linux-raid.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Giovanni Tessore <giotex@texsoft.it>
To: Asdo <asdo@shiftmail.org>
Cc: linux-raid@vger.kernel.org
Subject: Re: Read errors on raid5 ignored, array still clean .. then disaster !!
Date: Sat, 30 Jan 2010 23:20:49 +0100	[thread overview]
Message-ID: <4B64B0C1.1040503@texsoft.it> (raw)
In-Reply-To: <4B64A779.6070809@shiftmail.org>


> RAID-5 unfortunately is inherently insecure, here is why:
> If one drive gets kicked, MD starts recovering to a spare.
> At that point any single read error during the regeneration (that's a 
> scrub) will fail the array.
> This is a problem that cannot be overcome in theory.
Yes, I was just getting the same conclusion :-(
Suppose you have 2Tb mainstream disks, with a read error ratio of 1 
sector each 1E+14 bits = 1.25E+13 bytes.
It means that you likely get an error every 6.25 times you read the 
whole disk!
So in case of failure of a disk, you have 1 possibility over 6 to fail 
the array during recostruction.
Simply unacceptable!

I looked at specs of some enterprise disks, and the read error ratio for 
them is 1 sector each 1E+15 or each 1E+16. Better but still risky.
Ok.. I'll definitely move to raid-6.

Also raid-1 with less than 3 disks becomes useless the same way :-(
Idem for raid-10 ...wow

Well, these two threads on read errors came out as kinda instructive ... 
doh!!

Regards

-- 
Cordiali saluti.
Yours faithfully.

Giovanni Tessore



  reply	other threads:[~2010-01-30 22:20 UTC|newest]

Thread overview: 29+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-01-26 22:28 Read errors on raid5 ignored, array still clean .. then disaster !! Giovanni Tessore
2010-01-27  7:41 ` Luca Berra
2010-01-27  9:01   ` Goswin von Brederlow
2010-01-29 10:48   ` Neil Brown
2010-01-29 11:58     ` Goswin von Brederlow
2010-01-29 19:14     ` Giovanni Tessore
2010-01-30  7:58       ` Luca Berra
2010-01-30 15:52         ` Giovanni Tessore
2010-01-30  7:54     ` Luca Berra
2010-01-30 10:55     ` Giovanni Tessore
2010-01-30 18:44     ` Giovanni Tessore
2010-01-30 21:41       ` Asdo
2010-01-30 22:20         ` Giovanni Tessore [this message]
2010-01-31  1:23           ` Roger Heflin
2010-01-31 10:45             ` Giovanni Tessore
2010-01-31 14:08               ` Roger Heflin
2010-01-31 14:31         ` Asdo
2010-02-01 10:56           ` Giovanni Tessore
2010-02-01 12:45             ` Asdo
2010-02-01 15:11               ` Giovanni Tessore
2010-02-01 13:27             ` Luca Berra
2010-02-01 15:51               ` Giovanni Tessore
2010-01-27  9:01 ` Asdo
2010-01-27 10:09   ` Giovanni Tessore
2010-01-27 10:50     ` Asdo
2010-01-27 15:06       ` Goswin von Brederlow
2010-01-27 16:15       ` Giovanni Tessore
2010-01-27 19:33     ` Richard Scobie
  -- strict thread matches above, loose matches on Subject: below --
2010-01-27  9:56 Giovanni Tessore

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=4B64B0C1.1040503@texsoft.it \
    --to=giotex@texsoft.it \
    --cc=asdo@shiftmail.org \
    --cc=linux-raid@vger.kernel.org \
    /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).