All of lore.kernel.org
 help / color / mirror / Atom feed
From: Marc MERLIN <marc@merlins.org>
To: linux-btrfs@vger.kernel.org, Chris Mason <chris.mason@oracle.com>,
	mbroz@redhat.com, Calvin Walton <calvin.walton@kepstin.ca>,
	Martin Steigerwald <Martin@lichtvoll.de>
Cc: jeff@deserettechnology.com
Subject: Re: brtfs on top of dmcrypt with SSD -> Trim or no Trim
Date: Wed, 18 Jul 2012 11:13:16 -0700	[thread overview]
Message-ID: <20120718181316.GD16899@merlins.org> (raw)
In-Reply-To: <20120218160702.GB32373@merlins.org> <20120215165540.GC4763@merlins.org> <20120213001400.GD31989@merlins.org> <20120212223242.GA31989@merlins.org> <20120202032345.GB31903@merlins.org> <20120130003754.GD4380@merlins.org>


On Sat, Feb 18, 2012 at 08:07:02AM -0800, Marc MERLIN wrote:
> On Sat, Feb 18, 2012 at 01:39:24PM +0100, Martin Steigerwald wrote:
> > To Milan Broz: Well now I noticed that you linked to your own blog entry. 
> 
> He did not, I'm the one who did.
> I asked a bunch of questions since the online docs didn't address them for
> me. Some of you answered those for me, I asked access to the wiki and I
> updated the wiki to have the information you gave me.
> 
> While I have no inherent bias one way or another, obviously I did put some
> of your opinions on the wiki :)
> 
> > Please do not take my below statements personally - I might have written 
> > them a bit harshly. Actually I do not really know whether your statement 
> > that TRIM is overrated is correct, but before believing that TRIM does not 
> > give much advantage, I would like to see at least some evidence of any 
> > sort, cause for me my explaination below that it should make a difference 
> > at least seems logical to me.
> 
> That sounds like a reasonable request to me.
> 
> In the meantime I changed the page to 
> 'Does Btrfs support TRIM/discard?
> 
> "-o discard" is supported, but can have some negative consequences on
> performance on some SSDs or at least whether it adds worthwhile performance
> is up for debate depending on who you ask, and makes undeletion/recovery
> near impossible while being a security problem if you use dm-crypt
> underneath (see
> http://asalor.blogspot.com/2011/08/trim-dm-crypt-problems.html ), therefore
> it is not enabled by default. You are welcome to run your own benchmarks and
> post them here, with the caveat that they'll be very SSD firmware specific.'
> 
> I'll leave further edits to others ;)

TL;DR:
I'm going to change the FAQ to say people should use TRIM with dmcrypt
because not doing so definitely causes some lesser SSDs to suck, or 
possibly even fail and lose our data.


Longer version:
Ok, so several months later I can report back with useful info.

Not using TRIM on my Crucial RealSSD C300 256GB is most likely what caused
its garbage collection algorithm to fail (killing the drive and all its
data), and it was also causing BRTFS to hang badly when I was getting
within 10GB of the drive getting full.

I reported some problems I had with btrfs being very slow and hanging when I
only had 10GB free, and I'm now convinced that it was the SSD that was at
fault.

On the Crucial RealSSD C300 256GB, and from talking to their tech support
and other folks who happened to have gotten that 'drive' at work and also
got weird unexplained failures, I'm convinced that even its latest 007
firmware (the firmware it shipped with would just hang the system for a few
seconds every so often so I did upgrade to 007 early on), the drive does
very poorly without TRIM when it's getting close to full.
In my case, I hit a bug that is likely firmware and caused the drive to die
(not show up on the bus anymore). I went through special reset, power on but
don't talk to it procedures that eventually brought the drive back after 4
hours of trying, except the drive is now 'blank', all the partitions and
data are gone as far as the controller is concerned.
(yes, I had backups, thanks for asking :) ).

>From talking to their techs and other folks, it seems clear that TRIM is
greatly encouraged, and I'm pretty sure that had I used TRIM, I would not
have hit the problems that caused my drive to fail and suck so much when it
was getting full.

Now, I still think that the Crucial RealSSD C300 256GB has poor firmware
compared to some of its competition and there is no excuse for it just dying 
like that, but I'm going to change the FAQ to recommend that people do use
TRIM if they can, even if they use dm-crypt (assuming their kernel is at
least 3.2.0).

Any objections and/or comments?

