mirror of
https://github.com/HDFGroup/hdf5.git
synced 2025-01-30 15:32:37 +08:00
9a433b99a5
Lots of performance improvements & a couple new internal API interfaces. Description: Performance Improvements: - Cached file offset & length sizes in shared file struct, to avoid constantly looking them up in the FCPL. - Generic property improvements: - Added "revision" number to generic property classes to speed up comparisons. - Changed method of storing properties from using a hash-table to the TBBT routines in the library. - Share the propery names between classes and the lists derived from them. - Removed redundant 'def_value' buffer from each property. - Switching code to use a "copy on write" strategy for properties in each list, where the properties in each list are shared with the properties in the class, until a property's value is changed in a list. - Fixed error in layout code which was allocating too many buffers. - Redefined public macros of the form (H5open()/H5check, <variable>) internally to only be (<variable>), avoiding innumerable useless calls to H5open() and H5check_version(). - Reuse already zeroed buffers in H5F_contig_fill instead of constantly re-zeroing them. - Don't write fill values if writing entire dataset. - Use gettimeofday() system call instead of time() system when checking the modification time of a dataset. - Added reference counted string API and use it for tracking the names of objects opening in a file (for the ID->name code). - Removed redundant H5P_get() calls in B-tree routines. - Redefine H5T datatype macros internally to the library, to avoid calling H5check redundantly. - Keep dataspace information for dataset locally instead of reading from disk each time. Added new module to track open objects in a file, to allow this (which will be useful eventually for some FPH5 metadata caching issues). - Remove H5AC_find macro which was inlining metadata cache lookups, and call function instead. - Remove redundant memset() calls from H5G_namei() routine. - Remove redundant checking of object type when locating objects in metadata cache and rely on the address only. - Create default dataset object to use when default dataset creation property list is used to create datasets, bypassing querying for all the property list values. - Use default I/O vector size when performing raw data with the default dataset transfer property list, instead of querying for I/O vector size. - Remove H5P_DEFAULT internally to the library, replacing it with more specific default property list based on the type of property list needed. - Remove redundant memset() calls in object header message (H5O*) routines. - Remove redunant memset() calls in data I/O routines. - Split free-list allocation routines into malloc() and calloc()- like routines, instead of one combined routine. - Remove lots of indirection in H5O*() routines. - Simplify metadata cache entry comparison routine (used when flushing entire cache out). - Only enable metadata cache statistics when H5AC_DEBUG is turned on, instead of always tracking them. - Simplify address comparison macro (H5F_addr_eq). - Remove redundant metadata cache entry protections during dataset creation by protecting the object header once and making all the modifications necessary for the dataset creation before unprotecting it. - Reduce # of "number of element in extent" computations performed by computing and storing the value during dataspace creation. - Simplify checking for group location's file information, when file has not been involving in file-mounting operations. - Use binary encoding for modification time, instead of ASCII. - Hoist H5HL_peek calls (to get information in a local heap) out of loops in many group routine. - Use static variable for iterators of selections, instead of dynamically allocation them each time. - Lookup & insert new entries in one step, avoiding traversing group's B-tree twice. - Fixed memory leak in H5Gget_objname_idx() routine (tangential to performance improvements, but fixed along the way). - Use free-list for reference counted strings. - Don't bother copying object names into cached group entries, since they are re-created when an object is opened. The benchmark I used to measure these results created several thousand small (2K) datasets in a file and wrote out the data for them. This is Elena's "regular.c" benchmark. These changes resulted in approximately ~4.3x speedup of the development branch when compared to the previous code in the development branch and ~1.4x speedup compared to the release branch. Additionally, these changes reduce the total memory used (code and data) by the development branch by ~800KB, bringing the development branch back into the same ballpark as the release branch. I'll send out a more detailed description of the benchmark results as a followup note. New internal API routines: Added "reference counted strings" API for tracking strings that get used by multiple owners without duplicating the strings. Added "ternary search tree" API for text->object mappings. Platforms tested: Tested h5committest {arabica (fortran), eirene (fortran, C++) modi4 (parallel, fortran)} Other platforms/configurations tested? FreeBSD 4.7 (sleipnir) serial & parallel Solaris 2.6 (baldric) serial
179 lines
5.3 KiB
C
179 lines
5.3 KiB
C
/*
|
||
* Copyright © 1998 NCSA
|
||
* All rights reserved.
