On Fri, May 27, 2011 at 9:06 AM, Sylar Shen <kimulaaa@xxxxxxxxx> wrote: > Hi developers, > Recently I am testing radosgw about its functions. > Then I am curious that will radosgw implement the function or API of > quota in the future? > I've checked the mail archives and found that the quota issue had been > discussed. > And also, I know this may affect the performance of write ability. > But in most cases, administrator may want to set the quota of a bucket > for every user. > So would this function be implemented in the future? We're unlikely to implement quotas in the gateway. It's an S3-compatible implementation and S3 has no concept of limits -- the more space users take up, the more money the provider can charge them! ;) Previous discussions of quotas have centered more on the full filesystem, which is technically challenging for a number of reasons, although I think the Tcloud guys have done some work on that. I don't think it would be too difficult to implement a working solution for the *gateway* layer on your own, though... > On another hand, I know that the kernel of Ceph upgrades gradually. > I would like to know that will the performance of Ceph client and > re-exporting NFS become better if I upgrade the kernel to the latest > version? The kernel client hasn't gone through a lot of updating lately, but the current rc release will be faster than recent kernels since it re-enables local dentry lookups (at last!). NFS re-export is getting more attention lately so it's better than it used to be, but there aren't a lot of users yet and there are still some weird performance issues that you'll run across in any version of it. -Greg -- To unsubscribe from this list: send the line "unsubscribe ceph-devel" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
