Re: [Moosefs-users] Replication mechanism/speed

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

Wouldn't you have more chunks, then you would have sufficient redundancy to
cover a further failure that the 10 days wouldn't be important ?



1+ million files created must be extreme usage. 

 

 

 

 

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

 

From: Reinis Rozitis 

Date: 25/10/2010 13:27:03 

To: moosefs-users 

Subject: Re: [Moosefs-users] Replication mechanism/speed 

 

> While non-aggressive replication is fine (doesn't degrade the rest of the 

> system) is there a way to adjust / finetune it (or maybe its done 

> automatically)? 

> 

> Is it somewhat connected to also chunkserver count - like more 

> chunkservers 

> = higher replication rates (since the replication is distributed then) or 

> the goal size (the more file is undergoal (for example 1 copy out of 6) 

> the 

> faster it gets replicated) or its just some preset/hardcoded rate? 

 

Any info on this? 

 

We have simulated a downed node for a day and now the undergoal chunk/file 

count is like 1+ mil. With the 2 node setup it would take like 10 days to 

get in sync (while the new file/chunk creation is easily 100x times faster).


 

 

RR 

 

 

-----------------------------------------------------------------------------
 

Nokia and AT&T present the 2010 Calling All Innovators-North America contest


Create new apps & games for the Nokia N8 for consumers in U.S. and Canada 

$10 million total in prizes - $4M cash, 500 devices, nearly $6M in marketing


Develop with Nokia Qt SDK, Web Runtime, or Java and Publish to Ovi Store 

http://p.sf.net/sfu/nokia-dev2dev 

_______________________________________________ 

moosefs-users mailing list 

moo...@li... 

https://lists.sourceforge.net/lists/listinfo/moosefs-users