From mboxrd@z Thu Jan 1 00:00:00 1970 Message-ID: <600308d605090916167e4ea487@mail.gmail.com> Date: Sat, 10 Sep 2005 01:16:40 +0200 From: Francisco Ballesteros To: Russ Cox , Fans of the OS Plan 9 from Bell Labs <9fans@cse.psu.edu> Subject: Re: [9fans] reliability and failing over. In-Reply-To: Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable Content-Disposition: inline References: <600308d605090913554224787d@mail.gmail.com> <20050909210534.GI4207@server4.lensbuddy.com> <600308d6050909151067389b35@mail.gmail.com> <599f06db050909155055507829@mail.gmail.com> <600308d605090916023b856b47@mail.gmail.com> Cc: Topicbox-Message-UUID: 86dbc036-ead0-11e9-9d60-3106f5b1d025 Yep. I stand corrected. thanks. But let's try first the simplest (unoptimized) version. If it works well for real usage, I prefer a simpler (slower maybe) version. On 9/10/05, Russ Cox wrote: > > Plan B usage shows that latency is the biggest problem. > > I admit that only in unions, but if you join N different file servers > > in a directory, and then you dup the latency, it may be a problem. > > A workaround is just not to join too many servers, but it's a workaroun= d, > > not a fix. >=20 > Of course, one could issue walks in parallel to all members > of a union and then you'd get rid of this particular problem. > And doing so would be easier in user space. >=20 > Russ >