Information Resilience through User-Assisted Caching in Disruptive - PowerPoint PPT Presentation

Information Resilience through User-Assisted Caching in Disruptive Content-Centric Networks Vasilis Sourlas, Leandros Tassiulas, Ioannis Psaras, George Pavlou Best Paper Award IFIP Networking 2015 Ioannis Psaras EPSRC Fellow University College London i.psaras@ucl.ac.uk �

Problem Attacked When the network gets fragmented, and given we have a number of (in-network) caches, for how long can we keep the content “alive” in caches and end-user devices? – How do we find “alive” content (i.e., content still in caches)?

Goals • Find ways to: – Exploit all possible sources to retrieve content when the main path is “down” – Exploit in-network caching to prolong information lifetime in case of disasters – Natively support P2P-like content distribution at the network layer

Starting Points • Information-Centric Networking – Very promising future networking environment • Information retrieval is more important than location – Explicitly named content chunks/packets . – Request-response at the chunk/packet level. – Flexible to adaptation through its native support to caching, mobility and multicast. • In-network opportunistic caching – Salient characteristic of ICN. – Packets are opportunistically cached in passing by nodes. – Plenty of research on the optimization in-network caching system performance. • Disaster scenarios (earthquake, tsunami, etc.) – Usage of ICN functional parts, even when these are disconnected from the rest of the network (IETF ICNRG working group). – Difficult in today’s networks that mandate connectivity to central entities for communication.

ICN World ICN: Application-layer name à Network-layer name (the network routes to the content itself by name ) ICN Routing Engine some/weird/name some/weird/name D A B C some/weird/name E F

Information Resilience through SIT Server for content: Route based on SIT Route based on FIB some/weird/name Some sh!t happened!! D ✗ C: some/weird/name C: some/weird/name ✗ A B C R: some/weird/name F E R: some/weird/name

Key Design challenges & Contributions • How to augment the original NDN content router to increase information resilience under fragmentation? – How to forward Interests when network fragmented? • What changes are required to the main ICN packets format and their processing in order to enable P2P-like content distribution? • Can we measure information resilience ? – We build Markov processes for the hit probability and the time to absorption of an item and find lower bounds

Router Design Satisfied Interest Table (SIT) Content Store (CS) Face 0 Name Face List Name Data /a/b 1 . . /c/d 3,1 /a/b . . . . . Face 1 Index Type Ptr CS PIT Face 2 FIB SIT Pending Interest Table (PIT) Forwarding Info Base (FIB) Face 3 Name Req. Faces Prefix Face List /a/b 0,3 /a 2 /c/d 2 /c 0,1 • Content Store (CS) . . . . • Pending Interest Table (PIT) • Forwarding Information Base (FIB) Satisfied Interest Table (SIT) – Keeps track of data packet next hop. – “ Breadcrumbs ” for user-assisted caching. Same to NDN original model – Allows a list of outgoing faces. – Similar to Persistent Interests (PI) in C. Tsilopoulos and G. Xylomenos, “Supporting Diverse Traffic Types in ICN” ACM SIGCOMM ICN 2011.

Packet Processing • Interest Packet format – Destination flag ( DF ) bit to distinguish whether the Interest is headed towards content origin (DF=0), or towards neighbouring users (DF=1). • Interest Packet processing – Normal operation ( i.e., no fragmentation): Same as in NDN – Fragmentation Detected: If the Interest cannot find a match in CS, PIT and FIB then DF is set to 1 and follows entries in SIT . – An Interest with DF=1 can be replied both by routers and by users with matching cached content. • Data packet processing – Exactly the same as in NDN; follow the chain of PIT entries. – A passing by Data packet installs SIT entries. – Optionally cached in CS of each passing by router (under investigation).

Performance Bounds

System model

Absorbing State Probability

Mean Time to Absorption • Result: When the death rate of the users interested in a content item is larger than the corresponding birth rate, the item will finally get absorbed when the content origin is not reachable. – The formula above gives us the “time to absorption” [1] H. M. Taylor and S. Karlin, “An Introduction to Stochastic Modeling, 3rd edition”, Academic Press, 1998.

Performance Evaluation

Strategies/Policies (after the network fragmentation) • Interest forwarding policies – SIT based forwarding policy (STB) – Flooding forwarding policy (FLD) • Caching policies – No caching policy (NCP) – Edge caching policy (EDG) – En-route caching policy (NRT/LCE) • Placement/Replacement policies – Least Recently Used policy (LRU)

Evaluation setup • Tool: Icarus • Network topology: 50 nodes - Internet topology Zoo • Traffic demand: 1 req/sec at each node • Request distribution: Zipf and localised, i.e., different across different regions • Connection rate: 1 new user per sec • “Initialization period” of 1 hour. “Observation period” of 3 hours. Network fragmentation and origin servers of all items are not reachable.

Metrics • Satisfaction (% of issued interests ). • Absorbed Items ( % of content items ). • Mean Absorption Time ( sec ). • User Responses ( % of satisfied interests ) • Minimum Hop Distance ( hops ) • Traffic overhead ( hops ) Experiments • Model validation • Impact of cache size • Impact of users’ disconnection rate.

