Re: [PATCH v5 2/2] tcp: Add snd_wnd to TCP_INFO

2019-09-16 Thread David Miller
From: Thomas Higdon Date: Fri, 13 Sep 2019 23:23:35 + > Neal Cardwell mentioned that snd_wnd would be useful for diagnosing TCP > performance problems -- >> (1) Usually when we're diagnosing TCP performance problems, we do so >> from the sender, since the sender makes most of the >> performan

Re: [PATCH v5 2/2] tcp: Add snd_wnd to TCP_INFO

2019-09-14 Thread Soheil Hassas Yeganeh
On Sat, Sep 14, 2019 at 11:45 AM Neal Cardwell wrote: > > On Fri, Sep 13, 2019 at 7:23 PM Thomas Higdon wrote: > > > > Neal Cardwell mentioned that snd_wnd would be useful for diagnosing TCP > > performance problems -- > > > (1) Usually when we're diagnosing TCP performance problems, we do so > >

Re: [PATCH v5 2/2] tcp: Add snd_wnd to TCP_INFO

2019-09-14 Thread Neal Cardwell
On Fri, Sep 13, 2019 at 7:23 PM Thomas Higdon wrote: > > Neal Cardwell mentioned that snd_wnd would be useful for diagnosing TCP > performance problems -- > > (1) Usually when we're diagnosing TCP performance problems, we do so > > from the sender, since the sender makes most of the > > performanc

Re: [PATCH v5 2/2] tcp: Add snd_wnd to TCP_INFO

2019-09-13 Thread Yuchung Cheng
On Fri, Sep 13, 2019 at 4:23 PM Thomas Higdon wrote: > > Neal Cardwell mentioned that snd_wnd would be useful for diagnosing TCP > performance problems -- > > (1) Usually when we're diagnosing TCP performance problems, we do so > > from the sender, since the sender makes most of the > > performanc

[PATCH v5 2/2] tcp: Add snd_wnd to TCP_INFO

2019-09-13 Thread Thomas Higdon
Neal Cardwell mentioned that snd_wnd would be useful for diagnosing TCP performance problems -- > (1) Usually when we're diagnosing TCP performance problems, we do so > from the sender, since the sender makes most of the > performance-critical decisions (cwnd, pacing, TSO size, TSQ, etc). > From th