#include <signal.h>
#include <sys/mman.h>
+enum repair {
+ NO_REPAIR = 0,
+ MANUAL_REPAIR,
+ AUTO_REPAIR
+};
+
int geo_map(int block, unsigned long long stripe, int raid_disks,
int level, int layout);
void qsyndrome(uint8_t *p, uint8_t *q, uint8_t **sources, int disks, int size);
uint8_t **ptrs);
void xor_blocks(char *target, char **sources, int disks, int size);
-
/* Collect per stripe consistency information */
void raid6_collect(int chunk_size, uint8_t *p, uint8_t *q,
char *chunkP, char *chunkQ, int *results)
return curr_broken_disk;
}
+int lock_stripe(struct mdinfo *info, unsigned long long start,
+ int chunk_size, int data_disks, sighandler_t *sig) {
+ int rv;
+ if(mlockall(MCL_CURRENT | MCL_FUTURE) != 0) {
+ return 2;
+ }
+
+ sig[0] = signal(SIGTERM, SIG_IGN);
+ sig[1] = signal(SIGINT, SIG_IGN);
+ sig[2] = signal(SIGQUIT, SIG_IGN);
+
+ rv = sysfs_set_num(info, NULL, "suspend_lo", start * chunk_size * data_disks);
+ rv |= sysfs_set_num(info, NULL, "suspend_hi", (start + 1) * chunk_size * data_disks);
+ return rv * 256;
+}
+
+int unlock_all_stripes(struct mdinfo *info, sighandler_t *sig) {
+ int rv;
+ rv = sysfs_set_num(info, NULL, "suspend_lo", 0x7FFFFFFFFFFFFFFFULL);
+ rv |= sysfs_set_num(info, NULL, "suspend_hi", 0);
+ rv |= sysfs_set_num(info, NULL, "suspend_lo", 0);
+
+ signal(SIGQUIT, sig[2]);
+ signal(SIGINT, sig[1]);
+ signal(SIGTERM, sig[0]);
+
+ if(munlockall() != 0)
+ return 3;
+ return rv * 256;
+}
+
int check_stripes(struct mdinfo *info, int *source, unsigned long long *offsets,
int raid_disks, int chunk_size, int level, int layout,
unsigned long long start, unsigned long long length, char *name[],
- int repair, int failed_disk1, int failed_disk2)
+ enum repair repair, int failed_disk1, int failed_disk2)
{
/* read the data and p and q blocks, and check we got them right */
char *stripe_buf = xmalloc(raid_disks * chunk_size);
uint8_t *p = xmalloc(chunk_size);
uint8_t *q = xmalloc(chunk_size);
int *results = xmalloc(chunk_size * sizeof(int));
+ sighandler_t *sig = xmalloc(3 * sizeof(sighandler_t));
int i;
int diskP, diskQ;
int data_disks = raid_disks - 2;
int err = 0;
- sighandler_t sig[3];
- int rv;
extern int tables_ready;
printf("pos --> %llu\n", start);
- if(mlockall(MCL_CURRENT | MCL_FUTURE) != 0) {
- err = 2;
+ err = lock_stripe(info, start, chunk_size, data_disks, sig);
+ if(err != 0) {
+ if (err != 2)
+ unlock_all_stripes(info, sig);
goto exitCheck;
}
- sig[0] = signal(SIGTERM, SIG_IGN);
- sig[1] = signal(SIGINT, SIG_IGN);
- sig[2] = signal(SIGQUIT, SIG_IGN);
- rv = sysfs_set_num(info, NULL, "suspend_lo", start * chunk_size * data_disks);
- rv |= sysfs_set_num(info, NULL, "suspend_hi", (start + 1) * chunk_size * data_disks);
for (i = 0 ; i < raid_disks ; i++) {
- lseek64(source[i], offsets[i] + start * chunk_size, 0);
- read(source[i], stripes[i], chunk_size);
