All of lore.kernel.org
 help / color / mirror / Atom feed
From: Bill Davidsen <davidsen@tmr.com>
To: Dongjun Shin <djshin90@gmail.com>
Cc: "Evgeniy Polyakov" <johnpol@2ka.mipt.ru>,
	"Albert Cahalan" <acahalan@gmail.com>, "Greg KH" <greg@kroah.com>,
	"Jörn Engel" <joern@lazybastard.org>,
	linux-kernel@vger.kernel.org, "Ingo Oeser" <ioe-lkml@rameria.de>,
	"Pekka Enberg" <penberg@cs.helsinki.fi>,
	linux-mtd@lists.infradead.org,
	"Jan Engelhardt" <jengelh@linux01.gwdg.de>,
	linux-fsdevel@vger.kernel.org,
	"Andrew Morton" <akpm@linux-foundation.org>,
	"David Woodhouse" <dwmw2@infradead.org>,
	"Thomas Gleixner" <tglx@linutronix.de>
Subject: Re: [PATCH] LogFS take three
Date: Sat, 19 May 2007 11:18:17 -0400	[thread overview]
Message-ID: <464F1539.5050204@tmr.com> (raw)
In-Reply-To: <7fe698080705170120w18fe5521oa685cf248a45e1c6@mail.gmail.com>

Dongjun Shin wrote:

> There are so many flash-based storage and some disposable storages,
> as you pointed out, have poor quality. I think it's mainly because these
> are not designed for good quality, but for lowering the price.
> 
The reliability seems to be appropriate to the common use. I'm doubious 
that computer storage was a big design factor until the last few years. 
A good argument for buying large sizes, they are more likely to be 
recent design.

> These kind of devices are not ready for things like power failure because
> their use case is far from that. For example, removing flash card
> while taking pictures using digital camera is not a common use case.
> (there should be a written notice that this kind of action is against
> the warranty)
> 
They do well in such use, if you equate battery death to pulling the 
card (it may not be). I have tested that feature and not had a failure 
of any but the last item. Clearly not recommended, but sometimes 
unplanned needs arise.


> - In contrast to the embedded environment where CPU and flash is directly
> connected, the I/O path between CPU and flash in PC environment is longer.
> The latency for SW handshaking between CPU and flash will also be longer,
> which would make the performance optimization harder.
> 
> As I mentioned, some techniques like log-structured filesystem could
> perform generally better on any kind of flash-based storage with FTL.
> Although there are many kinds of FTL, it is commonly true that
> it performs well under workload where sequential write is dominant.
> 
> I also expect that FTL for PC environment will have better quality spec
> than the disposable storage.

The recent technology announcements from Intel are encouraging in that 
respect.

-- 
Bill Davidsen <davidsen@tmr.com>
   "We have more to fear from the bungling of the incompetent than from
the machinations of the wicked."  - from Slashdot

WARNING: multiple messages have this Message-ID (diff)
From: Bill Davidsen <davidsen@tmr.com>
To: Dongjun Shin <djshin90@gmail.com>
Cc: "David Woodhouse" <dwmw2@infradead.org>,
	"Jörn Engel" <joern@lazybastard.org>,
	"Andrew Morton" <akpm@linux-foundation.org>,
	linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org,
	linux-mtd@lists.infradead.org,
	"Albert Cahalan" <acahalan@gmail.com>,
	"Thomas Gleixner" <tglx@linutronix.de>,
	"Jan Engelhardt" <jengelh@linux01.gwdg.de>,
	"Evgeniy Polyakov" <johnpol@2ka.mipt.ru>,
	"Pekka Enberg" <penberg@cs.helsinki.fi>,
	"Greg KH" <greg@kroah.com>, "Ingo Oeser" <ioe-lkml@rameria.de>
Subject: Re: [PATCH] LogFS take three
Date: Sat, 19 May 2007 11:18:17 -0400	[thread overview]
Message-ID: <464F1539.5050204@tmr.com> (raw)
In-Reply-To: <7fe698080705170120w18fe5521oa685cf248a45e1c6@mail.gmail.com>

Dongjun Shin wrote:

> There are so many flash-based storage and some disposable storages,
> as you pointed out, have poor quality. I think it's mainly because these
> are not designed for good quality, but for lowering the price.
> 
The reliability seems to be appropriate to the common use. I'm doubious 
that computer storage was a big design factor until the last few years. 
A good argument for buying large sizes, they are more likely to be 
recent design.

> These kind of devices are not ready for things like power failure because
> their use case is far from that. For example, removing flash card
> while taking pictures using digital camera is not a common use case.
> (there should be a written notice that this kind of action is against
> the warranty)
> 
They do well in such use, if you equate battery death to pulling the 
card (it may not be). I have tested that feature and not had a failure 
of any but the last item. Clearly not recommended, but sometimes 
unplanned needs arise.


