Date: Mon, 18 Mar 2002 13:24:18 -0500 (EST) From: John Baldwin <jhb@FreeBSD.org> To: Brian Feldman <green@FreeBSD.org> Cc: cvs-all@FreeBSD.org, cvs-committers@FreeBSD.org Subject: RE: cvs commit: src/sys/vm vm_fault.c vm_glue.c vm_map.c vm_map. Message-ID: <XFMail.20020318132418.jhb@FreeBSD.org> In-Reply-To: <200203181508.g2IF8Am41245@freefall.freebsd.org>
next in thread | previous in thread | raw e-mail | index | archive | help
On 18-Mar-2002 Brian Feldman wrote: > green 2002/03/18 07:08:10 PST > > Modified files: > sys/vm vm_fault.c vm_glue.c vm_map.c vm_map.h > vm_pageout.c vm_zone.c > Log: > Back out the modification of vm_map locks from lockmgr to sx locks. The > best path forward now is likely to change the lockmgr locks to simple > sleep mutexes, then see if any extra contention it generates is greater > than removed overhead of managing local locking state information, > cost of extra calls into lockmgr, etc. You can't sleep while holding a mutex. The problem here is that sx locks and lockmgr locks intentionally do not have identical semantics. I would follow Matt's suggested plan of "dumbing down" the lockmgr locks to a common base with sx locks, then change to sx locks, then do the optimizations for upgrades using the upgrade/downgrade mechanism sx locks provide (which will require a slightly different algorithm). -- John Baldwin <jhb@FreeBSD.org> <>< http://www.FreeBSD.org/~jhb/ "Power Users Use the Power to Serve!" - http://www.FreeBSD.org/ To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe cvs-all" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?XFMail.20020318132418.jhb>