1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369
|
/*
* hashstats.c
*
* Copyright (C) 2014 SUSE. All rights reserved.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public
* License version 2 as published by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* General Public License for more details.
*/
#include <limits.h>
#include <stdio.h>
#include <stdint.h>
#include <stddef.h>
#include <stdlib.h>
#include <errno.h>
#include <string.h>
#include <getopt.h>
#include <inttypes.h>
#include "rbtree.h"
#include "list.h"
#include "csum.h"
#include "filerec.h"
#include "hash-tree.h"
#include "util.h"
#include "dbfile.h"
#include "bswap.h"
extern sqlite3 *gdb;
unsigned int blocksize;
int v2_hashfile = 0;
static int version_only = 0;
static int print_all_hashes = 0;
static int print_blocks = 0;
static int num_to_print = 10;
static int print_file_list = 0;
static char *serialize_fname = NULL;
static struct dbfile_config dbfile_cfg;
static sqlite3_stmt *top_hashes_stmt = NULL;
static sqlite3_stmt *files_count_stmt = NULL;
static sqlite3_stmt *find_blocks_stmt = NULL;
/* dirty hack so we don't have to add file_scan.o to hashstats */
int add_file_db(const char *filename, uint64_t inum, uint64_t subvolid,
uint64_t size, uint64_t mtime, unsigned int seq, int *delete)
{
return 0;
}
static int prepare_statements(void)
{
int ret;
#define FIND_TOP_HASHES \
"select digest, count(digest) from hashes group by digest having (count(digest) > 1) order by (count(digest)) desc;"
ret = sqlite3_prepare_v2(gdb, FIND_TOP_HASHES, -1, &top_hashes_stmt,
NULL);
if (ret) {
fprintf(stderr, "error %d while prepping hash search stmt: %s\n",
ret, sqlite3_errstr(ret));
return ret;
}
#define FIND_FILES_COUNT \
"select count (distinct files.filename) from files INNER JOIN hashes on hashes.digest = ?1 AND files.subvol=hashes.subvol AND files.ino=hashes.ino;"
ret = sqlite3_prepare_v2(gdb, FIND_FILES_COUNT, -1, &files_count_stmt,
NULL);
if (ret) {
fprintf(stderr, "error %d while preparing file count stmt: %s\n",
ret, sqlite3_errstr(ret));
return ret;
}
#define FIND_BLOCKS \
"select files.filename, hashes.loff, hashes.flags from files INNER JOIN hashes on hashes.digest = ?1 AND files.subvol=hashes.subvol AND files.ino=hashes.ino;"
ret = sqlite3_prepare_v2(gdb, FIND_BLOCKS, -1, &find_blocks_stmt, NULL);
if (ret) {
fprintf(stderr, "error %d while prepping find blocks stmt: %s\n",
ret, sqlite3_errstr(ret));
return ret;
}
return 0;
}
static void finalize_statements(void)
{
sqlite3_finalize(top_hashes_stmt);
sqlite3_finalize(files_count_stmt);
sqlite3_finalize(find_blocks_stmt);
}
static void printf_file_block_flags(unsigned int flags)
{
if (!flags)
return;
printf("( ");
if (flags & FILE_BLOCK_SKIP_COMPARE)
printf("skip_compare ");
if (flags & FILE_BLOCK_DEDUPED)
printf("deduped ");
if (flags & FILE_BLOCK_HOLE)
printf("hole ");
if (flags & FILE_BLOCK_PARTIAL)
printf("partial ");
printf(")");
}
static int print_all_blocks(unsigned char *digest)
{
int ret;
uint64_t loff;
unsigned int flags;
const unsigned char *filename;
ret = sqlite3_bind_blob(find_blocks_stmt, 1, digest, digest_len,
SQLITE_STATIC);
if (ret) {
fprintf(stderr, "Error %d binding digest for blocks: %s\n", ret,
sqlite3_errstr(ret));
return ret;
}
while ((ret = sqlite3_step(find_blocks_stmt)) == SQLITE_ROW) {
filename = sqlite3_column_text(find_blocks_stmt, 0);
loff = sqlite3_column_int64(find_blocks_stmt, 1);
flags = sqlite3_column_int(find_blocks_stmt, 2);
printf(" %s\tloff: %llu lblock: %llu "
"flags: 0x%x ", filename,
(unsigned long long)loff,
(unsigned long long)loff / blocksize,
flags);
printf_file_block_flags(flags);
printf("\n");
}
if (ret != SQLITE_DONE) {
fprintf(stderr,
"error %d running block stmt: %s\n",
ret, sqlite3_errstr(ret));
return ret;
}
sqlite3_reset(find_blocks_stmt);
return 0;
}
static void print_by_size(void)
{
int ret;
int header_printed = 0;
unsigned char *digest;
uint64_t count, files_count;
if (print_all_hashes)
printf("Print all hashes ");
else
printf("Print top %d hashes ", num_to_print);
