Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1471955 > unrolled thread

[RFC PATCH 1/6] proc: Reduce cache miss in {snmp,netstat}_seq_show

Back to article view | Back to linux.kernel

This discussion starts older than the indexed window; earlier articles aren't shown. The article labeled Started by below is the oldest one visible, not the original post.

Contents

  [RFC PATCH 1/6] proc: Reduce cache miss in {snmp,netstat}_seq_show Jia He <hejianet@gmail.com> - 2016-08-29 18:10 +0200
    Re: [RFC PATCH 1/6] proc: Reduce cache miss in  {snmp,netstat}_seq_show Eric Dumazet <eric.dumazet@gmail.com> - 2016-08-29 18:50 +0200
      Re: [RFC PATCH 1/6] proc: Reduce cache miss in  {snmp,netstat}_seq_show hejianet <hejianet@gmail.com> - 2016-08-30 10:20 +0200

#1471955 — [RFC PATCH 1/6] proc: Reduce cache miss in {snmp,netstat}_seq_show

This patch exchanges the two loop for collecting the percpu statistics
data. This can aggregate the data by going through all the items of each
cpu sequentially. In snmp_seq_show, just use one buff copy to dislay the
Udp and UdpLite data because they are the same.

Signed-off-by: Jia He <hejianet@gmail.com>
---
 net/ipv4/proc.c | 78 ++++++++++++++++++++++++++++++++++++---------------------
 1 file changed, 50 insertions(+), 28 deletions(-)

diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index 9f665b6..ed09566 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -380,11 +380,15 @@ static void icmp_put(struct seq_file *seq)
  */
 static int snmp_seq_show(struct seq_file *seq, void *v)
 {
-	int i;
+	int i, c;
+	unsigned long buff[TCP_MIB_MAX];
+	u64 buff64[IPSTATS_MIB_MAX];
 	struct net *net = seq->private;
 
-	seq_puts(seq, "Ip: Forwarding DefaultTTL");
+	memset(buff, 0, TCP_MIB_MAX * sizeof(unsigned long));
+	memset(buff64, 0, IPSTATS_MIB_MAX * sizeof(u64));
 
+	seq_puts(seq, "Ip: Forwarding DefaultTTL");
 	for (i = 0; snmp4_ipstats_list[i].name != NULL; i++)
 		seq_printf(seq, " %s", snmp4_ipstats_list[i].name);
 
@@ -393,11 +397,16 @@ static int snmp_seq_show(struct seq_file *seq, void *v)
 		   net->ipv4.sysctl_ip_default_ttl);
 
 	BUILD_BUG_ON(offsetof(struct ipstats_mib, mibs) != 0);
+
+	for_each_possible_cpu(c) {
+		for (i = 0; snmp4_ipstats_list[i].name != NULL; i++)
+			buff64[i] += snmp_get_cpu_field64(
+					net->mib.ip_statistics,
+					c, snmp4_ipstats_list[i].entry,
+					offsetof(struct ipstats_mib, syncp));
+	}
 	for (i = 0; snmp4_ipstats_list[i].name != NULL; i++)
-		seq_printf(seq, " %llu",
-			   snmp_fold_field64(net->mib.ip_statistics,
-					     snmp4_ipstats_list[i].entry,
-					     offsetof(struct ipstats_mib, syncp)));
+		seq_printf(seq, " %llu", buff64[i]);
 
 	icmp_put(seq);	/* RFC 2011 compatibility */
 	icmpmsg_put(seq);
@@ -407,38 +416,41 @@ static int snmp_seq_show(struct seq_file *seq, void *v)
 		seq_printf(seq, " %s", snmp4_tcp_list[i].name);
 
 	seq_puts(seq, "\nTcp:");
+	for_each_possible_cpu(c) {
+		for (i = 0; snmp4_tcp_list[i].name != NULL; i++)
+			buff[i] += snmp_get_cpu_field(net->mib.tcp_statistics,
+						c, snmp4_tcp_list[i].entry);
+	}
+
 	for (i = 0; snmp4_tcp_list[i].name != NULL; i++) {
 		/* MaxConn field is signed, RFC 2012 */
 		if (snmp4_tcp_list[i].entry == TCP_MIB_MAXCONN)
-			seq_printf(seq, " %ld",
-				   snmp_fold_field(net->mib.tcp_statistics,
-						   snmp4_tcp_list[i].entry));
+			seq_printf(seq, " %ld", buff[i]);
 		else
-			seq_printf(seq, " %lu",
-				   snmp_fold_field(net->mib.tcp_statistics,
-						   snmp4_tcp_list[i].entry));
+			seq_printf(seq, " %lu", buff[i]);
 	}
 
+	memset(buff, 0, TCP_MIB_MAX * sizeof(unsigned long));
+
+	for_each_possible_cpu(c) {
+		for (i = 0; snmp4_udp_list[i].name != NULL; i++)
+			buff[i] += snmp_get_cpu_field(net->mib.udp_statistics,
+						c, snmp4_udp_list[i].entry);
+	}
 	seq_puts(seq, "\nUdp:");
 	for (i = 0; snmp4_udp_list[i].name != NULL; i++)
 		seq_printf(seq, " %s", snmp4_udp_list[i].name);
-
 	seq_puts(seq, "\nUdp:");
 	for (i = 0; snmp4_udp_list[i].name != NULL; i++)
-		seq_printf(seq, " %lu",
-			   snmp_fold_field(net->mib.udp_statistics,
-					   snmp4_udp_list[i].entry));
+		seq_printf(seq, " %lu", buff[i]);
 
