This presentation is the property of its rightful owner.
1 / 40

# CSCI-4320/6360: Parallel Programming & Computing Tues./Fri. 12-1:30 p.m. MPI File I/O PowerPoint PPT Presentation

Prof. Chris Carothers Computer Science Department MRC 309a chrisc@cs.rpi.edu www.cs.rpi.edu/~chrisc/COURSES/PARALLEL/SPRING-2013 Adapted from: people.cs.uchicago.edu/~asiegel/courses/cspp51085/.../mpi-io.ppt.

CSCI-4320/6360: Parallel Programming & Computing Tues./Fri. 12-1:30 p.m. MPI File I/O

Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.

- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -

#### Presentation Transcript

PPC 2013 - MPI Parallel File I/O

Prof. Chris Carothers

Computer Science Department

MRC 309a

chrisc@cs.rpi.edu

www.cs.rpi.edu/~chrisc/COURSES/PARALLEL/SPRING-2013

### CSCI-4320/6360: Parallel Programming & ComputingTues./Fri. 12-1:30 p.m.MPI File I/O

PPC 2013 - MPI Parallel File I/O

### Common Ways of Doing I/O in Parallel Programs

• Sequential I/O:

• All processes send data to rank 0, and 0 writes it to the file

PPC 2013 - MPI Parallel File I/O

### Pros and Cons of Sequential I/O

• Pros:

• parallel machine may support I/O from only one process (e.g., no common file system)

• Some I/O libraries (e.g. HDF-4, NetCDF, PMPIO) not parallel

• resulting single file is handy for ftp, mv

• big blocks improve performance

• short distance from original, serial code

• Cons:

• lack of parallelism limits scalability, performance (single node bottleneck)

PPC 2013 - MPI Parallel File I/O

### Another Way

• Each process writes to a separate file

• Pros:

• parallelism, high performance

• Cons:

• lots of small files to manage

• LOTS OF METADATA – stress parallel filesystem

• difficult to read back data from different number of processes

PPC 2013 - MPI Parallel File I/O

### What is Parallel I/O?

• Multiple processes of a parallel program accessing data (reading or writing) from a common file

FILE

P(n-1)

P0

P1

P2

PPC 2013 - MPI Parallel File I/O

### Why Parallel I/O?

• Non-parallel I/O is simple but

• Poor performance (single process writes to one file) or

• Awkward and not interoperable with other tools (each process writes a separate file)

• Parallel I/O

• Provides high performance

• Can provide a single file that can be used with other tools (such as visualization programs)

PPC 2013 - MPI Parallel File I/O

### Why is MPI a Good Setting for Parallel I/O?

• Writing is like sending a message and reading is like receiving.

• Any parallel I/O system will need a mechanism to

• define collective operations (MPI communicators)

• define noncontiguous data layout in memory and file (MPI datatypes)

• Test completion of nonblocking operations (MPI request objects)

• i.e., lots of MPI-like machinery

PPC 2013 - MPI Parallel File I/O

### MPI-IO Background

• Marc Snir et al (IBM Watson) paper exploring MPI as context for parallel I/O (1994)

• MPI-IO email discussion group led by J.-P. Prost (IBM) and Bill Nitzberg (NASA), 1994

• MPI-IO group joins MPI Forum in June 1996

• MPI-2 standard released in July 1997

• MPI-IO is Chapter 9 of MPI-2

PPC 2013 - MPI Parallel File I/O

FILE

P(n-1)

P0

P1

P2

### Using MPI for Simple I/O

Each process needs to read a chunk of data from a common file

PPC 2013 - MPI Parallel File I/O

### Using Individual File Pointers

#include<stdio.h>

#include<stdlib.h>

#include "mpi.h"

#define FILESIZE 1000

int main(int argc, char **argv){

int rank, nprocs;

MPI_File fh;

MPI_Status status;

int bufsize, nints;

int buf[FILESIZE];

MPI_Init(&argc, &argv);

MPI_Comm_rank(MPI_COMM_WORLD, &rank);

MPI_Comm_size(MPI_COMM_WORLD, &nprocs);

bufsize = FILESIZE/nprocs;

nints = bufsize/sizeof(int);

MPI_File_open(MPI_COMM_WORLD, "datafile",

MPI_MODE_RDONLY, MPI_INFO_NULL, &fh);

MPI_File_seek(fh, rank * bufsize, MPI_SEEK_SET);

MPI_File_close(&fh);

}

PPC 2013 - MPI Parallel File I/O

### Using Explicit Offsets

#include<stdio.h>

#include<stdlib.h>

#include "mpi.h"

