From: linas@austin.ibm.com (Linas Vepstas)
To: Andrew Morton <akpm@osdl.org>
Cc: jeff@garzik.org, Arnd Bergmann <arnd@arndb.de>,
netdev@vger.kernel.org, James K Lewis <jklewis@us.ibm.com>,
linux-kernel@vger.kernel.org, linuxppc-dev@ozlabs.org
Subject: Re: [PATCH 6/6]: powerpc/cell spidernet refine locking
Date: Mon, 2 Oct 2006 12:47:22 -0500 [thread overview]
Message-ID: <20061002174722.GE4546@austin.ibm.com> (raw)
In-Reply-To: <20060929194752.2194f94f.akpm@osdl.org>
On Fri, Sep 29, 2006 at 07:47:52PM -0700, Andrew Morton wrote:
> On Fri, 29 Sep 2006 18:29:11 -0500
> linas@austin.ibm.com (Linas Vepstas) wrote:
>
> > The transmit side of the spider ethernet driver currently
> > places locks around some very large chunks of code. This
> > results in a fair amount of lock contention is some cases.
> > This patch makes the locks much more fine-grained, protecting
> > only the cirtical sections. One lock is used to protect
> > three locations: the queue head and tail pointers, and the
> > queue low-watermark location.
>
> You have spider_net_set_low_watermark() walking the tx_chain outside
> tx_chain.lock. Are you sure about that?
Yes. Its making an approximate count of the queue length, and I figured
that if its approximate to begin with, an unlocked version should be
just fine.
--linas
WARNING: multiple messages have this Message-ID (diff)
From: linas@austin.ibm.com (Linas Vepstas)
To: Andrew Morton <akpm@osdl.org>
Cc: jeff@garzik.org, netdev@vger.kernel.org,
James K Lewis <jklewis@us.ibm.com>,
linux-kernel@vger.kernel.org, Arnd Bergmann <arnd@arndb.de>,
linuxppc-dev@ozlabs.org
Subject: Re: [PATCH 6/6]: powerpc/cell spidernet refine locking
Date: Mon, 2 Oct 2006 12:47:22 -0500 [thread overview]
Message-ID: <20061002174722.GE4546@austin.ibm.com> (raw)
In-Reply-To: <20060929194752.2194f94f.akpm@osdl.org>
On Fri, Sep 29, 2006 at 07:47:52PM -0700, Andrew Morton wrote:
> On Fri, 29 Sep 2006 18:29:11 -0500
> linas@austin.ibm.com (Linas Vepstas) wrote:
>
> > The transmit side of the spider ethernet driver currently
> > places locks around some very large chunks of code. This
> > results in a fair amount of lock contention is some cases.
> > This patch makes the locks much more fine-grained, protecting
> > only the cirtical sections. One lock is used to protect
> > three locations: the queue head and tail pointers, and the
> > queue low-watermark location.
>
> You have spider_net_set_low_watermark() walking the tx_chain outside
> tx_chain.lock. Are you sure about that?
Yes. Its making an approximate count of the queue length, and I figured
that if its approximate to begin with, an unlocked version should be
just fine.
--linas
next prev parent reply other threads:[~2006-10-02 17:47 UTC|newest]
Thread overview: 33+ messages / expand[flat|nested] mbox.gz Atom feed top
2006-09-29 23:05 [PATCH 0/6]: powerpc/cell spidernet ethernet patches Linas Vepstas
2006-09-29 23:05 ` Linas Vepstas
2006-09-29 23:15 ` [PATCH 1/6]: powerpc/cell spidernet burst alignment patch Linas Vepstas
2006-09-30 10:29 ` Arnd Bergmann
2006-09-30 10:29 ` Arnd Bergmann
2006-09-29 23:17 ` [PATCH 2/6]: powerpc/cell spidernet low watermark patch Linas Vepstas
2006-09-30 10:30 ` Arnd Bergmann
2006-09-30 10:30 ` Arnd Bergmann
2006-09-29 23:19 ` [PATCH 3/6]: powerpc/cell spidernet stop error printing patch Linas Vepstas
2006-09-30 10:32 ` Arnd Bergmann
2006-09-30 10:32 ` Arnd Bergmann
2006-09-29 23:21 ` [PATCH 4/6]: powerpc/cell spidernet ethtool -i version number info Linas Vepstas
2006-09-30 10:33 ` Arnd Bergmann
2006-09-30 10:33 ` Arnd Bergmann
2006-10-02 17:14 ` Linas Vepstas
2006-10-02 17:14 ` Linas Vepstas
2006-09-29 23:26 ` [PATCH 5/6]: powerpc/cell spidernet ethtool -i version number Linas Vepstas
2006-09-30 10:35 ` Arnd Bergmann
2006-09-30 10:35 ` Arnd Bergmann
2006-09-29 23:29 ` [PATCH 6/6]: powerpc/cell spidernet refine locking Linas Vepstas
2006-09-30 2:47 ` Andrew Morton
2006-09-30 2:47 ` Andrew Morton
2006-10-02 17:47 ` Linas Vepstas [this message]
2006-10-02 17:47 ` Linas Vepstas
2006-09-30 10:40 ` [PATCH 0/6]: powerpc/cell spidernet ethernet patches Arnd Bergmann
2006-09-30 10:40 ` Arnd Bergmann
2006-10-02 16:27 ` Linas Vepstas
2006-10-02 16:27 ` Linas Vepstas
2006-10-02 16:50 ` Arnd Bergmann
2006-10-02 16:50 ` Arnd Bergmann
2006-10-02 17:23 ` Linas Vepstas
2006-10-02 17:23 ` Linas Vepstas
-- strict thread matches above, loose matches on Subject: below --
2006-08-18 22:07 [PATCH 0/6]: powerpc/cell spidernet ethernet driver update Linas Vepstas
2006-08-18 22:29 ` [PATCH 6/6]: powerpc/cell spidernet refine locking Linas Vepstas
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=20061002174722.GE4546@austin.ibm.com \
--to=linas@austin.ibm.com \
--cc=akpm@osdl.org \
--cc=arnd@arndb.de \
--cc=jeff@garzik.org \
--cc=jklewis@us.ibm.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linuxppc-dev@ozlabs.org \
--cc=netdev@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 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.