Date: Mon, 2 Nov 1998 19:37:25 +0000 (GMT) From: Terry Lambert <tlambert@primenet.com> To: peter.jeremy@auss2.alcatel.com.au (Peter Jeremy) Cc: hackers@FreeBSD.ORG Subject: Re: sync writes with softupdates enabled Message-ID: <199811021937.MAA02997@usr05.primenet.com> In-Reply-To: <98Nov2.163001est.40354@border.alcanet.com.au> from "Peter Jeremy" at Nov 2, 98 04:30:29 pm
next in thread | previous in thread | raw e-mail | index | archive | help
> >Now that this has been committed, can we have some feedback from people > >using mmap heavily on -current? > > There are no longer any sync writes as a result of using an MMAP'd > history file in inn. There is no obvious corruption of history file > or associated .pag file. > > Note that there is a similar bug in 2.2.x. The fix is similar, but > needs some thought since there appears to be a problem with the > parameters to vm_object_page_clean(). In particular, `syncio' is > defined as boolean_t, as passed as the `waitfor' argument to > VOP_FSYNC() - which is MNT_ASYNC or MNT_SYNC elsewhere. I haven't > had the time to work out the correct definitions. I have a problem with this. Has msync(2) been updated to "do the right thing" with regard to uncommitted data in an mmapped region? If so, how? I was pretty sure that it was impossible to identify the mapping object backing ranges -- or so the comments in the msync code imply. I don't think you can arbitrarily change these to async references; specifically, I think there is a problem with dirty page write through. Terry Lambert terry@lambert.org --- Any opinions in this posting are my own and not those of my present or previous employers. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199811021937.MAA02997>