Date: Fri, 03 Apr 1998 20:06:44 +0200 From: Poul-Henning Kamp <phk@critter.freebsd.dk> To: =?koi8-r?B?4c7E0sXKIP7F0s7P1w==?= <ache@nagual.pp.ru> Cc: "Alok K. Dhir" <adhir@worldbank.org>, current@FreeBSD.ORG, adkin003@tc.umn.edu Subject: Re: More info RE: X slowdown in -current Message-ID: <2814.891626804@critter.freebsd.dk> In-Reply-To: Your message of "Fri, 03 Apr 1998 21:48:36 %2B0400." <19980403214836.43861@nagual.pp.ru>
next in thread | previous in thread | raw e-mail | index | archive | help
In message <19980403214836.43861@nagual.pp.ru>, =?koi8-r?B?4c7E0sXKIP7F0s7P1w== >> If you compare version 1.33 and 1.35 you will see that there is no >> change in spl() placement and protection. I simply fail to see >> what the heck you think you need to fuck with splhigh for... >> >> Try to diff 1.33 and 1.35 and see what I mean... > >With splhigh() any version cause great slowness. The knob is not various >calculation styles but splhigh() itself. I suppose that splihigh() was >there for a long time, it means that proposed patch is workaround only and >real bug is somewhere else. In any case it manifestates itself very >recently after your general time changes. Why you not simple run >X11/Netscape to see the bug in action? It is very visible. The splhigh is needed to prevent a race in the P_SELECT flag handling, so clearly the bug must be somewhere else. It will take me some hours before I can reinstall a system with a -current, all my machines are doing something at the moment. Does a ktrace reveal anything ? -- Poul-Henning Kamp FreeBSD coreteam member phk@FreeBSD.ORG "Real hackers run -current on their laptop." "Drink MONO-tonic, it goes down but it will NEVER come back up!" To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-current" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?2814.891626804>