From: "Eric Z. Ayers" <Eric.Ayers@intec-telecom-systems.com>
To: Pavel Machek <pavel@suse.cz>
Cc: Doug Ledford <dledford@redhat.com>,
Max TenEyck Woodbury <mtew@cds.duke.edu>,
Eric.Ayers@intec-telecom-systems.com,
James Bottomley <James.Bottomley@steeleye.com>,
"Roets, Chris" <Chris.Roets@compaq.com>,
linux-kernel@vger.kernel.org, linux-scsi@vger.kernel.org
Subject: Re: Linux Cluster using shared scsi
Date: Thu, 3 May 2001 15:57:41 -0400 (EDT) [thread overview]
Message-ID: <15089.47157.268005.262050@gargle.gargle.HOWL> (raw)
In-Reply-To: <20010502230357.A9507@bug.ucw.cz>
In-Reply-To: <200105011445.KAA01117@localhost.localdomain> <3AEEDFFC.409D8271@redhat.com> <15086.60620.745722.345084@gargle.gargle.HOWL> <3AF025AE.511064F3@redhat.com> <3AF04648.73F5BFCE@cds.duke.edu> <3AF0483C.49C8CF90@redhat.com> <20010502230357.A9507@bug.ucw.cz>
Pavel Machek writes:
> Hi!
>
> > > > ...
> > > >
> > > > If told to hold a reservation, then resend your reservation request once every
> > > > 2 seconds (this actually has very minimal CPU/BUS usage and isn't as big a
> > > > deal as requesting a reservation every 2 seconds might sound). The first time
> > > > the reservation is refused, consider the reservation stolen by another machine
> > > > and exit (or optionally, reboot).
> > >
> > > Umm. Reboot? What do you think this is? Windoze?
> >
> > It's the *only* way to guarantee that the drive is never touched by more than
> > one machine at a time (notice, I've not been talking about a shared use drive,
> > only one machine in the cluster "owns" the drive at a time, and it isn't for
> > single transactions that it owns the drive, it owns the drive for as long as
> > it is alive, this is a limitation of the filesystes currently available in
> > mainstream kernels). The reservation conflict and subsequent reboot also
> > *only* happens when a reservation has been forcefully stolen from a
> >machine.
>
> I do not believe reboot from kernel is right approach. Tell init with
> special signal, maybe; but do not reboot forcefully. This is policy;
> doing reboot might be right answer in 90% cases; that does not mean
> you should do it always.
...
However distateful it sounds, there is precedent for the
behavior that Doug is proposing in commercial clustering
implementations. My recollection is that both Compaq TruCluster and
HP Service Guard have logic that will panic the kernel when a disk is
"stolen" from under a running service and there is a "network
partition" in the cluster.
A network partition occurs when multiple machines in the cluster are
runnig, but the HA software agents on two nodes can't communicate via
the network to arbitrate which node should be the owner of the disk.
-Eric
--
Eric Z. Ayers Lead Software Engineer
Phone: +1 404-705-2864 Computer Generation, Incorporated
Fax: +1 404-705-2805 an Intec Telecom Systems Company
Web: http://www.intec-telecom-systems.com/
Email: eric.ayers@intec-telecom-systems.com
Postal: Bldg G 4th Floor, 5775 Peachtree-Dunwoody Rd, Atlanta, GA 30342 USA
next prev parent reply other threads:[~2001-05-03 19:58 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2001-05-01 13:07 Roets, Chris
2001-05-01 14:45 ` James Bottomley
2001-05-01 16:10 ` Doug Ledford
2001-05-01 17:05 ` Eric Z. Ayers
2001-05-01 20:38 ` Alan Cox
2001-05-01 20:52 ` James Bottomley
2001-05-01 21:07 ` Eric Z. Ayers
2001-05-01 21:24 ` Alan Cox
2001-05-02 15:20 ` Doug Ledford
2001-05-02 16:37 ` Eddie Williams
2001-05-02 17:20 ` Mike Anderson
2001-05-02 17:50 ` Doug Ledford
2001-05-02 18:55 ` Mike Anderson
2001-05-02 20:31 ` Doug Ledford
2001-05-03 12:53 ` James Bottomley
2001-05-03 13:52 ` James Bottomley
2001-05-02 17:39 ` Max TenEyck Woodbury
2001-05-02 17:47 ` Doug Ledford
2001-05-02 21:03 ` Pavel Machek
2001-05-03 22:32 ` Jonathan Lundell
2001-05-02 21:47 ` Max TenEyck Woodbury
2001-05-02 23:16 ` Doug Ledford
2001-05-03 19:57 ` Eric Z. Ayers [this message]
2001-05-04 14:52 ` Eddie Williams
-- strict thread matches above, loose matches on Subject: below --
2001-04-27 15:11 James Bottomley
2001-04-27 13:18 Roets, Chris
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=15089.47157.268005.262050@gargle.gargle.HOWL \
--to=eric.ayers@intec-telecom-systems.com \
--cc=Chris.Roets@compaq.com \
--cc=James.Bottomley@steeleye.com \
--cc=dledford@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-scsi@vger.kernel.org \
--cc=mtew@cds.duke.edu \
--cc=pavel@suse.cz \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®