Abstract: Systems and methods for performing diagnostic tests within a multi-tenant environment are described. Diagnostics are performed on one or more components, such as host computing devices. The one or more components send resulting diagnostic information to an ingester which collects the diagnostic information. The ingester then sends the diagnostic information to a database. A generator is able to query the information in the database and create metrics. Based at least in part on metrics, an alarm may be triggered.

Abstract: Systems and methods for performing diagnostic tests within a multi-tenant environment are described. Diagnostics are performed on one or more components, such as host computing devices. The one or more components send resulting diagnostic information to an ingester which collects the diagnostic information. The ingester then sends the diagnostic information to a database. A generator is able to query the information in the database and create metrics. Based at least in part on metrics, an alarm may be triggered.

Abstract: A technology is described for determining a launch workflow for launching multiple computing instances on a physical host in a computing service environment using a predicted launch time. An example method may include receiving a launch plan to launch a plurality of computing instances on a physical host within a computing service environment. A first launch workflow and a second launch workflow may then be determined for the launch plan where the first launch workflow and the second launch workflow may specify different sequences of operations performed to launch the computing instance on the physical host. Predicted launch times for the first launch workflow and the second launch workflow may be obtained and the predicted launch times may be compared to determine a launch workflow used in executing the launch plan.

Abstract: Systems and methods for performing diagnostic tests within a multi-tenant environment are described. Diagnostics are performed on one or more components, such as host computing devices. The one or more components send resulting diagnostic information to an ingester which collects the diagnostic information. The ingester then sends the diagnostic information to a database. A generator is able to query the information in the database and create metrics. Based at least in part on metrics, an alarm may be triggered.

Abstract: A technology is described for managing computing capacity within a computing service environment. An example method may include determining a state of a computing service environment having a group of physical hosts that execute computing instances and determining a predicted demand for computing instance launches on the group of physical hosts. A co-location of the computing instance launches on the group of physical hosts may then be determined by applying the predicted demand for computing instance launches to the state of the computing service environment. A predicted launch time for the computing instance launches may then be determined using the co-location of the computing instance launches as an input feature. An additional physical host may then be added to the group of physical hosts to decrease the predicted launch time.

Abstract: A technology is described for predicting a launch time for a computing instance. An example method may include receiving a request for a predicted launch time to launch a computing instance on a physical host within a computing service environment. Data associated with launch features of a computing instance may then be obtained, where the launch features may be determined to have an impact on a launch time of the computing instance on a physical host within a computing service environment. The launch features of the computing instance may then be input to a machine learning model that outputs the predicted launch time for launching the computing instance within the computing service environment.

Abstract: A technology is described for providing a recommended launch configuration for a computing instance based on a predicted launch time. An example method may include receiving a launch plan to launch a computing instance on a physical host within a computing service environment, where the launch plan includes a launch configuration. Upon receiving the launch plan, a predicted launch time may be determined for the computing instance based on the launch configuration. The launch configuration may then be analyzed to identify changes to the launch configuration that may result in an improved predicted launch time as compared to the predicted launch time. A recommended change may then be provided for the launch configuration as a result of a determination that the change to the launch configuration results in the improved predicted launch time.

Abstract: Technology is described for determining computing instance placement. A request to launch a computing instance in a computing service environment may be received. Estimated launch times for the computing instance to launch on individual physical hosts in a group of physical hosts may be identified. A physical host in the group of physical hosts that can provide placement of the computing instance may be selected based in part on the estimated launch times for the computing instance and additional factors related to placement of the computing instance.

Abstract: Attacks, such as MITM and DoS attacks, on a distributed computing system may be detected by sending a work assignment to an execution device through a first communication channel. A report may then be received through a second communication channel of the work assignment received by the execution device. Information regarding the received work assignment may then be in view of information regarding the sent work assignment to determine whether an error, such as an MITM or DoS attack, has occurred. If the analysis indicates that the report does not include the sent work assignment, then a DoS attack may have occurred. If the analysis indicates that the work assignment received by the recipient does not correspond to the sent work assignment, then a MITM attack may have occurred. If an error has occurred, an indication might be recorded and/or other types of actions might also be taken.

Abstract: Technology is described for monitoring computing instance launch times. A launch plan for launching a computing instance in a computing service environment may be identified. A predicted launch time for launching the computing instance on a selected physical host in the computing service environment may be determined using a launch time prediction model. An actual launch time for launching the computing instance in the computing service environment may be identified. The predicted launch time that is determined using the launch time prediction model may be compared with the actual launch time for launching the computing instance in the computing service environment. The actual launch time may be determined as not being within a defined threshold of the predicted launch time. An alert may be generated to indicate that the actual launch time is not within the defined threshold of the predicted launch time.

Abstract: Technology is described for reducing computing instance launch times. A computing instance that is expected to be launched in a computing service environment during a defined time period may be identified. A machine image associated with the computing instance may be determined to be cached in the computing service environment using a launch time prediction model to reduce a launch time for launching the computing instance as compared to not caching the machine image. At least one physical host in the computing service environment that is available to cache the machine image may be selected to lower the launch time of the computing instance as predicted by the launch time prediction model. The machine image may be stored in the physical host in order to minimize the launch time for launching the computing instance in the computing service environment, using the processor.

Abstract: A method and apparatus for identifying abnormal clusters are disclosed. In the method and apparatus, host activity data is received and cluster processing is performed on the host activity data of the plurality of hosts to determine the presence of any abnormal clusters of abnormal host activity data. The cluster processing results in a yielded clusters that are then compared with baseline clusters to identify the abnormal clusters.

Abstract: A technology is described for predicting a launch time for a computing instance. An example method may include receiving a request for a predicted launch time to launch a computing instance on a physical host within a computing service environment. Data associated with launch features of a computing instance may then be obtained, where the launch features may be determined to have an impact on a launch time of the computing instance on a physical host within a computing service environment. The launch features of the computing instance may then be input to a machine learning model that outputs the predicted launch time for launching the computing instance within the computing service environment.

Abstract: Technology is described for determining computing instance placement. A request to launch a computing instance in a computing service environment may be received. Estimated launch times for the computing instance to launch on individual physical hosts in a group of physical hosts may be identified. A physical host in the group of physical hosts that can provide placement of the computing instance may be selected based in part on the estimated launch times for the computing instance and additional factors related to placement of the computing instance.

Abstract: Technology is described for reducing computing instance launch times. A computing instance that is expected to be launched in a computing service environment during a defined time period may be identified. A machine image associated with the computing instance may be determined to be cached in the computing service environment using a launch time prediction model to reduce a launch time for launching the computing instance as compared to not caching the machine image. At least one physical host in the computing service environment that is available to cache the machine image may be selected to lower the launch time of the computing instance as predicted by the launch time prediction model. The machine image may be stored in the physical host in order to minimize the launch time for launching the computing instance in the computing service environment, using the processor.