Re: What causes this error?
At Mon, 15 Nov 2010 18:03:23 -0600 Rhys Rhaven r...@rhavenindustrys.com wrote: Looks like the bug that I posted, which I believe Jean-Louis sent the patch for. I've been unable to test it as of yet. I compared my logs with your logs and it is much the same. I cannot find the patch you mentioned in the E-Mail archives. Can you (or Jean-Louis) re-post it? On 11/15/2010 04:11 PM, Robert Heller wrote: At Mon, 15 Nov 2010 15:34:31 -0500 Jean-Louis Martineaumartin...@zmanda.com wrote: Because ravel:/mnt/RAID0 was not dumped. Check the email report to know why or the client debug file (on ravel) The E-Mail report just says: FAILURE DUMP SUMMARY: ravel /mnt/RAID0 RESULTS MISSING ravel /mnt/RAID0 lev 1 FAILED [can't dump in degraded mode] And there isn't a sendbackup debug file for /mnt/RAID0. There are sendbackup debug files for the other file systems on ravel. There is a sendsize debug file for /mnt/RAID0 on ravel. Jean-Louis Robert Heller wrote: Using /var/log/amanda/60villagedrive/amdump.1 From Mon Nov 15 00:10:02 EST 2010 bach:/ 183m finished (0:17:59) haydn:/ 147m finished (0:20:35) ravel:/ 189m finished (0:20:36) ravel:/mnt/RAID0 1 816m failed: process terminated while waiting for dumping ravel:/mnt/sdb2 1 0m finished (0:20:34) .. This is in a CentOS 5.5 system: -sh-3.2$ rpm -qa amanda\* perl dump amanda-backup_server-3.2.0-1.rhel5 dump-0.4b41-4.el5 perl-5.8.8-32.el5_5.2 -- Robert Heller -- 978-544-6933 / hel...@deepsoft.com Deepwoods Software-- http://www.deepsoft.com/ () ascii ribbon campaign -- against html e-mail /\ www.asciiribbon.org -- against proprietary attachments
Re: What causes this error?
I attach the patch that was committed.
Jean-Louis
Robert Heller wrote:
At Mon, 15 Nov 2010 18:03:23 -0600 Rhys Rhaven r...@rhavenindustrys.com wrote:
Looks like the bug that I posted, which I believe Jean-Louis sent the
patch for. I've been unable to test it as of yet.
I compared my logs with your logs and it is much the same.
I cannot find the patch you mentioned in the E-Mail archives. Can you
(or Jean-Louis) re-post it?
Index: server-src/driver.c
===
--- server-src/driver.c (revision 3607)
+++ server-src/driver.c (revision 3608)
@@ -499,32 +499,10 @@
headqueue_disk(directq, diskp);
}
-/* handle any remaining dumps by dumping directly to tape, if possible */
-while(!empty(directq) taper_fd 0) {
- time_t sleep_time = 1;
- disk_t *sleep_diskp = NULL;
- time_t now = time(0);
+/* log error for any remaining dumps */
+while(!empty(directq)) {
+ diskp = dequeue_disk(directq);
- /* Find one we can do immediately or the sonner */
- for (diskp = directq.head; diskp != NULL; diskp = diskp-next) {
- if (diskp-to_holdingdisk == HOLD_REQUIRED ||
- degraded_mode) {
- sleep_time = 0;
- sleep_diskp = diskp;
- } else if (diskp-host-start_t - now sleep_time
- diskp-start_t -now sleep_time) {
- if (diskp-host-start_t diskp-start_t)
- sleep_time = diskp-host-start_t - now;
- else
- sleep_time = diskp-start_t - now;
- sleep_diskp = diskp;
- }
- }
- diskp = sleep_diskp;
- if (sleep_time 0)
- sleep(sleep_time);
- remove_disk(directq, diskp);
-
if (diskp-to_holdingdisk == HOLD_REQUIRED) {
