Preloading On-Demand Code Pieces in A Distributed Cloud Computing Network

A non-transitory machine-readable storage medium that provides instructions that, when executed by a processor, cause said processor to perform operations comprising:

• receiving, at a first one of a plurality of compute servers of a distributed cloud computing network, an indication of a hostname in a Transport Layer Security (TLS) handshake message from a client device;
• determining that a first one of a plurality of on-demand code pieces is configured to execute on the first compute server responsive to receiving an HTTP request for the hostname, wherein the first on-demand code piece is not loaded for execution on the first compute server at a time of receiving the indication of the hostname received in the TLS handshake message;
• responsive to the determining and prior to receiving the HTTP request for the hostname, preloading the first on-demand code piece for execution on the first compute server;
• receiving, at the first compute server, an HTTP request from the client device for the hostname that triggers execution of the preloaded first on-demand code piece;
• executing the preloaded first on-demand code piece;
• generating a response to the HTTP request based at least in part on the executed preloaded first on-demand code piece;
• and
• transmitting the generated response to the client device.

A first compute server, comprising:

• a processor;
• and
• a non-transitory machine-readable storage medium that provides instructions that, when executed by the processor, cause the apparatus to perform operations comprising:
• receiving, at the first compute server, an indication of a hostname in a Transport Layer Security (TLS) handshake message from a client device, wherein the first compute server is one of a plurality of compute servers of a distributed cloud computing network;
• determining that a first one of a plurality of on-demand code pieces is configured to execute on the first compute server responsive to receiving an HTTP request for the hostname, wherein the first on-demand code piece is not loaded for execution on the first compute server at a time of receiving the indication of the hostname received in the TLS handshake message;
• responsive to the determining and prior to receiving the HTTP request for the hostname, preloading the first on-demand code piece for execution on the first compute server;
• receiving, at the first compute server, an HTTP request from the client device for the hostname that triggers execution of the preloaded first on-demand code piece;
• executing the preloaded first on-demand code piece;
• generating a response to the HTTP request based at least in part on the executed preloaded first on-demand code piece;
• and
• transmitting the generated response to the client device.