System monitoring with metrics correlation for data center
A first set of values for a set of metrics is obtained. A given metric of the set of metrics monitors a given component of a set of components of a computing system. The first set of values is obtained during a period of expected behavior of the computing system. One or more correlations are determined between values of the first set of values to establish one or more expected correlations between values of two or more metrics. A second set of values for the set of metrics is obtained. A determination is made as to whether values of the second set of values maintain the one or more expected correlations determined based on the first set of values.
1. A method comprising:
monitoring, with one or more monitoring tools, data throughput between at least one virtualized machine and a network virtualization infrastructure of a computing system to obtain a first metric of data throughput, and data throughput between at least one storage device dedicated to the at least one virtualized machine and the network virtualization infrastructure to obtain a second metric of data throughput, wherein the computing system is a software-defined data center;
comparing the first metric of data throughput with the second metric of data throughput;
automatically transmitting, with an alert generation module of the computing system, an alert indicative of a lack of one or more expected correlations of the first and second metrics; and
causing implementation of, via a remedial entity associated with the computing system, one or more select remedial actions to address the lack of the one or more expected correlations of the first and second metrics;
wherein the alert is generated in response to detection of an imbalance between the first metric of data throughput and the second metric of data throughput;
wherein the imbalance comprises one or more differences between the first metric of data throughput and the second metric of data throughput; and
wherein the monitoring, comparing, transmitting and causing implementation steps are performed by at least one processing device, comprising a processor operatively coupled to a memory.
2. The method of claim 1 , wherein the one or more expected correlations are determined via a rule derived from domain knowledge.
3. The method of claim 1 , wherein the one or more expected correlations are determined via one or more machine learning algorithms.
4. The method of claim 1 , wherein automatically, transmitting includes notifying the remedial entity, associated with the computing system.
5. The method of claim 1 , further comprising conditioning:
first values of data throughput obtained between the at least one virtual zed machine and the network virtualization infrastructure; and
second values of data throughput obtained between the at least one storage device and the network virtualization infrastructure.
6. The method of claim 5 , wherein conditioning further comprises
transforming at least a portion of the first values and the second values to generate the first metric and the second metric.
7. The method of claim 5 , wherein the first values and the second values are obtained via the one or more monitoring tools.
8. The method of claim 7 , wherein the one or more monitoring, tools are at least partially integrated with a component of the computing system.
9. The method of claim 7 , wherein the one or more monitoring tools are not integrated with a component of the computing system.
10. The method of claim 7 , further comprising storing the first values and the second values.
11. The method of claim 1 , wherein the one or more differences includes the first metric of data throughput being greater than or less than the second metric of data throughput.
12. The method of claim 11 , wherein the one or more differences includes the second metric of data throughput being greater than the first metric of data throughput.
13. An article of manufacture comprising a non-transitory processor-readable storage medium having encoded therein executable code of one or more software programs, wherein the one or more software programs when executed by one or more processing devices implement steps of:
monitoring, with one or more monitoring tools, data throughput between at least one virtualized machine and a network virtualization infrastructure of a computing system to obtain a first metric of data throughput, and data throughput between at least one storage device dedicated to the at least one virtualized machine and the network virtualization infrastructure to obtain a second metric of data throughput, wherein the computing system is a software-defined data center;
comparing the first metric of data throughput with the second metric of data throughput;
automatically transmitting, with an alert generation module of the computing system, an alert indicative of a lack of one or more expected correlations of the first and second metrics; and
causing implementation of, via a remedial entity associated with the computing system, one or more select remedial actions to address the lack of the one or more expected correlations of the first and second metrics:
wherein the alert is generated in response to detection of an imbalance between the first metric of data throughput and the second metric of data throughput; and
wherein the imbalance comprises one or more differences between the first metric of data throughput and the second metric of data throughput.
14. An apparatus comprising:
a memory; and
a processor operatively coupled to the memory and configured to:
monitor, with one or more monitoring tools, data throughput between at least one virtualized machine and a network virtualization infrastructure of a computing system to obtain a first metric of data throughput, and data throughput between at least one storage device dedicated to the at least one virtualized machine and the network virtualization infrastructure to obtain a second metric of data throughput, wherein the computing system is a software-defined data center;
compare the first metric of data throughput with the second metric of data throughput;
automatically transmit, with an alert generation module of the computing system, an alert indicative of a lack of one or more expected correlations of the first and second metrics; and
cause implementation of, via a remedial entity associated with the computing system, one or more select remedial actions to address the lack of the one or more expected correlations of the first and second metrics;
wherein the alert is generated in response to detection of an imbalance between the first metric of data throughput and the second metric of data throughput; and
wherein the imbalance comprises one or more differences between the first metric of data throughput and the second metric of data throughput.
15. The apparatus of claim 14 , wherein the one or more expected correlations are determined via a rule derived from domain knowledge.
16. The apparatus of claim 14 , wherein the one or more expected correlations are determined via one or more machine learning algorithms.
17. The apparatus of claim 14 , wherein automatically transmitting includes notifying the remedial entity associated with the computing system.
18. The apparatus of claim 14 , further comprising conditioning:
first values of data throughput obtained between the at least one virtualized machine and the network virtualization infrastructure; and
second values of data throughput obtained between the at least one storage device and the network virtualization infrastructure.
19. The apparatus of claim 18 , wherein conditioning further comprises transforming at least a portion of the first values and the second values to generate the first metric and the second metric.
20. The apparatus of claim 14 , wherein the one or more differences includes at least one of the following:
the first metric of data throughput being greater than or less than the second metric of data throughput; and
the second metric of data throughput being greater than the first metric of data throughput.