Page MenuHomeFreeBSD

transportUmbrella
ActivePublic

Recent Activity

May 9 2019

tuexen closed D17614: RFC6582 - prevent cwnd to collapse down to 1 mss after exiting recovery.
May 9 2019, 7:11 AM · transport

Apr 25 2019

rscheff_gmx.at added a comment to D17614: RFC6582 - prevent cwnd to collapse down to 1 mss after exiting recovery.

Lawrence reviewed this during IETF104, Michael volunteered to follup up with the full commit process.

Apr 25 2019, 2:15 PM · transport

Apr 24 2019

scottl removed a member for transport: scottl.
Apr 24 2019, 3:29 PM

Mar 28 2019

lstewart accepted D17614: RFC6582 - prevent cwnd to collapse down to 1 mss after exiting recovery.
Mar 28 2019, 1:58 PM · transport

Feb 15 2019

lohithbsd_gmail.com added a member for transport: lohithbsd_gmail.com.
Feb 15 2019, 10:48 PM

Feb 5 2019

rscheff_gmx.at updated the diff for D17614: RFC6582 - prevent cwnd to collapse down to 1 mss after exiting recovery.
  • prepare to land
Feb 5 2019, 7:51 PM · transport
rscheff_gmx.at added a comment to D17614: RFC6582 - prevent cwnd to collapse down to 1 mss after exiting recovery.

Over the last two or three weeks, we have run a large number of performance regression tests including this patch, in particular again workloads with frequent app-stalls (no additional data to send for about an RTO interval). That type of workload very often causes burst to be transmitted, including self-inflicted packet drops.

Feb 5 2019, 1:01 PM · transport

Jan 31 2019

chengc_netapp.com accepted D17614: RFC6582 - prevent cwnd to collapse down to 1 mss after exiting recovery.

Looks good. I think Richard can update more that we recently tested this patch.

Jan 31 2019, 4:59 PM · transport

Jan 24 2019

rscheff_gmx.at added a comment to D17614: RFC6582 - prevent cwnd to collapse down to 1 mss after exiting recovery.

Looking at D8225, that all seems to be code while in loss recovery. This patch is to restore a sane minimum cwnd once exiting loss recovery - so I don't see how these would be directly related.

Jan 24 2019, 10:16 PM · transport
kbowling added a comment to D17614: RFC6582 - prevent cwnd to collapse down to 1 mss after exiting recovery.

I remember we tried to analyze and improve this and found some unintended consequences between @hiren and @lstewart https://reviews.freebsd.org/D8225 so it got backed out. @lstewart do you remember the details for backing it out?

Jan 24 2019, 9:25 PM · transport

Jan 18 2019

rscheff_gmx.at updated the diff for D17614: RFC6582 - prevent cwnd to collapse down to 1 mss after exiting recovery.
  • fixing trailing whitespaces
Jan 18 2019, 3:22 PM · transport
rscheff_gmx.at updated the diff for D17614: RFC6582 - prevent cwnd to collapse down to 1 mss after exiting recovery.
  • remove siftr patch
Jan 18 2019, 3:19 PM · transport
rscheff_gmx.at updated the diff for D17614: RFC6582 - prevent cwnd to collapse down to 1 mss after exiting recovery.
  • fixing trailing whitespaces
Jan 18 2019, 3:14 PM · transport
rscheff_gmx.at added a comment to D17614: RFC6582 - prevent cwnd to collapse down to 1 mss after exiting recovery.

Here is the output of the now functional siftr, without and with the patch;

Jan 18 2019, 12:09 PM · transport

Jan 16 2019

rscheff_gmx.at added a comment to D17614: RFC6582 - prevent cwnd to collapse down to 1 mss after exiting recovery.

I have been testing this patch against a stable/11 build. Over a 1Gb/s link with emulated 40ms RTT and (10^-4) loss rate, I use iperf from a FreeBSD node to send traffic to a 4.15.0-39-generic Ubuntu16.04 client.
[...]
Using siftr, I still see the single MSS cwnd, and sometimes with a 40ms delay to update a second cwnd. The full cwnd log is attached.


The congestion control in use is newreno.
timestamp cwnd ssthresh
...
1.92838096618652 115052 70875
1.92838382720947 1448 56940 <<< single MSS
1.96786689758301 2896 56940 <<< 40ms delay
1.96786999702454 4344 56940
1.96787786483765 5792 56940
1.96788096427917 7240 56940

Jan 16 2019, 12:08 AM · transport

Jan 15 2019

chengc_netapp.com added a comment to D17614: RFC6582 - prevent cwnd to collapse down to 1 mss after exiting recovery.

I have been testing this patch against a stable/11 build. Over a 1Gb/s link with emulated 40ms RTT and (10^-4) loss rate, I use iperf from a FreeBSD node to send traffic to a 4.15.0-39-generic Ubuntu16.04 client.

Jan 15 2019, 8:54 PM · transport

Jan 3 2019

rscheff_gmx.at added a comment to D17614: RFC6582 - prevent cwnd to collapse down to 1 mss after exiting recovery.

Attached is a tcptrace of a real-world observed issue, where the lack of RFC6582 results in cwnd shrinking down to 1 MSS, followed by delayed ACK timeout and congestion avoidance growth of cwnd (1 MSS per RTT).