#define FILESIZE 1000

int main(int argc, char **argv){

int rank, nprocs;

MPI_File fh;

MPI_Status status;

int bufsize, nints;

int buf[FILESIZE];

MPI_Init(&argc, &argv);

MPI_Comm_rank(MPI_COMM_WORLD, &rank);

MPI_Comm_size(MPI_COMM_WORLD, &nprocs);

bufsize = FILESIZE/nprocs;

nints = bufsize/sizeof(int);

MPI_File_open(MPI_COMM_WORLD, "datafile", MPI_MODE_RDONLY, MPI_INFO_NULL, &fh);

MPI_File_read_at(fh, rank*bufsize, buf, nints, MPI_INT, &status);

MPI_File_close(&fh);

}

PPC 2013 - MPI Parallel File I/O

### Function Details

MPI_File_open(MPI_Comm comm, char *file, int mode, MPI_Info info, MPI_File *fh)

(note: mode = MPI_MODE_RDONLY, MPI_MODE_RDWR, MPI_MODE_WRONLY,

MPI_MODE_CREATE, MPI_MODE_EXCL,

MPI_MODE_DELETE_ON_CLOSE, MPI_MODE_UNIQUE_OPEN,

MPI_MODE_SEQUENTIAL, MPI_MODE_APPEND)

MPI_File_close(MPI_File *fh)

MPI_File_read(MPI_File fh, void *buf, int count, MPI_Datatype type, MPI_Status *status)

MPI_File_read_at(MPI_File fh, int offset, void *buf, int count,

MPI_Datatype type, MPI_Status *status)

MPI_File_seek(MPI_File fh, MPI_Offset offset, in whence);

(note: whence = MPI_SEEK_SET, MPI_SEEK_CUR, or MPI_SEEK_END)

MPI_File_write(MPI_File fh, void *buf, int count, MPI_Datatype datatype, MPI_Status *status)

MPI_File_write_at( …same as read_at … );

(Note: Many other functions to get/set properties (see Gropp et al))

PPC 2013 - MPI Parallel File I/O

### Writing to a File

• Use MPI_File_write or MPI_File_write_at

• Use MPI_MODE_WRONLY or MPI_MODE_RDWR as the flags to MPI_File_open

• If the file doesn’t exist previously, the flag MPI_MODE_CREATE must also be passed to MPI_File_open

• We can pass multiple flags by using bitwise-or ‘|’ in C, or addition ‘+” in Fortran

PPC 2013 - MPI Parallel File I/O

### MPI Datatype Interlude

• Datatypes in MPI

• Elementary: MPI_INT, MPI_DOUBLE, etc

• everything we’ve used to this point

• Contiguous

• Next easiest: sequences of elementary types

• Vector

• Sequences separated by a constant “stride”

PPC 2013 - MPI Parallel File I/O

### MPI Datatypes, cont

• Indexed: more general

• does not assume a constant stride

• Struct

• General mixed types (like C structs)

PPC 2013 - MPI Parallel File I/O

### Creating simple datatypes

• Let’s just look at the simplest types: contiguous and vector datatypes.

• Contiguous example

• Let’s create a new datatype which is two ints side by side. The calling sequence is

MPI_Type_contiguous(int count, MPI_Datatype oldtype, MPI_Datatype *newtype);

MPI_Datatype newtype;

MPI_Type_contiguous(2, MPI_INT, &newtype);

MPI_Type_commit(newtype); /* required */

PPC 2013 - MPI Parallel File I/O

### Using File Views

• Processes write to shared file

• MPI_File_set_view assigns regions of the file to separate processes

PPC 2013 - MPI Parallel File I/O

### File Views

• Specified by a triplet (displacement, etype, and filetype) passed to MPI_File_set_view

• displacement = number of bytes to be skipped from the start of the file

• etype = basic unit of data access (can be any basic or derived datatype)

• filetype = specifies which portion of the file is visible to the process

• This is a collective operation and so all processors/ranks must use the same data rep, etypes in the group determined when the file was open..

