Date: Tue, 18 Sep 2007 19:52:45 +0400 From: Roman Bogorodskiy <novel@FreeBSD.org> To: Jeff Roberson <jroberson@chesapeake.net> Cc: freebsd-current@freebsd.org Subject: Re: SCHED_ULE on desktop system Message-ID: <20070918155244.GA1336@underworld.novel.ru> In-Reply-To: <20070917141820.M558@10.0.0.1> References: <20070916061932.GA93480@underworld.novel.ru> <20070915234855.G531@10.0.0.1> <20070916071421.GA1320@underworld.novel.ru> <20070916003323.U4507@10.0.0.1> <20070917044351.GA17565@underworld.novel.ru> <20070917162400.GA42669@underworld.novel.ru> <20070917141820.M558@10.0.0.1>
next in thread | previous in thread | raw e-mail | index | archive | help
--+QahgC5+KEYLbs62 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable Jeff Roberson wrote: > On Mon, 17 Sep 2007, Roman Bogorodskiy wrote: >=20 >> Roman Bogorodskiy wrote: >>=20 >>> Jeff Roberson wrote: >>>=20 >>>> On Sun, 16 Sep 2007, Roman Bogorodskiy wrote: >>>>=20 >>>>> Jeff Roberson wrote: >>>>>=20 >>>>>> This is contrary to the experiences of many others. Can you send me= =20 >>>>>> your >>>>>> dmesg? There may be something about your particular hardware that is >>>>>> triggering a bug. ULE is definitely designed to be responsive on the >>>>>> desktop. >>>>>=20 >>>>> Thanks for the quick answer! >>>>>=20 >>>>> Here's my dmesg: http://people.freebsd.org/~novel/misc/dmesg.txt >>>>=20 >>>> Roman, >>>>=20 >>>> The enclosed patch helps things on my system, however, there are still= =20 >>>> some >>>> delays due to IO issues. Let me know if this helps. >>>=20 >>> This patch seems to make my system react faster. However I need some >>> time to test it more carefully. >>=20 >> It looks like it's not really so, it's still very slow under load. :( >=20 > Roman, >=20 > Can you please verify that you are not swapping. If you are, try the pat= ch=20 > that I sent. Otherwise, can you try getting KTR_SCHED output for me? Pu= t=20 > the following in your kernel config file: Swap is not used at all (and I don't use WITNESS, etc). I will run through the steps you wrote ASAP. > options KTR > options KTR_COMPILE=3DKTR_SCHED > options KTR_MASK=3DKTR_SCHED > options KTR_ENTRIES=3D65536 >=20 >=20 > Then run the load that exhibits the problem. compile, play a movie, etc.= =20 > wait for a particularly bad pause and then run the following: >=20 > sysctl debug.ktr.mask=3D0 && ktrdump -ct > out && sysctl=20 > debug.ktr.mask=3D536870 >=20 > It's best to have the command ready in a shell so you can run it in the= =20 > closest proximity to the incident. Then gzip the results and email them = to=20 > me. >=20 > On my system I'm not able to play a movie while running buildworld due to= =20 > long disk waits. However, if I use a dvd driver, mplayer and x windows= =20 > both get enough cpu time to play the movie skip free. So this is not a c= pu=20 > scheduler problem as such. IO scheduling does feel less responsive than= =20 > 6.x but I have not done a side by side comparison. >=20 > Jeff >=20 >>=20 >>>> Thanks, >>>> Jeff >>>>=20 >>>>>=20 >>>>> Roman Bogorodskiy >>>>>=20 >>>=20 >>>=20 >>> Roman Bogorodskiy >>=20 >>=20 >> Roman Bogorodskiy >>=20 > _______________________________________________ > freebsd-current@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-current > To unsubscribe, send any mail to "freebsd-current-unsubscribe@freebsd.org" Roman Bogorodskiy --+QahgC5+KEYLbs62 Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.7 (FreeBSD) iQCVAwUBRu/0TIB0WzgdqspGAQJzUAQAyiIIaBV5U1qqACdmSgUVmiT+7R0hxZs5 KaoORGrBtfI/YQc7drAkWf/B2cET36wlkjdZwQKA5abkMq/89dP9cOxnwJR+wAbc V9/jBamA6CF5IZV5/jWiGasGCbMsMyYmBsLX4Zd5SWykBEyaLGZOj4HSuzK/VARt hPic2AnI/T0= =+jVC -----END PGP SIGNATURE----- --+QahgC5+KEYLbs62--
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20070918155244.GA1336>