darshan-convert.c 10.5 KB
Newer Older
1
/*
2 3 4
 * Copyright (C) 2015 University of Chicago.
 * See COPYRIGHT notice in top-level directory.
 *
5 6 7 8 9 10 11 12 13 14 15 16 17
 */

#include <stdio.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <fcntl.h>
#include <unistd.h>
#include <string.h>
#include <zlib.h>
#include <time.h>
#include <stdlib.h>
#include <getopt.h>
#include <assert.h>
18
#include <errno.h>
19 20 21

#include "darshan-logutils.h"

22
extern uint32_t darshan_hashlittle(const void *key, size_t length, uint32_t initval);
23 24 25 26 27 28

int usage (char *exename)
{
    fprintf(stderr, "Usage: %s [options] <infile> <outfile>\n", exename);
    fprintf(stderr, "       Converts darshan log from infile to outfile.\n");
    fprintf(stderr, "       rewrites the log file into the newest format.\n");
29
    fprintf(stderr, "       --bzip2 Use bzip2 compression instead of zlib.\n");
30
    fprintf(stderr, "       --obfuscate Obfuscate items in the log.\n");
31 32
    fprintf(stderr, "       --key <key> Key to use when obfuscating.\n");
    fprintf(stderr, "       --annotate <string> Additional metadata to add.\n");
33
    fprintf(stderr, "       --file <hash> Limit output to specified (hashed) file only.\n");
34
    fprintf(stderr, "       --reset-md Reset old metadata during conversion.\n");
35 36 37 38

    exit(1);
}

39
void parse_args (int argc, char **argv, char **infile, char **outfile,
40 41
                 int *bzip2, int *obfuscate, int *reset_md, int *key,
                 char **annotate, uint64_t* hash)
42 43
{
    int index;
44 45
    int ret;

46 47
    static struct option long_opts[] =
    {
48
        {"bzip2", 0, NULL, 'b'},
49
        {"annotate", 1, NULL, 'a'},
50
        {"obfuscate", 0, NULL, 'o'},
51
        {"reset-md", 0, NULL, 'r'},
52
        {"key", 1, NULL, 'k'},
53
        {"file", 1, NULL, 'f'},
54 55
        {"help",  0, NULL, 0},
        { 0, 0, 0, 0 }
56 57
    };

58
    *bzip2 = 0;
59
    *reset_md = 0;
60 61
    *hash = 0;

62 63 64 65 66 67 68 69
    while(1)
    {
        int c = getopt_long(argc, argv, "", long_opts, &index);

        if (c == -1) break;

        switch(c)
        {
70 71 72
            case 'b':
                *bzip2 = 1;
                break;
73 74 75
            case 'a':
                *annotate = optarg;
                break;
76 77 78
            case 'o':
                *obfuscate = 1;
                break;
79 80 81
            case 'r':
                *reset_md = 1;
                break;
82 83 84
            case 'k':
                *key = atoi(optarg);
                break;
85 86 87 88 89
            case 'f':
                ret = sscanf(optarg, "%" PRIu64, hash);
                if(ret != 1)
                    usage(argv[0]);
                break;
90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110
            case 0:
            case '?':
            default:
                usage(argv[0]);
                break;
        }
    }

    if (optind + 2 == argc)
    {
        *infile = argv[optind];
        *outfile = argv[optind+1];
    }
    else
    {
        usage(argv[0]);
    }

    return;
}

111
#if 0
112 113 114 115 116 117
static void reset_md_job(struct darshan_job *job)
{
    job->metadata[0] = '\0';
    return;
}

118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150
void obfuscate_job(int key, struct darshan_job *job)
{
    job->uid   = (int64_t) darshan_hashlittle(&job->uid, sizeof(job->uid), key);
    if (job->jobid != 0)
    {
        job->jobid = (int64_t) darshan_hashlittle(&job->jobid, sizeof(job->jobid), key);
    }

    return;
}

void obfuscate_exe(int key, char *exe)
{
    uint32_t hashed;

    hashed = darshan_hashlittle(exe, strlen(exe), key);
    memset(exe, 0, strlen(exe));
    sprintf(exe, "%u", hashed);

    return;
}

void obfuscate_file(int key, struct darshan_file *file)
{
    uint32_t hashed;

    hashed = darshan_hashlittle(file->name_suffix, sizeof(file->name_suffix), key);
    memset(file->name_suffix, 0, sizeof(file->name_suffix));
    sprintf(file->name_suffix, "%u", hashed);

    return;
}

151 152 153 154 155
void add_annotation (char *annotation,
                     struct darshan_job *job)
{
    char *token;
    char *save;
156
    int len;
157
    
