Date: Thu, 13 Jan 2022 12:15:30 -0800 From: Gleb Smirnoff <glebius@freebsd.org> To: Michael Tuexen <michael.tuexen@lurchi.franken.de> Cc: Jamie Landeg-Jones <jamie@catflap.org>, net@freebsd.org Subject: Re: compressed TIME-WAIT to be decomissioned Message-ID: <YeCIYl8Wm8jAM13h@FreeBSD.org> In-Reply-To: <2C135179-CFAF-491E-B699-7EEC980BCF1B@lurchi.franken.de> References: <Yd8im/VkTU1zdvOi@FreeBSD.org> <202201131825.20DIP6AT072280@donotpassgo.dyslexicfish.net> <YeBvst%2BYHe108KSw@FreeBSD.org> <YeBy1GKOfnH6ilck@FreeBSD.org> <2C135179-CFAF-491E-B699-7EEC980BCF1B@lurchi.franken.de>
next in thread | previous in thread | raw e-mail | index | archive | help
On Thu, Jan 13, 2022 at 09:11:09PM +0100, Michael Tuexen wrote: M> > On Thu, Jan 13, 2022 at 10:30:10AM -0800, Gleb Smirnoff wrote: M> > T> Sorry, the stats I was talking about are present in CURRENT only: M> > T> M> > T> netstat -sp tcp | grep TIME-WAIT M> > T> 3 times connection in TIME-WAIT responded with ACK M> > T> 0 times connection in TIME-WAIT was actively recycled M> > T> 0 times connection in TIME-WAIT responded with RST M> > T> M> > T> I will merge it to stable/13 today, so that those running 13 can check it out. M> > M> > Sorry, I actually can't merge it to stable, as it changes size of tcpstat M> > making kernel/netstat incompatible. So, if you are interested in this data M> > on stable, the patch needs to be applied manually: M> > M> > https://cgit.freebsd.org/src/commit?id=71d2d5adfe18e80e5f8afeb4f86ef69be1aaad81 M> Why did you not change M> M> + /* TCPS_TIME_WAIT usage stats */ M> + uint64_t tcps_tw_recycles; /* Times time-wait was recycled. */ M> + uint64_t tcps_tw_resets; /* Times time-wait sent a reset. */ M> + uint64_t tcps_tw_responds; /* Times time-wait sent a valid ack. */ M> + M> uint64_t _pad[6]; /* 3 UTO, 3 TBD */ M> M> to M> M> + /* TCPS_TIME_WAIT usage stats */ M> + uint64_t tcps_tw_recycles; /* Times time-wait was recycled. */ M> + uint64_t tcps_tw_resets; /* Times time-wait sent a reset. */ M> + uint64_t tcps_tw_responds; /* Times time-wait sent a valid ack. */ M> + M> - uint64_t _pad[6]; /* 3 UTO, 3 TBD */ M> + uint64_t _pad[3]; /* 3 UTO */ M> M> That way you could MFC it... Oh, you are right. That's why we have the pads :) Will MFC. -- Gleb Smirnoff
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?YeCIYl8Wm8jAM13h>