- }
- rv |= sysfs_set_num(info, NULL, "suspend_lo", 0x7FFFFFFFFFFFFFFFULL);
- rv |= sysfs_set_num(info, NULL, "suspend_hi", 0);
- rv |= sysfs_set_num(info, NULL, "suspend_lo", 0);
- signal(SIGQUIT, sig[2]);
- signal(SIGINT, sig[1]);
- signal(SIGTERM, sig[0]);
- if(munlockall() != 0) {
- err = 3;
- goto exitCheck;
+ off64_t seek_res = lseek64(source[i], offsets[i] + start * chunk_size,
+ SEEK_SET);
+ if (seek_res < 0) {
+ fprintf(stderr, "lseek to source %d failed\n", i);
+ unlock_all_stripes(info, sig);
+ err = -1;
+ goto exitCheck;
+ }
+ int read_res = read(source[i], stripes[i], chunk_size);
+ if (read_res < chunk_size) {
+ fprintf(stderr, "Failed to read complete chunk disk %d, aborting\n", i);
+ unlock_all_stripes(info, sig);
+ err = -1;
+ goto exitCheck;
+ }
}
-
- if(rv != 0) {
- err = rv * 256;
+ err = unlock_all_stripes(info, sig);
+ if(err != 0)
goto exitCheck;
- }
for (i = 0 ; i < data_disks ; i++) {
int disk = geo_map(i, start, raid_disks, level, layout);
if(disk == -65535) {
printf("Error detected at %llu: disk slot unknown\n", start);
}
- if(repair == 1) {
+ if(repair == MANUAL_REPAIR) {
printf("Repairing stripe %llu\n", start);
printf("Assuming slots %d (%s) and %d (%s) are incorrect\n",
failed_disk1, name[failed_disk1],
raid6_2data_recov(raid_disks, chunk_size, failed_block_index1, failed_block_index2, (uint8_t**)blocks);
}
}
- if(mlockall(MCL_CURRENT | MCL_FUTURE) != 0) {
- err = 2;
+
+ err = lock_stripe(info, start, chunk_size, data_disks, sig);
+ if(err != 0) {
+ if (err != 2)
+ unlock_all_stripes(info, sig);
+ goto exitCheck;
+ }
+
+ int write_res1, write_res2;
+ off64_t seek_res;
+
+ seek_res = lseek64(source[failed_disk1],
+ offsets[failed_disk1] + start * chunk_size, SEEK_SET);
+ if (seek_res < 0) {
+ fprintf(stderr, "lseek failed for failed_disk1\n");
+ unlock_all_stripes(info, sig);
+ err = -1;
goto exitCheck;
}
- sig[0] = signal(SIGTERM, SIG_IGN);
- sig[1] = signal(SIGINT, SIG_IGN);
- sig[2] = signal(SIGQUIT, SIG_IGN);
- rv = sysfs_set_num(info, NULL, "suspend_lo", start * chunk_size * data_disks);
- rv |= sysfs_set_num(info, NULL, "suspend_hi", (start + 1) * chunk_size * data_disks);
- lseek64(source[failed_disk1], offsets[failed_disk1] + start * chunk_size, 0);
- write(source[failed_disk1], stripes[failed_disk1], chunk_size);
- lseek64(source[failed_disk2], offsets[failed_disk2] + start * chunk_size, 0);
- write(source[failed_disk2], stripes[failed_disk2], chunk_size);
- rv |= sysfs_set_num(info, NULL, "suspend_lo", 0x7FFFFFFFFFFFFFFFULL);
- rv |= sysfs_set_num(info, NULL, "suspend_hi", 0);
- rv |= sysfs_set_num(info, NULL, "suspend_lo", 0);
- signal(SIGQUIT, sig[2]);
- signal(SIGINT, sig[1]);
- signal(SIGTERM, sig[0]);
- if(munlockall() != 0) {
- err = 3;
+ write_res1 = write(source[failed_disk1], stripes[failed_disk1], chunk_size);