char *qname = quote_string(diskp-name);
log_add(L_FAIL, %s %s %s %d [%s],
@@ -538,7 +516,7 @@
log_add(L_FAIL, %s %s %s %d [%s],
diskp-host-hostname, qname, sched(diskp)-datestamp,
sched(diskp)-level,
- _(can't dump in degraded mode));
+ _(can't dump in non degraded mode));
amfree(qname);
}
else {
@@ -555,10 +533,6 @@
}
}
-/* fill up the tape or start new one for taperflush */
-startaflush();
-event_loop(0);
-
short_dump_state();/* for amstatus */
g_printf(_(driver: QUITTING time %s telling children to quit\n),
@@ -1044,6 +1018,7 @@
enqueue_disk(directq, diskp);
diskp-to_holdingdisk = HOLD_NEVER;
}
+ if (empty(*rq)) force_flush = 1;
}
} else if (client_constrained(diskp)) {
free_assignedhd(holdp);
@@ -1326,6 +1301,7 @@
dumper_cmd(dumper, PORT_DUMP, diskp, NULL);
}
diskp-host-start_t = now + 15;
+ if (empty(*rq)) force_flush = 1;
if (result_argv)
g_strfreev(result_argv);
@@ -2114,6 +2090,7 @@
dp-inprogress = 0;
deallocate_bandwidth(dp-host-netif, sched(dp)-est_kps);
taper-dumper = NULL;
+taper-disk = NULL;
sched(dp)-dumper = NULL;
sched(dp)-taper = NULL;
start_some_dumps(runq);
@@ -2759,7 +2736,7 @@
continue;
}
- if(file.dumplevel 0 || file.dumplevel 9) {
+ if (file.dumplevel 0 || file.dumplevel 399) {
log_add(L_INFO, _(%s: ignoring file with bogus dump level %d.),
destname, file.dumplevel);
amfree(destname);
@@ -2825,6 +2802,8 @@
if (!nodump) {
schedule_ev_read = event_register((event_id_t)0, EV_READFD,
read_schedule, NULL);
+} else {
+ force_flush = 1;
}
}
@@ -3137,6 +3116,7 @@
log_add(L_WARNING, _(WARNING: got empty schedule from planner));
if(need_degraded==1) start_degraded_mode(runq);
schedule_done = 1;
+if (empty(runq)) force_flush = 1;
start_some_dumps(runq);
startaflush();
}
@@ -3805,13 +3785,9 @@
}
// when to start a flush
-// We don't start a flush if taper_tape_started == 1 dump_to_disk_terminated force_flush == 0,
-// it is a criteria need to exit the first event_loop without flushing everything to tape,
-// they will be flush in another event_loop.
if (taper-state TAPER_STATE_IDLE) {
if (!degraded_mode (!empty(tapeq) || !empty(directq))
- (((taper-state TAPER_STATE_TAPE_STARTED)
- force_flush == 1) ||// if tape already started and force_flush
+ (taper-state TAPER_STATE_TAPE_STARTED || // tape already started
!empty(roomq) || // holding disk constraint
idle_reason == IDLE_NO_DISKSPACE || // holding disk constraint
(my_flush_threshold_dumped tapeq_size // flush-threshold-dumped
What causes this error?
Using /var/log/amanda/60villagedrive/amdump.1 From Mon Nov 15 00:10:02 EST 2010 bach:/ 183m finished (0:17:59) haydn:/ 147m finished (0:20:35) ravel:/ 189m finished (0:20:36) ravel:/mnt/RAID0 1 816m failed: process terminated while waiting for dumping ravel:/mnt/sdb2 1 0m finished (0:20:34) .. This is in a CentOS 5.5 system: -sh-3.2$ rpm -qa amanda\* perl dump amanda-backup_server-3.2.0-1.rhel5 dump-0.4b41-4.el5 perl-5.8.8-32.el5_5.2 -- Robert Heller -- 978-544-6933 / hel...@deepsoft.com Deepwoods Software-- http://www.deepsoft.com/ () ascii ribbon campaign -- against html e-mail /\ www.asciiribbon.org -- against proprietary attachments
Re: What causes this error?
