diff options
author | Rickard Green <[email protected]> | 2015-03-20 21:37:15 +0100 |
---|---|---|
committer | Rickard Green <[email protected]> | 2015-03-20 21:37:15 +0100 |
commit | 6642d62c071f94d3e76254453099e2df01f7ad0e (patch) | |
tree | bb7acaeb1710092da6257ac3abd937bce67e394d /erts/emulator/beam | |
parent | 74099492bee421c4829537bca3c4bc0c4fbec031 (diff) | |
parent | f4e3cd1c970cfc5ad54f2ed64832d05749c305d4 (diff) | |
download | otp-6642d62c071f94d3e76254453099e2df01f7ad0e.tar.gz otp-6642d62c071f94d3e76254453099e2df01f7ad0e.tar.bz2 otp-6642d62c071f94d3e76254453099e2df01f7ad0e.zip |
Merge branch 'rickard/time_api/master/OTP-11997'
* rickard/time_api/master/OTP-11997: (22 commits)
Update primary bootstrap
inets: Suppress deprecated warning on erlang:now/0
inets: Cleanup of multiple copies of functions Add inets_lib with common functions used by multiple modules
inets: Update comments
Suppress deprecated warning on erlang:now/0
Use new time API and be back-compatible in inets Remove unused functions and removed redundant test
asn1 test SUITE: Eliminate use of now/0
Disable deprecated warning on erlang:now/0 in diameter_lib
Use new time API and be back-compatible in ssh
Replace all calls to now/0 in CT with new time API functions
test_server: Replace usage of erlang:now() with usage of new API
Replace usage of erlang:now() with usage of new API
Replace usage of erlang:now() with usage of new API
Replace usage of erlang:now() with usage of new API
Replace usage of erlang:now() with usage of new API
otp_SUITE: Warn for calls to erlang:now/0
Replace usage of erlang:now() with usage of new API
Multiple timer wheels
Erlang based BIF timer implementation for scalability
Implement ethread events with timeout
...
Diffstat (limited to 'erts/emulator/beam')
36 files changed, 3859 insertions, 1111 deletions
diff --git a/erts/emulator/beam/atom.names b/erts/emulator/beam/atom.names index c097866c7e..ae3f30d82f 100644 --- a/erts/emulator/beam/atom.names +++ b/erts/emulator/beam/atom.names @@ -109,6 +109,7 @@ atom bag atom band atom big atom bif_return_trap +atom bif_timer_server atom binary atom binary_bin_to_list_trap atom binary_copy_trap @@ -144,9 +145,11 @@ atom catchlevel atom cd atom cdr atom cflags +atom CHANGE='CHANGE' atom characters_to_binary_int atom characters_to_list_int atom clear +atom clock_service atom close atom closed atom code @@ -156,6 +159,7 @@ atom compat_rel atom compile atom compressed atom config_h +atom convert_time_unit atom connect atom connected atom connection_closed @@ -237,7 +241,7 @@ atom first atom firstline atom flags atom flush -atom flush_monitor_message +atom flush_monitor_messages atom force atom format_cpu_topology atom free @@ -345,6 +349,8 @@ atom message_queue_len atom messages atom meta atom meta_match_spec +atom micro_seconds +atom milli_seconds atom min_heap_size atom min_bin_vheap_size atom minor_version @@ -355,12 +361,15 @@ atom monitored_by atom monitor atom monitor_nodes atom monitors +atom monotonic atom more atom multi_scheduling atom multiline +atom nano_seconds atom name atom named_table atom namelist +atom native atom native_addresses atom Neq='=/=' atom Neqeq='/=' @@ -451,6 +460,7 @@ atom ports atom port_count atom port_limit atom port_op +atom positive atom print atom priority atom private @@ -510,6 +520,7 @@ atom schedulers_online atom scheme atom scientific atom scope +atom seconds atom sensitive atom sequential_tracer atom sequential_trace_token @@ -555,6 +566,7 @@ atom term_to_binary_trap atom this atom thread_pool_size atom threads +atom time_offset atom timeout atom timeout_value atom Times='*' diff --git a/erts/emulator/beam/benchmark.h b/erts/emulator/beam/benchmark.h index 904564a96b..7fc3933f3d 100644 --- a/erts/emulator/beam/benchmark.h +++ b/erts/emulator/beam/benchmark.h @@ -141,10 +141,10 @@ extern unsigned long long major_gc; /* (Assuming Solaris) */ -#define BM_TIMER_T hrtime_t -#define BM_START_TIMER(t) system_clock = sys_gethrtime() +#define BM_TIMER_T ErtsMonotonicTime +#define BM_START_TIMER(t) system_clock = ERTS_MONOTONIC_TO_NSEC(erts_os_monotonic_time()) #define BM_STOP_TIMER(t) do { \ - BM_TIMER_T tmp = (sys_gethrtime() - system_clock) - timer_time; \ + BM_TIMER_T tmp = (ERTS_MONOTONIC_TO_NSEC(erts_os_monotonic_time()) - system_clock) - timer_time; \ t##_time += (tmp > 0 ? tmp : 0); \ } while(0) diff --git a/erts/emulator/beam/bif.c b/erts/emulator/beam/bif.c index 49996e7f0b..af02a55b69 100644 --- a/erts/emulator/beam/bif.c +++ b/erts/emulator/beam/bif.c @@ -42,16 +42,22 @@ #define ERTS_PTAB_WANT_BIF_IMPL__ #include "erl_ptab.h" #include "erl_bits.h" +#include "erl_bif_unique.h" -static Export* flush_monitor_message_trap = NULL; +static Export* flush_monitor_messages_trap = NULL; static Export* set_cpu_topology_trap = NULL; static Export* await_proc_exit_trap = NULL; static Export* await_port_send_result_trap = NULL; Export* erts_format_cpu_topology_trap = NULL; static Export dsend_continue_trap_export; +Export *erts_convert_time_unit_trap = NULL; + static Export *await_sched_wall_time_mod_trap; static erts_smp_atomic32_t sched_wall_time; +static erts_smp_mtx_t ports_snapshot_mtx; +erts_smp_atomic_t erts_dead_ports_ptr; /* To store dying ports during snapshot */ + #define DECL_AM(S) Eterm AM_ ## S = am_atom_put(#S, sizeof(#S) - 1) /* @@ -393,7 +399,7 @@ remote_demonitor(Process *c_p, DistEntry *dep, Eterm ref, Eterm to) return res; } -static int demonitor(Process *c_p, Eterm ref) +static int demonitor(Process *c_p, Eterm ref, Eterm *multip) { ErtsMonitor *mon = NULL; /* The monitor entry to delete */ Process *rp; /* Local target process */ @@ -417,65 +423,73 @@ static int demonitor(Process *c_p, Eterm ref) goto done; } - if (mon->type != MON_ORIGIN) { - res = ERTS_DEMONITOR_BADARG; - goto done; - } - to = mon->pid; - - if (is_atom(to)) { - /* Monitoring a name at node to */ - ASSERT(is_node_name_atom(to)); - dep = erts_sysname_to_connected_dist_entry(to); - ASSERT(dep != erts_this_dist_entry); - if (dep) - deref_de = 1; - } else { - ASSERT(is_pid(to)); - dep = pid_dist_entry(to); - } - if (dep != erts_this_dist_entry) { - res = remote_demonitor(c_p, dep, ref, to); - /* remote_demonitor() unlocks link lock on c_p */ - unlock_link = 0; - } - else { /* Local monitor */ - if (deref_de) { - deref_de = 0; - erts_deref_dist_entry(dep); + switch (mon->type) { + case MON_TIME_OFFSET: + *multip = am_true; + erts_demonitor_time_offset(ref); + res = ERTS_DEMONITOR_TRUE; + break; + case MON_ORIGIN: + to = mon->pid; + *multip = am_false; + if (is_atom(to)) { + /* Monitoring a name at node to */ + ASSERT(is_node_name_atom(to)); + dep = erts_sysname_to_connected_dist_entry(to); + ASSERT(dep != erts_this_dist_entry); + if (dep) + deref_de = 1; + } else { + ASSERT(is_pid(to)); + dep = pid_dist_entry(to); } - dep = NULL; - rp = erts_pid2proc_opt(c_p, - ERTS_PROC_LOCK_MAIN|ERTS_PROC_LOCK_LINK, - to, - ERTS_PROC_LOCK_LINK, - ERTS_P2P_FLG_ALLOW_OTHER_X); - mon = erts_remove_monitor(&ERTS_P_MONITORS(c_p), ref); + if (dep != erts_this_dist_entry) { + res = remote_demonitor(c_p, dep, ref, to); + /* remote_demonitor() unlocks link lock on c_p */ + unlock_link = 0; + } + else { /* Local monitor */ + if (deref_de) { + deref_de = 0; + erts_deref_dist_entry(dep); + } + dep = NULL; + rp = erts_pid2proc_opt(c_p, + ERTS_PROC_LOCK_MAIN|ERTS_PROC_LOCK_LINK, + to, + ERTS_PROC_LOCK_LINK, + ERTS_P2P_FLG_ALLOW_OTHER_X); + mon = erts_remove_monitor(&ERTS_P_MONITORS(c_p), ref); #ifndef ERTS_SMP - ASSERT(mon); + ASSERT(mon); #else - if (!mon) - res = ERTS_DEMONITOR_FALSE; - else + if (!mon) + res = ERTS_DEMONITOR_FALSE; + else #endif - { - res = ERTS_DEMONITOR_TRUE; - erts_destroy_monitor(mon); - } - if (rp) { - ErtsMonitor *rmon; - rmon = erts_remove_monitor(&ERTS_P_MONITORS(rp), ref); - if (rp != c_p) - erts_smp_proc_unlock(rp, ERTS_PROC_LOCK_LINK); - if (rmon != NULL) - erts_destroy_monitor(rmon); - } - else { - ERTS_SMP_ASSERT_IS_NOT_EXITING(c_p); - } + { + res = ERTS_DEMONITOR_TRUE; + erts_destroy_monitor(mon); + } + if (rp) { + ErtsMonitor *rmon; + rmon = erts_remove_monitor(&ERTS_P_MONITORS(rp), ref); + if (rp != c_p) + erts_smp_proc_unlock(rp, ERTS_PROC_LOCK_LINK); + if (rmon != NULL) + erts_destroy_monitor(rmon); + } + else { + ERTS_SMP_ASSERT_IS_NOT_EXITING(c_p); + } + } + break; + default: + res = ERTS_DEMONITOR_BADARG; + *multip = am_false; + break; } - done: if (unlock_link) @@ -492,7 +506,8 @@ static int demonitor(Process *c_p, Eterm ref) BIF_RETTYPE demonitor_1(BIF_ALIST_1) { - switch (demonitor(BIF_P, BIF_ARG_1)) { + Eterm multi; + switch (demonitor(BIF_P, BIF_ARG_1, &multi)) { case ERTS_DEMONITOR_FALSE: case ERTS_DEMONITOR_TRUE: BIF_RET(am_true); @@ -510,6 +525,7 @@ BIF_RETTYPE demonitor_1(BIF_ALIST_1) BIF_RETTYPE demonitor_2(BIF_ALIST_2) { Eterm res = am_true; + Eterm multi = am_false; int info = 0; int flush = 0; Eterm list = BIF_ARG_2; @@ -532,13 +548,18 @@ BIF_RETTYPE demonitor_2(BIF_ALIST_2) if (is_not_nil(list)) goto badarg; - switch (demonitor(BIF_P, BIF_ARG_1)) { + switch (demonitor(BIF_P, BIF_ARG_1, &multi)) { case ERTS_DEMONITOR_FALSE: if (info) res = am_false; - if (flush) - BIF_TRAP2(flush_monitor_message_trap, BIF_P, BIF_ARG_1, res); + if (flush) { + flush_messages: + BIF_TRAP3(flush_monitor_messages_trap, BIF_P, + BIF_ARG_1, multi, res); + } case ERTS_DEMONITOR_TRUE: + if (multi == am_true && flush) + goto flush_messages; BIF_RET(res); case ERTS_DEMONITOR_YIELD_TRUE: ERTS_BIF_YIELD_RETURN(BIF_P, am_true); @@ -597,14 +618,12 @@ erts_queue_monitor_message(Process *p, } static BIF_RETTYPE -local_pid_monitor(Process *p, Eterm target) +local_pid_monitor(Process *p, Eterm target, Eterm mon_ref, int bool) { BIF_RETTYPE ret; - Eterm mon_ref; Process *rp; ErtsProcLocks p_locks = ERTS_PROC_LOCK_MAIN|ERTS_PROC_LOCK_LINK; - mon_ref = erts_make_ref(p); ERTS_BIF_PREP_RET(ret, mon_ref); if (target == p->common.id) { return ret; @@ -617,12 +636,18 @@ local_pid_monitor(Process *p, Eterm target) if (!rp) { erts_smp_proc_unlock(p, ERTS_PROC_LOCK_LINK); p_locks &= ~ERTS_PROC_LOCK_LINK; - erts_queue_monitor_message(p, &p_locks, - mon_ref, am_process, target, am_noproc); + if (bool) + ret = am_false; + else + erts_queue_monitor_message(p, &p_locks, + mon_ref, am_process, target, am_noproc); } else { ASSERT(rp != p); + if (bool) + ret = am_true; + erts_add_monitor(&ERTS_P_MONITORS(p), MON_ORIGIN, mon_ref, target, NIL); erts_add_monitor(&ERTS_P_MONITORS(rp), MON_TARGET, mon_ref, p->common.id, NIL); @@ -746,13 +771,28 @@ BIF_RETTYPE monitor_2(BIF_ALIST_2) int deref_de = 0; /* Only process monitors are implemented */ - if (BIF_ARG_1 != am_process) { + switch (BIF_ARG_1) { + case am_time_offset: { + Eterm ref; + if (BIF_ARG_2 != am_clock_service) + goto error; + ref = erts_make_ref(BIF_P); + erts_smp_proc_lock(BIF_P, ERTS_PROC_LOCK_LINK); + erts_add_monitor(&ERTS_P_MONITORS(BIF_P), MON_TIME_OFFSET, + ref, am_clock_service, NIL); + erts_smp_proc_unlock(BIF_P, ERTS_PROC_LOCK_LINK); + erts_monitor_time_offset(BIF_P->common.id, ref); + BIF_RET(ref); + } + case am_process: + break; + default: goto error; } if (is_internal_pid(target)) { local_pid: - ret = local_pid_monitor(BIF_P, target); + ret = local_pid_monitor(BIF_P, target, erts_make_ref(BIF_P), 0); } else if (is_external_pid(target)) { dep = external_pid_dist_entry(target); if (dep == erts_this_dist_entry) @@ -795,6 +835,25 @@ BIF_RETTYPE monitor_2(BIF_ALIST_2) return ret; } +BIF_RETTYPE erts_internal_monitor_process_2(BIF_ALIST_2) +{ + if (is_not_internal_pid(BIF_ARG_1)) { + if (is_external_pid(BIF_ARG_1) + && (external_pid_dist_entry(BIF_ARG_1) + == erts_this_dist_entry)) { + BIF_RET(am_false); + } + goto badarg; + } + + if (is_not_internal_ref(BIF_ARG_2)) + goto badarg; + + BIF_RET(local_pid_monitor(BIF_P, BIF_ARG_1, BIF_ARG_2, 1)); + +badarg: + BIF_ERROR(BIF_P, BADARG); +} /**********************************************************************/ /* this is a combination of the spawn and link BIFs */ @@ -3542,91 +3601,6 @@ BIF_RETTYPE self_0(BIF_ALIST_0) /**********************************************************************/ -/* - New representation of refs in R9, see erl_term.h - - In the first data word, only the usual 18 bits are used. Ordinarily, - in "long refs" all words are used (in other words, practically never - wrap around), but for compatibility with older nodes, "short refs" - exist. Short refs come into being by being converted from the old - external format for refs (tag REFERENCE_EXT). Short refs are - converted back to the old external format. - - When converting a long ref to the external format in the case of - preparing for sending to an older node, the ref is truncated by only - using the first word (with 18 significant bits), and using the old tag - REFERENCE_EXT. - - When comparing refs or different size, only the parts up to the length - of the shorter operand are used. This has the desirable effect that a - long ref sent to an old node and back will be treated as equal to - the original, although some of the bits have been lost. - - The hash value for a ref always considers only the first word, since - in the above scenario, the original and the copy should have the same - hash value. -*/ - -static Uint32 reference0; /* Initialized in erts_init_bif */ -static Uint32 reference1; -static Uint32 reference2; -static erts_smp_spinlock_t make_ref_lock; -static erts_smp_mtx_t ports_snapshot_mtx; -erts_smp_atomic_t erts_dead_ports_ptr; /* To store dying ports during snapshot */ - -void -erts_make_ref_in_array(Uint32 ref[ERTS_MAX_REF_NUMBERS]) -{ - erts_smp_spin_lock(&make_ref_lock); - - reference0++; - if (reference0 >= MAX_REFERENCE) { - reference0 = 0; - reference1++; - if (reference1 == 0) { - reference2++; - } - } - - ref[0] = reference0; - ref[1] = reference1; - ref[2] = reference2; - - erts_smp_spin_unlock(&make_ref_lock); -} - -Eterm erts_make_ref_in_buffer(Eterm buffer[REF_THING_SIZE]) -{ - Eterm* hp = buffer; - Uint32 ref[ERTS_MAX_REF_NUMBERS]; - - erts_make_ref_in_array(ref); - write_ref_thing(hp, ref[0], ref[1], ref[2]); - return make_internal_ref(hp); -} - -Eterm erts_make_ref(Process *p) -{ - Eterm* hp; - Uint32 ref[ERTS_MAX_REF_NUMBERS]; - - ERTS_SMP_LC_ASSERT(ERTS_PROC_LOCK_MAIN & erts_proc_lc_my_proc_locks(p)); - - hp = HAlloc(p, REF_THING_SIZE); - - erts_make_ref_in_array(ref); - write_ref_thing(hp, ref[0], ref[1], ref[2]); - - return make_internal_ref(hp); -} - -BIF_RETTYPE make_ref_0(BIF_ALIST_0) -{ - return erts_make_ref(BIF_P); -} - -/**********************************************************************/ - /* return the time of day */ BIF_RETTYPE time_0(BIF_ALIST_0) @@ -4607,6 +4581,28 @@ BIF_RETTYPE system_flag_2(BIF_ALIST_2) break; } #endif + } else if (BIF_ARG_1 == am_time_offset + && ERTS_IS_ATOM_STR("finalize", BIF_ARG_2)) { + ErtsTimeOffsetState res; + erts_smp_proc_unlock(BIF_P, ERTS_PROC_LOCK_MAIN); + res = erts_finalize_time_offset(); + erts_smp_proc_lock(BIF_P, ERTS_PROC_LOCK_MAIN); + switch (res) { + case ERTS_TIME_OFFSET_PRELIMINARY: { + DECL_AM(preliminary); + BIF_RET(AM_preliminary); + } + case ERTS_TIME_OFFSET_FINAL: { + DECL_AM(final); + BIF_RET(AM_final); + } + case ERTS_TIME_OFFSET_VOLATILE: { + DECL_AM(volatile); + BIF_RET(AM_volatile); + } + default: + ERTS_INTERNAL_ERROR("Unknown state"); + } } else if (ERTS_IS_ATOM_STR("scheduling_statistics", BIF_ARG_1)) { int what; if (ERTS_IS_ATOM_STR("disable", BIF_ARG_2)) @@ -4894,11 +4890,6 @@ void erts_init_trap_export(Export* ep, Eterm m, Eterm f, Uint a, void erts_init_bif(void) { - reference0 = 0; - reference1 = 0; - reference2 = 0; - - erts_smp_spinlock_init(&make_ref_lock, "make_ref"); erts_smp_mtx_init(&ports_snapshot_mtx, "ports_snapshot"); erts_smp_atomic_init_nob(&erts_dead_ports_ptr, (erts_aint_t) NULL); @@ -4919,9 +4910,13 @@ void erts_init_bif(void) am_erts_internal, am_dsend_continue_trap, 1, dsend_continue_trap_1); - flush_monitor_message_trap = erts_export_put(am_erlang, - am_flush_monitor_message, - 2); + flush_monitor_messages_trap = erts_export_put(am_erts_internal, + am_flush_monitor_messages, + 3); + + erts_convert_time_unit_trap = erts_export_put(am_erlang, + am_convert_time_unit, + 3); set_cpu_topology_trap = erts_export_put(am_erlang, am_set_cpu_topology, diff --git a/erts/emulator/beam/bif.h b/erts/emulator/beam/bif.h index 837cb017ac..d461c3f479 100644 --- a/erts/emulator/beam/bif.h +++ b/erts/emulator/beam/bif.h @@ -21,6 +21,7 @@ #define __BIF_H__ extern Export* erts_format_cpu_topology_trap; +extern Export *erts_convert_time_unit_trap; #define BIF_RETTYPE Eterm diff --git a/erts/emulator/beam/bif.tab b/erts/emulator/beam/bif.tab index 5a0ee2ffc3..471f687101 100644 --- a/erts/emulator/beam/bif.tab +++ b/erts/emulator/beam/bif.tab @@ -92,6 +92,8 @@ bif erlang:loaded/0 bif erlang:localtime/0 bif erlang:localtime_to_universaltime/2 bif erlang:make_ref/0 +bif erlang:unique_integer/0 +bif erlang:unique_integer/1 bif erlang:md5/1 bif erlang:md5_init/0 bif erlang:md5_update/2 @@ -104,6 +106,13 @@ ubif erlang:node/1 ubif erlang:node/0 bif erlang:nodes/1 bif erlang:now/0 +bif erlang:monotonic_time/0 +bif erlang:monotonic_time/1 +bif erlang:system_time/0 +bif erlang:system_time/1 +bif erlang:time_offset/0 +bif erlang:time_offset/1 +bif erlang:timestamp/0 bif erlang:open_port/2 @@ -160,6 +169,15 @@ bif erts_internal:map_to_tuple_keys/1 bif erts_internal:map_type/1 bif erts_internal:map_hashmap_children/1 +bif erts_internal:time_unit/0 + +bif erts_internal:get_bif_timer_servers/0 +bif erts_internal:create_bif_timer/0 +bif erts_internal:access_bif_timer/1 + +bif erts_internal:monitor_process/2 +bif erts_internal:is_system_process/1 + # inet_db support bif erlang:port_set_data/2 bif erlang:port_get_data/1 @@ -202,11 +220,6 @@ bif math:sqrt/1 bif math:atan2/2 bif math:pow/2 -bif erlang:start_timer/3 -bif erlang:send_after/3 -bif erlang:cancel_timer/1 -bif erlang:read_timer/1 - bif erlang:make_tuple/2 bif erlang:append_element/2 bif erlang:make_tuple/3 @@ -350,6 +363,8 @@ bif os:getenv/0 bif os:getenv/1 bif os:getpid/0 bif os:timestamp/0 +bif os:system_time/0 +bif os:system_time/1 # # Bifs in the erl_ddll module (the module actually does not exist) diff --git a/erts/emulator/beam/big.c b/erts/emulator/beam/big.c index d1e46e3063..a4ea9c59ca 100644 --- a/erts/emulator/beam/big.c +++ b/erts/emulator/beam/big.c @@ -1577,6 +1577,46 @@ Eterm erts_sint64_to_big(Sint64 x, Eterm **hpp) return make_big(hp); } +Eterm +erts_uint64_array_to_big(Uint **hpp, int neg, int len, Uint64 *array) +{ + Uint *headerp; + int i, pot_digits, digits; + + headerp = *hpp; + + pot_digits = digits = 0; + for (i = 0; i < len; i++) { +#if defined(ARCH_32) || HALFWORD_HEAP + Uint low_val = array[i] & ((Uint) 0xffffffff); + Uint high_val = (array[i] >> 32) & ((Uint) 0xffffffff); + BIG_DIGIT(headerp, pot_digits) = low_val; + pot_digits++; + if (low_val) + digits = pot_digits; + BIG_DIGIT(headerp, pot_digits) = high_val; + pot_digits++; + if (high_val) + digits = pot_digits; +#else + Uint val = array[i]; + BIG_DIGIT(headerp, pot_digits) = val; + pot_digits++; + if (val) + digits = pot_digits; +#endif + } + + if (neg) + *headerp = make_neg_bignum_header(digits); + else + *headerp = make_pos_bignum_header(digits); + + *hpp = headerp + 1 + digits; + + return make_big(headerp); +} + /* ** Convert a bignum to a double float */ diff --git a/erts/emulator/beam/big.h b/erts/emulator/beam/big.h index da31876d75..4e4611de16 100644 --- a/erts/emulator/beam/big.h +++ b/erts/emulator/beam/big.h @@ -104,6 +104,9 @@ typedef Uint dsize_t; /* Vector size type */ : ERTS_UINT64_BIG_HEAP_SIZE__((X) >= 0 ? (X) : -(Uint64)(X))) #define ERTS_UINT64_HEAP_SIZE(X) \ (IS_USMALL(0, (X)) ? 0 : ERTS_UINT64_BIG_HEAP_SIZE__((X))) +#define ERTS_MAX_SINT64_HEAP_SIZE (1 + 2) +#define ERTS_MAX_UINT64_HEAP_SIZE (1 + 2) +#define ERTS_UINT64_ARRAY_TO_BIG_MAX_HEAP_SZ(LEN) (2*(LEN)+1) #else @@ -111,6 +114,9 @@ typedef Uint dsize_t; /* Vector size type */ (IS_SSMALL((X)) ? 0 : (1 + 1)) #define ERTS_UINT64_HEAP_SIZE(X) \ (IS_USMALL(0, (X)) ? 0 : (1 + 1)) +#define ERTS_MAX_SINT64_HEAP_SIZE (1 + 1) +#define ERTS_MAX_UINT64_HEAP_SIZE (1 + 1) +#define ERTS_UINT64_ARRAY_TO_BIG_MAX_HEAP_SZ(LEN) ((LEN)+1) #endif @@ -156,6 +162,7 @@ int term_to_Uint(Eterm, Uint*); int term_to_UWord(Eterm, UWord*); int term_to_Sint(Eterm, Sint*); #if HAVE_INT64 +Eterm erts_uint64_array_to_big(Uint **, int, int, Uint64 *); int term_to_Uint64(Eterm, Uint64*); int term_to_Sint64(Eterm, Sint64*); #endif diff --git a/erts/emulator/beam/erl_alloc.types b/erts/emulator/beam/erl_alloc.types index 61def65235..e2f8da38b9 100644 --- a/erts/emulator/beam/erl_alloc.types +++ b/erts/emulator/beam/erl_alloc.types @@ -269,6 +269,7 @@ type BUSY_CALLER_TAB SHORT_LIVED SYSTEM busy_caller_table type BUSY_CALLER SHORT_LIVED SYSTEM busy_caller type PROC_SYS_TSK SHORT_LIVED PROCESSES proc_sys_task type PROC_SYS_TSK_QS SHORT_LIVED PROCESSES proc_sys_task_queues +type NEW_TIME_OFFSET SHORT_LIVED SYSTEM new_time_offset +if threads_no_smp # Need thread safe allocs, but std_alloc and fix_alloc are not; @@ -364,6 +365,7 @@ type AINFO_REQ STANDARD_LOW SYSTEM alloc_info_request type SCHED_WTIME_REQ STANDARD_LOW SYSTEM sched_wall_time_request type GC_INFO_REQ STANDARD_LOW SYSTEM gc_info_request type PORT_DATA_HEAP STANDARD_LOW SYSTEM port_data_heap +type BIF_TIMER_DATA LONG_LIVED_LOW SYSTEM bif_timer_data +else # "fullword" @@ -384,6 +386,7 @@ type AINFO_REQ SHORT_LIVED SYSTEM alloc_info_request type SCHED_WTIME_REQ SHORT_LIVED SYSTEM sched_wall_time_request type GC_INFO_REQ SHORT_LIVED SYSTEM gc_info_request type PORT_DATA_HEAP STANDARD SYSTEM port_data_heap +type BIF_TIMER_DATA LONG_LIVED SYSTEM bif_timer_data +endif diff --git a/erts/emulator/beam/erl_bif_binary.c b/erts/emulator/beam/erl_bif_binary.c index bd0d7c71cc..934904d58e 100644 --- a/erts/emulator/beam/erl_bif_binary.c +++ b/erts/emulator/beam/erl_bif_binary.c @@ -38,6 +38,7 @@ #include "big.h" #include "erl_binary.h" #include "erl_bits.h" +#include "erl_bif_unique.h" /* diff --git a/erts/emulator/beam/erl_bif_ddll.c b/erts/emulator/beam/erl_bif_ddll.c index 56cd2ba04f..fc4f819f56 100644 --- a/erts/emulator/beam/erl_bif_ddll.c +++ b/erts/emulator/beam/erl_bif_ddll.c @@ -45,6 +45,7 @@ #include "big.h" #include "dist.h" #include "erl_version.h" +#include "erl_bif_unique.h" #include "dtrace-wrapper.h" #ifdef ERTS_SMP diff --git a/erts/emulator/beam/erl_bif_info.c b/erts/emulator/beam/erl_bif_info.c index 0774ab51af..2eeebab9a3 100644 --- a/erts/emulator/beam/erl_bif_info.c +++ b/erts/emulator/beam/erl_bif_info.c @@ -42,6 +42,7 @@ #include "erl_cpu_topology.h" #include "erl_async.h" #include "erl_thr_progress.h" +#include "erl_bif_unique.h" #define ERTS_PTAB_WANT_DEBUG_FUNCS__ #include "erl_ptab.h" #ifdef HIPE @@ -540,6 +541,7 @@ pi_locks(Eterm info) switch (info) { case am_status: case am_priority: + case am_trap_exit: return ERTS_PROC_LOCK_STATUS; case am_links: case am_monitors: @@ -592,7 +594,7 @@ static Eterm pi_args[] = { am_min_bin_vheap_size, am_current_location, am_current_stacktrace, -}; +}; #define ERTS_PI_ARGS ((int) (sizeof(pi_args)/sizeof(Eterm))) @@ -2102,6 +2104,46 @@ BIF_RETTYPE system_info_1(BIF_ALIST_1) BIF_RET(am_opt); #endif BIF_RET(res); + } else if (BIF_ARG_1 == am_time_offset) { + switch (erts_time_offset_state()) { + case ERTS_TIME_OFFSET_PRELIMINARY: { + ERTS_DECL_AM(preliminary); + BIF_RET(AM_preliminary); + } + case ERTS_TIME_OFFSET_FINAL: { + ERTS_DECL_AM(final); + BIF_RET(AM_final); + } + case ERTS_TIME_OFFSET_VOLATILE: { + ERTS_DECL_AM(volatile); + BIF_RET(AM_volatile); + } + default: + ERTS_INTERNAL_ERROR("Invalid time offset state"); + } + } else if (ERTS_IS_ATOM_STR("os_monotonic_time_source", BIF_ARG_1)) { + BIF_RET(erts_monotonic_time_source(BIF_P)); + } else if (ERTS_IS_ATOM_STR("time_correction", BIF_ARG_1)) { + BIF_RET(erts_has_time_correction() ? am_true : am_false); + } else if (ERTS_IS_ATOM_STR("start_time", BIF_ARG_1)) { + BIF_RET(erts_get_monotonic_start_time(BIF_P)); + } else if (ERTS_IS_ATOM_STR("time_warp_mode", BIF_ARG_1)) { + switch (erts_time_warp_mode()) { + case ERTS_NO_TIME_WARP_MODE: { + ERTS_DECL_AM(no_time_warp); + BIF_RET(AM_no_time_warp); + } + case ERTS_SINGLE_TIME_WARP_MODE: { + ERTS_DECL_AM(single_time_warp); + BIF_RET(AM_single_time_warp); + } + case