NUMA support

Summary:
The aim here is to reduce the number of remote memory accesses on
systems with a NUMA memory architecture, typically multi-socket servers.

Linux provides a NUMA API for doing two things:
* Allocating memory local to a particular node
* Binding a thread to a particular node

When given the +RTS --numa flag, the runtime will
* Determine the number of NUMA nodes (N) by querying the OS
* Assign capabilities to nodes, so cap C is on node C%N
* Bind worker threads on a capability to the correct node
* Keep a separate free lists in the block layer for each node
* Allocate the nursery for a capability from node-local memory
* Allocate blocks in the GC from node-local memory

For example, using nofib/parallel/queens on a 24-core 2-socket machine:

```
$ ./Main 15 +RTS -N24 -s -A64m
  Total   time  173.960s  (  7.467s elapsed)

$ ./Main 15 +RTS -N24 -s -A64m --numa
  Total   time  150.836s  (  6.423s elapsed)
```

The biggest win here is expected to be allocating from node-local
memory, so that means programs using a large -A value (as here).

According to perf, on this program the number of remote memory accesses
were reduced by more than 50% by using `--numa`.

Test Plan:
* validate
* There's a new flag --debug-numa=<n> that pretends to do NUMA without
  actually making the OS calls, which is useful for testing the code
  on non-NUMA systems.
* TODO: I need to add some unit tests

Reviewers: erikd, austin, rwbarton, ezyang, bgamari, hvr, niteria

Subscribers: thomie

Differential Revision: https://phabricator.haskell.org/D2199

1 files changed, 7 insertions, 1 deletions

diff --git a/includes/rts/Flags.h b/includes/rts/Flags.h
index 8020a177b0..ff303dc5e6 100644
--- a/includes/rts/Flags.h
+++ b/includes/rts/Flags.h
@@ -73,6 +73,11 @@ typedef struct _GC_FLAGS {
                                  * to handle the exception before we
                                  * raise it again.
                                  */
+
+    rtsBool numa;               /* Use NUMA */
+    uint32_t nNumaNodes;        /* Number of nodes */
+    uint32_t numaMap[MAX_NUMA_NODES]; /* Map our internal node numbers to OS
+                                       * node numbers */
 } GC_FLAGS;
 
 /* See Note [Synchronization of flags and base APIs] */
@@ -93,6 +98,7 @@ typedef struct _DEBUG_FLAGS {
     rtsBool squeeze;        /* 'z'  stack squeezing & lazy blackholing */
     rtsBool hpc; 	    /* 'c' coverage */
     rtsBool sparks; 	    /* 'r' */
+    rtsBool numa; 	    /* '--debug-numa' */
 } DEBUG_FLAGS;
 
 /* See Note [Synchronization of flags and base APIs] */
@@ -184,7 +190,7 @@ typedef struct _MISC_FLAGS {
 #ifdef THREADED_RTS
 /* See Note [Synchronization of flags and base APIs] */
 typedef struct _PAR_FLAGS {
-  uint32_t       nNodes;         /* number of threads to run simultaneously */
+  uint32_t       nCapabilities;  /* number of threads to run simultaneously */
   rtsBool        migrate;        /* migrate threads between capabilities */
   uint32_t       maxLocalSparks;
   rtsBool        parGcEnabled;   /* enable parallel GC */