Because ravel:/mnt/RAID0 was not dumped. Check the email report to know why or the client debug file (on ravel) Jean-Louis Robert Heller wrote: Using /var/log/amanda/60villagedrive/amdump.1 From Mon Nov 15 00:10:02 EST 2010 bach:/ 183m finished (0:17:59) haydn:/ 147m finished (0:20:35) ravel:/ 189m finished (0:20:36) ravel:/mnt/RAID0 1 816m failed: process terminated while waiting for dumping ravel:/mnt/sdb2 1 0m finished (0:20:34) .. This is in a CentOS 5.5 system: -sh-3.2$ rpm -qa amanda\* perl dump amanda-backup_server-3.2.0-1.rhel5 dump-0.4b41-4.el5 perl-5.8.8-32.el5_5.2
Re: What causes this error?
At Mon, 15 Nov 2010 15:34:31 -0500 Jean-Louis Martineau martin...@zmanda.com wrote: Because ravel:/mnt/RAID0 was not dumped. Check the email report to know why or the client debug file (on ravel) The E-Mail report just says: FAILURE DUMP SUMMARY: ravel /mnt/RAID0 RESULTS MISSING ravel /mnt/RAID0 lev 1 FAILED [can't dump in degraded mode] And there isn't a sendbackup debug file for /mnt/RAID0. There are sendbackup debug files for the other file systems on ravel. There is a sendsize debug file for /mnt/RAID0 on ravel. Jean-Louis Robert Heller wrote: Using /var/log/amanda/60villagedrive/amdump.1 From Mon Nov 15 00:10:02 EST 2010 bach:/ 183m finished (0:17:59) haydn:/ 147m finished (0:20:35) ravel:/ 189m finished (0:20:36) ravel:/mnt/RAID0 1 816m failed: process terminated while waiting for dumping ravel:/mnt/sdb2 1 0m finished (0:20:34) .. This is in a CentOS 5.5 system: -sh-3.2$ rpm -qa amanda\* perl dump amanda-backup_server-3.2.0-1.rhel5 dump-0.4b41-4.el5 perl-5.8.8-32.el5_5.2 -- Robert Heller -- 978-544-6933 / hel...@deepsoft.com Deepwoods Software-- http://www.deepsoft.com/ () ascii ribbon campaign -- against html e-mail /\ www.asciiribbon.org -- against proprietary attachments
Re: What causes this error?
Looks like the bug that I posted, which I believe Jean-Louis sent the patch for. I've been unable to test it as of yet. On 11/15/2010 04:11 PM, Robert Heller wrote: At Mon, 15 Nov 2010 15:34:31 -0500 Jean-Louis Martineaumartin...@zmanda.com wrote: Because ravel:/mnt/RAID0 was not dumped. Check the email report to know why or the client debug file (on ravel) The E-Mail report just says: FAILURE DUMP SUMMARY: ravel /mnt/RAID0 RESULTS MISSING ravel /mnt/RAID0 lev 1 FAILED [can't dump in degraded mode] And there isn't a sendbackup debug file for /mnt/RAID0. There are sendbackup debug files for the other file systems on ravel. There is a sendsize debug file for /mnt/RAID0 on ravel. Jean-Louis Robert Heller wrote: Using /var/log/amanda/60villagedrive/amdump.1 From Mon Nov 15 00:10:02 EST 2010 bach:/ 183m finished (0:17:59) haydn:/ 147m finished (0:20:35) ravel:/ 189m finished (0:20:36) ravel:/mnt/RAID0 1 816m failed: process terminated while waiting for dumping ravel:/mnt/sdb2 1 0m finished (0:20:34) .. This is in a CentOS 5.5 system: -sh-3.2$ rpm -qa amanda\* perl dump amanda-backup_server-3.2.0-1.rhel5 dump-0.4b41-4.el5 perl-5.8.8-32.el5_5.2