ERTS_MULTI_TIME_WARP_MODE: { + ERTS_DECL_AM(multi_time_warp); + BIF_RET(AM_multi_time_warp); + } + default: + ERTS_INTERNAL_ERROR("Invalid time warp mode"); + } } else if (BIF_ARG_1 == am_allocated_areas) { res = erts_allocated_areas(NULL, NULL, BIF_P); BIF_RET(res); @@ -2703,9 +2745,11 @@ BIF_RETTYPE system_info_1(BIF_ALIST_1) BIF_RET(make_small(erts_db_get_max_tabs())); } else if (ERTS_IS_ATOM_STR("tolerant_timeofday",BIF_ARG_1)) { - BIF_RET(erts_disable_tolerant_timeofday - ? am_disabled - : am_enabled); + if (erts_has_time_correction() + && erts_time_offset_state() == ERTS_TIME_OFFSET_FINAL) { + BIF_RET(am_enabled); + } + BIF_RET(am_disabled); } else if (ERTS_IS_ATOM_STR("eager_check_io",BIF_ARG_1)) { BIF_RET(erts_eager_check_io ? am_true : am_false); @@ -3403,6 +3447,29 @@ BIF_RETTYPE erts_debug_get_internal_state_1(BIF_ALIST_1) else if (ERTS_IS_ATOM_STR("mmap", BIF_ARG_1)) { BIF_RET(erts_mmap_debug_info(BIF_P)); } + else if (ERTS_IS_ATOM_STR("unique_monotonic_integer_state", BIF_ARG_1)) { + BIF_RET(erts_debug_get_unique_monotonic_integer_state(BIF_P)); + } + else if (ERTS_IS_ATOM_STR("min_unique_monotonic_integer", BIF_ARG_1)) { + Sint64 value = erts_get_min_unique_monotonic_integer(); + if (IS_SSMALL(value)) + BIF_RET(make_small(value)); + else { + Uint hsz = ERTS_SINT64_HEAP_SIZE(value); + Eterm *hp = HAlloc(BIF_P, hsz); + BIF_RET(erts_sint64_to_big(value, &hp)); + } + } + else if (ERTS_IS_ATOM_STR("min_unique_integer", BIF_ARG_1)) { + Sint64 value = erts_get_min_unique_integer(); + if (IS_SSMALL(value)) + BIF_RET(make_small(value)); + else { + Uint hsz = ERTS_SINT64_HEAP_SIZE(value); + Eterm *hp = HAlloc(BIF_P, hsz); + BIF_RET(erts_sint64_to_big(value, &hp)); + } + } } else if (is_tuple(BIF_ARG_1)) { Eterm* tp = tuple_val(BIF_ARG_1); @@ -3619,6 +3686,38 @@ BIF_RETTYPE erts_debug_get_internal_state_1(BIF_ALIST_1) break; } + case 3: { + if (ERTS_IS_ATOM_STR("check_time_config", tp[1])) { + int res, time_correction; + ErtsTimeWarpMode time_warp_mode; + if (tp[2] == am_true) + time_correction = !0; + else if (tp[2] == am_false) + time_correction = 0; + else + break; + if (ERTS_IS_ATOM_STR("no_time_warp", tp[3])) + time_warp_mode = ERTS_NO_TIME_WARP_MODE; + else if (ERTS_IS_ATOM_STR("single_time_warp", tp[3])) + time_warp_mode = ERTS_SINGLE_TIME_WARP_MODE; + else if (ERTS_IS_ATOM_STR("multi_time_warp", tp[3])) + time_warp_mode = ERTS_MULTI_TIME_WARP_MODE; + else + break; + res = erts_check_time_adj_support(time_correction, + time_warp_mode); + BIF_RET(res ? am_true : am_false); + } + else if (ERTS_IS_ATOM_STR("make_unique_integer", tp[1])) { + Eterm res = erts_debug_make_unique_integer(BIF_P, + tp[2], + tp[3]); + if (is_non_value(res)) + break; + BIF_RET(res); + } + break; + } default: break; } @@ -3626,6 +3725,24 @@ BIF_RETTYPE erts_debug_get_internal_state_1(BIF_ALIST_1) BIF_ERROR(BIF_P, BADARG); } +BIF_RETTYPE erts_internal_is_system_process_1(BIF_ALIST_1) +{ + if (is_internal_pid(BIF_ARG_1)) { + Process *rp = erts_proc_lookup(BIF_ARG_1); + if (rp && (rp->static_flags & ERTS_STC_FLG_SYSTEM_PROC)) + BIF_RET(am_true); + BIF_RET(am_false); + } + + if (is_external_pid(BIF_ARG_1) + && external_pid_dist_entry(BIF_ARG_1) == erts_this_dist_entry) { + BIF_RET(am_false); + } + + BIF_ERROR(BIF_P, BADARG); +} + + static erts_smp_atomic_t hipe_test_reschedule_flag; @@ -3927,6 +4044,10 @@ BIF_RETTYPE erts_debug_set_internal_state_2(BIF_ALIST_2) #endif erl_exit(ERTS_DUMP_EXIT, "%T", BIF_ARG_2); } + else if (ERTS_IS_ATOM_STR("unique_monotonic_integer_state", BIF_ARG_1)) { + int res = erts_debug_set_unique_monotonic_integer_state(BIF_ARG_2); + BIF_RET(res ? am_true : am_false); + } } BIF_ERROR(BIF_P, BADARG); diff --git a/erts/emulator/beam/erl_bif_timer.c b/erts/emulator/beam/erl_bif_timer.c index 03ac97283c..0bd8d20c34 100644 --- a/erts/emulator/beam/erl_bif_timer.c +++ b/erts/emulator/beam/erl_bif_timer.c @@ -27,6 +27,7 @@ #include "error.h" #include "big.h" #include "erl_thr_progress.h" +#include "erl_bif_unique.h" /**************************************************************************** ** BIF Timer support @@ -480,7 +481,7 @@ setup_bif_timer(Uint32 xflags, tab_insert(btm); ASSERT(btm == tab_find(ref)); - btm->tm.active = 0; /* MUST be initalized */ + erts_init_timer(&btm->tm); erts_set_timer(&btm->tm, (ErlTimeoutProc) bif_timer_timeout, (ErlCancelProc) bif_timer_cleanup, @@ -489,8 +490,9 @@ setup_bif_timer(Uint32 xflags, return ref; } +BIF_RETTYPE old_send_after_3(BIF_ALIST_3); /* send_after(Time, Pid, Message) -> Ref */ -BIF_RETTYPE send_after_3(BIF_ALIST_3) +BIF_RETTYPE old_send_after_3(BIF_ALIST_3) { Eterm res; @@ -510,8 +512,9 @@ BIF_RETTYPE send_after_3(BIF_ALIST_3) } } +BIF_RETTYPE old_start_timer_3(BIF_ALIST_3); /* start_timer(Time, Pid, Message) -> Ref */ -BIF_RETTYPE start_timer_3(BIF_ALIST_3) +BIF_RETTYPE old_start_timer_3(BIF_ALIST_3) { Eterm res; @@ -531,8 +534,9 @@ BIF_RETTYPE start_timer_3(BIF_ALIST_3) } } +BIF_RETTYPE old_cancel_timer_1(BIF_ALIST_1); /* cancel_timer(Ref) -> false | RemainingTime */ -BIF_RETTYPE cancel_timer_1(BIF_ALIST_1) +BIF_RETTYPE old_cancel_timer_1(BIF_ALIST_1) { Eterm res; ErtsBifTimer *btm; @@ -569,8 +573,9 @@ BIF_RETTYPE cancel_timer_1(BIF_ALIST_1) BIF_RET(res); } +BIF_RETTYPE old_read_timer_1(BIF_ALIST_1); /* read_timer(Ref) -> false | RemainingTime */ -BIF_RETTYPE read_timer_1(BIF_ALIST_1) +BIF_RETTYPE old_read_timer_1(BIF_ALIST_1) { Eterm res; ErtsBifTimer *btm; @@ -652,7 +657,7 @@ erts_cancel_bif_timers(Process *p, ErtsProcLocks plocks) erts_smp_btm_rwunlock(); } -void erts_bif_timer_init(void) +static void erts_old_bif_timer_init(void) { int i; no_bif_timers = 0; @@ -703,3 +708,146 @@ erts_bif_timer_foreach(void (*func)(Eterm, Eterm, ErlHeapFragment *, void *), } } } + +typedef struct { + Uint ref_heap[REF_THING_SIZE]; + Eterm pid[1]; +} ErtsBifTimerServers; + +static ErtsBifTimerServers *bif_timer_servers; + +void erts_bif_timer_init(void) +{ + erts_old_bif_timer_init(); +} + +void +erts_bif_timer_start_servers(Eterm parent) +{ + Process *parent_proc; + Eterm *hp, btr_ref, arg_list_end; + ErlSpawnOpts so; + int i; + + bif_timer_servers = erts_alloc(ERTS_ALC_T_BIF_TIMER_DATA, + (sizeof(ErtsBifTimerServers) + + (sizeof(Eterm)*(erts_no_schedulers-1)))); + + so.flags = SPO_USE_ARGS|SPO_SYSTEM_PROC|SPO_PREFER_SCHED|SPO_OFF_HEAP_MSGS; + so.min_heap_size = H_MIN_SIZE; + so.min_vheap_size = BIN_VH_MIN_SIZE; + so.priority = PRIORITY_MAX; + so.max_gen_gcs = (Uint16) erts_smp_atomic32_read_nob(&erts_max_gen_gcs); + + /* + * Parent is "init" and schedulers have not yet been started, so it + * *should* be alive and well... + */ + ASSERT(is_internal_pid(parent)); + parent_proc = (Process *) erts_ptab_pix2intptr_ddrb(&erts_proc, + internal_pid_index(parent)); + ASSERT(parent_proc); + ASSERT(parent_proc->common.id == parent); + ASSERT(!ERTS_PROC_IS_EXITING(parent_proc)); + + erts_smp_proc_lock(parent_proc, ERTS_PROC_LOCK_MAIN); + + hp = HAlloc(parent_proc, 2*erts_no_schedulers + 2 + REF_THING_SIZE); + + btr_ref = erts_make_ref_in_buffer(hp); + hp += REF_THING_SIZE; + + arg_list_end = CONS(hp, btr_ref, NIL); + hp += 2; + + for (i = 0; i < erts_no_schedulers; i++) { + int sched = i+1; + Eterm arg_list = CONS(hp, make_small(i+1), arg_list_end); + hp += 2; + + so.scheduler = sched; /* Preferred scheduler */ + + bif_timer_servers->pid[i] = erl_create_process(parent_proc, + am_erts_internal, + am_bif_timer_server, + arg_list, + &so); + } + + erts_smp_proc_unlock(parent_proc, ERTS_PROC_LOCK_MAIN); + + hp = internal_ref_val(btr_ref); + for (i = 0; i < REF_THING_SIZE; i++) + bif_timer_servers->ref_heap[i] = hp[i]; +} + +BIF_RETTYPE +erts_internal_get_bif_timer_servers_0(BIF_ALIST_0) +{ + int i; + Eterm *hp, res = NIL; + + hp = HAlloc(BIF_P, erts_no_schedulers*2); + for (i = erts_no_schedulers-1; i >= 0; i--) { + res = CONS(hp, bif_timer_servers->pid[i], res); + hp += 2; + } + BIF_RET(res); +} + +BIF_RETTYPE +erts_internal_access_bif_timer_1(BIF_ALIST_1) +{ + int ix; + Uint32 *rdp; + Eterm ref, pid, *hp, res; + + if (is_not_internal_ref(BIF_ARG_1)) { + if (is_not_ref(BIF_ARG_1)) + BIF_ERROR(BIF_P, BADARG); + BIF_RET(am_undefined); + } + + rdp = internal_ref_numbers(BIF_ARG_1); + ix = (int) erts_get_ref_numbers_thr_id(rdp); + if (ix < 1 || erts_no_schedulers < ix) + BIF_RET(am_undefined); + + pid = bif_timer_servers->pid[ix-1]; + ASSERT(is_internal_pid(pid)); + + hp = HAlloc(BIF_P, 3 /* 2-tuple */ + REF_THING_SIZE); + for (ix = 0; ix < REF_THING_SIZE; ix++) + hp[ix] = bif_timer_servers->ref_heap[ix]; + ref = make_internal_ref(&hp[0]); + hp += REF_THING_SIZE; + + res = TUPLE2(hp, ref, pid); + BIF_RET(res); +} + +BIF_RETTYPE +erts_internal_create_bif_timer_0(BIF_ALIST_0) +{ + ErtsSchedulerData *esdp = ERTS_PROC_GET_SCHDATA(BIF_P); + Eterm *hp, btr_ref, t_ref, pid, res; + int ix; + + hp = HAlloc(BIF_P, 4 /* 3-tuple */ + 2*REF_THING_SIZE); + for (ix = 0; ix < REF_THING_SIZE; ix++) + hp[ix] = bif_timer_servers->ref_heap[ix]; + btr_ref = make_internal_ref(&hp[0]); + hp += REF_THING_SIZE; + + t_ref = erts_sched_make_ref_in_buffer(esdp, hp); + hp += REF_THING_SIZE; + + ASSERT(erts_get_ref_numbers_thr_id(internal_ref_numbers(t_ref)) + == (Uint32) esdp->no); + + pid = bif_timer_servers->pid[((int) esdp->no) - 1]; + + res = TUPLE3(hp, btr_ref, pid, t_ref); + + BIF_RET(res); +} diff --git a/erts/emulator/beam/erl_bif_timer.h b/erts/emulator/beam/erl_bif_timer.h index 1197c176f5..c2f5dfd3c3 100644 --- a/erts/emulator/beam/erl_bif_timer.h +++ b/erts/emulator/beam/erl_bif_timer.h @@ -33,4 +33,5 @@ void erts_cancel_bif_timers(Process *p, ErtsProcLocks plocks); void erts_bif_timer_init(void); void erts_bif_timer_foreach(void (*func)(Eterm,Eterm,ErlHeapFragment *,void *), void *arg); +void erts_bif_timer_start_servers(Eterm); #endif diff --git a/erts/emulator/beam/erl_bif_trace.c b/erts/emulator/beam/erl_bif_trace.c index f5e582b1c5..ac57205c47 100644 --- a/erts/emulator/beam/erl_bif_trace.c +++ b/erts/emulator/beam/erl_bif_trace.c @@ -38,6 +38,7 @@ #include "beam_bp.h" #include "erl_binary.h" #include "erl_thr_progress.h" +#include "erl_bif_unique.h" #define DECL_AM(S) Eterm AM_ ## S = am_atom_put(#S, sizeof(#S) - 1) diff --git a/erts/emulator/beam/erl_bif_unique.c b/erts/emulator/beam/erl_bif_unique.c new file mode 100644 index 0000000000..57b0bab72f --- /dev/null +++ b/erts/emulator/beam/erl_bif_unique.c @@ -0,0 +1,556 @@ +/* + * %CopyrightBegin% + * + * Copyright Ericsson AB 2014. All Rights Reserved. + * + * The contents of this file are subject to the Erlang Public License, + * Version 1.1, (the "License"); you may not use this file except in + * compliance with the License. You should have received a copy of the + * Erlang Public License along with this software. If not, it can be + * retrieved online at http://www.erlang.org/. + * + * Software distributed under the License is distributed on an "AS IS" + * basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See + * the License for the specific language governing rights and limitations + * under the License. + * + * %CopyrightEnd% + */ + +#ifdef HAVE_CONFIG_H +# include "config.h" +#endif + +#include "sys.h" +#include "erl_vm.h" +#include "erl_alloc.h" +#include "export.h" +#include "bif.h" +#include "erl_bif_unique.h" + +/* * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * *\ + * Reference * +\* */ + +static union { + erts_atomic64_t count; + char align__[ERTS_CACHE_LINE_SIZE]; +} global_reference erts_align_attribute(ERTS_CACHE_LINE_SIZE); + + +/* + * ref[0] indicate thread creating reference as follows: + * + * - ref[0] == 0 => Non-scheduler thread; + * - else; ref[0] <= erts_no_schedulers => + * ordinary scheduler with id == ref[0]; + * - else; ref[0] <= erts_no_schedulers + * + erts_no_dirty_cpu_schedulers => + * dirty cpu scheduler with id == 'ref[0] - erts_no_schedulers'; + * - else => + * dirty io scheduler with id == 'ref[0] + * - erts_no_schedulers + * - erts_no_dirty_cpu_schedulers' + */ + +#ifdef DEBUG +static Uint32 max_thr_id; +#endif + +static void +init_reference(void) +{ +#ifdef DEBUG + max_thr_id = (Uint32) erts_no_schedulers; +#ifdef ERTS_DIRTY_SCHEDULERS + max_thr_id += (Uint32) erts_no_dirty_cpu_schedulers; + max_thr_id += (Uint32) erts_no_dirty_io_schedulers; +#endif +#endif + erts_atomic64_init_nob(&global_reference.count, 0); +} + +static ERTS_INLINE void +global_make_ref_in_array(Uint32 thr_id, Uint32 ref[ERTS_MAX_REF_NUMBERS]) +{ + Uint64 value; + + value = (Uint64) erts_atomic64_inc_read_mb(&global_reference.count); + + erts_set_ref_numbers(ref, thr_id, value); +} + +static ERTS_INLINE void +make_ref_in_array(Uint32 ref[ERTS_MAX_REF_NUMBERS]) +{ + ErtsSchedulerData *esdp = erts_get_scheduler_data(); + if (esdp) + erts_sched_make_ref_in_array(esdp, ref); + else + global_make_ref_in_array(0, ref); +} + +void +erts_make_ref_in_array(Uint32 ref[ERTS_MAX_REF_NUMBERS]) +{ + make_ref_in_array(ref); +} + +Eterm erts_make_ref_in_buffer(Eterm buffer[REF_THING_SIZE]) +{ + Eterm* hp = buffer; + Uint32 ref[ERTS_MAX_REF_NUMBERS]; + + make_ref_in_array(ref); + write_ref_thing(hp, ref[0], ref[1], ref[2]); + return make_internal_ref(hp); +} + +Eterm erts_make_ref(Process *c_p) +{ + Eterm* hp; + Uint32 ref[ERTS_MAX_REF_NUMBERS]; + + ERTS_SMP_LC_ASSERT(ERTS_PROC_LOCK_MAIN & erts_proc_lc_my_proc_locks(c_p)); + + hp = HAlloc(c_p, REF_THING_SIZE); + + make_ref_in_array(ref); + write_ref_thing(hp, ref[0], ref[1], ref[2]); + + return make_internal_ref(hp); +} + +/* * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * *\ + * Unique Integer * +\* */ + +static struct { + union { + struct { + int left_shift; + int right_shift; + Uint64 mask; + Uint64 val0_max; + } o; + char align__[ERTS_CACHE_LINE_SIZE]; + } r; + union { + erts_atomic64_t val1; + char align__[ERTS_CACHE_LINE_SIZE]; + } w; +} unique_data erts_align_attribute(ERTS_CACHE_LINE_SIZE); + +static void +init_unique_integer(void) +{ + int bits; + unique_data.r.o.val0_max = (Uint64) erts_no_schedulers; +#ifdef ERTS_DIRTY_SCHEDULERS + unique_data.r.o.val0_max += (Uint64) erts_no_dirty_cpu_schedulers; + unique_data.r.o.val0_max += (Uint64) erts_no_dirty_io_schedulers; +#endif + bits = erts_fit_in_bits_int64(unique_data.r.o.val0_max); + unique_data.r.o.left_shift = bits; + unique_data.r.o.right_shift = 64 - bits; + unique_data.r.o.mask = (((Uint64) 1) << bits) - 1; + erts_atomic64_init_nob(&unique_data.w.val1, -1); +} + +#define ERTS_MAX_UNIQUE_INT_HEAP_SIZE ERTS_UINT64_ARRAY_TO_BIG_MAX_HEAP_SZ(2) + +static ERTS_INLINE Eterm +bld_unique_integer_term(Eterm **hpp, Uint *szp, + Uint64 val0, Uint64 val1, + int positive) +{ + Uint hsz; + Uint64 unique_val[2]; + + unique_val[0] = ((Uint64) val0); + unique_val[0] |= ((Uint64) val1) << unique_data.r.o.left_shift; + unique_val[1] = ((Uint64) val1) >> unique_data.r.o.right_shift; + unique_val[1] &= unique_data.r.o.mask; + + if (positive) { + unique_val[0]++; + if (unique_val[0] == 0) + unique_val[1]++; + } + else { + ASSERT(MIN_SMALL < 0); + if (unique_val[1] == 0 + && unique_val[0] < ((Uint64) -1*((Sint64) MIN_SMALL))) { + Sint64 s_unique_val = (Sint64) unique_val[0]; + s_unique_val += MIN_SMALL; + ASSERT(MIN_SMALL <= s_unique_val && s_unique_val < 0); + if (szp) + *szp = 0; + if (!hpp) + return THE_NON_VALUE; + return make_small((Sint) s_unique_val); + } + if (unique_val[0] < ((Uint64) -1*((Sint64) MIN_SMALL))) { + ASSERT(unique_val[1] != 0); + unique_val[1] -= 1; + } + unique_val[0] += MIN_SMALL; + } + + if (!unique_val[1]) { + if (unique_val[0] <= MAX_SMALL) { + if (szp) + *szp = 0; + if (!hpp) + return THE_NON_VALUE; + return make_small((Uint) unique_val[0]); + } + + if (szp) + *szp = ERTS_UINT64_HEAP_SIZE(unique_val[0]); + if (!hpp) + return THE_NON_VALUE; + return erts_uint64_to_big(unique_val[0], hpp); + } + else { + Eterm tmp, *tmp_hp, res; + DeclareTmpHeapNoproc(local_heap, 2*ERTS_MAX_UNIQUE_INT_HEAP_SIZE); + + UseTmpHeapNoproc(2*ERTS_MAX_UNIQUE_INT_HEAP_SIZE); + + tmp_hp = local_heap; + + tmp = erts_uint64_array_to_big(&tmp_hp, 0, 2, unique_val); + ASSERT(is_big(tmp)); + + hsz = big_arity(tmp) + 1; + + ASSERT(hsz <= ERTS_MAX_UNIQUE_INT_HEAP_SIZE); + + if (szp) + *szp = hsz; + + if (!hpp) + res = THE_NON_VALUE; + else { + int hix; + Eterm *hp = *hpp; + tmp_hp = big_val(tmp); + for (hix = 0; hix < hsz; hix++) + hp[hix] = tmp_hp[hix]; + + *hpp = hp + hsz; + res = make_big(hp); + } + + UnUseTmpHeapNoproc(2*ERTS_MAX_UNIQUE_INT_HEAP_SIZE); + + return res; + } +} + +static ERTS_INLINE Eterm unique_integer_bif(Process *c_p, int positive) +{ + ErtsSchedulerData *esdp; + Uint64 thr_id, unique; + Uint hsz; + Eterm *hp; + + esdp = ERTS_PROC_GET_SCHDATA(c_p); + thr_id = (Uint64) esdp->thr_id; + unique = esdp->unique++; + bld_unique_integer_term(NULL, &hsz, thr_id, unique, positive); + hp = hsz ? HAlloc(c_p, hsz) : NULL; + return bld_unique_integer_term(&hp, NULL, thr_id, unique, positive); +} + +Uint +erts_raw_unique_integer_heap_size(Uint64 val[ERTS_UNIQUE_INT_RAW_VALUES]) +{ + Uint sz; + bld_unique_integer_term(NULL, &sz, val[0], val[1], 0); + return sz; +} + +Eterm +erts_raw_make_unique_integer(Eterm **hpp, Uint64 val[ERTS_UNIQUE_INT_RAW_VALUES]) +{ + return bld_unique_integer_term(hpp, NULL, val[0], val[1], 0); +} + +void +erts_raw_get_unique_integer(Uint64 val[ERTS_UNIQUE_INT_RAW_VALUES]) +{ + ErtsSchedulerData *esdp = erts_get_scheduler_data(); + if (esdp) { + val[0] = (Uint64) esdp->thr_id; + val[1] = esdp->unique++; + } + else { + val[0] = (Uint64) 0; + val[1] = (Uint64) erts_atomic64_inc_read_nob(&unique_data.w.val1); + } +} + + +Sint64 +erts_get_min_unique_integer(void) +{ + return (Sint64) MIN_SMALL; +} + +/* --- Debug --- */ + +Eterm +erts_debug_make_unique_integer(Process *c_p, Eterm etval0, Eterm etval1) +{ + Uint64 val0, val1; + Uint hsz; + Eterm res, *hp, *end_hp; + + if (!term_to_Uint64(etval0, &val0)) + return THE_NON_VALUE; + + if (!term_to_Uint64(etval1, &val1)) + return THE_NON_VALUE; + + bld_unique_integer_term(NULL, &hsz, val0, val1, 0); + + hp = HAlloc(c_p, hsz); + end_hp = hp + hsz; + + res = bld_unique_integer_term(&hp, NULL, val0, val1, 0); + if (hp != end_hp) + ERTS_INTERNAL_ERROR("Heap allocation error"); + + return res; +} + +/* * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * *\ + * Strict Monotonic Counter * +\* */ + +static struct { + union { + erts_atomic64_t value; + char align__[ERTS_CACHE_LINE_SIZE]; + } w; +} raw_unique_monotonic_integer erts_align_attribute(ERTS_CACHE_LINE_SIZE); + +#if defined(ARCH_32) || HALFWORD_HEAP +# define ERTS_UNIQUE_MONOTONIC_OFFSET ERTS_SINT64_MIN +#else +# define ERTS_UNIQUE_MONOTONIC_OFFSET MIN_SMALL +#endif + +static void +init_unique_monotonic_integer(void) +{ + erts_atomic64_init_nob(&raw_unique_monotonic_integer.w.value, + (erts_aint64_t) -1); +} + +static ERTS_INLINE Uint64 +get_raw_unique_monotonic_integer(void) +{ + return (Uint64) erts_atomic64_inc_read_mb(&raw_unique_monotonic_integer.w.value); +} + +static ERTS_INLINE Uint +get_unique_monotonic_integer_heap_size(Uint64 raw, int positive) +{ + if (positive) { + Uint64 value = raw+1; + return ERTS_UINT64_HEAP_SIZE(value); + } + else { + Sint64 value = ((Sint64) raw) + ERTS_UNIQUE_MONOTONIC_OFFSET; + if (IS_SSMALL(value)) + return 0; +#if defined(ARCH_32) || HALFWORD_HEAP + return ERTS_SINT64_HEAP_SIZE(value); +#else + return ERTS_UINT64_HEAP_SIZE((Uint64) value); +#endif + } +} + +static ERTS_INLINE Eterm +make_unique_monotonic_integer_value(Eterm *hp, Uint hsz, Uint64 raw, int positive) +{ + Eterm res; +#ifdef DEBUG + Eterm *end_hp = hp + hsz; +#endif + + if (positive) { + Uint64 value = raw+1; + res = hsz ? erts_uint64_to_big(value, &hp) : make_small(value); + } + else { + Sint64 value = ((Sint64) raw) + ERTS_UNIQUE_MONOTONIC_OFFSET; + if (hsz == 0) + res = make_small(value); + else { +#if defined(ARCH_32) || HALFWORD_HEAP + res = erts_sint64_to_big(value, &hp); +#else + res = erts_uint64_to_big((Uint64) value, &hp); +#endif + } + } + + ASSERT(end_hp == hp); + + return res; +} + +static ERTS_INLINE Eterm +unique_monotonic_integer_bif(Process *c_p, int positive) +{ + Uint64 raw; + Uint hsz; + Eterm *hp; + + raw = get_raw_unique_monotonic_integer(); + hsz = get_unique_monotonic_integer_heap_size(raw, positive); + hp = hsz ? HAlloc(c_p, hsz) : NULL; + return make_unique_monotonic_integer_value(hp, hsz, raw, positive); +} + +Sint64 +erts_raw_get_unique_monotonic_integer(void) +{ + return get_raw_unique_monotonic_integer(); +} + +Uint +erts_raw_unique_monotonic_integer_heap_size(Sint64 raw) +{ + return get_unique_monotonic_integer_heap_size(raw, 0); +} + +Eterm +erts_raw_make_unique_monotonic_integer_value(Eterm **hpp, Sint64 raw) +{ + Uint hsz = get_unique_monotonic_integer_heap_size(raw, 0); + Eterm res = make_unique_monotonic_integer_value(*hpp, hsz, raw, 0); + *hpp += hsz; + return res; +} + +Sint64 +erts_get_min_unique_monotonic_integer(void) +{ + return ERTS_UNIQUE_MONOTONIC_OFFSET; +} + +/* --- Debug --- */ + +int +erts_debug_set_unique_monotonic_integer_state(Eterm et_value) +{ + Sint64 value; + + if (!term_to_Sint64(et_value, &value)) { + Uint64 uvalue; + if (!term_to_Uint64(et_value, &uvalue)) + return 0; + value = (Sint64) uvalue; + } + + erts_atomic64_set_mb(&raw_unique_monotonic_integer.w.value, + (erts_aint64_t) value); + return 1; +} + +Eterm +erts_debug_get_unique_monotonic_integer_state(Process *c_p) +{ + Uint64 value; + Eterm hsz, *hp; + + value = (Uint64) erts_atomic64_read_mb(&raw_unique_monotonic_integer.w.value); + + if (IS_USMALL(0, value)) + return make_small(value); + hsz = ERTS_UINT64_HEAP_SIZE(value); + hp = HAlloc(c_p, hsz); + return erts_uint64_to_big(value, &hp); +} + +/* * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * *\ + * Initilazation * +\* */ + +void +erts_bif_unique_init(void) +{ + init_reference(); + init_unique_monotonic_integer(); + init_unique_integer(); +} + +void +erts_sched_bif_unique_init(ErtsSchedulerData *esdp) +{ + esdp->unique = (Uint64) 0; + esdp->ref = (Uint64) 0; +} + +/* * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * *\ + * The BIFs * +\* */ + + +BIF_RETTYPE make_ref_0(BIF_ALIST_0) +{ + BIF_RETTYPE res; + Eterm* hp; + + ERTS_SMP_LC_ASSERT(ERTS_PROC_LOCK_MAIN & erts_proc_lc_my_proc_locks(BIF_P)); + + hp = HAlloc(BIF_P, REF_THING_SIZE); + + res = erts_sched_make_ref_in_buffer(ERTS_PROC_GET_SCHDATA(BIF_P), hp); + + BIF_RET(res); +} + +BIF_RETTYPE unique_integer_0(BIF_ALIST_0) +{ + BIF_RET(unique_integer_bif(BIF_P, 0)); +} + +BIF_RETTYPE unique_integer_1(BIF_ALIST_1) +{ + Eterm modlist = BIF_ARG_1; + int monotonic = 0; + int positive = 0; + BIF_RETTYPE res; + + while (is_list(modlist)) { + Eterm *consp = list_val(modlist); + switch (CAR(consp)) { + case am_monotonic: + monotonic = 1; + break; + case am_positive: + positive = 1; + break; + default: + BIF_ERROR(BIF_P, BADARG); + } + modlist = CDR(consp); + } + + if (is_not_nil(modlist)) + BIF_ERROR(BIF_P, BADARG); + + if (monotonic) + res = unique_monotonic_integer_bif(BIF_P, positive); + else + res = unique_integer_bif(BIF_P, positive); + + BIF_RET(res); +} diff --git a/erts/emulator/beam/erl_bif_unique.h b/erts/emulator/beam/erl_bif_unique.h new file mode 100644 index 0000000000..cd001172a1 --- /dev/null +++ b/erts/emulator/beam/erl_bif_unique.h @@ -0,0 +1,131 @@ +/* + * %CopyrightBegin% + * + * Copyright Ericsson AB 2014. All Rights Reserved. + * + * The contents of this file are subject to the Erlang Public License, + * Version 1.1, (the "License"); you may not use this file except in + * compliance with the License. You should have received a copy of the + * Erlang Public License along with this software. If not, it can be + * retrieved online at http://www.erlang.org/. + * + * Software distributed under the License is distributed on an "AS IS" + * basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See + * the License for the specific language governing rights and limitations + * under the License. + * + * %CopyrightEnd% + */ + +#ifndef ERTS_BIF_UNIQUE_H__ +#define ERTS_BIF_UNIQUE_H__ + +#include "erl_process.h" +#include "big.h" + +void erts_bif_unique_init(void); +void erts_sched_bif_unique_init(ErtsSchedulerData *esdp); + +/* reference */ +Eterm erts_make_ref(Process *); +Eterm erts_make_ref_in_buffer(Eterm buffer[REF_THING_SIZE]); +void erts_make_ref_in_array(Uint32 ref[ERTS_MAX_REF_NUMBERS]); + +/* strict monotonic counter */ + +#define