I’ve monitoring DHO minute by minute since September 8.
The following graph show the status for the GET operation since that day in periods of 4 hours. If in a period of four hours one GET fails the graph shows 0 (DOWN). If all requests are sucessuful the graph shows 1 (UP).
The graph shows some frequent downtimes since October, 27.
I tried to verify the data in the cloud. Do GET to all the files stored in the cloud and it stuck on some files. It stuck not only on GET, but also on PUT and DELETE for me. Sometimes it is impossible to GET one file for 1 or 2 hours and the problem occurs every day. Do they read the forum? Their cloud seems completely broken and unusable for me.
My apologies for the delayed response, much of the team has been out during the OpenStack conference.
We have been seeing more intermittent 500 errors than we’d like. We are working on adding capacity to the cluster which will help alleviate those. Be on the lookout for some maintenance windows in the coming weeks that will signal the beginning of this process.
Have you created a support ticket with details on this? I’d be interested to know what client or library you’re using to upload those files. Please include the dates and times so we can investigate in the logs.