* [Codel] fq_"codel" in apple's gear @ 2023-10-14 17:23 Dave Taht 2023-10-14 18:17 ` Jonathan Morton 0 siblings, 1 reply; 7+ messages in thread From: Dave Taht @ 2023-10-14 17:23 UTC (permalink / raw) To: codel I would really like someone with a fresh set of eyeballs to review the "codel" portion of apple's latest code drop here: https://www.linkedin.com/feed/update/urn:li:activity:7118969694987935744/ -- Oct 30: https://netdevconf.info/0x17/news/the-maestro-and-the-music-bof.html Dave Täht CSO, LibreQos ^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: [Codel] fq_"codel" in apple's gear 2023-10-14 17:23 [Codel] fq_"codel" in apple's gear Dave Taht @ 2023-10-14 18:17 ` Jonathan Morton 2023-10-14 18:50 ` Dave Taht 0 siblings, 1 reply; 7+ messages in thread From: Jonathan Morton @ 2023-10-14 18:17 UTC (permalink / raw) To: Dave Taht; +Cc: codel > On 14 Oct, 2023, at 8:23 pm, Dave Taht <dave.taht@gmail.com> wrote: > > I would really like someone with a fresh set of eyeballs to review the > "codel" portion of apple's latest code drop here: > > https://www.linkedin.com/feed/update/urn:li:activity:7118969694987935744/ So far as I can tell, it still implements DRR++ (with a comment referencing RFC-8290), but not Codel (there's also no comment referencing RFC-8289). There's at least one function for handling ECN which is simply not called, at least not in that source file. In fact, I looked in the header to see where an ECN mark counter was defined. It is referenced in essentially three places: the definition, an extraction for reporting to userspace, and an increment - in a function implementing L4S marking, not Codel. A similar counter for "early dropped" packets is incremented only when packets have to be dropped in an emergency because the queue is *full*. That's the other counter I would expect to be touched by an AQM implementation. So, no tangible improvement that I can find easily. - Jonathan Morton ^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: [Codel] fq_"codel" in apple's gear 2023-10-14 18:17 ` Jonathan Morton @ 2023-10-14 18:50 ` Dave Taht 2023-10-14 19:01 ` Dave Taht 0 siblings, 1 reply; 7+ messages in thread From: Dave Taht @ 2023-10-14 18:50 UTC (permalink / raw) To: Jonathan Morton; +Cc: codel On Sat, Oct 14, 2023 at 11:17 AM Jonathan Morton <chromatix99@gmail.com> wrote: > > > On 14 Oct, 2023, at 8:23 pm, Dave Taht <dave.taht@gmail.com> wrote: > > > > I would really like someone with a fresh set of eyeballs to review the > > "codel" portion of apple's latest code drop here: > > > > https://www.linkedin.com/feed/update/urn:li:activity:7118969694987935744/ > > So far as I can tell, it still implements DRR++ (with a comment referencing RFC-8290), but not Codel (there's also no comment referencing RFC-8289). There's at least one function for handling ECN which is simply not called, at least not in that source file. Thank you for summoning the gumption to look again. I was having blood pressure problems. > In fact, I looked in the header to see where an ECN mark counter was defined. It is referenced in essentially three places: the definition, an extraction for reporting to userspace, and an increment - in a function implementing L4S marking, not Codel. > > A similar counter for "early dropped" packets is incremented only when packets have to be dropped in an emergency because the queue is *full*. That's the other counter I would expect to be touched by an AQM implementation. Yep. I had run some tests then and saw the rtts climbing alarmingly, while polling their stack and only seeing drops in big bursty batches, total resets of the tcp flow, and so on. > So, no tangible improvement that I can find easily. > > - Jonathan Morton -- Oct 30: https://netdevconf.info/0x17/news/the-maestro-and-the-music-bof.html Dave Täht CSO, LibreQos ^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: [Codel] fq_"codel" in apple's gear 2023-10-14 18:50 ` Dave Taht @ 2023-10-14 19:01 ` Dave Taht 2023-10-14 19:44 ` Sebastian Moeller 0 siblings, 1 reply; 7+ messages in thread From: Dave Taht @ 2023-10-14 19:01 UTC (permalink / raw) To: Jonathan Morton, bloat; +Cc: codel I would be curious if fq_"codel" was still in use on the current apple products. On an OSX box, the magic command to look at the stats was: netstat -I en0 -qq # or whatever the right interface is And you can just poll that while slamming traffic through it. On Sat, Oct 14, 2023 at 11:50 AM Dave Taht <dave.taht@gmail.com> wrote: > > On Sat, Oct 14, 2023 at 11:17 AM Jonathan Morton <chromatix99@gmail.com> wrote: > > > > > On 14 Oct, 2023, at 8:23 pm, Dave Taht <dave.taht@gmail.com> wrote: > > > > > > I would really like someone with a fresh set of eyeballs to review the > > > "codel" portion of apple's latest code drop here: > > > > > > https://www.linkedin.com/feed/update/urn:li:activity:7118969694987935744/ > > > > So far as I can tell, it still implements DRR++ (with a comment referencing RFC-8290), but not Codel (there's also no comment referencing RFC-8289). There's at least one function for handling ECN which is simply not called, at least not in that source file. > > Thank you for summoning the gumption to look again. I was having blood > pressure problems. > > > In fact, I looked in the header to see where an ECN mark counter was defined. It is referenced in essentially three places: the definition, an extraction for reporting to userspace, and an increment - in a function implementing L4S marking, not Codel. > > > > A similar counter for "early dropped" packets is incremented only when packets have to be dropped in an emergency because the queue is *full*. That's the other counter I would expect to be touched by an AQM implementation. > > Yep. I had run some tests then and saw the rtts climbing alarmingly, > while polling their stack and only seeing drops in big bursty batches, > total resets of the tcp flow, and so on. > > > So, no tangible improvement that I can find easily. > > > > - Jonathan Morton > > > > -- > Oct 30: https://netdevconf.info/0x17/news/the-maestro-and-the-music-bof.html > Dave Täht CSO, LibreQos -- Oct 30: https://netdevconf.info/0x17/news/the-maestro-and-the-music-bof.html Dave Täht CSO, LibreQos ^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: [Codel] fq_"codel" in apple's gear 2023-10-14 19:01 ` Dave Taht @ 2023-10-14 19:44 ` Sebastian Moeller 2023-10-14 19:46 ` Dave Taht 0 siblings, 1 reply; 7+ messages in thread From: Sebastian Moeller @ 2023-10-14 19:44 UTC (permalink / raw) To: Dave Täht; +Cc: Jonathan Morton, bloat, codel Hi Dave, > On Oct 14, 2023, at 21:01, Dave Taht <dave.taht@gmail.com> wrote: > > netstat -I en0 -qq Here is a bit of output from macosx monterey 12.7 (on intel hardware). I know this is not really recent, ut it is the most recent I have available... This is on an realtek based USB3 ethernet dongle that used to support 1 Gbps, but at from macosx update on it is stuck on 100Mbps FastEthernet... Here is the output after a flent test: Out of my "--test-parameter markings=CS0,CS1,CS2,CS3,CS4,CS5,CS6,CS7" it seems only CS1 was honored and put into BK the rest all ended up in BE... I have zero clue what macos uses to steer packets into the different classes, might be DSCP alone, but then at least using some more exotic ones than boring CS6/CS7 No idea what CTL is, the average packet size mist be around 67 bytes... macbook:CAKE-autorate user$ netstat -I en3 -qq en3: [ sched: FQ_CODEL qlength: 0/128 ] [ pkts: 522515 bytes: 334464372 dropped pkts: 0 bytes: 0 ] ===================================================== [ pri: CTL (0) srv_cl: 0x480190 quantum: 605 drr_max: 8 ] [ queued pkts: 0 bytes: 0 ] [ dequeued pkts: 292918 bytes: 19787064 ] [ budget: 0 target qdelay: 10.00 msec update interval:100.00 msec ] [ flow control: 0 feedback: 0 stalls: 0 failed: 0 overwhelming: 0 ] [ drop overflow: 0 early: 0 memfail: 0 duprexmt:0 ] [ flows total: 0 new: 0 old: 0 ] [ throttle on: 0 off: 0 drop: 0 ] [ compressible pkts: 0 compressed pkts: 0] ===================================================== [ pri: VO (1) srv_cl: 0x400180 quantum: 605 drr_max: 8 ] [ queued pkts: 0 bytes: 0 ] [ dequeued pkts: 0 bytes: 0 ] [ budget: 0 target qdelay: 10.00 msec update interval:100.00 msec ] [ flow control: 0 feedback: 0 stalls: 0 failed: 0 overwhelming: 0 ] [ drop overflow: 0 early: 0 memfail: 0 duprexmt:0 ] [ flows total: 0 new: 0 old: 0 ] [ throttle on: 0 off: 0 drop: 0 ] [ compressible pkts: 0 compressed pkts: 0] ===================================================== [ pri: VI (2) srv_cl: 0x380100 quantum: 3028 drr_max: 6 ] [ queued pkts: 0 bytes: 0 ] [ dequeued pkts: 0 bytes: 0 ] [ budget: 0 target qdelay: 10.00 msec update interval:100.00 msec ] [ flow control: 0 feedback: 0 stalls: 0 failed: 0 overwhelming: 0 ] [ drop overflow: 0 early: 0 memfail: 0 duprexmt:0 ] [ flows total: 0 new: 0 old: 0 ] [ throttle on: 0 off: 0 drop: 0 ] [ compressible pkts: 0 compressed pkts: 0] ===================================================== [ pri: RV (3) srv_cl: 0x300110 quantum: 3028 drr_max: 6 ] [ queued pkts: 0 bytes: 0 ] [ dequeued pkts: 0 bytes: 0 ] [ budget: 0 target qdelay: 10.00 msec update interval:100.00 msec ] [ flow control: 0 feedback: 0 stalls: 0 failed: 0 overwhelming: 0 ] [ drop overflow: 0 early: 0 memfail: 0 duprexmt:0 ] [ flows total: 0 new: 0 old: 0 ] [ throttle on: 0 off: 0 drop: 0 ] [ compressible pkts: 0 compressed pkts: 0] ===================================================== [ pri: AV (4) srv_cl: 0x280120 quantum: 3028 drr_max: 6 ] [ queued pkts: 0 bytes: 0 ] [ dequeued pkts: 0 bytes: 0 ] [ budget: 0 target qdelay: 10.00 msec update interval:100.00 msec ] [ flow control: 0 feedback: 0 stalls: 0 failed: 0 overwhelming: 0 ] [ drop overflow: 0 early: 