Fortran API Reference

FTI Datatypes
FTI Constants
FTI_Init
FTI_InitType
FTI_Protect
FTI_Checkpoint
FTI_Status
FTI_Recover
FTI_Snapshot
FTI_Finalize

FTI Datatypes and Constants

FTI Datatypes

⬆️ Top

FTI datatypes are used in the C-API function FTI_Protect. With the count parameter and the datatype, FTI is able to determine the size of the allocated memory region at ptr.

The FTI Fortran interface defines a template of FTI_Protect for all intrinsic data types. Hence the datatype definitions are not necessary here and are not avalable for the Fortran interface.

FTI Constants

⬆️ Top

FTI_BUFS : 256
FTI_DONE : 1
FTI_SCES : 0
FTI_NSCS : -1

---

FTI_Init

⬆️ Top

• Reads configuration file.i
• Creates checkpoint directories.
• Detects topology of the system.
• Regenerates data upon recovery.

DEFINITION

FTI_Init ( config_file, global_comm, err )

ARGUMENTS

Variable	What for?
[IN] character (len=*) :: config_file	Path to the config file
[IN/OUT] integer :: global_comm	MPI communicator used for the execution
[OUT] integer :: err	Token for FTI error code.

ERROR HANDLING

Value	Reason
FTI_SCES	Success
FTI_NSCS	No Success
FTI_NREC	FTI couldn't recover ckpt files, no recovery possible

DESCRIPTION

This function initializes the FTI context. It should be called before other FTI functions, right after MPI initialization.

EXAMPLE

EXAMPLE

---

FTI_InitType

⬆️ Top

• Initializes a data type.

DEFINITION

FTI_InitType ( type_F, size_F, err )

INPUT

Variable	What for?
type(FTI_type), intent(OUT) :: type_F	The data type to be initialized
integer, intent(IN) :: size_F	The size of the data type to be initialized
integer, intent(OUT) :: err	Token for FTI error code.

OUTPUT

Value	Reason
FTI_SCES	Success

DESCRIPTION

This function initializes a data type. A variable’s type which isn’t defined by default by FTI (see: FTI Datatypes) should be added using this function before adding this variable to protected variables.

EXAMPLE

EXAMPLE

---

FTI_Protect

⬆️ Top

• Stores metadata concerning the variable to protect.

DEFINITION

FTI_Protect ( id, data, ierr )

INPUT

Variable	What for?
type(FTI_type), intent(OUT) :: id	Unique ID of the variable to protect
type_fort , pointer :: data	Pointer to memory address of variable
integer, intent(OUT) :: ierr	Token for FTI error code.

OUTPUT

Value	Reason
FTI_SCES	Success
exit(1)	Number of protected variables is > FTI_BUFS

DESCRIPTION

This function should be used to add data structure to the list of protected variables. This list of structures is the data that will be stored during a checkpoint and loaded during a recovery. It resets the dataset with given id if it was already previously registered. When size of a variable changes during execution it should be updated using this function before next check- point to properly store data.

EXAMPLE

EXAMPLE

---

FTI_Checkpoint

⬆️ Top

• Writes values of protected runtime variables to a checkpoint file of requested level.

DEFINITION

FTI_Checkpoint ( id_F, level, err )

INPUT

Variable	What for?
integer, intent(IN) :: id_F	Unique checkpoint ID
integer, intent(IN) :: level	Checkpoint level (1=L1, 2=L2, 3=L3, 4=L4)
integer, intent(OUT) :: err	Token for FTI error code.

OUTPUT

Value	Reason
FTI_DONE	Success
FTI_NSCS	Failure

DESCRIPTION

This function is used to store current values of protected variables into a checkpoint file. Depending on the checkpoint level file is stored in local, partner node or global directory. Checkpoint’s id must be different from 0.

EXAMPLE

EXAMPLE

---

FTI_Status

⬆️ Top

• Returns the current status of the recovery flag.

DEFINITION

FTI_Status ( status )

INPUT

Variable	What for?
integer, intent(OUT) :: status	Token for status flag.

OUTPUT

Value	Reason
integer 0	No checkpoints taken yet or recovered successfully
integer 1	At least one checkpoint is taken. If execution fails, the next start will be a restart
integer 2	The execution is a restart from checkpoint level L4 and keep_last_checkpoint was enabled during the last execution

DESCRIPTION

This function returns the current status of the recovery flag.

EXAMPLE

EXAMPLE

---

FTI_Recover

⬆️ Top

• Loads checkpoint data from the checkpoint file and initializes the runtime variables of the execution.

DEFINITION

FTI_Recover ( err )

INPUT

Variable	What for?
integer, intent(OUT) :: err	Token for FTI error code.

OUTPUT

Value	Reason
FTI_SCES	Success
FTI_NSCS	Failure

DESCRIPTION

This function loads the checkpoint data from the checkpoint file and it up- dates some basic checkpoint information. It should be called after initial- ization of protected variables after a failure. If a variable changes it’s size during execution it must have the latest size before Recover. The easiest way to do so is to add size of variable as another variable to protected list, and then call Recover twice. First to recover size of variable. Second to recover variable’s data (after an update of protected list).

EXAMPLE

Basic example:

EXAMPLE

Example if a variable changes its size during execution:

EXAMPLE

---

FTI_Snapshot

⬆️ Top

• Loads checkpoint data and initializes runtime variables upon recovery.
• Writes multilevel checkpoints regarding their requested frequencies.

DEFINITION

FTI_Snapshot ( err )

INPUT

Variable	What for?
integer, intent(OUT) :: err	Token for FTI error code.

OUTPUT

Value	Reason
FTI_SCES	Successfull call (without checkpointing) or if recovery successful
FTI_NSCS	Failure of FTI_Checkpoint
FTI_DONE	Success of FTI_Checkpoint
exit(1)	Failure on recovery

DESCRIPTION

This function loads the checkpoint data from the checkpoint file in case of restart. Otherwise, it checks if the current iteration requires checkpointing (see e.g.: ckpt_L1) and performs a checkpoint if needed (internal call to FTI_Checkpoint). Should be called after initialization of protected variables.

EXAMPLE

EXAMPLE

---

FTI_Finalize

⬆️ Top

• Frees the allocated memory.
• Communicates the end of the execution to dedicated threads.
• Cleans checkpoints and metadata.

DEFINITION

FTI_Finalize ( err )

INPUT

Variable	What for?
integer, intent(OUT) :: err	Token for FTI error code.

OUTPUT

Value	Reason
FTI_SCES	For application process
exit(0)	For FTI process

DESCRIPTION

This function notifies the FTI processes that the execution is over, frees some data structures and it closes. If this function is not called on the end of the program the FTI processes will never finish (deadlock). Should be called before MPI_Finalize().

EXAMPLE

EXAMPLE