public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Michael Tokarev <mjt@tls.msk.ru>
To: Wu Fengguang <wfg@mail.ustc.edu.cn>,
	Michael Tokarev <mjt@tls.msk.ru>,
	linux-kernel@vger.kernel.org
Subject: Re: [PATCH 00/32] Adaptive readahead V14
Date: Sun, 28 May 2006 23:23:33 +0400	[thread overview]
Message-ID: <4479F8B5.90906@tls.msk.ru> (raw)
In-Reply-To: <348818092.32485@ustc.edu.cn>

Wu Fengguang wrote:
> 
> It's not quite reasonable for readahead to worry about media errors.
> If the media fails, fix it. Or it will hurt read sooner or later.

Well... In reality, it is just the opposite.

Suppose there's a CD-rom with a scratch/etc, one sector is unreadable.
In order to "fix" it, one have to read it and write to another CD-rom,
or something.. or just ignore the error (if it's just a skip in a video
stream).  Let's assume the unreadable block is number U.

But current behavior is just insane.  An application requests block
number N, which is before U. Kernel tries to read-ahead blocks N..U.
Cdrom drive tries to read it, re-read it.. for some time.  Finally,
when all the N..U-1 blocks are read, kernel returns block number N
(as requested) to an application, successefully.

Now an app requests block number N+1, and kernel tries to read
blocks N+1..U+1.  Retrying again as in previous step.

And so on, up to when an app requests block number U-1.  And when,
finally, it requests block U, it receives read error.

So, kernel currentry tries to re-read the same failing block as
many times as the current readahead value (256 (times?) by default).

This whole process already killed my cdrom drive (I posted about it
to LKML several months ago) - literally, the drive has fried, and
does not work anymore.  Ofcourse that problem was a bug in firmware
(or whatever) of the drive *too*, but.. main problem with that is
current readahead logic as described above.

With that logic, an app also becomes unkillable (at least for some
time) -- ie, even when I knew something's wrong and the CDrom should
not behave like it was, I wasn't able to stop it until I powered the
machine off (just unplugged the power cable) - but.. too late.

Yes, bad media is just that - a bad thing.  But it's not a reason to
force power unplug to stop the process, and not a reason to burn a
drive (or anything else).  And this is where readahead comes into
play - it IS read-ahead logic who's responsible for the situation.

And there's alot of scratched/whatever CD-Rom drives out there -
unreadable CDrom (or a floppy which is already ancient, or some
other media) - you can't just say to every user out there that
linux isn't compatible with all people's stuff and those people
should "fix" it before ever trying to insert it into their linux
machine...

Thanks.

/mjt

  reply	other threads:[~2006-05-28 19:23 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <20060527154849.927021763@localhost.localdomain>
2006-05-27 15:48 ` [PATCH 00/32] Adaptive readahead V14 Wu Fengguang
2006-05-27 17:29   ` Michael Tokarev
     [not found]     ` <20060528120815.GB6478@mail.ustc.edu.cn>
2006-05-28 12:08       ` Wu Fengguang
2006-05-28 19:23         ` Michael Tokarev [this message]
     [not found]           ` <20060529030152.GA5994@mail.ustc.edu.cn>
2006-05-29  3:01             ` Wu Fengguang
2006-05-30  9:23             ` Jens Axboe
     [not found]               ` <20060530113221.GA8665@mail.ustc.edu.cn>
2006-05-30 11:32                 ` Wu Fengguang
2006-05-30 12:29                 ` Jens Axboe
     [not found]                   ` <20060530143417.GA9126@mail.ustc.edu.cn>
2006-05-30 14:34                     ` Wu Fengguang
     [not found] ` <20060527155125.911021581@localhost.localdomain>
2006-05-27 15:48   ` [PATCH 01/32] readahead: kconfig options Wu Fengguang
     [not found] ` <20060527155127.522802387@localhost.localdomain>
2006-05-27 15:48   ` [PATCH 04/32] mm: introduce PG_readahead Wu Fengguang
     [not found] ` <20060527155128.472551240@localhost.localdomain>
2006-05-27 15:48   ` [PATCH 06/32] readahead: delay page release in do_generic_mapping_read() Wu Fengguang
     [not found] ` <20060527155129.001886224@localhost.localdomain>
2006-05-27 15:48   ` [PATCH 07/32] readahead: insert cond_resched() calls Wu Fengguang
     [not found] ` <20060527155129.653903854@localhost.localdomain>
2006-05-27 15:48   ` [PATCH 08/32] readahead: {MIN,MAX}_RA_PAGES Wu Fengguang
     [not found] ` <20060527155130.013773601@localhost.localdomain>
2006-05-27 15:48   ` [PATCH 09/32] readahead: events accounting Wu Fengguang
     [not found] ` <20060527155130.538411854@localhost.localdomain>
2006-05-27 15:48   ` [PATCH 10/32] readahead: rescue_pages() Wu Fengguang
     [not found] ` <20060527155131.200177171@localhost.localdomain>
2006-05-27 15:49   ` [PATCH 11/32] readahead: sysctl parameters Wu Fengguang
     [not found] ` <20060527155132.649338979@localhost.localdomain>
2006-05-27 15:49   ` [PATCH 14/32] readahead: state based method - routines Wu Fengguang
     [not found] ` <20060527155133.216888332@localhost.localdomain>
2006-05-27 15:49   ` [PATCH 15/32] readahead: state based method Wu Fengguang
     [not found] ` <20060527155134.715578802@localhost.localdomain>
2006-05-27 15:49   ` [PATCH 18/32] readahead: initial method - thrashing guard size Wu Fengguang
     [not found] ` <20060527155135.584918734@localhost.localdomain>
2006-05-27 15:49   ` [PATCH 20/32] readahead: initial method - user recommended size Wu Fengguang
     [not found] ` <20060527155136.503037461@localhost.localdomain>
2006-05-27 15:49   ` [PATCH 22/32] readahead: backward prefetching method Wu Fengguang
     [not found] ` <20060527155137.552915509@localhost.localdomain>
2006-05-27 15:49   ` [PATCH 24/32] readahead: thrashing recovery method Wu Fengguang
2006-05-27 22:04     ` [PATCH 23/32] readahead: seeking reads method Ingo Oeser
     [not found] ` <20060527155138.046726658@localhost.localdomain>
2006-05-27 15:49   ` [PATCH 25/32] readahead: call scheme Wu Fengguang
     [not found] ` <20060527155138.454809673@localhost.localdomain>
2006-05-27 15:49   ` [PATCH 26/32] readahead: laptop mode Wu Fengguang
     [not found] ` <20060527155140.035991503@localhost.localdomain>
2006-05-27 15:49   ` [PATCH 27/32] readahead: loop case Wu Fengguang
     [not found] ` <20060527155141.697607086@localhost.localdomain>
2006-05-27 15:49   ` [PATCH 30/32] readahead: debug radix tree new functions Wu Fengguang
     [not found] ` <20060527155142.129761018@localhost.localdomain>
2006-05-27 15:49   ` [PATCH 31/32] readahead: debug traces showing accessed file names Wu Fengguang
     [not found] ` <20060527155142.715530234@localhost.localdomain>
2006-05-27 15:49   ` [PATCH 32/32] readahead: debug traces showing read patterns Wu Fengguang

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=4479F8B5.90906@tls.msk.ru \
    --to=mjt@tls.msk.ru \
    --cc=linux-kernel@vger.kernel.org \
    --cc=wfg@mail.ustc.edu.cn \
    /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