diff options
| author | Simon Marlow <marlowsd@gmail.com> | 2011-11-28 16:48:43 +0000 |
|---|---|---|
| committer | Simon Marlow <marlowsd@gmail.com> | 2011-11-29 12:21:18 +0000 |
| commit | 50de6034343abc93a7b01daccff34121042c0e7c (patch) | |
| tree | 24496a5fc6bc39c6baaa574608e53c5d76c169f6 /includes/Cmm.h | |
| parent | 1c2b838131134d44004dfdff18c302131478390d (diff) | |
| download | haskell-50de6034343abc93a7b01daccff34121042c0e7c.tar.gz | |
Make profiling work with multiple capabilities (+RTS -N)
This means that both time and heap profiling work for parallel
programs. Main internal changes:
- CCCS is no longer a global variable; it is now another
pseudo-register in the StgRegTable struct. Thus every
Capability has its own CCCS.
- There is a new built-in CCS called "IDLE", which records ticks for
Capabilities in the idle state. If you profile a single-threaded
program with +RTS -N2, you'll see about 50% of time in "IDLE".
- There is appropriate locking in rts/Profiling.c to protect the
shared cost-centre-stack data structures.
This patch does enough to get it working, I have cut one big corner:
the cost-centre-stack data structure is still shared amongst all
Capabilities, which means that multiple Capabilities will race when
updating the "allocations" and "entries" fields of a CCS. Not only
does this give unpredictable results, but it runs very slowly due to
cache line bouncing.
It is strongly recommended that you use -fno-prof-count-entries to
disable the "entries" count when profiling parallel programs. (I shall
add a note to this effect to the docs).
Diffstat (limited to 'includes/Cmm.h')
| -rw-r--r-- | includes/Cmm.h | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/includes/Cmm.h b/includes/Cmm.h index 641faa216e..11c02b4e3e 100644 --- a/includes/Cmm.h +++ b/includes/Cmm.h @@ -372,7 +372,7 @@ CCCS_ALLOC(bytes); /* CCS_ALLOC wants the size in words, because ccs->mem_alloc is in words */ -#define CCCS_ALLOC(__alloc) CCS_ALLOC(BYTES_TO_WDS(__alloc), W_[CCCS]) +#define CCCS_ALLOC(__alloc) CCS_ALLOC(BYTES_TO_WDS(__alloc), CCCS) #define HP_CHK_GEN_TICKY(alloc,liveness,reentry) \ HP_CHK_GEN(alloc,liveness,reentry); \ |