netdev - [PATCH 4/8] e1000: fix NAPI performance on 4-port adapters

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:	Fri, 12 Jan 2007 16:37:47 -0800
From:	"Kok, Auke" <auke-jan.h.kok@...el.com>
To:	"Garzik, Jeff" <jgarzik@...ox.com>
Cc:	netdev@...r.kernel.org,
	"Brandeburg, Jesse" <jesse.brandeburg@...el.com>,
	"Kok, Auke" <auke-jan.h.kok@...el.com>,
	"Kok, Auke" <auke@...-projects.org>,
	"Ronciak, John" <john.ronciak@...el.com>
Subject: [PATCH 4/8] e1000: fix NAPI performance on 4-port adapters


This fix attempts to solve a customer (IBM) reported issue with NAPI
enabled e1000 having bad performance when transmitting simultaneously
on four ports.  The issue comes down to an interaction between NAPI,
hardware interrupt balancing, and the driver rescheduling poll on
the same processor.  Try to fix by allowing the driver to re-enable
interrupts sooner instead of polling one more time, when there was
recently all the work completed in cleanup.

Signed-off-by: Jesse Brandeburg <jesse.brandeburg@...el.com>
Signed-off-by: Auke Kok <auke-jan.h.kok@...el.com>
---

 drivers/net/e1000/e1000_main.c |   13 ++++++++-----
 1 files changed, 8 insertions(+), 5 deletions(-)

diff --git a/drivers/net/e1000/e1000_main.c b/drivers/net/e1000/e1000_main.c
index d408949..ab1b40f 100644
--- a/drivers/net/e1000/e1000_main.c
+++ b/drivers/net/e1000/e1000_main.c
@@ -3814,7 +3814,7 @@ e1000_intr_msi(int irq, void *data)
 
 	for (i = 0; i < E1000_MAX_INTR; i++)
 		if (unlikely(!adapter->clean_rx(adapter, adapter->rx_ring) &
-		   !e1000_clean_tx_irq(adapter, adapter->tx_ring)))
+		   e1000_clean_tx_irq(adapter, adapter->tx_ring)))
 			break;
 
 	if (likely(adapter->itr_setting & 3))
@@ -3917,7 +3917,7 @@ e1000_intr(int irq, void *data)
 
 	for (i = 0; i < E1000_MAX_INTR; i++)
 		if (unlikely(!adapter->clean_rx(adapter, adapter->rx_ring) &
-		   !e1000_clean_tx_irq(adapter, adapter->tx_ring)))
+		   e1000_clean_tx_irq(adapter, adapter->tx_ring)))
 			break;
 
 	if (likely(adapter->itr_setting & 3))
@@ -3967,7 +3967,7 @@ e1000_clean(struct net_device *poll_dev, int *budget)
 	poll_dev->quota -= work_done;
 
 	/* If no Tx and not enough Rx work done, exit the polling mode */
-	if ((!tx_cleaned && (work_done == 0)) ||
+	if ((tx_cleaned && (work_done < work_to_do)) ||
 	   !netif_running(poll_dev)) {
 quit_polling:
 		if (likely(adapter->itr_setting & 3))
@@ -3997,7 +3997,7 @@ e1000_clean_tx_irq(struct e1000_adapter *adapter,
 #ifdef CONFIG_E1000_NAPI
 	unsigned int count = 0;
 #endif
-	boolean_t cleaned = FALSE;
+	boolean_t cleaned = TRUE;
 	unsigned int total_tx_bytes=0, total_tx_packets=0;
 
 	i = tx_ring->next_to_clean;
@@ -4028,7 +4028,10 @@ e1000_clean_tx_irq(struct e1000_adapter *adapter,
 #ifdef CONFIG_E1000_NAPI
 #define E1000_TX_WEIGHT 64
 		/* weight of a sort for tx, to avoid endless transmit cleanup */
-		if (count++ == E1000_TX_WEIGHT) break;
+		if (count++ == E1000_TX_WEIGHT) {
+			cleaned = FALSE;
+			break;
+		}
 #endif
 	}
 



---
Auke Kok <auke-jan.h.kok@...el.com>
-
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html