runtime: publish SUPPORT-260928-HOMELAB-BACKUP-ALERT-SPAM-CURRENT-RCA-1237R1
This commit is contained in:
File diff suppressed because one or more lines are too long
@@ -0,0 +1,455 @@
|
|||||||
|
CHAT_OUTPUT_BEGIN
|
||||||
|
COMMAND_ID=SUPPORT-260928-HOMELAB-BACKUP-ALERT-SPAM-CURRENT-RCA-1237R1
|
||||||
|
STATUS=OK
|
||||||
|
RC=0
|
||||||
|
HOST=pve01
|
||||||
|
MODE=read-only
|
||||||
|
COMPONENT=homelab-backup-alert-spam-current-rca
|
||||||
|
REFERENCE_REGISTER_CHECK=OK
|
||||||
|
REFERENCE_SHA256=5a3d8e5154c41cb582a4e0aca68090be1f0138918bf82131a948df326f9d8d66
|
||||||
|
ERROR_REGISTER_CHECK=OK
|
||||||
|
ERROR_REGISTER_SHA256=3b09a553ec0f527ed3afeed4753f52a74ee3036045bbfb3c685e9f8af4ba7ba0
|
||||||
|
COMMAND_SHA256=e205fb5749bd8d2a466e79a56e8d9f3a66537e7dcbd1c635202ab6df607b736b
|
||||||
|
DUPLICATE_FAILED_COMMAND_BLOCKED=false
|
||||||
|
EXECUTION_STARTED=true
|
||||||
|
CHANGE_DECLARED=false
|
||||||
|
RESULT_CONTRACT_VALID=true
|
||||||
|
RESULT_CONTRACT_STATUS=NOT_APPLICABLE
|
||||||
|
RESULT_CONTRACT_ERROR=NONE
|
||||||
|
COMMAND_RC=0
|
||||||
|
CHANGES_MADE=false
|
||||||
|
ROLLBACK_STARTED=false
|
||||||
|
ROLLBACK_RESTORED=null
|
||||||
|
MUTATION_OUTCOME=NO_MUTATION
|
||||||
|
SANITIZED=yes
|
||||||
|
SECRETS_INCLUDED=no
|
||||||
|
PRIVATE_ADDRESSES_INCLUDED=no
|
||||||
|
RAW_EVIDENCE_SHA256=c64c77856d1b796c0414be59dd0089c9687ec505d26bb8b4111ab68ee967e5a2
|
||||||
|
SANITIZED_OUTPUT_SHA256=c64c77856d1b796c0414be59dd0089c9687ec505d26bb8b4111ab68ee967e5a2
|
||||||
|
OUTPUT_BEGIN
|
||||||
|
BACKUP_ALERT_SPAM_CURRENT_RCA_BEGIN=true
|
||||||
|
COMMAND_ID=SUPPORT-260928-HOMELAB-BACKUP-ALERT-SPAM-CURRENT-RCA-1237R1
|
||||||
|
MODE=read-only
|
||||||
|
COMPONENT=homelab-backup-alert-spam-current-rca
|
||||||
|
MUTATION_BOUNDARY=READ_ONLY_ALERT_HEALTH_STATE_SOURCE_JOURNAL_LOCK_AND_QUIET_AUDIT;NO_ALERT_EXECUTION;NO_MAIL;NO_BACKUP;NO_CONFIG_WRITE;NO_WRAPPER_WRITE;NO_RELEASE_WRITE;NO_SYSTEMD_ACTION;NO_TIMER_CHANGE;NO_HEALTH_WRITE;NO_GIT_WRITE;NO_RETENTION;NO_DELETE;NO_RESTORE;NO_NETBIRD_SKLADCHIK_CHANGE
|
||||||
|
=== AUTHORITY ===
|
||||||
|
HOST=pve01
|
||||||
|
CLUSTER_QUORATE=Yes
|
||||||
|
RUNNER_SHA256=b248a4c32c9cc64e5747e7dce6c7fc0a23f5124a77c71ce72e27a81aceae9d2d
