public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Peter Osterlund <petero2@telia.com>
To: Andrew Morton <akpm@osdl.org>
Cc: axboe@suse.de, linux-kernel@vger.kernel.org
Subject: Re: [PATCH] Speed up the cdrw packet writing driver
Date: 25 Aug 2004 00:03:08 +0200	[thread overview]
Message-ID: <m3d61gchyb.fsf@telia.com> (raw)
In-Reply-To: <20040824144707.100e0cfd.akpm@osdl.org>

Andrew Morton <akpm@osdl.org> writes:

> Peter Osterlund <petero2@telia.com> wrote:
> >
> > Jens Axboe <axboe@suse.de> writes:
> > 
> > > On Mon, Aug 23 2004, Peter Osterlund wrote:
> > > > Jens Axboe <axboe@suse.de> writes:
> > > > 
> > > > > On Sat, Aug 14 2004, Peter Osterlund wrote:
> > > > > > 
> > > > > > This patch replaces the pd->bio_queue linked list with an rbtree.  The
> > > > > > list can get very long (>200000 entries on a 1GB machine), so keeping
> > > > > > it sorted with a naive algorithm is far too expensive.
> > > > > 
> > > > > It looks like you are assuming that bio->bi_sector is unique which isn't
> > > > > necessarily true. In that respect, list -> rbtree conversion isn't
> > > > > trivial (or, at least it requires extra code to handle this).
> > > > 
> > > > I don't think that is assumed anywhere.
> > > > 
> > > > [...]
> > > 
> > > You are right, the code looks fine indeed. The bigger problem is
> > > probably that a faster data structure is needed at all, having hundreds
> > > of thousands bio's pending for a packet writing device is not nice at
> > > all.
> > 
> > Why is it not nice? If the VM has decided to create 400MB of dirty
> > data on a DVD+RW packet device, I don't see a problem with submitting
> > all bio's at the same time to the packet device.
> 
> We also have a limit on the number of in-flight requests:
> /sys/block/sda/queue/nr_requests.  It defaults to 128.
> 
> Are you saying that your requests are so huge that each one has 1000 BIOs? 
> That would be odd, for an IDE interface.

No, the thing is that the packet driver doesn't create requests at
all. It stuffs incoming bio's in the rbtree, then the worker thread
collects bio's from the rbtree for the same "zone" on the disc (each
zone is 64kb on a CDRW and 32KB on a DVD). The driver then creates a
new bio with the same size as the zone size and submits it to the real
CD/DVD device.

-- 
Peter Osterlund - petero2@telia.com
http://w1.894.telia.com/~u89404340

  parent reply	other threads:[~2004-08-24 22:12 UTC|newest]

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2004-08-14 19:13 [PATCH] Speed up the cdrw packet writing driver Peter Osterlund
2004-08-23 11:43 ` Jens Axboe
2004-08-23 16:07   ` Peter Osterlund
2004-08-24 20:29     ` Jens Axboe
2004-08-24 21:04       ` Peter Osterlund
2004-08-24 21:47         ` Andrew Morton
2004-08-24 21:57           ` Lee Revell
2004-08-29 13:52             ` Alan Cox
2004-08-24 22:03           ` Peter Osterlund [this message]
2004-08-24 22:56             ` Andrew Morton
2004-08-25  5:38               ` Peter Osterlund
2004-08-25  6:50         ` Jens Axboe
2004-08-28  9:59           ` Peter Osterlund
2004-08-28 13:07             ` Jens Axboe
2004-08-28 18:42               ` Peter Osterlund
2004-08-28 19:45                 ` Andrew Morton
2004-08-28 20:57                   ` Peter Osterlund
2004-08-28 21:23                     ` Andrew Morton
2004-08-29 12:17                       ` Peter Osterlund

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=m3d61gchyb.fsf@telia.com \
    --to=petero2@telia.com \
    --cc=akpm@osdl.org \
    --cc=axboe@suse.de \
    --cc=linux-kernel@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