Date: Thu, 24 Nov 2011 18:02:59 GMT From: Martin Simmons <martin@lispworks.com> To: lev@freebsd.org Cc: freebsd-fs@freebsd.org Subject: Re: Does UFS2 send BIO_FLUSH to GEOM when update metadata (with softupdates)? Message-ID: <201111241802.pAOI2x3J020454@higson.cam.lispworks.com> In-Reply-To: <858572754.20111124023739@serebryakov.spb.ru> (message from Lev Serebryakov on Thu, 24 Nov 2011 02:37:39 %2B0400) References: <1957615267.20111123230026@serebryakov.spb.ru> <20111123194444.GE50300@deviant.kiev.zoral.com.ua> <858572754.20111124023739@serebryakov.spb.ru>
next in thread | previous in thread | raw e-mail | index | archive | help
>>>>> On Thu, 24 Nov 2011 02:37:39 +0400, Lev Serebryakov said: > > And it seems, that fflsuh() is never becomes BIO_FLUSH or BIO_WRITE > with BIO_ORDERED flag. It looks like disaster. > > It means, that fflush() can not guarantee its contract at all! Stdio's fflush doesn't have that contract -- it just flushes the user space buffers, not the kernel buffers. __Martin
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?201111241802.pAOI2x3J020454>