Computing process analysis by metrics profiling
First Claim
Patent Images
1. A system for managing computing resources of a provider network, the system comprising:
- one or more computing devices;
at least one memory having stored therein computer instructions that, upon execution by the system, at least cause the system to;
receive a request for instantiation of a virtual machine instance on one of the one or more computing devices, the one virtual machine instance associated with a customer of the provider network;
in response to the request, initiate a process to instantiate the requested virtual machine instance;
during execution of the process, monitor data associated with initialization of the requested virtual machine instance to a predetermined operational state of the requested virtual machine instance, the data including one or more of CPU cycles per unit time, data written and read per unit time, and input/output operations per unit time;
determine an expected profile of the monitored data during the initialization, the expected profile determined based at least in part on the requested virtual machine instance; and
based on a comparison between the monitored data and the expected profile, make a determination pertaining to progress of the initialization of the requested virtual machine instance and a determination of success or failure of the process to instantiate the requested virtual machine instance.
1 Assignment
0 Petitions
Accused Products
Abstract
A computing resource of a provider network is scheduled to undergo a process. During execution of the process, data associated with the process is monitored. An expected profile of the monitored data during execution of the process is determined. The expected profile is determined based on the type of the computing resource. Based on a comparison between the monitored data and the expected profile, a determination is made as to progress of the process.
17 Citations
18 Claims
-
1. A system for managing computing resources of a provider network, the system comprising:
-
one or more computing devices; at least one memory having stored therein computer instructions that, upon execution by the system, at least cause the system to; receive a request for instantiation of a virtual machine instance on one of the one or more computing devices, the one virtual machine instance associated with a customer of the provider network; in response to the request, initiate a process to instantiate the requested virtual machine instance; during execution of the process, monitor data associated with initialization of the requested virtual machine instance to a predetermined operational state of the requested virtual machine instance, the data including one or more of CPU cycles per unit time, data written and read per unit time, and input/output operations per unit time; determine an expected profile of the monitored data during the initialization, the expected profile determined based at least in part on the requested virtual machine instance; and based on a comparison between the monitored data and the expected profile, make a determination pertaining to progress of the initialization of the requested virtual machine instance and a determination of success or failure of the process to instantiate the requested virtual machine instance. - View Dependent Claims (2, 3, 4)
-
-
5. A method for managing computing resources by a provider network, the method comprising:
-
in response to a request for a process of a computing resource of the provider network, initiating the requested process; during execution of the process, monitoring data associated with the process of the computing resource; determining an expected profile of the monitored data during execution of the process, the expected profile determined based at least in part on the computing resource; and based on a comparison between the monitored data and the expected profile, making a determination as to progress of the process of the computing resource and a determination of success or failure of the process of the computing resource. - View Dependent Claims (6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16)
-
-
17. A non-transitory computer-readable storage medium having stored thereon computer-readable instructions that, upon execution on one or more computing devices, at least cause:
-
initiating a process associated with a computing resource of a provider network; during execution of the process, monitoring externally observable data associated with the process; determining an expected profile of the monitoring externally observable data during execution of the process, the expected profile determined based at least in part on the computing resource; and based on a comparison between the monitored data and the expected profile, making a determination as to progress of the process and a determination of success or failure of the process. - View Dependent Claims (18)
-
Specification