 	/* the UDP and UDP-Lite MIBs are the same */
 	seq_puts(seq, "\nUdpLite:");
 	for (i = 0; snmp4_udp_list[i].name != NULL; i++)
 		seq_printf(seq, " %s", snmp4_udp_list[i].name);
-
 	seq_puts(seq, "\nUdpLite:");
 	for (i = 0; snmp4_udp_list[i].name != NULL; i++)
-		seq_printf(seq, " %lu",
-			   snmp_fold_field(net->mib.udplite_statistics,
-					   snmp4_udp_list[i].entry));
+		seq_printf(seq, " %lu", buff[i]);
 
 	seq_putc(seq, '\n');
 	return 0;
@@ -464,29 +476,39 @@ static const struct file_operations snmp_seq_fops = {
  */
 static int netstat_seq_show(struct seq_file *seq, void *v)
 {
-	int i;
+	int i, c;
+	unsigned long buff[LINUX_MIB_MAX];
+	u64 buff64[IPSTATS_MIB_MAX];
 	struct net *net = seq->private;
 
+	memset(buff, 0, sizeof(unsigned long) * LINUX_MIB_MAX);
+	memset(buff64, 0, sizeof(u64) * IPSTATS_MIB_MAX);
+
 	seq_puts(seq, "TcpExt:");
 	for (i = 0; snmp4_net_list[i].name != NULL; i++)
 		seq_printf(seq, " %s", snmp4_net_list[i].name);
 
 	seq_puts(seq, "\nTcpExt:");
+	for_each_possible_cpu(c)
+		for (i = 0; snmp4_net_list[i].name != NULL; i++)
+			buff[i] += snmp_get_cpu_field(net->mib.net_statistics,
+						c, snmp4_net_list[i].entry);
 	for (i = 0; snmp4_net_list[i].name != NULL; i++)
-		seq_printf(seq, " %lu",
-			   snmp_fold_field(net->mib.net_statistics,
-					   snmp4_net_list[i].entry));
+		seq_printf(seq, " %lu", buff[i]);
 
 	seq_puts(seq, "\nIpExt:");
 	for (i = 0; snmp4_ipextstats_list[i].name != NULL; i++)
 		seq_printf(seq, " %s", snmp4_ipextstats_list[i].name);
 
 	seq_puts(seq, "\nIpExt:");
+	for_each_possible_cpu(c)
+		for (i = 0; snmp4_ipextstats_list[i].name != NULL; i++)
+			buff64[i] += snmp_get_cpu_field64(
+					net->mib.ip_statistics,
+					c, snmp4_ipextstats_list[i].entry,
+					offsetof(struct ipstats_mib, syncp));
 	for (i = 0; snmp4_ipextstats_list[i].name != NULL; i++)
-		seq_printf(seq, " %llu",
-			   snmp_fold_field64(net->mib.ip_statistics,
-					     snmp4_ipextstats_list[i].entry,
-					     offsetof(struct ipstats_mib, syncp)));
+		seq_printf(seq, " %llu", buff64[i]);
 
 	seq_putc(seq, '\n');
 	return 0;
-- 
1.8.3.1

[toc] | [next] | [standalone]

#1471982 — Re: [RFC PATCH 1/6] proc: Reduce cache miss in {snmp,netstat}_seq_show

On Tue, 2016-08-30 at 00:03 +0800, Jia He wrote:
> This patch exchanges the two loop for collecting the percpu statistics
> data. This can aggregate the data by going through all the items of each
> cpu sequentially. In snmp_seq_show, just use one buff copy to dislay the
> Udp and UdpLite data because they are the same.

This is obviously not true.

On my laptop it seems it handled no UdpLite frames, but got plenty of
Udp ones.

$ grep Udp /proc/net/snmp
Udp: InDatagrams NoPorts InErrors OutDatagrams RcvbufErrors SndbufErrors InCsumErrors
Udp: 1555889 108318 0 3740780 0 0 0
UdpLite: InDatagrams NoPorts InErrors OutDatagrams RcvbufErrors SndbufErrors InCsumErrors
UdpLite: 0 0 0 0 0 0 0

[toc] | [prev] | [next] | [standalone]

#1472303 — Re: [RFC PATCH 1/6] proc: Reduce cache miss in {snmp,netstat}_seq_show

Hi Eric


On 8/30/16 12:41 AM, Eric Dumazet wrote:
> On Tue, 2016-08-30 at 00:03 +0800, Jia He wrote:
>> This patch exchanges the two loop for collecting the percpu statistics
>> data. This can aggregate the data by going through all the items of each
>> cpu sequentially. In snmp_seq_show, just use one buff copy to dislay the
>> Udp and UdpLite data because they are the same.
> This is obviously not true.
>
> On my laptop it seems it handled no UdpLite frames, but got plenty of
> Udp ones.
>
> $ grep Udp /proc/net/snmp
> Udp: InDatagrams NoPorts InErrors OutDatagrams RcvbufErrors SndbufErrors InCsumErrors
> Udp: 1555889 108318 0 3740780 0 0 0
> UdpLite: InDatagrams NoPorts InErrors OutDatagrams RcvbufErrors SndbufErrors InCsumErrors
> UdpLite: 0 0 0 0 0 0 0
Thanks, you are right. I misunderstand the comments of source codes.
Will resend it

B.R.
Jia
>
>
>
> .
>

[toc] | [prev] | [standalone]

Back to top | Article view | linux.kernel

csiph-web