Re: [RFC PATCH v3 3/7] proc: Reduce cache miss in snmp6_seq_show
On 9/13/16 3:05 AM, Marcelo wrote: On Fri, Sep 09, 2016 at 02:33:58PM +0800, Jia He wrote: This is to use the generic interface snmp_get_cpu_field{,64}_batch to aggregate the data by going through all the items of each cpu sequentially. Signed-off-by: Jia He--- net/ipv6/proc.c | 32 +++- 1 file changed, 23 insertions(+), 9 deletions(-) diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c index 679253d0..50ba2c3 100644 --- a/net/ipv6/proc.c +++ b/net/ipv6/proc.c @@ -30,6 +30,11 @@ #include #include +#define MAX4(a, b, c, d) \ + max_t(u32, max_t(u32, a, b), max_t(u32, c, d)) +#define SNMP_MIB_MAX MAX4(UDP_MIB_MAX, TCP_MIB_MAX, \ + IPSTATS_MIB_MAX, ICMP_MIB_MAX) + static int sockstat6_seq_show(struct seq_file *seq, void *v) { struct net *net = seq->private; @@ -192,13 +197,19 @@ static void snmp6_seq_show_item(struct seq_file *seq, void __percpu *pcpumib, const struct snmp_mib *itemlist) { int i; - unsigned long val; - - for (i = 0; itemlist[i].name; i++) { - val = pcpumib ? - snmp_fold_field(pcpumib, itemlist[i].entry) : - atomic_long_read(smib + itemlist[i].entry); - seq_printf(seq, "%-32s\t%lu\n", itemlist[i].name, val); + unsigned long buff[SNMP_MIB_MAX]; + + memset(buff, 0, sizeof(unsigned long) * SNMP_MIB_MAX); This memset() could be moved... + + if (pcpumib) { ... here, so it's not executed if it hits the else block. Thanks for the suggestion B.R. Jia + snmp_get_cpu_field_batch(buff, itemlist, pcpumib); + for (i = 0; itemlist[i].name; i++) + seq_printf(seq, "%-32s\t%lu\n", + itemlist[i].name, buff[i]); + } else { + for (i = 0; itemlist[i].name; i++) + seq_printf(seq, "%-32s\t%lu\n", itemlist[i].name, + atomic_long_read(smib + itemlist[i].entry)); } } @@ -206,10 +217,13 @@ static void snmp6_seq_show_item64(struct seq_file *seq, void __percpu *mib, const struct snmp_mib *itemlist, size_t syncpoff) { int i; + u64 buff64[SNMP_MIB_MAX]; + + memset(buff64, 0, sizeof(unsigned long) * SNMP_MIB_MAX); + snmp_get_cpu_field64_batch(buff64, itemlist, mib, syncpoff); for (i = 0; itemlist[i].name; i++) - seq_printf(seq, "%-32s\t%llu\n", itemlist[i].name, - snmp_fold_field64(mib, itemlist[i].entry, syncpoff)); + seq_printf(seq, "%-32s\t%llu\n", itemlist[i].name, buff64[i]); } static int snmp6_seq_show(struct seq_file *seq, void *v) -- 1.8.3.1 -- To unsubscribe from this list: send the line "unsubscribe linux-sctp" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: [RFC PATCH v3 3/7] proc: Reduce cache miss in snmp6_seq_show
On Fri, Sep 09, 2016 at 02:33:58PM +0800, Jia He wrote: > This is to use the generic interface snmp_get_cpu_field{,64}_batch to > aggregate the data by going through all the items of each cpu sequentially. > > Signed-off-by: Jia He> --- > net/ipv6/proc.c | 32 +++- > 1 file changed, 23 insertions(+), 9 deletions(-) > > diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c > index 679253d0..50ba2c3 100644 > --- a/net/ipv6/proc.c > +++ b/net/ipv6/proc.c > @@ -30,6 +30,11 @@ > #include > #include > > +#define MAX4(a, b, c, d) \ > + max_t(u32, max_t(u32, a, b), max_t(u32, c, d)) > +#define SNMP_MIB_MAX MAX4(UDP_MIB_MAX, TCP_MIB_MAX, \ > + IPSTATS_MIB_MAX, ICMP_MIB_MAX) > + > static int sockstat6_seq_show(struct seq_file *seq, void *v) > { > struct net *net = seq->private; > @@ -192,13 +197,19 @@ static void snmp6_seq_show_item(struct seq_file *seq, > void __percpu *pcpumib, > const struct snmp_mib *itemlist) > { > int i; > - unsigned long val; > - > - for (i = 0; itemlist[i].name; i++) { > - val = pcpumib ? > - snmp_fold_field(pcpumib, itemlist[i].entry) : > - atomic_long_read(smib + itemlist[i].entry); > - seq_printf(seq, "%-32s\t%lu\n", itemlist[i].name, val); > + unsigned long buff[SNMP_MIB_MAX]; > + > + memset(buff, 0, sizeof(unsigned long) * SNMP_MIB_MAX); This memset() could be moved... > + > + if (pcpumib) { ... here, so it's not executed if it hits the else block. > + snmp_get_cpu_field_batch(buff, itemlist, pcpumib); > + for (i = 0; itemlist[i].name; i++) > + seq_printf(seq, "%-32s\t%lu\n", > +itemlist[i].name, buff[i]); > + } else { > + for (i = 0; itemlist[i].name; i++) > + seq_printf(seq, "%-32s\t%lu\n", itemlist[i].name, > +atomic_long_read(smib + itemlist[i].entry)); > } > } > > @@ -206,10 +217,13 @@ static void snmp6_seq_show_item64(struct seq_file *seq, > void __percpu *mib, > const struct snmp_mib *itemlist, size_t > syncpoff) > { > int i; > + u64 buff64[SNMP_MIB_MAX]; > + > + memset(buff64, 0, sizeof(unsigned long) * SNMP_MIB_MAX); > > + snmp_get_cpu_field64_batch(buff64, itemlist, mib, syncpoff); > for (i = 0; itemlist[i].name; i++) > - seq_printf(seq, "%-32s\t%llu\n", itemlist[i].name, > -snmp_fold_field64(mib, itemlist[i].entry, syncpoff)); > + seq_printf(seq, "%-32s\t%llu\n", itemlist[i].name, buff64[i]); > } > > static int snmp6_seq_show(struct seq_file *seq, void *v) > -- > 1.8.3.1 > > -- > To unsubscribe from this list: send the line "unsubscribe linux-sctp" in > the body of a message to majord...@vger.kernel.org > More majordomo info at http://vger.kernel.org/majordomo-info.html >
[RFC PATCH v3 3/7] proc: Reduce cache miss in snmp6_seq_show
This is to use the generic interface snmp_get_cpu_field{,64}_batch to aggregate the data by going through all the items of each cpu sequentially. Signed-off-by: Jia He--- net/ipv6/proc.c | 32 +++- 1 file changed, 23 insertions(+), 9 deletions(-) diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c index 679253d0..50ba2c3 100644 --- a/net/ipv6/proc.c +++ b/net/ipv6/proc.c @@ -30,6 +30,11 @@ #include #include +#define MAX4(a, b, c, d) \ + max_t(u32, max_t(u32, a, b), max_t(u32, c, d)) +#define SNMP_MIB_MAX MAX4(UDP_MIB_MAX, TCP_MIB_MAX, \ + IPSTATS_MIB_MAX, ICMP_MIB_MAX) + static int sockstat6_seq_show(struct seq_file *seq, void *v) { struct net *net = seq->private; @@ -192,13 +197,19 @@ static void snmp6_seq_show_item(struct seq_file *seq, void __percpu *pcpumib, const struct snmp_mib *itemlist) { int i; - unsigned long val; - - for (i = 0; itemlist[i].name; i++) { - val = pcpumib ? - snmp_fold_field(pcpumib, itemlist[i].entry) : - atomic_long_read(smib + itemlist[i].entry); - seq_printf(seq, "%-32s\t%lu\n", itemlist[i].name, val); + unsigned long buff[SNMP_MIB_MAX]; + + memset(buff, 0, sizeof(unsigned long) * SNMP_MIB_MAX); + + if (pcpumib) { + snmp_get_cpu_field_batch(buff, itemlist, pcpumib); + for (i = 0; itemlist[i].name; i++) + seq_printf(seq, "%-32s\t%lu\n", + itemlist[i].name, buff[i]); + } else { + for (i = 0; itemlist[i].name; i++) + seq_printf(seq, "%-32s\t%lu\n", itemlist[i].name, + atomic_long_read(smib + itemlist[i].entry)); } } @@ -206,10 +217,13 @@ static void snmp6_seq_show_item64(struct seq_file *seq, void __percpu *mib, const struct snmp_mib *itemlist, size_t syncpoff) { int i; + u64 buff64[SNMP_MIB_MAX]; + + memset(buff64, 0, sizeof(unsigned long) * SNMP_MIB_MAX); + snmp_get_cpu_field64_batch(buff64, itemlist, mib, syncpoff); for (i = 0; itemlist[i].name; i++) - seq_printf(seq, "%-32s\t%llu\n", itemlist[i].name, - snmp_fold_field64(mib, itemlist[i].entry, syncpoff)); + seq_printf(seq, "%-32s\t%llu\n", itemlist[i].name, buff64[i]); } static int snmp6_seq_show(struct seq_file *seq, void *v) -- 1.8.3.1