Throttling and limiting thread resources of service computing platform
Systems and techniques are provided for monitoring and managing the performance of services accessed by sites on a computing platform. When a performance issue is identified, a service is monitored to determine if calls to the service exceed a threshold completion time. If so, a resource available to call the service is adaptively throttled by the platform.
1. A computer-implement method comprising:
determining, by a computing platform that provides computing resources to a plurality of sites that are accessed by a plurality of users and that manages access by the sites to a first service, that the first service is not meeting at least one performance metric;
in response to determining that the first service is not meeting the at least one performance metric, determining whether the first service is thread-limited by the platform;
where the first service is not thread-limited by the platform:
setting a limit on the number of threads available for calls to the first service by sites on the platform;
monitoring performance of the service after setting the limit on the number of threads available for calls to the first service by sites on the platform and, based upon the performance of the service after setting the limit on the number of threads, changing the limit on the number of threads available for calls to the first service by sites on the platform; and
where the first service is thread-limited by the platform:
changing the limit on the number of threads available for calls to the first service.
2. The method of claim 1 , wherein the performance metric is based on a typical response time of calls made to the service.
3. The method of claim 2 , wherein the performance metric is a weighted average of response times of calls made to the service.
4. The method of claim 1 , wherein the service is a resource that is external to the computing platform.
5. The method of claim 1 , wherein the service is a resource that is provided by the computing platform, which is separate and distinct from the plurality of sites.
6. The method of claim 1 , wherein the first service is an external resource that is identified by the computing platform based on a plurality of direct calls made to the external resource by the plurality of sites on the platform.
7. The method of claim 6 , further comprising identifying a sub-service within the first service that is provided by a separate portion of the external resource based upon common portions of a uniform resource locator (URL) used to access the first service and the sub-service by the plurality of sites.
8. A computing platform that provides computing resources to a plurality of sites that are accessed by a plurality of users and that manages access by the sites to a first service, the computing platform comprising:
a processor; and
a computer-readable memory storing instructions for execution by the processor which, when executed by the processor, cause the processor to:
determine that the first service is not meeting at least one performance metric;
in response to determining that the first service is not meeting the at least one performance metric, determine whether the first service is thread-limited by the platform;
where the first service is not thread-limited by the platform:
set a limit on the number of threads available for calls to the first service by sites on the platform;
monitor performance of the service after setting the limit on the number of threads available for calls to the first service by sites on the platform and, based upon the performance of the service after setting the limit on the number of threads, change the limit on the number of threads available for calls to the first service by sites on the platform; and
where the first service is thread-limited by the platform:
change the limit on the number of threads available for calls to the first service.
9. The computing platform of claim 8 , wherein the performance metric is based on a typical response time of calls made to the service.
10. The computing platform of claim 9 , wherein the performance metric is a weighted average of response times of calls made to the service.
11. The computing platform of claim 9 , wherein the service is a resource that is external to the computing platform.
12. The computing platform of claim 9 , wherein the service is a resource that is provided by the computing platform, which is separate and distinct from the plurality of sites.
13. The computing platform of claim 8 , wherein the first service is an external resource that is identified by the computing platform based on a plurality of direct calls made to the external resource by the plurality of sites on the platform.
14. The computing platform of claim 13 , further comprising identifying a sub-service within the first service that is provided by a separate portion of the external resource based upon common portions of a uniform resource locator (URL) used to access the first service and the sub-service by the plurality of sites.