MB NG Task 2 Traffic Generation and Measurement

MB - NG Task 2 Traffic Generation and Measurement Definitions Pass-1 MB-NG Technical Meeting 03 May 02 R. Hughes-Jones Manchester 1

MB - NG Proposed Agenda u Load Traffic § § § Task 2. 1. 1 Define Simulated and Background Traffic Tools Control - logging u Measurement Systems § § § u u What do MB-NG NEED to measure • Tech and Political Task 2. 2. 1 Define low level Probe Measurements Metrics Pragmatic Tools Control - logging Relation to IETF and GGF Network Metrics Draft reports Next Technical “bits&bytes” Meeting AOB MB-NG Technical Meeting 03 May 02 R. Hughes-Jones Manchester 2

MB – NG Super. JANET 4 Development Network (22 Mar 02) MB - NG World. Com OC 48/POSSR-SC MAN MCC OSM-4 GEWAN-GBIC Leeds SJ 4 Dev C-Po. P Warrington 12416 OSM 1 OC 48 POS-SS Gigabit Ethernet 2. 5 Gbit POS Access 2. 5 Gbit POS core MPLS Admin. Domains RAL OSM-4 GEWAN-GBIC OSM 1 OC 48 POS-SS Super. JANET 4 Production Network SJ 4 Dev C-Po. P Reading 12416 OC 48/POSLR-SC SJ 4 Dev C-Po. P London 12416 World. Com Dark Fiber (SSE) POS MB-NG Technical Meeting 03 May 02 R. Hughes-Jones Manchester SJ 4 Dev ULCC 12016 OC 48/POSSR-SC ULCC UCL OSM-4 GEWAN-GBIC OSM 1 OC 48 POS-SS 3

MB - NG u u Defining Background Traffic Regular traffic - constant size packet, regular spaced in time Poisson traffic - constant size, exponential spacing to form transient queues IETF traffic mix - different sizes and different probability of each size sent Play back of real traffic patterns generated from packet headers pre-recorded from suitable points of the production network. This might include: § Video Conference traffic -> play back - rude/crude tools § UCL real conf playback tool § Multicast ? § General traffic captured at edge of a site, e. g. Manchester § Do tests with a gen to see what gets dropped 0. 5 Gbit typical poeak UCL u Web-bursty traffic – web mirror – wget Need to be able to reproduce traffic so no TCP as non-linear. Statistical reproducible OK In general UDP best mto understand the net but some TCP bground is good too u Self-Similar What about generating MPLS frames? ? u Consider UDP TCP flows u Need To. S / Qo. S to be set u How to control § § § Start Stop measure load as function of time – links and Queues Start and end numbers How to get data from the core routers – eg need PC in the Po. P? MB-NG Technical Meeting 03 May 02 R. Hughes-Jones Manchester 4

MB - NG Defining the Measurements (1) u Suggested Approach § § § What do we need to measure for MB-NG How do we analyse it ? What do we expect ? What does it tell us ? NOT defining the measurement matrix – link to Task 5 Policies u General Conditions include § § § IP operation MPLS Qo. S/Diffserv u u Apply techniques to understand the performance of: PC-PC Routers and (LAN) interconnects Development Core – useful to know about the GSR performance details how do we load it (PC only 1 Gig I/f – may be Spirant – Dante OC 48 kit. u End-2 -end MB-NG Technical Meeting 03 May 02 R. Hughes-Jones Manchester 5

MB - NG Defining the Measurements (10) u UDP round-trip latency vs packet size § § § Sum of dt/dl transfer rates Router performance Stack performance u UDP round-trip histograms § § Indication of network load Switching / transport effects – spikes u UDP 1 -way delay u UDP throughput vs Packet size and transmit delay § § § Throughput behaviour The effect of load on switch/router throughput Offered vs achieved throughput u UDP Packet Loss vs transmit rate and burst size § § § Loss rate ( note location of loss) Packet loss distribution as function of time Packet loss for simulated “TCP bursts” Buffer sizes in the path Detect packet re-ordering u UDP Inter-frame Jitter as function of packet transmit spacing § § Indication of network load Behaviour of end system NICs MB-NG Technical Meeting 03 May 02 R. Hughes-Jones Manchester 6

MB - NG Defining the Measurements (11) u TCP round-trip latency vs Message size § § Sum of dt/dl transfer rates (Router performance) Stack / protocol performance Detect Packet size dependencies u TCP round-trip histograms § § § Indication of network load (Switching / transport effects – spikes) Stack / protocol performance u TCP throughput vs Message size and transmit delay § § Throughput behaviour cf UDP Offered vs achieved throughput Packet loss distribution as function of time + Re-transmit rate Loss as func of pkt rate eg keep the data rate the same change pkt size – multi-streams u TCP throughput vs Window size / TCP tuning u TCP throughput vs number of streams § § § Stream throughput - benefits Packet loss distribution as function of time + Re-transmit rate Effect on Network u TCP Protocol behaviour - tcptrace § § What are the “burst” lengths Effect of routers / end system NICs MB-NG Technical Meeting 03 May 02 u All this for WRED Wt fair Qing. R. data rate const and ch pkt size – chack how well the Hughes-Jones Manchester routers do the Qing 7

MB - NG Next Steps u Who does what investigation u Draft reports u Next Technical “bits&bytes” Meeting 24 May Manchester Time Discussion! MB-NG Technical Meeting 03 May 02 R. Hughes-Jones Manchester 8