0 memfail: 0 duprexmt:0 ] [ flows total: 0 new: 0 old: 0 ] [ throttle on: 0 off: 0 drop: 0 ] [ compressible pkts: 0 compressed pkts: 0] ===================================================== [ pri: OAM (5) srv_cl: 0x200020 quantum: 1514 drr_max: 4 ] [ queued pkts: 0 bytes: 0 ] [ dequeued pkts: 0 bytes: 0 ] [ budget: 0 target qdelay: 10.00 msec update interval:100.00 msec ] [ flow control: 0 feedback: 0 stalls: 0 failed: 0 overwhelming: 0 ] [ drop overflow: 0 early: 0 memfail: 0 duprexmt:0 ] [ flows total: 0 new: 0 old: 0 ] [ throttle on: 0 off: 0 drop: 0 ] [ compressible pkts: 0 compressed pkts: 0] ===================================================== [ pri: RD (6) srv_cl: 0x180010 quantum: 1514 drr_max: 4 ] [ queued pkts: 0 bytes: 0 ] [ dequeued pkts: 13 bytes: 6684 ] [ budget: 0 target qdelay: 10.00 msec update interval:100.00 msec ] [ flow control: 0 feedback: 0 stalls: 0 failed: 0 overwhelming: 0 ] [ drop overflow: 0 early: 0 memfail: 0 duprexmt:0 ] [ flows total: 0 new: 0 old: 0 ] [ throttle on: 0 off: 0 drop: 0 ] [ compressible pkts: 0 compressed pkts: 0] ===================================================== [ pri: BE (7) srv_cl: 0x0 quantum: 1514 drr_max: 4 ] [ queued pkts: 0 bytes: 0 ] [ dequeued pkts: 225368 bytes: 314071428 ] [ budget: 0 target qdelay: 10.00 msec update interval:100.00 msec ] [ flow control: 0 feedback: 0 stalls: 0 failed: 0 overwhelming: 0 ] [ drop overflow: 0 early: 0 memfail: 0 duprexmt:0 ] [ flows total: 0 new: 0 old: 0 ] [ throttle on: 0 off: 0 drop: 0 ] [ compressible pkts: 0 compressed pkts: 0] ===================================================== [ pri: BK (8) srv_cl: 0x100080 quantum: 1514 drr_max: 2 ] [ queued pkts: 0 bytes: 0 ] [ dequeued pkts: 3831 bytes: 576846 ] [ budget: 0 target qdelay: 10.00 msec update interval:100.00 msec ] [ flow control: 0 feedback: 0 stalls: 0 failed: 0 overwhelming: 0 ] [ drop overflow: 0 early: 0 memfail: 0 duprexmt:0 ] [ flows total: 0 new: 0 old: 0 ] [ throttle on: 0 off: 0 drop: 0 ] [ compressible pkts: 0 compressed pkts: 0] ===================================================== [ pri: BK_SYS (9) srv_cl: 0x80090 quantum: 1514 drr_max: 2 ] [ queued pkts: 0 bytes: 0 ] [ dequeued pkts: 385 bytes: 22350 ] [ budget: 0 target qdelay: 10.00 msec update interval:100.00 msec ] [ flow control: 0 feedback: 0 stalls: 0 failed: 0 overwhelming: 0 ] [ drop overflow: 0 early: 0 memfail: 0 duprexmt:0 ] [ flows total: 0 new: 0 old: 0 ] [ throttle on: 0 off: 0 drop: 0 ] [ compressible pkts: 375 compressed pkts: 0] macbook:CAKE-autorate user$ uname -a Darwin macbook.local 21.6.0 Darwin Kernel Version 21.6.0: Fri Sep 15 16:17:23 PDT 2023; root:xnu-8020.240.18.703.5~1/RELEASE_X86_64 x86_64 Here is the flent output: bash-3.2$ echo "IPv4" ; date ; ping -c 10 netperf-eu.bufferbloat.net ; ./run-flent --ipv4 -l 60 -H netperf-eu.bufferbloat.net rrul_var --remote-metadata=root@192.168.42.1 --test-parameter=cpu_stats_hosts=root@192.168.42.1 --step-size=.05 --test-parameter bidir_streams=8 --test-parameter markings=CS0,CS1,CS2,CS3,CS4,CS5,CS6,CS7 --test-parameter ping_hosts=1.1.1.1 -D . -t IPv4_SQM_cake_layer-cake_LLA-ETH_OH34_U097pct45500of46719K-D090pct105000of116789K_hms-beagle2_en4TB2_TurrisOmnia-TurrisOS.6.3.2-pppoe-wan-eth2.7_2_bridged-FB7520-OpenWrt-r22256-14334c222e-OutdoorMSAN-VDSL100_2_netperf-eu.bufferbloat.net --log-file IPv4 Sat Oct 14 21:19:24 CEST 2023 PING demo.tohojo.dk (193.10.227.30): 56 data bytes 64 bytes from 193.10.227.30: icmp_seq=0 ttl=48 time=24.259 ms 64 bytes from 193.10.227.30: icmp_seq=1 ttl=48 time=22.789 ms 64 bytes from 193.10.227.30: icmp_seq=2 ttl=48 time=24.097 ms 64 bytes from 193.10.227.30: icmp_seq=3 ttl=48 time=24.433 ms 64 bytes from 193.10.227.30: icmp_seq=4 ttl=48 time=24.342 ms 64 bytes from 193.10.227.30: icmp_seq=5 ttl=48 time=24.325 ms 64 bytes from 193.10.227.30: icmp_seq=6 ttl=48 time=23.456 ms 64 bytes from 193.10.227.30: icmp_seq=7 ttl=48 time=22.628 ms 64 bytes from 193.10.227.30: icmp_seq=8 ttl=48 time=24.396 ms 64 bytes from 193.10.227.30: icmp_seq=9 ttl=48 time=23.521 ms --- demo.tohojo.dk ping statistics --- 10 packets transmitted, 10 packets received, 0.0% packet loss round-trip min/avg/max/stddev = 22.628/23.825/24.433/0.649 ms Starting Flent 2.1.1+git.7b931915 using Python 3.10.8. Starting rrul_var test. Expected run time: 70 seconds. Data file written to ./rrul_var-2023-10-14T211934.512820.IPv4_SQM_cake_layer-cake_LLA-ETH_OH34_U097pct45500of46719K-D090pct105000of116789K_hms-beagle2_en4TB2_TurrisOmnia-TurrisOS_6_3_2-pppoe-wan-eth2_7_2_bridged-FB7520-OpenWrt-r22256-14334c222e-OutdoorMSAN-VDSL100.flent.gz Summary of rrul_var test run from 2023-10-14 19:19:34.512820 Title: 'IPv4_SQM_cake_layer-cake_LLA-ETH_OH34_U097pct45500of46719K-D090pct105000of116789K_hms-beagle2_en4TB2_TurrisOmnia-TurrisOS.6.3.2-pppoe-wan-eth2.7_2_bridged-FB7520-OpenWrt-r22256-14334c222e-OutdoorMSAN-VDSL100_2_netperf-eu.bufferbloat.net' avg