Abstract: A facility comprising systems and method for automatically triggering the collection of comprehensive monitoring information in a distributed processing system. The facility compares the overall performance of distributed processing system to one or more performance metrics and, in response to determining that one or more performance metrics is not satisfied, triggers one or more of the nodes within the distributed processing system to increase one or more of its monitoring rate or its distribution rate. The facility collects and analyzes the collected information to provide resources that can be used to assess and diagnose failures within the distributed processing system. In this manner, the facility reacts to performance anomalies by triggering nodes within in the system to provide comprehensive performance information over a trigger period for diagnostic purposes.

Abstract: A facility for snapshot space accounting for a storage system, such as a filesystem is disclosed. The facility enables users to quickly and easily determine the amount of storage space that would be released or recovered if a snapshot were to be purged. The facility may work in conjunction with, or as part of, a snapshot service. The facility maintains an expiration data structure and a count data structure and uses these data structures in implementing the disclosed snapshot space accounting techniques. The expiration data structure represents the life cycle of each snapshot element maintained by the facility while the count data structure represents, for pairs of snapshots, the size of the information stored in the snapshot data that expired and that spans the corresponding pair of snapshots.

Abstract: A facility comprising systems and method for automatically triggering the collection of comprehensive monitoring information in a distributed processing system. The facility compares the overall performance of distributed processing system to one or more performance metrics and, in response to determining that one or more performance metrics is not satisfied, triggers one or more of the nodes within the distributed processing system to increase one or more of its monitoring rate or its distribution rate. The facility collects and analyzes the collected information to provide resources that can be used to assess and diagnose failures within the distributed processing system. In this manner, the facility reacts to performance anomalies by triggering nodes within in the system to provide comprehensive performance information over a trigger period for diagnostic purposes.

Abstract: A facility comprising systems and method for automatically triggering the collection of comprehensive monitoring information in a distributed processing system. The facility compares the overall performance of distributed processing system to one or more performance metrics and, in response to determining that one or more performance metrics is not satisfied, triggers one or more of the nodes within the distributed processing system to increase one or more of its monitoring rate or its distribution rate. The facility collects and analyzes the collected information to provide resources that can be used to assess and diagnose failures within the distributed processing system. In this manner, the facility reacts to performance anomalies by triggering nodes within in the system to provide comprehensive performance information over a trigger period for diagnostic purposes.

Abstract: A facility comprising systems and method for automatically triggering the collection of comprehensive monitoring information in a distributed processing system. The facility compares the overall performance of distributed processing system to one or more performance metrics and, in response to determining that one or more performance metrics is not satisfied, triggers one or more of the nodes within the distributed processing system to increase one or more of its monitoring rate or its distribution rate. The facility collects and analyzes the collected information to provide resources that can be used to assess and diagnose failures within the distributed processing system. In this manner, the facility reacts to performance anomalies by triggering nodes within in the system to provide comprehensive performance information over a trigger period for diagnostic purposes.

Abstract: A facility for snapshot space accounting for a storage system, such as a filesystem is disclosed. The facility enables users to quickly and easily determine the amount of storage space that would be released or recovered if a snapshot were to be purged. The facility may work in conjunction with, or as part of, a snapshot service. The facility maintains an expiration data structure and a count data structure and uses these data structures in implementing the disclosed snapshot space accounting techniques. The expiration data structure represents the life cycle of each snapshot element maintained by the facility while the count data structure represents, for pairs of snapshots, the size of the information stored in the snapshot data that expired and that spans the corresponding pair of snapshots.

Abstract: A facility for snapshot space accounting for a storage system, such as a filesystem is disclosed. The facility enables users to quickly and easily determine the amount of storage space that would be released or recovered if a snapshot were to be purged. The facility may work in conjunction with, or as part of, a snapshot service. The facility maintains an expiration data structure and a count data structure and uses these data structures in implementing the disclosed snapshot space accounting techniques. The expiration data structure represents the life cycle of each snapshot element maintained by the facility while the count data structure represents, for pairs of snapshots, the size of the information stored in the snapshot data that expired and that spans the corresponding pair of snapshots.