netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Stephen Hemminger <shemminger@vyatta.com>
To: David Miller <davem@davemloft.net>,
	Robert Olsson <Robert.Olsson@data.slu.se>
Cc: netdev@vger.kernel.org
Cc: Thomas Gleixner <tglx@linutronix.de>, Ingo Molnar <mingo@elte.hu>
Subject: [RFC 3/4] pktgen: clock optimizations
Date: Tue, 25 Aug 2009 23:15:16 -0700	[thread overview]
Message-ID: <20090826061728.771777518@vyatta.com> (raw)
In-Reply-To: 20090826061513.755294685@vyatta.com

[-- Attachment #1: pktgen-avoid-clock.patch --]
[-- Type: text/plain, Size: 1399 bytes --]

This optimizes pktgen to avoid calling ktime_get_ts unless
it is needed. 
  * if delay is 0, then no need to update next_tx
  * if queue is stopped, then keep old value will already force
    tx on next cycle.

Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>

---
 net/core/pktgen.c |   14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

--- a/net/core/pktgen.c	2009-08-25 22:49:55.966424251 -0700
+++ b/net/core/pktgen.c	2009-08-25 22:51:21.162461840 -0700
@@ -3425,11 +3425,12 @@ static __inline__ void pktgen_xmit(struc
 	txq = netdev_get_tx_queue(odev, queue_map);
 
 	__netif_tx_lock_bh(txq);
-	if (!netif_tx_queue_stopped(txq) &&
-	    !netif_tx_queue_frozen(txq)) {
+	if (netif_tx_queue_stopped(txq) || netif_tx_queue_frozen(txq))
+		pkt_dev->last_ok = 0; 			/* Retry it next time */
+	else {
 
 		atomic_inc(&(pkt_dev->skb->users));
-	      retry_now:
+retry_now:
 		ret = (*xmit)(pkt_dev->skb, odev);
 		if (likely(ret == NETDEV_TX_OK)) {
 			txq_trans_update(txq);
@@ -3453,10 +3454,9 @@ static __inline__ void pktgen_xmit(struc
 			pkt_dev->last_ok = 0;
 		}
 
-		pkt_dev->next_tx = ktime_add_ns(ktime_now(), pkt_dev->delay);
-	} else {			/* Retry it next time */
-		pkt_dev->last_ok = 0;
-		pkt_dev->next_tx = ktime_now();
+		if (pkt_dev->delay)
+			pkt_dev->next_tx = ktime_add_ns(ktime_now(),
+							pkt_dev->delay);
 	}
 
 	__netif_tx_unlock_bh(txq);

-- 


  parent reply	other threads:[~2009-08-26  6:25 UTC|newest]

Thread overview: 6+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2009-08-26  6:15 [RFC 0/4] pktgen patches Stephen Hemminger
2009-08-26  6:15 ` [RFC 1/4] pktgen: convert to use ktime_t Stephen Hemminger
2009-08-26  6:15 ` [RFC 2/4] pktgen: spin using hrtimer Stephen Hemminger
2009-08-26  6:15 ` Stephen Hemminger [this message]
2009-08-26  6:15 ` [RFC 4/4] pktgen: minor cleanup Stephen Hemminger
2009-08-26  6:54 ` [RFC 0/4] pktgen patches Eric Dumazet

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=20090826061728.771777518@vyatta.com \
    --to=shemminger@vyatta.com \
    --cc=Robert.Olsson@data.slu.se \
    --cc=davem@davemloft.net \
    --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 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).