erts: Add microstate accounting

Microstate accounting is a way to track which state the
different threads within ERTS are in. The main usage area
is to pin point performance bottlenecks by checking which
states the threads are in and then from there figuring out
why and where to optimize.

Since checking whether microstate accounting is on or off is
relatively expensive if done in a short loop only a few of the
states are enabled by default and more states can be enabled
through configure.

I've done some benchmarking and the overhead with it turned off
is not noticible and with it on it is a fraction of a percent.
If you enable the extra states, depending on the benchmark,
the ovehead when turned off is about 1% and when turned on
somewhere inbetween 5-15%.

OTP-12345

1 files changed, 16 insertions, 2 deletions

diff --git a/erts/emulator/beam/erl_alloc.h b/erts/emulator/beam/erl_alloc.h
index 14e80960f5..71e4713624 100644
--- a/erts/emulator/beam/erl_alloc.h
+++ b/erts/emulator/beam/erl_alloc.h
@@ -233,12 +233,14 @@ ERTS_ALC_INLINE
 void *erts_alloc(ErtsAlcType_t type, Uint size)
 {
     void *res;
+    ERTS_MSACC_PUSH_AND_SET_STATE_X(ERTS_MSACC_STATE_ALLOC);
     res = (*erts_allctrs[ERTS_ALC_T2A(type)].alloc)(
 	ERTS_ALC_T2N(type),
 	erts_allctrs[ERTS_ALC_T2A(type)].extra,
 	size);
     if (!res)
 	erts_alloc_n_enomem(ERTS_ALC_T2N(type), size);
+    ERTS_MSACC_POP_STATE_X();
     return res;
 }
 
@@ -246,6 +248,7 @@ ERTS_ALC_INLINE
 void *erts_realloc(ErtsAlcType_t type, void *ptr, Uint size)
 {
     void *res;
+    ERTS_MSACC_PUSH_AND_SET_STATE_X(ERTS_MSACC_STATE_ALLOC);
     res = (*erts_allctrs[ERTS_ALC_T2A(type)].realloc)(
 	ERTS_ALC_T2N(type),
 	erts_allctrs[ERTS_ALC_T2A(type)].extra,
@@ -253,37 +256,48 @@ void *erts_realloc(ErtsAlcType_t type, void *ptr, Uint size)
 	size);
     if (!res)
 	erts_realloc_n_enomem(ERTS_ALC_T2N(type), ptr, size);
+    ERTS_MSACC_POP_STATE_X();
     return res;
 }
 
 ERTS_ALC_INLINE
 void erts_free(ErtsAlcType_t type, void *ptr)
 {
+    ERTS_MSACC_PUSH_AND_SET_STATE_X(ERTS_MSACC_STATE_ALLOC);
     (*erts_allctrs[ERTS_ALC_T2A(type)].free)(
 	ERTS_ALC_T2N(type),
 	erts_allctrs[ERTS_ALC_T2A(type)].extra,
 	ptr);
+    ERTS_MSACC_POP_STATE_X();
 }
 
 
 ERTS_ALC_INLINE
 void *erts_alloc_fnf(ErtsAlcType_t type, Uint size)
 {
-    return (*erts_allctrs[ERTS_ALC_T2A(type)].alloc)(
+    void *res;
+    ERTS_MSACC_PUSH_AND_SET_STATE_X(ERTS_MSACC_STATE_ALLOC);
+    res = (*erts_allctrs[ERTS_ALC_T2A(type)].alloc)(
 	ERTS_ALC_T2N(type),
 	erts_allctrs[ERTS_ALC_T2A(type)].extra,
 	size);
+    ERTS_MSACC_POP_STATE_X();
+    return res;
 }
 
 
 ERTS_ALC_INLINE
 void *erts_realloc_fnf(ErtsAlcType_t type, void *ptr, Uint size)
 {
-    return (*erts_allctrs[ERTS_ALC_T2A(type)].realloc)(
+    void *res;
+    ERTS_MSACC_PUSH_AND_SET_STATE_X(ERTS_MSACC_STATE_ALLOC);
+    res = (*erts_allctrs[ERTS_ALC_T2A(type)].realloc)(
 	ERTS_ALC_T2N(type),
 	erts_allctrs[ERTS_ALC_T2A(type)].extra,
 	ptr,
 	size);
+    ERTS_MSACC_POP_STATE_X();
+    return res;
 }
 
 ERTS_ALC_INLINE