All of lore.kernel.org
 help / color / mirror / Atom feed
From: Brad Campbell <lists2009@fnarfbargle.com>
To: Wols Lists <antlists@youngman.org.uk>,
	Francisco Parada <advanceandconquer@gmail.com>
Cc: mdraid <linux-raid@vger.kernel.org>
Subject: Re: RAID6 - CPU At 100% Usage After Reassembly
Date: Tue, 11 Oct 2016 20:46:14 +0800	[thread overview]
Message-ID: <df339a8a-1f44-0d0f-41b3-a308a9c270ed@fnarfbargle.com> (raw)
In-Reply-To: <57FCAF93.9040305@youngman.org.uk>

On 11/10/16 17:23, Wols Lists wrote:

> It strikes me this would be a good addition too - I could probably
> manage something of the sort, but do you or anyone have the code to
> detect a green, and do that "disable parking and spindown"? It's a pain,
> but having a script that deals with all known and common issues with
> drives is probably a good thing.
>

The command to disable head parking is a vendor specific command, is 
non-volatile and requires a drive power cycle. So it's a one off set and 
forget when you get the drive.

Excerpt from hdparm man page :
        -J     Get/set the Western Digital (WD) Green Drive's "idle3" 
timeout value.  This timeout controls how often the drive parks its 
heads and enters a low power consumption state.  The factory default is 
eight (8) seconds, which is a very poor choice for use with Linux. 
Leaving it at the  default  will
               result in hundreds of thousands of head load/unload 
cycles in a very short period of time.  The drive mechanism is only 
rated for 300,000 to 1,000,000 cycles, so leaving it at the default 
could result in premature failure, not to mention the performance impact 
of the drive often having to wake-
               up before doing routine I/O.

I just set them to J 0. This applies to the WD Red drives also.

I forget how to tackle the spindown command. I think I used hdparm -S 
every boot, same as the setting scterc timeout.

None of the machines I use with RAID arrays are idle long enough to spin 
down the disks.



  reply	other threads:[~2016-10-11 12:46 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-09-04  4:04 RAID6 - CPU At 100% Usage After Reassembly Francisco Parada
2016-09-04 14:38 ` Michael J. Shaver
     [not found]   ` <CAOW94uv4zSGs+6be3zhcQaGZdiAgg-s4ZHZ=mszcURo6pqJyqA@mail.gmail.com>
2016-09-04 22:48     ` Francisco Parada
2016-09-13 15:22       ` Francisco Parada
2016-09-13 17:43         ` Shaohua Li
2016-09-13 18:15           ` Francisco Parada
     [not found]             ` <CAOW94utVBcLz191ifzKkjn+nsSthPWDAQF8R-PabcS2uPareag@mail.gmail.com>
2016-09-26 14:29               ` Francisco Parada
2016-09-30 13:06                 ` Francisco Parada
2016-10-05 11:12                   ` Francisco Parada
2016-10-06 23:55                     ` Shaohua Li
2016-10-07 11:23                       ` Francisco Parada
2016-10-10 19:52                         ` Anthony Youngman
2016-10-11  3:53                         ` Brad Campbell
2016-10-11  9:23                           ` Wols Lists
2016-10-11 12:46                             ` Brad Campbell [this message]
  -- strict thread matches above, loose matches on Subject: below --
2016-09-04  2:56 Francisco Parada

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=df339a8a-1f44-0d0f-41b3-a308a9c270ed@fnarfbargle.com \
    --to=lists2009@fnarfbargle.com \
    --cc=advanceandconquer@gmail.com \
    --cc=antlists@youngman.org.uk \
    --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 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.