MmmSkyscraper
Diamond Member
- Jul 6, 2004
- 9,472
- 1
- 76
An explanation of a similar occurence:
They went down in a similar fashion in '06. Here was their explanation for that.
"We were taking the low-load Saturday as an opportunity to perform some maintenance on the storage system, specifically on some very large (>100 million objects) buckets in order to obtain better load-balancing characteristics. Normally this procedure is entirely transparent to users and bucket owners. In this case, the re-balancing caused an internal transit link to become flooded, this cascaded into other network problems, and the system was made unavailable. We are taking several steps to ensure that we don't run into this situation again. We are modifying our maintenance procedures, and are adding further monitoring to prevent the transit link from getting full. In addition we are modifying the way that our system makes use of the network to prevent the cascading effect we saw on Saturday. Providing world-class reliability is our top priority for Amazon S3. We appreciate your patience, and hope to surpass your expectations going forward."