Jan 3 2019, 9:09 AM · transport

Jan 2 2019

chengc_netapp.com added a comment to D17614: RFC6582 - prevent cwnd to collapse down to 1 mss after exiting recovery.

Thanks for the review request.
I will test this patch in Emulab.net before I give more feedback.

Jan 2 2019, 3:04 PM · transport

Dec 18 2018

rscheff_gmx.at added a comment to D17614: RFC6582 - prevent cwnd to collapse down to 1 mss after exiting recovery.

This packetdrill script should complete without error, when IW10 and the above patch are applied, for a SACK session, or non-SACK session.

Dec 18 2018, 4:15 PM · transport

Dec 15 2018

rscheff_gmx.at updated the diff for D17614: RFC6582 - prevent cwnd to collapse down to 1 mss after exiting recovery.

Minor comment edit
and moving to GIT/Phabricator/ARC workflow

Dec 15 2018, 8:40 PM · transport

Nov 29 2018

rscheff_gmx.at added a reviewer for D17614: RFC6582 - prevent cwnd to collapse down to 1 mss after exiting recovery: chengc_netapp.com.
Nov 29 2018, 10:33 PM · transport
rscheff_gmx.at added reviewers for D17614: RFC6582 - prevent cwnd to collapse down to 1 mss after exiting recovery: tuexen, rrs, hiren.
Nov 29 2018, 10:08 PM · transport
julius.flohr_uni-due.de added a member for transport: julius.flohr_uni-due.de.
Nov 29 2018, 10:02 AM

Oct 18 2018

rscheff_gmx.at created D17614: RFC6582 - prevent cwnd to collapse down to 1 mss after exiting recovery.
Oct 18 2018, 10:03 PM · transport

Oct 3 2018

erj resigned from D4295: Add driver backpressure.
Oct 3 2018, 5:22 PM · transport

Oct 1 2018

kbowling accepted D4294: modernize TCP constants.

This LGTM taking @hiren suggestion to drop the unused TCPTV_CPU_VAR define. At LLNW we ran w/o delack to work around most of the issues this addresses in a more elegant way.

Oct 1 2018, 2:56 AM · transport

Jun 9 2018

benno removed a member for transport: benno.
Jun 9 2018, 8:21 PM

Jun 8 2018

lstewart added a member for transport: lstewart.
Jun 8 2018, 6:28 PM

May 23 2018

thj added a member for transport: thj.
May 23 2018, 6:37 AM

May 15 2018

mmacy added a member for transport: mmacy.
May 15 2018, 1:17 AM
eadler added a member for transport: eadler.
May 15 2018, 1:17 AM
mmacy added a watcher for transport: mmacy.
May 15 2018, 1:06 AM

May 7 2018

kmacy abandoned D4366: convert tcp timestamps to scaled sbintime.
May 7 2018, 8:00 AM · transport

May 4 2018

Herald added 1 blocking reviewer(s) for D4294: modernize TCP constants: transport.

@lstewart ping

May 4 2018, 6:07 PM · transport

May 3 2018

kmacy abandoned D4292: decouple maximum clock frequency from callout scheduling granularity.
May 3 2018, 6:12 PM · transport
kmacy abandoned D4293: update SRTT to account for flight size.

We needed to refine this further at ISLN.

May 3 2018, 3:56 AM · transport
Herald added a reviewer for D4366: convert tcp timestamps to scaled sbintime: transport.

@lstewart is this worth updating or should I just abandon?

May 3 2018, 3:55 AM · transport

Mar 9 2018

sbruno closed D14540: Several LRO fixes.
Mar 9 2018, 12:08 AM · transport

Mar 8 2018

gallatin accepted D14540: Several LRO fixes.
Mar 8 2018, 7:11 PM · transport
sbruno accepted D14540: Several LRO fixes.

I'll grab this and shovel it in after builds are done.

Mar 8 2018, 6:25 PM · transport
jason_eggnet.com added inline comments to D14540: Several LRO fixes.
Mar 8 2018, 5:36 PM · transport
rstone added inline comments to D14540: Several LRO fixes.
Mar 8 2018, 4:28 PM · transport
rstone accepted D14540: Several LRO fixes.
Mar 8 2018, 2:34 PM · transport
kbowling updated the diff for D14540: Several LRO fixes.

Fix comment per rstone and jegg

Mar 8 2018, 7:56 AM · transport

Mar 7 2018

jason_eggnet.com added inline comments to D14540: Several LRO fixes.
Mar 7 2018, 11:13 PM · transport
rstone accepted D14540: Several LRO fixes.

I've written some unit tests that covering these cases here:

Mar 7 2018, 10:32 PM · transport
kbowling created D14540: Several LRO fixes.
Mar 7 2018, 4:42 PM · transport

Dec 17 2017

tuexen added a member for transport: tuexen.
Dec 17 2017, 7:24 PM

Aug 29 2017

kmacy abandoned D4490: inpcb rtentry/l2 prepend caching.
Aug 29 2017, 12:25 AM · transport

Aug 25 2017

sbruno closed D12003: Use counter(9) for PLPMTUD counters by committing rS322900: Use counter(9) for PLPMTUD counters..
Aug 25 2017, 7:42 PM · transport