| 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
| ||
|
Message-ID: <18595.15208.734736.864386@robur.slu.se>
Date: Wed, 13 Aug 2008 21:52:08 +0200
From: Robert Olsson <robert@...ur.slu.se>
To: Andrew Gallatin <gallatin@...i.com>
Cc: David Miller <davem@...emloft.net>, netdev@...r.kernel.org,
Robert.Olsson@...a.slu.se
Subject: Re: CPU utilization increased in 2.6.27rc
Andrew Gallatin writes:
>
> Excellent! This completely fixes the increased CPU
> utilization I observed on both 10GbE and 1GbE interfaces,
> and CPU utilization is now reduced back to 2.6.26 levels.
> > Robert, this could explain some of the things in the
> > multiqueue testing profile you sent me a week or so
> > ago.
I've just rerun the virtual 10g router experiment with the current
git including the pkt_sched patch. The full experiment is below. In this
case the profile looks the same as before. No improvement due to this
patch here.
In this case we have not any old numbers to compare with as we're
testing new functionality. I'm not to unhappy about the performance
and there must be some functions the in profile...
Virtual IP forwarding experiment. We're splitting an incoming flow
load (10g) among 4 CPU's and keep the incoming flows per-CPU including
TX and also skb clearing
Network flow load into (eth0) 10G 82598. Total 295+293+293+220 kpps
4 * (4096 concurrent flows at 30 pkts)
eth0 1500 0 3996889 0 1280 0 19 0 0 0 BMRU
eth1 1500 0 1 0 0 0 3998236 0 0 0 BMRU
I've configured RSS with ixgbe so all 4 CPU's are used and hacked driver
so skb gets tagged with incoming CPU. The 2:nd col in softnet_stat is used
to verify tagging and affinity is correct until hard_xmit and even for TX-skb
cleaning to avoid all cache misses and true per-CPU forwarding. The ixgbe driver
1.3.31.5 from Intel's site is needed for RSS etc and bit modified for this test.
softnet_stat
000f3236 001e63f8 00000872 00000000 00000000 00000000 00000000 00000000 00000000
000f52df 001ea58c 000008b8 00000000 00000000 00000000 00000000 00000000 00000000
000f3d90 001e7af8 00000a3b 00000000 00000000 00000000 00000000 00000000 00000000
000f4174 001e82c2 00000a17 00000000 00000000 00000000 00000000 00000000 00000000
eth0 (incoming)
214: 4 0 0 6623 PCI-MSI-edge eth0:v3-Rx
215: 0 5 6635 0 PCI-MSI-edge eth0:v2-Rx
216: 0 7152 5 0 PCI-MSI-edge eth0:v1-Rx
217: 7115 0 0 5 PCI-MSI-edge eth0:v0-Rx
eth1 (outgoing)
201: 3 0 0 3738 PCI-MSI-edge eth1:v7-Tx
202: 0 4 3743 0 PCI-MSI-edge eth1:v6-Tx
203: 0 3743 4 0 PCI-MSI-edge eth1:v5-Tx
204: 3746 0 0 6 PCI-MSI-edge eth1:v4-Tx
CPU: AMD64 processors, speed 3000 MHz (estimated)
Counted CPU_CLK_UNHALTED events (Cycles outside of halt state) with a unit mask of 0x00 (No unit mask) count 3000
samples % image name app name symbol name
407896 8.7211 vmlinux vmlinux cache_alloc_refill
339524 7.2592 vmlinux vmlinux __qdisc_run
243352 5.2030 vmlinux vmlinux dev_queue_xmit
227855 4.8717 vmlinux vmlinux kfree
214975 4.5963 vmlinux vmlinux __alloc_skb
172008 3.6776 vmlinux vmlinux cache_flusharray
168307 3.5985 vmlinux vmlinux ip_route_input
160995 3.4422 vmlinux vmlinux dev_kfree_skb_irq
146116 3.1240 vmlinux vmlinux netif_receive_skb
137763 2.9455 vmlinux vmlinux free_block
133732 2.8593 vmlinux vmlinux eth_type_trans