ERTS_MAX_UNIQUE_MONOTONIC_INTEGER_HEAP_SIZE ERTS_MAX_UINT64_HEAP_SIZE + +/* + * Note that a raw value is an intermediate value that + * not necessarily correspond to the end result. + */ +Sint64 erts_raw_get_unique_monotonic_integer(void); +Uint erts_raw_unique_monotonic_integer_heap_size(Sint64 raw); +Eterm erts_raw_make_unique_monotonic_integer_value(Eterm **hpp, Sint64 raw); + +Sint64 erts_get_min_unique_monotonic_integer(void); + +int erts_debug_set_unique_monotonic_integer_state(Eterm et_value); +Eterm erts_debug_get_unique_monotonic_integer_state(Process *c_p); + +/* unique integer */ +#define ERTS_UNIQUE_INT_RAW_VALUES 2 +#define ERTS_MAX_UNIQUE_INT_HEAP_SIZE ERTS_UINT64_ARRAY_TO_BIG_MAX_HEAP_SZ(2) + +Uint erts_raw_unique_integer_heap_size(Uint64 val[ERTS_UNIQUE_INT_RAW_VALUES]); +Eterm erts_raw_make_unique_integer(Eterm **hpp, Uint64 val[ERTS_UNIQUE_INT_RAW_VALUES]); +void erts_raw_get_unique_integer(Uint64 val[ERTS_UNIQUE_INT_RAW_VALUES]); +Sint64 erts_get_min_unique_integer(void); + +Eterm erts_debug_make_unique_integer(Process *c_p, + Eterm etval0, + Eterm etval1); + + +ERTS_GLB_INLINE void erts_set_ref_numbers(Uint32 ref[ERTS_MAX_REF_NUMBERS], + Uint32 thr_id, Uint64 value); +ERTS_GLB_INLINE Uint32 erts_get_ref_numbers_thr_id(Uint32 ref[ERTS_MAX_REF_NUMBERS]); +ERTS_GLB_INLINE Uint64 erts_get_ref_numbers_value(Uint32 ref[ERTS_MAX_REF_NUMBERS]); +ERTS_GLB_INLINE void erts_sched_make_ref_in_array(ErtsSchedulerData *esdp, + Uint32 ref[ERTS_MAX_REF_NUMBERS]); +ERTS_GLB_INLINE Eterm erts_sched_make_ref_in_buffer(ErtsSchedulerData *esdp, + Eterm buffer[REF_THING_SIZE]); + +#if ERTS_GLB_INLINE_INCL_FUNC_DEF + +ERTS_GLB_INLINE void +erts_set_ref_numbers(Uint32 ref[ERTS_MAX_REF_NUMBERS], Uint32 thr_id, Uint64 value) +{ + /* + * We cannot use thread id in the first 18-bit word since + * the hash/phash/phash2 BIFs only hash on this word. If + * we did, we would get really poor hash values. Instead + * we have to shuffle the bits a bit. + */ + ASSERT(thr_id == (thr_id & ((Uint32) 0x3ffff))); + ref[0] = (Uint32) (value & ((Uint64) 0x3ffff)); + ref[1] = (((Uint32) (value & ((Uint64) 0xfffc0000))) + | (thr_id & ((Uint32) 0x3ffff))); + ref[2] = (Uint32) ((value >> 32) & ((Uint64) 0xffffffff)); +} + +ERTS_GLB_INLINE Uint32 +erts_get_ref_numbers_thr_id(Uint32 ref[ERTS_MAX_REF_NUMBERS]) +{ + return ref[1] & ((Uint32) 0x3ffff); +} + +ERTS_GLB_INLINE Uint64 +erts_get_ref_numbers_value(Uint32 ref[ERTS_MAX_REF_NUMBERS]) +{ + return (((((Uint64) ref[2]) & ((Uint64) 0xffffffff)) << 32) + | (((Uint64) ref[1]) & ((Uint64) 0xfffc0000)) + | (((Uint64) ref[0]) & ((Uint64) 0x3ffff))); +} + +ERTS_GLB_INLINE void +erts_sched_make_ref_in_array(ErtsSchedulerData *esdp, + Uint32 ref[ERTS_MAX_REF_NUMBERS]) +{ + Uint64 value; + + ASSERT(esdp); + value = esdp->ref++; + erts_set_ref_numbers(ref, (Uint32) esdp->thr_id, value); +} + +ERTS_GLB_INLINE Eterm +erts_sched_make_ref_in_buffer(ErtsSchedulerData *esdp, + Eterm buffer[REF_THING_SIZE]) +{ + Eterm* hp = buffer; + Uint32 ref[ERTS_MAX_REF_NUMBERS]; + + erts_sched_make_ref_in_array(esdp, ref); + write_ref_thing(hp, ref[0], ref[1], ref[2]); + return make_internal_ref(hp); +} + +#endif /* ERTS_GLB_INLINE_INCL_FUNC_DEF */ + +#endif /* ERTS_BIF_UNIQUE_H__ */ diff --git a/erts/emulator/beam/erl_gc.c b/erts/emulator/beam/erl_gc.c index d1a7ee113b..4a116c0740 100644 --- a/erts/emulator/beam/erl_gc.c +++ b/erts/emulator/beam/erl_gc.c @@ -39,6 +39,7 @@ #include "hipe_mode_switch.h" #endif #include "dtrace-wrapper.h" +#include "erl_bif_unique.h" #define ERTS_INACT_WR_PB_LEAVE_MUCH_LIMIT 1 #define ERTS_INACT_WR_PB_LEAVE_MUCH_PERCENTAGE 20 @@ -96,10 +97,10 @@ typedef struct { static Uint setup_rootset(Process*, Eterm*, int, Rootset*); static void cleanup_rootset(Rootset *rootset); -static Uint combined_message_size(Process* p); +static Uint combined_message_size(Process* p, int off_heap_msgs); static void remove_message_buffers(Process* p); -static int major_collection(Process* p, int need, Eterm* objv, int nobj, Uint *recl); -static int minor_collection(Process* p, int need, Eterm* objv, int nobj, Uint *recl); +static int major_collection(Process* p, int need, Eterm* objv, int nobj, Uint *recl, int off_heap_msgs); +static int minor_collection(Process* p, int need, Eterm* objv, int nobj, Uint *recl, int off_heap_msgs); static void do_minor(Process *p, Uint new_sz, Eterm* objv, int nobj); static Eterm* sweep_rootset(Rootset *rootset, Eterm* htop, char* src, Uint src_size); static Eterm* sweep_one_area(Eterm* n_hp, Eterm* n_htop, char* src, Uint src_size); @@ -402,7 +403,9 @@ erts_garbage_collect(Process* p, int need, Eterm* objv, int nobj) { Uint reclaimed_now = 0; int done = 0; + int off_heap_msgs; Uint ms1, s1, us1; + erts_aint32_t state; ErtsSchedulerData *esdp; #ifdef USE_VM_PROBES DTRACE_CHARBUF(pidbuf, DTRACE_TERM_BUF_SIZE); @@ -419,7 +422,8 @@ erts_garbage_collect(Process* p, int need, Eterm* objv, int nobj) trace_gc(p, am_gc_start); } - erts_smp_atomic32_read_bor_nob(&p->state, ERTS_PSFLG_GC); + state = erts_smp_atomic32_read_bor_nob(&p->state, ERTS_PSFLG_GC); + off_heap_msgs = state & ERTS_PSFLG_OFF_HEAP_MSGS; if (erts_system_monitor_long_gc != 0) { get_now(&ms1, &s1, &us1); } @@ -445,11 +449,11 @@ erts_garbage_collect(Process* p, int need, Eterm* objv, int nobj) while (!done) { if ((FLAGS(p) & F_NEED_FULLSWEEP) != 0) { DTRACE2(gc_major_start, pidbuf, need); - done = major_collection(p, need, objv, nobj, &reclaimed_now); + done = major_collection(p, need, objv, nobj, &reclaimed_now, off_heap_msgs); DTRACE2(gc_major_end, pidbuf, reclaimed_now); } else { DTRACE2(gc_minor_start, pidbuf, need); - done = minor_collection(p, need, objv, nobj, &reclaimed_now); + done = minor_collection(p, need, objv, nobj, &reclaimed_now, off_heap_msgs); DTRACE2(gc_minor_end, pidbuf, reclaimed_now); } } @@ -832,7 +836,7 @@ erts_garbage_collect_literals(Process* p, Eterm* literals, } static int -minor_collection(Process* p, int need, Eterm* objv, int nobj, Uint *recl) +minor_collection(Process* p, int need, Eterm* objv, int nobj, Uint *recl, int off_heap_msgs) { Uint mature = HIGH_WATER(p) - HEAP_START(p); @@ -871,20 +875,22 @@ minor_collection(Process* p, int need, Eterm* objv, int nobj, Uint *recl) Uint size_after; Uint need_after; Uint stack_size = STACK_SZ_ON_HEAP(p); - Uint fragments = MBUF_SIZE(p) + combined_message_size(p); + Uint fragments = MBUF_SIZE(p) + combined_message_size(p, off_heap_msgs); Uint size_before = fragments + (HEAP_TOP(p) - HEAP_START(p)); Uint new_sz = next_heap_size(p, HEAP_SIZE(p) + fragments, 0); do_minor(p, new_sz, objv, nobj); - /* - * Copy newly received message onto the end of the new heap. - */ - ErtsGcQuickSanityCheck(p); - for (msgp = p->msg.first; msgp; msgp = msgp->next) { - if (msgp->data.attached) { - erts_move_msg_attached_data_to_heap(&p->htop, &p->off_heap, msgp); - ErtsGcQuickSanityCheck(p); + if (!off_heap_msgs) { + /* + * Copy newly received message onto the end of the new heap. + */ + ErtsGcQuickSanityCheck(p); + for (msgp = p->msg.first; msgp; msgp = msgp->next) { + if (msgp->data.attached) { + erts_move_msg_attached_data_to_heap(&p->htop, &p->off_heap, msgp); + ErtsGcQuickSanityCheck(p); + } } } ErtsGcQuickSanityCheck(p); @@ -1210,7 +1216,7 @@ do_minor(Process *p, Uint new_sz, Eterm* objv, int nobj) */ static int -major_collection(Process* p, int need, Eterm* objv, int nobj, Uint *recl) +major_collection(Process* p, int need, Eterm* objv, int nobj, Uint *recl, int off_heap_msgs) { Rootset rootset; Roots* roots; @@ -1223,8 +1229,7 @@ major_collection(Process* p, int need, Eterm* objv, int nobj, Uint *recl) Uint oh_size = (char *) OLD_HTOP(p) - oh; Uint n; Uint new_sz; - Uint fragments = MBUF_SIZE(p) + combined_message_size(p); - ErlMessage *msgp; + Uint fragments = MBUF_SIZE(p) + combined_message_size(p, off_heap_msgs); size_before = fragments + (HEAP_TOP(p) - HEAP_START(p)); @@ -1434,13 +1439,16 @@ major_collection(Process* p, int need, Eterm* objv, int nobj, Uint *recl) ErtsGcQuickSanityCheck(p); - /* - * Copy newly received message onto the end of the new heap. - */ - for (msgp = p->msg.first; msgp; msgp = msgp->next) { - if (msgp->data.attached) { - erts_move_msg_attached_data_to_heap(&p->htop, &p->off_heap, msgp); - ErtsGcQuickSanityCheck(p); + if (!off_heap_msgs) { + ErlMessage *msgp; + /* + * Copy newly received message onto the end of the new heap. + */ + for (msgp = p->msg.first; msgp; msgp = msgp->next) { + if (msgp->data.attached) { + erts_move_msg_attached_data_to_heap(&p->htop, &p->off_heap, msgp); + ErtsGcQuickSanityCheck(p); + } } } @@ -1501,15 +1509,17 @@ adjust_after_fullsweep(Process *p, Uint size_before, int need, Eterm *objv, int * mbuf list. */ static Uint -combined_message_size(Process* p) +combined_message_size(Process* p, int off_heap_msgs) { - Uint sz = 0; + Uint sz; ErlMessage *msgp; - for (msgp = p->msg.first; msgp; msgp = msgp->next) { - if (msgp->data.attached) { + if (off_heap_msgs) + return 0; + + for (sz = 0, msgp = p->msg.first; msgp; msgp = msgp->next) { + if (msgp->data.attached) sz += erts_msg_attached_data_size(msgp); - } } return sz; } diff --git a/erts/emulator/beam/erl_init.c b/erts/emulator/beam/erl_init.c index fe065e196d..5aeb5b2590 100644 --- a/erts/emulator/beam/erl_init.c +++ b/erts/emulator/beam/erl_init.c @@ -45,6 +45,7 @@ #include "erl_thr_queue.h" #include "erl_async.h" #include "erl_ptab.h" +#include "erl_bif_unique.h" #ifdef HIPE #include "hipe_mode_switch.h" /* for hipe_mode_switch_init() */ @@ -134,7 +135,9 @@ static void erl_init(int ncpu, int legacy_proc_tab, int port_tab_sz, int port_tab_sz_ignore_files, - int legacy_port_tab); + int legacy_port_tab, + int time_correction, + ErtsTimeWarpMode time_warp_mode); static erts_atomic_t exiting; @@ -185,10 +188,6 @@ static int no_dirty_io_schedulers; Uint32 verbose; /* See erl_debug.h for information about verbose */ #endif -int erts_disable_tolerant_timeofday; /* Time correction can be disabled it is - * not and/or it is too slow. - */ - int erts_atom_table_size = ATOM_LIMIT; /* Maximum number of atoms */ int erts_pd_initial_size = 10; @@ -268,6 +267,19 @@ this_rel_num(void) return this_rel; } +static ERTS_INLINE void +set_default_time_adj(int *time_correction_p, ErtsTimeWarpMode *time_warp_mode_p) +{ + *time_correction_p = 1; + *time_warp_mode_p = ERTS_NO_TIME_WARP_MODE; + if (!erts_check_time_adj_support(*time_correction_p, + *time_warp_mode_p)) { + *time_correction_p = 0; + ASSERT(erts_check_time_adj_support(*time_correction_p, + *time_warp_mode_p)); + } +} + /* * Common error printout function, all error messages * that don't go to the error logger go through here. @@ -283,13 +295,22 @@ static int early_init(int *argc, char **argv); void erts_short_init(void) { - int ncpu = early_init(NULL, NULL); + + int ncpu; + int time_correction; + ErtsTimeWarpMode time_warp_mode; + + set_default_time_adj(&time_correction, + &time_warp_mode); + ncpu = early_init(NULL, NULL); erl_init(ncpu, ERTS_DEFAULT_MAX_PROCESSES, 0, ERTS_DEFAULT_MAX_PORTS, 0, - 0); + 0, + time_correction, + time_warp_mode); erts_initialized = 1; } @@ -299,12 +320,15 @@ erl_init(int ncpu, int legacy_proc_tab, int port_tab_sz, int port_tab_sz_ignore_files, - int legacy_port_tab) + int legacy_port_tab, + int time_correction, + ErtsTimeWarpMode time_warp_mode) { init_benchmarking(); + erts_bif_unique_init(); erts_init_monitors(); - erts_init_time(); + erts_init_time(time_correction, time_warp_mode); erts_init_sys_common_misc(); erts_init_process(ncpu, proc_tab_sz, legacy_proc_tab); erts_init_scheduling(no_schedulers, @@ -315,6 +339,7 @@ erl_init(int ncpu, no_dirty_io_schedulers #endif ); + erts_late_init_time_sup(); erts_init_cpu_topology(); /* Must be after init_scheduling */ erts_init_gc(); /* Must be after init_scheduling */ erts_alloc_late_init(); @@ -364,12 +389,13 @@ erl_init(int ncpu, erl_nif_init(); } -static void +static Eterm erl_first_process_otp(char* modname, void* code, unsigned size, int argc, char** argv) { int i; Eterm start_mod; Eterm args; + Eterm res; Eterm* hp; Process parent; ErlSpawnOpts so; @@ -399,10 +425,11 @@ erl_first_process_otp(char* modname, void* code, unsigned size, int argc, char** hp += 2; args = CONS(hp, env, args); - so.flags = 0; - (void) erl_create_process(&parent, start_mod, am_start, args, &so); + so.flags = SPO_SYSTEM_PROC; + res = erl_create_process(&parent, start_mod, am_start, args, &so); erts_smp_proc_unlock(&parent, ERTS_PROC_LOCK_MAIN); erts_cleanup_empty_process(&parent); + return res; } Eterm @@ -508,9 +535,9 @@ void erts_usage(void) /* erts_fprintf(stderr, "-b func set the boot function (default boot)\n"); */ - erts_fprintf(stderr, "-c disable continuous date/time correction with\n"); - erts_fprintf(stderr, " respect to uptime\n"); - + erts_fprintf(stderr, "-c bool enable or disable time correction\n"); + erts_fprintf(stderr, "-C mode set time warp mode; valid modes are:\n"); + erts_fprintf(stderr, " no_time_warp|single_time_warp|multi_time_warp\n"); erts_fprintf(stderr, "-d don't write a crash dump for internally detected errors\n"); erts_fprintf(stderr, " (halt(String) will still produce a crash dump)\n"); erts_fprintf(stderr, "-fn[u|a|l] Control how filenames are interpreted\n"); @@ -682,7 +709,6 @@ early_init(int *argc, char **argv) /* erts_sched_compact_load = 1; erts_printf_eterm_func = erts_printf_term; - erts_disable_tolerant_timeofday = 0; display_items = 200; erts_backtrace_depth = DEFAULT_BACKTRACE_SIZE; erts_async_max_threads = ERTS_DEFAULT_NO_ASYNC_THREADS; @@ -1145,6 +1171,7 @@ early_init(int *argc, char **argv) /* /* Creates threads on Windows that depend on the arguments, so has to be after erl_sys_args */ erl_sys_init(); + erts_early_init_time_sup(); erts_ets_realloc_always_moves = 0; erts_ets_always_compress = 0; @@ -1188,7 +1215,11 @@ erl_start(int argc, char **argv) int port_tab_sz_ignore_files = 0; int legacy_proc_tab = 0; int legacy_port_tab = 0; + int time_correction; + ErtsTimeWarpMode time_warp_mode; + set_default_time_adj(&time_correction, + &time_warp_mode); envbufsz = sizeof(envbuf); if (erts_sys_getenv_raw(ERL_MAX_ETS_TABLES_ENV, envbuf, &envbufsz) == 0) @@ -1906,9 +1937,55 @@ erl_start(int argc, char **argv) } break; } + case 'C': + arg = get_arg(argv[i]+2, argv[i+1], &i); + if (sys_strcmp(arg, "no_time_warp") == 0) + time_warp_mode = ERTS_NO_TIME_WARP_MODE; + else if (sys_strcmp(arg, "single_time_warp") == 0) + time_warp_mode = ERTS_SINGLE_TIME_WARP_MODE; + else if (sys_strcmp(arg, "multi_time_warp") == 0) + time_warp_mode = ERTS_MULTI_TIME_WARP_MODE; + else { + erts_fprintf(stderr, + "Invalid time warp mode: %s\n", arg); + erts_usage(); + } + break; case 'c': - if (argv[i][2] == 0) { /* -c: documented option */ - erts_disable_tolerant_timeofday = 1; + if (sys_strcmp(argv[i]+2, "false") == 0) + goto time_correction_false; + else if (sys_strcmp(argv[i]+2, "true") == 0) + goto time_correction_true; +#ifdef ERTS_OPCODE_COUNTER_SUPPORT + else if (argv[i][2] == 'i') { /* -ci: undcoumented option*/ + count_instructions = 1; + } +#endif + else if (argv[i][2] == '\0') { + if (i + 1 >= argc) + goto time_correction_false; + else { + if (sys_strcmp(argv[i+1], "false") == 0) { + (void) get_arg(argv[i]+2, argv[i+1], &i); + goto time_correction_false; + } + else if (sys_strcmp(argv[i+1], "true") == 0) { + (void) get_arg(argv[i]+2, argv[i+1], &i); + time_correction_true: + time_correction = 1; + break; + } + else { + time_correction_false: + time_correction = 0; + break; + } + } + } + else { + arg = get_arg(argv[i]+2, argv[i+1], &i); + erts_fprintf(stderr, "Invalid time correnction value: %s\n", arg); + erts_usage(); } break; case 'W': @@ -1955,6 +2032,30 @@ erl_start(int argc, char **argv) i++; } + if (!erts_check_time_adj_support(time_correction, time_warp_mode)) { + char *time_correction_str = time_correction ? "Enabled" : "Disabled"; + char *time_warp_str = "undefined"; + switch (time_warp_mode) { + case ERTS_NO_TIME_WARP_MODE: + time_warp_str = "no"; + break; + case ERTS_SINGLE_TIME_WARP_MODE: + time_warp_str = "single"; + break; + case ERTS_MULTI_TIME_WARP_MODE: + time_warp_str = "multi"; + break; + default: + time_warp_str = "undefined"; + break; + } + erts_fprintf(stderr, "%s time correction with %s time warp mode " + "is not supported on this platform\n", + time_correction_str, + time_warp_str); + erts_usage(); + } + /* Output format on windows for sprintf defaults to three exponents. * We use two-exponent to mimic normal sprintf behaviour. */ @@ -1988,7 +2089,9 @@ erl_start(int argc, char **argv) legacy_proc_tab, port_tab_sz, port_tab_sz_ignore_files, - legacy_port_tab); + legacy_port_tab, + time_correction, + time_warp_mode); load_preloaded(); erts_end_staging_code_ix(); @@ -1996,7 +2099,11 @@ erl_start(int argc, char **argv) erts_initialized = 1; - erl_first_process_otp("otp_ring0", NULL, 0, boot_argc, boot_argv); + { + Eterm init = erl_first_process_otp("otp_ring0", NULL, 0, + boot_argc, boot_argv); + erts_bif_timer_start_servers(init); + } #ifdef ERTS_SMP erts_start_schedulers(); diff --git a/erts/emulator/beam/erl_lock_check.c b/erts/emulator/beam/erl_lock_check.c index b105ece6f1..261460d054 100644 --- a/erts/emulator/beam/erl_lock_check.c +++ b/erts/emulator/beam/erl_lock_check.c @@ -140,7 +140,6 @@ static erts_lc_lock_order_t erts_lock_order[] = { { "async_enq_mtx", NULL }, #ifdef ERTS_SMP { "atom_tab", NULL }, - { "make_ref", NULL }, { "misc_op_list_pre_alloc_lock", "address" }, { "message_pre_alloc_lock", "address" }, { "ptimer_pre_alloc_lock", "address", }, @@ -168,6 +167,8 @@ static erts_lc_lock_order_t erts_lock_order[] = { { "timer_wheel", NULL }, { "system_block", NULL }, { "timeofday", NULL }, + { "get_time", NULL }, + { "get_corrected_time", NULL }, { "breakpoints", NULL }, { "pollsets_lock", NULL }, { "pix_lock", "address" }, @@ -184,10 +185,8 @@ static erts_lc_lock_order_t erts_lock_order[] = { { "efile_drv dtrace mutex", NULL }, #endif { "mtrace_buf", NULL }, -#ifdef __WIN32__ #ifdef ERTS_SMP - { "sys_gethrtime", NULL }, -#endif + { "os_monotonic_time", NULL }, #endif { "erts_alloc_hard_debug", NULL }, { "hard_dbg_mseg", NULL }, diff --git a/erts/emulator/beam/erl_lock_count.c b/erts/emulator/beam/erl_lock_count.c index cf6996ea06..ddeb56a6be 100644 --- a/erts/emulator/beam/erl_lock_count.c +++ b/erts/emulator/beam/erl_lock_count.c @@ -104,11 +104,10 @@ static void lcnt_clear_stats(erts_lcnt_lock_stats_t *stats) { } static void lcnt_time(erts_lcnt_time_t *time) { -#if 0 || defined(HAVE_GETHRTIME) - SysHrTime hr_time; - hr_time = sys_gethrtime(); - time->s = (unsigned long)(hr_time / 1000000000LL); - time->ns = (unsigned long)(hr_time - 1000000000LL*time->s); +#if 0 || defined(ERTS_HAVE_OS_MONOTONIC_TIME_SUPPORT) + ErtsMonotonicTime mtime = ERTS_MONOTONIC_TO_NSEC(erts_os_monotonic_time()); + time->s = (unsigned long) (mtime / 1000000000LL); + time->ns = (unsigned long) (mtime - 1000000000LL*time->s); #else SysTimeval tv; sys_gettimeofday(&tv); diff --git a/erts/emulator/beam/erl_lock_count.h b/erts/emulator/beam/erl_lock_count.h index ffbb93da1b..09fadd7e9e 100644 --- a/erts/emulator/beam/erl_lock_count.h +++ b/erts/emulator/beam/erl_lock_count.h @@ -76,7 +76,7 @@ /* histogram */ #define ERTS_LCNT_HISTOGRAM_MAX_NS (((unsigned long)1LL << 28) - 1) -#if 0 || defined(HAVE_GETHRTIME) +#if 0 || defined(ERTS_HAVE_OS_MONOTONIC_TIME_SUPPORT) #define ERTS_LCNT_HISTOGRAM_SLOT_SIZE (30) #define ERTS_LCNT_HISTOGRAM_RSHIFT (0) #else diff --git a/erts/emulator/beam/erl_message.c b/erts/emulator/beam/erl_message.c index 43a03c793e..22cbae10d1 100644 --- a/erts/emulator/beam/erl_message.c +++ b/erts/emulator/beam/erl_message.c @@ -994,7 +994,7 @@ erts_send_message(Process* sender, #endif ); BM_SWAP_TIMER(send,system); - } else if (sender == receiver) { + } else if (sender == receiver && !(sender->flags & F_OFF_HEAP_MSGS)) { /* Drop message if receiver has a pending exit ... */ #ifdef ERTS_SMP ErtsProcLocks need_locks = (~(*receiver_locks) diff --git a/erts/emulator/beam/erl_message.h b/erts/emulator/beam/erl_message.h index 6b8c3cebc7..8713941769 100644 --- a/erts/emulator/beam/erl_message.h +++ b/erts/emulator/beam/erl_message.h @@ -213,15 +213,25 @@ do { \ if ((M)->data.attached) { \ Uint need__ = erts_msg_attached_data_size((M)); \ if ((ST) - (HT) >= need__) { \ - Uint *htop__ = (HT); \ + Uint *htop__; \ + move__attached__msg__data____: \ + htop__ = (HT); \ erts_move_msg_attached_data_to_heap(&htop__, &MSO((P)), (M));\ ASSERT(htop__ - (HT) <= need__); \ (HT) = htop__; \ } \ else { \ + int off_heap_msgs__ = (int) (P)->flags & F_OFF_HEAP_MSGS; \ + if (!off_heap_msgs__) \ + need__ = 0; \ { SWPO ; } \ - (FC) -= erts_garbage_collect((P), 0, NULL, 0); \ + (FC) -= erts_garbage_collect((P), need__, NULL, 0); \ { SWPI ; } \ + if (off_heap_msgs__) { \ + ASSERT((M)->data.attached); \ + ASSERT((ST) - (HT) >= need__); \ + goto move__attached__msg__data____; \ + } \ } \ ASSERT(!