|
||||||
|
SOURCE_1236_STATUS=OK
|
||||||
|
SOURCE_1236_RC=0
|
||||||
|
SOURCE_1236_CHANGES_MADE=false
|
||||||
|
SOURCE_1236_DECISION=HOLD_1236_V2_SERVICE_LAST_RUN_NOT_SUCCESS
|
||||||
|
SOURCE_1236_NEXT_GATE=RECONCILE_POST_RECOVERY_SCHEDULER
|
||||||
|
SOURCE_1236_POST_RECOVERY_V2_FAILED_COUNT=0
|
||||||
|
SOURCE_1236_POST_RECOVERY_FRESH_HELPER_FAILED_COUNT=0
|
||||||
|
SOURCE_1236_POST_RECOVERY_SCHEDULE_SUCCESS_COUNT=7
|
||||||
|
=== LIVE_IDENTITIES ===
|
||||||
|
WRAPPER_SHA256=894f8ea346b53a3d7846dbd6eeb5b89333957eb6d7a4f2f64fd4557cae176e1c
|
||||||
|
HELPER_SHA256=4e39404b1ddb97392645adce6280f697182cca03714d3a462d363eebce9b1860
|
||||||
|
VZDUMP_CONF_SHA256=027e4b04852a4b83d558eb861d432b6fad4f234e12ab77d327f274d0fdedbfad
|
||||||
|
AUDIT_SHA256=f7b936fa997bdefdd0c3c5d1d96e496888ebebc8ea85a60ed3bf5bcc9bf4962a
|
||||||
|
ALERT_SCRIPT_SHA256=2b92cd44fc5b43decba0ea0706c4c84e1912cdc6d7b9bcb10bbf9552c98dc3f9
|
||||||
|
=== CURRENT_UNIT_STATE ===
|
||||||
|
UNIT=homelab-backup-v2.service ACTIVE=activating ENABLED=static RESULT=success EXEC_MAIN_STATUS=0 MAINPID=1856481
|
||||||
|
UNIT=homelab-backup-v2.timer ACTIVE=active ENABLED=enabled RESULT=success EXEC_MAIN_STATUS= MAINPID=
|
||||||
|
UNIT=homelab-backup-audit.service ACTIVE=failed ENABLED=static RESULT=exit-code EXEC_MAIN_STATUS=1 MAINPID=0
|
||||||
|
UNIT=homelab-backup-audit.timer ACTIVE=active ENABLED=enabled RESULT=success EXEC_MAIN_STATUS= MAINPID=
|
||||||
|
UNIT=homelab-alertmanager-backup-health.service ACTIVE=inactive ENABLED=static RESULT=success EXEC_MAIN_STATUS=0 MAINPID=0
|
||||||
|
UNIT=homelab-alertmanager-backup-health.timer ACTIVE=active ENABLED=enabled RESULT=success EXEC_MAIN_STATUS= MAINPID=
|
||||||
|
=== CURRENT_HEALTH_FILES ===
|
||||||
|
HEALTH1_EXISTS=true
|
||||||
|
HEALTH1_SHA256=d89fb55b92f2b9908e2d2d8da3b9a0d0db6d2fe84c6e6d37bcec1a86e4384222
|
||||||
|
HEALTH1_JSON_OK=true
|
||||||
|
HEALTH1_SCHEMA=homelab-backup-audit-v3
|
||||||
|
HEALTH1_STATUS=RED
|
||||||
|
HEALTH1_GENERATED_AT_EPOCH=1790568997
|
||||||
|
HEALTH1_AGE_SECONDS=855
|
||||||
|
HEALTH1_ISSUE_COUNT=2
|
||||||
|
HEALTH1_ISSUE_1={"code":"LOCK_BUSY","logical_id":"/run/homelab-backup-heavy.lock","root_cause":"ACTIVE_OR_ORPHAN_LOCK","severity":"HIGH"}
