Data Center TCP (DCTCP) 1TCP in the Data Center • We’ll see TCP does not meet demands of apps. – Suffers from bursty packet drops, Incast *SIGCOMM ‘09+, ... – Builds up large queues: Adds significant latency. Wastes precious buffers, esp. bad with shallow-buffered switches. • Operators work around TCP problems. ‒ Ad-hoc, inefficient, often expensive solutions ‒ No solid understanding of consequences, tradeoffs 2Methodology • What’s really going on? – Interviews with developers and operators – Analysis of applications – Switches: shallow-buffered vs deep-buffered – Measurements • A systematic study of transport in Microsoft’s DCs – Identify impairments – Identify requirements • Our solution: Data Center TCP 3Case Study: Microsoft Bing • Measurements from 6000 server production cluster • Instrumentation passively collects logs ‒ Application-level ‒ Socket-level ‒ Selected packet-level • More than 150TB of compressed data over a month 4Workloads • Partition/Aggregate (Query) • Short messages [50KB-1MB] (Coordination, Control state) • Large flows [1MB-50MB] (Data update) 5 Delay-sensitive Delay-sensitive Throughput-sensitiveImpairments • Incast • Queue Buildup • Buffer Pressure 6Incast Really Happens • Requests are jittered over 10ms window. • Jittering switched off around 8:30 am. 7 Jittering trades off median against high percentiles. 99.9th percentile is being tracked. MLA Query Completion Time (ms)Data Center Transport Requirements 8 1. High Burst Tolerance – Incast due to Partition/Aggregate is common. 2. Low Latency – Short flows, queries 3. High Throughput – Continuous data updates, large file transfers The challenge is to achieve these three together.Tension Between Requirements 9 High Burst Tolerance High Throughput Low Latency DCTCP Deep Buffers: Queuing Delays Increase Latency Shallow Buffers: Bad for Bursts & Throughput Reduced RTOmin (SIGCOMM ‘09) Doesn’t Help Latency AQM – RED: Avg Queue Not Fast Enough for Incast Objective: Low Queue Occupancy & High ThroughputThe DCTCP Algorithm 10Small Queues & TCP Throughput: The Buffer Sizing Story 17 • Bandwidth-delay product rule of thumb: – A single flow needs buffers for 100% Throughput. B Cwnd Buffer Size Throughput 100%Small Queues & TCP Throughput: The Buffer Sizing Story 17 • Bandwidth-delay product rule of thumb: – A single flow needs buffers for 100% Throughput. • Appenzeller rule of thumb (SIGCOMM ‘04): – Large # of flows: is enough. B Cwnd Buffer Size Throughput 100%Small Queues & TCP Throughput: The Buffer Sizing Story 17 • Bandwidth-delay product rule of thumb: – A single flow needs buffers for 100% Throughput. • Appenzeller rule of thumb (SIGCOMM ‘04): – Large # of flows: is enough. • Can’t rely on stat-mux benefit in the DC. – Measurements show typically 1-2 big flows at each server, at most 4.Small Queues & TCP Throughput: The Buffer Sizing Story 17 • Bandwidth-delay product rule of thumb: – A single flow needs buffers for 100% Throughput. • Appenzeller rule of thumb (SIGCOMM ‘04): – Large # of flows: is enough. • Can’t rely on stat-mux benefit in the DC. – Measurements show typically 1-2 big flows at each server, at most 4. B Real Rule of Thumb: Low Variance in Sending Rate → Small Buffers SufficeTwo Key Ideas 1. React in proportion to the extent of congestion, not its presence. Reduces variance in sending rates, lowering queuing requirements. 2. Mark based on instantaneous queue length. Fast feedback to better deal with bursts. 18 ECN Marks TCP DCTCP 1 0 1 1 1 1 0 1 1 1 Cut window by 50% Cut window by 40% 0 0 0 0 0 0 0 0 0 1 Cut window by 50% Cut window by 5%Data Center TCP Algorithm Switch side: – Mark packets when Queue Length > K. 19 Sender side: – Maintain running average of fraction of packets marked (α). In each RTT: Adaptive window decreases: – Note: decrease factor between 1 and 2. B K Mark Don’t MarkRate-based Feedback • Sources estimate fraction of time queue size exceeds a threshold, α. – a robust statistic, acting as a proxy to the load Queue Size Sample Path Queue Size Empirical Distribution * Excerpted from Kelly et al., “Stability and fairness of explicit congestion control with small buffers”, Computer Communication Review, 2008.DCTCP in Action 20 Setup: Win 7, Broadcom 1Gbps Switch Scenario: 2 long-lived flows, K = 30KB (Kbytes)Why it Works 1. High Burst Tolerance Large buffer headroom → bursts fit. Aggressive marking → sources react before packets are dropped. 2. Low Latency Small buffer occupancies → low queuing delay. 3. High Throughput ECN averaging → smooth rate adjustments, low variance. 21Analysis • How low can DCTCP maintain queues without loss of throughput? • How do we set the DCTCP parameters? 22 Need to quantify queue size oscillations (Stability). 85% Less Buffer than TCP Detailed analysis @ http://www.stanford.edu/~balaji/papers/11analysisof.pdfEvaluation • Implemented in Windows stack. • Real hardware, 1Gbps and 10Gbps experiments – 90 server testbed – Broadcom Triumph 48 1G ports – 4MB shared memory – Cisco Cat4948 48 1G ports – 16MB shared memory – Broadcom Scorpion 24 10G ports – 4MB shared memory • Numerous micro-benchmarks – Throughput and Queue Length – Multi-hop – Queue Buildup – Buffer Pressure • Cluster traffic benchmark 23 – Fairness and Convergence – Incast – Static vs Dynamic Buffer MgmtCluster Traffic Benchmark • Emulate traffic within 1 Rack of Bing cluster – 45 1G servers, 10G server for external traffic • Generate query, and background traffic – Flow sizes and arrival times follow distributions seen in Bing • Metric: – Flow completion time for queries and background flows. 24 We use RTOmin = 10ms for both TCP & DCTCP.Baseline 25 Background Flows Query FlowsBaseline 25 Background Flows Query Flows Low latency for short flows.Baseline 25 Background Flows Query Flows Low latency for short flows. High throughput for long flows.Baseline 25 Background Flows Query Flows Low latency for short flows. High throughput for long flows. High burst tolerance for query
View Full Document