124262 2.6568 vmlinux vmlinux ip_rcv
110170 2.3555 vmlinux vmlinux list_del
100508 2.1489 vmlinux vmlinux ip_finish_output
96777 2.0691 vmlinux vmlinux ip_forward
89212 1.9074 vmlinux vmlinux check_addr
diff --git a/net/core/dev.c b/net/core/dev.c
index 8d13a9b..6fdf427 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1714,6 +1714,9 @@ static struct netdev_queue *dev_pick_tx(struct net_device *dev,
{
u16 queue_index = 0;
+ if (dev->real_num_tx_queues > 1)
+ return netdev_get_tx_queue(dev, skb->queue_mapping);
+
if (dev->select_queue)
queue_index = dev->select_queue(dev, skb);
else if (dev->real_num_tx_queues > 1)
@@ -4872,3 +4875,4 @@ EXPORT_SYMBOL(dev_load);
#endif
EXPORT_PER_CPU_SYMBOL(softnet_data);
+EXPORT_PER_CPU_SYMBOL(netdev_rx_stat);
--- ixgbe.h.orig 2008-07-30 13:11:46.000000000 +0200
+++ ixgbe.h 2008-07-30 17:42:59.000000000 +0200
@@ -28,6 +28,8 @@
#ifndef _IXGBE_H_
#define _IXGBE_H_
+#define CONFIG_NETDEVICES_MULTIQUEUE
+
#include <linux/pci.h>
#include <linux/netdevice.h>
#include <linux/vmalloc.h>
@@ -106,6 +108,10 @@
#define IXGBE_TX_FLAGS_VLAN_PRIO_MASK 0x0000e000
#define IXGBE_TX_FLAGS_VLAN_SHIFT 16
+#define IXGBE_NO_LRO
+#define IXGBE_NAPI
+#define CONFIG_IXGBE_NAPI
+
#ifndef IXGBE_NO_LRO
#define IXGBE_LRO_MAX 32 /*Maximum number of LRO descriptors*/
#define IXGBE_LRO_GLOBAL 10
--- ixgbe_main.c.orig 2008-07-30 13:12:02.000000000 +0200
+++ ixgbe_main.c 2008-07-30 19:26:07.000000000 +0200
@@ -71,7 +71,7 @@
#endif
-#define BASE_VERSION "1.3.31.5"
+#define BASE_VERSION "1.3.31.5-080730"
#define DRV_VERSION BASE_VERSION LRO DRIVERNAPI DRV_HW_PERF
char ixgbe_driver_version[] = DRV_VERSION;
@@ -257,6 +257,9 @@
total_packets++;
total_bytes += skb->len;
#endif
+ if(skb->queue_mapping == smp_processor_id())
+ __get_cpu_var(netdev_rx_stat).dropped++;
+
}
ixgbe_unmap_and_free_tx_resource(adapter,
@@ -426,6 +429,9 @@
struct sk_buff *skb, bool is_vlan, u16 tag)
{
int ret;
+
+ skb->queue_mapping = smp_processor_id();
+
#ifdef CONFIG_IXGBE_NAPI
if (!(adapter->flags & IXGBE_FLAG_IN_NETPOLL)) {
#ifdef NETIF_F_HW_VLAN_TX
@@ -2875,7 +2881,11 @@
rss_i = min(4, rss_i);
rss_m = 0x3;
nrq = dcb_i * vmdq_i * rss_i;
+#ifdef CONFIG_NETDEVICES_MULTIQUEUE
+ ntq = nrq;
+#else
ntq = dcb_i * vmdq_i;
+#endif
break;
case (IXGBE_FLAG_VMDQ_ENABLED | IXGBE_FLAG_DCB_ENABLED):
dcb_m = 0x7 << 3;
@@ -3242,7 +3252,7 @@
out:
#ifdef CONFIG_NETDEVICES_MULTIQUEUE
/* Notify the stack of the (possibly) reduced Tx Queue count. */
- adapter->netdev->egress_subqueue_count = adapter->num_tx_queues;
+ // adapter->netdev->egress_subqueue_count = adapter->num_tx_queues;
#endif
return err;
@@ -3794,6 +3804,8 @@
}
#endif /* CONFIG_PM */
+extern DEFINE_PER_CPU(struct netif_rx_stats, netdev_rx_stat);
+
static int ixgbe_suspend(struct pci_dev *pdev, pm_message_t state)
{
struct net_device *netdev = pci_get_drvdata(pdev);
@@ -4402,6 +4414,9 @@
#ifdef CONFIG_NETDEVICES_MULTIQUEUE
r_idx = (adapter->num_tx_queues - 1) & skb->queue_mapping;
+
+ if(skb->queue_mapping == smp_processor_id())
+ __get_cpu_var(netdev_rx_stat).dropped++;
#endif
tx_ring = &adapter->tx_ring[r_idx];
Cheers.
--ro
--
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
Powered by blists - more mailing lists