Date: Sat, 20 Apr 2013 07:52:29 -0700 From: Adrian Chadd <adrian@freebsd.org> To: "O. Hartmann" <ohartman@zedat.fu-berlin.de> Cc: FreeBSD Current <freebsd-current@freebsd.org> Subject: Re: CURRENT: extremely unresponsive disk I/O Message-ID: <CAJ-Vmo=FUJ7iXVZ9jgDVnAO2VSJyA6wg=voe=S-hX%2B9RDiOxDw@mail.gmail.com> In-Reply-To: <1366447937.1475.35.camel@thor.walstatt.dyndns.org> References: <1366447937.1475.35.camel@thor.walstatt.dyndns.org>
next in thread | previous in thread | raw e-mail | index | archive | help
Think you could trace down which kernel commit introduced the regression? It should be pretty easy if you know the window is only two weeks long. Thanks, Adrian On 20 April 2013 01:52, O. Hartmann <ohartman@zedat.fu-berlin.de> wrote: > Since a couple of weeks now, FreeBSD 10.0-CURRENT is really unresponsive > when managing high disk I/O. > > This is most noticeable when starting the buildworld process, hwen clang > 3.3 starts to build the llvm backend libraries and doing some sort of > portmaster/portupgrade in parallel: even a "make rmconfig config" takes > aprox. a minute to show up. > > Is there a known issue at this moment? I can not see such a behaviour on > FreeBSD 9.1-STABLE (similar hardware). > > Oliver
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?CAJ-Vmo=FUJ7iXVZ9jgDVnAO2VSJyA6wg=voe=S-hX%2B9RDiOxDw>