amount of available RAM as the master machine would have had, to be
able to run the mfsmaster process. And the assumption for larger filesystems
would be that not every chunk server in the cluster would have this, so the
dedicated planning of a metalogger server(S) was likely assumed. 

 

On 11-11-10 2:28 PM, Steve wrote: 

Sure its possible to start a metalogger your self. It just seems as though 

it could have been part of the chunkservers