> - In contrast to the embedded environment where CPU and flash is directly
> connected, the I/O path between CPU and flash in PC environment is longer.
> The latency for SW handshaking between CPU and flash will also be longer,
> which would make the performance optimization harder.
> 
> As I mentioned, some techniques like log-structured filesystem could
> perform generally better on any kind of flash-based storage with FTL.
> Although there are many kinds of FTL, it is commonly true that
> it performs well under workload where sequential write is dominant.
> 
> I also expect that FTL for PC environment will have better quality spec
> than the disposable storage.

The recent technology announcements from Intel are encouraging in that 
respect.

-- 
Bill Davidsen <davidsen@tmr.com>
   "We have more to fear from the bungling of the incompetent than from
the machinations of the wicked."  - from Slashdot

  parent reply	other threads:[~2007-05-19 15:19 UTC|newest]

Thread overview: 227+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2007-05-15 15:19 [PATCH] LogFS take three Jörn Engel
2007-05-15 15:19 ` Jörn Engel
2007-05-15 15:21 ` Review status (Re: [PATCH] LogFS take three) Jörn Engel
2007-05-15 15:21   ` Jörn Engel
2007-05-15 15:21   ` Jörn Engel
2007-05-17 16:03   ` Evgeniy Polyakov
2007-05-17 16:03     ` Evgeniy Polyakov
2007-05-17 16:03     ` Evgeniy Polyakov
2007-05-17 17:10     ` Jörn Engel
2007-05-17 17:10       ` Jörn Engel
2007-05-17 17:10       ` Jörn Engel
2007-05-20 17:30       ` Evgeniy Polyakov
2007-05-20 17:30         ` Evgeniy Polyakov
2007-05-20 17:30         ` Evgeniy Polyakov
2007-05-23 12:58         ` Jörn Engel
2007-05-23 12:58           ` Jörn Engel
2007-05-23 12:58           ` Jörn Engel
2007-05-23 15:07           ` Evgeniy Polyakov
2007-05-23 15:07             ` Evgeniy Polyakov
2007-05-23 15:07             ` Evgeniy Polyakov
2007-05-23 15:14             ` Jörn Engel
2007-05-23 15:14               ` Jörn Engel
2007-05-23 15:14               ` Jörn Engel
2007-05-23 15:53               ` Evgeniy Polyakov
2007-05-23 15:53                 ` Evgeniy Polyakov
2007-05-23 15:53                 ` Evgeniy Polyakov
2007-05-15 18:37 ` [PATCH] LogFS take three Sam Ravnborg
2007-05-15 18:37   ` Sam Ravnborg
2007-05-15 18:37   ` Sam Ravnborg
2007-05-15 19:10   ` Jörn Engel
2007-05-15 19:10     ` Jörn Engel
2007-05-15 19:10     ` Jörn Engel
2007-05-15 19:07 ` John Stoffel
2007-05-15 19:07   ` John Stoffel
2007-05-15 19:19   ` Jörn Engel
2007-05-15 19:19     ` Jörn Engel
2007-05-15 19:19     ` Jörn Engel
2007-05-16  4:54     ` David Woodhouse
2007-05-16  4:54       ` David Woodhouse
2007-05-16  4:54       ` David Woodhouse
2007-05-16 11:09       ` Jörn Engel
2007-05-16 11:09         ` Jörn Engel
2007-05-16 11:09         ` Jörn Engel
2007-05-16 11:34         ` Jamie Lokier
2007-05-16 11:34           ` Jamie Lokier
2007-05-16 11:34           ` Jamie Lokier
2007-05-16 11:38           ` Artem Bityutskiy
2007-05-16 11:38             ` Artem Bityutskiy
2007-05-16 11:38             ` Artem Bityutskiy
2007-05-16 12:25             ` Jamie Lokier
2007-05-16 12:25               ` Jamie Lokier
2007-05-16 12:25               ` Jamie Lokier
2007-05-16 12:49               ` Jörn Engel
2007-05-16 12:49                 ` Jörn Engel
2007-05-16 12:49                 ` Jörn Engel
2007-05-16 11:50           ` Jörn Engel
2007-05-16 11:50             ` Jörn Engel
2007-05-16 11:50             ` Jörn Engel
2007-05-16 12:06             ` CaT
2007-05-16 12:06               ` CaT
2007-05-16 12:06               ` CaT
2007-05-17 17:07               ` Jan Engelhardt
2007-05-17 17:07                 ` Jan Engelhardt
2007-05-16 12:29             ` Evgeniy Polyakov
2007-05-16 12:29               ` Evgeniy Polyakov
2007-05-16 12:29               ` Evgeniy Polyakov