PPC 2013 - MPI Parallel File I/O

### File Interoperability

• Users can optionally create files with a portable binary data representation

• “datarep” parameter to MPI_File_set_view

• native -default, same as in memory, not portable

• internal - impl. defined representation providing an impl. defined level of portability

• external32 - a specific representation defined in MPI, (basically 32-bit big-endian IEEE format), portable across machines and MPI implementations

PPC 2013 - MPI Parallel File I/O

### File View Example

MPI_File thefile;

for (i=0; i<BUFSIZE; i++)

buf[i] = myrank * BUFSIZE + i;

MPI_File_open(MPI_COMM_WORLD, "testfile",

MPI_MODE_CREATE | MPI_MODE_WRONLY,

MPI_INFO_NULL, &thefile);

MPI_File_set_view(thefile, myrank * BUFSIZE,

MPI_INT, MPI_INT, "native",

MPI_INFO_NULL);

MPI_File_write(thefile, buf, BUFSIZE, MPI_INT,

MPI_STATUS_IGNORE);

MPI_File_close(&thefile);

PPC 2013 - MPI Parallel File I/O

### Ways to Write to a Shared File

like Unix seek

• MPI_File_seek

• MPI_File_write_at

• MPI_File_write_shared

• Collective operations

combine seek and I/O

use shared file pointer

good when order

doesn’t matter

PPC 2013 - MPI Parallel File I/O

### Collective I/O in MPI

• A critical optimization in parallel I/O

• Allows communication of “big picture” to file system

• Framework for 2-phase I/O, in which communication precedes I/O (can use MPI machinery)

• Basic idea: build large blocks, so that reads/writes in I/O system will be large

Small individual

requests

Large collective

access

PPC 2013 - MPI Parallel File I/O

### Collective I/O

• _all indicates that all processes in the group specified by the communicator passed to MPI_File_open will call this function

• Each process specifies only its own access information -- the argument list is the same as for the non-collective functions

PPC 2013 - MPI Parallel File I/O

### Collective I/O

• By calling the collective I/O functions, the user allows an implementation to optimize the request based on the combined request of all processes

• The implementation can merge the requests of different processes and service the merged request efficiently

• Particularly effective when the accesses of different processes are noncontiguous and interleaved

PPC 2013 - MPI Parallel File I/O

### Collective non-contiguousMPI-IO examples

#define “mpi.h”

#define FILESIZE 1048576

#define INTS_PER_BLK 16

int main(int argc, char **argv){

int *buf, rank, nprocs, nints, bufsize;

MPI_File fh;

MPI_Datatype filetype;

MPI_Init(&argc, &argv);

MPI_Comm_rank(MPI_COMM_WORLD, &rank);

MPI_Comm_size(MPI_COMM_WORLD, &nprocs);

bufsize = FILESIZE/nprocs;

buf = (int *) malloc(bufsize);

nints = bufsize/sizeof(int);

MPI_File_open(MPI_COMM_WORLD, “filename”, MPI_MODE_RD_ONLY, MPI_INFO_NULL, &fh);

MPI_Type_vector(nints/INTS_PER_BLK, INTS_PER_BLK, INTS_PER_BLK*nprocs, MPI_INT, &filetype);

MPI_Type_commit(&filetype);

MPI_File_set_view(fh, INTS_PER_BLK*sizeof(int)*rank, MPI_INT, filetype, “native”, MPI_INFO_NULL);

MPI_Type_free(&filetype);

free(buf)

MPI_Finalize();

return(0);

}

PPC 2013 - MPI Parallel File I/O

• Note that the _all version has the same argument list

• Difference is that all processes involved in MPI_Open must call this the read

• Contrast with the non-all version where any subset may or may not call it

• Allows for many optimizations

PPC 2013 - MPI Parallel File I/O

### Split Collective I/O

• A restricted form of nonblocking collective I/O

• Only one active nonblocking collective operation allowed at a time on a file handle

• Therefore, no request object necessary

MPI_File_write_all_begin(fh, buf, count, datatype);

// available on Blue Gene/L, but may not improve

// performance

for (i=0; i<1000; i++) {

/* perform computation */

}

MPI_File_write_all_end(fh, buf, &status);

PPC 2013 - MPI Parallel File I/O

### Passing Hints to the Implementation

MPI_Info info;

MPI_Info_create(&info);

/* no. of I/O devices to be used for file striping */

MPI_Info_set(info, "striping_factor", "4");

/* the striping unit in bytes */

MPI_Info_set(info, "striping_unit", "65536");

MPI_File_open(MPI_COMM_WORLD, "/pfs/datafile",

MPI_MODE_CREATE | MPI_MODE_RDWR, info, &fh);

MPI_Info_free(&info);

PPC 2013 - MPI Parallel File I/O

### Examples of Hints (used in ROMIO)

• striping_unit

• striping_factor

• cb_buffer_size

• cb_nodes

• ind_rd_buffer_size

• ind_wr_buffer_size

• start_iodevice

• pfs_svr_buf

• direct_write

MPI-2 predefined hints

New Algorithm Parameters

Platform-specific hints

PPC 2013 - MPI Parallel File I/O

### I/O Consistency Semantics

• The consistency semantics specify the results when multiple processes access a common file and one or more processes write to the file

• MPI guarantees stronger consistency semantics if the communicator used to open the file accurately specifies all the processes that are accessing the file, and weaker semantics if not

• The user can take steps to ensure consistency when MPI does not automatically do so

PPC 2013 - MPI Parallel File I/O

Process 0

Process 1

MPI_File_open(MPI_COMM_WORLD,…)

MPI_File_write_at(off=0,cnt=100)

MPI_File_open(MPI_COMM_WORLD,…)

MPI_File_write_at(off=100,cnt=100)

### Example 1

• File opened with MPI_COMM_WORLD. Each process writes to a separate region of the file and reads back only what it wrote.

