| Message ID | 20200807212916.2883031-7-jwadams@google.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | metricfs metric file system and examples | expand |
Jonathan Adams <jwadams@google.com> writes: How is that related to core? The x86 subsys prefix is 'x86' and for this particular thing it's 'x86/irq:'. That applies to the rest of the series as well. > Add metricfs support for displaying percpu irq counters for x86. > The top directory is /sys/kernel/debug/metricfs/irq_x86. > Then there is a subdirectory for each x86-specific irq counter. > For example: > > cat /sys/kernel/debug/metricfs/irq_x86/TLB/values What is 'TLB'? I'm not aware of any vector which is named TLB. The changelog is pretty useless in providing any form of rationale for this. It tells the WHAT, but not the WHY. Also what is does this file contain? Aggregates, one line per CPU or the value of the random CPU of the day? I'm not going to dive into the macro zoo to figure that out. > jwadams@google.com: rebased to 5.8-pre6 > This is work originally done by another engineer at > google, who would rather not have their name associated with > this patchset. They're okay with me sending it under my name. I can understand why they wont have their name associated with this. > +#ifdef CONFIG_METRICFS > +METRICFS_ITEM(NMI, __nmi_count, "Non-maskable interrupts"); > +#ifdef CONFIG_X86_LOCAL_APIC > +METRICFS_ITEM(LOC, apic_timer_irqs, "Local timer interrupts"); > +METRICFS_ITEM(SPU, irq_spurious_count, "Spurious interrupts"); > +METRICFS_ITEM(PMI, apic_perf_irqs, "Performance monitoring interrupts"); > +METRICFS_ITEM(IWI, apic_irq_work_irqs, "IRQ work interrupts"); > +METRICFS_ITEM(RTR, icr_read_retry_count, "APIC ICR read retries"); > +#endif .... So you are adding NR_CPUS * NR_DIRECT_VECTORS debugfs files which show exactly the same information as /proc/interrupts, right? Aside of that _all_ of this information is available via tracepoints as well. That's NR_CPUS * 15 and incomplete because x86 has 23 of those directly handled vectors which do not go through the irq core. So with just 15 and 256 CPUs that's 3840 files. Impressive number especially without any information why this is useful and provides value over the existing mechanisms to retrieve exactly the same information. The cover letter talks a lot about who Google finds this useful, but that's not really a convincing argument for this metric failsystem addon. Thanks, tglx
On 13/08/20 12:11, Thomas Gleixner wrote: >> Add metricfs support for displaying percpu irq counters for x86. >> The top directory is /sys/kernel/debug/metricfs/irq_x86. >> Then there is a subdirectory for each x86-specific irq counter. >> For example: >> >> cat /sys/kernel/debug/metricfs/irq_x86/TLB/values > What is 'TLB'? I'm not aware of any vector which is named TLB. There's a "TLB" entry in /proc/interrupts. Paolo
Paolo Bonzini <pbonzini@redhat.com> writes: > On 13/08/20 12:11, Thomas Gleixner wrote: >>> Add metricfs support for displaying percpu irq counters for x86. >>> The top directory is /sys/kernel/debug/metricfs/irq_x86. >>> Then there is a subdirectory for each x86-specific irq counter. >>> For example: >>> >>> cat /sys/kernel/debug/metricfs/irq_x86/TLB/values >> What is 'TLB'? I'm not aware of any vector which is named TLB. > > There's a "TLB" entry in /proc/interrupts. It's TLB shootdowns and not TLB. Thanks, tglx
On 13/08/20 14:13, Thomas Gleixner wrote: >>>> Add metricfs support for displaying percpu irq counters for x86. >>>> The top directory is /sys/kernel/debug/metricfs/irq_x86. >>>> Then there is a subdirectory for each x86-specific irq counter. >>>> For example: >>>> >>>> cat /sys/kernel/debug/metricfs/irq_x86/TLB/values >>> What is 'TLB'? I'm not aware of any vector which is named TLB. >> There's a "TLB" entry in /proc/interrupts. > It's TLB shootdowns and not TLB. Yes but it's using the shortcut name on the left of the table. > +METRICFS_ITEM(LOC, apic_timer_irqs, "Local timer interrupts"); > +METRICFS_ITEM(SPU, irq_spurious_count, "Spurious interrupts"); > +METRICFS_ITEM(PMI, apic_perf_irqs, "Performance monitoring interrupts"); > +METRICFS_ITEM(IWI, apic_irq_work_irqs, "IRQ work interrupts"); > +METRICFS_ITEM(RTR, icr_read_retry_count, "APIC ICR read retries"); > +#endif > +METRICFS_ITEM(PLT, x86_platform_ipis, "Platform interrupts"); > +#ifdef CONFIG_SMP > +METRICFS_ITEM(RES, irq_resched_count, "Rescheduling interrupts"); > +METRICFS_ITEM(CAL, irq_call_count, "Function call interrupts"); > +METRICFS_ITEM(TLB, irq_tlb_count, "TLB shootdowns"); Paolo
