On Thu, May 10, 2012 at 01:20:49AM +0900, MORITA Kazutaka wrote: > current object cache and it should work as you expect. If I need the > write cache which works like a block device one, I should implement it > as another cache feature. Yes - I posted a prototype patch for that about half a year ago. If I get a bit time I'll port it over to the current protocol variant for the cache and will post it. Especially for deployments using a gateway sheep and minimal local storage on the gateway node the object cache doesn't seem overly useful. > > Anyway, I think now I am fine with adding a new option to disable object > > cache globally, but I don't agree to disable it as default. > > If I can disable it, it's okay to me. I still think the feature which > doesn't follow the block storage semantics shouldn't be default like > asyncflush, though. Seconded. |