IBM AIX: Environment Settings and Utilities

IBM AIX 5L V5.3

IBM AIX V6

Last updated: 11-May-2010

Sections

Selecting one of the following will take you directly to that section:

Optimization Flags

Optimization Flags

-bmaxdata:0x20000000, -bmaxdata:0x40000000, -bmaxdata:0x50000000, -bmaxdata:0x60000000, -bmaxdata:0x80000000
-bdatapsize:64K
-bstackpsize:64K
-btextpsize:64K
-blpdata
-D__IBM_FAST_VECTOR
-D__IBM_FAST_SET_MAP_ITERATOR
-D_ILS_MACROS

- -bmaxdata:0x20000000, -bmaxdata:0x40000000, -bmaxdata:0x50000000, -bmaxdata:0x60000000, -bmaxdata:0x80000000
- -bmaxdata:(\S+)\b
- Causes the system loader to put the heap in it's own segment of the size specified. This is only required for 32-bit applications, as their segments are 256M. If the last digit of the value is "C", then it also turns off the malloc pool option for that executable.
- -bdatapsize:64K
- -bdatapsize:64K\b
- Specifies a non-default page size of 64K for the program data segment.
- -bstackpsize:64K
- -bstackpsize:64K\b
- Specifies a non-default page size of 64K for the program stack segment.
- -btextpsize:64K
- -btextpsize:64K\b
- Specifies a non-default page size of 64K for the program text segment.
- -blpdata
- -blpdata\b
- Sets the bit in the file's XCOFF header indicating that this executable will request the use of large pages when they are available on the system and when the user has an appropriate privilege
- -D__IBM_FAST_VECTOR
- -D__IBM_FAST_VECTOR\b
- The __IBM_FAST_VECTOR macro defines a different iterator for the std::vector template class. This iterator results in faster code, but is not compatible with code using the default iterator for a std::vector template class. All uses of std::vector for a data type must use the same iterator. Add -D__IBM_FAST_VECTOR to the compile line, or "#define __IBM_FAST_VECTOR 1" to your source code to use the faster iterator for std::vector template class. You must compile all sources with this macro.
- -D__IBM_FAST_SET_MAP_ITERATOR
- -D__IBM_FAST_SET_MAP_ITERATOR\b
- The __IBM_FAST_SET_MAP_ITERATOR macro defines a different iterator for the std::vector template class. This iterator results in faster code, but is not compatible with code using the default iterator for a std::vector template class. All uses of std::vector for a data type must use the same iterator. Add -D__IBM_FAST_SET_MAP_ITERATOR to the compile line, or "#define __IBM_FAST_SET_MAP_ITERATOR 1" to your source code to use the faster iterator for std::vector template class. You must compile all sources with this macro.
- -D_ILS_MACROS
- -D_ILS_MACROS\b
- Causes AIX to define "ischar()" (and friends) as macro's and not subroutines.

System and Other Tuning Information

System Commands

drmgr -r -c cpu
Deconfigures one core from the active partition. Use it N times to deconfigure N cores.

smtctl -m on|off -w now|boot
Controls the enabling and disabling of processor simultaneous multi-threading mode.

vmo -r -o lgpg_regions=n -o lgpg_size=16777216
Sets the size of large pages to 16M, and set the number to use, with -r, takes effect on the next IPL.

bosboot -q
Regenerates the IPL boot to set the options specified with smtctl and vmo.

ulimit
Controls resources allowed to be used by processes. All resource are set to unlimited, of primary importance is the "stack" and "data/heap" settings.

chsyscfg -m system -r prof -i name=profile,lpar_name=partition,lpar_proc_compat_mode=POWER6_enhanced
This command enables the POWERPC architecture optional instructions supported on POWER6.

Usage: chsyscfg -r lpar | prof | sys | sysprof | frame
                -m <managed system> | -e <managed frame>
                -f <configuration file> | -i "<configuration data>"
                [--help]

Changes partitions, partition profiles, system profiles, or the attributes of a
managed system or a managed frame.

    -r                        - the type of resource(s) to be changed:
                                  lpar    - partition
                                  prof    - partition profile
                                  sys     - managed system
                                  sysprof - system profile
                                  frame   - managed frame
    -m <managed system>       - the managed system's name
    -e <managed frame>        - the managed frame's name
    -f <configuration file>   - the name of the file containing the
                                configuration data for this command.
                                The format is:
                                  attr_name1=value,attr_name2=value,...
                                or
                                  "attr_name1=value1,value2,...",...
    -i "<configuration data>" - the configuration data for this command.
                                The format is:
                                  "attr_name1=value,attr_name2=value,..."
                                or
                                  ""attr_name1=value1,value2,...",..."
    --help                    - prints this help

The valid attribute names for this command are:
    -r prof     required: name, lpar_id | lpar_name
                optional: ...
                          lpar_proc_compat_mode (default | POWER6_enhanced)

bindprocessor $$ <n>
The next program is to be bound to the specified processor.

Environment variables set before the run:

MEMORY_AFFINITY=MCM
Cause the OS to alloc memory "closest" to the chip that first requests it.

MALLOCOPTIONS=POOL
Selects the OS malloc option that allocates/frees small objects very quickly.

XLFRTEOPTS=intrinthrds=1
Causes the Fortran runtime to only use a single thread.

MALLOCMULTIHEAP=1
Selects the OS malloc option that allocates, and uses, a unique malloc heap per thread to eliminate mutliple threads from locking on a single malloc heap.

XLSMPOPTS=<options>
The XLSMPOPTS environment variable allows you to specify options that affect SMP execution.

            spins=0:yields=0  Forces threads to wait for work, rather than sleeping.
            startproc=0       Enables thread binding to processors, with the number
                              specified being the first processor used.
            stride=1          The increment of the processor number to bind threads to.