+
+ seek_res = lseek64(source[failed_disk2],
+ offsets[failed_disk2] + start * chunk_size, SEEK_SET);
+ if (seek_res < 0) {
+ fprintf(stderr, "lseek failed for failed_disk1\n");
+ unlock_all_stripes(info, sig);
+ err = -1;
goto exitCheck;
}
+ write_res2 = write(source[failed_disk2], stripes[failed_disk2], chunk_size);
+
+ err = unlock_all_stripes(info, sig);
+ if(err != 0)
+ goto exitCheck;
- if(rv != 0) {
- err = rv * 256;
+ if (write_res1 != chunk_size || write_res2 != chunk_size) {
+ fprintf(stderr, "Failed to write a complete chunk.\n");
goto exitCheck;
}
- }
+ } else if (disk >= 0 && repair == AUTO_REPAIR) {
+ printf("Auto-repairing slot %d (%s)\n", disk, name[disk]);
+ if (disk == diskQ) {
+ qsyndrome(p, (uint8_t*)stripes[diskQ], (uint8_t**)blocks, data_disks, chunk_size);
+ } else {
+ char *all_but_failed_blocks[data_disks];
+ int failed_block_index = block_index_for_slot[disk];
+ for (i=0; i < data_disks; i++)
+ if (failed_block_index == i)
+ all_but_failed_blocks[i] = stripes[diskP];
+ else
+ all_but_failed_blocks[i] = blocks[i];
+ xor_blocks(stripes[disk],
+ all_but_failed_blocks, data_disks, chunk_size);
+ }
+
+ err = lock_stripe(info, start, chunk_size, data_disks, sig);
+ if(err != 0) {
+ if (err != 2)
+ unlock_all_stripes(info, sig);
+ goto exitCheck;
+ }
+
+ lseek64(source[disk], offsets[disk] + start * chunk_size, 0);
+ int write_res = write(source[disk], stripes[disk], chunk_size);
+
+ err = unlock_all_stripes(info, sig);
+ if(err != 0 || write_res != chunk_size)
+ goto exitCheck;
+
+ if (write_res != chunk_size) {
+ fprintf(stderr, "Failed to write a full chunk.\n");
+ goto exitCheck;
+ }
+ }
length--;
start++;
free(stripe_buf);
free(stripes);
free(blocks);
+ free(block_index_for_slot);
free(p);
free(q);
free(results);
+ free(sig);
return err;
}
int chunk_size = 0;
int layout = -1;
int level = 6;
- int repair = 0;
- int failed_disk1, failed_disk2;
+ enum repair repair = NO_REPAIR;
+ int failed_disk1 = -1;
+ int failed_disk2 = -1;
unsigned long long start, length;
int i;
int mdfd;
prg++;
if (argc < 4) {
- fprintf(stderr, "Usage: %s md_device start_stripe length_stripes\n", prg);
+ fprintf(stderr, "Usage: %s md_device start_stripe length_stripes [autorepair]\n", prg);
fprintf(stderr, " or: %s md_device repair stripe failed_slot_1 failed_slot_2\n", prg);
exit_err = 1;
goto exitHere;
goto exitHere;
}
- info = sysfs_read(mdfd, -1,
+ info = sysfs_read(mdfd, NULL,
GET_LEVEL|
GET_LAYOUT|
GET_DISKS|
exit_err = 1;
goto exitHere;
}
- repair = 1;
+ repair = MANUAL_REPAIR;
start = getnum(argv[3], &err);
length = 1;
failed_disk1 = getnum(argv[4], &err);
else {
start = getnum(argv[2], &err);
length = getnum(argv[3], &err);
+ if (argc >= 5 && strcmp(argv[4], "autorepair")==0)
+ repair = AUTO_REPAIR;
}
if (err) {
projects / thirdparty / mdadm.git / blobdiff