(M)->data.attached); \ } \ diff --git a/erts/emulator/beam/erl_monitors.h b/erts/emulator/beam/erl_monitors.h index fb11dbbd22..9972890db7 100644 --- a/erts/emulator/beam/erl_monitors.h +++ b/erts/emulator/beam/erl_monitors.h @@ -82,6 +82,7 @@ /* Type tags for monitors */ #define MON_ORIGIN 1 #define MON_TARGET 3 +#define MON_TIME_OFFSET 7 /* Type tags for links */ #define LINK_PID 1 /* ...Or port */ @@ -103,7 +104,7 @@ typedef struct erts_monitor_or_link { typedef struct erts_monitor { struct erts_monitor *left, *right; Sint16 balance; - Uint16 type; /* MON_ORIGIN | MON_TARGET */ + Uint16 type; /* MON_ORIGIN | MON_TARGET | MON_TIME_OFFSET */ Eterm ref; Eterm pid; /* In case of distributed named monitor, this is the nodename atom in MON_ORIGIN process, otherwise a pid or diff --git a/erts/emulator/beam/erl_nif.c b/erts/emulator/beam/erl_nif.c index e28365cb1b..c7c8b3fee3 100644 --- a/erts/emulator/beam/erl_nif.c +++ b/erts/emulator/beam/erl_nif.c @@ -36,6 +36,7 @@ #include "erl_thr_progress.h" #include "dtrace-wrapper.h" #include "erl_process.h" +#include "erl_bif_unique.h" #if defined(USE_DYNAMIC_TRACE) && (defined(USE_DTRACE) || defined(USE_SYSTEMTAP)) #define HAVE_USE_DTRACE 1 #endif diff --git a/erts/emulator/beam/erl_process.c b/erts/emulator/beam/erl_process.c index ba09ee57c2..f74a2ee54c 100644 --- a/erts/emulator/beam/erl_process.c +++ b/erts/emulator/beam/erl_process.c @@ -43,6 +43,7 @@ #include "erl_async.h" #include "dtrace-wrapper.h" #include "erl_ptab.h" +#include "erl_bif_unique.h" #define ERTS_DELAYED_WAKEUP_INFINITY (~(Uint64) 0) @@ -701,8 +702,8 @@ init_sched_wall_time(ErtsSchedWallTime *swtp) static ERTS_INLINE Uint64 sched_wall_time_ts(void) { -#ifdef HAVE_GETHRTIME - return (Uint64) sys_gethrtime(); +#ifdef ERTS_HAVE_OS_MONOTONIC_TIME_SUPPORT + return (Uint64) erts_os_monotonic_time(); #else Uint64 res; SysTimeval tv; @@ -2185,7 +2186,7 @@ aux_work_timeout_late_init(void) { aux_work_tmo->initialized = 1; if (erts_atomic32_read_nob(&aux_work_tmo->refc)) { - aux_work_tmo->timer.data.active = 0; + erts_init_timer(&aux_work_tmo->timer.data); erts_set_timer(&aux_work_tmo->timer.data, aux_work_timeout, NULL, @@ -2218,7 +2219,6 @@ aux_work_timeout(void *unused) if (refc != 1 || 1 != erts_atomic32_cmpxchg_relb(&aux_work_tmo->refc, 0, 1)) { /* Setup next timeout... */ - aux_work_tmo->timer.data.active = 0; erts_set_timer(&aux_work_tmo->timer.data, aux_work_timeout, NULL, @@ -2237,7 +2237,7 @@ setup_aux_work_timer(void) else #endif { - aux_work_tmo->timer.data.active = 0; + erts_init_timer(&aux_work_tmo->timer.data); erts_set_timer(&aux_work_tmo->timer.data, aux_work_timeout, NULL, @@ -2638,6 +2638,13 @@ thr_prgr_fin_wait(void *vssi) static void init_aux_work_data(ErtsAuxWorkData *awdp, ErtsSchedulerData *esdp, char *dawwp); +void +erts_interupt_aux_thread_timed(ErtsMonotonicTime timeout_time) +{ + /* TODO only poke when needed (based on timeout_time) */ + erts_sched_poke(ERTS_SCHED_SLEEP_INFO_IX(-1)); +} + static void * aux_thread(void *unused) { @@ -2646,6 +2653,11 @@ aux_thread(void *unused) erts_aint32_t aux_work; ErtsThrPrgrCallbacks callbacks; int thr_prgr_active = 1; + ErtsTimerWheel *timer_wheel = erts_default_timer_wheel; + ErtsNextTimeoutRef nxt_tmo_ref = erts_get_next_timeout_reference(timer_wheel); + + if (!timer_wheel) + ERTS_INTERNAL_ERROR("Missing aux timer wheel"); #ifdef ERTS_ENABLE_LOCK_CHECK { @@ -2669,6 +2681,7 @@ aux_thread(void *unused) sched_prep_spin_wait(ssi); while (1) { + ErtsMonotonicTime current_time; erts_aint32_t flgs; aux_work = erts_atomic32_read_acqb(&ssi->aux_work); @@ -2680,28 +2693,56 @@ aux_thread(void *unused) erts_thr_progress_leader_update(NULL); } - if (!aux_work) { - if (thr_prgr_active) - erts_thr_progress_active(NULL, thr_prgr_active = 0); - erts_thr_progress_prepare_wait(NULL); + if (aux_work) { + current_time = erts_get_monotonic_time(); + if (current_time >= erts_next_timeout_time(nxt_tmo_ref)) { + if (!thr_prgr_active) + erts_thr_progress_active(NULL, thr_prgr_active = 1); + erts_bump_timers(timer_wheel, current_time); + } + } + else { + ErtsMonotonicTime timeout_time; + timeout_time = erts_check_next_timeout_time(timer_wheel, + ERTS_SEC_TO_MONOTONIC(10*60)); + current_time = erts_get_monotonic_time(); + if (current_time >= timeout_time) { + if (!thr_prgr_active) + erts_thr_progress_active(NULL, thr_prgr_active = 1); + } + else { + if (thr_prgr_active) + erts_thr_progress_active(NULL, thr_prgr_active = 0); + erts_thr_progress_prepare_wait(NULL); - ERTS_SCHED_FAIR_YIELD(); + ERTS_SCHED_FAIR_YIELD(); - flgs = sched_spin_wait(ssi, 0); + flgs = sched_spin_wait(ssi, 0); - if (flgs & ERTS_SSI_FLG_SLEEPING) { - ASSERT(flgs & ERTS_SSI_FLG_WAITING); - flgs = sched_set_sleeptype(ssi, ERTS_SSI_FLG_TSE_SLEEPING); if (flgs & ERTS_SSI_FLG_SLEEPING) { - int res; - ASSERT(flgs & ERTS_SSI_FLG_TSE_SLEEPING); ASSERT(flgs & ERTS_SSI_FLG_WAITING); - do { - res = erts_tse_wait(ssi->event); - } while (res == EINTR); + flgs = sched_set_sleeptype(ssi, ERTS_SSI_FLG_TSE_SLEEPING); + if (flgs & ERTS_SSI_FLG_SLEEPING) { + int res; + ASSERT(flgs & ERTS_SSI_FLG_TSE_SLEEPING); + ASSERT(flgs & ERTS_SSI_FLG_WAITING); + current_time = erts_get_monotonic_time(); + do { + Sint64 timeout; + if (current_time >= timeout_time) + break; + timeout = ERTS_MONOTONIC_TO_NSEC(timeout_time + - current_time + - 1) + 1; + res = erts_tse_twait(ssi->event, timeout); + current_time = erts_get_monotonic_time(); + } while (res == EINTR); + } } + erts_thr_progress_finalize_wait(NULL); } - erts_thr_progress_finalize_wait(NULL); + if (current_time >= timeout_time) + erts_bump_timers(timer_wheel, current_time); } flgs = sched_prep_spin_wait(ssi); @@ -2768,6 +2809,7 @@ scheduler_wait(int *fcalls, ErtsSchedulerData *esdp, ErtsRunQueue *rq) sched_wall_time_change(esdp, thr_prgr_active); while (1) { + ErtsMonotonicTime current_time; aux_work = erts_atomic32_read_acqb(&ssi->aux_work); if (aux_work) { @@ -2781,34 +2823,65 @@ scheduler_wait(int *fcalls, ErtsSchedulerData *esdp, ErtsRunQueue *rq) erts_thr_progress_leader_update(esdp); } - if (aux_work) + if (aux_work) { flgs = erts_smp_atomic32_read_acqb(&ssi->flags); + current_time = erts_get_monotonic_time(); + if (current_time >= erts_next_timeout_time(esdp->next_tmo_ref)) { + if (!ERTS_SCHEDULER_IS_DIRTY(esdp) && !thr_prgr_active) { + erts_thr_progress_active(esdp, thr_prgr_active = 1); + sched_wall_time_change(esdp, 1); + } + erts_bump_timers(esdp->timer_wheel, current_time); + } + } else { - if (!ERTS_SCHEDULER_IS_DIRTY(esdp)) { - if (thr_prgr_active) { - erts_thr_progress_active(esdp, thr_prgr_active = 0); - sched_wall_time_change(esdp, 0); + ErtsMonotonicTime timeout_time; + timeout_time = erts_check_next_timeout_time(esdp->timer_wheel, + ERTS_SEC_TO_MONOTONIC(10*60)); + current_time = erts_get_monotonic_time(); + if (current_time >= timeout_time) { + if (!ERTS_SCHEDULER_IS_DIRTY(esdp) && !thr_prgr_active) { + erts_thr_progress_active(esdp, thr_prgr_active = 1); + sched_wall_time_change(esdp, 1); } - erts_thr_progress_prepare_wait(esdp); } + else { + if (!ERTS_SCHEDULER_IS_DIRTY(esdp)) { + if (thr_prgr_active) { + erts_thr_progress_active(esdp, thr_prgr_active = 0); + sched_wall_time_change(esdp, 0); + } + erts_thr_progress_prepare_wait(esdp); + } - ERTS_SCHED_FAIR_YIELD(); + ERTS_SCHED_FAIR_YIELD(); - flgs = sched_spin_wait(ssi, spincount); - if (flgs & ERTS_SSI_FLG_SLEEPING) { - ASSERT(flgs & ERTS_SSI_FLG_WAITING); - flgs = sched_set_sleeptype(ssi, ERTS_SSI_FLG_TSE_SLEEPING); + flgs = sched_spin_wait(ssi, spincount); if (flgs & ERTS_SSI_FLG_SLEEPING) { - int res; - ASSERT(flgs & ERTS_SSI_FLG_TSE_SLEEPING); ASSERT(flgs & ERTS_SSI_FLG_WAITING); - do { - res = erts_tse_wait(ssi->event); - } while (res == EINTR); + flgs = sched_set_sleeptype(ssi, ERTS_SSI_FLG_TSE_SLEEPING); + if (flgs & ERTS_SSI_FLG_SLEEPING) { + int res; + ASSERT(flgs & ERTS_SSI_FLG_TSE_SLEEPING); + ASSERT(flgs & ERTS_SSI_FLG_WAITING); + current_time = erts_get_monotonic_time(); + do { + Sint64 timeout; + if (current_time >= timeout_time) + break; + timeout = ERTS_MONOTONIC_TO_NSEC(timeout_time + - current_time + - 1) + 1; + res = erts_tse_twait(ssi->event, timeout); + current_time = erts_get_monotonic_time(); + } while (res == EINTR); + } } + if (!ERTS_SCHEDULER_IS_DIRTY(esdp)) + erts_thr_progress_finalize_wait(esdp); } - if (!ERTS_SCHEDULER_IS_DIRTY(esdp)) - erts_thr_progress_finalize_wait(esdp); + if (current_time >= timeout_time) + erts_bump_timers(esdp->timer_wheel, current_time); } if (!(flgs & ERTS_SSI_FLG_WAITING)) { @@ -2841,7 +2914,6 @@ scheduler_wait(int *fcalls, ErtsSchedulerData *esdp, ErtsRunQueue *rq) else #endif { - erts_aint_t dt; erts_smp_atomic32_set_relb(&function_calls, 0); *fcalls = 0; @@ -2866,6 +2938,7 @@ scheduler_wait(int *fcalls, ErtsSchedulerData *esdp, ErtsRunQueue *rq) goto sys_aux_work; while (spincount-- > 0) { + ErtsMonotonicTime current_time; sys_poll_aux_work: @@ -2875,8 +2948,9 @@ scheduler_wait(int *fcalls, ErtsSchedulerData *esdp, ErtsRunQueue *rq) ASSERT(!erts_port_task_have_outstanding_io_tasks()); erl_sys_schedule(1); /* Might give us something to do */ - dt = erts_do_time_read_and_reset(); - if (dt) erts_bump_timer(dt); + current_time = erts_get_monotonic_time(); + if (current_time >= erts_next_timeout_time(esdp->next_tmo_ref)) + erts_bump_timers(esdp->timer_wheel, current_time); sys_aux_work: #ifndef ERTS_SMP @@ -2991,8 +3065,11 @@ scheduler_wait(int *fcalls, ErtsSchedulerData *esdp, ErtsRunQueue *rq) erl_sys_schedule(0); - dt = erts_do_time_read_and_reset(); - if (dt) erts_bump_timer(dt); + { + ErtsMonotonicTime current_time = erts_get_monotonic_time(); + if (current_time >= erts_next_timeout_time(esdp->next_tmo_ref)) + erts_bump_timers(esdp->timer_wheel, current_time); + } #ifndef ERTS_SMP if (rq->len == 0 && !rq->misc.start) @@ -5262,6 +5339,10 @@ init_scheduler_data(ErtsSchedulerData* esdp, int num, #else esdp->no = (Uint) num; #endif + + esdp->timer_wheel = erts_default_timer_wheel; + esdp->next_tmo_ref = erts_get_next_timeout_reference(esdp->timer_wheel); + esdp->ssi = ssi; esdp->current_process = NULL; esdp->current_port = NULL; @@ -5274,6 +5355,9 @@ init_scheduler_data(ErtsSchedulerData* esdp, int num, esdp->run_queue = runq; esdp->run_queue->scheduler = esdp; + esdp->thr_id = (Uint32) num; + erts_sched_bif_unique_init(esdp); + if (daww_ptr) { init_aux_work_data(&esdp->aux_work_data, esdp, *daww_ptr); #ifdef ERTS_SMP @@ -5834,6 +5918,13 @@ schedule_out_process(ErtsRunQueue *c_rq, erts_aint32_t state, Process *p, Proces int check_emigration_need; #endif +#ifdef ERTS_SMP + if ((p->static_flags & ERTS_STC_FLG_PREFER_SCHED) + && p->preferred_run_queue != RUNQ_READ_RQ(&p->run_queue)) { + RUNQ_SET_RQ(&p->run_queue, p->preferred_run_queue); + } +#endif + a = state; while (1) { @@ -5872,6 +5963,7 @@ schedule_out_process(ErtsRunQueue *c_rq, erts_aint32_t state, Process *p, Proces free_proxy_proc(proxy); erts_smp_runq_lock(c_rq); + return 0; #ifdef ERTS_DIRTY_SCHEDULERS @@ -6584,7 +6676,7 @@ suspend_scheduler(ErtsSchedulerData *esdp) int res; do { - res = erts_tse_wait(ssi->event); + res = erts_tse_twait(ssi->event, -1); } while (res == EINTR); } } @@ -6747,6 +6839,7 @@ suspend_scheduler(ErtsSchedulerData *esdp) erts_smp_mtx_unlock(&schdlr_sspnd.mtx); while (1) { + ErtsMonotonicTime current_time; erts_aint32_t qmask; erts_aint32_t flgs; @@ -6771,30 +6864,64 @@ suspend_scheduler(ErtsSchedulerData *esdp) } } - if (!aux_work) { - if (thr_prgr_active) { - erts_thr_progress_active(esdp, thr_prgr_active = 0); - sched_wall_time_change(esdp, 0); + if (aux_work) { + current_time = erts_get_monotonic_time(); + if (current_time >= erts_next_timeout_time(esdp->next_tmo_ref)) { + if (!thr_prgr_active) { + erts_thr_progress_active(esdp, thr_prgr_active = 1); + sched_wall_time_change(esdp, 1); + } + erts_bump_timers(esdp->timer_wheel, current_time); } - erts_thr_progress_prepare_wait(esdp); - flgs = sched_spin_suspended(ssi, - ERTS_SCHED_SUSPEND_SLEEP_SPINCOUNT); - if (flgs == (ERTS_SSI_FLG_SLEEPING - | ERTS_SSI_FLG_WAITING - | ERTS_SSI_FLG_SUSPENDED)) { - flgs = sched_set_suspended_sleeptype(ssi); + } + else { + ErtsMonotonicTime timeout_time; + timeout_time = erts_check_next_timeout_time(esdp->timer_wheel, + ERTS_SEC_TO_MONOTONIC(60*60)); + current_time = erts_get_monotonic_time(); + + if (current_time >= timeout_time) { + if (!thr_prgr_active) { + erts_thr_progress_active(esdp, thr_prgr_active = 1); + sched_wall_time_change(esdp, 1); + } + } + else { + if (thr_prgr_active) { + erts_thr_progress_active(esdp, thr_prgr_active = 0); + sched_wall_time_change(esdp, 0); + } + erts_thr_progress_prepare_wait(esdp); + flgs = sched_spin_suspended(ssi, + ERTS_SCHED_SUSPEND_SLEEP_SPINCOUNT); if (flgs == (ERTS_SSI_FLG_SLEEPING - | ERTS_SSI_FLG_TSE_SLEEPING | ERTS_SSI_FLG_WAITING | ERTS_SSI_FLG_SUSPENDED)) { - int res; - - do { - res = erts_tse_wait(ssi->event); - } while (res == EINTR); + flgs = sched_set_suspended_sleeptype(ssi); + if (flgs == (ERTS_SSI_FLG_SLEEPING + | ERTS_SSI_FLG_TSE_SLEEPING + | ERTS_SSI_FLG_WAITING + | ERTS_SSI_FLG_SUSPENDED)) { + int res; + + current_time = erts_get_monotonic_time(); + do { + Sint64 timeout; + if (current_time >= timeout_time) + break; + timeout = ERTS_MONOTONIC_TO_NSEC(timeout_time + - current_time + - 1) + 1; + res = erts_tse_twait(ssi->event, timeout); + current_time = erts_get_monotonic_time(); + } while (res == EINTR); + } } + erts_thr_progress_finalize_wait(esdp); } - erts_thr_progress_finalize_wait(esdp); + + if (current_time >= timeout_time) + erts_bump_timers(esdp->timer_wheel, current_time); } flgs = sched_prep_spin_suspended(ssi, (ERTS_SSI_FLG_WAITING @@ -7613,6 +7740,9 @@ sched_thread_func(void *vesdp) ErtsThrPrgrCallbacks callbacks; ErtsSchedulerData *esdp = vesdp; Uint no = esdp->no; + + esdp->timer_wheel = erts_create_timer_wheel((int) no); + esdp->next_tmo_ref = erts_get_next_timeout_reference(esdp->timer_wheel); #ifdef ERTS_SMP ERTS_SCHED_SLEEP_INFO_IX(no - 1)->event = erts_tse_fetch(); callbacks.arg = (void *) esdp->ssi; @@ -7715,6 +7845,8 @@ sched_dirty_cpu_thread_func(void *vesdp) callbacks.wait = NULL; callbacks.finalize_wait = NULL; + esdp->thr_id += erts_no_schedulers; + erts_thr_progress_register_unmanaged_thread(&callbacks); #ifdef ERTS_ENABLE_LOCK_CHECK { @@ -7776,6 +7908,8 @@ sched_dirty_io_thread_func(void *vesdp) callbacks.wait = NULL; callbacks.finalize_wait = NULL; + esdp->thr_id += erts_no_schedulers + erts_no_dirty_cpu_schedulers; + erts_thr_progress_register_unmanaged_thread(&callbacks); #ifdef ERTS_ENABLE_LOCK_CHECK { @@ -8878,7 +9012,6 @@ Process *schedule(Process *p, int calls) { Process *proxy_p = NULL; ErtsRunQueue *rq; - erts_aint_t dt; ErtsSchedulerData *esdp; int context_reds; int fcalls; @@ -9008,11 +9141,13 @@ Process *schedule(Process *p, int calls) ERTS_SMP_CHK_NO_PROC_LOCKS; - dt = erts_do_time_read_and_reset(); - if (dt) { - erts_smp_runq_unlock(rq); - erts_bump_timer(dt); - erts_smp_runq_lock(rq); + { + ErtsMonotonicTime current_time = erts_get_monotonic_time(); + if (current_time >= erts_next_timeout_time(esdp->next_tmo_ref)) { + erts_smp_runq_unlock(rq); + erts_bump_timers(esdp->timer_wheel, current_time); + erts_smp_runq_lock(rq); + } } BM_STOP_TIMER(system); @@ -9158,6 +9293,7 @@ Process *schedule(Process *p, int calls) else if (!ERTS_SCHEDULER_IS_DIRTY(esdp) && (fcalls > input_reductions && prepare_for_sys_schedule(esdp, !0))) { + ErtsMonotonicTime current_time; /* * Schedule system-level activities. */ @@ -9170,8 +9306,10 @@ Process *schedule(Process *p, int calls) #endif erts_smp_runq_unlock(rq); erl_sys_schedule(1); - dt = erts_do_time_read_and_reset(); - if (dt) erts_bump_timer(dt); + + current_time = erts_get_monotonic_time(); + if (current_time >= erts_next_timeout_time(esdp->next_tmo_ref)) + erts_bump_timers(esdp->timer_wheel, current_time); #ifdef ERTS_SMP erts_smp_runq_lock(rq); @@ -10476,7 +10614,10 @@ erl_create_process(Process* parent, /* Parent of process (default group leader). int ix = so->scheduler-1; ASSERT(0 <= ix && ix < erts_no_run_queues); rq = ERTS_RUNQ_IX(ix); - state |= ERTS_PSFLG_BOUND; + if (!(so->flags & SPO_PREFER_SCHED)) { + /* Unsupported feature... */ + state |= ERTS_PSFLG_BOUND; + } } prio = (erts_aint32_t) so->priority; } @@ -10484,6 +10625,9 @@ erl_create_process(Process* parent, /* Parent of process (default group leader). state |= (((prio & ERTS_PSFLGS_PRIO_MASK) << ERTS_PSFLGS_ACT_PRIO_OFFSET) | ((prio & ERTS_PSFLGS_PRIO_MASK) << ERTS_PSFLGS_USR_PRIO_OFFSET)); + if (so->flags & SPO_OFF_HEAP_MSGS) + state |= ERTS_PSFLG_OFF_HEAP_MSGS; + if (!rq) rq = erts_get_runq_proc(parent); @@ -10507,11 +10651,25 @@ erl_create_process(Process* parent, /* Parent of process (default group leader). heap_need = arg_size; p->flags = erts_default_process_flags; + if (so->flags & SPO_OFF_HEAP_MSGS) + p->flags |= F_OFF_HEAP_MSGS; +#ifdef ERTS_SMP + p->preferred_run_queue = NULL; +#endif + p->static_flags = 0; + if (so->flags & SPO_SYSTEM_PROC) + p->static_flags |= ERTS_STC_FLG_SYSTEM_PROC; if (so->flags & SPO_USE_ARGS) { p->min_heap_size = so->min_heap_size; p->min_vheap_size = so->min_vheap_size; p->max_gen_gcs = so->max_gen_gcs; + if (so->flags & SPO_PREFER_SCHED) { +#ifdef ERTS_SMP + p->preferred_run_queue = rq; +#endif + p->static_flags |= ERTS_STC_FLG_PREFER_SCHED; + } } else { p->min_heap_size = H_MIN_SIZE; p->min_vheap_size = BIN_VH_MIN_SIZE; @@ -10589,7 +10747,7 @@ erl_create_process(Process* parent, /* Parent of process (default group leader). #ifdef ERTS_SMP p->common.u.alive.ptimer = NULL; #else - sys_memset(&p->common.u.alive.tm, 0, sizeof(ErlTimer)); + erts_init_timer(&p->common.u.alive.tm); #endif p->common.u.alive.reg = NULL; @@ -10782,7 +10940,7 @@ void erts_init_empty_process(Process *p) #ifdef ERTS_SMP p->common.u.alive.ptimer = NULL; #else - memset(&(p->common.u.alive.tm), 0, sizeof(ErlTimer)); + erts_init_timer(&p->common.u.alive.tm); #endif p->next = NULL; p->off_heap.first = NULL; @@ -10832,6 +10990,8 @@ void erts_init_empty_process(Process *p) p->parent = NIL; p->approx_started = 0; + p->static_flags = 0; + p->common.u.alive.started_interval = 0; #ifdef HIPE @@ -10857,6 +11017,7 @@ void erts_init_empty_process(Process *p) p->pending_suspenders = NULL; p->pending_exit.reason = THE_NON_VALUE; p->pending_exit.bp = NULL; + p->preferred_run_queue = NULL; erts_proc_lock_init(p); erts_smp_proc_unlock(p, ERTS_PROC_LOCKS_ALL); RUNQ_SET_RQ(&p->run_queue, ERTS_RUNQ_IX(0)); @@ -11482,7 +11643,8 @@ static void doit_exit_monitor(ErtsMonitor *mon, void *vpcontext) ErtsMonitor *rmon; Process *rp; - if (mon->type == MON_ORIGIN) { + switch (mon->type) { + case MON_ORIGIN: /* We are monitoring someone else, we need to demonitor that one.. */ if (is_atom(mon->pid)) { /* remote by name */ ASSERT(is_node_name_atom(mon->pid)); @@ -11545,7 +11707,8 @@ static void doit_exit_monitor(ErtsMonitor *mon, void *vpcontext) } } } - } else { /* type == MON_TARGET */ + break; + case MON_TARGET: ASSERT(mon->type == MON_TARGET); ASSERT(is_pid(mon->pid) || is_internal_port(mon->pid)); if (is_internal_port(mon->pid)) { @@ -11604,6 +11767,12 @@ static void doit_exit_monitor(ErtsMonitor *mon, void *vpcontext) } } } + break; + case MON_TIME_OFFSET: + erts_demonitor_time_offset(mon->ref); + break; + default: + ERTS_INTERNAL_ERROR("Invalid monitor type"); } done: /* As the monitors are previously removed from the process, @@ -11762,6 +11931,9 @@ erts_do_exit_process(Process* p, Eterm reason) } #endif + if (p->static_flags & ERTS_STC_FLG_SYSTEM_PROC) + erl_exit(1, "System process %T terminated: %T\n", p->common.id, reason); + #ifdef ERTS_SMP ERTS_SMP_CHK_HAVE_ONLY_MAIN_PROC_LOCK(p); /* By locking all locks (main lock is already locked) when going diff --git a/erts/emulator/beam/erl_process.h b/erts/emulator/beam/erl_process.h index d12ac792af..743711cc3b 100644 --- a/erts/emulator/beam/erl_process.h +++ b/erts/emulator/beam/erl_process.h @@ -348,7 +348,7 @@ typedef struct { } ErtsRunQueueInfo; -#ifdef HAVE_GETHRTIME +#ifdef ERTS_HAVE_OS_MONOTONIC_TIME_SUPPORT # undef ERTS_HAVE_SCHED_UTIL_BALANCING_SUPPORT_OPT # define ERTS_HAVE_SCHED_UTIL_BALANCING_SUPPORT_OPT 1 #endif @@ -564,6 +564,8 @@ struct ErtsSchedulerData_ { Eterm* x_reg_array; /* X registers */ FloatDef* f_reg_array; /* Floating point registers. */ + ErtsTimerWheel *timer_wheel; + ErtsNextTimeoutRef next_tmo_ref; #ifdef ERTS_SMP ethr_tid tid; /* Thread id */ struct erl_bits_state erl_bits_state; /* erl_bits.c state */ @@ -590,6 +592,10 @@ struct ErtsSchedulerData_ { ErtsAuxWorkData aux_work_data; ErtsAtomCacheMap atom_cache_map; + Uint32 thr_id; + Uint64 unique; + Uint64 ref; + ErtsSchedAllocData alloc_data; Uint64 reductions; @@ -936,6 +942,8 @@ struct process { Eterm parent; /* Pid of process that created this process. */ erts_approx_time_t approx_started; /* Time when started. */ + Uint32 static_flags; /* Flags that do *not* change */ + /* This is the place, where all fields that differs between memory * architectures, have gone to. */ @@ -967,6 +975,7 @@ struct process { ErtsSchedulerData *scheduler_data; Eterm suspendee; ErtsPendingSuspend *pending_suspenders; + ErtsRunQueue *preferred_run_queue; erts_smp_atomic_t run_queue; #ifdef HIPE struct hipe_process_state_smp hipe_smp; @@ -1076,14 +1085,15 @@ void erts_check_for_holes(Process* p); #define ERTS_PSFLG_RUNNING_SYS ERTS_PSFLG_BIT(15) #define ERTS_PSFLG_PROXY ERTS_PSFLG_BIT(16) #define ERTS_PSFLG_DELAYED_SYS ERTS_PSFLG_BIT(17) +#define ERTS_PSFLG_OFF_HEAP_MSGS ERTS_PSFLG_BIT(18) #ifdef ERTS_DIRTY_SCHEDULERS -#define ERTS_PSFLG_DIRTY_CPU_PROC ERTS_PSFLG_BIT(18) -#define ERTS_PSFLG_DIRTY_IO_PROC ERTS_PSFLG_BIT(19) -#define ERTS_PSFLG_DIRTY_CPU_PROC_IN_Q ERTS_PSFLG_BIT(20) -#define ERTS_PSFLG_DIRTY_IO_PROC_IN_Q ERTS_PSFLG_BIT(21) -#define ERTS_PSFLG_MAX (ERTS_PSFLGS_ZERO_BIT_OFFSET + 22) +#define ERTS_PSFLG_DIRTY_CPU_PROC ERTS_PSFLG_BIT(19) +#define ERTS_PSFLG_DIRTY_IO_PROC ERTS_PSFLG_BIT(20) +#define ERTS_PSFLG_DIRTY_CPU_PROC_IN_Q ERTS_PSFLG_BIT(21) +#define ERTS_PSFLG_DIRTY_IO_PROC_IN_Q ERTS_PSFLG_BIT(22) +#define ERTS_PSFLG_MAX (ERTS_PSFLGS_ZERO_BIT_OFFSET + 23) #else -#define ERTS_PSFLG_MAX (ERTS_PSFLGS_ZERO_BIT_OFFSET + 18) +#define ERTS_PSFLG_MAX (ERTS_PSFLGS_ZERO_BIT_OFFSET + 19) #endif #define ERTS_PSFLGS_IN_PRQ_MASK (ERTS_PSFLG_IN_PRQ_MAX \ @@ -1098,6 +1108,12 @@ void erts_check_for_holes(Process* p); #define ERTS_PSFLGS_GET_PRQ_PRIO(PSFLGS) \ (((PSFLGS) >> ERTS_PSFLGS_USR_PRIO_OFFSET) & ERTS_PSFLGS_PRIO_MASK) +/* + * Static flags that do not change after process creation. + */ +#define ERTS_STC_FLG_SYSTEM_PROC (((Uint32) 1) << 0) +#define ERTS_STC_FLG_PREFER_SCHED (((Uint32) 1) << 1) + /* The sequential tracing token is a tuple of size 5: * * {Flags, Label, Serial, Sender} @@ -1125,6 +1141,9 @@ void erts_check_for_holes(Process* p); #define SPO_LINK 1 #define SPO_USE_ARGS 2 #define SPO_MONITOR 4 +#define SPO_OFF_HEAP_MSGS 8 +#define SPO_SYSTEM_PROC 16 +#define SPO_PREFER_SCHED 32 /* * The following struct contains options for a process to be spawned. @@ -1212,6 +1231,7 @@ extern struct erts_system_profile_flags_t erts_system_profile_flags; #define F_P2PNR_RESCHED (1 << 9) /* Process has been rescheduled via erts_pid2proc_not_running() */ #define F_FORCE_GC (1 << 10) /* Force gc at process in-scheduling */ #define F_DISABLE_GC (1 << 11) /* Disable GC */ +#define F_OFF_HEAP_MSGS (1 << 12) /* process trace_flags */ #define F_SENSITIVE (1 << 0) @@ -2228,6 +2248,8 @@ extern int erts_disable_proc_not_running_opt; void erts_smp_notify_inc_runq(ErtsRunQueue *runq); +void erts_interupt_aux_thread_timed(ErtsMonotonicTime timeout_time); + #ifdef ERTS_SMP void erts_sched_finish_poke(ErtsSchedulerSleepInfo *, erts_aint32_t); ERTS_GLB_INLINE void erts_sched_poke(ErtsSchedulerSleepInfo *ssi); diff --git a/erts/emulator/beam/erl_thr_progress.c b/erts/emulator/beam/erl_thr_progress.c index c2365c5cf7..4c9b00d2ee 100644 --- a/erts/emulator/beam/erl_thr_progress.c +++ b/erts/emulator/beam/erl_thr_progress.c @@ -1359,18 +1359,16 @@ void erts_thr_progress_fatal_error_wait(SWord timeout) { erts_aint32_t bc; SWord time_left = timeout; - SysTimeval to; + ErtsMonotonicTime timeout_time; /* * Counting poll intervals may give us a too long timeout - * if cpu is busy. If we got tolerant time of day we use it - * to prevent this. + * if cpu is busy. We use timeout time to try to prevent + * this. In case we havn't got time correction this may + * however fail too... */ - if (!erts_disable_tolerant_timeofday) { - erts_get_timeval(&to); - to.tv_sec += timeout / 1000; - to.tv_sec += timeout % 1000; - } + timeout_time = erts_get_monotonic_time(); + timeout_time += ERTS_MSEC_TO_MONOTONIC((ErtsMonotonicTime) timeout); while (1) { if (erts_milli_sleep(ERTS_THR_PRGR_FTL_ERR_BLCK_POLL_INTERVAL) == 0) @@ -1380,14 +1378,8 @@ erts_thr_progress_fatal_error_wait(SWord timeout) { break; /* Succefully blocked all managed threads */ if (time_left <= 0) break; /* Timeout */ - if (!erts_disable_tolerant_timeofday) { - SysTimeval now; - erts_get_timeval(&now); - if (now.tv_sec > to.tv_sec) - break; /* Timeout */ - if (now.tv_sec == to.tv_sec && now.tv_usec >= to.tv_usec) - break; /* Timeout */ - } + if (timeout_time <= erts_get_monotonic_time()) + break; /* Timeout */ } } diff --git a/erts/emulator/beam/erl_threads.h b/erts/emulator/beam/erl_threads.h index 1fd800d524..dc20ac207f 100644 --- a/erts/emulator/beam/erl_threads.h +++ b/erts/emulator/beam/erl_threads.h @@ -652,6 +652,8 @@ ERTS_GLB_INLINE void erts_tse_set(erts_tse_t *ep); ERTS_GLB_INLINE void erts_tse_reset(erts_tse_t *ep); ERTS_GLB_INLINE int erts_tse_wait(erts_tse_t *ep); ERTS_GLB_INLINE int erts_tse_swait(erts_tse_t *ep, int spincount); +ERTS_GLB_INLINE int erts_tse_twait(erts_tse_t *ep, Sint64 tmo); +ERTS_GLB_INLINE int erts_tse_stwait(erts_tse_t *ep, int spincount, Sint64 tmo); ERTS_GLB_INLINE int erts_tse_is_tmp(erts_tse_t *ep); ERTS_GLB_INLINE void erts_thr_set_main_status(int, int); ERTS_GLB_INLINE int erts_thr_get_main_status(void); @@ -3490,6 +3492,27 @@ ERTS_GLB_INLINE int erts_tse_swait(erts_tse_t *ep, int spincount) #endif } +ERTS_GLB_INLINE int erts_tse_twait(erts_tse_t *ep, Sint64 tmo) +{ +#ifdef USE_THREADS + return ethr_event_twait(&((ethr_ts_event *) ep)->event, + (ethr_sint64_t) tmo); +#else + return ENOTSUP; +#endif +} + +ERTS_GLB_INLINE int erts_tse_stwait(erts_tse_t *ep, int spincount, Sint64 tmo) +{ +#ifdef USE_THREADS + return ethr_event_stwait(&((ethr_ts_event *) ep)->event, + spincount, + (ethr_sint64_t) tmo); +#else + return ENOTSUP; +#endif +} + ERTS_GLB_INLINE int erts_tse_is_tmp(erts_tse_t *ep) { #ifdef USE_THREADS diff --git a/erts/emulator/beam/erl_time.h b/erts/emulator/beam/erl_time.h index 7ed1a395ad..f201a8b4e3 100644 --- a/erts/emulator/beam/erl_time.h +++ b/erts/emulator/beam/erl_time.h @@ -20,11 +20,16 @@ #ifndef ERL_TIME_H__ #define ERL_TIME_H__ -#define ERTS_SHORT_TIME_T_MAX ERTS_AINT32_T_MAX -#define ERTS_SHORT_TIME_T_MIN ERTS_AINT32_T_MIN -typedef erts_aint32_t erts_short_time_t; +#if defined(DEBUG) || 0 +#define ERTS_TIME_ASSERT(B) ERTS_ASSERT(B) +#else +#define ERTS_TIME_ASSERT(B) ((void) 1) +#endif + +typedef struct ErtsTimerWheel_ ErtsTimerWheel; +typedef erts_atomic64_t * ErtsNextTimeoutRef; +extern ErtsTimerWheel *erts_default_timer_wheel; -extern erts_smp_atomic32_t do_time; /* set at clock interrupt */ extern SysTimeval erts_first_emu_time; /* @@ -34,8 +39,8 @@ typedef struct erl_timer { struct erl_timer* next; /* next entry tiw slot or chain */ struct erl_timer* prev; /* prev entry tiw slot or chain */ Uint slot; /* slot in timer wheel */ - Uint count; /* number of loops remaining */ - int active; /* 1=activated, 0=deactivated */ + erts_smp_atomic_t