#include <IncrementalStMan.h>

Public Member Functions
	IncrementalStMan (uInt bucketSize=0, Bool checkBucketSize=True, uInt cacheSize=1)
	Create an incremental storage manager with the given name. More...

	IncrementalStMan (const String &dataManagerName, uInt bucketSize=0, Bool checkBucketSize=True, uInt cacheSize=1)

	~IncrementalStMan ()

Public Member Functions inherited from casacore::ISMBase
	ISMBase (uInt bucketSize=0, Bool checkBucketSize=True, uInt cacheSize=1)
	Create an incremental storage manager without a name. More...

	ISMBase (const String &dataManagerName, uInt bucketSize, Bool checkBucketSize, uInt cacheSize)
	Create an incremental storage manager with the given name. More...

	ISMBase (const String &aDataManName, const Record &spec)
	Create an incremental storage manager with the given name. More...

	~ISMBase ()

virtual DataManager *	clone () const
	Clone this object. More...

virtual String	dataManagerType () const
	Get the type name of the data manager (i.e. More...

virtual String	dataManagerName () const
	Get the name given to the storage manager (in the constructor). More...

virtual Record	dataManagerSpec () const
	Record a record containing data manager specifications. More...

virtual Record	getProperties () const
	Get data manager properties that can be modified. More...

virtual void	setProperties (const Record &spec)
	Modify data manager properties. More...

uInt	version () const
	Get the version of the class. More...

void	setCacheSize (uInt cacheSize, Bool canExceedNrBuckets)
	Set the cache size (in buckets). More...

uInt	cacheSize () const
	Get the current cache size (in buckets). More...

void	clearCache ()
	Clear the cache used by this storage manager. More...

virtual void	showCacheStatistics (ostream &os) const
	Show the statistics of all caches used. More...

void	showIndexStatistics (ostream &os)
	Show the index statistics. More...

void	showBucketLayout (ostream &os)
	Show the layout of the buckets. More...

uInt	bucketSize () const
	Get the bucket size (in bytes). More...

uInt	uIntSize () const
	Get the size of a uInt in external format (can be canonical or local). More...

uInt	rownrSize () const
	Get the size of a rownr in external format (can be canonical or local). More...

ISMBucket *	getBucket (rownr_t rownr, rownr_t &bucketStartRow, rownr_t &bucketNrrow)
	Get the bucket containing the given row. More...

ISMBucket *	nextBucket (uInt &cursor, rownr_t &bucketStartRow, rownr_t &bucketNrrow)
	Get the next bucket. More...

char *	tempBuffer () const
	Get access to the temporary buffer. More...

uInt	uniqueNr ()
	Get a unique column number for the column (it is only unique for this storage manager). More...

rownr_t	nrow () const
	Get the number of rows in this storage manager. More...

virtual Bool	canAddRow () const
	Can the storage manager add rows? (yes) More...

virtual Bool	canRemoveRow () const
	Can the storage manager delete rows? (yes) More...

virtual Bool	canAddColumn () const
	Can the storage manager add columns? (not yet) More...

virtual Bool	canRemoveColumn () const
	Can the storage manager delete columns? (not yet) More...

ISMColumn &	getColumn (uInt colnr)
	Get access to the given column. More...

void	addBucket (rownr_t rownr, ISMBucket *bucket)
	Add a bucket to the storage manager (i.e. More...

void	setBucketDirty ()
	Make the current bucket in the cache dirty (i.e. More...

StManArrayFile *	openArrayFile (ByteIO::OpenOption opt)
	Open (if needed) the file for indirect arrays with the given mode. More...

Bool	checkBucketLayout (uInt &offendingCursor, rownr_t &offendingBucketStartRow, uInt &offendingBucketNrow, uInt &offendingBucketNr, uInt &offendingCol, uInt &ffendingIndex, rownr_t &offendingRow, rownr_t &offendingPrevRow)
	Check that there are no repeated rowIds in the buckets comprising this ISM. More...

Public Member Functions inherited from casacore::DataManager
	DataManager ()
	Default constructor. More...

virtual	~DataManager ()

void	dataManagerInfo (Record &info) const
	Add SEQNR and SPEC (the DataManagerSpec subrecord) to the info. More...

virtual Bool	isStorageManager () const
	Is the data manager a storage manager? The default is yes. More...

virtual Bool	canReallocateColumns () const
	Tell if the data manager wants to reallocate the data manager column objects. More...

virtual DataManagerColumn *	reallocateColumn (DataManagerColumn *column)
	Reallocate the column object if it is part of this data manager. More...

uInt	sequenceNr () const
	Get the (unique) sequence nr of this data manager. More...

uInt	ncolumn () const
	Get the nr of columns in this data manager (can be zero). More...

