agora inbox for [email protected]help / color / mirror / Atom feed
[PATCH v22 2/8] Row pattern recognition patch (parse/analysis). 265+ messages / 2 participants [nested] [flat]
* [PATCH v22 2/8] Row pattern recognition patch (parse/analysis). @ 2024-09-19 04:48 Tatsuo Ishii <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Tatsuo Ishii @ 2024-09-19 04:48 UTC (permalink / raw) --- src/backend/parser/parse_agg.c | 7 + src/backend/parser/parse_clause.c | 296 +++++++++++++++++++++++++++++- src/backend/parser/parse_expr.c | 6 + src/backend/parser/parse_func.c | 3 + 4 files changed, 311 insertions(+), 1 deletion(-) diff --git a/src/backend/parser/parse_agg.c b/src/backend/parser/parse_agg.c index efa730c167..a80263f90d 100644 --- a/src/backend/parser/parse_agg.c +++ b/src/backend/parser/parse_agg.c @@ -580,6 +580,10 @@ check_agglevels_and_constraints(ParseState *pstate, Node *expr) errkind = true; break; + case EXPR_KIND_RPR_DEFINE: + errkind = true; + break; + /* * There is intentionally no default: case here, so that the * compiler will warn if we add a new ParseExprKind without @@ -970,6 +974,9 @@ transformWindowFuncCall(ParseState *pstate, WindowFunc *wfunc, case EXPR_KIND_CYCLE_MARK: errkind = true; break; + case EXPR_KIND_RPR_DEFINE: + errkind = true; + break; /* * There is intentionally no default: case here, so that the diff --git a/src/backend/parser/parse_clause.c b/src/backend/parser/parse_clause.c index 8118036495..9762dce81f 100644 --- a/src/backend/parser/parse_clause.c +++ b/src/backend/parser/parse_clause.c @@ -98,7 +98,14 @@ static WindowClause *findWindowClause(List *wclist, const char *name); static Node *transformFrameOffset(ParseState *pstate, int frameOptions, Oid rangeopfamily, Oid rangeopcintype, Oid *inRangeFunc, Node *clause); - +static void transformRPR(ParseState *pstate, WindowClause *wc, WindowDef *windef, + List **targetlist); +static List *transformDefineClause(ParseState *pstate, WindowClause *wc, WindowDef *windef, + List **targetlist); +static void transformPatternClause(ParseState *pstate, WindowClause *wc, + WindowDef *windef); +static List *transformMeasureClause(ParseState *pstate, WindowClause *wc, + WindowDef *windef); /* * transformFromClause - @@ -2956,6 +2963,10 @@ transformWindowDefinitions(ParseState *pstate, rangeopfamily, rangeopcintype, &wc->endInRangeFunc, windef->endOffset); + + /* Process Row Pattern Recognition related clauses */ + transformRPR(pstate, wc, windef, targetlist); + wc->winref = winref; result = lappend(result, wc); @@ -3820,3 +3831,286 @@ transformFrameOffset(ParseState *pstate, int frameOptions, return node; } + +/* + * transformRPR + * Process Row Pattern Recognition related clauses + */ +static void +transformRPR(ParseState *pstate, WindowClause *wc, WindowDef *windef, + List **targetlist) +{ + /* + * Window definition exists? + */ + if (windef == NULL) + return; + + /* + * Row Pattern Common Syntax clause exists? + */ + if (windef->rpCommonSyntax == NULL) + return; + + /* Check Frame option. Frame must start at current row */ + if ((wc->frameOptions & FRAMEOPTION_START_CURRENT_ROW) == 0) + ereport(ERROR, + (errcode(ERRCODE_SYNTAX_ERROR), + errmsg("FRAME must start at current row when row patttern recognition is used"))); + + /* Transform AFTER MACH SKIP TO clause */ + wc->rpSkipTo = windef->rpCommonSyntax->rpSkipTo; + + /* Transform AFTER MACH SKIP TO variable */ + wc->rpSkipVariable = windef->rpCommonSyntax->rpSkipVariable; + + /* Transform SEEK or INITIAL clause */ + wc->initial = windef->rpCommonSyntax->initial; + + /* Transform DEFINE clause into list of TargetEntry's */ + wc->defineClause = transformDefineClause(pstate, wc, windef, targetlist); + + /* Check PATTERN clause and copy to patternClause */ + transformPatternClause(pstate, wc, windef); + + /* Transform MEASURE clause */ + transformMeasureClause(pstate, wc, windef); +} + +/* + * transformDefineClause Process DEFINE clause and transform ResTarget into + * list of TargetEntry. + * + * XXX we only support column reference in row pattern definition search + * condition, e.g. "price". <row pattern definition variable name>.