RepoMirrors/mars
1
0
Fork 0
mirror of https://github.com/schoebel/mars synced 2025-01-28 18:23:25 +00:00
Code Issues Packages Projects Releases Wiki Activity

light: fix becoming primary when logfiles are damaged

Browse Source 
When logfile replay aborts with an error, becoming primary would be
impossible.
Without this, repair would be only possible by complete destruction
of the resource.

A previous version of this patch introduced
/proc/sys/mars/allow_primary_when_damaged which would complicate
the sysadmin interface. People would be unsure what to do.
This commit is contained in:
Thomas Schoebel-Theuer 2014-09-06 17:58:37 +02:00 committed by Thomas Schoebel-Theuer
parent 69386b33d9
commit d67336420d
1 changed files with 7 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
kernel/sy_old/mars_light.c
View File

@ -572,6 +572,7 @@ struct mars_rotate {
bool has_emergency;
bool wants_sync;
bool gets_sync;
bool log_is_really_damaged;
spinlock_t inf_lock;
bool infs_is_dirty[MAX_INFOS];
struct trans_logger_info infs[MAX_INFOS];
@ -3154,7 +3155,9 @@ int _check_logging_status(struct mars_rotate *rot, int *log_nr, long long *oldpo
status = 0;
if (rot->aio_info.current_size > *oldpos_start) {
if (rot->aio_info.current_size - *oldpos_start < REPLAY_TOLERANCE &&
if ((rot->aio_info.current_size - *oldpos_start < REPLAY_TOLERANCE ||
(rot->log_is_really_damaged &&
rot->todo_primary)) &&
(rot->todo_primary ||
(rot->relevant_log &&
rot->next_relevant_log &&
@ -3235,7 +3238,7 @@ int _make_logging_status(struct mars_rotate *rot)
* Allow switching over to a new logfile.
*/
if (!trans_brick->power.button && !trans_brick->power.led_on && trans_brick->power.led_off) {
if (rot->next_relevant_log) {
if (rot->next_relevant_log && !rot->log_is_really_damaged) {
int replay_tolerance = _get_tolerance(rot);
bool skip_new = !!rot->todo_primary;
MARS_DBG("check switchover from '%s' to '%s' (size = %lld, skip_new = %d, replay_tolerance = %d)\n", dent->d_path, rot->next_relevant_log->d_path, rot->next_relevant_log->new_stat.size, skip_new, replay_tolerance);
@ -3678,7 +3681,7 @@ int make_log_finalize(struct mars_global *global, struct mars_dent *dent)
make_rot_msg(rot, "wrn-space-low", "EMERGENCY: the space on /mars/ is becoming low.");
}
rot->log_is_really_damaged = false;
if (trans_brick->replay_mode) {
if (trans_brick->replay_code > 0) {
MARS_INF_TO(rot->log_say, "logfile replay ended successfully at position %lld\n", trans_brick->replay_current_pos);
@ -3688,6 +3691,7 @@ int make_log_finalize(struct mars_global *global, struct mars_dent *dent)
} else if (trans_brick->replay_code < 0) {
MARS_ERR_TO(rot->log_say, "logfile replay stopped with error = %d at position %lld\n", trans_brick->replay_code, trans_brick->replay_current_pos);
make_rot_msg(rot, "err-replay-stop", "logfile replay stopped with error = %d at position %lld", trans_brick->replay_code, trans_brick->replay_current_pos);
rot->log_is_really_damaged = true;
}
}