wheel; + ErtsMonotonicTime timeout_pos; /* Timeout in absolute clock ticks */ /* called when timeout */ void (*timeout)(void*); /* called when cancel (may be NULL) */ @@ -62,7 +67,6 @@ union ErtsSmpPTimer_ { ErtsSmpPTimer *next; }; - void erts_create_smp_ptimer(ErtsSmpPTimer **timer_ref, Eterm id, ErlTimeoutProc timeout_func, @@ -70,36 +74,43 @@ void erts_create_smp_ptimer(ErtsSmpPTimer **timer_ref, void erts_cancel_smp_ptimer(ErtsSmpPTimer *ptimer); #endif +void erts_monitor_time_offset(Eterm id, Eterm ref); +int erts_demonitor_time_offset(Eterm ref); + +void erts_early_init_time_sup(void); +void erts_late_init_time_sup(void); + /* timer-wheel api */ -void erts_init_time(void); +ErtsTimerWheel *erts_create_timer_wheel(int); +ErtsNextTimeoutRef erts_get_next_timeout_reference(ErtsTimerWheel *); +void erts_init_time(int time_correction, ErtsTimeWarpMode time_warp_mode); void erts_set_timer(ErlTimer*, ErlTimeoutProc, ErlCancelProc, void*, Uint); void erts_cancel_timer(ErlTimer*); -void erts_bump_timer(erts_short_time_t); -Uint erts_timer_wheel_memory_size(void); Uint erts_time_left(ErlTimer *); -erts_short_time_t erts_next_time(void); +void erts_bump_timers(ErtsTimerWheel *, ErtsMonotonicTime); +Uint erts_timer_wheel_memory_size(void); #ifdef DEBUG void erts_p_slpq(void); #endif -ERTS_GLB_INLINE erts_short_time_t erts_do_time_read_and_reset(void); -ERTS_GLB_INLINE void erts_do_time_add(erts_short_time_t); +ErtsMonotonicTime erts_check_next_timeout_time(ErtsTimerWheel *, + ErtsMonotonicTime); + +ERTS_GLB_INLINE void erts_init_timer(ErlTimer *p); +ERTS_GLB_INLINE ErtsMonotonicTime erts_next_timeout_time(ErtsNextTimeoutRef); #if ERTS_GLB_INLINE_INCL_FUNC_DEF -ERTS_GLB_INLINE erts_short_time_t erts_do_time_read_and_reset(void) +ERTS_GLB_INLINE void erts_init_timer(ErlTimer *p) { - erts_short_time_t time = erts_smp_atomic32_xchg_acqb(&do_time, 0); - if (time < 0) - erl_exit(ERTS_ABORT_EXIT, "Internal time management error\n"); - return time; + erts_smp_atomic_init_nob(&p->wheel, (erts_aint_t) NULL); } -ERTS_GLB_INLINE void erts_do_time_add(erts_short_time_t elapsed) +ERTS_GLB_INLINE ErtsMonotonicTime erts_next_timeout_time(ErtsNextTimeoutRef nxt_tmo_ref) { - erts_smp_atomic32_add_relb(&do_time, elapsed); + return (ErtsMonotonicTime) erts_atomic64_read_acqb((erts_atomic64_t *) nxt_tmo_ref); } #endif /* #if ERTS_GLB_INLINE_INCL_FUNC_DEF */ @@ -121,25 +132,228 @@ void erts_get_now_cpu(Uint* megasec, Uint* sec, Uint* microsec); typedef UWord erts_approx_time_t; erts_approx_time_t erts_get_approx_time(void); -void erts_get_timeval(SysTimeval *tv); -erts_time_t erts_get_time(void); +int erts_has_time_correction(void); +int erts_check_time_adj_support(int time_correction, + ErtsTimeWarpMode time_warp_mode); + +ErtsTimeWarpMode erts_time_warp_mode(void); + +typedef enum { + ERTS_TIME_OFFSET_PRELIMINARY, + ERTS_TIME_OFFSET_FINAL, + ERTS_TIME_OFFSET_VOLATILE +} ErtsTimeOffsetState; + +ErtsTimeOffsetState erts_time_offset_state(void); +ErtsTimeOffsetState erts_finalize_time_offset(void); +struct process; +Eterm erts_get_monotonic_start_time(struct process *c_p); +Eterm erts_monotonic_time_source(struct process*c_p); + +#ifdef SYS_CLOCK_RESOLUTION +#define ERTS_CLKTCK_RESOLUTION ((ErtsMonotonicTime) (SYS_CLOCK_RESOLUTION*1000)) +#else +#define ERTS_CLKTCK_RESOLUTION (erts_time_sup__.r.o.clktck_resolution) +#endif + +struct erts_time_sup_read_only__ { + ErtsMonotonicTime monotonic_time_unit; +#ifndef SYS_CLOCK_RESOLUTION + ErtsMonotonicTime clktck_resolution; +#endif +}; + +typedef struct { + union { + struct erts_time_sup_read_only__ o; + char align__[(((sizeof(struct erts_time_sup_read_only__) - 1) + / ASSUMED_CACHE_LINE_SIZE) + 1) + * ASSUMED_CACHE_LINE_SIZE]; + } r; +} ErtsTimeSupData; + +extern ErtsTimeSupData erts_time_sup__; -ERTS_GLB_INLINE int erts_cmp_timeval(SysTimeval *t1p, SysTimeval *t2p); +ERTS_GLB_INLINE Uint64 +erts_time_unit_conversion(Uint64 value, + Uint32 from_time_unit, + Uint32 to_time_unit); #if ERTS_GLB_INLINE_INCL_FUNC_DEF -ERTS_GLB_INLINE int -erts_cmp_timeval(SysTimeval *t1p, SysTimeval *t2p) +ERTS_GLB_INLINE Uint64 +erts_time_unit_conversion(Uint64 value, + Uint32 from_time_unit, + Uint32 to_time_unit) { - if (t1p->tv_sec == t2p->tv_sec) { - if (t1p->tv_usec < t2p->tv_usec) - return -1; - else if (t1p->tv_usec > t2p->tv_usec) - return 1; - return 0; - } - return t1p->tv_sec < t2p->tv_sec ? -1 : 1; + Uint64 high, low, result; + if (value <= ~((Uint64) 0)/to_time_unit) + return (value*to_time_unit)/from_time_unit; + + low = value & ((Uint64) 0xffffffff); + high = (value >> 32) & ((Uint64) 0xffffffff); + + low *= to_time_unit; + high *= to_time_unit; + + high += (low >> 32) & ((Uint64) 0xffffffff); + low &= ((Uint64) 0xffffffff); + + result = high % from_time_unit; + high /= from_time_unit; + high <<= 32; + + result <<= 32; + result += low; + result /= from_time_unit; + result += high; + + return result; } -#endif /* #if ERTS_GLB_INLINE_INCL_FUNC_DEF */ +#endif /* ERTS_GLB_INLINE_INCL_FUNC_DEF */ + +#if ERTS_COMPILE_TIME_MONOTONIC_TIME_UNIT + +/* + * If the monotonic time unit is a compile time constant, + * it is assumed (and need) to be a power of 10. + */ + +#define ERTS_MONOTONIC_TIME_UNIT \ + ((ErtsMonotonicTime) ERTS_COMPILE_TIME_MONOTONIC_TIME_UNIT) + +#if ERTS_COMPILE_TIME_MONOTONIC_TIME_UNIT == 1000*1000*1000 +/* Nano-second time unit */ + +#define ERTS_MONOTONIC_TO_SEC__(NSEC) ((NSEC) / (1000*1000*1000)) +#define ERTS_MONOTONIC_TO_MSEC__(NSEC) ((NSEC) / (1000*1000)) +#define ERTS_MONOTONIC_TO_USEC__(NSEC) ((NSEC) / 1000) +#define ERTS_MONOTONIC_TO_NSEC__(NSEC) (NSEC) + +#define ERTS_SEC_TO_MONOTONIC__(SEC) (((ErtsMonotonicTime) (SEC))*(1000*1000*1000)) +#define ERTS_MSEC_TO_MONOTONIC__(MSEC) (((ErtsMonotonicTime) (MSEC))*(1000*1000)) +#define ERTS_USEC_TO_MONOTONIC__(USEC) (((ErtsMonotonicTime) (USEC))*1000) +#define ERTS_NSEC_TO_MONOTONIC__(NSEC) ((ErtsMonotonicTime) (NSEC)) + +#elif ERTS_COMPILE_TIME_MONOTONIC_TIME_UNIT == 1000*1000 +/* Micro-second time unit */ + +#define ERTS_MONOTONIC_TO_SEC__(USEC) ((USEC) / (1000*1000)) +#define ERTS_MONOTONIC_TO_MSEC__(USEC) ((USEC) / 1000) +#define ERTS_MONOTONIC_TO_USEC__(USEC) (USEC) +#define ERTS_MONOTONIC_TO_NSEC__(USEC) ((USEC)*1000) + +#define ERTS_SEC_TO_MONOTONIC__(SEC) (((ErtsMonotonicTime) (SEC))*(1000*1000)) +#define ERTS_MSEC_TO_MONOTONIC__(MSEC) (((ErtsMonotonicTime) (MSEC))*1000) +#define ERTS_USEC_TO_MONOTONIC__(USEC) ((ErtsMonotonicTime) (USEC)) +#define ERTS_NSEC_TO_MONOTONIC__(NSEC) (((ErtsMonotonicTime) (NSEC))/1000) + +#elif ERTS_COMPILE_TIME_MONOTONIC_TIME_UNIT == 1000 +/* Milli-second time unit */ + +#define ERTS_MONOTONIC_TO_SEC__(MSEC) ((USEC)/(1000)) +#define ERTS_MONOTONIC_TO_MSEC__(MSEC) (MSEC) +#define ERTS_MONOTONIC_TO_USEC__(MSEC) ((MSEC)*1000) +#define ERTS_MONOTONIC_TO_NSEC__(MSEC) ((MSEC)*(1000*1000)) + +#define ERTS_SEC_TO_MONOTONIC__(SEC) (((ErtsMonotonicTime) (SEC))*1000) +#define ERTS_MSEC_TO_MONOTONIC__(MSEC) ((ErtsMonotonicTime) (MSEC)) +#define ERTS_USEC_TO_MONOTONIC__(USEC) (((ErtsMonotonicTime) (USEC))/1000) +#define ERTS_NSEC_TO_MONOTONIC__(NSEC) (((ErtsMonotonicTime) (NSEC))/(1000*1000)) + +#else +#error Missing implementation for monotonic time unit +#endif + +#define ERTS_MONOTONIC_TO_CLKTCKS__(MON) \ + ((MON) / (ERTS_MONOTONIC_TIME_UNIT/ERTS_CLKTCK_RESOLUTION)) +#define ERTS_CLKTCKS_TO_MONOTONIC__(TCKS) \ + ((TCKS) * (ERTS_MONOTONIC_TIME_UNIT/ERTS_CLKTCK_RESOLUTION)) + +#else /* !ERTS_COMPILE_TIME_MONOTONIC_TIME_UNIT */ + +#define ERTS_MONOTONIC_TIME_UNIT (erts_time_sup__.r.o.monotonic_time_unit) + +#define ERTS_CONV_FROM_MON_UNIT___(M, TO) \ + ((ErtsMonotonicTime) \ + erts_time_unit_conversion((Uint64) (M), \ + (Uint32) ERTS_MONOTONIC_TIME_UNIT, \ + (Uint32) (TO))) + +#define ERTS_CONV_TO_MON_UNIT___(M, FROM) \ + ((ErtsMonotonicTime) \ + erts_time_unit_conversion((Uint64) (M), \ + (Uint32) (FROM), \ + (Uint32) ERTS_MONOTONIC_TIME_UNIT)) \ + +#define ERTS_MONOTONIC_TO_SEC__(M) \ + ERTS_CONV_FROM_MON_UNIT___((M), 1) +#define ERTS_MONOTONIC_TO_MSEC__(M) \ + ERTS_CONV_FROM_MON_UNIT___((M), 1000) +#define ERTS_MONOTONIC_TO_USEC__(M) \ + ERTS_CONV_FROM_MON_UNIT___((M), 1000*1000) +#define ERTS_MONOTONIC_TO_NSEC__(M) \ + ERTS_CONV_FROM_MON_UNIT___((M), 1000*1000*1000) + +#define ERTS_SEC_TO_MONOTONIC__(SEC) \ + ERTS_CONV_TO_MON_UNIT___((SEC), 1) +#define ERTS_MSEC_TO_MONOTONIC__(MSEC) \ + ERTS_CONV_TO_MON_UNIT___((MSEC), 1000) +#define ERTS_USEC_TO_MONOTONIC__(USEC) \ + ERTS_CONV_TO_MON_UNIT___((USEC), 1000*1000) +#define ERTS_NSEC_TO_MONOTONIC__(NSEC) \ + ERTS_CONV_TO_MON_UNIT___((NSEC), 1000*1000*1000) + +#define ERTS_MONOTONIC_TO_CLKTCKS__(MON) \ + ERTS_CONV_FROM_MON_UNIT___((MON), ERTS_CLKTCK_RESOLUTION) +#define ERTS_CLKTCKS_TO_MONOTONIC__(TCKS) \ + ERTS_CONV_TO_MON_UNIT___((TCKS), ERTS_CLKTCK_RESOLUTION) + +#endif /* !ERTS_COMPILE_TIME_MONOTONIC_TIME_UNIT */ + +#define ERTS_MSEC_TO_CLKTCKS__(MON) \ + ((MON) * (ERTS_CLKTCK_RESOLUTION/1000)) +#define ERTS_CLKTCKS_TO_MSEC__(TCKS) \ + ((TCKS) / (ERTS_CLKTCK_RESOLUTION/1000)) + +#define ERTS_MONOTONIC_TO_SEC(X) \ + (ERTS_TIME_ASSERT((X) >= 0), \ + ERTS_MONOTONIC_TO_SEC__((X))) +#define ERTS_MONOTONIC_TO_MSEC(X) \ + (ERTS_TIME_ASSERT((X) >= 0), \ + ERTS_MONOTONIC_TO_MSEC__((X))) +#define ERTS_MONOTONIC_TO_USEC(X) \ + (ERTS_TIME_ASSERT((X) >= 0), \ + ERTS_MONOTONIC_TO_USEC__((X))) +#define ERTS_MONOTONIC_TO_NSEC(X) \ + (ERTS_TIME_ASSERT((X) >= 0), \ + ERTS_MONOTONIC_TO_NSEC__((X))) +#define ERTS_SEC_TO_MONOTONIC(X) \ + (ERTS_TIME_ASSERT((X) >= 0), \ + ERTS_SEC_TO_MONOTONIC__((X))) +#define ERTS_MSEC_TO_MONOTONIC(X) \ + (ERTS_TIME_ASSERT((X) >= 0), \ + ERTS_MSEC_TO_MONOTONIC__((X))) +#define ERTS_USEC_TO_MONOTONIC(X) \ + (ERTS_TIME_ASSERT((X) >= 0), \ + ERTS_USEC_TO_MONOTONIC__((X))) +#define ERTS_NSEC_TO_MONOTONIC(X) \ + (ERTS_TIME_ASSERT((X) >= 0), \ + ERTS_NSEC_TO_MONOTONIC__((X))) + +#define ERTS_MONOTONIC_TO_CLKTCKS(X) \ + (ERTS_TIME_ASSERT((X) >= 0), \ + ERTS_MONOTONIC_TO_CLKTCKS__((X))) +#define ERTS_CLKTCKS_TO_MONOTONIC(X) \ + (ERTS_TIME_ASSERT((X) >= 0), \ + ERTS_CLKTCKS_TO_MONOTONIC__((X))) + +#define ERTS_MSEC_TO_CLKTCKS(X) \ + (ERTS_TIME_ASSERT((X) >= 0), \ + ERTS_MSEC_TO_CLKTCKS__((X))) +#define ERTS_CLKTCKS_TO_MSEC(X) \ + (ERTS_TIME_ASSERT((X) >= 0), \ + ERTS_CLKTCKS_TO_MSEC__((X))) + #endif /* ERL_TIME_H__ */ diff --git a/erts/emulator/beam/erl_time_sup.c b/erts/emulator/beam/erl_time_sup.c index 3272a5326d..d47d1682d7 100644 --- a/erts/emulator/beam/erl_time_sup.c +++ b/erts/emulator/beam/erl_time_sup.c @@ -18,60 +18,8 @@ */ /* -** Support routines for the timer wheel -** -** This code contains two strategies for dealing with -** date/time changes in the system. -** If the system has some kind of high resolution timer (HAVE_GETHRTIME), -** the high resolution timer is used to correct the time-of-day and the -** timeouts, the base source is the hrtimer, but at certain intervals the -** OS time-of-day is checked and if it is not within certain bounds, the -** delivered time gets slowly adjusted for each call until -** it corresponds to the system time (built-in adjtime...). -** The call gethrtime() is detected by autoconf on Unix, but other -** platforms may define it in erl_*_sys.h and implement -** their own high resolution timer. The high resolution timer -** strategy is (probably) best on all systems where the timer have -** a resolution higher or equal to gettimeofday (or what's implemented -** is sys_gettimeofday()). The actual resolution is the interesting thing, -** not the unit's thats used (i.e. on VxWorks, nanoseconds can be -** retrieved in terms of units, but the actual resolution is the same as -** for the clock ticks). -** If the systems best timer routine is kernel ticks returned from -** sys_times(), and the actual resolution of sys_gettimeofday() is -** better (like most unixes that does not have any realtime extensions), -** another strategy is used. The tolerant gettimeofday() corrects -** the value with respect to uptime (sys_times() return value) and checks -** for correction both when delivering timeticks and delivering nowtime. -** this strategy is slower, but accurate on systems without better timer -** routines. The kernel tick resolution is not enough to implement -** a gethrtime routine. On Linux and other non solaris unix-boxes the second -** strategy is used, on all other platforms we use the first. -** -** The following is expected (from sys.[ch] and erl_*_sys.h): -** -** 64 bit integers. So it is, and so it will be. -** -** sys_init_time(), will return the clock resolution in MS and -** that's about it. More could be added of course -** If the clock-rate is constant (i.e. 1 ms) one can define -** SYS_CLOCK_RESOLUTION (to 1), -** which makes erts_deliver_time/erts_time_remaining a bit faster. -** -** if HAVE_GETHRTIME is defined: -** sys_gethrtime() will return a SysHrTime (long long) representing -** nanoseconds, sys_init_hrtime() will do any initialization. -** else -** a long (64bit) integer type called Sint64 should be defined. -** -** sys_times() will return clock_ticks since start and -** fill in a SysTimes structure (struct tms). Instead of CLK_TCK, -** SYS_CLK_TCK is used to determine the resolution of kernel ticks. -** -** sys_gettimeofday() will take a SysTimeval (a struct timeval) as parameter -** and fill it in as gettimeofday(X,NULL). -** -*/ + * Support routines for the time + */ #ifdef HAVE_CONFIG_H # include "config.h" @@ -80,384 +28,1029 @@ #include "sys.h" #include "erl_vm.h" #include "global.h" - + static erts_smp_mtx_t erts_timeofday_mtx; - -static SysTimeval inittv; /* Used everywhere, the initial time-of-day */ +static erts_smp_mtx_t erts_get_time_mtx; static SysTimes t_start; /* Used in elapsed_time_both */ -static SysTimeval gtv; /* Used in wall_clock_elapsed_time_both */ -static SysTimeval then; /* Used in get_now */ -static SysTimeval last_emu_time; /* Used in erts_get_emu_time() */ -SysTimeval erts_first_emu_time; /* Used in erts_get_emu_time() */ +static ErtsMonotonicTime prev_wall_clock_elapsed; /* Used in wall_clock_elapsed_time_both */ +static ErtsMonotonicTime previous_now; /* Used in get_now */ + +static ErtsMonitor *time_offset_monitors = NULL; +static Uint no_time_offset_monitors = 0; -union { - erts_smp_atomic_t time; - char align[ERTS_CACHE_LINE_SIZE]; -} approx erts_align_attribute(ERTS_CACHE_LINE_SIZE); +#ifdef DEBUG +static int time_sup_initialized = 0; +#endif + +#define ERTS_MONOTONIC_TIME_KILO \ + ((ErtsMonotonicTime) 1000) +#define ERTS_MONOTONIC_TIME_MEGA \ + (ERTS_MONOTONIC_TIME_KILO*ERTS_MONOTONIC_TIME_KILO) +#define ERTS_MONOTONIC_TIME_GIGA \ + (ERTS_MONOTONIC_TIME_MEGA*ERTS_MONOTONIC_TIME_KILO) +#define ERTS_MONOTONIC_TIME_TERA \ + (ERTS_MONOTONIC_TIME_GIGA*ERTS_MONOTONIC_TIME_KILO) static void -init_approx_time(void) +schedule_send_time_offset_changed_notifications(ErtsMonotonicTime new_offset); + +/* + * NOTE! ERTS_MONOTONIC_TIME_START *need* to be a multiple + * of ERTS_MONOTONIC_TIME_UNIT. + */ + +#if ERTS_COMPILE_TIME_MONOTONIC_TIME_UNIT + +#ifdef ARCH_32 +/* + * Want to use a big-num of arity 2 as long as possible (584 years + * in the nano-second time unit case). + */ +#define ERTS_MONOTONIC_TIME_START \ + (((((((ErtsMonotonicTime) 1) << 32)-1) \ + / ERTS_MONOTONIC_TIME_UNIT) \ + * ERTS_MONOTONIC_TIME_UNIT) \ + + ERTS_MONOTONIC_TIME_UNIT) + +#else /* ARCH_64 */ + +#if ERTS_COMPILE_TIME_MONOTONIC_TIME_UNIT <= 1000*1000 + +/* + * Using micro second time unit or lower. Start at zero since + * time will remain an immediate for a very long time anyway + * (18279 years in the micro second case)... + */ +#define ERTS_MONOTONIC_TIME_START ((ErtsMonotonicTime) 0) + +#else /* ERTS_COMPILE_TIME_MONOTONIC_TIME_UNIT > 1000*1000 */ + +/* + * Want to use an immediate as long as possible (36 years in the + * nano-second time unit case). +*/ +#define ERTS_MONOTONIC_TIME_START \ + ((((ErtsMonotonicTime) MIN_SMALL) \ + / ERTS_MONOTONIC_TIME_UNIT) \ + * ERTS_MONOTONIC_TIME_UNIT) + +#endif /* ERTS_COMPILE_TIME_MONOTONIC_TIME_UNIT > 1000*1000 */ + +#endif /* ARCH_64 */ + +#define ERTS_MONOTONIC_OFFSET_NATIVE ERTS_MONOTONIC_TIME_START +#define ERTS_MONOTONIC_OFFSET_NSEC ERTS_MONOTONIC_TO_NSEC__(ERTS_MONOTONIC_TIME_START) +#define ERTS_MONOTONIC_OFFSET_USEC ERTS_MONOTONIC_TO_USEC__(ERTS_MONOTONIC_TIME_START) +#define ERTS_MONOTONIC_OFFSET_MSEC ERTS_MONOTONIC_TO_MSEC__(ERTS_MONOTONIC_TIME_START) +#define ERTS_MONOTONIC_OFFSET_SEC ERTS_MONOTONIC_TO_SEC__(ERTS_MONOTONIC_TIME_START) + +#else /* ERTS_COMPILE_TIME_MONOTONIC_TIME_UNIT */ + +/* + * Initialized in erts_init_time_sup()... + */ + +#define ERTS_MONOTONIC_TIME_START (time_sup.r.o.start) +#define ERTS_MONOTONIC_OFFSET_NATIVE (time_sup.r.o.start_offset.native) +#define ERTS_MONOTONIC_OFFSET_NSEC (time_sup.r.o.start_offset.nsec) +#define ERTS_MONOTONIC_OFFSET_USEC (time_sup.r.o.start_offset.usec) +#define ERTS_MONOTONIC_OFFSET_MSEC (time_sup.r.o.start_offset.msec) +#define ERTS_MONOTONIC_OFFSET_SEC (time_sup.r.o.start_offset.sec) + +#endif /* ERTS_COMPILE_TIME_MONOTONIC_TIME_UNIT */ + +#define ERTS_MONOTONIC_TO_SYS_TIME_VAL(TVP, MT) \ + do { \ + ErtsMonotonicTime sec__, usec__; \ + sec__ = ERTS_MONOTONIC_TO_SEC((MT)); \ + usec__ = ERTS_MONOTONIC_TO_USEC((MT)) - sec__*1000000; \ + ASSERT(usec__ < 1000000); \ + (TVP)->tv_sec = sec__; \ + (TVP)->tv_usec = usec__; \ + } while (0) + +#define ERTS_MAX_SYSTEM_TIME_DIFF ERTS_MSEC_TO_MONOTONIC(10) +#define ERTS_SYSTEM_TIME_DIFF_EXCEED_LIMIT(ESYSTIME, OSSYSTIME) \ + (((Uint64) (ESYSTIME)) - (((Uint64) (OSSYSTIME)) \ + - ERTS_MAX_SYSTEM_TIME_DIFF) \ + > 2*ERTS_MAX_SYSTEM_TIME_DIFF) + +#define ERTS_TIME_CORRECTION_LARGE_ADJ_DIFF (ERTS_MAX_SYSTEM_TIME_DIFF/2) +#define ERTS_TIME_CORRECTION_SMALL_ADJ_DIFF ERTS_USEC_TO_MONOTONIC(500) + +struct time_sup_read_only__ { + ErtsMonotonicTime (*get_time)(void); + int correction; + ErtsTimeWarpMode warp_mode; +#ifdef ERTS_HAVE_OS_MONOTONIC_TIME_SUPPORT + ErtsMonotonicTime moffset; + int os_monotonic_disable; + char *os_monotonic_func; + char *os_monotonic_clock_id; + int os_monotonic_locked; + Uint64 os_monotonic_resolution; +#endif +#if !ERTS_COMPILE_TIME_MONOTONIC_TIME_UNIT + ErtsMonotonicTime start; + struct { + ErtsMonotonicTime native; + ErtsMonotonicTime nsec; + ErtsMonotonicTime usec; + ErtsMonotonicTime msec; + ErtsMonotonicTime sec; + } start_offset; +#endif +}; + +typedef struct { +#ifndef ERTS_HAVE_CORRECTED_OS_MONOTONIC + ErtsMonotonicTime drift; /* Correction for os monotonic drift */ +#endif + ErtsMonotonicTime error; /* Correction for error between system times */ +} ErtsMonotonicCorrection; + +typedef struct { + ErtsMonotonicTime erl_mtime; + ErtsMonotonicTime os_mtime; + ErtsMonotonicCorrection correction; +} ErtsMonotonicCorrectionInstance; + +#define ERTS_DRIFT_INTERVALS 5 +typedef struct { + struct { + struct { + ErtsMonotonicTime sys; + ErtsMonotonicTime mon; + } diff; + struct { + ErtsMonotonicTime sys; + ErtsMonotonicTime mon; + } time; + } intervals[ERTS_DRIFT_INTERVALS]; + struct { + ErtsMonotonicTime sys; + ErtsMonotonicTime mon; + } acc; + int ix; + int dirty_counter; +} ErtsMonotonicDriftData; + +typedef struct { + ErtsMonotonicCorrectionInstance prev; + ErtsMonotonicCorrectionInstance curr; +#ifndef ERTS_HAVE_CORRECTED_OS_MONOTONIC + ErtsMonotonicDriftData drift; +#endif + ErtsMonotonicTime last_check; + int short_check_interval; +} ErtsMonotonicCorrectionData; + +struct time_sup_infrequently_changed__ { +#ifdef ERTS_HAVE_OS_MONOTONIC_TIME_SUPPORT + struct { + erts_smp_rwmtx_t rwmtx; + ErlTimer timer; + ErtsMonotonicCorrectionData cdata; + } parmon; + ErtsMonotonicTime minit; +#endif + int finalized_offset; + SysTimeval inittv; /* Used everywhere, the initial time-of-day */ + ErtsMonotonicTime not_corrected_moffset; + erts_atomic64_t offset; +}; + +struct time_sup_frequently_changed__ { + ErtsMonotonicTime last_not_corrected_time; +}; + +static struct { + union { + struct time_sup_read_only__ o; + char align__[ERTS_ALC_CACHE_LINE_ALIGN_SIZE(sizeof(struct time_sup_read_only__))]; + } r; + union { + struct time_sup_infrequently_changed__ c; + char align__[ERTS_ALC_CACHE_LINE_ALIGN_SIZE(sizeof(struct time_sup_infrequently_changed__))]; + } inf; + union { + struct time_sup_frequently_changed__ c; + char align__[ERTS_ALC_CACHE_LINE_ALIGN_SIZE(sizeof(struct time_sup_frequently_changed__))]; + } f; +} time_sup erts_align_attribute(ERTS_CACHE_LINE_SIZE); + +ErtsTimeSupData erts_time_sup__ erts_align_attribute(ERTS_CACHE_LINE_SIZE); + +/* + * erts_get_approx_time() returns an *approximate* time + * in seconds. NOTE that this time may jump backwards!!! + */ +erts_approx_time_t +erts_get_approx_time(void) { - erts_smp_atomic_init_nob(&approx.time, 0); + SysTimeval tv; + sys_gettimeofday(&tv); + + return (erts_approx_time_t) tv.tv_sec; } -static ERTS_INLINE erts_approx_time_t -get_approx_time(void) +static ERTS_INLINE void +init_time_offset(ErtsMonotonicTime offset) { - return (erts_approx_time_t) erts_smp_atomic_read_nob(&approx.time); + erts_atomic64_init_nob(&time_sup.inf.c.offset, (erts_aint64_t) offset); } static ERTS_INLINE void -update_approx_time(SysTimeval *tv) +set_time_offset(ErtsMonotonicTime offset) { - erts_approx_time_t new_secs = (erts_approx_time_t) tv->tv_sec; - erts_approx_time_t old_secs = get_approx_time(); - if (old_secs != new_secs) - erts_smp_atomic_set_nob(&approx.time, new_secs); + erts_atomic64_set_relb(&time_sup.inf.c.offset, (erts_aint64_t) offset); } -/* - * erts_get_approx_time() returns an *approximate* time - * in seconds. NOTE that this time may jump backwards!!! - */ -erts_approx_time_t -erts_get_approx_time(void) +static ERTS_INLINE ErtsMonotonicTime +get_time_offset(void) { - return get_approx_time(); + return (ErtsMonotonicTime) erts_atomic64_read_acqb(&time_sup.inf.c.offset); } -#ifdef HAVE_GETHRTIME -int erts_disable_tolerant_timeofday; +#ifdef ERTS_HAVE_OS_MONOTONIC_TIME_SUPPORT + +/* + * Time correction adjustments made due to + * error between Erlang system time and OS + * system time: + * - Large adjustment ~1% + * - Small adjustment ~0.05% + */ +#define ERTS_TCORR_ERR_UNIT 2048 +#define ERTS_TCORR_ERR_LARGE_ADJ 20 +#define ERTS_TCORR_ERR_SMALL_ADJ 1 -static SysHrTime hr_init_time, hr_last_correction_check, - hr_correction, hr_last_time; +#define ERTS_INIT_SHORT_INTERVAL_COUNTER 10 +#define ERTS_LONG_TIME_CORRECTION_CHECK ERTS_SEC_TO_MONOTONIC(60) +#define ERTS_SHORT_TIME_CORRECTION_CHECK ERTS_SEC_TO_MONOTONIC(15) -static void init_tolerant_timeofday(void) +#define ERTS_TIME_DRIFT_MAX_ADJ_DIFF ERTS_USEC_TO_MONOTONIC(100) +#define ERTS_TIME_DRIFT_MIN_ADJ_DIFF ERTS_USEC_TO_MONOTONIC(5) + +static ERTS_INLINE ErtsMonotonicTime +calc_corrected_erl_mtime(ErtsMonotonicTime os_mtime, + ErtsMonotonicCorrectionInstance *cip, + ErtsMonotonicTime *os_mdiff_p) { - /* Should be in sys.c */ -#if defined(HAVE_SYSCONF) && defined(_SC_NPROCESSORS_CONF) - if (sysconf(_SC_NPROCESSORS_CONF) > 1) { - char b[1024]; - int maj,min,build; - os_flavor(b,1024); - os_version(&maj,&min,&build); - if (!strcmp(b,"sunos") && maj <= 5 && min <= 7) { - erts_disable_tolerant_timeofday = 1; - } - } + ErtsMonotonicTime erl_mtime, diff = os_mtime - cip->os_mtime; + ERTS_TIME_ASSERT(diff >= 0); +#ifndef ERTS_HAVE_CORRECTED_OS_MONOTONIC + diff += (cip->correction.drift*diff)/ERTS_MONOTONIC_TIME_UNIT; #endif - hr_init_time = sys_gethrtime(); - hr_last_correction_check = hr_last_time = hr_init_time; - hr_correction = 0; + erl_mtime = cip->erl_mtime; + erl_mtime += diff; + erl_mtime += cip->correction.error*(diff/ERTS_TCORR_ERR_UNIT); + if (os_mdiff_p) + *os_mdiff_p = diff; + return erl_mtime; } -static void get_tolerant_timeofday(SysTimeval *tv) +static ErtsMonotonicTime get_corrected_time(void) { - SysHrTime diff_time, curr; + ErtsMonotonicTime os_mtime; + ErtsMonotonicCorrectionData cdata; + ErtsMonotonicCorrectionInstance *cip; + + erts_smp_rwmtx_rlock(&time_sup.inf.c.parmon.rwmtx); + + os_mtime = erts_os_monotonic_time(); + + cdata = time_sup.inf.c.parmon.cdata; - if (erts_disable_tolerant_timeofday) { - sys_gettimeofday(tv); - return; + erts_smp_rwmtx_runlock(&time_sup.inf.c.parmon.rwmtx); + + if (os_mtime >= cdata.curr.os_mtime) + cip = &cdata.curr; + else { + if (os_mtime < cdata.prev.os_mtime) + erl_exit(ERTS_ABORT_EXIT, + "OS monotonic time stepped backwards\n"); + cip = &cdata.prev; } - *tv = inittv; - diff_time = ((curr = sys_gethrtime()) + hr_correction - hr_init_time) / 1000; - if (curr < hr_init_time) { - erl_exit(1,"Unexpected behaviour from operating system high " - "resolution timer"); + return calc_corrected_erl_mtime(os_mtime, cip, NULL); +} + +static void +check_time_correction(void *unused) +{ + ErtsMonotonicCorrectionData cdata; + ErtsMonotonicCorrection new_correction; + ErtsMonotonicCorrectionInstance *cip; + ErtsMonotonicTime mdiff, sdiff, os_mtime, erl_mtime, os_stime, erl_stime, time_offset; + Uint timeout; + SysTimeval tod; + int set_new_correction, begin_short_intervals = 0; + + erts_smp_rwmtx_rlock(&time_sup.inf.c.parmon.rwmtx); + + ASSERT(time_sup.inf.c.finalized_offset); + + os_mtime = erts_os_monotonic_time(); + sys_gettimeofday(&tod); + + cdata = time_sup.inf.c.parmon.cdata; + + erts_smp_rwmtx_runlock(&time_sup.inf.c.parmon.rwmtx); + + if (os_mtime < cdata.curr.os_mtime) + erl_exit(ERTS_ABORT_EXIT, + "OS monotonic time stepped backwards\n"); + cip = &cdata.curr; + + erl_mtime = calc_corrected_erl_mtime(os_mtime, cip, &mdiff); + time_offset = get_time_offset(); + erl_stime = erl_mtime + time_offset; + + os_stime = ERTS_SEC_TO_MONOTONIC(tod.tv_sec); + os_stime += ERTS_USEC_TO_MONOTONIC(tod.tv_usec); + + sdiff = erl_stime - os_stime; + + new_correction = cip->correction; + + if (time_sup.r.o.warp_mode == ERTS_MULTI_TIME_WARP_MODE + && (sdiff < -2*ERTS_TIME_CORRECTION_SMALL_ADJ_DIFF + || 2*ERTS_TIME_CORRECTION_SMALL_ADJ_DIFF < sdiff)) { + /* System time diff exeeded limits; change time offset... */ + time_offset -= sdiff; + sdiff = 0; + set_time_offset(time_offset); + schedule_send_time_offset_changed_notifications(time_offset); + begin_short_intervals = 1; + if (cdata.curr.correction.error == 0) + set_new_correction = 0; + else { + set_new_correction = 1; + new_correction.error = 0; + } + } + else if (cdata.curr.correction.error == 0) { + if (sdiff < -ERTS_TIME_CORRECTION_SMALL_ADJ_DIFF) { + set_new_correction = 1; + if (sdiff < -ERTS_TIME_CORRECTION_LARGE_ADJ_DIFF) + new_correction.error = ERTS_TCORR_ERR_LARGE_ADJ; + else + new_correction.error = ERTS_TCORR_ERR_SMALL_ADJ; + } + else if (sdiff > ERTS_TIME_CORRECTION_SMALL_ADJ_DIFF) { + set_new_correction = 1; + if (sdiff > ERTS_TIME_CORRECTION_LARGE_ADJ_DIFF) + new_correction.error = -ERTS_TCORR_ERR_LARGE_ADJ; + else + new_correction.error = -ERTS_TCORR_ERR_SMALL_ADJ; + } + else { + set_new_correction = 0; + } + } + else if (cdata.curr.correction.error > 0) { + if (sdiff < 0) { + if (cdata.curr.correction.error == ERTS_TCORR_ERR_LARGE_ADJ + || -ERTS_TIME_CORRECTION_LARGE_ADJ_DIFF <= sdiff) + set_new_correction = 0; + else { + new_correction.error = ERTS_TCORR_ERR_LARGE_ADJ; + set_new_correction = 1; + } + } + else if (sdiff > ERTS_TIME_CORRECTION_SMALL_ADJ_DIFF) { + set_new_correction = 1; + if (sdiff > ERTS_TIME_CORRECTION_LARGE_ADJ_DIFF) + new_correction.error = -ERTS_TCORR_ERR_LARGE_ADJ; + else + new_correction.error = -ERTS_TCORR_ERR_SMALL_ADJ; + } + else { + set_new_correction = 1; + new_correction.error = 0; + } + } + else /* if (cdata.curr.correction.error < 0) */ { + if (0 < sdiff) { + if (cdata.curr.correction.error == -ERTS_TCORR_ERR_LARGE_ADJ + || sdiff <= ERTS_TIME_CORRECTION_LARGE_ADJ_DIFF) + set_new_correction = 0; + else { + new_correction.error = -ERTS_TCORR_ERR_LARGE_ADJ; + set_new_correction = 1; + } + set_new_correction = 0; + } + else if (sdiff < -ERTS_TIME_CORRECTION_SMALL_ADJ_DIFF) { + set_new_correction = 1; + if (sdiff < -ERTS_TIME_CORRECTION_LARGE_ADJ_DIFF) + new_correction.error = ERTS_TCORR_ERR_LARGE_ADJ; + else + new_correction.error = ERTS_TCORR_ERR_SMALL_ADJ; + } + else { + set_new_correction = 1; + new_correction.error = 0; + } } - if ((curr - hr_last_correction_check) / 1000 > 1000000) { - /* Check the correction need */ - SysHrTime tv_diff, diffdiff; - SysTimeval tmp; - int done = 0; - - sys_gettimeofday(&tmp); - tv_diff = ((SysHrTime) tmp.tv_sec) * 1000000 + tmp.tv_usec; - tv_diff -= ((SysHrTime) inittv.tv_sec) * 1000000 + inittv.tv_usec; - diffdiff = diff_time - tv_diff; - if (diffdiff > 10000) { - SysHrTime corr = (curr - hr_last_time) / 100; - if (corr / 1000 >= diffdiff) { - ++done; - hr_correction -= ((SysHrTime)diffdiff) * 1000; - } else { - hr_correction -= corr; +#ifndef ERTS_HAVE_CORRECTED_OS_MONOTONIC + { + ErtsMonotonicDriftData *ddp = &time_sup.inf.c.parmon.cdata.drift; + int ix = ddp->ix; + ErtsMonotonicTime mtime_diff, old_os_mtime; + + old_os_mtime = ddp->intervals[ix].time.mon; + mtime_diff = os_mtime - old_os_mtime; + + if (mtime_diff >= ERTS_SEC_TO_MONOTONIC(10)) { + ErtsMonotonicTime drift_adj, drift_adj_diff, old_os_stime, + stime_diff, mtime_acc, stime_acc, avg_drift_adj; + + old_os_stime = ddp->intervals[ix].time.sys; + + mtime_acc = ddp->acc.mon; + stime_acc = ddp->acc.sys; + + avg_drift_adj = ((stime_acc - mtime_acc)*ERTS_MONOTONIC_TIME_UNIT) / mtime_acc; + + mtime_diff = os_mtime - old_os_mtime; + stime_diff = os_stime - old_os_stime; + drift_adj = ((stime_diff - mtime_diff)*ERTS_MONOTONIC_TIME_UNIT) / mtime_diff; + + ix++; + if (ix >= ERTS_DRIFT_INTERVALS) + ix = 0; + mtime_acc -= ddp->intervals[ix].diff.mon; + mtime_acc += mtime_diff; + stime_acc -= ddp->intervals[ix].diff.sys; + stime_acc += stime_diff; + + ddp->intervals[ix].diff.mon = mtime_diff; + ddp->intervals[ix].diff.sys = stime_diff; + ddp->intervals[ix].time.mon = os_mtime; + ddp->intervals[ix].time.sys = os_stime; + + ddp->ix = ix; + ddp->acc.mon = mtime_acc; + ddp->acc.sys = stime_acc; + + /* + * If calculated drift adjustment is if off by more than 20% from the + * average drift we interpret this as a discontinous leap in system + * time and ignore it. If it actually is a change in drift we will + * later detect this when the average drift change. + */ + drift_adj_diff = avg_drift_adj - drift_adj; + if (drift_adj_diff < -ERTS_TIME_DRIFT_MAX_ADJ_DIFF + || ERTS_TIME_DRIFT_MAX_ADJ_DIFF < drift_adj_diff) { + ddp->dirty_counter = ERTS_DRIFT_INTERVALS; + begin_short_intervals = 1; } - diff_time = (curr + hr_correction - hr_init_time) / 1000; - } else if (diffdiff < -10000) { - SysHrTime corr = (curr - hr_last_time) / 100; - if (corr / 1000 >= -diffdiff) { - ++done; - hr_correction -= ((SysHrTime)diffdiff) * 1000; - } else { - hr_correction += corr; + else { + if (ddp->dirty_counter <= 0) { + drift_adj = ((stime_acc - mtime_acc)*ERTS_MONOTONIC_TIME_UNIT) / mtime_acc; + } + if (ddp->dirty_counter >= 0) { + if (ddp->dirty_counter == 0) { + /* Force set new drift correction... */ + set_new_correction = 1; + } + ddp->dirty_counter--; + } + drift_adj_diff = drift_adj - new_correction.drift; + if (drift_adj_diff) { + if (drift_adj_diff > ERTS_TIME_DRIFT_MAX_ADJ_DIFF) + drift_adj_diff = ERTS_TIME_DRIFT_MAX_ADJ_DIFF; + else if (drift_adj_diff < -ERTS_TIME_DRIFT_MAX_ADJ_DIFF) + drift_adj_diff = -ERTS_TIME_DRIFT_MAX_ADJ_DIFF; + new_correction.drift += drift_adj_diff; + + if (drift_adj_diff < -ERTS_TIME_DRIFT_MIN_ADJ_DIFF + || ERTS_TIME_DRIFT_MIN_ADJ_DIFF < drift_adj_diff) { + set_new_correction = 1; + } + } } - diff_time = (curr + hr_correction - hr_init_time) / 1000; - } else { - ++done; } - if (done) { - hr_last_correction_check = curr; + } +#endif + + begin_short_intervals |= set_new_correction; + + if (begin_short_intervals) { + time_sup.inf.c.parmon.cdata.short_check_interval + = ERTS_INIT_SHORT_INTERVAL_COUNTER; + } + else if ((os_mtime - time_sup.inf.c.parmon.cdata.last_check + >= ERTS_SHORT_TIME_CORRECTION_CHECK - ERTS_MONOTONIC_TIME_UNIT) + && time_sup.inf.c.parmon.cdata.short_check_interval > 0) { + time_sup.inf.c.parmon.cdata.short_check_interval--; + } + time_sup.inf.c.parmon.cdata.last_check = os_mtime; + + if (new_correction.error == 0) + timeout = ERTS_MONOTONIC_TO_MSEC(ERTS_LONG_TIME_CORRECTION_CHECK); + else { + ErtsMonotonicTime ecorr = new_correction.error; + if (sdiff < 0) + sdiff = -1*sdiff; + if (ecorr < 0) + ecorr = -1*ecorr; + if (sdiff > ecorr*(ERTS_LONG_TIME_CORRECTION_CHECK/ERTS_TCORR_ERR_UNIT)) + timeout = ERTS_MONOTONIC_TO_MSEC(ERTS_LONG_TIME_CORRECTION_CHECK); + else { + timeout = ERTS_MONOTONIC_TO_MSEC((ERTS_TCORR_ERR_UNIT*sdiff)/ecorr); + if (timeout < 10) + timeout = 10; } } - tv->tv_sec += (int) (diff_time / ((SysHrTime) 1000000)); - tv->tv_usec += (int) (diff_time % ((SysHrTime) 1000000)); - if (tv->tv_usec >= 1000000) { - tv->tv_usec -= 1000000; - tv->tv_sec += 1; + + if (timeout > ERTS_MONOTONIC_TO_MSEC(ERTS_SHORT_TIME_CORRECTION_CHECK) + && time_sup.inf.c.parmon.cdata.short_check_interval) { + timeout = ERTS_MONOTONIC_TO_MSEC(ERTS_SHORT_TIME_CORRECTION_CHECK); } - hr_last_time = curr; -} + + if (set_new_correction) { + erts_smp_rwmtx_rwlock(&time_sup.inf.c.parmon.rwmtx); -#define correction (hr_correction/1000000) + os_mtime = erts_os_monotonic_time(); -#else /* !HAVE_GETHRTIME */ -#if !defined(CORRECT_USING_TIMES) -#define init_tolerant_timeofday() -#define get_tolerant_timeofday(tvp) sys_gettimeofday(tvp) -#else + /* Save previous correction instance */ + time_sup.inf.c.parmon.cdata.prev = *cip; -typedef Sint64 Milli; - -static clock_t init_ct; -static Sint64 ct_wrap; -static Milli init_tv_m; -static Milli correction_supress; -static Milli last_ct_diff; -static Milli last_cc; -static clock_t last_ct; - -/* sys_times() might need to be wrapped and the values shifted (right) - a bit to cope with newer linux (2.5.*) kernels, this has to be taken care - of dynamically to start with, a special version that uses - the times() return value as a high resolution timer can be made - to fully utilize the faster ticks, like on windows, but for now, we'll - settle with this silly workaround */ -#ifdef ERTS_WRAP_SYS_TIMES -#define KERNEL_TICKS() (sys_times_wrap() & \ - ((1UL << ((sizeof(clock_t) * 8) - 1)) - 1)) -#else -SysTimes dummy_tms; + /* + * Current correction instance begin when + * OS monotonic time has increased one unit. + */ + os_mtime++; -#define KERNEL_TICKS() (sys_times(&dummy_tms) & \ - ((1UL << ((sizeof(clock_t) * 8) - 1)) - 1)) + /* + * Erlang monotonic time corresponding to + * next OS monotonic time using previous + * correction. + */ + erl_mtime = calc_corrected_erl_mtime(os_mtime, cip, NULL); -#endif + /* + * Save new current correction instance. + */ + time_sup.inf.c.parmon.cdata.curr.erl_mtime = erl_mtime; + time_sup.inf.c.parmon.cdata.curr.os_mtime = os_mtime; + time_sup.inf.c.parmon.cdata.curr.correction = new_correction; -static void init_tolerant_timeofday(void) -{ - last_ct = init_ct = KERNEL_TICKS(); - last_cc = 0; - init_tv_m = (((Milli) inittv.tv_sec) * 1000) + - (inittv.tv_usec / 1000); - ct_wrap = 0; - correction_supress = 0; + erts_smp_rwmtx_rwunlock(&time_sup.inf.c.parmon.rwmtx); + } + + erts_set_timer(&time_sup.inf.c.parmon.timer, + check_time_correction, + NULL, + NULL, + timeout); } +#ifndef ERTS_HAVE_CORRECTED_OS_MONOTONIC -static void get_tolerant_timeofday(SysTimeval *tvp) +static void +init_check_time_correction(void *unused) { - clock_t current_ct; - SysTimeval current_tv; - Milli ct_diff; - Milli tv_diff; - Milli current_correction; - Milli act_correction; /* long shown to be too small */ - Milli max_adjust; - - if (erts_disable_tolerant_timeofday) { - sys_gettimeofday(tvp); - return; + ErtsMonotonicDriftData *ddp; + ErtsMonotonicTime old_mtime, old_stime, mtime, stime, mtime_diff, stime_diff; + int ix; + SysTimeval tod; + + ddp = &time_sup.inf.c.parmon.cdata.drift; + ix = ddp->ix; + old_mtime = ddp->intervals[0].time.mon; + old_stime = ddp->intervals[0].time.sys; + + mtime = erts_os_monotonic_time(); + sys_gettimeofday(&tod); + + stime = ERTS_SEC_TO_MONOTONIC(tod.tv_sec); + stime += ERTS_USEC_TO_MONOTONIC(tod.tv_usec); + + mtime_diff = mtime - old_mtime; + stime_diff = stime - old_stime; + if (100*stime_diff < 80*mtime_diff || 120*mtime_diff < 100*stime_diff ) { + /* Had a system time leap... pretend no drift... */ + stime_diff = mtime_diff; + } + + /* + * We use old time values in order to trigger + * a drift adjustment, and repeat this interval + * in all slots... + */ + for (ix = 0; ix < ERTS_DRIFT_INTERVALS; ix++) { + ddp->intervals[ix].diff.mon = mtime_diff; + ddp->intervals[ix].diff.sys = stime_diff; + ddp->intervals[ix].time.mon = old_mtime; + ddp->intervals[ix].time.sys = old_stime; } -#ifdef ERTS_WRAP_SYS_TIMES -#define TICK_MS (1000 / SYS_CLK_TCK_WRAP) + ddp->acc.sys = stime_diff*ERTS_DRIFT_INTERVALS; + ddp->acc.mon = mtime_diff*ERTS_DRIFT_INTERVALS; + ddp->ix = 0; + ddp->dirty_counter = ERTS_DRIFT_INTERVALS; + + check_time_correction(NULL); +} + +#endif + +static ErtsMonotonicTime +finalize_corrected_time_offset(SysTimeval *todp) +{ + ErtsMonotonicTime os_mtime; + ErtsMonotonicCorrectionData cdata; + ErtsMonotonicCorrectionInstance *cip; + + erts_smp_rwmtx_rlock(&time_sup.inf.c.parmon.rwmtx); + + os_mtime = erts_os_monotonic_time(); + sys_gettimeofday(todp); + + cdata = time_sup.inf.c.parmon.cdata; + + erts_smp_rwmtx_runlock(&time_sup.inf.c.parmon.rwmtx); + + if (os_mtime < cdata.curr.os_mtime) + erl_exit(ERTS_ABORT_EXIT, + "OS monotonic time stepped backwards\n"); + cip = &cdata.curr; + + return calc_corrected_erl_mtime(os_mtime, cip, NULL); +} + +static void +late_init_time_correction(void) +{ + if (time_sup.inf.c.finalized_offset) { + erts_init_timer(&time_sup.inf.c.parmon.timer); + erts_set_timer(&time_sup.inf.c.parmon.timer, +#ifndef ERTS_HAVE_CORRECTED_OS_MONOTONIC + init_check_time_correction, #else -#define TICK_MS (1000 / SYS_CLK_TCK) + check_time_correction, #endif - current_ct = KERNEL_TICKS(); - sys_gettimeofday(¤t_tv); - - /* I dont know if uptime can move some units backwards - on some systems, but I allow for small backward - jumps to avoid such problems if they exist...*/ - if (last_ct > 100 && current_ct < (last_ct - 100)) { - ct_wrap += ((Sint64) 1) << ((sizeof(clock_t) * 8) - 1); + NULL, + NULL, + ERTS_MONOTONIC_TO_MSEC(ERTS_SHORT_TIME_CORRECTION_CHECK)); } - last_ct = current_ct; - ct_diff = ((ct_wrap + current_ct) - init_ct) * TICK_MS; +} - /* - * We will adjust the time in milliseconds and we allow for 1% - * adjustments, but if this function is called more often then every 100 - * millisecond (which is obviously possible), we will never adjust, so - * we accumulate small times by setting last_ct_diff iff max_adjust > 0 - */ - if ((max_adjust = (ct_diff - last_ct_diff)/100) > 0) - last_ct_diff = ct_diff; +#endif /* ERTS_HAVE_OS_MONOTONIC_TIME_SUPPORT */ - tv_diff = ((((Milli) current_tv.tv_sec) * 1000) + - (current_tv.tv_usec / 1000)) - init_tv_m; +static ErtsMonotonicTime get_not_corrected_time(void) +{ + SysTimeval tmp_tv; + ErtsMonotonicTime stime, mtime; - current_correction = ((ct_diff - tv_diff) / TICK_MS) * TICK_MS; /* trunc */ + erts_smp_mtx_lock(&erts_get_time_mtx); - /* - * We allow the current_correction value to wobble a little, as it - * suffers from the low resolution of the kernel ticks. - * if it hasn't changed more than one tick in either direction, - * we will keep the old value. - */ - if ((last_cc > current_correction + TICK_MS) || - (last_cc < current_correction - TICK_MS)) { - last_cc = current_correction; - } else { - current_correction = last_cc; - } - - /* - * As time goes, we try to get the actual correction to 0, - * that is, make erlangs time correspond to the systems dito. - * The act correction is what we seem to need (current_correction) - * minus the correction suppression. The correction supression - * will change slowly (max 1% of elapsed time) but in millisecond steps. - */ - act_correction = current_correction - correction_supress; - if (max_adjust > 0) { - /* - * Here we slowly adjust erlangs time to correspond with the - * system time by changing the correction_supress variable. - * It can change max_adjust milliseconds which is 1% of elapsed time - */ - if (act_correction > 0) { - if (current_correction - correction_supress > max_adjust) { - correction_supress += max_adjust; - } else { - correction_supress = current_correction; - } - act_correction = current_correction - correction_supress; - } else if (act_correction < 0) { - if (correction_supress - current_correction > max_adjust) { - correction_supress -= max_adjust; - } else { - correction_supress = current_correction; + sys_gettimeofday(&tmp_tv); + + stime = ERTS_SEC_TO_MONOTONIC(tmp_tv.tv_sec); + stime += ERTS_USEC_TO_MONOTONIC(tmp_tv.tv_usec); + + mtime = stime - time_sup.inf.c.not_corrected_moffset; + + if (mtime >= time_sup.f.c.last_not_corrected_time) + time_sup.f.c.last_not_corrected_time = mtime; + else { + mtime = time_sup.f.c.last_not_corrected_time; + + if (time_sup.r.o.warp_mode == ERTS_MULTI_TIME_WARP_MODE) { + ErtsMonotonicTime new_offset = stime - mtime; + new_offset = ERTS_MONOTONIC_TO_USEC(new_offset); + new_offset = ERTS_USEC_TO_MONOTONIC(new_offset); + if (time_sup.inf.c.not_corrected_moffset != new_offset) { + time_sup.inf.c.not_corrected_moffset = new_offset; + set_time_offset(new_offset); + schedule_send_time_offset_changed_notifications(new_offset); } - act_correction = current_correction - correction_supress; } + } - /* - * The actual correction will correct the timeval so that system - * time warps gets smothed down. - */ - current_tv.tv_sec += act_correction / 1000; - current_tv.tv_usec += (act_correction % 1000) * 1000; - - if (current_tv.tv_usec >= 1000000) { - ++current_tv.tv_sec ; - current_tv.tv_usec -= 1000000; - } else if (current_tv.tv_usec < 0) { - --current_tv.tv_sec; - current_tv.tv_usec += 1000000; - } - *tvp = current_tv; -#undef TICK_MS + + ASSERT(stime == mtime + time_sup.inf.c.not_corrected_moffset); + + erts_smp_mtx_unlock(&erts_get_time_mtx); + + return mtime; } -#endif /* CORRECT_USING_TIMES */ -#endif /* !HAVE_GETHRTIME */ +int erts_check_time_adj_support(int time_correction, + ErtsTimeWarpMode time_warp_mode) +{ + if (!time_correction) + return 1; -/* -** Why this? Well, most platforms have a constant clock resolution of 1, -** we dont want the deliver_time/time_remaining routines to waste -** time dividing and multiplying by/with a variable that's always one. -** so the return value of sys_init_time is ignored on those platforms. -*/ - -#ifndef SYS_CLOCK_RESOLUTION -static int clock_resolution; -#define CLOCK_RESOLUTION clock_resolution + /* User wants time correction */ + +#ifdef ERTS_HAVE_OS_MONOTONIC_TIME_SUPPORT + return !time_sup.r.o.os_monotonic_disable; #else -#define CLOCK_RESOLUTION SYS_CLOCK_RESOLUTION + return 0; #endif +} -/* -** The clock resolution should really be the resolution of the -** time function in use, which on most platforms -** is 1. On VxWorks the resolution should be -** the number of ticks per second (or 1, which would work nicely to). -** -** Setting lower resolutions is mostly interesting when timers are used -** instead of something like select. -*/ - -static SysTimeval last_delivered; - -static void init_erts_deliver_time(const SysTimeval *inittv) +int +erts_has_time_correction(void) { - /* We set the initial values for deliver_time here */ - last_delivered = *inittv; - last_delivered.tv_usec = 1000 * (last_delivered.tv_usec / 1000); - /* ms resolution */ + return time_sup.r.o.correction; } -static void do_erts_deliver_time(const SysTimeval *current) +void +erts_early_init_time_sup(void) { - SysTimeval cur_time; - erts_time_t elapsed; - - /* calculate and deliver appropriate number of ticks */ - cur_time = *current; - cur_time.tv_usec = 1000 * (cur_time.tv_usec / 1000); /* ms resolution */ - elapsed = (1000 * (cur_time.tv_sec - last_delivered.tv_sec) + - (cur_time.tv_usec - last_delivered.tv_usec) / 1000) / - CLOCK_RESOLUTION; + ErtsSysInitTimeResult sys_init_time_res + = ERTS_SYS_INIT_TIME_RESULT_INITER; - /* Sometimes the time jump backwards, - resulting in a negative elapsed time. We compensate for - this by simply pretend as if the time stood still. :) */ + sys_init_time(&sys_init_time_res); - if (elapsed > 0) { + erts_time_sup__.r.o.monotonic_time_unit + = sys_init_time_res.os_monotonic_time_unit; - ASSERT(elapsed < ((erts_time_t) ERTS_SHORT_TIME_T_MAX)); +#ifndef SYS_CLOCK_RESOLUTION + erts_time_sup__.r.o.clktck_resolution + = sys_init_time_res.sys_clock_resolution; + erts_time_sup__.r.o.clktck_resolution *= 1000; +#endif - erts_do_time_add((erts_short_time_t) elapsed); - last_delivered = cur_time; - } +#ifdef ERTS_HAVE_OS_MONOTONIC_TIME_SUPPORT + time_sup.r.o.os_monotonic_disable + = !sys_init_time_res.have_os_monotonic; + time_sup.r.o.os_monotonic_func + = sys_init_time_res.os_monotonic_info.func; + time_sup.r.o.os_monotonic_clock_id + = sys_init_time_res.os_monotonic_info.clock_id; + time_sup.r.o.os_monotonic_locked + = sys_init_time_res.os_monotonic_info.locked_use; + time_sup.r.o.os_monotonic_resolution + = sys_init_time_res.os_monotonic_info.resolution; +#endif } int -erts_init_time_sup(void) +erts_init_time_sup(int time_correction, ErtsTimeWarpMode time_warp_mode) { +#if !ERTS_COMPILE_TIME_MONOTONIC_TIME_UNIT + ErtsMonotonicTime abs_start; +#endif + + ASSERT(ERTS_MONOTONIC_TIME_MIN < ERTS_MONOTONIC_TIME_MAX); + erts_smp_mtx_init(&erts_timeofday_mtx, "timeofday"); + erts_smp_mtx_init(&erts_get_time_mtx, "get_time"); - init_approx_time(); + time_sup.r.o.correction = time_correction; + time_sup.r.o.warp_mode = time_warp_mode; + + if (time_warp_mode == ERTS_SINGLE_TIME_WARP_MODE) + time_sup.inf.c.finalized_offset = 0; + else + time_sup.inf.c.finalized_offset = ~0; + +#if !ERTS_COMPILE_TIME_MONOTONIC_TIME_UNIT + +#ifdef ARCH_32 + time_sup.r.o.start = ((((ErtsMonotonicTime) 1) << 32)-1); + time_sup.r.o.start /= ERTS_MONOTONIC_TIME_UNIT; + time_sup.r.o.start *= ERTS_MONOTONIC_TIME_UNIT; + time_sup.r.o.start += ERTS_MONOTONIC_TIME_UNIT; + abs_start = time_sup.r.o.start; +#else /* ARCH_64 */ + if (ERTS_MONOTONIC_TIME_UNIT <= 1000*1000) + abs_start = time_sup.r.o.start = 0; + else { + time_sup.r.o.start = ((ErtsMonotonicTime) MIN_SMALL); + time_sup.r.o.start /= ERTS_MONOTONIC_TIME_UNIT; + time_sup.r.o.start *= ERTS_MONOTONIC_TIME_UNIT; + abs_start = -1*time_sup.r.o.start; + } +#endif - last_emu_time.tv_sec = 0; - last_emu_time.tv_usec = 0; + time_sup.r.o.start_offset.native = time_sup.r.o.start; + time_sup.r.o.start_offset.nsec = (ErtsMonotonicTime) + erts_time_unit_conversion((Uint64) abs_start, + (Uint32) ERTS_MONOTONIC_TIME_UNIT, + (Uint32) 1000*1000*1000); + time_sup.r.o.start_offset.usec = (ErtsMonotonicTime) + erts_time_unit_conversion((Uint64) abs_start, + (Uint32) ERTS_MONOTONIC_TIME_UNIT, + (Uint32) 1000*1000); + time_sup.r.o.start_offset.msec = (ErtsMonotonicTime) + erts_time_unit_conversion((Uint64) abs_start, + (Uint32) ERTS_MONOTONIC_TIME_UNIT, + (Uint32) 1000); + time_sup.r.o.start_offset.sec = (ErtsMonotonicTime) + erts_time_unit_conversion((Uint64) abs_start, + (Uint32) ERTS_MONOTONIC_TIME_UNIT, + (Uint32) 1); + if (time_sup.r.o.start < 0) { + time_sup.r.o.start_offset.nsec *= -1; + time_sup.r.o.start_offset.usec *= -1; + time_sup.r.o.start_offset.msec *= -1; + time_sup.r.o.start_offset.sec *= -1; + } -#ifndef SYS_CLOCK_RESOLUTION - clock_resolution = sys_init_time(); -#else - (void) sys_init_time(); #endif - sys_gettimeofday(&inittv); + + if (ERTS_MONOTONIC_TIME_UNIT < ERTS_CLKTCK_RESOLUTION) + ERTS_INTERNAL_ERROR("Too small monotonic time time unit"); + +#ifndef ERTS_HAVE_OS_MONOTONIC_TIME_SUPPORT + time_sup.r.o.correction = 0; +#else + if (time_sup.r.o.os_monotonic_disable) + time_sup.r.o.correction = 0; + + if (time_sup.r.o.correction) { + ErtsMonotonicCorrectionData *cdatap; + erts_smp_rwmtx_opt_t rwmtx_opts = ERTS_SMP_RWMTX_OPT_DEFAULT_INITER; + ErtsMonotonicTime offset; + time_sup.inf.c.minit = erts_os_monotonic_time(); + sys_gettimeofday(&time_sup.inf.c.inittv); + time_sup.r.o.moffset = -1*time_sup.inf.c.minit; + offset = ERTS_SEC_TO_MONOTONIC(time_sup.inf.c.inittv.tv_sec); + offset += ERTS_USEC_TO_MONOTONIC(time_sup.inf.c.inittv.tv_usec); + init_time_offset(offset); + + rwmtx_opts.type = ERTS_SMP_RWMTX_TYPE_EXTREMELY_FREQUENT_READ; + rwmtx_opts.lived = ERTS_SMP_RWMTX_LONG_LIVED; + + erts_smp_rwmtx_init_opt(&time_sup.inf.c.parmon.rwmtx, + &rwmtx_opts, "get_corrected_time"); + + cdatap = &time_sup.inf.c.parmon.cdata; -#ifdef HAVE_GETHRTIME - sys_init_hrtime(); +#ifndef ERTS_HAVE_CORRECTED_OS_MONOTONIC + cdatap->drift.intervals[0].time.sys + = ERTS_SEC_TO_MONOTONIC(time_sup.inf.c.inittv.tv_sec); + cdatap->drift.intervals[0].time.sys + += ERTS_USEC_TO_MONOTONIC(time_sup.inf.c.inittv.tv_usec); + cdatap->drift.intervals[0].time.mon = time_sup.inf.c.minit; + cdatap->curr.correction.drift = 0; +#endif + cdatap->curr.correction.error = 0; + cdatap->curr.erl_mtime = 0; + cdatap->curr.os_mtime = time_sup.inf.c.minit; + cdatap->last_check = time_sup.inf.c.minit; + cdatap->short_check_interval = ERTS_INIT_SHORT_INTERVAL_COUNTER; + cdatap->prev = cdatap->curr; + + time_sup.r.o.get_time = get_corrected_time; + } + else #endif - init_tolerant_timeofday(); + { + ErtsMonotonicTime stime, offset; + time_sup.r.o.get_time = get_not_corrected_time; + stime = ERTS_SEC_TO_MONOTONIC(time_sup.inf.c.inittv.tv_sec); + stime += ERTS_USEC_TO_MONOTONIC(time_sup.inf.c.inittv.tv_usec); + offset = stime; + time_sup.inf.c.not_corrected_moffset = offset; + init_time_offset(offset); + time_sup.f.c.last_not_corrected_time = 0; + } + + prev_wall_clock_elapsed = 0; - init_erts_deliver_time(&inittv); - gtv = inittv; - then.tv_sec = then.tv_usec = 0; + previous_now = ERTS_MONOTONIC_TO_USEC(get_time_offset()); - erts_deliver_time(); +#ifdef DEBUG + time_sup_initialized = 1; +#endif - return CLOCK_RESOLUTION; + return ERTS_CLKTCK_RESOLUTION/1000; } + +void +erts_late_init_time_sup(void) +{ +#ifdef ERTS_HAVE_OS_MONOTONIC_TIME_SUPPORT + /* Timer wheel must be initialized */ + if (time_sup.r.o.get_time == get_corrected_time) + late_init_time_correction(); +#endif +} + +ErtsTimeWarpMode erts_time_warp_mode(void) +{ + return time_sup.r.o.warp_mode; +} + +ErtsTimeOffsetState erts_time_offset_state(void) +{ + switch (time_sup.r.o.warp_mode) { + case ERTS_NO_TIME_WARP_MODE: + return ERTS_TIME_OFFSET_FINAL; + case ERTS_SINGLE_TIME_WARP_MODE: + if (time_sup.inf.c.finalized_offset) + return ERTS_TIME_OFFSET_FINAL; + return ERTS_TIME_OFFSET_PRELIMINARY; + case ERTS_MULTI_TIME_WARP_MODE: + return ERTS_TIME_OFFSET_VOLATILE; + default: + ERTS_INTERNAL_ERROR("Invalid time warp mode"); + return ERTS_TIME_OFFSET_VOLATILE; + } +} + +/* + * erts_finalize_time_offset() will only change time offset + * the first time it is called when the emulator has been + * started in "single time warp" mode. Returns previous + * state: + * * ERTS_TIME_OFFSET_PRELIMINARY - Finalization performed + * * ERTS_TIME_OFFSET_FINAL - Already finialized; nothing changed + * * ERTS_TIME_OFFSET_VOLATILE - Not supported, either in + * * no correction mode (or multi time warp mode; not yet implemented). + */ + +ErtsTimeOffsetState +erts_finalize_time_offset(void) +{ + switch (time_sup.r.o.warp_mode) { + case ERTS_NO_TIME_WARP_MODE: + return ERTS_TIME_OFFSET_FINAL; + case ERTS_MULTI_TIME_WARP_MODE: + return ERTS_TIME_OFFSET_VOLATILE; + case ERTS_SINGLE_TIME_WARP_MODE: { + ErtsTimeOffsetState res = ERTS_TIME_OFFSET_FINAL; + + erts_smp_mtx_lock(&erts_get_time_mtx); + + if (!time_sup.inf.c.finalized_offset) { + ErtsMonotonicTime mtime, new_offset; + SysTimeval tv; + +#ifdef ERTS_HAVE_OS_MONOTONIC_TIME_SUPPORT + if (!time_sup.r.o.correction) +#endif + { + ErtsMonotonicTime stime; + sys_gettimeofday(&tv); + + stime = ERTS_SEC_TO_MONOTONIC(tv.tv_sec); + stime += ERTS_USEC_TO_MONOTONIC(tv.tv_usec); + + mtime = stime - time_sup.inf.c.not_corrected_moffset; + + if (mtime >= time_sup.f.c.last_not_corrected_time) { + time_sup.f.c.last_not_corrected_time = mtime; + new_offset = time_sup.inf.c.not_corrected_moffset; + } + else { + mtime = time_sup.f.c.last_not_corrected_time; + + ASSERT(time_sup.inf.c.not_corrected_moffset != stime - mtime); + new_offset = stime - mtime; + time_sup.inf.c.not_corrected_moffset = new_offset; + } + + } +#ifdef ERTS_HAVE_OS_MONOTONIC_TIME_SUPPORT + else { + mtime = finalize_corrected_time_offset(&tv); + new_offset = ERTS_SEC_TO_MONOTONIC(tv.tv_sec); + new_offset += ERTS_USEC_TO_MONOTONIC(tv.tv_usec); + new_offset -= mtime; + + } +#endif + new_offset = ERTS_MONOTONIC_TO_USEC(new_offset); + new_offset = ERTS_USEC_TO_MONOTONIC(new_offset); + + set_time_offset(new_offset); + schedule_send_time_offset_changed_notifications(new_offset); + + time_sup.inf.c.finalized_offset = ~0; + res = ERTS_TIME_OFFSET_PRELIMINARY; + } + + erts_smp_mtx_unlock(&erts_get_time_mtx); + +#ifdef ERTS_HAVE_OS_MONOTONIC_TIME_SUPPORT + if (res == ERTS_TIME_OFFSET_PRELIMINARY + && time_sup.r.o.get_time == get_corrected_time) { + late_init_time_correction(); + } +#endif + + return res; + } + default: + ERTS_INTERNAL_ERROR("Invalid time warp mode"); + return ERTS_TIME_OFFSET_VOLATILE; + } +} + /* info functions */ void @@ -498,23 +1091,16 @@ elapsed_time_both(UWord *ms_user, UWord *ms_sys, void wall_clock_elapsed_time_both(UWord *ms_total, UWord *ms_diff) { - UWord prev_total; - SysTimeval tv; + ErtsMonotonicTime now, elapsed; erts_smp_mtx_lock(&erts_timeofday_mtx); - get_tolerant_timeofday(&tv); - - *ms_total = 1000 * (tv.tv_sec - inittv.tv_sec) + - (tv.tv_usec - inittv.tv_usec) / 1000; + now = time_sup.r.o.get_time(); - prev_total = 1000 * (gtv.tv_sec - inittv.tv_sec) + - (gtv.tv_usec - inittv.tv_usec) / 1000; - *ms_diff = *ms_total - prev_total; - gtv = tv; - - /* must sync the machine's idea of time here */ - do_erts_deliver_time(&tv); + elapsed = ERTS_MONOTONIC_TO_MSEC(now); + *ms_total = (UWord) elapsed; + *ms_diff = (UWord) (elapsed - prev_wall_clock_elapsed); + prev_wall_clock_elapsed = elapsed; erts_smp_mtx_unlock(&erts_timeofday_mtx); } @@ -890,38 +1476,41 @@ univ_to_local(Sint *year, Sint *month, Sint *day, return 0; } - /* get a timestamp */ void get_now(Uint* megasec, Uint* sec, Uint* microsec) { - SysTimeval now; + ErtsMonotonicTime now_megasec, now_sec, now, mtime, time_offset; + mtime = time_sup.r.o.get_time(); + time_offset = get_time_offset(); + now = ERTS_MONOTONIC_TO_USEC(mtime + time_offset); + erts_smp_mtx_lock(&erts_timeofday_mtx); - - get_tolerant_timeofday(&now); - do_erts_deliver_time(&now); - - /* Make sure time is later than last */ - if (then.tv_sec > now.tv_sec || - (then.tv_sec == now.tv_sec && then.tv_usec >= now.tv_usec)) { - now = then; - now.tv_usec++; - } - /* Check for carry from above + general reasonability */ - if (now.tv_usec >= 1000000) { - now.tv_usec = 0; - now.tv_sec++; - } - then = now; + + /* Make sure now time is later than last time */ + if (now <= previous_now) + now = previous_now + 1; + + previous_now = now; erts_smp_mtx_unlock(&erts_timeofday_mtx); - - *megasec = (Uint) (now.tv_sec / 1000000); - *sec = (Uint) (now.tv_sec % 1000000); - *microsec = (Uint) (now.tv_usec); - update_approx_time(&now); + now_megasec = now / ERTS_MONOTONIC_TIME_TERA; + now_sec = now / ERTS_MONOTONIC_TIME_MEGA; + *megasec = (Uint) now_megasec; + *sec = (Uint) (now_sec - now_megasec*ERTS_MONOTONIC_TIME_MEGA); + *microsec = (Uint) (now - now_sec*ERTS_MONOTONIC_TIME_MEGA); + + ASSERT(((ErtsMonotonicTime) *megasec)*ERTS_MONOTONIC_TIME_TERA + + ((ErtsMonotonicTime) *sec)*ERTS_MONOTONIC_TIME_MEGA + + ((ErtsMonotonicTime) *microsec) == now); +} + +ErtsMonotonicTime +erts_get_monotonic_time(void) +{ + return time_sup.r.o.get_time(); } void @@ -934,102 +1523,466 @@ get_sys_now(Uint* megasec, Uint* sec, Uint* microsec) *megasec = (Uint) (now.tv_sec / 1000000); *sec = (Uint) (now.tv_sec % 1000000); *microsec = (Uint) (now.tv_usec); - - update_approx_time(&now); } +#ifdef HAVE_ERTS_NOW_CPU +void erts_get_now_cpu(Uint* megasec, Uint* sec, Uint* microsec) { + SysCpuTime t; + SysTimespec tp; -/* deliver elapsed *ticks* to the machine - takes a pointer - to a struct timeval representing current time (to save - a gettimeofday() where possible) or NULL */ + sys_get_proc_cputime(t, tp); + *microsec = (Uint)(tp.tv_nsec / 1000); + t = (tp.tv_sec / 1000000); + *megasec = (Uint)(t % 1000000); + *sec = (Uint)(tp.tv_sec % 1000000); +} +#endif -void erts_deliver_time(void) { - SysTimeval now; - - erts_smp_mtx_lock(&erts_timeofday_mtx); - - get_tolerant_timeofday(&now); - do_erts_deliver_time(&now); - - erts_smp_mtx_unlock(&erts_timeofday_mtx); +#include "big.h" - update_approx_time(&now); +void +erts_monitor_time_offset(Eterm id, Eterm ref) +{ + erts_smp_mtx_lock(&erts_get_time_mtx); + erts_add_monitor(&time_offset_monitors, MON_TIME_OFFSET, ref, id, NIL); + no_time_offset_monitors++; + erts_smp_mtx_unlock(&erts_get_time_mtx); } -/* get *real* time (not ticks) remaining until next timeout - if there - isn't one, give a "long" time, that is guaranteed - to not cause overflow when we report elapsed time later on */ +int +erts_demonitor_time_offset(Eterm ref) +{ + int res; + ErtsMonitor *mon; + ASSERT(is_internal_ref(ref)); + erts_smp_mtx_lock(&erts_get_time_mtx); + mon = erts_remove_monitor(&time_offset_monitors, ref); + if (!mon) + res = 0; + else { + ASSERT(no_time_offset_monitors > 0); + no_time_offset_monitors--; + res = 1; + } + erts_smp_mtx_unlock(&erts_get_time_mtx); + if (res) + erts_destroy_monitor(mon); + return res; +} -void erts_time_remaining(SysTimeval *rem_time) +typedef struct { + Eterm pid; + Eterm ref; + Eterm heap[REF_THING_SIZE]; +} ErtsTimeOffsetMonitorInfo; + +typedef struct { + Uint ix; + ErtsTimeOffsetMonitorInfo *to_mon_info; +} ErtsTimeOffsetMonitorContext; + +static void +save_time_offset_monitor(ErtsMonitor *mon, void *vcntxt) { - erts_time_t ticks; - SysTimeval cur_time; - erts_time_t elapsed; - - /* erts_next_time() returns no of ticks to next timeout or -1 if none */ - - ticks = (erts_time_t) erts_next_time(); - if (ticks == (erts_time_t) -1) { - /* timer queue empty */ - /* this will cause at most 100000000 ticks */ - rem_time->tv_sec = 100000; - rem_time->tv_usec = 0; - } else { - /* next timeout after ticks ticks */ - ticks *= CLOCK_RESOLUTION; - - erts_smp_mtx_lock(&erts_timeofday_mtx); - - get_tolerant_timeofday(&cur_time); - cur_time.tv_usec = 1000 * - (cur_time.tv_usec / 1000);/* ms resolution*/ - elapsed = 1000 * (cur_time.tv_sec - last_delivered.tv_sec) + - (cur_time.tv_usec - last_delivered.tv_usec) / 1000; - - erts_smp_mtx_unlock(&erts_timeofday_mtx); + ErtsTimeOffsetMonitorContext *cntxt; + Eterm *from_hp, *to_hp; + Uint mix; + int hix; + + cntxt = (ErtsTimeOffsetMonitorContext *) vcntxt; + mix = (cntxt->ix)++; + cntxt->to_mon_info[mix].pid = mon->pid; + to_hp = &cntxt->to_mon_info[mix].heap[0]; + + ASSERT(is_internal_ref(mon->ref)); + from_hp = internal_ref_val(mon->ref); + ASSERT(thing_arityval(*from_hp) + 1 == REF_THING_SIZE); + + for (hix = 0; hix < REF_THING_SIZE; hix++) + to_hp[hix] = from_hp[hix]; + + cntxt->to_mon_info[mix].ref + = make_internal_ref(&cntxt->to_mon_info[mix].heap[0]); + +} + +static void +send_time_offset_changed_notifications(void *new_offsetp) +{ + ErtsMonotonicTime new_offset; + ErtsTimeOffsetMonitorInfo *to_mon_info; + Uint no_monitors; + char *tmp = NULL; + +#ifdef ARCH_64 + new_offset = (ErtsMonotonicTime) new_offsetp; +#else + new_offset = *((ErtsMonotonicTime *) new_offsetp); + erts_free(ERTS_ALC_T_NEW_TIME_OFFSET, new_offsetp); +#endif + new_offset -= ERTS_MONOTONIC_OFFSET_NATIVE; + + erts_smp_mtx_lock(&erts_get_time_mtx); + + no_monitors = no_time_offset_monitors; + if (no_monitors) { + ErtsTimeOffsetMonitorContext cntxt; + Uint alloc_sz; - if (ticks <= elapsed) { /* Ooops, better hurry */ - rem_time->tv_sec = rem_time->tv_usec = 0; - return; + /* Monitor info array size */ + alloc_sz = no_monitors*sizeof(ErtsTimeOffsetMonitorInfo); + /* + template max size */ + alloc_sz += 6*sizeof(Eterm); /* 5-tuple */ + alloc_sz += ERTS_MAX_SINT64_HEAP_SIZE*sizeof(Eterm); /* max offset size */ + tmp = erts_alloc(ERTS_ALC_T_TMP, alloc_sz); + + to_mon_info = (ErtsTimeOffsetMonitorInfo *) tmp; + cntxt.ix = 0; + cntxt.to_mon_info = to_mon_info; + + erts_doforall_monitors(time_offset_monitors, + save_time_offset_monitor, + &cntxt); + + ASSERT(cntxt.ix == no_monitors); + } + + erts_smp_mtx_unlock(&erts_get_time_mtx); + + if (no_monitors) { + Eterm *hp, *patch_refp, new_offset_term, message_template; + Uint mix, hsz; + + /* Make message template */ + + hp = (Eterm *) (tmp + no_monitors*sizeof(ErtsTimeOffsetMonitorInfo)); + + hsz = 6; /* 5-tuple */ + hsz += REF_THING_SIZE; + hsz += ERTS_SINT64_HEAP_SIZE(new_offset); + + if (IS_SSMALL(new_offset)) + new_offset_term = make_small(new_offset); + else + new_offset_term = erts_sint64_to_big(new_offset, &hp); + message_template = TUPLE5(hp, + am_CHANGE, + THE_NON_VALUE, /* Patch point for ref */ + am_time_offset, + am_clock_service, + new_offset_term); + patch_refp = &hp[2]; + + ASSERT(*patch_refp == THE_NON_VALUE); + + for (mix = 0; mix < no_monitors; mix++) { + Process *rp = erts_proc_lookup(to_mon_info[mix].pid); + if (rp) { + Eterm ref = to_mon_info[mix].ref; + ErtsProcLocks rp_locks = ERTS_PROC_LOCK_LINK; + erts_smp_proc_lock(rp, ERTS_PROC_LOCK_LINK); + if (erts_lookup_monitor(ERTS_P_MONITORS(rp), ref)) { + ErlHeapFragment *bp; + ErlOffHeap *ohp; + Eterm message; + + hp = erts_alloc_message_heap(hsz, &bp, &ohp, rp, &rp_locks); + *patch_refp = ref; + ASSERT(hsz == size_object(message_template)); + message = copy_struct(message_template, hsz, &hp, ohp); + erts_queue_message(rp, &rp_locks, bp, message, NIL +#ifdef USE_VM_PROBES + , NIL +#endif + ); + } + erts_smp_proc_unlock(rp, rp_locks); + } } - rem_time->tv_sec = (ticks - elapsed) / 1000; - rem_time->tv_usec = 1000 * ((ticks - elapsed) % 1000); + + erts_free(ERTS_ALC_T_TMP, tmp); } } -void erts_get_timeval(SysTimeval *tv) +static void +schedule_send_time_offset_changed_notifications(ErtsMonotonicTime new_offset) { - erts_smp_mtx_lock(&erts_timeofday_mtx); - get_tolerant_timeofday(tv); - erts_smp_mtx_unlock(&erts_timeofday_mtx); - update_approx_time(tv); +#ifdef ARCH_64 + void *new_offsetp = (void *) new_offset; + ASSERT(sizeof(void *) == sizeof(ErtsMonotonicTime)); +#else + void *new_offsetp = erts_alloc(ERTS_ALC_T_NEW_TIME_OFFSET, + sizeof(ErtsMonotonicTime)); + *((ErtsMonotonicTime *) new_offsetp) = new_offset; +#endif + erts_schedule_misc_aux_work(1, + send_time_offset_changed_notifications, + new_offsetp); } -erts_time_t -erts_get_time(void) +static ERTS_INLINE Eterm +make_time_val(Process *c_p, ErtsMonotonicTime time_val) { - SysTimeval sys_tv; - - erts_smp_mtx_lock(&erts_timeofday_mtx); - - get_tolerant_timeofday(&sys_tv); - - erts_smp_mtx_unlock(&erts_timeofday_mtx); + Sint64 val = (Sint64) time_val; + Eterm *hp; + Uint sz; - update_approx_time(&sys_tv); + if (IS_SSMALL(val)) + return make_small(val); - return sys_tv.tv_sec; + sz = ERTS_SINT64_HEAP_SIZE(val); + hp = HAlloc(c_p, sz); + return erts_sint64_to_big(val, &hp); } -#ifdef HAVE_ERTS_NOW_CPU -void erts_get_now_cpu(Uint* megasec, Uint* sec, Uint* microsec) { - SysCpuTime t; - SysTimespec tp; +Eterm +erts_get_monotonic_start_time(struct process *c_p) +{ + return make_time_val(c_p, ERTS_MONOTONIC_OFFSET_NATIVE); +} - sys_get_proc_cputime(t, tp); - *microsec = (Uint)(tp.tv_nsec / 1000); - t = (tp.tv_sec / 1000000); - *megasec = (Uint)(t % 1000000); - *sec = (Uint)(tp.tv_sec % 1000000); +static Eterm +bld_monotonic_time_source(Uint **hpp, Uint *szp, Sint64 os_mtime) +{ +#ifndef ERTS_HAVE_OS_MONOTONIC_TIME_SUPPORT + return NIL; +#else + int i = 0; + Eterm k[5]; + Eterm v[5]; + + if (time_sup.r.o.os_monotonic_disable) + return NIL; + + k[i] = erts_bld_atom(hpp, szp, "function"); + v[i++] = erts_bld_atom(hpp, szp, time_sup.r.o.os_monotonic_func); + + if (time_sup.r.o.os_monotonic_clock_id) { + k[i] = erts_bld_atom(hpp, szp, "clock_id"); + v[i++] = erts_bld_atom(hpp, szp, time_sup.r.o.os_monotonic_clock_id); + } + + if (time_sup.r.o.os_monotonic_resolution) { + k[i] = erts_bld_atom(hpp, szp, "resolution"); + v[i++] = erts_bld_uint64(hpp, szp, time_sup.r.o.os_monotonic_resolution); + } + + k[i] = erts_bld_atom(hpp, szp, "parallel"); + v[i++] = time_sup.r.o.os_monotonic_locked ? am_no : am_yes; + + k[i] = erts_bld_atom(hpp, szp, "time"); + v[i++] = erts_bld_sint64(hpp, szp, os_mtime); + + return erts_bld_2tup_list(hpp, szp, (Sint) i, k, v); +#endif } + +Eterm +erts_monotonic_time_source(struct process *c_p) +{ + Uint hsz = 0; + Eterm *hp = NULL; + Sint64 os_mtime = 0; +#ifdef ERTS_HAVE_OS_MONOTONIC_TIME_SUPPORT + if (!time_sup.r.o.os_monotonic_disable) + os_mtime = (Sint64) erts_os_monotonic_time(); +#endif + + bld_monotonic_time_source(NULL, &hsz, os_mtime); + if (hsz) + hp = HAlloc(c_p, hsz); + return bld_monotonic_time_source(&hp, NULL, os_mtime); +} + + +#include "bif.h" + +static ERTS_INLINE Eterm +time_unit_conversion(Process *c_p, Eterm term, ErtsMonotonicTime val, ErtsMonotonicTime muloff) +{ + ErtsMonotonicTime result; + BIF_RETTYPE ret; + + if (val < 0) + goto trap_to_erlang_code; + + /* Convert to common user specified time units */ + switch (term) { + case am_seconds: + case make_small(1): + result = ERTS_MONOTONIC_TO_SEC(val) + muloff*ERTS_MONOTONIC_OFFSET_SEC; + ERTS_BIF_PREP_RET(ret, make_time_val(c_p, result)); + break; + case am_milli_seconds: + case make_small(1000): + result = ERTS_MONOTONIC_TO_MSEC(val) + muloff*ERTS_MONOTONIC_OFFSET_MSEC; + ERTS_BIF_PREP_RET(ret, make_time_val(c_p, result)); + break; + case am_micro_seconds: + case make_small(1000*1000): + result = ERTS_MONOTONIC_TO_USEC(val) + muloff*ERTS_MONOTONIC_OFFSET_USEC; + ERTS_BIF_PREP_RET(ret, make_time_val(c_p, result)); + break; +#ifdef ARCH_64 + case am_nano_seconds: + case make_small(1000*1000*1000): + result = ERTS_MONOTONIC_TO_NSEC(val) + muloff*ERTS_MONOTONIC_OFFSET_NSEC; + ERTS_BIF_PREP_RET(ret, make_time_val(c_p, result)); + break; #endif + default: { + Eterm value, native_res; +#ifndef ARCH_64 + Sint user_res; + if (term == am_nano_seconds) + goto to_nano_seconds; + if (term_to_Sint(term, &user_res)) { + if (user_res == 1000*1000*1000) { + to_nano_seconds: + result = (ERTS_MONOTONIC_TO_NSEC(val) + + muloff*ERTS_MONOTONIC_OFFSET_NSEC); + ERTS_BIF_PREP_RET(ret, make_time_val(c_p, result)); + break; + } + if (user_res <= 0) + goto badarg; + } +#else + if (is_small(term)) { + if (signed_val(term) <= 0) + goto badarg; + } +#endif + else if (is_big(term)) { + if (big_sign(term)) + goto badarg; + } + else { + badarg: + ERTS_BIF_PREP_ERROR(ret, c_p, BADARG); + break; + } + + trap_to_erlang_code: + /* Do it in erlang code instead; pass along values to use... */ + value = make_time_val(c_p, val + muloff*ERTS_MONOTONIC_OFFSET_NATIVE); + native_res = make_time_val(c_p, ERTS_MONOTONIC_TIME_UNIT); + + ERTS_BIF_PREP_TRAP3(ret, erts_convert_time_unit_trap, c_p, + value, native_res, term); + + break; + } + } + + return ret; +} + +/* Built in functions */ + +BIF_RETTYPE monotonic_time_0(BIF_ALIST_0) +{ + ErtsMonotonicTime mtime = time_sup.r.o.get_time(); + mtime += ERTS_MONOTONIC_OFFSET_NATIVE; + BIF_RET(make_time_val(BIF_P, mtime)); +} + +BIF_RETTYPE monotonic_time_1(BIF_ALIST_1) +{ + BIF_RET(time_unit_conversion(BIF_P, BIF_ARG_1, time_sup.r.o.get_time(), 1)); +} + +BIF_RETTYPE system_time_0(BIF_ALIST_0) +{ + ErtsMonotonicTime mtime, offset; + mtime = time_sup.r.o.get_time(); + offset = get_time_offset(); + BIF_RET(make_time_val(BIF_P, mtime + offset)); +} + +BIF_RETTYPE system_time_1(BIF_ALIST_0) +{ + ErtsMonotonicTime mtime, offset; + mtime = time_sup.r.o.get_time(); + offset = get_time_offset(); + BIF_RET(time_unit_conversion(BIF_P, BIF_ARG_1, mtime + offset, 0)); +} + +BIF_RETTYPE erts_internal_time_unit_0(BIF_ALIST_0) +{ + BIF_RET(make_time_val(BIF_P, ERTS_MONOTONIC_TIME_UNIT)); +} + +BIF_RETTYPE time_offset_0(BIF_ALIST_0) +{ + ErtsMonotonicTime time_offset = get_time_offset(); + time_offset -= ERTS_MONOTONIC_OFFSET_NATIVE; + BIF_RET(make_time_val(BIF_P, time_offset)); +} + +BIF_RETTYPE time_offset_1(BIF_ALIST_1) +{ + BIF_RET(time_unit_conversion(BIF_P, BIF_ARG_1, get_time_offset(), -1)); +} + + +BIF_RETTYPE timestamp_0(BIF_ALIST_0) +{ + Eterm *hp, res; + ErtsMonotonicTime stime, mtime, all_sec, offset; + Uint mega_sec, sec, micro_sec; + + mtime = time_sup.r.o.get_time(); + offset = get_time_offset(); + stime = ERTS_MONOTONIC_TO_USEC(mtime + offset); + all_sec = stime / ERTS_MONOTONIC_TIME_MEGA; + mega_sec = (Uint) (stime / ERTS_MONOTONIC_TIME_TERA); + sec = (Uint) (all_sec - (((ErtsMonotonicTime) mega_sec) + * ERTS_MONOTONIC_TIME_MEGA)); + micro_sec = (Uint) (stime - all_sec*ERTS_MONOTONIC_TIME_MEGA); + + ASSERT(((ErtsMonotonicTime) mega_sec)*ERTS_MONOTONIC_TIME_TERA + + ((ErtsMonotonicTime) sec)*ERTS_MONOTONIC_TIME_MEGA + + micro_sec == stime); + + /* + * Mega seconds is the only value that potentially + * ever could be a bignum. However, that wont happen + * during at least the next 4 million years... + * + * (System time will also have wrapped in the + * 64-bit integer before we get there...) + */ + + ASSERT(IS_USMALL(0, mega_sec)); + ASSERT(IS_USMALL(0, sec)); + ASSERT(IS_USMALL(0, micro_sec)); + + hp = HAlloc(BIF_P, 4); + res = TUPLE3(hp, + make_small(mega_sec), + make_small(sec), + make_small(micro_sec)); + BIF_RET(res); +} + +BIF_RETTYPE os_system_time_0(BIF_ALIST_0) +{ + ErtsMonotonicTime stime; + SysTimeval tod; + sys_gettimeofday(&tod); + stime = ERTS_SEC_TO_MONOTONIC(tod.tv_sec); + stime += ERTS_USEC_TO_MONOTONIC(tod.tv_usec); + BIF_RET(make_time_val(BIF_P, stime)); +} + +BIF_RETTYPE os_system_time_1(BIF_ALIST_0) +{ + ErtsMonotonicTime stime; + SysTimeval tod; + sys_gettimeofday(&tod); + stime = ERTS_SEC_TO_MONOTONIC(tod.tv_sec); + stime += ERTS_USEC_TO_MONOTONIC(tod.tv_usec); + BIF_RET(time_unit_conversion(BIF_P, BIF_ARG_1, stime, 0)); +} + diff --git a/erts/emulator/beam/global.h b/erts/emulator/beam/global.h index 42daa2c9ef..634fe533d0 100644 --- a/erts/emulator/beam/global.h +++ b/erts/emulator/beam/global.h @@ -348,8 +348,6 @@ extern Uint display_items; /* no of items to display in traces etc */ extern int erts_backtrace_depth; extern erts_smp_atomic32_t erts_max_gen_gcs; -extern int erts_disable_tolerant_timeofday; - extern int bif_reductions; /* reductions + fcalls (when doing call_bif) */ extern int stackdump_on_exit; @@ -789,9 +787,6 @@ erts_bld_port_info(Eterm **hpp, void erts_bif_info_init(void); /* bif.c */ -Eterm erts_make_ref(Process *); -Eterm erts_make_ref_in_buffer(Eterm buffer[REF_THING_SIZE]); -void erts_make_ref_in_array(Uint32 ref[ERTS_MAX_REF_NUMBERS]); ERTS_GLB_INLINE Eterm erts_proc_store_ref(Process *c_p, Uint32 ref[ERTS_MAX_REF_NUMBERS]); @@ -1310,7 +1305,9 @@ erts_alloc_message_heap_state(Uint size, state = erts_smp_atomic32_read_acqb(&receiver->state); if (statep) *statep = state; - if (state & (ERTS_PSFLG_EXITING|ERTS_PSFLG_PENDING_EXIT)) + if (state & (ERTS_PSFLG_OFF_HEAP_MSGS + | ERTS_PSFLG_EXITING + | ERTS_PSFLG_PENDING_EXIT)) goto allocate_in_mbuf; #endif @@ -1330,7 +1327,9 @@ erts_alloc_message_heap_state(Uint size, state = erts_smp_atomic32_read_nob(&receiver->state); if (statep) *statep = state; - if ((state & (ERTS_PSFLG_EXITING|ERTS_PSFLG_PENDING_EXIT)) + if ((state & (ERTS_PSFLG_OFF_HEAP_MSGS + | ERTS_PSFLG_EXITING + | ERTS_PSFLG_PENDING_EXIT)) || (receiver->flags & F_DISABLE_GC) || HEAP_LIMIT(receiver) - HEAP_TOP(receiver) <= size) { /* diff --git a/erts/emulator/beam/io.c b/erts/emulator/beam/io.c index fb0edbcb1a..8ffe718334 100644 --- a/erts/emulator/beam/io.c +++ b/erts/emulator/beam/io.c @@ -47,6 +47,7 @@ #include "external.h" #include "dtrace-wrapper.h" #include "erl_map.h" +#include "erl_bif_unique.h" extern ErlDrvEntry fd_driver_entry; #ifndef __OSE__ diff --git a/erts/emulator/beam/sys.h b/erts/emulator/beam/sys.h index d2a8b9e7f4..aeb28e72f3 100644 --- a/erts/emulator/beam/sys.h +++ b/erts/emulator/beam/sys.h @@ -21,6 +21,25 @@ #define __SYS_H__ +#if defined(DEBUG) || defined(ERTS_ENABLE_LOCK_CHECK) +# undef ERTS_CAN_INLINE +# define ERTS_CAN_INLINE 0 +# undef ERTS_INLINE +# define ERTS_INLINE +#endif + +#if ERTS_CAN_INLINE +#define ERTS_GLB_INLINE static ERTS_INLINE +#else +#define ERTS_GLB_INLINE +#endif + +#if ERTS_CAN_INLINE || defined(ERTS_DO_INCL_GLB_INLINE_FUNC_DEF) +# define ERTS_GLB_INLINE_INCL_FUNC_DEF 1 +#else +# define ERTS_GLB_INLINE_INCL_FUNC_DEF 0 +#endif + #if defined(VALGRIND) && !defined(NO_FPE_SIGNALS) # define NO_FPE_SIGNALS #endif @@ -132,24 +151,8 @@ typedef ERTS_SYS_FD_TYPE ErtsSysFdType; # endif #endif -#if defined(DEBUG) || defined(ERTS_ENABLE_LOCK_CHECK) -# undef ERTS_CAN_INLINE -# define ERTS_CAN_INLINE 0 -# undef ERTS_INLINE -# define ERTS_INLINE -#endif - -#if ERTS_CAN_INLINE -#define ERTS_GLB_INLINE static ERTS_INLINE -#else -#define ERTS_GLB_INLINE -#endif - -#if ERTS_CAN_INLINE || defined(ERTS_DO_INCL_GLB_INLINE_FUNC_DEF) -# define ERTS_GLB_INLINE_INCL_FUNC_DEF 1 -#else -# define ERTS_GLB_INLINE_INCL_FUNC_DEF 