From mboxrd@z Thu Jan 1 00:00:00 1970 Message-ID: <600308d6050909151067389b35@mail.gmail.com> Date: Sat, 10 Sep 2005 00:10:58 +0200 From: Francisco Ballesteros To: Fans of the OS Plan 9 from Bell Labs <9fans@cse.psu.edu> In-Reply-To: <20050909210534.GI4207@server4.lensbuddy.com> 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> Subject: [9fans] reliability and failing over. Topicbox-Message-UUID: 8636e016-ead0-11e9-9d60-3106f5b1d025 Funny. The 9p reliability project looks to me a lot like the redirfs that we played with before introducing the Plan B volumes into the kernel. It provided failover (on replicated FSs, by some other means) and could recover the fids just by keeping track of their paths. The user level process I'm with now is quite similar to that (appart from including the language to select particular volumes) it maintains a fid table knowning which server, and which path within the server are the ones for each fid. It's what the Plan B kernel ns does, but within a server. Probably, the increase in latency you are seeing is the one I'm going to see in volfs. The 2x penalty in performace is what one could expect, becaus= e you have twice the latency. However, the in-kernel implementation has no penalty at all, because the kernel can rewrite the mount tables. Maybe we should talk about this. Eric? Russ? What do you say? Is it worth to pay the extra latency just to avoid a change (serious, I admit) in the kernel? On 9/9/05, Uriel wrote: > On Fri, Sep 09, 2005 at 10:55:01PM +0200, Francisco Ballesteros wrote: > > What about sched=B4ing the next town hall meeting > > for the third friday of september? > > I'm willing to run it if there are no objections or anyone else > > prefers to do that. > > > > Preferences regarding time? Was the last one (8pm gmt?) > > convenient? > I had tentatively scheduled the next THM for Sep 10th, but I have been > too stressed to even send out an announcement. >=20 > After some research it seems that Saturdays are the best days for most > people(specially given the diversity of timezones involved), 20:00 GMT > seems like a time that works reasonably well for most people. >=20 > For consistency(and avoid having to come up with a new date/time), I > suggest having a THM the third Saturday of the month at 20:00 GMT >=20 > Any complains? if not, I will make it 'official' in the Wiki >=20 > For the Summary of the last THM see(thanks to Hyperion for writing it > up): >=20 > http://plan9.bell-labs.com/wiki/plan9/thm_2005-08-15_Summary/ >=20 > uriel >