Scalable distributed end-to-end performance delay measurement for segment routing policies
The present technology is directed to a scalable solution for end-to-end performance delay measurement for Segment Routing Policies on both SR-MPLS and SRv6 data planes. The scalability of the solution stems from the use of distributed PM sessions along SR Policy ECMP paths. This is achieved by dividing the SR policy into smaller sections comprised of SPT trees or sub-paths, each of which is associated with a Root-Node. Downstream SID List TLVs may be used in Probe query messages for signaling SPT information to the Root-Nodes Alternatively, this SPT signaling may be accomplished by using a centralized controller. Root-Nodes are responsible for dynamically creating PM sessions and measuring delay metrics for their associated SPT tree section. The root-nodes then send the delay metrics for their local section to an ingress PE node or to a centralized controller using delay metric TLV field of the response message.
1. A computer-implemented method for implementing distributed delay measurement comprising:
dividing a segment routing policy domain, established between an ingress node and an egress node, into a plurality of sections, wherein each section comprises a Root-Node and one or more paths originating from the Root-Node and spanning the section;
creating one or more local delay measurement sessions at each Root-Node, wherein each of the one or more local delay measurement sessions corresponds to a different path from the one or more paths originating from the Root-Node; and
calculating one or more end to end delay metrics for the segment routing policy domain by utilizing the one or more local delay measurements from each of the Root-Nodes along the segment routing policy domain.
2. The computer-implemented method of claim 1 , wherein the one or more end to end delay metrics are associated with one or more end-to-end paths between the ingress node and the egress node.
3. The computer-implemented method of claim 1 , wherein the sections, the paths spanning each of the sections and the corresponding Root-Nodes are determined by one or more delay measurement query messages sent by the ingress node.
4. The computer-implemented method of claim 3 , wherein an extended link delay metric is used in the one or more delay measurement query messages sent by the ingress node.
5. The computer-implemented method of claim 4 , wherein the extended link delay metric provides information that identifies the Root-Node for each downstream section and delay metrics for each path spanning the corresponding downstream section.
6. The computer-implemented method of claim 5 , wherein the delay measurement query messages comprising the extended link delay metric are sent, by the ingress node, to one or more adjacent Root-Nodes and forwarded thereon to each of one or more downstream Root-Nodes.
7. The computer-implemented method of claim 1 , wherein a centralized controller is used to setup the sections, Root-Nodes and the one or more paths spanning each of the sections in the segment routing policy domain.
8. The computer-implemented method of claim 1 , wherein the one or more local delay measurements at each Root-Nodes include an internal fabric delay within the Root-Node.
9. The computer-implemented method of claim 1 , wherein the one or more local delay measurements at each of the Root-Nodes include one or more input/output line card delays.
10. The computer-implemented method of claim 1 , wherein the local delay measurement sessions are created at select Root-Nodes, such that the distributed delay performance measurement is carried out only for select Sections along the segment routing policy domain.
11. A non-transitory computer-readable storage medium comprising instructions stored therein, which when executed by one or more processors, cause the processors to perform operations comprising:
partition a segment routing policy domain, established between an ingress node and an egress node, into a plurality of Sections, wherein each section comprises a Root-Node and one or more paths originating from the Root-Node and spanning the Section;
create one or more local delay measurement sessions at each Root-Node, wherein each of the one or more local delay measurement sessions corresponds to a different path from the one or more paths originating from the Root-Node and spanning the Section; and
calculate one or more end to end delay metrics for the segment routing policy domain by utilizing the one or more local delay measurements from each of the Root-Nodes along the segment routing policy domain.
12. The one or more non-transitory computer-readable medium of claim 11 , wherein the one or more end to end delay metrics are associated with one or more end-to-end paths between the ingress node and the egress node.
13. The one or more non-transitory computer-readable medium of claim 11 , wherein the Sections, the paths spanning each of the Sections and the corresponding Root-Nodes are determined by one or more delay measurement query messages sent by the ingress node.
14. The one or more non-transitory computer-readable medium of claim 13 , wherein an extended link delay metric is used in the one or more delay measurement query messages sent by the ingress node.
15. The one or more non-transitory computer-readable medium of claim 14 , wherein the extended link delay metric provides information that identifies the Root-Node for each downstream section and delay metrics for each path spanning the corresponding downstream section.
16. The one or more non-transitory computer-readable medium of claim 15 , wherein the one or more delay measurement query messages are sent, by the ingress node, to one or more adjacent Root-Nodes and forwarded thereon to each of one or more downstream Root-Nodes.
17. The one or more non-transitory computer-readable medium of claim 11 , wherein a centralized controller is used to setup the sections, Root-Nodes and the one or more paths spanning each of the sections in the segment routing policy domain.
18. The one or more non-transitory computer-readable medium of claim 11 , wherein the one or more local delay measurements sessions at each Root-Node include an internal fabric delay within the Root-Node.
19. The one or more non-transitory computer-readable medium of claim 11 , wherein the one or more local delay measurements sessions at each Root-Node include one or more input/output line card delays.
20. A system comprising:
a controller unit in communication with one or more segment routing capable nodes associated with a segment routing policy processors;
a communication interface disposed between the controller unit and the one or more segment routing capable nodes, wherein the communication interface facilitate communication between the controller unit and the one or more segment routing capable nodes, wherein
the controller unit, acting through the communication interface, designates one or more segment routing capable nodes as Root-Nodes, wherein
the controller unit initiate one or more Root-Nodes to establish one or more local delay measurement sessions, wherein
each of the one or more local delay measurement sessions corresponds to a different path established between the Root-Node and one or more adjacent downstream Root-Nodes, wherein
the controller unit calculates one or more end to end delay metrics for the segment routing policy domain by utilizing the one or more local delay measurements from each of the Root-Nodes along the segment routing policy domain.