2007-05-16 12:55               ` Jörn Engel
2007-05-16 12:55                 ` Jörn Engel
2007-05-16 12:55                 ` Jörn Engel
2007-05-17 17:08                 ` Jan Engelhardt
2007-05-17 17:08                   ` Jan Engelhardt
2007-05-17 17:08                   ` Jan Engelhardt
2007-05-16 13:41             ` John Stoffel
2007-05-16 13:41               ` John Stoffel
2007-05-16 13:53               ` Jörn Engel
2007-05-16 13:53                 ` Jörn Engel
2007-05-16 13:53                 ` Jörn Engel
2007-05-16 14:04                 ` David Woodhouse
2007-05-16 14:04                   ` David Woodhouse
2007-05-16 14:04                   ` David Woodhouse
2007-05-16 14:13                   ` Artem Bityutskiy
2007-05-16 14:13                     ` Artem Bityutskiy
2007-05-16 14:13                     ` Artem Bityutskiy
2007-05-16 14:17                   ` Kevin Bowling
2007-05-16 14:17                     ` Kevin Bowling
2007-05-17  9:12                     ` Pavel Machek
2007-05-17  9:12                       ` Pavel Machek
2007-05-17  9:12                       ` Pavel Machek
2007-05-17  9:52                       ` David Woodhouse
2007-05-17  9:52                         ` David Woodhouse
2007-05-17  9:52                         ` David Woodhouse
2007-05-19 15:00                     ` Bill Davidsen
2007-05-19 15:00                       ` Bill Davidsen
2007-05-16 14:29                 ` CaT
2007-05-16 14:29                   ` CaT
2007-05-17 17:14                 ` Jan Engelhardt
2007-05-17 17:14                   ` Jan Engelhardt
2007-05-17 17:14                   ` Jan Engelhardt
2007-05-19 14:45                 ` David Weinehall
2007-05-19 14:45                   ` David Weinehall
2007-05-19 14:45                   ` David Weinehall
2007-05-19 16:17                   ` Jamie Lokier
2007-05-19 16:17                     ` Jamie Lokier
2007-05-19 16:27                     ` Evgeniy Polyakov
2007-05-19 16:27                       ` Evgeniy Polyakov
2007-05-19 16:27                       ` Evgeniy Polyakov
2007-05-17 16:59         ` Jan Engelhardt
2007-05-17 16:59           ` Jan Engelhardt
2007-05-17 16:59           ` Jan Engelhardt
2007-05-17 11:39     ` Arnd Bergmann
2007-05-17 11:39       ` Arnd Bergmann
2007-05-17 11:39       ` Arnd Bergmann
2007-05-15 20:37 ` Andrew Morton
2007-05-15 20:37   ` Andrew Morton
2007-05-16  0:06   ` Jörn Engel
2007-05-16  0:06     ` Jörn Engel
2007-05-16  0:06     ` Jörn Engel
2007-05-16  2:11     ` Jörn Engel
2007-05-16  2:11       ` Jörn Engel
2007-05-16  5:22     ` Willy Tarreau
2007-05-16  5:22       ` Willy Tarreau
2007-05-16 11:23       ` Jörn Engel
2007-05-16 11:23         ` Jörn Engel
2007-05-16 11:23         ` Jörn Engel
2007-05-17 17:26     ` Jan Engelhardt
2007-05-17 17:26       ` Jan Engelhardt
2007-05-17 17:26       ` Jan Engelhardt
2007-05-17 17:45       ` Evgeniy Polyakov
2007-05-17 17:45         ` Evgeniy Polyakov
2007-05-18  1:00         ` Kyle Moffett
2007-05-18  1:00           ` Kyle Moffett
2007-05-18  6:16           ` Jan Engelhardt
2007-05-18  6:16             ` Jan Engelhardt
2007-05-16 12:07   ` David Woodhouse
2007-05-16 12:07     ` David Woodhouse
2007-05-16 12:07     ` David Woodhouse
2007-05-16 15:34     ` Andrew Morton
2007-05-16 15:34       ` Andrew Morton
2007-05-16 15:49       ` David Woodhouse
2007-05-16 15:49         ` David Woodhouse
2007-05-16 16:41         ` Jörn Engel
2007-05-16 16:41           ` Jörn Engel
2007-05-16 16:41           ` Jörn Engel
     [not found]           ` <7fe698080705162312t4e7ed90byd10ef8e664027b17@mail.gmail.com>
2007-05-17  6:25             ` David Woodhouse
2007-05-17  6:25               ` David Woodhouse
2007-05-17  8:20               ` Dongjun Shin
2007-05-17  8:20                 ` Dongjun Shin
