On 08/08/2013 11:27 AM, Adam Brenner wrote: > Howdy, > > I am in the process of testing bcache on our HPC cluster to act as > cache for our gluster storage (~750TB). > > I notice that during the setup process on our test cluster, our > backing device (where all our data is stored) will need to be > formatted in order to support bcache. You can't convert an in use block device into a backing store. Your best bet is to replace your gluster bricks either one at a time or in acceptable groups with bricks that are bcache backed. But without knowing more about how your gluster setup is architect-ed this is just a guess. > Does a way exist so we do not have to format our backing device? Or is > working being done to support this? In your particular case converting in place is not likely a very good method even if it were supported. Gluster is designed to be flexible in such a way that you can replace existing storage bricks with new and improved bcache backed bricks by simply replacing a replica in a set. > > Thanks, > -Adam > > -- > Adam Brenner > Computer Science, Undergraduate Student > Donald Bren School of Information and Computer Sciences > > Research Computing Support > Office of Information Technology > http://www.oit.uci.edu/rcs/ > > University of California, Irvine > www.ics.uci.edu/~aebrenne/ > aebrenne@xxxxxxx > -- > To unsubscribe from this list: send the line "unsubscribe linux-bcache" in > the body of a message to majordomo@xxxxxxxxxxxxxxx > More majordomo info at http://vger.kernel.org/majordomo-info.html -- To unsubscribe from this list: send the line "unsubscribe linux-bcache" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
