Systems and methods for performing localized server-side monitoring in a content delivery network
View Patent ↗Some embodiments provide systems and methods for performing localized and real-time server-side network performance monitoring. These systems and methods leverage the distributed architecture of a content delivery network (CDN) so as to perform distributed monitoring with each Point-of-Presence of the CDN responsible for monitoring performance to a localized set of end users. These systems and methods also leverage existing traffic flows from a server to a particular end user in order to perform real-time server-side network performance monitoring without the injection of specialized monitoring packets and without active involvement of the end user in deriving the performance measurements. The performance measurements are then used to optimize delivery of existing and future traffic flows to the end user.
1. A computer-implemented method for optimizing content delivery, the computer-implemented method comprising:
monitoring a first throughput rate with which outgoing application layer packets of first content pass from a particular server to a first user;
determining content delivery performance to the first user based on said monitoring;
receiving a request for second content at the particular server from a different second user; and
optimizing transfer of the second content from the particular server to the second user before passing a first packet of the second content to the second user and in response to the content delivery performance to the first user, wherein said optimizing comprises at least one of (i) configuring a second throughput rate with which to initiate passing the second content to the second user based on the first throughput rate of the first content to the first user or (ii) selecting a particular encoding from a plurality of second content encodings to pass to the second user based on the first throughput rate of the first content to the first user, and wherein said optimizing further comprises reducing resources consumed in transferring the second content to the second user in response to the content delivery performance to the first user not providing a specific user experience.
2. The computer-implemented method of claim 1 , wherein reducing the resources comprises selecting the particular encoding from the plurality of second content encodings with a smallest file size.
3. The computer-implemented method of claim 1 , wherein the plurality of second content encodings comprise at least one of different file sizes, bitrates, compression levels, and resolutions for the second content.
4. The computer-implemented method of claim 1 , wherein reducing the resources comprises throttling an amount of available bandwidth when transferring the second content to the second user.
5. The computer-implemented method of claim 1 , wherein said optimizing further comprises increasing resources consumed in transferring the second content to the second user in response to the content delivery performance to the first user providing the specific user experience.
6. The computer-implemented method of claim 1 , wherein determining the content delivery performance comprises monitoring an effective throughput rate, latency, and frame loss with which application layer packets encoding the first content pass from the server to the first user.
7. The computer-implemented method of claim 1 , further comprising
monitoring the second throughput rate at which the second content passes from the particular server to the second user.
8. The computer-implemented method of claim 1 , further comprising receiving a third request comprising an identifier from a third user, wherein said identifier is one of an Internet Protocol (IP) address and Autonomous System (AS) number, and optimizing transfer of the third content from the particular server to the third user according to said second rate based on said identifier identifying the third user as operating in a same region as the second user and the third user as operating in a different region than the first user.
9. The computer-implemented method of claim 7 further comprising linking a first timestamp to the first throughput rate and a second timestamp to the second throughput rate, wherein the first timestamp identifies when the first throughput rate is monitored and the second timestamp identifies when the second throughput rate is monitored.
10. The computer-implemented method of claim 1 , further comprising optimizing transfer of third content from the particular server to a third user using the second throughput rate instead of the first throughput rate based on the second timestamp being more recent than the first timestamp.
11. The computer-implemented method of claim 7 , wherein selecting the particular encoding comprises selecting a first encoding from the plurality of second content encodings in response to the content delivery performance to the first user being less than a specific threshold and selecting a second encoding from the plurality of second content encodings in response to the content delivery performance to the first user being greater than the specific threshold, wherein the second encoding consumes greater resources than the first encoding when passing from the particular server to the second user.
12. The computer-implemented method of claim 7 further comprising monitoring a rate resulting from congestion control procedures of the particular server regulating transfer of the second content to the second user.
13. The computer-implemented method of claim 12 further comprising interrupting transfer of the second content to the second user and reoptimizing the second content based on the rate, wherein said interrupting and reoptimizing comprises interrupting transfer of a first variant of the second content and resuming said transfer with a second variant of the second content, wherein the second variant comprises at least one of a different file size, resolution, compression level, bitrate, and encoding of the second content than the first variant.
14. A computer-implemented method for optimizing content delivery, the computer implemented method comprising: monitoring a first throughput rate, latency, and frame loss with which outgoing application layer packets encoding first content pass from a particular server to a first user; determining content delivery performance to the first user based on said monitoring; receiving a request for second content at the particular server from a different second user; and optimizing transfer of the second content from the particular server to the second user before passing a first packet of the second content to the second user and in response to the content delivery performance to the first user, wherein said optimizing comprises at least one of (i) configuring a second throughput rate with which to initiate passing the second content to the second user based on the first throughput rate of the first content to the first user or (ii) selecting a particular encoding from a plurality of second content encodings to pass to the second user based on the first throughput rate of the first content to the first user.