darshan-convert.c 7.3 KB
Newer Older
1
/*
Kevin Harms's avatar
Kevin Harms committed
2
 *  (C) 2011 by Argonne National Laboratory.
3 4 5 6 7 8 9 10 11 12 13 14 15 16
 *      See COPYRIGHT in top-level directory.
 */

#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>
17
#include <errno.h>
18 19 20

#include "darshan-logutils.h"

21
extern uint32_t darshan_hashlittle(const void *key, size_t length, uint32_t initval);
22 23 24 25 26 27

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");
28
    fprintf(stderr, "       --obfuscate Obfuscate items in the log.\n");
29 30
    fprintf(stderr, "       --key <key> Key to use when obfuscating.\n");
    fprintf(stderr, "       --annotate <string> Additional metadata to add.\n");
31
    fprintf(stderr, "       --file <hash> Limit output to specified (hashed) file only.\n");
32 33 34 35

    exit(1);
}

36
void parse_args (int argc, char **argv, char **infile, char **outfile,
37
                 int *obfuscate, int *key, char **annotate, uint64_t* hash)
38 39
{
    int index;
40 41
    int ret;

42 43
    static struct option long_opts[] =
    {
44
        {"annotate", 1, NULL, 'a'},
45 46
        {"obfuscate", 0, NULL, 'o'},
        {"key", 1, NULL, 'k'},
47
        {"file", 1, NULL, 'f'},
48 49 50
        {"help",  0, NULL, 0}
    };

51 52
    *hash = 0;

53 54 55 56 57 58 59 60
    while(1)
    {
        int c = getopt_long(argc, argv, "", long_opts, &index);

        if (c == -1) break;

        switch(c)
        {
61 62 63
            case 'a':
                *annotate = optarg;
                break;
64 65 66 67 68 69
            case 'o':
                *obfuscate = 1;
                break;
            case 'k':
                *key = atoi(optarg);
                break;
70 71 72 73 74
            case 'f':
                ret = sscanf(optarg, "%" PRIu64, hash);
                if(ret != 1)
                    usage(argv[0]);
                break;
75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95
            case 0:
            case '?':
            default:
                usage(argv[0]);
                break;
        }
    }

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

    return;
}

96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128
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;
}

129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145
void add_annotation (char *annotation,
                     struct darshan_job *job)
{
    char *token;
    char *save;

    for(token=strtok_r(annotation, "\t", &save);
        token != NULL;
        token=strtok_r(NULL, "\t", &save))
    {
        strcat(job->metadata, token);
        strcat(job->metadata, "\n");
    }

    return;
}

146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161
int main(int argc, char **argv)
{
    int ret;
    char *infile_name;
    char *outfile_name;
    struct darshan_job job;
    struct darshan_file cp_file;
    char tmp_string[1024];
    darshan_fd infile;
    darshan_fd outfile;
    int i;
    int mount_count;
    int64_t* devs;
    char** mnt_pts;
    char** fs_types;
    int last_rank = 0;
162 163
    int obfuscate = 0;
    int key = 0;
164
    char *annotation = NULL;
165
    uint64_t hash;
166

167
    parse_args(argc, argv, &infile_name, &outfile_name, &obfuscate, &key, &annotation, &hash);
168 169 170 171

    infile = darshan_log_open(infile_name, "r");
    if(!infile)
    {
172
        fprintf(stderr, "darshan_log_open() failed to open %s\n.", infile_name);
173 174 175 176 177 178 179 180 181
        return(-1);
    }
 
    /* TODO: safety check that outfile_name doesn't exist; we don't want to
     * overwrite something by accident.
     */
    outfile = darshan_log_open(outfile_name, "w");
    if(!outfile)
    {
182
        fprintf(stderr, "darshan_log_open() failed to open %s\n.", outfile_name);
183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199
        return(-1);
    }

    /* TODO: for now this tool is just reading the input file and throwing
     * away the data.  Need to write the log_put*() functions and use this
     * program as a test harness
     */
  
    /* 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);
        return(-1);
    }

200
    if (obfuscate) obfuscate_job(key, &job);
201
    if (annotation) add_annotation(annotation, &job);
202

203 204 205 206 207 208 209 210
    ret = darshan_log_putjob(outfile, &job);
    if (ret < 0)
    {
        fprintf(stderr, "Error: unable to write job information to log file.\n");
        darshan_log_close(outfile);
        return(-1);
    }

211
    ret = darshan_log_getexe(infile, tmp_string);
212 213 214 215 216 217
    if(ret < 0)
    {
        fprintf(stderr, "Error: unable to read trailing job information.\n");
        darshan_log_close(infile);
        return(-1);
    }
218

219 220
    if (obfuscate) obfuscate_exe(key, tmp_string);

221 222 223 224 225 226 227
    ret = darshan_log_putexe(outfile, tmp_string);
    if(ret < 0)
    {
        fprintf(stderr, "Error: unable to write trailing job information.\n");
        darshan_log_close(outfile);
        return(-1);
    }
228
   
229
    ret = darshan_log_getmounts(infile, &devs, &mnt_pts, &fs_types, &mount_count);
230 231 232 233 234 235 236
    if(ret < 0)
    {
        fprintf(stderr, "Error: unable to read trailing job information.\n");
        darshan_log_close(infile);
        return(-1);
    }

237 238 239 240 241 242 243 244
    ret = darshan_log_putmounts(outfile, devs, mnt_pts, fs_types, mount_count);
    if(ret < 0)
    {
        fprintf(stderr, "Error: unable to write mount information.\n");
        darshan_log_close(outfile);
        return(-1);
    }

245 246 247 248 249 250 251
    ret = darshan_log_getfile(infile, &job, &cp_file);
    if(ret < 0)
    {
        fprintf(stderr, "Error: failed to process log file.\n");
        fflush(stderr);
    }
    if(ret == 0)
252
    {
253
        goto done;
254 255
    }

256
    do
257 258 259 260 261 262 263 264 265
    {
        if(cp_file.rank != -1 && cp_file.rank < last_rank)
        {
            fprintf(stderr, "Error: log file contains out of order rank data.\n");
            fflush(stderr);
            return(-1);
        }
        if(cp_file.rank != -1)
            last_rank = cp_file.rank;
266

267
        if(!hash || hash == cp_file.hash)
268
        {
269 270 271 272 273 274 275 276
            if (obfuscate) obfuscate_file(key, &cp_file);

            ret = darshan_log_putfile(outfile, &job, &cp_file);
            if (ret < 0)
            {
                fprintf(stderr, "Error: failed to write file record.\n");
                break;
            }
277
        }
278
    } while((ret = darshan_log_getfile(infile, &job, &cp_file)) == 1);
279 280 281

    if(ret < 0)
    {
282
        fprintf(stderr, "Error: failed to process log file.\n");
283 284 285
        fflush(stderr);
    }

286
done:
287 288 289 290 291 292 293 294 295 296 297 298 299 300 301
    for(i=0; i<mount_count; i++)
    {
        free(mnt_pts[i]);
        free(fs_types[i]);
    }
    if(mount_count > 0)
    {
        free(devs);
        free(mnt_pts);
        free(fs_types);
    }
 
    darshan_log_close(infile);
    darshan_log_close(outfile);

302
    return(ret);
303 304
}

305