From mboxrd@z Thu Jan 1 00:00:00 1970 From: Felix Radensky Subject: Re: e100 "Ferguson" release Date: Sun, 10 Aug 2003 12:00:12 +0300 Sender: netdev-bounce@oss.sgi.com Message-ID: <3F36099C.7090002@allot.com> References: <20030805152418.GB6695@gtf.org> Mime-Version: 1.0 Content-Type: multipart/alternative; boundary="Boundary_(ID_NRV+4kR+TEKMqsKNRaPtwQ)" Cc: "Feldman, Scott" , Ben Greear , netdev@oss.sgi.com Return-path: To: Jeff Garzik Errors-to: netdev-bounce@oss.sgi.com List-Id: netdev.vger.kernel.org --Boundary_(ID_NRV+4kR+TEKMqsKNRaPtwQ) Content-type: text/plain; charset=us-ascii; format=flowed Content-transfer-encoding: 7BIT Hi, Jeff, Scott Are you planning to fix this before 2.4.22-final ? Thanks. Felix. Jeff Garzik wrote: >On Tue, Aug 05, 2003 at 08:19:25AM -0700, Feldman, Scott wrote: > > >>>I've also noticed that the number of hard_start_xmit failures >>>in e1000 has increased significantly in version 5.1.13-k1. In >>>version 5.0.43-k1 the number of failures was much smaller. >>> >>> >>Interesting. Felix, would you undo the change[1] below in 5.1.13-k1 and >>see what happens? With the change below, 5.1.13 would be more >>aggressive on Tx cleanup, so we'll be quicker waking the queue than >>before. >> >>-scott >> >> for(i = 0; i < E1000_MAX_INTR; i++) >>- if(!e1000_clean_rx_irq(adapter) && >>+ if(!e1000_clean_rx_irq(adapter) & >> !e1000_clean_tx_irq(adapter)) >> break; >> >>[1] Something still bothers me about this new form where we're mixing a >>bit-wise operator with logical operands. Should this bother me? >> >> > >It doesn't matter to the compiler if you make it explicit: > > unsigned int rx_work = e1000_clean_rx_irq(); > unsigned int tx_work = e1000_clean_tx_irq(); > if (!rx_work && !tx_work) > break; > > > > --Boundary_(ID_NRV+4kR+TEKMqsKNRaPtwQ) Content-type: text/html; charset=us-ascii Content-transfer-encoding: 7BIT Hi, Jeff, Scott

Are you planning to fix this before 2.4.22-final ?

Thanks.

Felix.

Jeff Garzik wrote:
On Tue, Aug 05, 2003 at 08:19:25AM -0700, Feldman, Scott wrote:
  
I've also noticed that the number of hard_start_xmit failures 
in e1000 has increased significantly in version 5.1.13-k1. In 
version 5.0.43-k1 the number of failures was much smaller.
      
Interesting.  Felix, would you undo the change[1] below in 5.1.13-k1 and
see what happens?  With the change below, 5.1.13 would be more
aggressive on Tx cleanup, so we'll be quicker waking the queue than
before. 

-scott

        for(i = 0; i < E1000_MAX_INTR; i++)
-               if(!e1000_clean_rx_irq(adapter) &&
+               if(!e1000_clean_rx_irq(adapter) &
                   !e1000_clean_tx_irq(adapter))
                        break;

[1] Something still bothers me about this new form where we're mixing a
bit-wise operator with logical operands.  Should this bother me?
    

It doesn't matter to the compiler if you make it explicit:

	unsigned int rx_work = e1000_clean_rx_irq();
	unsigned int tx_work = e1000_clean_tx_irq();
	if (!rx_work && !tx_work)
		break;

--Boundary_(ID_NRV+4kR+TEKMqsKNRaPtwQ)--