linux-btrfs.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Adam Borowski <kilobyte@angband.pl>
To: kreijack@inwind.it
Cc: Graham Cobb <g.btrfs@cobb.uk.net>, linux-btrfs@vger.kernel.org
Subject: Re: [RFC][PATCH V3] btrfs: ssd_metadata: storing metadata on SSD
Date: Sun, 5 Apr 2020 23:58:03 +0200	[thread overview]
Message-ID: <20200405215803.GA21928@angband.pl> (raw)
In-Reply-To: <4f10882a-fa89-25e0-901c-aff8010d46cd@libero.it>

On Sun, Apr 05, 2020 at 08:47:15PM +0200, Goffredo Baroncelli wrote:
> Currently BTRFS allocates the chunk on the basis of the free space.
> 
> For my tests I have a smaller ssd (20GB) and a bigger hdd (230GB).
> This means that the latter has higher priority for the allocation,
> until the free space became equal.
> 
> The rationale behind my patch is the following:
> - is quite simple (even tough in 3 iteration I put two errors :-) )
> - BTRFS has already two kind of information to store: data and metadata.
>   The former is (a lot ) bigger, than the latter. Having two kind of storage,
>   one faster (and expensive) than the other, it is natural to put the metadata
>   in the faster one, and the data in the slower one.

But why do you assume that SSD means fast?  Even with traditional disks
only, you can have a SATA-connected array for data and NVMe for metadata,
legacy NVMe for data and NVMe Optane for metadata -- but the real fun starts
if you put metadata on Optane pmem.

There are many storage tiers, and your patch hard-codes the lowest one as
the only determinator.


Meow!
-- 
⢀⣴⠾⠻⢶⣦⠀
⣾⠁⢠⠒⠀⣿⡁ in the beginning was the boot and root floppies and they were good.
⢿⡄⠘⠷⠚⠋⠀                                       -- <willmore> on #linux-sunxi
⠈⠳⣄⠀⠀⠀⠀

  reply	other threads:[~2020-04-05 21:58 UTC|newest]

Thread overview: 28+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-04-05  8:26 [RFC][PATCH V3] btrfs: ssd_metadata: storing metadata on SSD Goffredo Baroncelli
2020-04-05  8:26 ` [PATCH] btrfs: add ssd_metadata mode Goffredo Baroncelli
2020-04-14  5:24   ` Paul Jones
2020-10-23  7:23   ` Wang Yugui
2020-10-23 10:11     ` Adam Borowski
2020-10-23 11:25       ` Qu Wenruo
2020-10-23 12:37         ` Wang Yugui
2020-10-23 12:45           ` Qu Wenruo
2020-10-23 13:10           ` Steven Davies
2020-10-23 13:49             ` Wang Yugui
2020-10-23 18:03           ` Goffredo Baroncelli
2020-10-24  3:26             ` Paul Jones
2020-04-05 10:57 ` [RFC][PATCH V3] btrfs: ssd_metadata: storing metadata on SSD Graham Cobb
2020-04-05 18:47   ` Goffredo Baroncelli
2020-04-05 21:58     ` Adam Borowski [this message]
2020-04-06  2:24   ` Zygo Blaxell
2020-04-06 16:43     ` Goffredo Baroncelli
2020-04-06 17:21       ` Zygo Blaxell
2020-04-06 17:33         ` Goffredo Baroncelli
2020-04-06 17:40           ` Zygo Blaxell
2020-05-29 16:06 ` Hans van Kranenburg
2020-05-29 16:40   ` Goffredo Baroncelli
2020-05-29 18:37     ` Hans van Kranenburg
2020-05-30  4:59 ` Qu Wenruo
2020-05-30  6:48   ` Goffredo Baroncelli
2020-05-30  8:57     ` Paul Jones
  -- strict thread matches above, loose matches on Subject: below --
2020-04-27 15:06 Torstein Eide
2020-04-28 19:31 ` Goffredo Baroncelli

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=20200405215803.GA21928@angband.pl \
    --to=kilobyte@angband.pl \
    --cc=g.btrfs@cobb.uk.net \
    --cc=kreijack@inwind.it \
    --cc=linux-btrfs@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).