• MPI guarantees that the data will be read correctly

PPC 2013 - MPI Parallel File I/O

### Example 2

• Same as example 1, except that each process wants to read what the other process wrote (overlapping accesses)

• In this case, MPI does not guarantee that the data will automatically be read correctly

Process 0

Process 1

/* incorrect program */

MPI_File_open(MPI_COMM_WORLD,…)

MPI_File_write_at(off=0,cnt=100)

MPI_Barrier

/* incorrect program */

MPI_File_open(MPI_COMM_WORLD,…)

MPI_File_write_at(off=100,cnt=100)

MPI_Barrier

• In the above program, the read on each process is not guaranteed to get the data written by the other process!

PPC 2013 - MPI Parallel File I/O

### Example 2 contd.

• The user must take extra steps to ensure correctness

• There are three choices:

• set atomicity to true

• close the file and reopen it

• ensure that no write sequence on any process is concurrent with any sequence (read or write) on another process/MPI rank

• Can hurt performance….

PPC 2013 - MPI Parallel File I/O

Process 0

Process 1

MPI_File_open(MPI_COMM_WORLD,…)

MPI_File_set_atomicity(fh1,1)

MPI_File_write_at(off=0,cnt=100)

MPI_Barrier

MPI_File_open(MPI_COMM_WORLD,…)

MPI_File_set_atomicity(fh2,1)

MPI_File_write_at(off=100,cnt=100)

MPI_Barrier

### Example 2, Option 1Set atomicity to true

PPC 2013 - MPI Parallel File I/O

### Example 2, Option 2Close and reopen file

Process 0

Process 1

MPI_File_open(MPI_COMM_WORLD,…)

MPI_File_write_at(off=0,cnt=100)

MPI_File_close

MPI_Barrier

MPI_File_open(MPI_COMM_WORLD,…)

MPI_File_open(MPI_COMM_WORLD,…)

MPI_File_write_at(off=100,cnt=100)

MPI_File_close

MPI_Barrier

MPI_File_open(MPI_COMM_WORLD,…)

PPC 2013 - MPI Parallel File I/O

### Example 2, Option 3

• Ensure that no write sequence on any process is concurrent with any sequence (read or write) on another process

• a sequence is a set of operations between any pair of open, close, or file_sync functions

• a write sequence is a sequence in which any of the functions is a write operation

PPC 2013 - MPI Parallel File I/O

Process 0

Process 1

MPI_File_open(MPI_COMM_WORLD,…)

MPI_File_write_at(off=0,cnt=100)

MPI_File_sync

MPI_Barrier

MPI_File_sync /*collective*/

MPI_File_sync /*collective*/

MPI_Barrier

MPI_File_sync

MPI_File_close

MPI_File_open(MPI_COMM_WORLD,…)

MPI_File_sync /*collective*/

MPI_Barrier

MPI_File_sync

MPI_File_write_at(off=100,cnt=100)

MPI_File_sync

MPI_Barrier

MPI_File_sync /*collective*/

MPI_File_close

### Example 2, Option 3

PPC 2013 - MPI Parallel File I/O

### General Guidelines for Achieving High I/O Performance

• Buy sufficient I/O hardware for the machine

• Use fast file systems, not NFS-mounted home directories

• Do not perform I/O from one process only

• Make large requests wherever possible

• For noncontiguous requests, use derived datatypes and a single collective I/O call

PPC 2013 - MPI Parallel File I/O

### Optimizations

• Given complete access information, an implementation can perform optimizations such as:

• Data Sieving: Read large chunks and extract what is really needed

• Collective I/O: Merge requests of different processes into larger requests

• Improved prefetching and caching

PPC 2013 - MPI Parallel File I/O

### Summary

• MPI-IO has many features that can help users achieve high performance

• The most important of these features are the ability to specify noncontiguous accesses, the collective I/O functions, and the ability to pass hints to the implementation

• Users must use the above features!

• In particular, when accesses are noncontiguous, users must create derived datatypes, define file views, and use the collective I/O functions