From mboxrd@z Thu Jan 1 00:00:00 1970 From: Pekka Pietikainen Subject: Funny timestamps (Was: Re: rwlock recursion on CPU#0, netfilter related?) Date: Fri, 30 Sep 2005 09:49:19 +0300 Message-ID: <20050930064919.GA21573@ee.oulu.fi> References: <20050925105834.GA15243@ee.oulu.fi> <20050925134344.GJ731@sunbeam.de.gnumonks.org> <20050925201945.GA21176@ee.oulu.fi> <20050928145815.GA421@ee.oulu.fi> <20050929120538.GT4168@sunbeam.de.gnumonks.org> Mime-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Return-path: To: netdev@oss.sgi.com Content-Disposition: inline In-Reply-To: <20050929120538.GT4168@sunbeam.de.gnumonks.org> Sender: netdev-bounce@oss.sgi.com Errors-to: netdev-bounce@oss.sgi.com List-Id: netdev.vger.kernel.org On Thu, Sep 29, 2005 at 02:05:38PM +0200, Harald Welte wrote: > > This one is still around, so it's a different bug. Looks like it's a 64-bit > > issue, a 32-bit ping gives realistic ping times. tcpdump timestamps are also > > affected, they're completely off too. So looks like someone broke packet > > timestamps on 64-bit some time after 2.6.13. > > luckily I'm not the core network maintainer ;) Here's the actual bug report: https://bugzilla.redhat.com/bugzilla/show_bug.cgi?id=168166 Ended up being a userspace thing, maybe. But still makes me wonder what change actually broke things. It must have been something soon after 2.6.13. And there's still tcpdump, which doesn't seem to go into the problem mode when I test it now, except that nothing should have changed in the kernel/tcpdump/libpcap versions. Blah.