median 99th % # data pts Ping (ms) ICMP 1.1.1.1 (extra) : 13.10 12.90 17.40 ms 1396 Ping (ms) avg : 27.07 N/A N/A ms 1639 Ping (ms)::ICMP : 26.15 26.10 30.70 ms 1399 Ping (ms)::UDP 0 (CS0) : 27.78 27.55 32.13 ms 1639 Ping (ms)::UDP 1 (CS1) : 29.34 29.51 35.09 ms 1639 Ping (ms)::UDP 2 (CS2) : 26.18 26.06 30.56 ms 1639 Ping (ms)::UDP 3 (CS3) : 26.22 26.06 30.77 ms 1639 Ping (ms)::UDP 4 (CS4) : 26.20 25.98 30.93 ms 1639 Ping (ms)::UDP 5 (CS5) : 26.20 26.06 31.33 ms 1639 Ping (ms)::UDP 6 (CS6) : 28.13 28.11 32.86 ms 1639 Ping (ms)::UDP 7 (CS7) : 26.51 26.44 31.39 ms 1639 TCP download avg : 11.33 N/A N/A Mbits/s 1639 TCP download sum : 90.62 N/A N/A Mbits/s 1639 TCP download::0 (CS0) : 11.39 11.25 17.48 Mbits/s 1639 TCP download::1 (CS1) : 10.66 10.21 28.97 Mbits/s 1639 TCP download::2 (CS2) : 12.17 11.99 18.87 Mbits/s 1639 TCP download::3 (CS3) : 11.29 11.06 18.27 Mbits/s 1639 TCP download::4 (CS4) : 11.87 11.34 23.51 Mbits/s 1639 TCP download::5 (CS5) : 10.51 10.49 16.58 Mbits/s 1639 TCP download::6 (CS6) : 11.37 11.15 18.32 Mbits/s 1639 TCP download::7 (CS7) : 11.36 11.25 16.99 Mbits/s 1639 TCP totals : 130.00 N/A N/A Mbits/s 1639 TCP upload avg : 4.92 N/A N/A Mbits/s 1639 TCP upload sum : 39.38 N/A N/A Mbits/s 1639 TCP upload::0 (CS0) : 5.50 5.48 7.94 Mbits/s 1639 TCP upload::1 (CS1) : 2.13 2.19 2.64 Mbits/s 1639 TCP upload::2 (CS2) : 5.47 5.47 7.13 Mbits/s 1639 TCP upload::3 (CS3) : 5.47 5.48 6.97 Mbits/s 1639 TCP upload::4 (CS4) : 5.47 5.49 7.23 Mbits/s 1639 TCP upload::5 (CS5) : 5.46 5.46 6.83 Mbits/s 1639 TCP upload::6 (CS6) : 4.96 4.95 6.25 Mbits/s 1639 TCP upload::7 (CS7) : 4.92 4.94 6.18 Mbits/s 1639 cpu_stats_root@192.168.42.1::load : 0.40 0.42 0.83 1243 bash-3.2$ ^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: [Codel] fq_"codel" in apple's gear 2023-10-14 19:44 ` Sebastian Moeller @ 2023-10-14 19:46 ` Dave Taht 2023-10-15 13:09 ` Sebastian Moeller 0 siblings, 1 reply; 7+ messages in thread From: Dave Taht @ 2023-10-14 19:46 UTC (permalink / raw) To: Sebastian Moeller; +Cc: Jonathan Morton, bloat, codel thank you! A packet capture, however, would be more revealing... On Sat, Oct 14, 2023 at 12:44 PM Sebastian Moeller <moeller0@gmx.de> wrote: > > Hi Dave, > > > > On Oct 14, 2023, at 21:01, Dave Taht <dave.taht@gmail.com> wrote: > > > > netstat -I en0 -qq > > Here is a bit of output from macosx monterey 12.7 (on intel hardware). I know this is not really recent, ut it is the most recent I have available... > > This is on an realtek based USB3 ethernet dongle that used to support 1 Gbps, but at from macosx update on it is stuck on 100Mbps FastEthernet... > > > Here is the output after a flent test: > > Out of my "--test-parameter markings=CS0,CS1,CS2,CS3,CS4,CS5,CS6,CS7" it seems only CS1 was honored and put into BK the rest all ended up in BE... > I have zero clue what macos uses to steer packets into the different classes, might be DSCP alone, but then at least using some more exotic ones than boring CS6/CS7 > No idea what CTL is, the average packet size mist be around 67 bytes... > > > macbook:CAKE-autorate user$ netstat -I en3 -qq > en3: > [ sched: FQ_CODEL qlength: 0/128 ] > [ pkts: 522515 bytes: 334464372 dropped pkts: 0 bytes: 0 ] > ===================================================== > [ pri: CTL (0) srv_cl: 0x480190 quantum: 605 drr_max: 8 ] > [ queued pkts: 0 bytes: 0 ] > [ dequeued pkts: 292918 bytes: 19787064 ] > [ budget: 0 target qdelay: 10.00 msec update interval:100.00 msec ] > [ flow control: 0 feedback: 0 stalls: 0 failed: 0 overwhelming: 0 ] > [ drop overflow: 0 early: 0 memfail: 0 duprexmt:0 ] > [ flows total: 0 new: 0 old: 0 ] > [ throttle on: 0 off: 0 drop: 0 ] > [ compressible pkts: 0 compressed pkts: 0] > ===================================================== > [ pri: VO (1) srv_cl: 0x400180 quantum: 605 drr_max: 8 ] > [ queued pkts: 0 bytes: 0 ] > [ dequeued pkts: 0 bytes: 0 ] > [ budget: 0 target qdelay: 10.00 msec update interval:100.00 msec ] > [ flow control: 0 feedback: 0 stalls: 0 failed: 0 overwhelming: 0 ] > [ drop overflow: 0 early: 0 memfail: 0 duprexmt:0 ] > [ flows total: 0 new: 0 old: 0 ] > [ throttle on: 0 off: 0 drop: 0 ] > [ compressible pkts: 0 compressed pkts: 0] > ===================================================== > [ pri: VI (2) srv_cl: 0x380100 quantum: 3028 drr_max: 6 ] > [ queued pkts: 0 bytes: 0 ] > [ dequeued pkts: 0 bytes: 0 ] > [ budget: 0 target qdelay: 10.00 msec update interval:100.00 msec ] > [ flow control: 0 feedback: 0 stalls: 0 failed: 0 overwhelming: 0 ] > [ drop overflow: 0 early: 0 memfail: 0 duprexmt:0 ] > [ flows total: 0 new: 0 old: 0 ] > [ throttle on: 0 off: 0 drop: 0 ] > [ compressible pkts: 0 compressed pkts: 0] > ===================================================== > [ pri: RV (3) srv_cl: 0x300110 quantum: 3028 drr_max: 6 ] > [ queued pkts: 0 bytes: 0 ] > [ dequeued