All of lore.kernel.org
 help / color / mirror / Atom feed
From: Phillip Susi <phill@thesusis.net>
To: Wols Lists <antlists@youngman.org.uk>
Cc: Roy Sigurd Karlsbakk <roy@karlsbakk.net>,
	Linux Raid <linux-raid@vger.kernel.org>
Subject: Re: raid10 redundancy
Date: Tue, 18 May 2021 12:05:26 -0400	[thread overview]
Message-ID: <874kf0yq31.fsf@vps.thesusis.net> (raw)
In-Reply-To: <60A2EC87.9080701@youngman.org.uk>


Wols Lists writes:

> When rebuilding a mirror (of any sort), one block written requires ONE
> block read. When rebuilding a parity array, one block written requires
> one STRIPE read.

Again, we're in agreement here.  What you keep ignoring is the fact that
both of these take the same amount of time, provided that you are IO bound.

> That's a hell of a lot more load on the machine. And when faced with a
> production machine that needs to work (as opposed to a hobbyist machine
> which can dedicate itself solely to a rebuild), you have the two
> conflicting requirements that you need to finish the rebuild as quickly
> as possible for data safety, but you also need the computer to do real
> work. Minimising disk i/o is *crucial*.

That is true, it does put less load on the machine giving it more time
to perform other tasks, but your original argument was that it is more
likely to fail during a rebuild.  I suppose if you take the two together
and assume the machine is busy servicing other tasks while doing the
rebuild, then both are probably going to slow down somewhat leading to
the rebuild taking a little longer, but I have a hard time believing
that it is going to be 2-3 times longer, or that it is really very
likely of having a second failure in that time.

  parent reply	other threads:[~2021-05-18 16:16 UTC|newest]

Thread overview: 50+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-05-06  5:09 raid10 redundancy d tbsky
2021-05-06  7:48 ` Xiao Ni
2021-05-06  9:57   ` d tbsky
2021-05-06 12:38     ` Reindl Harald
2021-05-07  1:28       ` d tbsky
2021-05-08 13:47         ` keld
2021-05-09  0:52           ` Phillip Susi
2021-05-12 17:22             ` David T-G
2021-05-12 17:26               ` Reindl Harald
2021-05-12 17:39                 ` David T-G
2021-05-13 15:38               ` Andy Smith
2021-05-13 15:46               ` Phillip Susi
2021-05-13 15:59                 ` Andy Smith
2021-05-14 14:28                   ` Phillip Susi
2021-05-14 14:37                     ` Andy Smith
2021-05-17  2:07                       ` Brad Campbell
2021-05-06 13:09     ` Phillip Susi
2021-05-07  1:47       ` d tbsky
     [not found]         ` <86A76859-3098-4AB8-9AE7-46FF54736B88@websitemanagers.com.au>
2021-05-07  3:05           ` d tbsky
2021-05-07  3:26         ` Reindl Harald
2021-05-07 14:53         ` Andy Smith
2021-05-08  1:54           ` d tbsky
2021-05-08  5:55             ` Andy Smith
2021-05-09  1:10         ` Phillip Susi
2021-05-07  1:26     ` d tbsky
2021-05-06 10:39 ` Peter Grandi
2021-05-07  1:37   ` d tbsky
     [not found] ` <AD8C004B-FE83-4ABD-B58A-1F7F8683CD1F@websitemanagers.com.au>
2021-05-07  1:12   ` d tbsky
2021-05-07  9:46     ` Wols Lists
2021-05-11  0:04       ` Phil Turmel
2021-05-12 17:27         ` David T-G
2021-05-12 18:20           ` Phil Turmel
2021-05-12 16:31 ` Roy Sigurd Karlsbakk
2021-05-13 15:38   ` Phillip Susi
2021-05-13 18:21     ` Phil Turmel
2021-05-14 14:30       ` Phillip Susi
2021-05-14 14:48         ` Roy Sigurd Karlsbakk
2021-05-17 20:50           ` Phillip Susi
2021-05-17 22:21             ` Wols Lists
2021-05-18  0:12               ` Phil Turmel
2021-05-18 16:05               ` Phillip Susi [this message]
2021-05-18 17:38                 ` Reindl Harald
2021-05-18 18:51                   ` Phillip Susi
2021-05-18 19:02                     ` Reindl Harald
2021-05-18 23:48                 ` antlists
2021-05-19  3:42                   ` Adam Goryachev
2021-05-19 13:02                     ` Phillip Susi
2021-05-19 21:19                       ` Reindl Harald
2021-05-20  1:32                       ` Adam Goryachev
     [not found]                         ` <CAAMCDeeOnraMDNCF6ZZqPAxUrih2gSse1wDYgOfd1LqY-Ffqxw@mail.gmail.com>
2021-05-20 15:08                           ` antlists

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=874kf0yq31.fsf@vps.thesusis.net \
    --to=phill@thesusis.net \
    --cc=antlists@youngman.org.uk \
    --cc=linux-raid@vger.kernel.org \
    --cc=roy@karlsbakk.net \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.