Modifying an SD-wan based on flow metrics
Some embodiments provide a method for modifying an SD-WAN (software-defined wide-area network). The method collects, from a set of managed forwarding elements (MFEs), multiple metrics associated with multiple data message flows sent between the set of MFEs. The method analyzes the collected multiple metrics to group the data message flows according to multiple types and to identify a ranking of the multiple groups of data message flows according to traffic throughput. The method uses the ranking to identify a set of one or more groups of data message flows. The method modifies the SD-WAN to improve forwarding through the SD-WAN for the identified set of one or more groups of data message flows.
1. A method for modifying an SD-WAN (software-defined wide-area network), the method comprising:
collecting, from a set of managed forwarding elements (MFEs), a plurality of metrics associated with a plurality of data message flows sent between the set of MFEs;
analyzing the collected plurality of metrics to group the data message flows according to a plurality of types and to identify a ranking of the plurality of groups of data message flows according to traffic throughput;
using the ranking to identify a set of one or more groups of data message flows; and
modifying the SD-WAN to improve forwarding through the SD-WAN for the identified set of one or more groups of data message flows;
wherein the at least one data message flow in the set of one or more groups of data message flows is associated with a destination network address assigned to an application hosted in a datacenter in a geographic region, wherein modifying the SD-WAN to improve forwarding for the identified set of one or more groups of data message flows comprises deploying a first MFE to the geographic region to improve forwarding to and from the application, the at least one data message flow destined for the application is one of a plurality of data message flows associated with destination network addresses located in the particular geographic region, the second MFE forwards data messages belonging to the at least one data message flow destined for the application; and a first message flow in the plurality of data messages flows associated with destination network addresses located in the geographic region is forwarded to and from the destination network addresses by a second MFEs in the set of MFEs.
2. The method of claim 1 , wherein collecting, from the set of MFEs, the plurality of metrics associated with the plurality of data message flows sent between the set of MFEs comprises collecting a plurality of quality of experience (QoE) scores associated with a plurality of SaaS applications from a particular compute machine (i) that collects QoE metrics from the set of MFEs and (ii) that uses the collected QoE metrics to compute the plurality of QoE scores.
3. The method of claim 2 , wherein the QoE metrics comprise at least packet loss rate, packet delay rate, packet jitter rate, and throughput.
4. The method of claim 2 , wherein the plurality of QoE scores specify traffic throughput associated with the plurality of flows, wherein analyzing the collected plurality of metrics to rank the plurality of data message flows according to traffic throughput comprises identifying the specified traffic throughputs from the plurality of QoE scores.
5. The method of claim 1 , wherein the additional MFE forwards data messages belonging only to the at least one data message flow destined for the particular SaaS application based on a first set of forwarding rules specifying the additional MFE as a next hop for reaching the destination network address assigned to the particular SaaS application.
6. The method of claim 5 , wherein a second set of forwarding rules specifies the one or more existing MFEs in the set of MFEs as next hops for reaching other destination network addresses located in the particular geographic region.
7. The method of claim 1 , wherein modifying the SD-WAN to improve forwarding through the SD-WAN for the identified set of one or more groups of data message flows comprises increasing capacities for a set of managed links across which data messages belonging to the identified set of one or more groups of data message flows are forwarded.
8. The method of claim 1 , wherein the identified set of one or more groups of data message flows are specified as hot flows.
9. A non-transitory machine readable medium storing a program for execution by a set of processing units, the program for modifying an SD-WAN (software-defined wide-area network), the program comprising sets of instructions for:
collecting, from a set of managed forwarding elements (MFEs), a plurality of metrics associated with a plurality of data message flows sent between the set of MFEs;
analyzing the collected plurality of metrics to group the data message flows according to a plurality of types and to identify a ranking of the plurality of groups of data message flows according to traffic throughput;
using the ranking to identify a set of one or more groups of data message flows; and
modifying the SD-WAN to improve forwarding through the SD-WAN for the identified set of one or more groups of data message flows;
wherein the at least one data message flow in the set of one or more groups of data message flows is associated with a destination network address assigned to an application hosted in a datacenter in a geographic region, wherein modifying the SD-WAN to improve forwarding for the identified set of one or more groups of data message flows comprises deploying a first MFE to the geographic region to improve forwarding to and from the application, the at least one data message flow destined for the application is one of a plurality of data message flows associated with destination network addresses located in the particular geographic region, the second MFE forwards data messages belonging to the at least one data message flow destined for the application; and a first message flow in the plurality of data messages flows associated with destination network addresses located in the geographic region is forwarded to and from the destination network addresses by a second MFEs in the set of MFEs.
10. The non-transitory machine readable medium of claim 9 , wherein the set of instructions for collecting, from the set of MFEs, the plurality of metrics associated with the plurality of data message flows sent between the set of MFEs comprises a set of instructions for collecting a plurality of quality of experience (QoE) scores associated with a plurality of SaaS applications from a particular compute machine (i) that collects QoE metrics from the set of MFEs and (ii) that uses the collected QoE metrics to compute the plurality of QoE scores.
11. The non-transitory machine readable medium of claim 10 , wherein the QoE metrics comprise at least packet loss rate, packet delay rate, packet jitter rate, and throughput.
12. The non-transitory machine readable medium of claim 10 , wherein the plurality of QoE scores specify traffic throughput associated with the plurality of flows, wherein the set of instructions for analyzing the collected plurality of metrics to rank the plurality of data message flows according to traffic throughput comprises a set of instructions for identifying the specified traffic throughputs from the plurality of QoE scores.
13. The non-transitory machine readable medium of claim 9 , wherein the additional MFE forwards data messages belonging only to the at least one data message flow destined for the particular SaaS application based on a first set of forwarding rules specifying the additional MFE as a next hop for reaching the destination network address assigned to the particular SaaS application.
14. The non-transitory machine readable medium of claim 13 , wherein a second set of forwarding rules specifies the one or more existing MFEs in the set of MFEs as next hops for reaching other destination network addresses located in the particular geographic region.
15. The non-transitory machine readable medium of claim 9 , wherein the set of instructions for modifying the SD-WAN to improve forwarding through the SD-WAN for the identified set of one or more groups of data message flows comprises a set of instructions for increasing capacities for a set of managed links across which data messages belonging to the identified set of one or more groups of data message flows are forwarded.
16. The non-transitory machine readable medium of claim 9 , wherein the identified set of one or more groups of data message flows are specified as hot flows.