|
||
*
|
||
* Programmer: Robb Matzke <matzke@llnl.gov>
|
||
* Thursday, July 30, 1998
|
||
*
|
||
* Purpose: Determines if the modification time message is working
|
||
* properly. Specifically, the code in H5O_mtime_decode() is
|
||
* very OS-dependent and this test tries to figure out if it's
|
||
* working properly.
|
||
*/
|
||
#include "h5test.h"
|
||
|
||
const char *FILENAME[] = {
|
||
"mtime",
|
||
NULL
|
||
};
|
||
|
||
#define TESTFILE1 "tmtimeo.h5"
|
||
#define MTIME1 1041605080
|
||
#define TESTFILE2 "tmtimen.h5"
|
||
#define MTIME2 1041606478
|
||
|
||
|
||
/*-------------------------------------------------------------------------
|
||
* Function: main
|
||
*
|
||
* Purpose: H5O_mtime_decode() test.
|
||
*
|
||
* Return: Success:
|
||
*
|
||
* Failure:
|
||
*
|
||
* Programmer: Robb Matzke
|
||
* Thursday, July 30, 1998
|
||
*
|
||
* Modifications:
|
||
* Added checks for old and new modification time messages
|
||
* in pre-created datafiles (generated with gen_old_mtime.c and
|
||
* gen_new_mtime.c).
|
||
* Quincey Koziol
|
||
* Friday, January 3, 2003
|
||
*
|
||
*-------------------------------------------------------------------------
|
||
*/
|
||
int
|
||
main(void)
|
||
{
|
||
hid_t fapl, file, space, dset;
|
||
hsize_t size[1] = {2};
|
||
time_t now;
|
||
struct tm *tm;
|
||
H5G_stat_t sb1, sb2;
|
||
signed char buf1[32], buf2[32];
|
||
char filename[1024];
|
||
|
||
h5_reset();
|
||
fapl = h5_fileaccess();
|
||
|
||
TESTING("modification time messages");
|
||
|
||
/* Create the file, create a dataset, then close the file */
|
||
h5_fixname(FILENAME[0], fapl, filename, sizeof filename);
|
||
if ((file=H5Fcreate(filename, H5F_ACC_TRUNC, H5P_DEFAULT, fapl))<0)
|
||
return 1;
|
||
if ((space=H5Screate_simple(1, size, NULL))<0) return 1;
|
||
if ((dset=H5Dcreate(file, "dset", H5T_NATIVE_SCHAR, space, H5P_DEFAULT))<0)
|
||
return 1;
|
||
now = time(NULL);
|
||
if (H5Dclose(dset)<0) return 1;
|
||
if (H5Sclose(space)<0) return 1;
|
||
if (H5Fclose(file)<0) return 1;
|
||
|
||
/*
|
||
* Open the file and get the modification time. We'll test the new
|
||
* H5Gget_objinfo() arguments too: being able to stat something without
|
||
* knowing its name.