Bool	asBigEndian () const
	Have the data to be stored in big or little endian canonical format? More...

const TSMOption &	tsmOption () const
	Get the TSM option. More...

MultiFileBase *	multiFile ()
	Get the MultiFile pointer (can be 0). More...

String	keywordName (const String &keyword) const
	Compose a keyword name from the given keyword appended with the sequence number (e.g. More...

String	fileName () const
	Compose a unique filename from the table name and sequence number. More...

ByteIO::OpenOption	fileOption () const
	Get the AipsIO option of the underlying file. More...

virtual Bool	isRegular () const
	Is this a regular storage manager? It is regular if it allows addition of rows and writing data in them. More...

Table &	table () const
	Get the table this object is associated with. More...

virtual Bool	canRenameColumn () const
	Does the data manager allow to rename columns? (default yes) More...

virtual void	setMaximumCacheSize (uInt nMiB)
	Set the maximum cache size (in bytes) to be used by a storage manager. More...

virtual void	showCacheStatistics (std::ostream &) const
	Show the data manager's IO statistics. More...

DataManagerColumn *	createScalarColumn (const String &columnName, int dataType, const String &dataTypeId)
	Create a column in the data manager on behalf of a table column. More...

DataManagerColumn *	createDirArrColumn (const String &columnName, int dataType, const String &dataTypeId)
	Create a direct array column. More...

DataManagerColumn *	createIndArrColumn (const String &columnName, int dataType, const String &dataTypeId)
	Create an indirect array column. More...

DataManager *	getClone () const
	Has the object already been cloned? More...

void	setClone (DataManager *clone) const
	Set the pointer to the clone. More...

Private Member Functions
	IncrementalStMan (const IncrementalStMan &that)
	Copy constructor cannot be used. More...

IncrementalStMan &	operator= (const IncrementalStMan &that)
	Assignment cannot be used. More...

Additional Inherited Members
Static Public Member Functions inherited from casacore::ISMBase
static DataManager *	makeObject (const String &dataManagerType, const Record &spec)
	Make the object from the type name string. More...

Static Public Member Functions inherited from casacore::DataManager
static void	registerCtor (const String &type, DataManagerCtor func)
	Register a mapping of a data manager type to its static construction function. More...

static DataManagerCtor	getCtor (const String &dataManagerType)
	Get the "constructor" of a data manager (thread-safe). More...

static Bool	isRegistered (const String &dataManagerType)
	Test if a data manager is registered (thread-safe). More...

static DataManager *	unknownDataManager (const String &dataManagerType, const Record &spec)
	Serve as default function for theirRegisterMap, which catches all unknown data manager types. More...

Static Public Attributes inherited from casacore::DataManager
static rownr_t	MAXROWNR32
	Define the highest row number that can be represented as signed 32-bit. More...

Protected Member Functions inherited from casacore::DataManager
void	decrementNcolumn ()
	Decrement number of columns (in case a column is deleted). More...

void	setEndian (Bool bigEndian)
	Tell the data manager if big or little endian format is needed. More...

void	setTsmOption (const TSMOption &tsmOption)
	Tell the data manager which TSM option to use. More...

void	setMultiFile (MultiFileBase *mfile)
	Tell the data manager that MultiFile can be used. More...

void	throwDataTypeOther (const String &columnName, int dataType) const
	Throw an exception in case data type is TpOther, because the storage managers (and maybe other data managers) do not support such columns. More...

Detailed Description

The Incremental Storage Manager

Intended use:

Public interface

Review Status

Reviewed By:: UNKNOWN
Date Reviewed:: before2004/08/25
Test programs:: tIncrementalStMan

Prerequisite

The Table Data Managers concept as described in module file Tables.h
ROIncrementalStManAccessor for a discussion of the cache size

Etymology

IncrementalStMan is the data manager storing values in an incremental way (similar to an incremental backup). A value is only stored when it differs from the previous value.

Synopsis

IncrementalStMan stores the data in a way that a value is only stored when it is different from the value in the previous row. This storage manager is very well suited for columns with slowly changing values, because the resulting file can be much smaller. It is not suited at all for columns with continuously changing data.

In general it can be advantageous to use this storage manager when a value changes at most every 4 rows (although it depends on the length of the data values themselves). The following simple example shows the approximate savings that can be achieved when storing a column with double values changing every CH rows.

\#rows    CH     normal length      ISM length      compress ratio
   5        4000000          1606000               2.5
  50        4000000           164000              24.5
 500        4000000            32800             122

There is a special test program nISMBucket in the Tables module doing a simple, but usually adequate, simulation of the amount of storage needed for a scenario.

