From: Pavel Machek <pavel@ucw.cz>
To: Jeff Garzik <jgarzik@pobox.com>
Cc: Hans Reiser <reiser@namesys.com>,
"Mudama, Eric" <eric_mudama@Maxtor.com>,
"'Norman Diamond'" <ndiamond@wta.att.ne.jp>,
"'Wes Janzen '" <superchkn@sbcglobal.net>,
"'Rogier Wolff '" <R.E.Wolff@BitWizard.nl>,
"'John Bradford '" <john@grabjohn.com>,
linux-kernel@vger.kernel.org, nikita@namesys.com,
"'Pavel Machek '" <pavel@ucw.cz>,
"'Justin Cormack '" <justin@street-vision.com>,
"'Vitaly Fertman '" <vitaly@namesys.com>,
"'Krzysztof Halasa '" <khc@pm.waw.pl>
Subject: Re: Blockbusting news, results get worse
Date: Tue, 28 Oct 2003 02:21:43 +0100 [thread overview]
Message-ID: <20031028012143.GA427@elf.ucw.cz> (raw)
In-Reply-To: <3F9D7666.6010504@pobox.com>
Hi!
> >>or put it under heavy write workload and remove
> >>power.
> >>
> >Can you tell us more about what really happens to disk drives when the
> >power is cut while a block is being written? We engage in a lot of
> >uninformed speculation, and it would be nice if someone who really knows
> >told us....
> >
> >Do drives have enough capacitance under normal conditions to finish
> >writing the block? Does ECC on the drive detect that the block was bad
> >and so we don't need to detect it in the FS?
>
>
> Does it really matter to speculate about this?
>
> If you don't FLUSH CACHE, you have no guarantees your data is on the
> platter.
Well, even without FLUSH CACHE, you can expect that sector being
writen during powerfail either contains old data *or* new data.
If sector can become unreadable after powerfail, I guess journaling
people would like to know, and if powerfail may mean adjacent (or even
unrelated?) sectors to be damaged, everyone needs to know...
Pavel
--
When do you have a heart between your knees?
[Johanka's followup: and *two* hearts?]
next prev parent reply other threads:[~2003-10-28 1:22 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2003-10-27 17:43 Blockbusting news, results get worse Mudama, Eric
2003-10-27 18:48 ` Hans Reiser
2003-10-27 19:47 ` Jeff Garzik
2003-10-27 20:03 ` John Bradford
2003-10-29 20:01 ` Pavel Machek
2003-10-30 8:30 ` John Bradford
2003-10-28 1:21 ` Pavel Machek [this message]
2003-10-28 12:54 ` Krzysztof Halasa
-- strict thread matches above, loose matches on Subject: below --
2003-10-29 20:11 Mudama, Eric
2003-10-27 18:06 Mudama, Eric
2003-10-27 19:18 ` Andre Hedrick
2003-10-27 13:07 Samium Gromoff
2003-10-26 22:12 Mudama, Eric
2003-10-26 18:33 Mudama, Eric
2003-10-26 22:03 ` Andre Hedrick
2003-10-27 9:34 ` Norman Diamond
2003-10-27 10:23 ` Jan-Benedict Glaw
2003-10-27 23:31 ` Jason Lunz
2003-10-28 20:56 ` Hans Reiser
2003-10-26 7:37 Norman Diamond
2003-10-26 10:39 ` John Bradford
2003-10-26 9:41 ` Pavel Machek
2003-10-26 11:38 ` Norman Diamond
2003-10-26 11:56 ` Pavel Machek
2003-10-26 12:06 ` Hans Reiser
2003-10-26 13:59 ` Krzysztof Halasa
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=20031028012143.GA427@elf.ucw.cz \
--to=pavel@ucw.cz \
--cc=R.E.Wolff@BitWizard.nl \
--cc=eric_mudama@Maxtor.com \
--cc=jgarzik@pobox.com \
--cc=john@grabjohn.com \
--cc=justin@street-vision.com \
--cc=khc@pm.waw.pl \
--cc=linux-kernel@vger.kernel.org \
--cc=ndiamond@wta.att.ne.jp \
--cc=nikita@namesys.com \
--cc=reiser@namesys.com \
--cc=superchkn@sbcglobal.net \
--cc=vitaly@namesys.com \
/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;
as well as URLs for NNTP newsgroup(s).