Skip site navigation (1)Skip section navigation (2)
Date:      Sat, 26 Feb 2005 12:22:59 +0100
From:      Hexren <me@hexren.net>
To:        Odhiambo Washington <wash@wananchi.com>
Cc:        freebsd-pf@freebsd.org
Subject:   Re[2]: Please test: MPSAFE callouts
Message-ID:  <72456382.20050226122259@hexren.net>
In-Reply-To: <20050225164156.GC43437@ns2.wananchi.com>
References:  <200502211852.01792.max@love2party.net> <200502251734.08309.max@love2party.net> <20050225164156.GC43437@ns2.wananchi.com>

next in thread | previous in thread | raw e-mail | index | archive | help
OW> * Max Laier <max@love2party.net> [20050225 19:34]: wrote:
>> On Monday 21 February 2005 18:51, Max Laier wrote:
>> > All,
>> >
>> > Pyun reminded me that we are still useing Giant to protect our callouts. We
>> > don't have to since we protect our code in there with our own mutex and the
>> > netstack is Giant-free as well now (provided that mpsafenet is enabled).
>> >
>> > If you have testing capabilities, please take the attached diffs for a ride
>> > (on SMP hardware) with debug.mpsafenet=1 and MPSAFE NICs.  It'd be great if
>> > we could enable it for 5.4R, but we need proper testing to do so!
>> >
>> > NOTE: If you use user/group rules you still need to set debug.mpsafenet=0,
>> > but testing of this scenario is welcome as well.
>> >
>> > Thanks in advance for your feedback!
>> 
>> Has anyone even cared enough to compile this?  C'mon it's not that hard and we 
>> really need some feedback!


OW> I don't have an SMP hardware otherwise I could have tried ;)


---------------------------------------------

For showing that I actually read what is postet here ;)
Me too :(



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?72456382.20050226122259>