From: Milan Broz <gmazyland@gmail.com>
To: device-mapper development <dm-devel@redhat.com>
Subject: Re: [PATCH 9/9] dm crypt: sort writes
Date: Sat, 29 Mar 2014 09:11:47 +0100 [thread overview]
Message-ID: <53368043.5000808@gmail.com> (raw)
In-Reply-To: <1396037476-26595-10-git-send-email-snitzer@redhat.com>
On 03/28/2014 09:11 PM, Mike Snitzer wrote:
> From: Mikulas Patocka <mpatocka@redhat.com>
>
> Write requests are sorted in a red-black tree structure and are submitted
> in the sorted order.
>
> In theory the sorting should be performed by the underlying disk scheduler,
> however, in practice the disk scheduler accepts and sorts only 128 requests.
> In order to sort more requests, we need to implement our own sorting.
Hi,
I think it would be nice to mention why simply increasing queue nr_request
doesn't help. It is definitely not limited to 128, it is only default value.
(I just wonder how this helps for SSDs where I think it depends what's fw
doing with io requests anyway).
It would be nice to have sysfs switch to disable sorting in dmcrypt but that
can be added later.
Anyway, thanks for rebasing these patches!
...
> +#define io_node rb_entry(parent, struct dm_crypt_io, rb_node)
> + if (sector < io_node->sector)
> + p = &io_node->rb_node.rb_left;
> + else
> + p = &io_node->rb_node.rb_right;
> +#undef io_node
Btw, could this be switched to inline function instead of define,
or it is only me who thinks #define here is ugly? :)
Thanks,
Milan
next prev parent reply other threads:[~2014-03-29 8:11 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-03-28 20:11 [PATCH 0/9] dm crypt: improve cpu scalability Mike Snitzer
2014-03-28 20:11 ` [PATCH 1/9] dm crypt: fix cpu hotplug crash by removing per-cpu structure Mike Snitzer
2014-03-28 20:11 ` [PATCH 2/9] block: use kmalloc alignment for bio slab Mike Snitzer
2014-03-28 20:11 ` [PATCH 3/9] dm crypt: use per-bio data Mike Snitzer
2014-03-28 20:11 ` [PATCH 4/9] dm crypt: use unbound workqueue for request processing Mike Snitzer
2014-03-28 20:11 ` [PATCH 5/9] dm crypt: don't allocate pages for a partial request Mike Snitzer
2014-03-28 20:11 ` [PATCH 6/9] dm crypt: avoid deadlock in mempools Mike Snitzer
2014-03-28 20:11 ` [PATCH 7/9] dm crypt: remove io_pool Mike Snitzer
2014-03-28 20:11 ` [PATCH 8/9] dm crypt: offload writes to thread Mike Snitzer
2014-04-01 16:27 ` Ondrej Kozina
2014-04-01 16:32 ` Mike Snitzer
2014-04-01 18:15 ` Mikulas Patocka
2014-04-01 18:23 ` Mike Snitzer
2014-04-02 6:55 ` Ondrej Kozina
2014-04-01 18:01 ` Mikulas Patocka
2014-04-01 19:08 ` Milan Broz
2014-03-28 20:11 ` [PATCH 9/9] dm crypt: sort writes Mike Snitzer
2014-03-29 8:11 ` Milan Broz [this message]
2014-03-31 12:39 ` Mike Snitzer
2014-03-31 23:37 ` Akira Hayakawa
2014-04-01 1:01 ` Mike Snitzer
2014-04-01 17:35 ` Milan Broz
2014-04-01 20:15 ` Alasdair G Kergon
2014-04-01 23:21 ` Akira Hayakawa
2014-04-02 3:19 ` Akira Hayakawa
2014-04-02 3:38 ` Mike Snitzer
2014-04-02 4:18 ` Akira Hayakawa
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=53368043.5000808@gmail.com \
--to=gmazyland@gmail.com \
--cc=dm-devel@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 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).