2007-05-17  8:43                 ` David Woodhouse
2007-05-17  8:43                   ` David Woodhouse
2007-05-17  8:43                   ` David Woodhouse
2007-05-17 12:05                   ` Jörn Engel
2007-05-17 12:05                     ` Jörn Engel
2007-05-17 12:05                     ` Jörn Engel
2007-05-17 20:18                 ` Pavel Machek
2007-05-17 20:18                   ` Pavel Machek
2007-05-18  0:01                   ` Dongjun Shin
2007-05-18  0:01                     ` Dongjun Shin
2007-05-18  6:17                     ` Jan Engelhardt
2007-05-18  6:17                       ` Jan Engelhardt
2007-05-18  6:47                       ` David Woodhouse
2007-05-18  6:47                         ` David Woodhouse
2007-05-19 15:18                 ` Bill Davidsen [this message]
2007-05-19 15:18                   ` Bill Davidsen
2007-05-19  6:15   ` Rob Landley
2007-05-19  6:15     ` Rob Landley
2007-05-19  9:24     ` Jan Engelhardt
2007-05-19  9:24       ` Jan Engelhardt
2007-05-19 17:26       ` Rob Landley
2007-05-19 17:26         ` Rob Landley
2007-05-15 23:26 ` Albert Cahalan
2007-05-15 23:26   ` Albert Cahalan
2007-05-16  0:09   ` Jörn Engel
2007-05-16  0:09     ` Jörn Engel
2007-05-16  0:09     ` Jörn Engel
2007-05-16 11:18   ` Jamie Lokier
2007-05-16 11:18     ` Jamie Lokier
2007-05-16 11:18     ` Jamie Lokier
2007-05-16 12:08     ` Pekka Enberg
2007-05-16 12:08       ` Pekka Enberg
2007-05-16 12:58       ` Jörn Engel
2007-05-16 12:58         ` Jörn Engel
2007-05-16 12:58         ` Jörn Engel
2007-05-16  2:37 ` Roland Dreier
2007-05-16  2:37   ` Roland Dreier
2007-05-16 11:35   ` Jörn Engel
2007-05-16 11:35     ` Jörn Engel
2007-05-16 11:35     ` Jörn Engel
2007-05-16 10:21 ` Pekka J Enberg
2007-05-16 10:21   ` Pekka J Enberg
2007-05-16 12:26   ` Jörn Engel
2007-05-16 12:26     ` Jörn Engel
2007-05-16 12:36     ` Pekka Enberg
2007-05-16 12:36       ` Pekka Enberg
2007-05-16 12:36       ` Pekka Enberg
2007-05-16 12:38       ` Pekka Enberg
2007-05-16 12:38         ` Pekka Enberg
2007-05-16 13:20       ` Jörn Engel
2007-05-16 13:20         ` Jörn Engel
2007-05-16 13:20         ` Jörn Engel
2007-05-17 20:58         ` Pekka Enberg
2007-05-17 20:58           ` Pekka Enberg
2007-05-17 20:58           ` Pekka Enberg
2007-05-17 21:36           ` Arnd Bergmann
2007-05-17 21:36             ` Arnd Bergmann
2007-05-17 21:36             ` Arnd Bergmann
2007-05-17 21:50             ` Jörn Engel
2007-05-17 21:50               ` Jörn Engel
2007-05-17 21:50               ` Jörn Engel
2007-05-16 19:17 ` Pavel Machek
2007-05-16 19:17   ` Pavel Machek
2007-05-16 19:23   ` Jörn Engel
2007-05-16 19:23     ` Jörn Engel
2007-05-16 19:23     ` Jörn Engel
2007-05-17 15:08 ` Arnd Bergmann
2007-05-17 15:08   ` Arnd Bergmann
2007-05-17 15:08   ` Arnd Bergmann
2007-05-17 20:21   ` Jörn Engel
2007-05-17 20:21     ` Jörn Engel
2007-05-17 20:21     ` Jörn Engel
2007-05-17 21:00     ` Arnd Bergmann
2007-05-17 21:00       ` Arnd Bergmann
2007-05-17 21:00       ` Arnd Bergmann
2007-05-17 21:30       ` Jörn Engel
2007-05-17 21:30         ` Jörn Engel
2007-05-17 22:01     ` Jamie Lokier
2007-05-17 22:01       ` Jamie Lokier
2007-05-17 22:01       ` Jamie Lokier

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=464F1539.5050204@tmr.com \
    --to=davidsen@tmr.com \
    --cc=acahalan@gmail.com \
    --cc=akpm@linux-foundation.org \
    --cc=djshin90@gmail.com \
    --cc=dwmw2@infradead.org \
    --cc=greg@kroah.com \
    --cc=ioe-lkml@rameria.de \
    --cc=jengelh@linux01.gwdg.de \
    --cc=joern@lazybastard.org \
    --cc=johnpol@2ka.mipt.ru \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mtd@lists.infradead.org \
    --cc=penberg@cs.helsinki.fi \
    --cc=tglx@linutronix.de \
    /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.