Evaluating CoDel, FQ_CoDel and PIE: how good are they really? Naeem - PowerPoint PPT Presentation

Evaluating CoDel, FQ_CoDel and PIE: how good are they really? Naeem Khademi <naeemk@ifi.uio.no> David Ros <David.Ros@telecom-bretagne.eu> Michael Welzl <michawe@ifi.uio.no> ICCRG – IETF 88 Vancouver, BC, Canada N. Khademi, D. Ros, M. Welzl () Evaluating CoDel, FQ_CoDel and PIE November 5, 2013 1 / 23

Outline Outline New AQM Kids Experimental Setup A Basic Test Parameter Sensitivity AQM on 802.11 WLANs FQ_CoDel: Blending SFQ and AQM ECN Conclusions and Future Work Q&A N. Khademi, D. Ros, M. Welzl () Evaluating CoDel, FQ_CoDel and PIE November 5, 2013 2 / 23

New AQM Kids The New AQM Kids on the Block... ◮ Two very recent proposals: ◮ (FQ_)CoDel (IETF 84) ◮ PIE (IETF 85) ◮ Some older AQMs dating back to early 90’s/00’s (*RED, REM, BLUE, CHOKe,...) ◮ Designed to be better than RED, just like CoDel and PIE ◮ Little academic literature available on CoDel and PIE Literature (bold = peer-reviewed) CoDel PIE FQ_CoDel [NJ12][GRT + 13] [WP12] [Whi13] [Whi13] Wired, sim [Whi13] [GRT + 13] � Wired, real-life � � Wireless (any) - � � NOTE: [WP12] and [Whi13] are on DOCSIS 3.0 while [GRT + 13] has tests with LP CC. N. Khademi, D. Ros, M. Welzl () Evaluating CoDel, FQ_CoDel and PIE November 5, 2013 3 / 23

New AQM Kids The New AQM Kids on the Block (cont.) AQM Deployment Status ◮ (W)RED is available on plenty of HW but mostly "turned off" Mentioned Reasons for Lack of Deployment ◮ Bad implementation (?) ◮ Hard to tune RED params ◮ Sally Floyd’s ARED (2001 draft, available in Linux) adaptively tunes RED params aiming for a certain target queuing => with fixed BW maps to a "target delay" ◮ Target delay can be set in ARED, CoDel and PIE N. Khademi, D. Ros, M. Welzl () Evaluating CoDel, FQ_CoDel and PIE November 5, 2013 4 / 23

Experimental Setup Experimental Setup ◮ Traffic: 60/180/300 sec (wired/wireless/RTT=500 ms) of iperf , repeated for 10 runs ◮ AQM iface: GSO TSO off, BQL=1514, txqueuelen=1000 ◮ TCP: Linux default with reno ◮ Topology: Dumbbell with 4 sender-receiver pairs Model Dell OptiPlex GX620 100 Mbps CPU Intel(R) Pentium(R) 4 CPU 3.00 GHz RAM 1 GB PC2-4200 (533 MHz) 100 Mbps A Q M Broadcom NetXtreme BCM5751 100 Mbps 100 Mbps Ethernet RTL-8139 ( AQM interface ) Dummynet router RTL8111/8168B ( Dummynet router) 100 Mbps tg3 Ethernet driver 8139too ( AQM interface) 100 Mbps 100 Mbps r8168 ( Dummynet router) 802.11 b/g D-Link DWL-G520 AR5001X+ 100 Mbps 100 Mbps 10 Mbps 802.11 driver ath5k A Q M 100 Mbps 100 Mbps Dummynet router Bottleneck router Linux 3.8.2 (FC14) OS kernel Linux 3.10.4 ( AQM router) (FC16) 100 Mbps 100 Mbps N. Khademi, D. Ros, M. Welzl () Evaluating CoDel, FQ_CoDel and PIE November 5, 2013 5 / 23

