From: Tejun Heo <tj@kernel.org>
To: Alexander Gordeev <agordeev@redhat.com>
Cc: linux-kernel@vger.kernel.org, linux-ide@vger.kernel.org
Subject: Re: [PATCH RESEND v3 5/6] AHCI: Optimize single IRQ interrupt processing
Date: Tue, 23 Sep 2014 16:57:10 -0400 [thread overview]
Message-ID: <20140923205710.GB17332@mtj.dyndns.org> (raw)
In-Reply-To: <b1a04379e05e40f9774fb4668609fac4255a6514.1411297686.git.agordeev@redhat.com>
Hello, Alexander.
On Sun, Sep 21, 2014 at 03:19:28PM +0200, Alexander Gordeev wrote:
> Split interrupt service routine into hardware context handler
> and threaded context handler. That allows to protect ports with
> individual locks rather than with a single host-wide lock and
> move port interrupts handling out of the hardware interrupt
> context.
>
> Testing was done by transferring 8GB on two hard drives in
> parallel using command 'dd if=/dev/sd{a,b} of=/dev/null'. With
> lock_stat statistics I measured access times to ata_host::lock
> spinlock (since interrupt handler code is fully embraced with
> this lock). The average lock's holdtime decreased eight times
> while average waittime decreased two times.
>
> Both before and after the change the transfer time is the same,
> while 'perf record -e cycles:k ...' shows 1%-4% CPU time spent
> in ahci_single_irq_intr() routine before the update and not even
> sampled/shown ahci_single_irq_intr() after the update.
Hmmm... how does it affect single device operation tho? It does make
individual interrupt handling heavier, no?
Thanks.
--
tejun
next prev parent reply other threads:[~2014-09-23 20:57 UTC|newest]
Thread overview: 29+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-09-21 13:19 [PATCH RESEND v3 0/6] AHCI: Optimize interrupt processing Alexander Gordeev
2014-09-21 13:19 ` [PATCH RESEND v3 1/6] AHCI: Cleanup checking of multiple MSIs/SLM modes Alexander Gordeev
2014-09-23 20:18 ` Tejun Heo
2014-09-21 13:19 ` [PATCH RESEND v3 2/6] AHCI: Move host activation code into ahci_host_activate() Alexander Gordeev
2014-09-23 20:22 ` Tejun Heo
2014-09-23 20:55 ` Tejun Heo
2014-09-21 13:19 ` [PATCH RESEND v3 3/6] AHCI: Make few function names more descriptive Alexander Gordeev
2014-09-23 20:22 ` Tejun Heo
2014-09-21 13:19 ` [PATCH RESEND v3 4/6] AHCI: Get rid of redundant arg to ahci_handle_port_interrupt() Alexander Gordeev
2014-09-21 13:19 ` [PATCH RESEND v3 5/6] AHCI: Optimize single IRQ interrupt processing Alexander Gordeev
2014-09-23 20:57 ` Tejun Heo [this message]
2014-09-24 10:42 ` Alexander Gordeev
2014-09-24 13:04 ` Tejun Heo
2014-09-24 13:27 ` Chuck Ebbert
2014-09-24 13:36 ` Tejun Heo
2014-09-24 14:08 ` Alexander Gordeev
2014-09-24 14:39 ` Tejun Heo
2014-09-24 14:59 ` Alexander Gordeev
2014-09-25 3:27 ` Tejun Heo
2014-10-01 15:31 ` Alexander Gordeev
2014-10-01 15:39 ` Alexander Gordeev
2014-10-05 2:23 ` Tejun Heo
2014-10-05 16:16 ` Tejun Heo
2014-10-06 7:27 ` Alexander Gordeev
2014-10-06 12:58 ` Tejun Heo
2014-10-06 13:24 ` Alexander Gordeev
2014-10-06 14:54 ` Tejun Heo
2014-09-25 3:00 ` Elliott, Robert (Server Storage)
2014-09-21 13:19 ` [PATCH RESEND v3 6/6] AHCI: Do not read HOST_IRQ_STAT reg in multi-MSI mode Alexander Gordeev
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=20140923205710.GB17332@mtj.dyndns.org \
--to=tj@kernel.org \
--cc=agordeev@redhat.com \
--cc=linux-ide@vger.kernel.org \
--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;
as well as URLs for NNTP newsgroup(s).