summaryrefslogtreecommitdiff
path: root/rts/ClosureFlags.c
diff options
context:
space:
mode:
authorSimon Marlow <marlowsd@gmail.com>2010-12-15 12:08:43 +0000
committerSimon Marlow <marlowsd@gmail.com>2010-12-15 12:08:43 +0000
commitf30d527344db528618f64a25250a3be557d9f287 (patch)
tree5b827afed254139a197cbdcdd37bebe8fa859d67 /rts/ClosureFlags.c
parent99b6e6ac44c6c610b0d60e3b70a2341c83d23106 (diff)
downloadhaskell-f30d527344db528618f64a25250a3be557d9f287.tar.gz
Implement stack chunks and separate TSO/STACK objects
This patch makes two changes to the way stacks are managed: 1. The stack is now stored in a separate object from the TSO. This means that it is easier to replace the stack object for a thread when the stack overflows or underflows; we don't have to leave behind the old TSO as an indirection any more. Consequently, we can remove ThreadRelocated and deRefTSO(), which were a pain. This is obviously the right thing, but the last time I tried to do it it made performance worse. This time I seem to have cracked it. 2. Stacks are now represented as a chain of chunks, rather than a single monolithic object. The big advantage here is that individual chunks are marked clean or dirty according to whether they contain pointers to the young generation, and the GC can avoid traversing clean stack chunks during a young-generation collection. This means that programs with deep stacks will see a big saving in GC overhead when using the default GC settings. A secondary advantage is that there is much less copying involved as the stack grows. Programs that quickly grow a deep stack will see big improvements. In some ways the implementation is simpler, as nothing special needs to be done to reclaim stack as the stack shrinks (the GC just recovers the dead stack chunks). On the other hand, we have to manage stack underflow between chunks, so there's a new stack frame (UNDERFLOW_FRAME), and we now have separate TSO and STACK objects. The total amount of code is probably about the same as before. There are new RTS flags: -ki<size> Sets the initial thread stack size (default 1k) Egs: -ki4k -ki2m -kc<size> Sets the stack chunk size (default 32k) -kb<size> Sets the stack chunk buffer size (default 1k) -ki was previously called just -k, and the old name is still accepted for backwards compatibility. These new options are documented.
Diffstat (limited to 'rts/ClosureFlags.c')
-rw-r--r--rts/ClosureFlags.c10
1 files changed, 6 insertions, 4 deletions
diff --git a/rts/ClosureFlags.c b/rts/ClosureFlags.c
index d5181cae22..41810f4025 100644
--- a/rts/ClosureFlags.c
+++ b/rts/ClosureFlags.c
@@ -59,8 +59,9 @@ StgWord16 closure_flags[] = {
[RET_FUN] = ( 0 ),
[UPDATE_FRAME] = ( _BTM ),
[CATCH_FRAME] = ( _BTM ),
- [STOP_FRAME] = ( _BTM ),
- [BLACKHOLE] = ( _NS| _UPT ),
+ [UNDERFLOW_FRAME] = ( _BTM ),
+ [STOP_FRAME] = ( _BTM ),
+ [BLACKHOLE] = ( _NS| _UPT ),
[BLOCKING_QUEUE] = ( _NS| _MUT|_UPT ),
[MVAR_CLEAN] = (_HNF| _NS| _MUT|_UPT ),
[MVAR_DIRTY] = (_HNF| _NS| _MUT|_UPT ),
@@ -74,7 +75,8 @@ StgWord16 closure_flags[] = {
[WEAK] = (_HNF| _NS| _UPT ),
[PRIM] = (_HNF| _NS| _UPT ),
[MUT_PRIM] = (_HNF| _NS| _MUT|_UPT ),
- [TSO] = (_HNF| _NS| _MUT|_UPT ),
+ [TSO] = (_HNF| _NS| _MUT|_UPT ),
+ [STACK] = (_HNF| _NS| _MUT|_UPT ),
[TREC_CHUNK] = ( _NS| _MUT|_UPT ),
[ATOMICALLY_FRAME] = ( _BTM ),
[CATCH_RETRY_FRAME] = ( _BTM ),
@@ -82,6 +84,6 @@ StgWord16 closure_flags[] = {
[WHITEHOLE] = ( 0 )
};
-#if N_CLOSURE_TYPES != 59
+#if N_CLOSURE_TYPES != 61
#error Closure types changed: update ClosureFlags.c!
#endif