158 159 160 161 162 163 164 165 166 167 168
    /* check for newline in existing metadata, insert if needed */
    len = strlen(job->metadata);
    if(len > 0 && len < sizeof(job->metadata))
    {
        if(job->metadata[len-1] != '\n')
        {
            job->metadata[len] = '\n';
            job->metadata[len+1] = '\0';
        }
    }

169 170
    /* determine remaining space in metadata string */
    int remaining = sizeof(job->metadata) - strlen(job->metadata);
171 172 173 174 175

    for(token=strtok_r(annotation, "\t", &save);
        token != NULL;
        token=strtok_r(NULL, "\t", &save))
    {
176 177 178 179 180 181 182 183 184 185 186 187
        if ((strlen(token)+1) < remaining)
        {
            strcat(job->metadata, token);
            strcat(job->metadata, "\n");
            remaining -= (strlen(token)+1);
        }
        else
        {
            fprintf(stderr,
                    "not enough space left in metadata for: current=%s token=%s (remain=%d:need=%d)\n",
                    job->metadata, token, remaining-1, strlen(token)+1);
        }
188 189 190 191
    }

    return;
}
192
#endif
193

194 195 196 197 198
int main(int argc, char **argv)
{
    int ret;
    char *infile_name;
    char *outfile_name;
199
    struct darshan_header header;
200
    struct darshan_job job;
201
    char tmp_string[4096];
202 203 204 205 206
    darshan_fd infile;
    darshan_fd outfile;
    int i;
    int mount_count;
    char** mnt_pts;
207 208 209 210
    struct darshan_record_ref *rec_hash = NULL;
    struct darshan_record_ref *ref, *tmp;
    char *mod_buf;
    int mod_buf_sz;
211
    char** fs_types;
212 213 214
    int bzip2;
    enum darshan_comp_type comp_type;

215 216
    int obfuscate = 0;
    int key = 0;
217
    char *annotation = NULL;
218
    uint64_t hash;
219
    int reset_md = 0;
220

221 222
    parse_args(argc, argv, &infile_name, &outfile_name, &bzip2, &obfuscate,
               &reset_md, &key, &annotation, &hash);
223

224
    infile = darshan_log_open(infile_name);
225 226
    if(!infile)
    {
227
        fprintf(stderr, "darshan_log_open() failed to open %s\n.", infile_name);
228 229 230
        return(-1);
    }
 
231 232
    comp_type = bzip2 ? comp_type = DARSHAN_BZIP2_COMP : DARSHAN_ZLIB_COMP;
    outfile = darshan_log_create(outfile_name, comp_type);
233 234
    if(!outfile)
    {
235
        fprintf(stderr, "darshan_log_create() failed to create %s\n.", outfile_name);
236 237 238 239 240 241 242 243 244 245 246
        darshan_log_close(infile);
        return(-1);
    }

    /* read header from input file */
    ret = darshan_log_getheader(infile, &header);
    if(ret < 0)
    {
        fprintf(stderr, "Error: unable to read header from input log file %s.\n", infile_name);
        darshan_log_close(infile);
        darshan_log_close(outfile);
247 248 249
        return(-1);
    }

250 251 252
    /* NOTE: we do not write the header to the output file until the end, as
     * the mapping data stored in this structure may change in the conversion
     * process (particularly, if we are converting between libz/bz2 compression)
253
     */
254

255 256 257 258 259 260
    /* read job info */
    ret = darshan_log_getjob(infile, &job);
    if(ret < 0)
    {
        fprintf(stderr, "Error: unable to read job information from log file.\n");
        darshan_log_close(infile);
261
        darshan_log_close(outfile);
262 263 264
        return(-1);
    }

265
#if 0
266
    if (reset_md) reset_md_job(&job);
267
    if (obfuscate) obfuscate_job(key, &job);
268
    if (annotation) add_annotation(annotation, &job);
269
#endif
270

271 272 273 274
    ret = darshan_log_putjob(outfile, &job);
    if (ret < 0)
    {
        fprintf(stderr, "Error: unable to write job information to log file.\n");
275
        darshan_log_close(infile);
276 277 278 279
        darshan_log_close(outfile);
        return(-1);
    }