printf("(this may take some time)\n");
while ((ret = sqlite3_step(top_hashes_stmt)) == SQLITE_ROW) {
digest = (unsigned char *)sqlite3_column_blob(top_hashes_stmt, 0);
count = sqlite3_column_int64(top_hashes_stmt, 1);
ret = sqlite3_bind_blob(files_count_stmt, 1, digest, digest_len,
SQLITE_STATIC);
if (ret) {
fprintf(stderr, "Error %d binding digest: %s\n", ret,
sqlite3_errstr(ret));
return;
}
ret = sqlite3_step(files_count_stmt);
if (ret != SQLITE_ROW && ret != SQLITE_DONE) {
fprintf(stderr, "error %d, file count search: %s\n",
ret, sqlite3_errstr(ret));
return;
}
files_count = sqlite3_column_int64(files_count_stmt, 0);
if (!header_printed) {
printf("Hash, # Blocks, # Files\n");
header_printed = 1;
}
debug_print_digest(stdout, digest);
printf(", %"PRIu64", %"PRIu64"\n", count, files_count);
sqlite3_reset(files_count_stmt);
if (print_blocks) {
ret = print_all_blocks(digest);
if (ret)
return;
}
if (!print_all_hashes && --num_to_print == 0) {
ret = SQLITE_DONE;
break;
}
}
if (ret != SQLITE_DONE) {
fprintf(stderr, "error %d retrieving hashes from table: %s\n",
ret, sqlite3_errstr(ret));
}
}
static int print_files_cb(void *priv, int argc, char **argv, char **column)
{
int i;
for(i = 0; i < argc; i++)
printf("%s\t", argv[i]);
printf("\n");
return 0;
}
static void print_filerecs(void)
{
int ret;
char *errorstr;
#define LIST_FILES \
"select ino, subvol, blocks, size, filename from files;"
printf("Showing %"PRIu64" files.\nInode\tSubvol ID\tBlocks Stored\tSize\tFilename\n",
dbfile_cfg.num_files);
ret = sqlite3_exec(gdb, LIST_FILES, print_files_cb, gdb, &errorstr);
if (ret) {
fprintf(stderr, "error %d, executing file search: %s\n", ret,
errorstr);
return;
}
}
static void print_file_info(void)
{
printf("Raw header info for \"%s\":\n", serialize_fname);
printf(" version: %d.%d\tblock_size: %u\n", dbfile_cfg.major,
dbfile_cfg.minor, dbfile_cfg.blocksize);
printf(" num_files: %"PRIu64"\tnum_hashes: %"PRIu64"\n",
dbfile_cfg.num_files, dbfile_cfg.num_hashes);
}
static void usage(const char *prog)
{
printf("hashstats %s\n", VERSTRING);
if (version_only)
return;
printf("Print information about duperemove hashes.\n\n");
printf("Usage: %s [-n NUM] [-a] [-b] [-l] hashfile\n", prog);
printf("Where \"hashfile\" is a file generated by running duperemove\n");
printf("with the '--write-hashes' option. By default a list of hashes\n");
printf("with the most shared blocks are printed.\n");
printf("\n\t<switches>\n");
printf("\t-n NUM\t\tPrint top N hashes, sorted by bucket size.\n");
printf("\t \t\tDefault is 10.\n");
printf("\t-a\t\tPrint all hashes (overrides '-n', above)\n");
printf("\t-b\t\tPrint info on each block within our hash buckets\n");
printf("\t-l\t\tPrint a list of all files\n");
printf("\t--help\t\tPrints this help text.\n");
}
enum {
HELP_OPTION = CHAR_MAX + 1,
VERSION_OPTION,
HASH_OPTION,
};
static int parse_options(int argc, char **argv)
{
int c;
static struct option long_ops[] = {
{ "help", 0, 0, HELP_OPTION },
{ "version", 0, 0, VERSION_OPTION },
{ 0, 0, 0, 0}
};
if (argc < 2)
return 1;
while ((c = getopt_long(argc, argv, "labn:?", long_ops, NULL))
!= -1) {
switch (c) {
case 'l':
print_file_list = 1;
break;
case 'a':
print_all_hashes = 1;
break;
case 'b':
print_blocks = 1;
break;
case 'n':
num_to_print = atoi(optarg);
break;
case VERSION_OPTION:
version_only = 1;
return 1;
case HELP_OPTION:
case '?':
default:
version_only = 0;
return 1;
}
}
if ((argc - optind) != 1)
return 1;
serialize_fname = argv[optind];
return 0;
}
int main(int argc, char **argv)
{
int ret;
struct hash_tree tree;
init_filerec();
init_hash_tree(&tree);
if (parse_options(argc, argv)) {
usage(argv[0]);
return EINVAL;
}
if (init_csum_module(DEFAULT_HASH_STR))
return ENOMEM;
ret = dbfile_open(serialize_fname, &dbfile_cfg);
if (ret)
return ret;
blocksize = dbfile_cfg.blocksize;
ret = prepare_statements();
if (ret)
return ret;
print_file_info();
if (num_to_print || print_all_hashes)
print_by_size();
if (print_file_list)
print_filerecs();
finalize_statements();
dbfile_close();
return ret;
}
|