Re: [PATCH 05/61] perf tools: Introduce c2c_decode_stats function
On Wed, Sep 21, 2016 at 11:16:26AM -0400, Don Zickus wrote: > On Wed, Sep 21, 2016 at 11:18:29AM +0200, Jiri Olsa wrote: > > On Wed, Sep 21, 2016 at 09:08:40AM +, Stanislav Ievlev wrote: > > > Hi, Jiri! > > > > > > Why are you not using unsigned integer for counters in c2c_stats > > > structure? > > > > hi, > > never really thought of that, because that's one of the original > > patches I could take almost untouched.. so no real reason ;-) > > Hi Jirka, > > I can't recall the reason Dick and myself started that way. I think it > makes sense to use u32 here. So I am fine with it. :-) ok, will change thanks, jirka
Re: [PATCH 05/61] perf tools: Introduce c2c_decode_stats function
On Wed, Sep 21, 2016 at 11:18:29AM +0200, Jiri Olsa wrote: > On Wed, Sep 21, 2016 at 09:08:40AM +, Stanislav Ievlev wrote: > > Hi, Jiri! > > > > Why are you not using unsigned integer for counters in c2c_stats structure? > > hi, > never really thought of that, because that's one of the original > patches I could take almost untouched.. so no real reason ;-) Hi Jirka, I can't recall the reason Dick and myself started that way. I think it makes sense to use u32 here. So I am fine with it. :-) Cheers, Don > > jirka > > > > > On Mon, Sep 19, 2016 at 4:27 PM Jiri Olsa wrote: > > > > > Introducing c2c_decode_stats function, which decodes > > > data_src data into new struct c2c_stats. > > > > > > +struct c2c_stats { > > > + int nr_entries; > > > + > > > + int locks; /* count of 'lock' transactions */ > > > + int store; /* count of all stores in trace */ > > > + int st_uncache; /* stores to uncacheable address */ > > > + int st_noadrs; /* cacheable store with no address */ > > > + int st_l1hit;/* count of stores that hit L1D */ > > > + int st_l1miss; /* count of stores that miss L1D */ > > > + int load;/* count of all loads in trace */ > > > + int ld_excl; /* exclusive loads, rmt/lcl DRAM - > > > snp none/miss */ > > > + int ld_shared; /* shared loads, rmt/lcl DRAM - snp > > > hit */ > > > + int ld_uncache; /* loads to uncacheable address */ > > > + int ld_io; /* loads to io address */ > > > + int ld_miss; /* loads miss */ > > > + int ld_noadrs; /* cacheable load with no address */ > > > + int ld_fbhit;/* count of loads hitting Fill Buffer > > > */ > > > + int ld_l1hit;/* count of loads that hit L1D */ > > > + int ld_l2hit;/* count of loads that hit L2D */ > > > + int ld_llchit; /* count of loads that hit LLC */ > > > + int lcl_hitm;/* count of loads with local HITM */ > > > + int rmt_hitm;/* count of loads with remote HITM */ > > > + int rmt_hit; /* count of loads with remote hit > > > clean; */ > > > + int lcl_dram;/* count of loads miss to local DRAM > > > */ > > > + int rmt_dram;/* count of loads miss to remote DRAM > > > */ > > > + int nomap; /* count of load/stores with no phys > > > adrs */ > > > + int noparse; /* count of unparsable data sources > > > */ > > > +}; > > > > > >
Re: [PATCH 05/61] perf tools: Introduce c2c_decode_stats function
