Description of the flags used for the Fujitsu SPECjbb2005 results:
Fujitsu Ltd.
Feb 14, 2007


< Hardware setting >
Memory system is in "Non Mirror Mode".

PRIMEQUEST 580 memory system supports DSSA (Dual Sync System
Architecture )
and works in one of following two mode.


(1) Mirror Mode
   Address buses and Data buses are duplicated.
   And  most of internal action of chipset is also duplicated.

   In this mode, system memory throughput becomes half but higher
   reliability is expected by the memory system duplication.


(2) Non Mirror Mode
   Address buses and data buses are not duplicated.
   And the internal action of chipset is not duplicated.

   In this mode, full memory bandwidth is available,
   but the system duplication for higher reliability does not work.

Please see the detail of DSSA in the attached file.
"Fujitsu-linux-20051026_2.pdf".

< Policy setting >

numactl --localalloc
	Sets the process policy to the standard local allocation policy.

< Linux User Command >

taskset
	retrieve or set a processes's CPU affinity.

	-c <cpu_id>
		specify a numerical list of processors.

< JVM Command Line Options >

-Xms

	Sets the initial size of the heap. 
	This value can be specified in kilobytes (K,k), megabytes (M,m), or gigabytes (G,g).

	Default:
	If you do not set this, the minimum Java heap size defaults to (depending on which mode you are running): 
	-server mode: 25% of the amount of free physical memory in the system, up to 64 MB and at least 8 MB. 
	-client mode: 25% of the amount of free physical memory in the system, up to 16 MB and at least 8 MB. 

-Xmx

	Sets the maximum size of the heap. 
	This value can be specified in kilobytes (K,k), megabytes (M,m), or gigabytes (G,g).
	Use the following guidelines to determine this value:

	Default:
	If you do not set this, the maximum java heap size defaults to (depending on which mode you are running):
	-server mode: 75% of the physical memory up to 1 GB (reserved memory for the heap).
	-client mode: 75% of the physical memory up to 1 GB (reserved memory for the heap). 
	If the O/S imposes a process size limit, the default will be half the available physical memory. 

-XXaggressive

	Performs adaptive optimizations as early as possible in the Java
	application run. To do this, the bottleneck detector will run with
	a higher frequency from the start and then gradually lower
	its frequency. This options also tells BEA JRockit to use the available
	memory aggressively. 

	Default:
	If neither opt nor memory is specified, the application will run as if both were specified.

-XXtlasize=2m

	This flag specifies how large a Thread Local Area (TLA) should be.
	A TLA is a chunk of memory on the heap where a thread creates objects.
	The thread has exclusive use on this area and therefore object
	allocations are very cheap inside the TLA.

	Default: 
	The default value for the minimum size is 2 kB.
	The default value for the preferred size is 16 kB for heaps of 256 MB or above.
	For heaps below 256 MB, the default value increases linearly with the heap size
	from 2 kB up to 16 kB, in steps of 2 kB.
	The minimum value cannot be lower than the large object limit.
	If it is, the minimum size will be raised to match the large object limit.
	This can only happen if the large object limit is explicitly set.

-XXlargeObjectLimit=128k

	This flag specifies the limit for when objects are treated as large objects.
	This value can be specified in kilobytes (K,k), megabytes (M,m),
	or gigabytes (G,g). 

	Default: 
	If no value is specified, the default is 2 KB.

-XXallocClearChunks 

	This option allows you to clear a TLA for references and values at TLA
	allocation time and pre-fetch the next chunk. 
	When an integer, a reference, or anything else is declared, it has a 
	default value of 0 or null (depending upon type). 
	At the appropriate time, you will need to clear these references and
	values to free the memory on the heap so Java can use-or reuse-it. 
	You can do either when the object is allocated or, 
	by using this option, when you request a new TLA. 

	Default:
	By default, this mechanism is disabled. 
	If you use this option but do not specify a boolean value, the default is true.

-XXallocClearChunkSize=1k

	When used with -XXallocClearChunkSize, this option sets the size of the chunks to be cleared.
	
	Default: 
	If this option is used but no value is specified, the default is 512 bytes.

-XXhpm:enable

	This option uses hardware performance counters instead of software sampling in
	the HotSpot detector, which drives optimizations.

	Default:
	This option is disabled default.

-XXlazyUnlocking

	When -XXlazyUnlocking is set, locks will not be released when a critical section is exited.
	Instead, once a lock is acquired, the next thread that tries to acquire such a 
	lock will have to ensure that the lock is or can be released.
	It does this by determining if the initial thread still uses the lock.
	A shared lock will convert to a normal lock and not stay in lazy mode.

	Default:
	If -XXlazyUnlocking ia not set, locks will be released when a critical section is exited.

-XXcompactratio

	This option sets the compaction ratio.
	
	Default: 
	If you are running a static compaction, the default is approximately 6%;
	however, if you are not using static compaction, the default applies
	only at the beginning of the run.