Linux RAID subsystem development
 help / color / mirror / Atom feed
From: Wol's lists <antlists@youngman.org.uk>
To: Marc MERLIN <marc@merlins.org>, Phil Turmel <philip@turmel.org>,
	Kay Diederichs <kay.diederichs@uni-konstanz.de>
Cc: Andreas Klauer <Andreas.Klauer@metamorpher.de>,
	Adam Goryachev <mailinglists@websitemanagers.com.au>,
	Roger Heflin <rogerheflin@gmail.com>,
	linux-raid@vger.kernel.org
Subject: Re: force remapping a pending sector in sw raid5 array
Date: Fri, 9 Feb 2018 22:07:57 +0000	[thread overview]
Message-ID: <3345d6f0-80d0-bfaf-9974-a7472d499117@youngman.org.uk> (raw)
In-Reply-To: <20180209212252.GN9565@merlins.org>

On 09/02/18 21:22, Marc MERLIN wrote:
> Interesting. I figured once a sector went pending once, it would not actually be re-used and
> be remapped on the next write. Seems like it didn't happen here.

Because there's all sorts of reasons a sector can go pending.

My favourite example is to compare it to DRAM. DRAM needs refreshing 
every couple of seconds, otherwise it loses its contents and cannot be 
read, but it's perfectly okay to rewrite and re-use it.

Likewise, the magnetism in a drive can decay such that the data is 
unreadable, but there's nothing actually wrong with the drive. (If the 
data next door is repeatedly rewritten, the rewrite can "leak" and trash 
nearby data ...) The decay time for that should be years.

The problem of course is when the problem has a decay time measured in 
minutes or hours. The rewrite succeeds, so the sector doesn't get 
remapped, but when you next read it it has died :-(

Cheers,
Wol

  reply	other threads:[~2018-02-09 22:07 UTC|newest]

Thread overview: 32+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-02-06 18:14 force remapping a pending sector in sw raid5 array Marc MERLIN
2018-02-06 18:59 ` Reindl Harald
2018-02-06 19:36   ` Marc MERLIN
2018-02-06 20:03 ` Andreas Klauer
2018-02-06 21:51 ` Adam Goryachev
2018-02-06 22:02   ` Marc MERLIN
2018-02-06 22:31     ` Roger Heflin
2018-02-06 22:46       ` Marc MERLIN
2018-02-07  4:29   ` Marc MERLIN
2018-02-07  9:42 ` Kay Diederichs
2018-02-09 19:29   ` Marc MERLIN
2018-02-09 19:57     ` Kay Diederichs
2018-02-09 20:02     ` Roger Heflin
2018-02-09 20:13     ` Phil Turmel
2018-02-09 20:29       ` Marc MERLIN
2018-02-09 20:44         ` Phil Turmel
2018-02-09 21:22           ` Marc MERLIN
2018-02-09 22:07             ` Wol's lists [this message]
2018-02-09 22:36               ` Marc MERLIN
2018-02-09 20:52         ` Kay Diederichs
2018-02-11 20:52           ` Roger Heflin
2018-02-09 21:17         ` Kay Diederichs
2018-02-10 21:43       ` Mateusz Korniak
2018-02-11 15:41         ` Marc MERLIN
2018-02-11 16:41           ` Marc MERLIN
2018-02-11 17:13         ` Phil Turmel
2018-02-11 18:02           ` Wols Lists
2018-02-12 10:43           ` Mateusz Korniak
2018-02-12 15:29             ` Phil Turmel
2018-02-12 16:49               ` Marc MERLIN
2018-02-12 17:16                 ` Phil Turmel
2018-02-12 17:30                   ` Marc MERLIN

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=3345d6f0-80d0-bfaf-9974-a7472d499117@youngman.org.uk \
    --to=antlists@youngman.org.uk \
    --cc=Andreas.Klauer@metamorpher.de \
    --cc=kay.diederichs@uni-konstanz.de \
    --cc=linux-raid@vger.kernel.org \
    --cc=mailinglists@websitemanagers.com.au \
    --cc=marc@merlins.org \
    --cc=philip@turmel.org \
    --cc=rogerheflin@gmail.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