On Wed, Sep 21, 2016 at 09:08:40AM +, Stanislav Ievlev wrote: > Hi, Jiri! > > Why are you not using unsigned integer for counters in c2c_stats structure? hi, never really thought of that, because that's one of the original patches I could take almost untouched.. so no real reason ;-) jirka > > On Mon, Sep 19, 2016 at 4:27 PM Jiri Olsa wrote: > > > Introducing c2c_decode_stats function, which decodes > > data_src data into new struct c2c_stats. > > > > +struct c2c_stats { > > + int nr_entries; > > + > > + int locks; /* count of 'lock' transactions */ > > + int store; /* count of all stores in trace */ > > + int st_uncache; /* stores to uncacheable address */ > > + int st_noadrs; /* cacheable store with no address */ > > + int st_l1hit;/* count of stores that hit L1D */ > > + int st_l1miss; /* count of stores that miss L1D */ > > + int load;/* count of all loads in trace */ > > + int ld_excl; /* exclusive loads, rmt/lcl DRAM - > > snp none/miss */ > > + int ld_shared; /* shared loads, rmt/lcl DRAM - snp > > hit */ > > + int ld_uncache; /* loads to uncacheable address */ > > + int ld_io; /* loads to io address */ > > + int ld_miss; /* loads miss */ > > + int ld_noadrs; /* cacheable load with no address */ > > + int ld_fbhit;/* count of loads hitting Fill Buffer > > */ > > + int ld_l1hit;/* count of loads that hit L1D */ > > + int ld_l2hit;/* count of loads that hit L2D */ > > + int ld_llchit; /* count of loads that hit LLC */ > > + int lcl_hitm;/* count of loads with local HITM */ > > + int rmt_hitm;/* count of loads with remote HITM */ > > + int rmt_hit; /* count of loads with remote hit > > clean; */ > > + int lcl_dram;/* count of loads miss to local DRAM > > */ > > + int rmt_dram;/* count of loads miss to remote DRAM > > */ > > + int nomap; /* count of load/stores with no phys > > adrs */ > > + int noparse; /* count of unparsable data sources */ > > +}; > > > >
Re: [PATCH 05/61] perf tools: Introduce c2c_decode_stats function
On 09/19/2016 01:15 PM, Nilay Vaish wrote: On 19 September 2016 at 08:09, Jiri Olsa wrote: diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h index 7f69bf9d789d..27c6bb5abafb 100644 --- a/tools/perf/util/mem-events.h +++ b/tools/perf/util/mem-events.h @@ -2,6 +2,10 @@ #define __PERF_MEM_EVENTS_H #include +#include +#include +#include +#include "stat.h" struct perf_mem_event { boolrecord; @@ -33,4 +37,36 @@ int perf_mem__lck_scnprintf(char *out, size_t sz, struct mem_info *mem_info); int perf_script__meminfo_scnprintf(char *bf, size_t size, struct mem_info *mem_info); +struct c2c_stats { + int nr_entries; + + int locks; /* count of 'lock' transactions */ + int store; /* count of all stores in trace */ + int st_uncache; /* stores to uncacheable address */ + int st_noadrs; /* cacheable store with no address */ No address! Why would that happen? [Resending without the html] There are a small number of instructions that will trigger a perf mem event and will have no address associated with them.Three of them include mfence, wrmsr, and rdtsc.I believe there are at least two more. -- Nilay
Re: [PATCH 05/61] perf tools: Introduce c2c_decode_stats function
On 19 September 2016 at 08:09, Jiri Olsa wrote: > diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h > index 7f69bf9d789d..27c6bb5abafb 100644 > --- a/tools/perf/util/mem-events.h > +++ b/tools/perf/util/mem-events.h > @@ -2,6 +2,10 @@ > #define __PERF_MEM_EVENTS_H > > #include > +#include > +#include > +#include > +#include "stat.h" > > struct perf_mem_event { > boolrecord; > @@ -33,4 +37,36 @@ int perf_mem__lck_scnprintf(char *out, size_t sz, struct > mem_info *mem_info); > > int perf_script__meminfo_scnprintf(char *bf, size_t size, struct mem_info > *mem_info); > > +struct c2c_stats { > + int nr_entries; > + > + int locks; /* count of 'lock' transactions */ > + int store; /* count of all stores in trace */ > + int st_uncache; /* stores to uncacheable address */ > + int st_noadrs; /* cacheable store with no address */ No address! Why would that happen? -- Nilay
