Venkat Subbiah wrote:
Since most network devices have a single status register for both
receiver and transmit (and errors and the like), which needs a lock to
protect access, you will likely end up with serious thrashing of moving
the lock between cpus.
Any ways to measure the trashing of
Venkat
-Original Message-
From: Lennart Sorensen [mailto:[EMAIL PROTECTED]
Sent: Thursday, September 13, 2007 1:45 PM
To: Venkat Subbiah
Cc: Chris Snook; linux-kernel@vger.kernel.org
Subject: Re: irq load balancing
On Thu, Sep 13, 2007 at 01:31:39PM -0700, Venkat Subbiah wrote:
> Doing it i
On Thu, Sep 13, 2007 at 01:31:39PM -0700, Venkat Subbiah wrote:
> Doing it in a round-robin fashion will be disastrous for performance.
> Your cache miss rate will go through the roof and you'll hit the slow
> paths in the network stack most of the time.
> > Most of the work in my system is spent
:45 PM
To: Venkat Subbiah
Cc: linux-kernel@vger.kernel.org
Subject: Re: irq load balancing
Venkat Subbiah wrote:
> Most of the load in my system is triggered by a single ethernet IRQ.
> Essentially the IRQ schedules a tasklet and most of the work is done
in the
> taskelet which is schedule
To: Venkat Subbiah
Cc: linux-kernel@vger.kernel.org
Subject: Re: irq load balancing
Venkat Subbiah wrote:
Most of the load in my system is triggered by a single ethernet IRQ.
Essentially the IRQ schedules a tasklet and most of the work is done
in the
taskelet which is scheduled in the IRQ. From
On Thu, Sep 13, 2007 at 01:31:39PM -0700, Venkat Subbiah wrote:
Doing it in a round-robin fashion will be disastrous for performance.
Your cache miss rate will go through the roof and you'll hit the slow
paths in the network stack most of the time.
Most of the work in my system is spent in
-Original Message-
From: Lennart Sorensen [mailto:[EMAIL PROTECTED]
Sent: Thursday, September 13, 2007 1:45 PM
To: Venkat Subbiah
Cc: Chris Snook; linux-kernel@vger.kernel.org
Subject: Re: irq load balancing
On Thu, Sep 13, 2007 at 01:31:39PM -0700, Venkat Subbiah wrote:
Doing it in a round-robin
Venkat Subbiah wrote:
Since most network devices have a single status register for both
receiver and transmit (and errors and the like), which needs a lock to
protect access, you will likely end up with serious thrashing of moving
the lock between cpus.
Any ways to measure the trashing of
Venkat Subbiah wrote:
Most of the load in my system is triggered by a single ethernet IRQ.
Essentially the IRQ schedules a tasklet and most of the work is done in the
taskelet which is scheduled in the IRQ. From what I read looks like the
tasklet would be executed on the same CPU on which it was
On Tue, 11 Sep 2007 16:18:15 -0700
"Venkat Subbiah" <[EMAIL PROTECTED]> wrote:
> Most of the load in my system is triggered by a single ethernet IRQ.
> Essentially the IRQ schedules a tasklet and most of the work is done
> in the taskelet which is scheduled in the IRQ. From what I read looks
>
On 9/12/07, Venkat Subbiah <[EMAIL PROTECTED]> wrote:
> Most of the load in my system is triggered by a single ethernet IRQ.
> Essentially the IRQ schedules a tasklet and most of the work is done in the
> taskelet which is scheduled in the IRQ. From what I read looks like the
> tasklet would be
On Tue, 11 Sep 2007 16:18:15 -0700
"Venkat Subbiah" <[EMAIL PROTECTED]> wrote:
> Most of the load in my system is triggered by a single ethernet IRQ.
> Essentially the IRQ schedules a tasklet and most of the work is done in the
> taskelet which is scheduled in the IRQ. From what I read looks
Venkat Subbiah wrote:
Most of the load in my system is triggered by a single ethernet IRQ.
Essentially the IRQ schedules a tasklet and most of the work is done in the
taskelet which is scheduled in the IRQ. From what I read looks like the
tasklet would be executed on the same CPU on which it was
On Tue, 11 Sep 2007 16:18:15 -0700
Venkat Subbiah [EMAIL PROTECTED] wrote:
Most of the load in my system is triggered by a single ethernet IRQ.
Essentially the IRQ schedules a tasklet and most of the work is done in the
taskelet which is scheduled in the IRQ. From what I read looks like the
On 9/12/07, Venkat Subbiah [EMAIL PROTECTED] wrote:
Most of the load in my system is triggered by a single ethernet IRQ.
Essentially the IRQ schedules a tasklet and most of the work is done in the
taskelet which is scheduled in the IRQ. From what I read looks like the
tasklet would be
On Tue, 11 Sep 2007 16:18:15 -0700
Venkat Subbiah [EMAIL PROTECTED] wrote:
Most of the load in my system is triggered by a single ethernet IRQ.
Essentially the IRQ schedules a tasklet and most of the work is done
in the taskelet which is scheduled in the IRQ. From what I read looks
like the
Most of the load in my system is triggered by a single ethernet IRQ.
Essentially the IRQ schedules a tasklet and most of the work is done in the
taskelet which is scheduled in the IRQ. From what I read looks like the tasklet
would be executed on the same CPU on which it was scheduled. So this
Most of the load in my system is triggered by a single ethernet IRQ.
Essentially the IRQ schedules a tasklet and most of the work is done in the
taskelet which is scheduled in the IRQ. From what I read looks like the tasklet
would be executed on the same CPU on which it was scheduled. So this
18 matches
Mail list logo