280
    ret = darshan_log_getexe(infile, tmp_string);
281 282 283 284
    if(ret < 0)
    {
        fprintf(stderr, "Error: unable to read trailing job information.\n");
        darshan_log_close(infile);
285
        darshan_log_close(outfile);
286 287
        return(-1);
    }
288

289
#if 0
290
    if (obfuscate) obfuscate_exe(key, tmp_string);
291
#endif
292

293 294 295 296
    ret = darshan_log_putexe(outfile, tmp_string);
    if(ret < 0)
    {
        fprintf(stderr, "Error: unable to write trailing job information.\n");
297
        darshan_log_close(infile);
298 299 300
        darshan_log_close(outfile);
        return(-1);
    }
301 302

    ret = darshan_log_getmounts(infile, &mnt_pts, &fs_types, &mount_count);
303 304 305 306
    if(ret < 0)
    {
        fprintf(stderr, "Error: unable to read trailing job information.\n");
        darshan_log_close(infile);
307
        darshan_log_close(outfile);
308 309 310
        return(-1);
    }

311
    ret = darshan_log_putmounts(outfile, mnt_pts, fs_types, mount_count);
312 313 314
    if(ret < 0)
    {
        fprintf(stderr, "Error: unable to write mount information.\n");
315
        darshan_log_close(infile);
316 317 318 319
        darshan_log_close(outfile);
        return(-1);
    }

320
    ret = darshan_log_gethash(infile, &rec_hash);
321 322
    if(ret < 0)
    {
323 324 325 326
        fprintf(stderr, "Error: unable to read darshan record hash.\n");
        darshan_log_close(infile);
        darshan_log_close(outfile);
        return(-1);
327
    }
328 329 330

    ret = darshan_log_puthash(outfile, rec_hash);
    if(ret < 0)
331
    {
332 333 334 335
        fprintf(stderr, "Error: unable to write darshan record hash.\n");
        darshan_log_close(infile);
        darshan_log_close(outfile);
        return(-1);
336 337
    }

338 339 340 341 342
    mod_buf = malloc(DARSHAN_DEF_COMP_BUF_SZ);
    if(!mod_buf)
        return(-1);

    for(i=0; i<DARSHAN_MAX_MODS; i++)
343
    {
344 345 346 347 348 349
        memset(mod_buf, 0, DARSHAN_DEF_COMP_BUF_SZ);
        mod_buf_sz = DARSHAN_DEF_COMP_BUF_SZ;

        /* check each module for any data */
        ret = darshan_log_getmod(infile, i, mod_buf, &mod_buf_sz);
        if(ret < 0)
350
        {
351 352 353 354
            fprintf(stderr, "Error: failed to get module %s data.\n",
                darshan_module_names[i]);
            darshan_log_close(infile);
            darshan_log_close(outfile);
355 356
            return(-1);
        }
357
        else if(ret == 0)
358
        {
359 360
            /* skip modules not present in log file */
            continue;
361
        }
362

363 364 365 366 367 368 369 370 371 372
        /* we have module data to convert */
        ret = darshan_log_putmod(outfile, i, mod_buf, mod_buf_sz);
        if(ret < 0)
        {
            fprintf(stderr, "Error: failed to put module %s data.\n",
                darshan_module_names[i]);
            darshan_log_close(infile);
            darshan_log_close(outfile);
            return(-1);
        }
373
    }
374
    free(mod_buf);
375 376 377 378 379 380 381 382 383 384 385

    for(i=0; i<mount_count; i++)
    {
        free(mnt_pts[i]);
        free(fs_types[i]);
    }
    if(mount_count > 0)
    {
        free(mnt_pts);
        free(fs_types);
    }
386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403

    HASH_ITER(hlink, rec_hash, ref, tmp)
    {
        HASH_DELETE(hlink, rec_hash, ref);
        free(ref->rec.name);
        free(ref);
    }

    /* write header to output file */
    ret = darshan_log_putheader(outfile);
    if(ret < 0)
    {
        fprintf(stderr, "Error: unable to write header to output log file %s.\n", outfile_name);
        darshan_log_close(infile);
        darshan_log_close(outfile);
        return(-1);
    }

404 405 406
    darshan_log_close(infile);
    darshan_log_close(outfile);

407
    return(ret);
408 409
}

410 411 412 413 414 415 416 417
/*
 * Local variables:
 *  c-indent-level: 4
 *  c-basic-offset: 4
 * End:
 *
 * vim: ts=8 sts=4 sw=4 expandtab
 */