Date: Wed, 28 Jan 2015 19:46:04 +0200 From: Konstantin Belousov <kostikbel@gmail.com> To: Don Lewis <truckman@FreeBSD.org> Cc: svn-src-head@FreeBSD.org, svn-src-all@FreeBSD.org, src-committers@FreeBSD.org Subject: Re: svn commit: r277828 - in head/sys: fs/tmpfs vm Message-ID: <20150128174604.GN42409@kib.kiev.ua> In-Reply-To: <201501281741.t0SHf6gW001232@gw.catspoiler.org> References: <201501281037.t0SAbNR3053095@svn.freebsd.org> <201501281741.t0SHf6gW001232@gw.catspoiler.org>
next in thread | previous in thread | raw e-mail | index | archive | help
On Wed, Jan 28, 2015 at 09:41:06AM -0800, Don Lewis wrote: > On 28 Jan, Konstantin Belousov wrote: > > Author: kib > > Date: Wed Jan 28 10:37:23 2015 > > New Revision: 277828 > > URL: https://svnweb.freebsd.org/changeset/base/277828 > > > > Log: > > Update mtime for tmpfs files modified through memory mapping. Similar > > to UFS, perform updates during syncer scans, which in particular means > > that tmpfs now performs scan on sync. Also, this means that a mtime > > update may be delayed up to 30 seconds after the write. > > Maybe disable the scan if mounted noatime? It is for mtime, not atime, updates. In fact, I thought about per-mount option to enable/disable mtime updates, but then decided that it is too exotic. I will add if if real performance complain appear, this also explains relatively long MFC timeout.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20150128174604.GN42409>