|
||||||
|
HEALTH1_ISSUE_2={"code":"SOURCE_OFFHOST_MISSING","logical_id":"-","root_cause":"CR_BRANCH_SHA_NOT_EXACT","severity":"MEDIUM"}
|
||||||
|
HEALTH1_SOURCE_LOCAL_HEAD=db592a25c6ac587bf16472a6132b66698c42f663
|
||||||
|
HEALTH1_SOURCE_REMOTE_HEAD=None
|
||||||
|
HEALTH1_SOURCE_PUSHURL_DISABLED=true
|
||||||
|
HEALTH1_SOURCE_EXACT=false
|
||||||
|
HEALTH2_EXISTS=true
|
||||||
|
HEALTH2_SHA256=d89fb55b92f2b9908e2d2d8da3b9a0d0db6d2fe84c6e6d37bcec1a86e4384222
|
||||||
|
HEALTH2_JSON_OK=true
|
||||||
|
HEALTH2_SCHEMA=homelab-backup-audit-v3
|
||||||
|
HEALTH2_STATUS=RED
|
||||||
|
HEALTH2_GENERATED_AT_EPOCH=1790568997
|
||||||
|
HEALTH2_AGE_SECONDS=855
|
||||||
|
HEALTH2_ISSUE_COUNT=2
|
||||||
|
HEALTH2_ISSUE_1={"code":"LOCK_BUSY","logical_id":"/run/homelab-backup-heavy.lock","root_cause":"ACTIVE_OR_ORPHAN_LOCK","severity":"HIGH"}
|
||||||
|
HEALTH2_ISSUE_2={"code":"SOURCE_OFFHOST_MISSING","logical_id":"-","root_cause":"CR_BRANCH_SHA_NOT_EXACT","severity":"MEDIUM"}
|
||||||
|
HEALTH2_SOURCE_LOCAL_HEAD=db592a25c6ac587bf16472a6132b66698c42f663
|
||||||
|
HEALTH2_SOURCE_REMOTE_HEAD=None
|
||||||
|
HEALTH2_SOURCE_PUSHURL_DISABLED=true
|
||||||
|
HEALTH2_SOURCE_EXACT=false
|
||||||
|
HEALTH_FILES_IDENTICAL=true
|
||||||
|
HEALTH_EPOCH_VALID=true
|
||||||
|
=== CURRENT_ALERT_STATE ===
|
||||||
|
ALERT_STATE_EXISTS=true
|
||||||
|
ALERT_STATE_SHA256=493ce50563cb31030f2b16ff4ad722a7ac5ec211a77b2e89625491c057e8827d
|
||||||
|
ALERT_STATE_JSON_OK=true
|
||||||
|
ALERT_STATE_KEYS=code_counts,issue_keys,migration_silent,notify_tokens,raw_issue_keys,schema,updated_epoch
|
||||||
|
ALERT_STATE_SAFE_JSON={"code_counts":{"LOCK_BUSY":4,"SOURCE_OFFHOST_MISSING":263},"issue_keys":["LOCK_BUSY|/run/homelab-backup-heavy.lock|ACTIVE_OR_ORPHAN_LOCK","SOURCE_OFFHOST_MISSING|-|CR_BRANCH_SHA_NOT_EXACT"],"migration_silent":false,"notify_tokens":"[REDACTED]","raw_issue_keys":["LOCK_BUSY|/run/homelab-backup-heavy.lock|ACTIVE_OR_ORPHAN_LOCK","SOURCE_OFFHOST_MISSING|-|CR_BRANCH_SHA_NOT_EXACT"],"schema":"homelab-backup-alert-state-v2","updated_epoch":1790569001}
|
||||||
|
ALERT_STATE_SAFE_TRUNCATED=false
|
||||||
|