<column + * reference> is not supported, e.g. "A.price". + */ +static List * +transformDefineClause(ParseState *pstate, WindowClause *wc, WindowDef *windef, + List **targetlist) +{ + /* DEFINE variable name initials */ + static char *defineVariableInitials = "abcdefghijklmnopqrstuvwxyz"; + + ListCell *lc, + *l; + ResTarget *restarget, + *r; + List *restargets; + List *defineClause; + char *name; + int initialLen; + int i; + + /* + * If Row Definition Common Syntax exists, DEFINE clause must exist. (the + * raw parser should have already checked it.) + */ + Assert(windef->rpCommonSyntax->rpDefs != NULL); + + /* + * Check and add "A AS A IS TRUE" if pattern variable is missing in DEFINE + * per the SQL standard. + */ + restargets = NIL; + foreach(lc, windef->rpCommonSyntax->rpPatterns) + { + A_Expr *a; + bool found = false; + + if (!IsA(lfirst(lc), A_Expr)) + ereport(ERROR, + errmsg("node type is not A_Expr")); + + a = (A_Expr *) lfirst(lc); + name = strVal(a->lexpr); + + foreach(l, windef->rpCommonSyntax->rpDefs) + { + restarget = (ResTarget *) lfirst(l); + + if (!strcmp(restarget->name, name)) + { + found = true; + break; + } + } + + if (!found) + { + /* + * "name" is missing. So create "name AS name IS TRUE" ResTarget + * node and add it to the temporary list. + */ + A_Const *n; + + restarget = makeNode(ResTarget); + n = makeNode(A_Const); + n->val.boolval.type = T_Boolean; + n->val.boolval.boolval = true; + n->location = -1; + restarget->name = pstrdup(name); + restarget->indirection = NIL; + restarget->val = (Node *) n; + restarget->location = -1; + restargets = lappend((List *) restargets, restarget); + } + } + + if (list_length(restargets) >= 1) + { + /* add missing DEFINEs */ + windef->rpCommonSyntax->rpDefs = + list_concat(windef->rpCommonSyntax->rpDefs, restargets); + list_free(restargets); + } + + /* + * Check for duplicate row pattern definition variables. The standard + * requires that no two row pattern definition variable names shall be + * equivalent. + */ + restargets = NIL; + foreach(lc, windef->rpCommonSyntax->rpDefs) + { + restarget = (ResTarget *) lfirst(lc); + name = restarget->name; + + /* + * Add DEFINE expression (Restarget->val) to the targetlist as a + * TargetEntry if it does not exist yet. Planner will add the column + * ref var node to the outer plan's target list later on. This makes + * DEFINE expression could access the outer tuple while evaluating + * PATTERN. + * + * XXX: adding whole expressions of DEFINE to the plan.targetlist is + * not so good, because it's not necessary to evalute the expression + * in the target list while running the plan. We should extract the + * var nodes only then add them to the plan.targetlist. + */ + findTargetlistEntrySQL99(pstate, (Node *) restarget->val, + targetlist, EXPR_KIND_RPR_DEFINE); + + /* + * Make sure that the row pattern definition search condition is a + * boolean expression. + */ + transformWhereClause(pstate, restarget->val, + EXPR_KIND_RPR_DEFINE, "DEFINE"); + + foreach(l, restargets) + { + char *n; + + r = (ResTarget *) lfirst(l); + n = r->name; + + if (!strcmp(n, name)) + ereport(ERROR, + (errcode(ERRCODE_SYNTAX_ERROR), + errmsg("row pattern definition variable name \"%s\" appears more than once in DEFINE clause", + name), + parser_errposition(pstate, exprLocation((Node *) r)))); + } + restargets = lappend(restargets, restarget); + } + list_free(restargets); + + /* + * Create list of row pattern DEFINE variable name's initial. We assign + * [a-z] to them (up to 26 variable names are allowed). + */ + restargets = NIL; + i = 0; + initialLen = strlen(defineVariableInitials); + + foreach(lc, windef->rpCommonSyntax->rpDefs) + { + char initial[2]; + + restarget = (ResTarget *) lfirst(lc); + name = restarget->name; + + if (i >= initialLen) + { + ereport(ERROR, + (errcode(ERRCODE_SYNTAX_ERROR), + errmsg("number of row pattern definition variable names exceeds %d", + initialLen), + parser_errposition(pstate, + exprLocation((Node *) restarget)))); + } + initial[0] = defineVariableInitials[i++]; + initial[1] = '\0'; + wc->defineInitial = lappend(wc->defineInitial, + makeString(pstrdup(initial))); + } + + defineClause = transformTargetList(pstate, windef->rpCommonSyntax->rpDefs, + EXPR_KIND_RPR_DEFINE); + + /* mark column origins */ + markTargetListOrigins(pstate, defineClause); + + /* mark all nodes in the DEFINE clause tree with collation information */ + assign_expr_collations(pstate, (Node *) defineClause); + + return defineClause; +} + +/* + * transformPatternClause + * Process PATTERN clause and return PATTERN clause in the raw parse tree + */ +static void +transformPatternClause(ParseState *pstate, WindowClause *wc, + WindowDef *windef) +{ + ListCell *lc; + + /* + * Row Pattern Common Syntax clause exists? + */ + if (windef->rpCommonSyntax == NULL) + return; + + wc->patternVariable = NIL; + wc->patternRegexp = NIL; + foreach(lc, windef->rpCommonSyntax->rpPatterns) + { + A_Expr *a; + char *name; + char *regexp; + + if (!IsA(lfirst(lc), A_Expr)) + ereport(ERROR, + errmsg("node type is not A_Expr")); + + a = (A_Expr *) lfirst(lc); + name = strVal(a->lexpr); + + wc->patternVariable = lappend(wc->patternVariable, makeString(pstrdup(name))); + regexp = strVal(lfirst(list_head(a->name))); + + wc->patternRegexp = lappend(wc->patternRegexp, makeString(pstrdup(regexp))); + } +} + +/* + * transformMeasureClause + * Process MEASURE clause + * XXX MEASURE clause is not supported yet + */ +static List * +transformMeasureClause(ParseState *pstate, WindowClause *wc, + WindowDef *windef) +{ + if (windef->rowPatternMeasures == NIL) + return NIL; + + ereport(ERROR, + (errcode(ERRCODE_SYNTAX_ERROR), + errmsg("%s", "MEASURE clause is not supported yet"), + parser_errposition(pstate, exprLocation((Node *) windef->rowPatternMeasures)))); + return NIL; +} diff --git a/src/backend/parser/parse_expr.c b/src/backend/parser/parse_expr.c index 36c1b7a88f..fe154bcaa0 100644 --- a/src/backend/parser/parse_expr.c +++ b/src/backend/parser/parse_expr.c @@ -577,6 +577,7 @@ transformColumnRef(ParseState *pstate, ColumnRef *cref) case EXPR_KIND_COPY_WHERE: case EXPR_KIND_GENERATED_COLUMN: case EXPR_KIND_CYCLE_MARK: + case EXPR_KIND_RPR_DEFINE: /* okay */ break; @@ -1860,6 +1861,9 @@ transformSubLink(ParseState *pstate, SubLink *sublink) case EXPR_KIND_GENERATED_COLUMN: err = _("cannot use subquery in column generation expression"); break; + case EXPR_KIND_RPR_DEFINE: + err = _("cannot use subquery in DEFINE expression"); + break; /* * There is intentionally no default: case here, so that the @@ -3199,6 +3203,8 @@ ParseExprKindName(ParseExprKind exprKind) return "GENERATED AS"; case EXPR_KIND_CYCLE_MARK: return "CYCLE"; + case EXPR_KIND_RPR_DEFINE: + return "DEFINE"; /* * There is intentionally no default: case here, so that the diff --git a/src/backend/parser/parse_func.c b/src/backend/parser/parse_func.c index 9b23344a3b..4c482abb30 100644 --- a/src/backend/parser/parse_func.c +++ b/src/backend/parser/parse_func.c @@ -2658,6 +2658,9 @@ check_srf_call_placement(ParseState *pstate, Node *last_srf, int location) case EXPR_KIND_CYCLE_MARK: errkind = true; break; + case EXPR_KIND_RPR_DEFINE: + errkind = true; + break; /* * There is intentionally no default: case here, so that the -- 2.25.1 ----Next_Part(Thu_Sep_19_13_59_47_2024_608)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v22-0003-Row-pattern-recognition-patch-rewriter.patch" ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source @ 2025-07-27 15:48 Lukas Fittl <[email protected]> 0 siblings, 0 replies; 265+ messages in thread From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw) In passing also reduce the per-loop overhead caused by repeated divisions in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large, instead diff first and then turn it into nanosecs. --- src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------ src/include/portability/instr_time.h | 30 ++++++++----- 2 files changed, 65 insertions(+), 24 deletions(-) diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c index a5621251afc..b77ef2063b6 100644 --- a/src/bin/pg_test_timing/pg_test_timing.c +++ b/src/bin/pg_test_timing/pg_test_timing.c @@ -16,6 +16,7 @@ static const char *progname; static unsigned int test_duration = 3; static double max_rprct = 99.99; +static bool fast_timing = false; /* record duration in powers of 2 nanoseconds */ static long long int histogram[32]; @@ -56,6 +57,7 @@ handle_args(int argc, char *argv[]) static struct option long_options[] = { {"duration", required_argument, NULL, 'd'}, {"cutoff", required_argument, NULL, 'c'}, + {"fast", no_argument, NULL, 'f'}, {NULL, 0, NULL, 0} }; @@ -68,7 +70,7 @@ handle_args(int argc, char *argv[]) { if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0) { - printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname); + printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname); exit(0); } if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0) @@ -78,7 +80,7 @@ handle_args(int argc, char *argv[]) } } - while ((option = getopt_long(argc, argv, "d:c:", + while ((option = getopt_long(argc, argv, "d:c:f:", long_options, &optindex)) != -1) { switch (option) @@ -125,6 +127,10 @@ handle_args(int argc, char *argv[]) } break; + case 'f': + fast_timing = true; + break; + default: fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); @@ -155,11 +161,31 @@ test_timing(unsigned int duration) uint64 total_time; int64 time_elapsed = 0; uint64 loop_count = 0; - uint64 prev, - cur; instr_time start_time, end_time, - temp; + prev, + cur; + char *time_source = NULL; + bool fast_timing_used = false; + + INSTR_TIME_INITIALIZE(); + +#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__) + if (fast_timing && has_rdtsc) + { + time_source = "RDTSC"; + fast_timing_used = true; + } + else if (has_rdtscp) + time_source = "RDTSCP"; + else + time_source = PG_INSTR_CLOCK_NAME; +#else + time_source = PG_INSTR_CLOCK_NAME; +#endif + if (fast_timing && !fast_timing_used) + printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n")); + printf(_("Time source: %s\n"), time_source); /* * Pre-zero the statistics data structures. They're already zero by @@ -173,8 +199,11 @@ test_timing(unsigned int duration) total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0; - INSTR_TIME_SET_CURRENT(start_time); - cur = INSTR_TIME_GET_NANOSEC(start_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(start_time); + else + INSTR_TIME_SET_CURRENT(start_time); + cur = start_time; while (time_elapsed < total_time) { @@ -182,9 +211,11 @@ test_timing(unsigned int duration) bits; prev = cur; - INSTR_TIME_SET_CURRENT(temp); - cur = INSTR_TIME_GET_NANOSEC(temp); - diff = cur - prev; + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(cur); + else + INSTR_TIME_SET_CURRENT(cur); + diff = INSTR_TIME_DIFF_NANOSEC(cur, prev); /* Did time go backwards? */ if (unlikely(diff < 0)) @@ -217,11 +248,13 @@ test_timing(unsigned int duration) largest_diff_count++; loop_count++; - INSTR_TIME_SUBTRACT(temp, start_time); - time_elapsed = INSTR_TIME_GET_NANOSEC(temp); + time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time); } - INSTR_TIME_SET_CURRENT(end_time); + if (fast_timing) + INSTR_TIME_SET_CURRENT_FAST(end_time); + else + INSTR_TIME_SET_CURRENT(end_time); INSTR_TIME_SUBTRACT(end_time, start_time); diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index e2e339a0c4f..f02296f1026 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow; */ #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW) #define PG_INSTR_CLOCK CLOCK_MONOTONIC_RAW +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC_RAW)" #elif defined(CLOCK_MONOTONIC) #define PG_INSTR_CLOCK CLOCK_MONOTONIC +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_MONOTONIC)" #else #define PG_INSTR_CLOCK CLOCK_REALTIME +#define PG_INSTR_CLOCK_NAME "clock_gettime (CLOCK_REALTIME)" #endif #if defined(__x86_64__) && defined(__linux__) @@ -174,7 +177,7 @@ pg_get_ticks(void) } static inline int64_t -pg_ticks_to_ns(instr_time t) +pg_ticks_to_ns(int64 ticks) { /* * Would multiplication overflow? If so perform computation in two parts. @@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t) */ int64 ns = 0; - if (unlikely(t.ticks > max_ticks_no_overflow)) + if (unlikely(ticks > max_ticks_no_overflow)) { /* * Compute how often the maximum number of ticks fits completely into @@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t) * value. In a 2nd step we adjust the number of elapsed ticks and * convert the remaining ticks. */ - int64 count = t.ticks / max_ticks_no_overflow; + int64 count = ticks / max_ticks_no_overflow; int64 max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; ns = max_ns * count; @@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t) * Subtract the ticks that we now already accounted for, so that they * don't get counted twice. */ - t.ticks -= count * max_ticks_no_overflow; - Assert(t.ticks >= 0); + ticks -= count * max_ticks_no_overflow; + Assert(ticks >= 0); } - ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; + ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION; return ns; } @@ -226,14 +229,14 @@ pg_initialize_get_ticks() #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_get_ticks()) -#define INSTR_TIME_GET_NANOSEC(t) \ - pg_ticks_to_ns(t) - +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + (pg_ticks_to_ns(ticks)) #else /* WIN32 */ /* Use QueryPerformanceCounter() */ +#define PG_INSTR_CLOCK_NAME "QueryPerformanceCounter" /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */ static inline instr_time @@ -265,8 +268,8 @@ GetTimerFrequency(void) #define INSTR_TIME_SET_CURRENT(t) \ ((t) = pg_query_performance_counter()) -#define INSTR_TIME_GET_NANOSEC(t) \ - ((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency()))) +#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \ + ((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency()))) #endif /* WIN32 */ @@ -285,9 +288,14 @@ GetTimerFrequency(void) #define INSTR_TIME_SUBTRACT(x,y) \ ((x).ticks -= (y).ticks) +#define INSTR_TIME_DIFF_NANOSEC(x,y) \ + (INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks)) + #define INSTR_TIME_ACCUM_DIFF(x,y,z) \ ((x).ticks += (y).ticks - (z).ticks) +#define INSTR_TIME_GET_NANOSEC(t) \ + (INSTR_TIME_TICKS_TO_NANOSEC((t).ticks)) #define INSTR_TIME_GET_DOUBLE(t) \ ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) -- 2.47.3 --vtqqtrpooseurzip-- ^ permalink raw reply [nested|flat] 265+ messages in thread
end of thread, other threads:[~2025-07-27 15:48 UTC | newest] Thread overview: 265+ messages (download: mbox mbox.gz follow: Atom feed) -- links below jump to the message on this page -- 2024-09-19 04:48 [PATCH v22 2/8] Row pattern recognition patch (parse/analysis). Tatsuo Ishii <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]> 2025-07-27 15:48 [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source Lukas Fittl <[email protected]>
This inbox is served by agora; see mirroring instructions for how to clone and mirror all data and code used for this inbox