pkts: 0 bytes: 0 ] > [ budget: 0 target qdelay: 10.00 msec update interval:100.00 msec ] > [ flow control: 0 feedback: 0 stalls: 0 failed: 0 overwhelming: 0 ] > [ drop overflow: 0 early: 0 memfail: 0 duprexmt:0 ] > [ flows total: 0 new: 0 old: 0 ] > [ throttle on: 0 off: 0 drop: 0 ] > [ compressible pkts: 0 compressed pkts: 0] > ===================================================== > [ pri: AV (4) srv_cl: 0x280120 quantum: 3028 drr_max: 6 ] > [ queued pkts: 0 bytes: 0 ] > [ dequeued pkts: 0 bytes: 0 ] > [ budget: 0 target qdelay: 10.00 msec update interval:100.00 msec ] > [ flow control: 0 feedback: 0 stalls: 0 failed: 0 overwhelming: 0 ] > [ drop overflow: 0 early: 0 memfail: 0 duprexmt:0 ] > [ flows total: 0 new: 0 old: 0 ] > [ throttle on: 0 off: 0 drop: 0 ] > [ compressible pkts: 0 compressed pkts: 0] > ===================================================== > [ pri: OAM (5) srv_cl: 0x200020 quantum: 1514 drr_max: 4 ] > [ queued pkts: 0 bytes: 0 ] > [ dequeued pkts: 0 bytes: 0 ] > [ budget: 0 target qdelay: 10.00 msec update interval:100.00 msec ] > [ flow control: 0 feedback: 0 stalls: 0 failed: 0 overwhelming: 0 ] > [ drop overflow: 0 early: 0 memfail: 0 duprexmt:0 ] > [ flows total: 0 new: 0 old: 0 ] > [ throttle on: 0 off: 0 drop: 0 ] > [ compressible pkts: 0 compressed pkts: 0] > ===================================================== > [ pri: RD (6) srv_cl: 0x180010 quantum: 1514 drr_max: 4 ] > [ queued pkts: 0 bytes: 0 ] > [ dequeued pkts: 13 bytes: 6684 ] > [ budget: 0 target qdelay: 10.00 msec update interval:100.00 msec ] > [ flow control: 0 feedback: 0 stalls: 0 failed: 0 overwhelming: 0 ] > [ drop overflow: 0 early: 0 memfail: 0 duprexmt:0 ] > [ flows total: 0 new: 0 old: 0 ] > [ throttle on: 0 off: 0 drop: 0 ] > [ compressible pkts: 0 compressed pkts: 0] > ===================================================== > [ pri: BE (7) srv_cl: 0x0 quantum: 1514 drr_max: 4 ] > [ queued pkts: 0 bytes: 0 ] > [ dequeued pkts: 225368 bytes: 314071428 ] > [ budget: 0 target qdelay: 10.00 msec update interval:100.00 msec ] > [ flow control: 0 feedback: 0 stalls: 0 failed: 0 overwhelming: 0 ] > [ drop overflow: 0 early: 0 memfail: 0 duprexmt:0 ] > [ flows total: 0 new: 0 old: 0 ] > [ throttle on: 0 off: 0 drop: 0 ] > [ compressible pkts: 0 compressed pkts: 0] > ===================================================== > [ pri: BK (8) srv_cl: 0x100080 quantum: 1514 drr_max: 2 ] > [ queued pkts: 0 bytes: 0 ] > [ dequeued pkts: 3831 bytes: 576846 ] > [ budget: 0 target qdelay: 10.00 msec update interval:100.00 msec ] > [ flow control: 0 feedback: 0 stalls: 0 failed: 0 overwhelming: 0 ] > [ drop overflow: 0 early: 0 memfail: 0 duprexmt:0 ] > [ flows total: 0 new: 0 old: 0 ] > [ throttle on: 0 off: 0 drop: 0 ] > [ compressible pkts: 0 compressed pkts: 0] > ===================================================== > [ pri: BK_SYS (9) srv_cl: 0x80090 quantum: 1514 drr_max: 2 ] > [ queued pkts: 0 bytes: 0 ] > [ dequeued pkts: 385 bytes: 22350 ] > [ budget: 0 target qdelay: 10.00 msec update interval:100.00 msec ] > [ flow control: 0 feedback: 0 stalls: 0 failed: 0 overwhelming: 0 ] > [ drop overflow: 0 early: 0 memfail: 0 duprexmt:0 ] > [ flows total: 0 new: 0 old: 0 ] > [ throttle on: 0 off: 0 drop: 0 ] > [ compressible pkts: 375 compressed pkts: 0] > macbook:CAKE-autorate user$ uname -a > Darwin macbook.local 21.6.0 Darwin Kernel Version 21.6.0: Fri Sep 15 16:17:23 PDT 2023; root:xnu-8020.240.18.703.5~1/RELEASE_X86_64 x86_64 > > > Here is the flent output: > > bash-3.2$ echo "IPv4" ; date ; ping -c 10 netperf-eu.bufferbloat.net ; ./run-flent --ipv4 -l 60 -H netperf-eu.bufferbloat.net rrul_var --remote-metadata=root@192.168.42.1 --test-parameter=cpu_stats_hosts=root@192.168.42.1 --step-size=.05 --test-parameter bidir_streams=8 --test-parameter markings=CS0,CS1,CS2,CS3,CS4,CS5,CS6,CS7 --test-parameter ping_hosts=1.1.1.1 -D . -t IPv4_SQM_cake_layer-cake_LLA-ETH_OH34_U097pct45500of46719K-D090pct105000of116789K_hms-beagle2_en4TB2_TurrisOmnia-TurrisOS.6.3.2-pppoe-wan-eth2.7_2_bridged-FB7520-OpenWrt-r22256-14334c222e-OutdoorMSAN-VDSL100_2_netperf-eu.bufferbloat.net --log-file > IPv4 > Sat Oct 14 21:19:24 CEST 2023 > PING demo.tohojo.dk (193.10.227.30): 56 data bytes > 64 bytes from 193.10.227.30: icmp_seq=0 ttl=48 time=24.259 ms > 64 bytes from 193.10.227.30: icmp_seq=1 ttl=48 time=22.789 ms > 64 bytes from 193.10.227.30: icmp_seq=2 ttl=48 time=24.097 ms > 64 bytes from 193.10.227.30: icmp_seq=3 ttl=48 time=24.433 ms > 64 bytes from 193.10.227.30: icmp_seq=4 ttl=48 time=24.342 ms > 64 bytes from 193.10.227.30: icmp_seq=5 ttl=48 time=24.325 ms > 64 bytes from 193.10.227.30: icmp_seq=6 ttl=48 time=23.456 ms > 64 bytes from 193.10.227.30: icmp_seq=7 ttl=48 time=22.628 ms > 64 bytes from 193.10.227.30: icmp_seq=8 ttl=48 time=24.396 ms > 64 bytes from 193.10.227.30: icmp_seq=9 ttl=48 time=23.521 ms > > --- demo.tohojo.dk ping statistics --- > 10 packets transmitted, 10 packets received, 0.0% packet loss > round-trip min/avg/max/stddev = 22.628/23.825/24.433/0.649 ms > Starting Flent 2.1.1+git.7b931915 using Python 3.10.8. > Starting rrul_var test. Expected run time: 70 seconds. > Data file written to ./rrul_var-2023-10-14T211934.512820.IPv4_SQM_cake_layer-cake_LLA-ETH_OH34_U097pct45500of46719K-D090pct105000of116789K_hms-beagle2_en4TB2_TurrisOmnia-TurrisOS_6_3_2-pppoe-wan-eth2_7_2_bridged-FB7520-OpenWrt-r22256-14334c222e-OutdoorMSAN-VDSL100.flent.gz > > Summary of rrul_var test run from 2023-10-14 19:19:34.512820 > Title: 'IPv4_SQM_cake_layer-cake_LLA-ETH_OH34_U097pct45500of46719K-D090pct105000of116789K_hms-beagle2_en4TB2_TurrisOmnia-TurrisOS.6.3.2-pppoe-wan-eth2.7_2_bridged-FB7520-OpenWrt-r22256-14334c222e-OutdoorMSAN-VDSL100_2_netperf-eu.bufferbloat.net' > > avg median 99th % # data pts > Ping (ms) ICMP 1.1.1.1 (extra) : 13.10 12.90 17.40 ms 1396 > Ping (ms) avg : 27.07 N/A N/A ms 1639 > Ping (ms)::ICMP : 26.15 26.10 30.70 ms 1399 > Ping (ms)::UDP 0 (CS0) : 27.78 27.55 32.13 ms 1639 > Ping (ms)::UDP 1 (CS1) : 29.34 29.51 35.09 ms 1639 > Ping (ms)::UDP 2 (CS2) : 26.18 26.06 30.56 ms 1639 > Ping (ms)::UDP 3 (CS3) : 26.22 26.06 30.77 ms 1639 > Ping (ms)::UDP 4 (CS4) : 26.20 25.98 30.93 ms 1639 > Ping (ms)::UDP 5 (CS5) : 26.20 26.06 31.33 ms 1639 > Ping (ms)::UDP 6 (CS6) : 28.13 28.11 32.86 ms 1639 > Ping (ms)::UDP 7 (CS7) : 26.51 26.44 31.39 ms 1639 > TCP download avg : 11.33 N/A N/A Mbits/s 1639 > TCP download sum : 90.62 N/A N/A Mbits/s 1639 > TCP download::0 (CS0) : 11.39 11.25 17.48 Mbits/s 1639 > TCP download::1 (CS1) : 10.66 10.21 28.97 Mbits/s 1639 > TCP download::2 (CS2) : 12.17 11.99 18.87 Mbits/s 1639 > TCP download::3 (CS3) : 11.29 11.06 18.27 Mbits/s 1639 > TCP download::4 (CS4) : 11.87 11.34 23.51 Mbits/s 1639 > TCP download::5 (CS5) : 10.51 10.49 16.58 Mbits/s 1639 > TCP download::6 (CS6) : 11.37 11.15 18.32 Mbits/s 1639 > TCP download::7 (CS7) : 11.36 11.25 16.99 Mbits/s 1639 > TCP totals : 130.00 N/A N/A Mbits/s 1639 > TCP upload avg : 4.92 N/A N/A Mbits/s 1639 > TCP upload sum : 39.38 N/A N/A Mbits/s 1639 > TCP upload::0 (CS0) : 5.50 5.48 7.94 Mbits/s 1639 > TCP upload::1 (CS1) : 2.13 2.19 2.64 Mbits/s 1639 > TCP upload::2 (CS2) : 5.47 5.47 7.13 Mbits/s 1639 > TCP upload::3 (CS3) : 5.47 5.48 6.97 Mbits/s 1639 > TCP upload::4 (CS4) : 5.47 5.49 7.23 Mbits/s 1639 > TCP upload::5 (CS5) : 5.46 5.46 6.83 Mbits/s 1639 > TCP upload::6 (CS6) : 4.96 4.95 6.25 Mbits/s 1639 > TCP upload::7 (CS7) : 4.92 4.94 6.18 Mbits/s 1639 > cpu_stats_root@192.168.42.1::load : 0.40 0.42 0.83 1243 > bash-3.2$ > > > -- Oct 30: https://netdevconf.info/0x17/news/the-maestro-and-the-music-bof.html Dave Täht CSO, LibreQos ^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: [Codel] fq_"codel" in apple's gear 2023-10-14 19:46 ` Dave Taht @ 2023-10-15 13:09 ` Sebastian Moeller 0 siblings, 0 replies; 7+ messages in thread From: Sebastian Moeller @ 2023-10-15 13:09 UTC (permalink / raw) To: Dave Täht; +Cc: Jonathan Morton, bloat, codel Hi Dave, > On Oct 14, 2023, at 21:46, Dave Taht <dave.taht@gmail.com> wrote: > > thank you! A packet capture, however, would be more revealing... will try to get a packet capture later, when the rest of the users are a sleep... But I want to re-iterate 12.7 is not a recent macos version by any account, so the data will not be all that extrapolatable... Regards Sebastian > > On Sat, Oct 14, 2023 at 12:44 PM Sebastian Moeller <moeller0@gmx.de> wrote: >> >> Hi Dave, >> >> >>> On Oct 14, 2023, at 21:01, Dave Taht <dave.taht@gmail.com> wrote: >>> >>> netstat -I en0 -qq >> >> Here is a bit of output from macosx monterey 12.7 (on intel hardware). I know this is not really recent, ut it is the most recent I have available... >> >> This is on an realtek based USB3 ethernet dongle that used to support 1 Gbps, but at from macosx update on it is stuck on 100Mbps FastEthernet... >> >> >> Here is the output after a flent test: >> >> Out of my "--test-parameter markings=CS0,CS1,CS2,CS3,CS4,CS5,CS6,CS7" it seems only CS1 was honored and put into BK the rest all ended up in BE... >> I have zero clue what macos uses to steer packets into the different classes, might be DSCP alone, but then at least using some more exotic ones than boring CS6/CS7 >> No idea what CTL is, the average packet size mist be around 67 bytes... >> >> >> macbook:CAKE-autorate user$ netstat -I en3 -qq >> en3: >> [ sched: FQ_CODEL qlength: 0/128 ] >> [ pkts: 522515 bytes: 334464372 dropped pkts: 0 bytes: 0 ] >> ===================================================== >> [ pri: CTL (0) srv_cl: 0x480190 quantum: 605 drr_max: 8 ] >> [ queued pkts: 0 bytes: 0 ] >> [ dequeued pkts: 292918 bytes: 19787064 ] >> [ budget: 0 target qdelay: 10.00 msec update interval:100.00 msec ] >> [ flow control: 0 feedback: 0 stalls: 0 