ALERT_STATE_FIELD_SCHEMA="homelab-backup-alert-state-v2"
|
||||||
|
ALERT_STATE_FIELD_UPDATED_EPOCH=1790569001
|
||||||
|
ALERT_STATE_FIELD_ISSUE_KEYS=["LOCK_BUSY|/run/homelab-backup-heavy.lock|ACTIVE_OR_ORPHAN_LOCK","SOURCE_OFFHOST_MISSING|-|CR_BRANCH_SHA_NOT_EXACT"]
|
||||||
|
=== ALERT_FILTER_SOURCE ===
|
||||||
|
ALERT_EMBEDDED_SOURCE_FOUND=true
|
||||||
|
ALERT_EMBEDDED_SOURCE_SHA256=344306105083cd8bc64e19d451f7f66c17accc43a2f413538d2f9e2687b2540e
|
||||||
|
ALERT_EMBEDDED_SOURCE_BEGIN
|
||||||
|
0001:import sys,os,json,re,subprocess,pathlib,time
|
||||||
|
0002:mode=sys.argv[1]
|
||||||
|
0003:AUDIT="/usr/local/sbin/homelab-backup-audit"
|
||||||
|
0004:HEALTH=pathlib.Path("/var/lib/homelab-health/backup-audit-v2.json")
|
||||||
|
0005:STATE=pathlib.Path("/var/lib/homelab-alerting/backup-alert-state.json")
|
||||||
|
0006:USERCFG=pathlib.Path("/etc/pve/user.cfg")
|
||||||
|
0007:SCHEMA="homelab-backup-alert-state-v2"
|
||||||
|
0008:THRESHOLDS={"RPO_BREACH":2,"SOURCE_OFFHOST_MISSING":2,"LOCK_BUSY":3}
|
||||||
|
0009:def recipient():
|
||||||
|
0010: text=USERCFG.read_text(encoding="utf-8",errors="replace")
|
||||||
|
0011: m=re.findall(r"(?i)\b[A-Z0-9._+-]+@[A-Z0-9.-]+\.[A-Z]{2,}\b",text)
|
||||||
|
0012: if len(m)!=1: raise SystemExit(65)
|
||||||
|
0013: return m[0]
|
||||||
|
0014:def send(subject,body):
|
||||||
|
0015: rcpt=recipient()
|
||||||
|
0016: msg=f"From: h***@gram1.ru\nTo: {rcpt}\nSubject: {subject}\nContent-Type: text/plain; charset=UTF-8\n\n{body}\n"
|
||||||
|
0017: p=subprocess.run(["/usr/sbin/sendmail","-t"],input=msg,text=True,stdout=subprocess.PIPE,stderr=subprocess.PIPE)
|
||||||
|
0018: if p.returncode!=0: raise SystemExit(p.returncode or 75)
|
||||||
|
0019:def key(i):
|
||||||
|
0020: return "|".join(str(i.get(x,"")) for x in ("code","logical_id","root_cause"))
|
||||||
|
0021:def token(i):[REDACTED]
|
||||||
|
0022: code=str(i.get("code",""))
|
||||||
|
0023: return "group:"+code if code in THRESHOLDS else "issue:"+key(i)
|
||||||
|
0024:if mode=="email-test":
|
||||||
|
0025: send("Workers2 backup alerting test","Workers2 backup/DR alerting route test. If you received this, the local MTA accepted the controlled test generated during backup closure.")
