State management and object storage in a distributed cloud computing network
A first compute server of a distributed cloud computing network receives a request from a first client device for an object to be handled by an object worker that includes a single instantiation of a piece of code that solely controls reading and writing access to the first object. A determination is made that the object worker is instantiated for the object and is currently running in the first compute server, and the piece of code processes the first request. The first compute server receives a message to be processed by the first object worker from a second compute server. The message includes a second request for the object from a second client device connected to the second compute server. The piece of code processes the message and transmits a reply to the second compute server.
1. A method, comprising:
instantiating, at a first one of a plurality of compute servers of a distributed cloud computing network, a first single piece of code that solely controls reading and writing to an object, wherein while instantiated at the first one of the plurality of compute servers, other entities of the distributed cloud computing network communicate with the instantiation of the first single piece of code;
receiving a plurality of first requests for the object and processing the plurality of first requests with the instantiated first single piece of code at the first one of the plurality of compute servers;
determining, by the first one of a plurality of compute servers, that the object has not been requested by client devices connected to the first one of the plurality of compute servers for a first period of time; and
automatically migrating the instantiated first single piece of code from the first one of the plurality of compute servers to a second one of the plurality of compute servers in response to the determining that the object has not been requested by client devices connected to the first one of the plurality of compute servers for the first period of time.
2. The method of claim 1 , wherein automatically migrating the instantiated first single piece of code from the first one of the plurality of compute servers to the second one of the plurality of compute servers comprises:
instantiating the first single piece of code at the second one of the plurality of compute servers and modifying a directory service to specify that the second one of the plurality of compute servers has sole control for reading and writing to the object.
3. The method of claim 2 , further comprising:
receiving, at the first one of the plurality of compute servers, a second request for the object after instantiating the first single piece of code at the second one of the plurality of compute servers and prior to modifying the directory service to specify that the second one of the plurality of compute servers has sole control for the reading and the writing to the object; and
redirecting the second request to the second one of the plurality of compute servers.
4. The method of claim 1 , wherein automatically migrating the instantiated first single piece of code from the first one of the plurality of compute servers to the second one of the plurality of compute servers comprises:
maintaining a tracking of one or more compute servers requesting the object over a second period of time, the one or more compute servers including the second one of the plurality of compute servers; and
identifying the second one of the plurality of compute servers as having a highest number of requests for the object over the second period of time.
5. The method of claim 1 , wherein the first single piece of code is instantiated at the first one of the plurality of compute servers as a result of the first one of the plurality of compute servers receiving a first request for the object from a client device, wherein the first one of the plurality of compute servers is closest to the client device in terms of an anycast implementation.
6. The method of claim 1 , wherein automatically migrating the instantiated first single piece of code from the first one of the plurality of compute servers to the second one of the plurality of compute servers comprises:
evaluating a set of one or more parameters associated with the plurality of compute servers, wherein the instantiated first single piece of code is automatically migrated to the second one of the plurality of compute servers based on the set of one or more parameters associated with the plurality of compute servers.
7. The method of claim 6 , wherein the set of one or more parameters includes a minimum total latency, wherein the second one of the plurality of compute servers has the minimum total latency of the plurality of compute servers.
8. A non-transitory machine-readable storage medium that provides instructions that, when executed by a processing system, cause the processing system to perform operations comprising:
instantiating, at a first one of a plurality of compute servers of a distributed cloud computing network, a first single piece of code that solely controls reading and writing to an object, wherein while instantiated at the first one of the plurality of compute servers, other entities of the distributed cloud computing network communicate with the instantiation of the first single piece of code;
receiving a plurality of first requests for the object and processing the plurality of first requests with the instantiated first single piece of code at the first one of the plurality of compute servers;
determining, by the first one of a plurality of compute servers, that the object has not been requested by client devices connected to the first one of the plurality of compute servers for a first period of time; and
automatically migrating the instantiated first single piece of code from the first one of the plurality of compute servers to a second one of the plurality of compute servers in response to the determining that the object has not been requested by client devices connected to the first one of the plurality of compute servers for the first period of time.
9. The non-transitory machine-readable storage medium of claim 8 , wherein automatically migrating the instantiated first single piece of code from the first one of the plurality of compute servers to the second one of the plurality of compute servers comprises:
instantiating the first single piece of code at the second one of the plurality of compute servers and modifying a directory service to specify that the second one of the plurality of compute servers has sole control for reading and writing to the object.