Model Validation 30000 V =50, � =1 , � =0.1, ��� =0 20000 10000 70 Absorption Time ( sec ) Theoretical 60 Experimental 50 40 30 20 10 0 0 200 400 600 800 1000 Information Item Perfect match between model and simulation!

Impact of the cache size 7000 100 110 Satisfaction (% of issued interests) V =50, � =1, � =0.1 V =50, � =1, � =0.1 V =50, � =1, � =0.1 STB-NCP Mean Absorption Time ( sec ) STB-NCP STB-EDG-LRU 100 Absorbed Items (% of items) 90 6000 STB-EDG-LRU STB-NRT-LRU 90 STB-NRT-LRU 80 FLD-NCP FLD-NCP FLD-EDG-LRU 5000 80 70 FLD-EDG-LRU FLD-NRT-LRU FLD-NRT-LRU 70 60 4000 60 50 50 3000 40 40 STB-NCP 30 2000 30 STB-EDG-LRU STB-NRT-LRU 20 20 FLD-NCP 1000 FLD-EDG-LRU 10 10 FLD-NRT-LRU 0 0 0 0 5 10 15 20 25 30 35 40 0 5 10 15 20 25 30 35 40 0 5 10 15 20 25 30 35 40 C / M (%) C / M (%) C / M (%) 4,0 40 100 User Resps. (% of responded interests) V =50, � =1, � =0.1 V =50, � =1, � =0.1 V =50, � =1, � =0.1 98 STB-NCP 35 3,5 96 Minimum Hop Distance Traffic Overhead ( hops ) STB-EDG-LRU 50 STB-NCP STB-NRT-LRU 30 STB-EDG-LRU FLD-NCP 3,0 STB-NRT-LRU FLD-EDG-LRU 40 25 FLD-NCP FLD-NRT-LRU FLD-EDG-LRU FLD-NRT-LRU 2,5 20 30 STB-NCP STB-EDG-LRU 15 STB-NRT-LRU 20 2,0 FLD-NCP 10 FLD-EDG-LRU 10 FLD-NRT-LRU 1,5 5 0 0 1,0 0 5 10 15 20 25 30 35 40 0 5 10 15 20 25 30 35 40 0 5 10 15 20 25 30 35 40 C / M (%) C / M (%) C / M (%) Popular messages can stay in the network for hours even with modest amounts of cache.

Impact of users’ disconnection rate 2000 85 V =50, � =1, C / M =5% Satisfaction (% of issued interests) 100 V =50, � =1, C / M =5% V =50, � =1, C / M =5% Mean Absorption Time ( sec ) Absorbed Items (% of items) 1600 80 90 STB-NCP 80 STB-EDG-LRU STB-NCP FLD-NCP 1200 STB-NRT-LRU STB-EDG-LRU FLD-EDG-LRU FLD-NCP STB-NRT-LRU FLD-NRT-LRU 70 36 800 FLD-EDG-LRU FLD-NRT-LRU 60 400 STB-NCP 30 50 STB-EDG-LRU STB-NRT-LRU FLD-NCP 24 40 30 FLD-EDG-LRU 20 FLD-NRT-LRU 30 10 18 0 20 0,0 0,2 0,4 0,6 0,8 1,0 1,5 2,0 0,0 0,2 0,4 0,6 0,8 1,0 1,5 2,0 0,0 0,2 0,4 0,6 0,8 1,0 1,5 2,0 � � � 4,0 27 User Resps. (% of responded interests) V =50, � =1, C / M =5% V =50, � =1, C / M =5% V =50, � =1, C / M =5% 50 24 3,5 Minimum Hop Distance Traffic Overhead ( hops ) 21 40 3,0 18 STB-NCP STB-EDG-LRU 15 STB-NRT-LRU 30 2,5 FLD-NCP 12 FLD-EDG-LRU STB-NCP FLD-NRT-LRU 2,0 STB-NCP 20 STB-EDG-LRU 9 STB-EDG-LRU STB-NRT-LRU STB-NRT-LRU FLD-NCP 6 1,5 FLD-NCP FLD-EDG-LRU 10 FLD-EDG-LRU FLD-NRT-LRU 3 FLD-NRT-LRU 1,0 0 0 0,0 0,2 0,4 0,6 0,8 1,0 1,5 2,0 0,0 0,2 0,4 0,6 0,8 1,0 1,5 2,0 0,0 0,2 0,4 0,6 0,8 1,0 1,5 2,0 � � � • When disconnection rate is larger than 0.2, less than 5% of the satisfied interests are served from users. • The STB enabled mechanisms discard less popular items fast and maintain the rest items for a longer period.

Conclusions q It is very easy to make the network resilient to fragmentation (at least in case of disasters). q The Satisfied Interest Table (SIT) is not memory-intensive – acts like a cache. q Some (popular) content can stay in the network for hours. q Scoped flooding can improve performance significantly (results on the way). q P2P can be supported natively in an ICN world and is very very helpful in case of disasters/fragmentation q We’re working to incorporate the Satisfied Interest Table (SIT) in the NDN normal operation.