|
||||||
|
0026: print("EMAIL_TEST_ACCEPTED=YES")
|
||||||
|
0027: raise SystemExit(0)
|
||||||
|
0028:if mode!="health-alert": raise SystemExit(64)
|
||||||
|
0029:p=subprocess.run([AUDIT,"write-health"],text=True,stdout=subprocess.PIPE,stderr=subprocess.PIPE)
|
||||||
|
0030:if p.returncode not in (0,1): raise SystemExit(p.returncode or 75)
|
||||||
|
0031:try:
|
||||||
|
0032: h=json.loads(HEALTH.read_text(encoding="utf-8"))
|
||||||
|
0033:except Exception:
|
||||||
|
0034: raise SystemExit(69)
|
||||||
|
0035:issues=h.get("issues") if isinstance(h.get("issues"),list) else []
|
||||||
|
0036:cur={key(i):i for i in issues if isinstance(i,dict)}
|
||||||
|
0037:codes=set(str(i.get("code","")) for i in cur.values())
|
||||||
|
0038:oldj={}
|
||||||
|
0039:if STATE.is_file():
|
||||||
|
0040: try:
|
||||||
|
0041: oldj=json.loads(STATE.read_text(encoding="utf-8"))
|
||||||
|
0042: if not isinstance(oldj,dict): oldj={}
|
||||||
|
0043: except Exception:
|
||||||
|
0044: oldj={}
|
||||||
|
0045:migrating=oldj.get("schema")!=SCHEMA
|
||||||
|
0046:prev_counts=oldj.get("code_counts") if isinstance(oldj.get("code_counts"),dict) and not migrating else {}
|
||||||
|
0047:counts={}
|
||||||
|
0048:for code in codes:
|
||||||
|
0049: try: prev=int(prev_counts.get(code,0))
|
||||||
|
0050: except Exception: prev=0
|
||||||
|
0051: counts[code]=prev+1
|
||||||
|
0052:actionable={}
|
||||||
|
0053:for k,i in cur.items():
|
||||||
|
0054: code=str(i.get("code",""))
|
||||||
|
0055: need=int(THRESHOLDS.get(code,1))
|
||||||
|
0056: if counts.get(code,0)>=need:
|
||||||
|
0057: actionable[k]=i
|
||||||
|
0058:tokens=[REDACTED]
|
||||||
|
0059:old_tokens=[REDACTED]
|
||||||
|
0060:if not migrating:
|
||||||
|
0061: old_tokens=[REDACTED]
|
||||||
|
0062:added=[REDACTED]
|
||||||
|
0063:removed=[REDACTED]
|
||||||
|
0064:if added:
|
||||||
|
0065: lines=[
|
||||||
|
0066: "Workers2 backup/DR actionable alert state changed.",
|
||||||
|
0067: "",
|
||||||
|
0068: "Transient debounce policy: RPO_BREACH=2 checks; SOURCE_OFFHOST_MISSING=2 checks; LOCK_BUSY=3 checks; all other issue codes=immediate.",
|
||||||
|
0069: ""
|
||||||
|
0070: ]
|
||||||
|
0071: for k in sorted(actionable):
|
||||||
|
0072: i=actionable[k]
|
||||||
|
0073: lines.append(f"{i.get('severity','UNKNOWN')} {i.get('code','UNKNOWN')} logical_id={i.get('logical_id','-')} root_cause={i.get('root_cause','UNKNOWN')}")
|
||||||
|
0074: suppressed=len(cur)-len(actionable)
|
||||||
|
0075: if suppressed:
|
||||||
|
0076: lines.extend(["",f"Suppressed transient issue(s) still below threshold: {suppressed}"])
|
||||||
|
0077: send(f"[Workers2 BACKUP ALERT] {len(actionable)} actionable issue(s)","\n".join(lines))
|
||||||
|
0078: print("ALERT_EMAIL_ACCEPTED=YES")
|
||||||
|
0079:elif old_tokens and not tokens:[REDACTED]
|
||||||
|
0080: send("[Workers2 BACKUP RECOVERY] all actionable issues cleared","Workers2 backup/DR actionable audit state is clear. All previously notified actionable backup issues are cleared.")