Thanks,
Marc
-- 
"A mouse is a device used to point at the xterm you want to type in" - A.S.R.
Microsoft is to operating systems ....
                                      .... what McDonalds is to gourmet cooking
Home page: http://marc.merlins.org/  

  parent reply	other threads:[~2012-07-18 18:13 UTC|newest]

Thread overview: 68+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-01-30  0:37 brtfs on top of dmcrypt with SSD. No corruption iff write cache off? Marc MERLIN
2012-02-01 17:56 ` Chris Mason
2012-02-02  3:23   ` Marc MERLIN
2012-02-02 12:42     ` Chris Mason
     [not found]       ` <20120202152722.GI12429@merlins.org>
2012-02-12 22:32         ` Marc MERLIN
2012-02-12 23:47           ` Milan Broz
2012-02-13  0:14             ` Marc MERLIN
2012-02-15 15:42               ` Calvin Walton
2012-02-15 16:55                 ` Marc MERLIN
2012-02-15 16:59                   ` Hugo Mills
2012-02-22 10:28                     ` Justin Ossevoort
2012-02-22 11:07                       ` Hugo Mills
2012-02-16  6:33               ` Chris Samuel
2012-02-18 12:33               ` Martin Steigerwald
2012-02-18 12:39               ` Martin Steigerwald
2012-02-18 12:49                 ` Martin Steigerwald
2012-07-18 18:13               ` Marc MERLIN [this message]
2012-07-18 20:04                 ` brtfs on top of dmcrypt with SSD -> Trim or no Trim Fajar A. Nugraha
2012-07-18 20:37                   ` Marc MERLIN
2012-07-18 21:34                   ` Clemens Eisserer
2012-07-18 21:48                     ` Marc MERLIN
2012-07-18 21:49                 ` Martin Steigerwald
2012-07-18 22:04                   ` Marc MERLIN
2012-07-19 10:40                     ` Martin Steigerwald
2012-07-22 18:58                     ` brtfs on top of dmcrypt with SSD -> ssd or nossd + crypt performance? Marc MERLIN
2012-07-22 19:35                       ` Martin Steigerwald
2012-07-22 19:43                         ` Martin Steigerwald
2012-07-22 20:44                         ` Marc MERLIN
2012-07-22 22:41                           ` brtfs on top of dmcrypt with SSD -> file access 5x slower than spinning disk Marc MERLIN
2012-07-23  6:42                             ` How can btrfs take 23sec to stat 23K files from an SSD? Marc MERLIN
2012-07-24  7:56                               ` Martin Steigerwald
2012-07-27  4:40                                 ` Marc MERLIN
2012-07-27 11:08                               ` Chris Mason
2012-07-27 18:42                                 ` Marc MERLIN
2012-02-18 16:07             ` brtfs on top of dmcrypt with SSD. No corruption iff write cache off? Marc MERLIN
2012-02-19  0:53               ` Clemens Eisserer
2012-07-25 15:45 du -s src is a lot slower on SSD than spinning disk in the same laptop Marc MERLIN
     [not found] ` <alpine.LFD.2.00.1207252023080.4340@(none)>
2012-07-25 23:38   ` Marc MERLIN
2012-07-26  3:32   ` Ted Ts'o
2012-07-26  3:35     ` Marc MERLIN
2012-07-26  6:54     ` Marc MERLIN
2012-08-01  5:30       ` Marc MERLIN
2012-08-01  6:01         ` How can btrfs take 23sec to stat 23K files from an SSD? Marc MERLIN
2012-08-01  6:08           ` Fajar A. Nugraha
2012-08-01  6:21             ` Marc MERLIN
2012-08-01 21:57               ` Martin Steigerwald
2012-08-02  5:07                 ` Marc MERLIN
2012-08-02 11:18                   ` Martin Steigerwald
2012-08-02 17:39                     ` Marc MERLIN
2012-08-02 20:20                       ` Martin Steigerwald
2012-08-02 20:44                         ` Marc MERLIN
2012-08-02 21:21                           ` Martin Steigerwald
2012-08-02 21:49                             ` Marc MERLIN
2012-08-03 18:45                               ` Martin Steigerwald
2012-08-16  7:45                                 ` Marc MERLIN
2012-08-02 11:25                   ` Martin Steigerwald
2012-08-01  6:36           ` Chris Samuel
2012-08-01  6:40             ` Marc MERLIN
2012-08-01  8:18         ` du -s src is a lot slower on SSD than spinning disk in the same laptop Spelic
2012-08-16  7:50         ` Marc MERLIN
     [not found]           ` <502CC2A2.4010506@shiftmail.org>
2012-08-16 17:55             ` Marc MERLIN
2012-09-05 16:52               ` ext4 crash with 3.5.2 in ext4_ext_remove_space Marc MERLIN
2012-09-05 17:50                 ` Lukáš Czerner
2012-09-05 17:53                   ` Marc MERLIN
2012-09-06  4:24                   ` Marc MERLIN
2012-09-07 15:19                     ` Marc MERLIN
2012-09-07 15:39                       ` Lukáš Czerner
2012-09-07 15:51                         ` Marc MERLIN

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=20120718181316.GD16899@merlins.org \
    --to=marc@merlins.org \
    --cc=Martin@lichtvoll.de \
    --cc=calvin.walton@kepstin.ca \
    --cc=chris.mason@oracle.com \
    --cc=jeff@deserettechnology.com \
    --cc=linux-btrfs@vger.kernel.org \
    --cc=mbroz@redhat.com \
    /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.