public inbox for linux-bcache@vger.kernel.org
 help / color / mirror / Atom feed
From: Brad Campbell <brad-+nnirC7rrGZibQn6LdNjmg@public.gmane.org>
To: James Harper <james.harper-NMzNsA1hOHcW+bLBXbPJGg@public.gmane.org>
Cc: "linux-bcache-u79uwXL29TY76Z2rM5mHXA@public.gmane.org"
	<linux-bcache-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>
Subject: Re: how much of ssd to use?
Date: Sat, 02 Mar 2013 15:02:48 +0800	[thread overview]
Message-ID: <5131A418.3080105@fnarfbargle.com> (raw)
In-Reply-To: <6035A0D088A63A46850C3988ED045A4B3876B655-mzsoxcrO4/2UD0RQwgcqbDSf8X3wrgjD@public.gmane.org>

On 02/03/13 14:19, James Harper wrote:
> I've read that SSD drives work best when you only use some percentage of them (75%, 50%, etc) because by leaving unused space it allows the SSD more headroom to shuffle data around internally to keep things optimal. Those articles are most likely written for a filesystem on an OS that might not know about TRIM/UNMAP etc.
>
> Has anyone done any testing on sustained random write throughput on a (say) 60GB flash drive with only 50% dedicated to bcache, or 75%, or 100%?
>

SSD's use spare space to shuffle things around so they can reclaim space 
freed in sizes less than a full erase block. Bcache explicitly uses big 
buckets in such a way as to remove the requirement for this. Nothing is 
freed in a way that would cause fragmentation of the sector space, so no 
re-organising is required on the part of the drive.

      parent reply	other threads:[~2013-03-02  7:02 UTC|newest]

Thread overview: 2+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-03-02  6:19 how much of ssd to use? James Harper
     [not found] ` <6035A0D088A63A46850C3988ED045A4B3876B655-mzsoxcrO4/2UD0RQwgcqbDSf8X3wrgjD@public.gmane.org>
2013-03-02  7:02   ` Brad Campbell [this message]

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=5131A418.3080105@fnarfbargle.com \
    --to=brad-+nnirc7rrgzibqn6ldnjmg@public.gmane.org \
    --cc=james.harper-NMzNsA1hOHcW+bLBXbPJGg@public.gmane.org \
    --cc=linux-bcache-u79uwXL29TY76Z2rM5mHXA@public.gmane.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