failed: 0 overwhelming: 0 ] >> [ drop overflow: 0 early: 0 memfail: 0 duprexmt:0 ] >> [ flows total: 0 new: 0 old: 0 ] >> [ throttle on: 0 off: 0 drop: 0 ] >> [ compressible pkts: 0 compressed pkts: 0] >> ===================================================== >> [ pri: VO (1) srv_cl: 0x400180 quantum: 605 drr_max: 8 ] >> [ queued pkts: 0 bytes: 0 ] >> [ dequeued pkts: 0 bytes: 0 ] >> [ budget: 0 target qdelay: 10.00 msec update interval:100.00 msec ] >> [ flow control: 0 feedback: 0 stalls: 0 failed: 0 overwhelming: 0 ] >> [ drop overflow: 0 early: 0 memfail: 0 duprexmt:0 ] >> [ flows total: 0 new: 0 old: 0 ] >> [ throttle on: 0 off: 0 drop: 0 ] >> [ compressible pkts: 0 compressed pkts: 0] >> ===================================================== >> [ pri: VI (2) srv_cl: 0x380100 quantum: 3028 drr_max: 6 ] >> [ queued pkts: 0 bytes: 0 ] >> [ dequeued pkts: 0 bytes: 0 ] >> [ budget: 0 target qdelay: 10.00 msec update interval:100.00 msec ] >> [ flow control: 0 feedback: 0 stalls: 0 failed: 0 overwhelming: 0 ] >> [ drop overflow: 0 early: 0 memfail: 0 duprexmt:0 ] >> [ flows total: 0 new: 0 old: 0 ] >> [ throttle on: 0 off: 0 drop: 0 ] >> [ compressible pkts: 0 compressed pkts: 0] >> ===================================================== >> [ pri: RV (3) srv_cl: 0x300110 quantum: 3028 drr_max: 6 ] >> [ queued pkts: 0 bytes: 0 ] >> [ dequeued pkts: 0 bytes: 0 ] >> [ budget: 0 target qdelay: 10.00 msec update interval:100.00 msec ] >> [ flow control: 0 feedback: 0 stalls: 0 failed: 0 overwhelming: 0 ] >> [ drop overflow: 0 early: 0 memfail: 0 duprexmt:0 ] >> [ flows total: 0 new: 0 old: 0 ] >> [ throttle on: 0 off: 0 drop: 0 ] >> [ compressible pkts: 0 compressed pkts: 0] >> ===================================================== >> [ pri: AV (4) srv_cl: 0x280120 quantum: 3028 drr_max: 6 ] >> [ queued pkts: 0 bytes: 0 ] >> [ dequeued pkts: 0 bytes: 0 ] >> [ budget: 0 target qdelay: 10.00 msec update interval:100.00 msec ] >> [ flow control: 0 feedback: 0 stalls: 0 failed: 0 overwhelming: 0 ] >> [ drop overflow: 0 early: 0 memfail: 0 duprexmt:0 ] >> [ flows total: 0 new: 0 old: 0 ] >> [ throttle on: 0 off: 0 drop: 0 ] >> [ compressible pkts: 0 compressed pkts: 0] >> ===================================================== >> [ pri: OAM (5) srv_cl: 0x200020 quantum: 1514 drr_max: 4 ] >> [ queued pkts: 0 bytes: 0 ] >> [ dequeued pkts: 0 bytes: 0 ] >> [ budget: 0 target qdelay: 10.00 msec update interval:100.00 msec ] >> [ flow control: 0 feedback: 0 stalls: 0 failed: 0 overwhelming: 0 ] >> [ drop overflow: 0 early: 0 memfail: 0 duprexmt:0 ] >> [ flows total: 0 new: 0 old: 0 ] >> [ throttle on: 0 off: 0 drop: 0 ] >> [ compressible pkts: 0 compressed pkts: 0] >> ===================================================== >> [ pri: RD (6) srv_cl: 0x180010 quantum: 1514 drr_max: 4 ] >> [ queued pkts: 0 bytes: 0 ] >> [ dequeued pkts: 13 bytes: 6684 ] >> [ budget: 0 target qdelay: 10.00 msec update interval:100.00 msec ] >> [ flow control: 0 feedback: 0 stalls: 0 failed: 0 overwhelming: 0 ] >> [ drop overflow: 0 early: 0 memfail: 0 duprexmt:0 ] >> [ flows total: 0 new: 0 old: 0 ] >> [ throttle on: 0 off: 0 drop: 0 ] >> [ compressible pkts: 0 compressed pkts: 0] >> ===================================================== >> [ pri: BE (7) srv_cl: 0x0 quantum: 1514 drr_max: 4 ] >> [ queued pkts: 0 bytes: 0 ] >> [ dequeued pkts: 225368 bytes: 314071428 ] >> [ budget: 0 target qdelay: 10.00 msec update interval:100.00 msec ] >> [ flow control: 0 feedback: 0 stalls: 0 failed: 0 overwhelming: 0 ] >> [ drop overflow: 0 early: 0 memfail: 0 duprexmt:0 ] >> [ flows total: 0 new: 0 old: 0 ] >> [ throttle on: 0 off: 0 drop: 0 ] >> [ compressible pkts: 0 compressed pkts: 0] >> ===================================================== >> [ pri: BK (8) srv_cl: 0x100080 quantum: 1514 drr_max: 2 ] >> [ queued pkts: 0 bytes: 0 ] >> [ dequeued pkts: 3831 bytes: 576846 ] >> [ budget: 0 target qdelay: 10.00 msec update interval:100.00 msec ] >> [ flow control: 0 feedback: 0 stalls: 0 failed: 0 overwhelming: 0 ] >> [ drop overflow: 0 early: 0 memfail: 0 duprexmt:0 ] >> [ flows total: 0 new: 0 old: 0 ] >> [ throttle on: 0 off: 0 drop: 0 ] >> [ compressible pkts: 0 compressed pkts: 0] >> ===================================================== >> [ pri: BK_SYS (9) srv_cl: 0x80090 quantum: 1514 drr_max: 2 ] >> [ queued pkts: 0 bytes: 0 ] >> [ dequeued pkts: 385 bytes: 22350 ] >> [ budget: 0 target qdelay: 10.00 msec update interval:100.00 msec ] >> [ flow control: 0 feedback: 0 stalls: 0 failed: 0 overwhelming: 0 ] >> [ drop overflow: 0 early: 0 memfail: 0 duprexmt:0 ] >> [ flows total: 0 new: 0 old: 0 ] >> [ throttle on: 0 off: 0 drop: 0 ] >> [ compressible pkts: 375 compressed pkts: 0] >> macbook:CAKE-autorate user$ uname -a >> Darwin macbook.local 21.6.0 Darwin Kernel Version 21.6.0: Fri Sep 15 16:17:23 PDT 2023; root:xnu-8020.240.18.703.5~1/RELEASE_X86_64 