Cache purging in a distributed networked system

A non-transitory machine-readable storage medium that provides instructions that, if executed by one or more processors of a compute server of a distributed network system will cause the compute server to perform operations comprising:

• receiving, at the compute server of the distributed networked system, a first purge request to purge a first resource from cache, wherein the compute server is part of a first data center of a plurality of data centers of the distributed networked system;
• determining that the first purge request does not include a first cache key for the first resource, and responsive to this determination:
• determining that the first purge request is valid,
• purging the first resource from cache of the first data center,
• generating the first cache key for the first resource, and
• causing a second purge request that includes the generated first cache key to be sent to one or more other data centers of the plurality of data centers of the distributed network system, the second purge request to purge the first resource;
• receiving, at the compute server, a third purge request to purge a second resource from cache;
• and
• determining that the third purge request includes a second cache key for the second resource, and responsive to this determination:
• not performing a determination of whether the third purge request is valid, and
• purging, based on the second cache key, the second resource from cache of the first data center.

A compute server of a distributed networked system, comprising:

• a set of one or more processors;
• and
• a set of one or more non-transitory machine-readable storage mediums coupled with the set of one or more processors that stores instructions that, when executed by the set of one or more processors, causes the compute server of the distributed networked system to perform operations including:
• receiving, at the compute server of the distributed network system, a first purge request to purge a first resource from cache, wherein the compute server is part of a first data center of a plurality of data centers of the distributed networked system;
• determining that the first purge request does not include a first cache key for the first resource, and responsive to this determination:
• determining that the first purge request is valid,
• purging the first resource from cache of the first data center,
• generating the first cache key for the first resource, and
• causing a second purge request that includes the generated first cache key to be sent to one or more other data centers of the plurality of data centers of the distributed network system, the second purge request to purge the first resource;
• receiving, at the compute server, a third purge request to purge a second resource from cache;
• and
• determining that the third purge request includes a second cache key for the second resource, and responsive to this determination:
• not performing a determination of whether the third purge request is valid, and
• purging, based on the second cache key, the second resource from cache of the first data center.