IncrementalStMan stores the values (and associated indices) in fixed-length buckets. A BucketCache object is used to read/write the buckets. The default cache size is 1 bucket (which is fine for sequential access), but for random access it can make sense to increase the size of the cache. This can be done using the class ROIncrementalStManAccessor.

The IncrementalStMan can hold values of any standard data type (thus from Bool to String). It can handle scalars, direct and indirect arrays. It can support an arbitrary number of columns. The values in each of them can vary at its own speed.
A bucket contains the values of several consecutive rows. At the beginning of a bucket the values of the starting row of all columns for this storage manager are repeated. In this way the value of a cell can always be found in the bucket and no references to previous buckets are needed.
A bucket should be big enough to hold all starting values and a reasonable number of other values. As a rule of thumb it should be big enough to hold at least 100 values of each column. In general the default bucket size will do. Only in special cases (e.g. when storing large variable length strings) the bucket size should be set explicitly. Giving a zero bucket size means that a suitale default bucket size will be calculated.
When a table is filled sequentially each bucket can be filled as much as possible. When writing in a random way, buckets can contain some unused space, because a bucket in the middle of the file has to be split when a new value has to be put in it.

Each column in the IncrementalStMan has the following properties to achieve the "store-different-values-only" behaviour.

When a row is not explicitly put, it has the same value as the previous row. The first row gets the standard undefined values when not put. The order of put's and addRow's is not important.
E.g. when a table has N rows and row N and the following M rows have the same value, the following schematic code has the same effect:
add 1 row; put value in row N; add M rows;
add M+1 rows; put value in row N;
When putting a scalar or direct array, it is tested if it matches the previous row. If so, it is not stored again. This test is not done for indirect arrays, because those can be (very) big and it would be too time-consuming. So the only way to save space for indirect arrays is by not putting them as explained in the previous item.
For indirect arrays the buckets contain a pointer only. The arrays themselves are stored in a separate file.
When a value of an existing row is updated, only that one row is updated. The next row(s) keep their value, even if it was shared with the row being updated.
For scalars and direct arrays it will be tested if the new value matches the value in the previous and/or next row. If so, those rows will be combined to save storage.
The IncrementalStMan is optimized for sequential access to a table.
- A bucket is accessed only once, because a bucket contains consecutive rows.
- For each column a copy is kept of the last value read. So the value for the next rows (with that same value) is immediately available.
For random access the performance can be improved by setting the cache size using class

ROIncrementalStManAccessor.

Note: This class contains many public functions which are only used by other ISM classes; The only useful function for the user is the constructor;

Motivation

IncrementalStMan can save a lot of storage space. Unlike the old StManMirAIO it stores the values directly in the file to save on memory usage.

Example

This example shows how to create a table and how to attach the storage manager to some columns.

SetupNewTable newtab("name.data", tableDesc, Table::New);
IncrementalStMan stman;                  // define storage manager
newtab.bindColumn ("column1", stman);    // bind column to st.man.
newtab.bindColumn ("column2", stman);    // bind column to st.man.
Table tab(newtab);                       // actually create table

Definition at line 181 of file IncrementalStMan.h.

Constructor & Destructor Documentation

◆ IncrementalStMan() [1/3]

casacore::IncrementalStMan::IncrementalStMan	(	uInt	bucketSize = `0`,
		Bool	checkBucketSize = `True`,
		uInt	cacheSize = `1`
	)

explicit

Create an incremental storage manager with the given name.

If no name is used, it is set to an empty string. The name can be used to construct a

ROIncrementalStManAccessor object (e.g. to set the cache size).
The bucket size has to be given in bytes and the cache size in buckets. Bucket size 0 means that the storage manager will set the bucket size such that it can contain about 100 rows (with a minimum size of 32768 bytes). However, if that results in a very large bucket size (>327680) it'll make it smaller. Note it uses 32 bytes for the size of variable length strings, so this heuristic may fail when a column contains large strings. When checkBucketSize is set and Bucket size > 0 the storage manager throws an exception when the size is too small to hold the values of at least 2 rows. For this check it uses 0 for the length of variable length strings.

◆ IncrementalStMan() [2/3]

casacore::IncrementalStMan::IncrementalStMan	(	const String &	dataManagerName,
		uInt	bucketSize = `0`,
		Bool	checkBucketSize = `True`,
		uInt	cacheSize = `1`
	)

explicit

◆ ~IncrementalStMan()

casacore::IncrementalStMan::~IncrementalStMan ( )

◆ IncrementalStMan() [3/3]

casacore::IncrementalStMan::IncrementalStMan ( const IncrementalStMan & that )

private

Copy constructor cannot be used.

Member Function Documentation

◆ operator=()

IncrementalStMan& casacore::IncrementalStMan::operator= ( const IncrementalStMan & that )