Abstract: A technique for analyzing data in order to detect issues within a cloud-based service is disclosed. Host computing devices in a data center launch virtual machines, where at least some virtual machines run a pipelined stack for a streaming service. Virtual machines in the host computing devices generate event data including timestamps. Metadata generated by the pipelined stack during each streaming session is analyzed to identify deadzones in the corresponding host computing device, and the event data is processed to identify potential root causes of the corresponding deadzones. The event data can be generated by the virtual machine hosting the streaming service or by different virtual machines on the same host computing device. A distribution of events of each event type relative to the identified deadzones is determined and an operation of the host computing device can be adjusted based on the distribution.

Abstract: A technique for analyzing data in order to detect issues within a cloud-based service is disclosed. Host computing devices in a data center launch virtual machines, where at least some virtual machines run a pipelined stack for a streaming service. Virtual machines in the host computing devices generate event data including timestamps. Metadata generated by the pipelined stack during each streaming session is analyzed to identify deadzones in the corresponding host computing device, and the event data is processed to identify potential root causes of the corresponding deadzones. The event data can be generated by the virtual machine hosting the streaming service or by different virtual machines on the same host computing device. A distribution of events of each event type relative to the identified deadzones is determined and an operation of the host computing device can be adjusted based on the distribution.

Abstract: Apparatuses, systems, and techniques to identify a cause of a performance regression in a web-based service. In at least one embodiment, a cause of a performance regression is identified by comparing performance metrics associated with a first group of user interactions with a web-based service to performance metrics associated with a second group of user interactions with the web-based service.

Abstract: A technique for evaluating qualitative streaming experience using session performance metadata is disclosed herein. A pipeline of a streaming service can be adapted to collect metadata, such as timestamps, from various components of the pipeline. The metadata can then be analyzed to calculate an objective quality metric for each streaming session using weighted scores derived from the metadata for a plurality of different components including, but not limited to, stutter, latency, and/or picture quality. The quality metric is designed to have high correlation with subjective measures of quality by users of the streaming service, but provides dense data samples compared to typical sparse responses collected from user feedback (e.g., user surveys). The objective quality metric can be utilized to quickly adjust, either manually or automatically, the streaming service parameters to improve the quality of the streaming service due to changes in, e.g., streaming content.