|
||
*/
|
||
h5_fixname(FILENAME[0], fapl, filename, sizeof filename);
|
||
if ((file = H5Fopen(filename, H5F_ACC_RDONLY, fapl))<0) return 1;
|
||
if (H5Gget_objinfo(file, "dset", TRUE, &sb1)<0) return 1;
|
||
if ((dset=H5Dopen(file, "dset"))<0) return 1;
|
||
if (H5Gget_objinfo(dset, ".", TRUE, &sb2)<0) return 1;
|
||
if (H5Dclose(dset)<0) return 1;
|
||
if (H5Fclose(file)<0) return 1;
|
||
|
||
/* Compare times from the two ways of calling H5Gget_objinfo() */
|
||
if (sb1.objno[0]!=sb2.objno[0] || sb1.objno[1]!=sb2.objno[1] ||
|
||
sb1.mtime!=sb2.mtime) {
|
||
H5_FAILED();
|
||
puts(" Calling H5Gget_objinfo() with the dataset ID returned");
|
||
puts(" different values than calling it with a file and dataset");
|
||
puts(" name.");
|
||
return 1;
|
||
}
|
||
|
||
/* Compare times -- they must be within 60 seconds of one another */
|
||
if (0==sb1.mtime) {
|
||
SKIPPED();
|
||
puts(" The modification time could not be decoded on this OS.");
|
||
puts(" Modification times will be mantained in the file but");
|
||
puts(" cannot be queried on this system. See H5O_mtime_decode().");
|
||
return 0;
|
||
} else if (fabs(HDdifftime(now, sb1.mtime))>60.0) {
|
||
H5_FAILED();
|
||
tm = localtime(&(sb1.mtime));
|
||
strftime((char*)buf1, sizeof buf1, "%Y-%m-%d %H:%M:%S", tm);
|
||
tm = localtime(&now);
|
||
strftime((char*)buf2, sizeof buf2, "%Y-%m-%d %H:%M:%S", tm);
|
||
printf(" got: %s\n ans: %s\n", buf1, buf2);
|
||
return 1;
|
||
}
|
||
PASSED();
|
||
|
||
/* Check opening existing file with old-style modification time information
|
||
* and make certain that the time is correct
|
||
*/
|
||
TESTING("accessing old modification time messages");
|
||
|
||
{
|
||
char testfile[512]="";
|
||
char *srcdir = HDgetenv("srcdir");
|
||
if (srcdir && ((HDstrlen(srcdir) + strlen(TESTFILE1) + 1) < sizeof(testfile))){
|
||
HDstrcpy(testfile, srcdir);
|
||
HDstrcat(testfile, "/");
|
||
}
|
||
HDstrcat(testfile, TESTFILE1);
|
||
file = H5Fopen(testfile, H5F_ACC_RDONLY, H5P_DEFAULT);
|
||
if (file >= 0){
|
||
if(H5Gget_objinfo(file, "/Dataset1", TRUE, &sb1)<0)
|
||
return 1;
|
||
if(sb1.mtime!=MTIME1) return 1;
|
||
if (H5Fclose(file)<0) return 1;
|
||
}
|
||
else {
|
||
printf("***cannot open the pre-created old modification test file (%s)\n",
|
||
testfile);
|
||
return 1;
|
||
} /* end else */
|
||
}
|
||
PASSED();
|
||
|
||
/* Check opening existing file with new-style modification time information
|
||
* and make certain that the time is correct
|
||
*/
|
||
TESTING("accessing new modification time messages");
|
||
|
||
{
|
||
char testfile[512]="";
|
||
char *srcdir = HDgetenv("srcdir");
|
||
if (srcdir && ((HDstrlen(srcdir) + strlen(TESTFILE2) + 1) < sizeof(testfile))){
|
||
HDstrcpy(testfile, srcdir);
|
||
HDstrcat(testfile, "/");
|
||
}
|
||
HDstrcat(testfile, TESTFILE2);
|
||
file = H5Fopen(testfile, H5F_ACC_RDONLY, H5P_DEFAULT);
|
||
if (file >= 0){
|
||
if(H5Gget_objinfo(file, "/Dataset1", TRUE, &sb2)<0)
|
||
return 1;
|
||
if(sb2.mtime!=MTIME2) return 1;
|
||
if (H5Fclose(file)<0) return 1;
|
||
}
|
||
else {
|
||
printf("***cannot open the pre-created old modification test file (%s)\n",
|
||
testfile);
|
||
return 1;
|
||
} /* end else */
|
||
}
|
||
PASSED();
|
||
|
||
/* All looks good */
|
||
puts("All modification time tests passed.");
|
||
h5_cleanup(FILENAME, fapl);
|
||
return 0;
|
||
}
|
||
|
||
|