Paolo Bonzini <pbonzini@redhat.com> writes: > On 13/08/20 14:13, Thomas Gleixner wrote: >>>>> cat /sys/kernel/debug/metricfs/irq_x86/TLB/values >>>> What is 'TLB'? I'm not aware of any vector which is named TLB. >>> There's a "TLB" entry in /proc/interrupts. >> It's TLB shootdowns and not TLB. > > Yes but it's using the shortcut name on the left of the table. Fair enough, that's the first column in /proc/interrupts. I totally missed the explanation in the elaborate changelog. Thanks, tglx
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 181060247e3c..ffacbbc4066c 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -12,6 +12,7 @@ #include <linux/delay.h> #include <linux/export.h> #include <linux/irq.h> +#include <linux/metricfs.h> #include <asm/irq_stack.h> #include <asm/apic.h> @@ -374,3 +375,82 @@ void fixup_irqs(void) } } #endif + +#ifdef CONFIG_METRICFS +#define METRICFS_ITEM(name, field, desc) \ +static void \ +metricfs_##name(struct metric_emitter *e, int cpu) \ +{ \ + int64_t v = irq_stats(cpu)->field; \ + METRIC_EMIT_PERCPU_INT(e, cpu, v); \ +} \ +METRIC_EXPORT_PERCPU_COUNTER(name, desc, metricfs_##name) + +METRICFS_ITEM(NMI, __nmi_count, "Non-maskable interrupts"); +#ifdef CONFIG_X86_LOCAL_APIC +METRICFS_ITEM(LOC, apic_timer_irqs, "Local timer interrupts"); +METRICFS_ITEM(SPU, irq_spurious_count, "Spurious interrupts"); +METRICFS_ITEM(PMI, apic_perf_irqs, "Performance monitoring interrupts"); +METRICFS_ITEM(IWI, apic_irq_work_irqs, "IRQ work interrupts"); +METRICFS_ITEM(RTR, icr_read_retry_count, "APIC ICR read retries"); +#endif +METRICFS_ITEM(PLT, x86_platform_ipis, "Platform interrupts"); +#ifdef CONFIG_SMP +METRICFS_ITEM(RES, irq_resched_count, "Rescheduling interrupts"); +METRICFS_ITEM(CAL, irq_call_count, "Function call interrupts"); +METRICFS_ITEM(TLB, irq_tlb_count, "TLB shootdowns"); +#endif +#ifdef CONFIG_X86_THERMAL_VECTOR +METRICFS_ITEM(TRM, irq_thermal_count, "Thermal event interrupts"); +#endif +#ifdef CONFIG_X86_MCE_THRESHOLD +METRICFS_ITEM(THR, irq_threshold_count, "Threshold APIC interrupts"); +#endif +#ifdef CONFIG_X86_MCE_AMD +METRICFS_ITEM(DFR, irq_deferred_error_count, "Deferred Error APIC interrupts"); +#endif +#ifdef CONFIG_HAVE_KVM +METRICFS_ITEM(PIN, kvm_posted_intr_ipis, "Posted-interrupt notification event"); +METRICFS_ITEM(PIW, kvm_posted_intr_wakeup_ipis, + "Posted-interrupt wakeup event"); +#endif + +static int __init init_irq_metricfs(void) +{ + struct metricfs_subsys *subsys; + + subsys = metricfs_create_subsys("irq_x86", NULL); + + metric_init_NMI(subsys); +#ifdef CONFIG_X86_LOCAL_APIC + metric_init_LOC(subsys); + metric_init_SPU(subsys); + metric_init_PMI(subsys); + metric_init_IWI(subsys); + metric_init_RTR(subsys); +#endif + metric_init_PLT(subsys); +#ifdef CONFIG_SMP + metric_init_RES(subsys); + metric_init_CAL(subsys); + metric_init_TLB(subsys); +#endif +#ifdef CONFIG_X86_THERMAL_VECTOR + metric_init_TRM(subsys); +#endif +#ifdef CONFIG_X86_MCE_THRESHOLD + metric_init_THR(subsys); +#endif +#ifdef CONFIG_X86_MCE_AMD + metric_init_DFR(subsys); +#endif +#ifdef CONFIG_HAVE_KVM + metric_init_PIN(subsys); + metric_init_PIW(subsys); +#endif + + return 0; +} +module_init(init_irq_metricfs); + +#endif
Add metricfs support for displaying percpu irq counters for x86. The top directory is /sys/kernel/debug/metricfs/irq_x86. Then there is a subdirectory for each x86-specific irq counter. For example: cat /sys/kernel/debug/metricfs/irq_x86/TLB/values Signed-off-by: Jonathan Adams <jwadams@google.com> --- jwadams@google.com: rebased to 5.8-pre6 This is work originally done by another engineer at google, who would rather not have their name associated with this patchset. They're okay with me sending it under my name. --- arch/x86/kernel/irq.c | 80 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 80 insertions(+)