Experimental Setup Experimental Setup (cont.) ◮ AQM parameters used unless otherwise noted. CoDel PIE ARED interval=100 ms parameters in [pie]. target=5 ms parameters in [FGS01]. PIE Parameter Default value ARED Parameter Default value t update 30 ms interval 500 ms T target 20 ms α min ( 0 . 01 , p max / 4 ) α 0.125 β 0.9 β 1.25 N. Khademi, D. Ros, M. Welzl () Evaluating CoDel, FQ_CoDel and PIE November 5, 2013 6 / 23

Experimental Setup Experimental Setup (cont.) ◮ RTT is measured on per-packet basis using Synthetic Packet Pairs (SPP) tool [spp] ◮ Gives a very precise distribution of perceived RTT on the path ◮ Goodput is measured per 5-sec intervals ◮ long-term throughput/goodput does not reflect AQM performance over time (e.g. bursts of packet drops are not desired) N. Khademi, D. Ros, M. Welzl () Evaluating CoDel, FQ_CoDel and PIE November 5, 2013 7 / 23

A Basic Test A Basic Test Single TCP Flow ( RTT base =100 ms) 240 10 230 9.5 220 9 210 8.5 200 8 190 Goodput (Mbps) 7.5 180 RTT (ms) 7 170 6.5 160 6 150 5.5 140 5 130 120 4.5 110 4 100 3.5 1 1 1 5 5 5 10 10 10 20 20 20 30 30 30 1 1 1 5 5 5 10 10 10 20 20 20 30 30 30 Target Delay (ms) Target Delay (ms) CoDel PIE ARED CoDel PIE ARED (a) Per-packet RTT (b) Goodput Per-packet RTT and goodput. Bottom and top of whisker-box plots show 10th and 90th percentiles respectively. N. Khademi, D. Ros, M. Welzl () Evaluating CoDel, FQ_CoDel and PIE November 5, 2013 8 / 23

A Basic Test A Basic Test (cont.) CoDel vs. RED from K. Nichols, “Controlling Queue Delay” [NJ12] ◮ A similar trend can be observed between CoDel and RED in a different test in [NJ12] FTP traffic mix w/ and w/o web-browsing and CBR applications and RTTs from 10 ∼ 500 ms. N. Khademi, D. Ros, M. Welzl () Evaluating CoDel, FQ_CoDel and PIE November 5, 2013 9 / 23

Parameter Sensitivity Parameter Sensitivity (cont.) Target Delay (Per-packet RTT) 250 250 250 240 240 240 230 230 230 220 220 220 210 210 210 200 200 200 190 190 190 RTT (ms) RTT (ms) RTT (ms) 180 180 180 170 170 170 160 160 160 150 150 150 140 140 140 130 130 130 120 120 120 110 110 110 100 100 100 1 1 1 5 5 5 10 10 10 20 20 20 30 30 30 1 1 1 5 5 5 10 10 10 20 20 20 30 30 30 1 1 1 5 5 5 10 10 10 20 20 20 30 30 30 Target Delay (ms) Target Delay (ms) Target Delay (ms) CoDel PIE ARED CoDel PIE ARED CoDel PIE ARED (c) Light (d) Moderate (e) Heavy Per-packet RTT. Light, moderate and heavy congestion scenarios (4 senders and RTT base =100 ms). Light , moderate and heavy congestion correspond to 4, 16 and 64 concurrent TCP flows respectively. N. Khademi, D. Ros, M. Welzl () Evaluating CoDel, FQ_CoDel and PIE November 5, 2013 10 / 23

Parameter Sensitivity Parameter Sensitivity (cont.) Target Delay (Goodput) 10 Goodput (Mbps) 10 9.5 9.5 9 9 8.5 1 1 1 5 5 5 10 10 10 20 20 20 30 30 30 8.5 Goodput (Mbps) Target Delay (ms) 8 CoDel PIE ARED 7.5 (g) Moderate 7 10 6.5 Goodput (Mbps) 9.5 6 9 5.5 1 1 1 5 5 5 10 10 10 20 20 20 30 30 30 8.5 Target Delay (ms) 1 1 1 5 5 5 10 10 10 20 20 20 30 30 30 Target Delay (ms) CoDel PIE ARED CoDel PIE ARED (f) Light (h) Heavy Goodput. Light, Moderate and Heavy congestion scenarios (4 senders and RTT base =100 ms). N. Khademi, D. Ros, M. Welzl () Evaluating CoDel, FQ_CoDel and PIE November 5, 2013 11 / 23