0 -#endif +#define ERTS_MK_VSN_INT(Major, Minor, Build) \ + ((((Major) & 0x3ff) << 20) | (((Minor) & 0x3ff) << 10) | ((Build) & 0x3ff)) #ifndef ERTS_EXIT_AFTER_DUMP # define ERTS_EXIT_AFTER_DUMP exit @@ -385,17 +388,45 @@ typedef Sint SWord; typedef UWord BeamInstr; #ifndef HAVE_INT64 -#if SIZEOF_LONG == 8 -#define HAVE_INT64 1 +# if SIZEOF_LONG == 8 +# define HAVE_INT64 1 typedef unsigned long Uint64; typedef long Sint64; -#elif SIZEOF_LONG_LONG == 8 -#define HAVE_INT64 1 +# ifdef ULONG_MAX +# define ERTS_UINT64_MAX ULONG_MAX +# endif +# ifdef LONG_MAX +# define ERTS_SINT64_MAX LONG_MAX +# endif +# ifdef LONG_MIN +# define ERTS_SINT64_MIN LONG_MIN +# endif +# elif SIZEOF_LONG_LONG == 8 +# define HAVE_INT64 1 typedef unsigned long long Uint64; typedef long long Sint64; -#else -#define HAVE_INT64 0 +# ifdef ULLONG_MAX +# define ERTS_UINT64_MAX ULLONG_MAX +# endif +# ifdef LLONG_MAX +# define ERTS_SINT64_MAX LLONG_MAX +# endif +# ifdef LLONG_MIN +# define ERTS_SINT64_MIN LLONG_MIN +# endif +# else +# error "No 64-bit integer type found" +# endif +#endif + +#ifndef ERTS_UINT64_MAX +# define ERTS_UINT64_MAX (~((Uint64) 0)) #endif +#ifndef ERTS_SINT64_MAX +# define ERTS_SINT64_MAX ((Sint64) ((((Uint64) 1) << 63)-1)) +#endif +#ifndef ERTS_SINT64_MIN +# define ERTS_SINT64_MIN (-1*(((Sint64) 1) << 63)) #endif #if SIZEOF_LONG == 4 @@ -672,10 +703,31 @@ extern char *erts_default_arg0; extern char os_type[]; -extern int sys_init_time(void); +typedef enum { + ERTS_NO_TIME_WARP_MODE, + ERTS_SINGLE_TIME_WARP_MODE, + ERTS_MULTI_TIME_WARP_MODE +} ErtsTimeWarpMode; + +typedef struct { + int have_os_monotonic; + ErtsMonotonicTime os_monotonic_time_unit; + ErtsMonotonicTime sys_clock_resolution; + struct { + Uint64 resolution; + char *func; + char *clock_id; + int locked_use; + } os_monotonic_info; +} ErtsSysInitTimeResult; + +#define ERTS_SYS_INIT_TIME_RESULT_INITER \ + {0, (ErtsMonotonicTime) -1, (ErtsMonotonicTime) 1} + +extern void sys_init_time(ErtsSysInitTimeResult *); extern void erts_deliver_time(void); extern void erts_time_remaining(SysTimeval *); -extern int erts_init_time_sup(void); +extern int erts_init_time_sup(int, ErtsTimeWarpMode); extern void erts_sys_init_float(void); extern void erts_thread_init_float(void); extern void erts_thread_disable_fpe(void); @@ -726,7 +778,7 @@ extern char *erts_sys_ddll_error(int code); void erts_sys_schedule_interrupt(int set); #ifdef ERTS_SMP -void erts_sys_schedule_interrupt_timed(int set, erts_short_time_t msec); +void erts_sys_schedule_interrupt_timed(int, ErtsMonotonicTime); void erts_sys_main_thread(void); #endif @@ -765,6 +817,7 @@ int univ_to_local( int local_to_univ(Sint *year, Sint *month, Sint *day, Sint *hour, Sint *minute, Sint *second, int isdst); void get_now(Uint*, Uint*, Uint*); +ErtsMonotonicTime erts_get_monotonic_time(void); void get_sys_now(Uint*, Uint*, Uint*); void set_break_quit(void (*)(void), void (*)(void)); diff --git a/erts/emulator/beam/time.c b/erts/emulator/beam/time.c index 2fd8e0cf00..9f997e1d0b 100644 --- a/erts/emulator/beam/time.c +++ b/erts/emulator/beam/time.c @@ -83,7 +83,8 @@ #define ASSERT_NO_LOCKED_LOCKS #endif -static erts_smp_mtx_t tiw_lock; +#define ERTS_MONOTONIC_DAY ERTS_SEC_TO_MONOTONIC(60*60*24) +#define ERTS_CLKTCKS_DAY ERTS_MONOTONIC_TO_CLKTCKS(ERTS_MONOTONIC_DAY) /* BEGIN tiw_lock protected variables @@ -91,18 +92,12 @@ static erts_smp_mtx_t tiw_lock; ** The individual timer cells in tiw are also protected by the same mutex. */ +/* timing wheel size NEED to be a power of 2 */ #ifdef SMALL_MEMORY -#define TIW_SIZE 8192 +#define TIW_SIZE (1 << 13) #else -#define TIW_SIZE 65536 /* timing wheel size (should be a power of 2) */ +#define TIW_SIZE (1 << 20) #endif -static ErlTimer** tiw; /* the timing wheel, allocated in init_time() */ -static Uint tiw_pos; /* current position in wheel */ -static Uint tiw_nto; /* number of timeouts in wheel */ -static Uint tiw_min; -static ErlTimer *tiw_min_ptr; - -/* END tiw_lock protected variables */ /* Actual interval time chosen by sys_init_time() */ @@ -114,83 +109,135 @@ static int tiw_itime; /* Constant after init */ # define TIW_ITIME tiw_itime #endif -erts_smp_atomic32_t do_time; /* set at clock interrupt */ -static ERTS_INLINE erts_short_time_t do_time_read(void) +struct ErtsTimerWheel_ { + ErlTimer *w[TIW_SIZE]; + ErtsMonotonicTime pos; + Uint nto; + struct { + ErlTimer *head; + ErlTimer **tail; + Uint nto; + } at_once; + int true_next_timeout_time; + ErtsMonotonicTime next_timeout_time; + erts_atomic64_t next_timeout; + erts_smp_atomic32_t is_bumping; + erts_smp_mtx_t lock; +}; + +ErtsTimerWheel *erts_default_timer_wheel; /* managed by aux thread */ + +static ERTS_INLINE ErtsTimerWheel * +get_timer_wheel(ErlTimer *p) +{ + return (ErtsTimerWheel *) erts_smp_atomic_read_acqb(&p->wheel); +} + +static ERTS_INLINE void +set_timer_wheel(ErlTimer *p, ErtsTimerWheel *tiw) { - return erts_smp_atomic32_read_acqb(&do_time); + erts_smp_atomic_set_relb(&p->wheel, (erts_aint_t) tiw); } -static ERTS_INLINE erts_short_time_t do_time_update(void) +static ERTS_INLINE void +init_next_timeout(ErtsTimerWheel *tiw, + ErtsMonotonicTime time) { - return do_time_read(); + erts_atomic64_init_nob(&tiw->next_timeout, + (erts_aint64_t) time); } -static ERTS_INLINE void do_time_init(void) +static ERTS_INLINE void +set_next_timeout(ErtsTimerWheel *tiw, + ErtsMonotonicTime time, + int true_timeout) { - erts_smp_atomic32_init_nob(&do_time, 0); + tiw->true_next_timeout_time = true_timeout; + tiw->next_timeout_time = time; + erts_atomic64_set_relb(&tiw->next_timeout, + (erts_aint64_t) time); } /* get the time (in units of TIW_ITIME) to the next timeout, or -1 if there are no timeouts */ -static erts_short_time_t next_time_internal(void) /* PRE: tiw_lock taken by caller */ +static ERTS_INLINE ErtsMonotonicTime +find_next_timeout(ErtsTimerWheel *tiw, + ErtsMonotonicTime curr_time, + ErtsMonotonicTime max_search_time) { - int i, tm, nto; - Uint32 min; - ErlTimer* p; - erts_short_time_t dt; - - if (tiw_nto == 0) - return -1; /* no timeouts in wheel */ + int start_ix, tiw_pos_ix; + ErlTimer *p; + int true_min_timeout; + ErtsMonotonicTime min_timeout, min_timeout_pos, slot_timeout_pos, timeout_limit; + + ERTS_SMP_LC_ASSERT(erts_smp_lc_mtx_is_locked(&tiw->lock)); + + if (tiw->true_next_timeout_time) + return tiw->next_timeout_time; - if (tiw_min_ptr) { - min = tiw_min; - dt = do_time_read(); - return ((min >= dt) ? (min - dt) : 0); + /* We never set next timeout beyond timeout_limit */ + timeout_limit = curr_time + ERTS_MONOTONIC_DAY; + + if (tiw->nto == 0) { /* no timeouts in wheel */ + true_min_timeout = tiw->true_next_timeout_time = 0; + min_timeout_pos = ERTS_MONOTONIC_TO_CLKTCKS(timeout_limit); + goto found_next; } - - /* start going through wheel to find next timeout */ - tm = nto = 0; - min = (Uint32) -1; /* max Uint32 */ - i = tiw_pos; + + /* + * Don't want others entering trying to bump + * timers while we are checking... + */ + set_next_timeout(tiw, timeout_limit, 0); + + true_min_timeout = 1; + slot_timeout_pos = tiw->pos; + min_timeout_pos = ERTS_MONOTONIC_TO_CLKTCKS(curr_time + max_search_time); + + start_ix = tiw_pos_ix = (int) (tiw->pos & (TIW_SIZE-1)); + do { - p = tiw[i]; - while (p != NULL) { - nto++; - if (p->count == 0) { - /* found next timeout */ - dt = do_time_read(); - /* p->count is zero */ - tiw_min_ptr = p; - tiw_min = tm; - return ((tm >= dt) ? (tm - dt) : 0); - } else { - /* keep shortest time in 'min' */ - if (tm + p->count*TIW_SIZE < min) { - min = tm + p->count*TIW_SIZE; - tiw_min_ptr = p; - tiw_min = min; - } + slot_timeout_pos++; + if (slot_timeout_pos >= min_timeout_pos) { + true_min_timeout = 0; + break; + } + + p = tiw->w[tiw_pos_ix]; + + while (p) { + ErtsMonotonicTime timeout_pos; + ASSERT(p != p->next); + timeout_pos = p->timeout_pos; + if (min_timeout_pos > timeout_pos) { + min_timeout_pos = timeout_pos; + if (min_timeout_pos <= slot_timeout_pos) + goto found_next; } p = p->next; } - /* when we have found all timeouts the shortest time will be in min */ - if (nto == tiw_nto) break; - tm++; - i = (i + 1) % TIW_SIZE; - } while (i != tiw_pos); - dt = do_time_read(); - if (min <= (Uint32) dt) - return 0; - if ((min - (Uint32) dt) > (Uint32) ERTS_SHORT_TIME_T_MAX) - return ERTS_SHORT_TIME_T_MAX; - return (erts_short_time_t) (min - (Uint32) dt); + + tiw_pos_ix++; + if (tiw_pos_ix == TIW_SIZE) + tiw_pos_ix = 0; + } while (start_ix != tiw_pos_ix); + +found_next: + + min_timeout = ERTS_CLKTCKS_TO_MONOTONIC(min_timeout_pos); + if (min_timeout != tiw->next_timeout_time) + set_next_timeout(tiw, min_timeout, true_min_timeout); + + return min_timeout; } -static void remove_timer(ErlTimer *p) { +static void +remove_timer(ErtsTimerWheel *tiw, ErlTimer *p) +{ /* first */ if (!p->prev) { - tiw[p->slot] = p->next; + tiw->w[p->slot] = p->next; if(p->next) p->next->prev = NULL; } else { @@ -207,79 +254,164 @@ static void remove_timer(ErlTimer *p) { p->next = NULL; p->prev = NULL; - /* Make sure cancel callback isn't called */ - p->active = 0; - tiw_nto--; + + set_timer_wheel(p, NULL); + tiw->nto--; +} + +ErtsMonotonicTime +erts_check_next_timeout_time(ErtsTimerWheel *tiw, + ErtsMonotonicTime max_search_time) +{ + ErtsMonotonicTime next, curr; + + curr = erts_get_monotonic_time(); + + erts_smp_mtx_lock(&tiw->lock); + + next = find_next_timeout(tiw, curr, max_search_time); + + erts_smp_mtx_unlock(&tiw->lock); + + return next; } -/* Private export to erl_time_sup.c */ -erts_short_time_t erts_next_time(void) +#ifndef DEBUG +#define ERTS_DBG_CHK_SAFE_TO_SKIP_TO(TIW, TO) ((void) 0) +#else +#define ERTS_DBG_CHK_SAFE_TO_SKIP_TO(TIW, TO) debug_check_safe_to_skip_to((TIW), (TO)) +static void +debug_check_safe_to_skip_to(ErtsTimerWheel *tiw, ErtsMonotonicTime skip_to_pos) { - erts_short_time_t ret; + int slots, ix; + ErlTimer *tmr; + ErtsMonotonicTime tmp; + + ix = (int) (tiw->pos & (TIW_SIZE-1)); + tmp = skip_to_pos - tiw->pos; + ASSERT(tmp >= 0); + if (tmp < (ErtsMonotonicTime) TIW_SIZE) + slots = (int) tmp; + else + slots = TIW_SIZE; - erts_smp_mtx_lock(&tiw_lock); - (void)do_time_update(); - ret = next_time_internal(); - erts_smp_mtx_unlock(&tiw_lock); - return ret; + while (slots > 0) { + tmr = tiw->w[ix]; + while (tmr) { + ASSERT(tmr->timeout_pos > skip_to_pos); + tmr = tmr->next; + } + ix++; + if (ix == TIW_SIZE) + ix = 0; + slots--; + } } +#endif -static ERTS_INLINE void bump_timer_internal(erts_short_time_t dt) /* PRE: tiw_lock is write-locked */ +void +erts_bump_timers(ErtsTimerWheel *tiw, ErtsMonotonicTime curr_time) { - Uint keep_pos; - Uint count; - ErlTimer *p, **prev, *timeout_head, **timeout_tail; - Uint dtime = (Uint) dt; - - /* no need to bump the position if there aren't any timeouts */ - if (tiw_nto == 0) { - erts_smp_mtx_unlock(&tiw_lock); - return; + int tiw_pos_ix, slots; + ErlTimer *p, *timeout_head, **timeout_tail; + ErtsMonotonicTime bump_to, tmp_slots; + + if (erts_smp_atomic32_cmpxchg_nob(&tiw->is_bumping, 1, 0) != 0) + return; /* Another thread is currently bumping... */ + + bump_to = ERTS_MONOTONIC_TO_CLKTCKS(curr_time); + + erts_smp_mtx_lock(&tiw->lock); + + if (tiw->pos >= bump_to) { + timeout_head = NULL; + goto done; } - /* if do_time > TIW_SIZE we want to go around just once */ - count = (Uint)(dtime / TIW_SIZE) + 1; - keep_pos = (tiw_pos + dtime) % TIW_SIZE; - if (dtime > TIW_SIZE) dtime = TIW_SIZE; - - timeout_head = NULL; - timeout_tail = &timeout_head; - while (dtime > 0) { - /* this is to decrease the counters with the right amount */ - /* when dtime >= TIW_SIZE */ - if (tiw_pos == keep_pos) count--; - prev = &tiw[tiw_pos]; - while ((p = *prev) != NULL) { - ASSERT( p != p->next); - if (p->count < count) { /* we have a timeout */ - /* remove min time */ - if (tiw_min_ptr == p) { - tiw_min_ptr = NULL; - tiw_min = 0; - } + /* Don't want others here while we are bumping... */ + set_next_timeout(tiw, curr_time + ERTS_MONOTONIC_DAY, 0); + if (!tiw->at_once.head) { + timeout_head = NULL; + timeout_tail = &timeout_head; + } + else { + ASSERT(tiw->nto >= tiw->at_once.nto); + timeout_head = tiw->at_once.head; + timeout_tail = tiw->at_once.tail; + tiw->nto -= tiw->at_once.nto; + tiw->at_once.head = NULL; + tiw->at_once.tail = &tiw->at_once.head; + tiw->at_once.nto = 0; + } + + if (tiw->nto == 0) { + ERTS_DBG_CHK_SAFE_TO_SKIP_TO(tiw, bump_to); + tiw->pos = bump_to; + goto done; + } + + if (tiw->true_next_timeout_time) { + ErtsMonotonicTime skip_until_pos; + /* + * No need inspecting slots where we know no timeouts + * to trigger should reside. + */ + + skip_until_pos = ERTS_MONOTONIC_TO_CLKTCKS(tiw->next_timeout_time); + if (skip_until_pos > bump_to) + skip_until_pos = bump_to; + + ERTS_DBG_CHK_SAFE_TO_SKIP_TO(tiw, skip_until_pos); + ASSERT(skip_until_pos > tiw->pos); + + tiw->pos = skip_until_pos - 1; + } + + tiw_pos_ix = (int) ((tiw->pos+1) & (TIW_SIZE-1)); + tmp_slots = (bump_to - tiw->pos); + if (tmp_slots < (ErtsMonotonicTime) TIW_SIZE) + slots = (int) tmp_slots; + else + slots = TIW_SIZE; + + while (slots > 0) { + p = tiw->w[tiw_pos_ix]; + while (p) { + ErlTimer *next = p->next; + ASSERT(p != next); + if (p->timeout_pos <= bump_to) { /* we have a timeout */ /* Remove from list */ - remove_timer(p); + remove_timer(tiw, p); *timeout_tail = p; /* Insert in timeout queue */ timeout_tail = &p->next; } - else { - /* no timeout, just decrease counter */ - p->count -= count; - prev = &p->next; - } + p = next; } - tiw_pos = (tiw_pos + 1) % TIW_SIZE; - dtime--; + tiw_pos_ix++; + if (tiw_pos_ix == TIW_SIZE) + tiw_pos_ix = 0; + slots--; } - tiw_pos = keep_pos; - if (tiw_min_ptr) - tiw_min -= dt; - - erts_smp_mtx_unlock(&tiw_lock); + + ASSERT(tmp_slots >= (ErtsMonotonicTime) TIW_SIZE + || tiw_pos_ix == (int) ((bump_to+1) & (TIW_SIZE-1))); + + tiw->pos = bump_to; + + /* Search at most two seconds ahead... */ + (void) find_next_timeout(tiw, curr_time, ERTS_SEC_TO_MONOTONIC(2)); + +done: + + erts_smp_mtx_unlock(&tiw->lock); + erts_smp_atomic32_set_nob(&tiw->is_bumping, 0); + /* Call timedout timers callbacks */ while (timeout_head) { + ErlTimeoutProc timeout; + void *arg; p = timeout_head; timeout_head = p->next; /* Here comes hairy use of the timer fields! @@ -288,35 +420,69 @@ static ERTS_INLINE void bump_timer_internal(erts_short_time_t dt) /* PRE: tiw_lo * accesses any field until the ->timeout * callback is called. */ + ASSERT(p->timeout_pos <= bump_to); p->next = NULL; p->prev = NULL; p->slot = 0; - (*p->timeout)(p->arg); + timeout = p->timeout; + arg = p->arg; + (*timeout)(arg); } } -void erts_bump_timer(erts_short_time_t dt) /* dt is value from do_time */ +Uint +erts_timer_wheel_memory_size(void) +{ +#ifdef ERTS_SMP + return sizeof(ErtsTimerWheel)*(1 + erts_no_schedulers); +#else + return sizeof(ErtsTimerWheel); +#endif +} + +ErtsTimerWheel * +erts_create_timer_wheel(int no) { - erts_smp_mtx_lock(&tiw_lock); - bump_timer_internal(dt); + ErtsMonotonicTime mtime; + int i; + ErtsTimerWheel *tiw; + tiw = (ErtsTimerWheel *) erts_alloc(ERTS_ALC_T_TIMER_WHEEL, + sizeof(ErtsTimerWheel)); + for(i = 0; i < TIW_SIZE; i++) + tiw->w[i] = NULL; + + erts_smp_atomic32_init_nob(&tiw->is_bumping, 0); + erts_smp_mtx_init_x(&tiw->lock, "timer_wheel", make_small(no)); + + mtime = erts_get_monotonic_time(); + tiw->pos = ERTS_MONOTONIC_TO_CLKTCKS(mtime); + tiw->nto = 0; + tiw->at_once.head = NULL; + tiw->at_once.tail = &tiw->at_once.head; + tiw->at_once.nto = 0; + tiw->true_next_timeout_time = 0; + tiw->next_timeout_time = mtime + ERTS_MONOTONIC_DAY; + init_next_timeout(tiw, mtime + ERTS_MONOTONIC_DAY); + return tiw; } -Uint -erts_timer_wheel_memory_size(void) +ErtsNextTimeoutRef +erts_get_next_timeout_reference(ErtsTimerWheel *tiw) { - return (Uint) TIW_SIZE * sizeof(ErlTimer*); + return (ErtsNextTimeoutRef) &tiw->next_timeout; } + /* this routine links the time cells into a free list at the start and sets the time queue as empty */ void -erts_init_time(void) +erts_init_time(int time_correction, ErtsTimeWarpMode time_warp_mode) { - int i, itime; + int itime; /* system dependent init; must be done before do_time_init() if timer thread is enabled */ - itime = erts_init_time_sup(); + itime = erts_init_time_sup(time_correction, time_warp_mode); #ifdef TIW_ITIME_IS_CONSTANT if (itime != TIW_ITIME) { erl_exit(ERTS_ABORT_EXIT, "timer resolution mismatch %d != %d", itime, TIW_ITIME); @@ -325,117 +491,110 @@ erts_init_time(void) tiw_itime = itime; #endif - erts_smp_mtx_init(&tiw_lock, "timer_wheel"); - - tiw = (ErlTimer**) erts_alloc(ERTS_ALC_T_TIMER_WHEEL, - TIW_SIZE * sizeof(ErlTimer*)); - for(i = 0; i < TIW_SIZE; i++) - tiw[i] = NULL; - do_time_init(); - tiw_pos = tiw_nto = 0; - tiw_min_ptr = NULL; - tiw_min = 0; + erts_default_timer_wheel = erts_create_timer_wheel(0); } +void +erts_set_timer(ErlTimer *p, ErlTimeoutProc timeout, + ErlCancelProc cancel, void *arg, Uint to) +{ + ErtsMonotonicTime timeout_time, timeout_pos; + ErtsMonotonicTime curr_time; + ErtsTimerWheel *tiw; + ErtsSchedulerData *esdp; + + curr_time = erts_get_monotonic_time(); + esdp = erts_get_scheduler_data(); + if (esdp) + tiw = esdp->timer_wheel; + else + tiw = erts_default_timer_wheel; + erts_smp_mtx_lock(&tiw->lock); + if (get_timer_wheel(p)) + ERTS_INTERNAL_ERROR("Double set timer"); -/* -** Insert a process into the time queue, with a timeout 't' -*/ -static void -insert_timer(ErlTimer* p, Uint t) -{ - Uint tm; - Uint64 ticks; + p->timeout = timeout; + p->cancel = cancel; + p->arg = arg; - /* The current slot (tiw_pos) in timing wheel is the next slot to be - * be processed. Hence no extra time tick is needed. - * - * (x + y - 1)/y is precisely the "number of bins" formula. - */ - ticks = (t + (TIW_ITIME - 1)) / TIW_ITIME; + if (to == 0) { + timeout_pos = ERTS_MONOTONIC_TO_CLKTCKS(curr_time); + tiw->nto++; + tiw->at_once.nto++; + *tiw->at_once.tail = p; + p->next = NULL; + p->timeout_pos = timeout_pos; + timeout_time = ERTS_CLKTCKS_TO_MONOTONIC(timeout_pos); + } + else { + int tm; + ErtsMonotonicTime ticks; - /* - * Ticks must be a Uint64, or the addition may overflow here, - * resulting in an incorrect value for p->count below. - */ - ticks += do_time_update(); /* Add backlog of unprocessed time */ - - /* calculate slot */ - tm = (ticks + tiw_pos) % TIW_SIZE; - p->slot = (Uint) tm; - p->count = (Uint) (ticks / TIW_SIZE); + ticks = ERTS_MSEC_TO_CLKTCKS(to); + timeout_pos = ERTS_MONOTONIC_TO_CLKTCKS(curr_time - 1) + 1 + ticks; + + /* calculate slot */ + tm = (int) (timeout_pos & (TIW_SIZE-1)); + p->slot = (Uint) tm; - /* insert at head of list at slot */ - p->next = tiw[tm]; - p->prev = NULL; - if (p->next != NULL) - p->next->prev = p; - tiw[tm] = p; + /* insert at head of list at slot */ + p->next = tiw->w[tm]; + p->prev = NULL; + if (p->next != NULL) + p->next->prev = p; + tiw->w[tm] = p; + tiw->nto++; - /* insert min time */ - if ((tiw_nto == 0) || ((tiw_min_ptr != NULL) && (ticks < tiw_min))) { - tiw_min = ticks; - tiw_min_ptr = p; - } - if ((tiw_min_ptr == p) && (ticks > tiw_min)) { - /* some other timer might be 'min' now */ - tiw_min = 0; - tiw_min_ptr = NULL; + timeout_time = ERTS_CLKTCKS_TO_MONOTONIC(timeout_pos); + p->timeout_pos = timeout_pos; + + ASSERT(ERTS_MSEC_TO_MONOTONIC(to) <= timeout_time - curr_time); + ASSERT(timeout_time - curr_time + < ERTS_MSEC_TO_MONOTONIC(to) + ERTS_CLKTCKS_TO_MONOTONIC(1)); } - tiw_nto++; -} + if (timeout_time < tiw->next_timeout_time) + set_next_timeout(tiw, timeout_time, 1); -void -erts_set_timer(ErlTimer* p, ErlTimeoutProc timeout, ErlCancelProc cancel, - void* arg, Uint t) -{ + set_timer_wheel(p, tiw); + + erts_smp_mtx_unlock(&tiw->lock); - erts_deliver_time(); - erts_smp_mtx_lock(&tiw_lock); - if (p->active) { /* XXX assert ? */ - erts_smp_mtx_unlock(&tiw_lock); - return; - } - p->timeout = timeout; - p->cancel = cancel; - p->arg = arg; - p->active = 1; - insert_timer(p, t); - erts_smp_mtx_unlock(&tiw_lock); #if defined(ERTS_SMP) - if (t <= (Uint) ERTS_SHORT_TIME_T_MAX) - erts_sys_schedule_interrupt_timed(1, (erts_short_time_t) t); + if (tiw == erts_default_timer_wheel) + erts_interupt_aux_thread_timed(timeout_time); #endif + } void -erts_cancel_timer(ErlTimer* p) +erts_cancel_timer(ErlTimer *p) { - erts_smp_mtx_lock(&tiw_lock); - if (!p->active) { /* allow repeated cancel (drivers) */ - erts_smp_mtx_unlock(&tiw_lock); + ErtsTimerWheel *tiw; + ErlCancelProc cancel; + void *arg; + + tiw = get_timer_wheel(p); + if (!tiw) return; - } + + erts_smp_mtx_lock(&tiw->lock); + if (tiw != get_timer_wheel(p)) + cancel = NULL; + else { + remove_timer(tiw, p); + p->slot = 0; - /* is it the 'min' timer, remove min */ - if (p == tiw_min_ptr) { - tiw_min_ptr = NULL; - tiw_min = 0; + cancel = p->cancel; + arg = p->arg; } + erts_smp_mtx_unlock(&tiw->lock); - remove_timer(p); - p->slot = p->count = 0; - - if (p->cancel != NULL) { - erts_smp_mtx_unlock(&tiw_lock); - (*p->cancel)(p->arg); - return; - } - erts_smp_mtx_unlock(&tiw_lock); + if (cancel) + (*cancel)(arg); } /* @@ -447,59 +606,58 @@ erts_cancel_timer(ErlTimer* p) Uint erts_time_left(ErlTimer *p) { - Uint left; - erts_short_time_t dt; + ErtsTimerWheel *tiw; + ErtsMonotonicTime current_time, timeout_time; - erts_smp_mtx_lock(&tiw_lock); - - if (!p->active) { - erts_smp_mtx_unlock(&tiw_lock); + tiw = get_timer_wheel(p); + if (!tiw) return 0; - } - if (p->slot < tiw_pos) - left = (p->count + 1) * TIW_SIZE + p->slot - tiw_pos; + erts_smp_mtx_lock(&tiw->lock); + if (tiw != get_timer_wheel(p)) + timeout_time = ERTS_MONOTONIC_TIME_MIN; else - left = p->count * TIW_SIZE + p->slot - tiw_pos; - dt = do_time_read(); - if (left < dt) - left = 0; - else - left -= dt; - - erts_smp_mtx_unlock(&tiw_lock); + timeout_time = ERTS_CLKTCKS_TO_MONOTONIC(p->timeout_pos); + erts_smp_mtx_unlock(&tiw->lock); - return (Uint) left * TIW_ITIME; + current_time = erts_get_monotonic_time(); + if (timeout_time <= current_time) + return 0; + return (Uint) ERTS_MONOTONIC_TO_MSEC(timeout_time - current_time); } #ifdef DEBUG void erts_p_slpq(void) { + ErtsTimerWheel *tiw = erts_default_timer_wheel; + ErtsMonotonicTime current_time = erts_get_monotonic_time(); int i; ErlTimer* p; - erts_smp_mtx_lock(&tiw_lock); + erts_smp_mtx_lock(&tiw->lock); /* print the whole wheel, starting at the current position */ - erts_printf("\ntiw_pos = %d tiw_nto %d\n", tiw_pos, tiw_nto); - i = tiw_pos; - if (tiw[i] != NULL) { + erts_printf("\ncurrent time = %bps tiw_pos = %d tiw_nto %d\n", + current_time, tiw->pos, tiw->nto); + i = tiw->pos; + if (tiw->w[i] != NULL) { erts_printf("%d:\n", i); - for(p = tiw[i]; p != NULL; p = p->next) { - erts_printf(" (count %d, slot %d)\n", - p->count, p->slot); + for(p = tiw->w[i]; p != NULL; p = p->next) { + erts_printf(" (timeout time %bps, slot %d)\n", + ERTS_CLKTCKS_TO_MONOTONIC(p->timeout_pos), + p->slot); } } - for(i = (i+1)%TIW_SIZE; i != tiw_pos; i = (i+1)%TIW_SIZE) { - if (tiw[i] != NULL) { + for(i = ((i+1) & (TIW_SIZE-1)); i != (tiw->pos & (TIW_SIZE-1)); i = ((i+1) & (TIW_SIZE-1))) { + if (tiw->w[i] != NULL) { erts_printf("%d:\n", i); - for(p = tiw[i]; p != NULL; p = p->next) { - erts_printf(" (count %d, slot %d)\n", - p->count, p->slot); + for(p = tiw->w[i]; p != NULL; p = p->next) { + erts_printf(" (timeout time %bps, slot %d)\n", + ERTS_CLKTCKS_TO_MONOTONIC(p->timeout_pos), p->slot); } } } - erts_smp_mtx_unlock(&tiw_lock); + erts_smp_mtx_unlock(&tiw->lock); } #endif /* DEBUG */ diff --git a/erts/emulator/beam/utils.c b/erts/emulator/beam/utils.c index 3549e18538..127f1e4a6a 100644 --- a/erts/emulator/beam/utils.c +++ b/erts/emulator/beam/utils.c @@ -49,6 +49,7 @@ #include "beam_bp.h" #include "erl_ptab.h" #include "erl_check_io.h" +#include "erl_bif_unique.h" #ifdef HIPE # include "hipe_mode_switch.h" #endif @@ -4510,7 +4511,7 @@ erts_create_smp_ptimer(ErtsSmpPTimer **timer_ref, res->timer.timeout_func = timeout_func; res->timer.timer_ref = timer_ref; res->timer.id = id; - res->timer.tm.active = 0; /* MUST be initalized */ + erts_init_timer(&res->timer.tm); ASSERT(!*timer_ref); @@ -5087,8 +5088,8 @@ erts_smp_ensure_later_interval_acqb(erts_interval_t *icp, Uint64 ic) */ Uint64 erts_timestamp_millis(void) { -#ifdef HAVE_GETHRTIME - return (Uint64) (sys_gethrtime() / 1000000); +#ifdef ERTS_HAVE_OS_MONOTONIC_TIME_SUPPORT + return ERTS_MONOTONIC_TO_MSEC(erts_os_monotonic_time()); #else Uint64 res; SysTimeval tv; |