x86_64 >> >> >> Here is the flent output: >> >> bash-3.2$ echo "IPv4" ; date ; ping -c 10 netperf-eu.bufferbloat.net ; ./run-flent --ipv4 -l 60 -H netperf-eu.bufferbloat.net rrul_var --remote-metadata=root@192.168.42.1 --test-parameter=cpu_stats_hosts=root@192.168.42.1 --step-size=.05 --test-parameter bidir_streams=8 --test-parameter markings=CS0,CS1,CS2,CS3,CS4,CS5,CS6,CS7 --test-parameter ping_hosts=1.1.1.1 -D . -t IPv4_SQM_cake_layer-cake_LLA-ETH_OH34_U097pct45500of46719K-D090pct105000of116789K_hms-beagle2_en4TB2_TurrisOmnia-TurrisOS.6.3.2-pppoe-wan-eth2.7_2_bridged-FB7520-OpenWrt-r22256-14334c222e-OutdoorMSAN-VDSL100_2_netperf-eu.bufferbloat.net --log-file >> IPv4 >> Sat Oct 14 21:19:24 CEST 2023 >> PING demo.tohojo.dk (193.10.227.30): 56 data bytes >> 64 bytes from 193.10.227.30: icmp_seq=0 ttl=48 time=24.259 ms >> 64 bytes from 193.10.227.30: icmp_seq=1 ttl=48 time=22.789 ms >> 64 bytes from 193.10.227.30: icmp_seq=2 ttl=48 time=24.097 ms >> 64 bytes from 193.10.227.30: icmp_seq=3 ttl=48 time=24.433 ms >> 64 bytes from 193.10.227.30: icmp_seq=4 ttl=48 time=24.342 ms >> 64 bytes from 193.10.227.30: icmp_seq=5 ttl=48 time=24.325 ms >> 64 bytes from 193.10.227.30: icmp_seq=6 ttl=48 time=23.456 ms >> 64 bytes from 193.10.227.30: icmp_seq=7 ttl=48 time=22.628 ms >> 64 bytes from 193.10.227.30: icmp_seq=8 ttl=48 time=24.396 ms >> 64 bytes from 193.10.227.30: icmp_seq=9 ttl=48 time=23.521 ms >> >> --- demo.tohojo.dk ping statistics --- >> 10 packets transmitted, 10 packets received, 0.0% packet loss >> round-trip min/avg/max/stddev = 22.628/23.825/24.433/0.649 ms >> Starting Flent 2.1.1+git.7b931915 using Python 3.10.8. >> Starting rrul_var test. Expected run time: 70 seconds. >> Data file written to ./rrul_var-2023-10-14T211934.512820.IPv4_SQM_cake_layer-cake_LLA-ETH_OH34_U097pct45500of46719K-D090pct105000of116789K_hms-beagle2_en4TB2_TurrisOmnia-TurrisOS_6_3_2-pppoe-wan-eth2_7_2_bridged-FB7520-OpenWrt-r22256-14334c222e-OutdoorMSAN-VDSL100.flent.gz >> >> Summary of rrul_var test run from 2023-10-14 19:19:34.512820 >> Title: 'IPv4_SQM_cake_layer-cake_LLA-ETH_OH34_U097pct45500of46719K-D090pct105000of116789K_hms-beagle2_en4TB2_TurrisOmnia-TurrisOS.6.3.2-pppoe-wan-eth2.7_2_bridged-FB7520-OpenWrt-r22256-14334c222e-OutdoorMSAN-VDSL100_2_netperf-eu.bufferbloat.net' >> >> avg median 99th % # data pts >> Ping (ms) ICMP 1.1.1.1 (extra) : 13.10 12.90 17.40 ms 1396 >> Ping (ms) avg : 27.07 N/A N/A ms 1639 >> Ping (ms)::ICMP : 26.15 26.10 30.70 ms 1399 >> Ping (ms)::UDP 0 (CS0) : 27.78 27.55 32.13 ms 1639 >> Ping (ms)::UDP 1 (CS1) : 29.34 29.51 35.09 ms 1639 >> Ping (ms)::UDP 2 (CS2) : 26.18 26.06 30.56 ms 1639 >> Ping (ms)::UDP 3 (CS3) : 26.22 26.06 30.77 ms 1639 >> Ping (ms)::UDP 4 (CS4) : 26.20 25.98 30.93 ms 1639 >> Ping (ms)::UDP 5 (CS5) : 26.20 26.06 31.33 ms 1639 >> Ping (ms)::UDP 6 (CS6) : 28.13 28.11 32.86 ms 1639 >> Ping (ms)::UDP 7 (CS7) : 26.51 26.44 31.39 ms 1639 >> TCP download avg : 11.33 N/A N/A Mbits/s 1639 >> TCP download sum : 90.62 N/A N/A Mbits/s 1639 >> TCP download::0 (CS0) : 11.39 11.25 17.48 Mbits/s 1639 >> TCP download::1 (CS1) : 10.66 10.21 28.97 Mbits/s 1639 >> TCP download::2 (CS2) : 12.17 11.99 18.87 Mbits/s 1639 >> TCP download::3 (CS3) : 11.29 11.06 18.27 Mbits/s 1639 >> TCP download::4 (CS4) : 11.87 11.34 23.51 Mbits/s 1639 >> TCP download::5 (CS5) : 10.51 10.49 16.58 Mbits/s 1639 >> TCP download::6 (CS6) : 11.37 11.15 18.32 Mbits/s 1639 >> TCP download::7 (CS7) : 11.36 11.25 16.99 Mbits/s 1639 >> TCP totals : 130.00 N/A N/A Mbits/s 1639 >> TCP upload avg : 4.92 N/A N/A Mbits/s 1639 >> TCP upload sum : 39.38 N/A N/A Mbits/s 1639 >> TCP upload::0 (CS0) : 5.50 5.48 7.94 Mbits/s 1639 >> TCP upload::1 (CS1) : 2.13 2.19 2.64 Mbits/s 1639 >> TCP upload::2 (CS2) : 5.47 5.47 7.13 Mbits/s 1639 >> TCP upload::3 (CS3) : 5.47 5.48 6.97 Mbits/s 1639 >> TCP upload::4 (CS4) : 5.47 5.49 7.23 Mbits/s 1639 >> TCP upload::5 (CS5) : 5.46 5.46 6.83 Mbits/s 1639 >> TCP upload::6 (CS6) : 4.96 4.95 6.25 Mbits/s 1639 >> TCP upload::7 (CS7) : 4.92 4.94 6.18 Mbits/s 1639 >> cpu_stats_root@192.168.42.1::load : 0.40 0.42 0.83 1243 >> bash-3.2$ >> >> >> > > > -- > Oct 30: https://netdevconf.info/0x17/news/the-maestro-and-the-music-bof.html > Dave Täht CSO, LibreQos ^ permalink raw reply [flat|nested] 7+ messages in thread
end of thread, other threads:[~2023-10-15 13:09 UTC | newest] Thread overview: 7+ messages (download: mbox.gz / follow: Atom feed) -- links below jump to the message on this page -- 2023-10-14 17:23 [Codel] fq_"codel" in apple's gear Dave Taht 2023-10-14 18:17 ` Jonathan Morton 2023-10-14 18:50 ` Dave Taht 2023-10-14 19:01 ` Dave Taht 2023-10-14 19:44 ` Sebastian Moeller 2023-10-14 19:46 ` Dave Taht 2023-10-15 13:09 ` Sebastian Moeller
This is a public inbox, see mirroring instructions for how to clone and mirror all data and code used for this inbox