AQM on 802.11 WLANs AQM on 802.11 WLANs ◮ 802.11 is a challenging environment for AQM deployment ◮ Varying MCS (BW) by RA and MAC retries ◮ Some drivers still use SampleRate instead of Minstrel (e.g. in FBSD) ◮ Shared channel with various active STAs ◮ Direction-based unfairness (uplink vs. downlink) ◮ Hard to predict the BW as input to ARED ◮ We use TCP max achievable BW for testing (e.g. ∼ 27 Mbps in .11g) ◮ CoDel and PIE use delay ◮ CoDel: queuing delay by timestamping ◮ PIE: estimated queuing delay (queue_length / departure_rate) ◮ Public Wi-Fi e.g. at airports, hotels, corporations with bottleneck on wlanX interface N. Khademi, D. Ros, M. Welzl () Evaluating CoDel, FQ_CoDel and PIE November 5, 2013 12 / 23

AQM on 802.11 WLANs AQM on 802.11 WLANs (cont.) 802.11 Downlink Traffic Scenario – Target Delay=5 ms 280 22 270 21.5 260 250 21 240 230 20.5 220 Goodput (Mbps) 20 210 RTT (ms) 200 19.5 190 180 19 170 18.5 160 150 18 140 130 17.5 120 17 110 100 16.5 1 1 1 4 4 4 8 8 8 16 16 16 1 1 1 4 4 4 8 8 8 16 16 16 Flows per sender # Flows per sender # CoDel PIE ARED CoDel PIE ARED (i) Per-packet RTT (j) Goodput 4 senders, RTT base =100 ms. N. Khademi, D. Ros, M. Welzl () Evaluating CoDel, FQ_CoDel and PIE November 5, 2013 13 / 23

AQM on 802.11 WLANs AQM on 802.11 WLANs (cont.) ◮ AQM on AP’s wlanX interface ◮ ∼ 65%/ ∼ 70% ACK loss at AQM (ARED) router for 16/32 flows. 802.11 Mixed Traffic – Target Delay=5 ms (Uplink’s Stats) 2400 2200 2000 1800 27 Goodput (Mbps) 1600 26.5 RTT (ms) 26 1400 25.5 1200 25 24.5 1000 24 1 1 1 4 4 4 8 8 8 16 16 16 800 Flows per sender # 600 CoDel PIE ARED 400 1 1 1 4 4 4 8 8 8 16 16 16 (l) Goodput Flows per sender # CoDel PIE ARED (k) Per-packet RTT 4 senders, RTT base =100 ms. N. Khademi, D. Ros, M. Welzl () Evaluating CoDel, FQ_CoDel and PIE November 5, 2013 14 / 23

FQ_CoDel: Blending SFQ and AQM FQ_CoDel: Blending SFQ and AQM Comparison between CoDel and FQ_CoDel – target _ delay =5 ms ◮ SFQ is highly likely to improve 210 the performance when 200 combined with any AQM 190 180 ◮ Flow isolation/protection 170 RTT (ms) 160 with non-responsive traffic 150 ◮ Close to 100% flow-level 140 130 fairness on the edge 120 ◮ Significantly Lower 10th 110 100 percentile and median RTTs 1 1 4 4 8 8 16 16 Flows per sender # but with longer (upper) CoDel FQ-CoDel distribution tail Per-packet RTT. 4 senders and RTT base =100 ms. N. Khademi, D. Ros, M. Welzl () Evaluating CoDel, FQ_CoDel and PIE November 5, 2013 15 / 23