[PATCH 05/61] perf tools: Introduce c2c_decode_stats function
Introducing c2c_decode_stats function, which decodes data_src data into new struct c2c_stats. Original-patch-by: Dick Fowles Original-patch-by: Don Zickus Link: http://lkml.kernel.org/n/tip-7garqfmx5izaqysde9jik...@git.kernel.org Signed-off-by: Jiri Olsa --- tools/perf/util/mem-events.c | 98 tools/perf/util/mem-events.h | 36 2 files changed, 134 insertions(+) diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c index bbc368e7d1e4..502fcee91973 100644 --- a/tools/perf/util/mem-events.c +++ b/tools/perf/util/mem-events.c @@ -9,6 +9,7 @@ #include "mem-events.h" #include "debug.h" #include "symbol.h" +#include "sort.h" unsigned int perf_mem_events__loads_ldlat = 30; @@ -268,3 +269,100 @@ int perf_script__meminfo_scnprintf(char *out, size_t sz, struct mem_info *mem_in return i; } + +int c2c_decode_stats(struct c2c_stats *stats, struct mem_info *mi) +{ + union perf_mem_data_src *data_src = &mi->data_src; + u64 daddr = mi->daddr.addr; + u64 op = data_src->mem_op; + u64 lvl= data_src->mem_lvl; + u64 snoop = data_src->mem_snoop; + u64 lock = data_src->mem_lock; + int err = 0; + +#define P(a, b) PERF_MEM_##a##_##b + + stats->nr_entries++; + + if (lock & P(LOCK, LOCKED)) stats->locks++; + + if (op & P(OP, LOAD)) { + /* load */ + stats->load++; + + if (!daddr) { + stats->ld_noadrs++; + return -1; + } + + if (lvl & P(LVL, HIT)) { + if (lvl & P(LVL, UNC)) stats->ld_uncache++; + if (lvl & P(LVL, IO)) stats->ld_io++; + if (lvl & P(LVL, LFB)) stats->ld_fbhit++; + if (lvl & P(LVL, L1 )) stats->ld_l1hit++; + if (lvl & P(LVL, L2 )) stats->ld_l2hit++; + if (lvl & P(LVL, L3 )) { + if (snoop & P(SNOOP, HITM)) + stats->lcl_hitm++; + else + stats->ld_llchit++; + } + + if (lvl & P(LVL, LOC_RAM)) { + stats->lcl_dram++; + if (snoop & P(SNOOP, HIT)) + stats->ld_shared++; + else + stats->ld_excl++; + } + + if ((lvl & P(LVL, REM_RAM1)) || + (lvl & P(LVL, REM_RAM2))) { + stats->rmt_dram++; + if (snoop & P(SNOOP, HIT)) + stats->ld_shared++; + else + stats->ld_excl++; + } + } + + if ((lvl & P(LVL, REM_CCE1)) || + (lvl & P(LVL, REM_CCE2))) { + if (snoop & P(SNOOP, HIT)) + stats->rmt_hit++; + else if (snoop & P(SNOOP, HITM)) + stats->rmt_hitm++; + } + + if ((lvl & P(LVL, MISS))) + stats->ld_miss++; + + } else if (op & P(OP, STORE)) { + /* store */ + stats->store++; + + if (!daddr) { + stats->st_noadrs++; + return -1; + } + + if (lvl & P(LVL, HIT)) { + if (lvl & P(LVL, UNC)) stats->st_uncache++; + if (lvl & P(LVL, L1 )) stats->st_l1hit++; + } + if (lvl & P(LVL, MISS)) + if (lvl & P(LVL, L1)) stats->st_l1miss++; + } else { + /* unparsable data_src? */ + stats->noparse++; + return -1; + } + + if (!mi->daddr.map || !mi->iaddr.map) { + stats->nomap++; + return -1; + } + +#undef P + return err; +} diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h index 7f69bf9d789d..27c6bb5abafb 100644 --- a/tools/perf/util/mem-events.h +++ b/tools/perf/util/mem-events.h @@ -2,6 +2,10 @@ #define __PERF_MEM_EVENTS_H #include +#include +#include +#include +#include "stat.h" struct perf_mem_event { boolrecord; @@ -33,4 +37,36 @@ int perf_mem__lck_scnprintf(char *out, size_t sz, struct mem_info *mem_info); int perf_script__meminfo_scnprintf(char *bf, size_t size, struct mem_info *mem_info); +struct c2c_stats { + int nr_entries; + + int locks; /* count of 'lock' transactions */ + int store; /* count of all stores in trace */ + in