Date: Mon, 9 Mar 1998 23:01:16 +0000 (GMT) From: Terry Lambert <tlambert@primenet.com> To: shimon@simon-shapiro.org Cc: lada@ws2301.gud.siemens.at, dmlb@ragnet.demon.co.uk, wilko@yedi.iaf.nl, julian@whistle.com, hackers@FreeBSD.ORG, lada@ws2301.gud.siemens.co.at Subject: Re: SCSI Bus redundancy... Message-ID: <199803092301.QAA04865@usr08.primenet.com> In-Reply-To: <XFMail.980309094907.shimon@simon-shapiro.org> from "Simon Shapiro" at Mar 9, 98 09:49:07 am
next in thread | previous in thread | raw e-mail | index | archive | help
> > OLTP does not exists in Austria (i.e. not over Internet). The secure
*******
> OLTP, at least what I mean by OLTP, is a concept/transaction type; On-Line
> Transaction Processing. As Such it exists in Australia. Has nothing to do
*********
8-).
I think he was thinking of OLTP in terms of E-Commerce services not
existing in his country.
> What I am trying to acomplish in this conversation, is that the range of
> services and their sensitivity to interruption is wide. FreeBSD is
> migrating from a hacker's desktop to a high caliber server. Some services
> and features need to acompany this migration, or it will fail.
> All O/Ss going into the service market are going through this perocess. M$
> Nice Try is already going there.
This is a salient point. The ISP's who are interested in the HA
aspects of such servers are more interested because of interruption
of service issues, more than they are concerned with data-vaulting.
I'm personally more concerned with being able to lock down the gears
into a known-to-the-OS state, at all times. I can deal with rolling
incomplete transactions back seperately, if I need transactions.
The disk write cache is problematic. Most modern disks, when they lose
DC, do *not* flush the dirty portion of their write cache. Because the
cache is permitted to reorder operations without regard to their OS
dependency order, this means that a write cache that's not written
completely potentially damages dependency ordered data that the OS
believes has been written.
Dependency ordered data like that created by DOW or Soft Updates
technologies.
With disk write caching turned on, I still need a UPS to be able to
do this reliably, since I have to (1) not add more work to the write
cache which might potentially push out already delayed writes, and
(2) cause the disk to flush it's write cache.
High availability can also mean "comes back up quickly, and is robust
in the face of deleterious conditions".
Terry Lambert
terry@lambert.org
---
Any opinions in this posting are my own and not those of my present
or previous employers.
To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-hackers" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199803092301.QAA04865>