10. The non-transitory machine-readable storage medium of claim 9 , wherein the operations further comprise:
receiving, at the first one of the plurality of compute servers, a second request for the object after instantiating the first single piece of code at the second one of the plurality of compute servers and prior to modifying the directory service to specify that the second one of the plurality of compute servers has sole control for the reading and the writing to the object; and
redirecting the second request to the second one of the plurality of compute servers.
11. The non-transitory machine-readable storage medium of claim 8 , wherein automatically migrating the instantiated first single piece of code from the first one of the plurality of compute servers to the second one of the plurality of compute servers comprises:
maintaining a tracking of one or more compute servers requesting the object over a second period of time, the one or more compute servers including the second one of the plurality of compute servers; and
identifying the second one of the plurality of compute servers of the one or more compute servers as having a highest number of requests for the object over the second period of time.
12. The non-transitory machine-readable storage medium of claim 8 , wherein the first single piece of code is instantiated at the first one of the plurality of compute servers as a result of the first one of the plurality of compute servers receiving a first request for the object from a client device, wherein the first one of the plurality of compute servers is closest to the client device in terms of an anycast implementation.
13. The non-transitory machine-readable storage medium of claim 8 , wherein automatically migrating the instantiated first single piece of code from the first one of the plurality of compute servers to the second one of the plurality of compute servers comprises:
evaluating a set of one or more parameters associated with the plurality of compute servers, wherein the instantiated first single piece of code is automatically migrated to the second one of the plurality of compute servers based on the set of one or more parameters associated with the plurality of compute servers.
14. The non-transitory machine-readable storage medium of claim 13 , wherein the set of one or more parameters includes a minimum total latency, wherein the second one of the plurality of compute servers has the minimum total latency of the plurality of compute servers.
15. An apparatus, comprising:
a processing system; and
a non-transitory machine-readable storage medium coupled with the processing system and that provides instructions that, if executed by the processing system, cause the apparatus to perform operations including:
instantiate, at a first one of a plurality of compute servers of a distributed cloud computing network, a first single piece of code that solely controls reading and writing to an object, wherein while instantiated at the first one of the plurality of compute servers, other entities of the distributed cloud computing network communicate with the instantiation of the first single piece of code;
receive a plurality of first requests for the object and process the plurality of first requests with the instantiated first single piece of code at the first one of the plurality of compute servers;
determine, by the first one of a plurality of compute servers, that the object has not been requested by client devices connected to the first one of the plurality of compute servers for a first period of time; and
automatically migrate the instantiated first single piece of code from the first one of the plurality of compute servers to a second one of the plurality of compute servers in response to the determination that the object has not been requested by client devices connected to the first one of the plurality of compute servers for the first period of time.
16. The apparatus of claim 15 , wherein automatic migration of the instantiated first single piece of code from the first one of the plurality of compute servers to the second one of the plurality of compute servers further causes the apparatus to perform operations including:
instantiate the first single piece of code at the second one of the plurality of compute servers and modify a directory service to specify that the second one of the plurality of compute servers has sole control for reading and writing to the object.
17. The apparatus of claim 16 , wherein the instructions further cause the apparatus to perform operations including:
receive, at the first one of the plurality of compute servers, a second request for the object after instantiating the first single piece of code at the second one of the plurality of compute servers and prior to modification of the directory service to specify that the second one of the plurality of compute servers has sole control for the reading and the writing to the object; and
redirect the second request to the second one of the plurality of compute servers.
18. The apparatus of claim 15 , wherein automatic migration of the instantiated first single piece of code from the first one of the plurality of compute servers to the second one of the plurality of compute servers further causes the apparatus to perform operations including:
maintain a tracking of one or more compute servers requesting the object over a second period of time, the one or more compute servers including the second one of the plurality of compute servers; and
identify the second one of the plurality of compute servers of the one or more compute servers as having a highest number of requests for the object over the second period of time.
19. The apparatus of claim 15 , wherein the first single piece of code is instantiated at the first one of the plurality of compute servers as a result of the first one of the plurality of compute servers receiving a first request for the object from a client device, wherein the first one of the plurality of compute servers is closest to the client device in terms of an anycast implementation.
20. The apparatus of claim 15 , wherein automatic migration of the instantiated first single piece of code from the first one of the plurality of compute servers to the second one of the plurality of compute servers further causes the apparatus to perform operations including:
evaluate a set of one or more parameters associated with the plurality of compute servers, wherein the instantiated first single piece of code is to be automatically migrated to the second one of the plurality of compute servers based on the set of one or more parameters associated with the plurality of compute servers.
21. The apparatus of claim 20 , wherein the set of one or more parameters includes a minimum total latency, wherein the second one of the plurality of compute servers has the minimum total latency of the plurality of compute servers.