On Tue, Oct 20, 2015 at 3:31 PM, Robert Coli <rc...@eventbrite.com> wrote:
> On Tue, Oct 20, 2015 at 9:13 AM, Branton Davis <branton.da...@spanning.com > > wrote: > >> >>> Just to clarify, I was thinking about a scenario/disaster where we lost >> the entire cluster and had to rebuild from backups. I assumed we would >> start each node with the backed up data and commit log directories already >> there and with auto_bootstrap=false, and I also hoped that we could do all >> nodes at once, since they each already had their data. Is that wrong? If >> so, how would you handle such a situation? >> > > "The one case I can imagine is when you are starting a cluster which is > not receiving any write traffic and does contain snapshots. " > > The case you describe is in that class of cases. > > =Rob > > > >> >> > > Thanks for confirming!
