Change default values of CVARs in RMA code.

Change default values of MPIR_CVAR_CH3_RMA_NREQUEST_NEW_THRESHOLD,
MPIR_CVAR_CH3_RMA_NREQUEST_VISIT_THRESHOLD and
MPIR_CVAR_CH3_RMA_NREQUEST_TEST_THRESHOLD for better performance.

This experience is from running graph500 on single node on BLUES
and breadboard machine, with 16 or 8 processes and problem size is
2^16 to 2^20. We make the number of new requests since the last
attempt to complete pending requests to 0, so that the issuing code
will always try to complete pending requests. We also disable the
threshold of completed requests in GC and make the threshold of
tested requests in GC to be 100, so that we have opportunity to
find more pending requests in GC.
Signed-off-by: Pavan Balaji <balaji@anl.gov>

src/mpid/ch3/src/ch3u_rma_sync.c

@@ -41,7 +41,7 @@ cvars:
     - name        : MPIR_CVAR_CH3_RMA_NREQUEST_NEW_THRESHOLD
       category    : CH3
       type        : int
-      default     : 128
+      default     : 0
       class       : none
       verbosity   : MPI_T_VERBOSITY_USER_BASIC
       scope       : MPI_T_SCOPE_ALL_EQ
@@ -54,7 +54,7 @@ cvars:
     - name        : MPIR_CVAR_CH3_RMA_GC_NUM_COMPLETED
       category    : CH3
       type        : int
-      default     : 1
+      default     : (-1)
       class       : none
       verbosity   : MPI_T_VERBOSITY_USER_BASIC
       scope       : MPI_T_SCOPE_ALL_EQ
@@ -80,7 +80,7 @@ cvars:
     - name        : MPIR_CVAR_CH3_RMA_GC_NUM_TESTED
       category    : CH3
       type        : int
-      default     : (-1)
+      default     : 100
       class       : none
       verbosity   : MPI_T_VERBOSITY_USER_BASIC
       scope       : MPI_T_SCOPE_ALL_EQ