Put another way - is there a way to throttle the metadata sync requests in a
multisite cluster? They seem to be overwhelming the master zone rgw server, it
constantly runs at 40%+ CPU and watching the logs it just appears to be a
steady stream of /admin/log?type=metadata requests from the
Is your client using the DeleteObjects call to delete 1000 per request?:
https://docs.aws.amazon.com/AmazonS3/latest/API/API_DeleteObjects.html
On Fri, Jun 3, 2022 at 9:35 AM J-P Methot
wrote:
> Read/writes are super fast. It's only deletes that are incredibly slow,
> both through the s3 api
Dear Ceph community,
I am trying to deploy csi on a k8s cluster to be able to create/mount ceph rbd
volumes. The installation is based in helm and it fails deploying the rbd
plugin pods:
Events:
Type Reason Age FromMessage
--