On 2007-Mar-03 16:12:32 +0100, Andre Oppermann <andre_at_freebsd.org> wrote: >Peter Jeremy wrote: >>On 2007-Jan-26 11:59:06 -0500, Andrew Gallatin <gallatin_at_cs.duke.edu> >>wrote: >> >>>When running some benchmarks, I noticed tons of duplicate acks showing >>>up in systat -tcp (thousands, or tens of thousands per second). >> >>Whilst investigating other problems, I've just seen the same on 6.2. ... >This thing is really strange and difficult to debug. At least for me, it's not readily reproducable. I've written a perl script to try and locate the problem in tcpdumps I've taken for other reasons and haven't seen any recurrences of it. >I haven't experienced this bug myself which makes it even harder to debug. It's not something you'd probably notice unless you were specifically looking. In my case, I only noticed because I am trying to track an ipfilter bug and that connection setup had been flagged so I was studying the tcpdump output. Any ideas on where to add some checks to try and detect this without needing to pour over tcpdump traces? -- Peter Jeremy
This archive was generated by hypermail 2.4.0 : Wed May 19 2021 - 11:39:06 UTC