|
||||||
|
0081: print("RECOVERY_EMAIL_ACCEPTED=YES")
|
||||||
|
0082:STATE.parent.mkdir(parents=True,exist_ok=True)
|
||||||
|
0083:tmp=STATE.with_name(STATE.name+".tmp")
|
||||||
|
0084:payload={
|
||||||
|
0085: "schema":SCHEMA,
|
||||||
|
0086: "updated_epoch":int(time.time()),
|
||||||
|
0087: "issue_keys":sorted(actionable),
|
||||||
|
0088: "notify_tokens":[REDACTED]
|
||||||
|
0089: "raw_issue_keys":sorted(cur),
|
||||||
|
0090: "code_counts":{k:int(v) for k,v in sorted(counts.items())},
|
||||||
|
0091: "migration_silent":bool(migrating)
|
||||||
|
0092:}
|
||||||
|
0093:tmp.write_text(json.dumps(payload,separators=(",",":"),sort_keys=True)+"\n",encoding="utf-8")
|
||||||
|
0094:os.chmod(tmp,0o600)
|
||||||
|
0095:os.replace(tmp,STATE)
|
||||||
|
0096:print("ALERT_FILTER_SCHEMA="+SCHEMA)
|
||||||
|
0097:print("ALERT_RAW_ISSUE_COUNT="+str(len(cur)))
|
||||||
|
0098:print("ALERT_ACTIONABLE_ISSUE_COUNT="+str(len(actionable)))
|
||||||
|
0099:print("ALERT_NOTIFY_TOKEN_COUNT=[REDACTED]
|
||||||
|
0100:print("ALERT_ADDED_TOKEN_COUNT=[REDACTED]
|
||||||
|
0101:print("ALERT_REMOVED_TOKEN_COUNT=[REDACTED]
|
||||||
|
0102:print("ALERT_SUPPRESSED_TRANSIENT_COUNT="+str(len(cur)-len(actionable)))
|
||||||
|
0103:print("ALERT_STATE_MIGRATION_SILENT="+("true" if migrating else "false"))
|
||||||
|
0104:print("HEALTH_ALERT_STATE=OK")
|
||||||
|
ALERT_EMBEDDED_SOURCE_END
|
||||||
|
=== AUDIT_SOURCE_RELEVANT ===
|
||||||
|
183- ("homelab-alertmanager-backup-health.timer","ALERT_TIMER_BAD"),
|
||||||
|
184-]:
|
||||||
|
185- ok,a,e=unit_ok(unit)
|
||||||
|
186- if not ok: issues.append({"severity":"HIGH","code":code,"logical_id":unit,"root_cause":"UNIT_"+a+"_"+e})
|
||||||
|
187-
|
||||||
|
188:for lock in ["/run/homelab-backup-heavy.lock","/run/lock/homelab-app-cloud-quorum-queue.lock","/run/lock/homelab-vm-cloud-quorum-queue.lock","/run/lock/homelab-backup-dispatcher.lock"]:
|
||||||
|
189- p=pathlib.Path(lock)
|
||||||
|
190- if p.exists():
|
||||||
|
191: lrc,_,_=run(["flock","-n",str(p),"-c","true"],5)
|
||||||
|
192: if lrc!=0: issues.append({"severity":"HIGH","code":"LOCK_BUSY","logical_id":lock,"root_cause":"ACTIVE_OR_ORPHAN_LOCK"})
|
||||||
|
193-
|
||||||
|
194-env=os.environ.copy(); env["HOMELAB_BACKUP_GFS_POLICY"]=GFSP; env["HOMELAB_BACKUP_TARGET_REGISTRY"]=str(REG)
|
||||||
|
195-grc,gout,_=run([GFSH,"validate"],20,env)
|
||||||
|
196-if grc!=0 or "GFS_POLICY=OK" not in gout:
|
||||||
|
197- issues.append({"severity":"CRITICAL","code":"GFS_INVALID","logical_id":"-","root_cause":"GFS_VALIDATE_FAILED"})
|
||||||
|
--
|
||||||
|
287-except Exception:
|
||||||
|
288- cloudb_ok=False
|
||||||
|
289-if not cloudb_ok:
|
||||||
|
290- issues.append({"severity":"CRITICAL","code":"CLOUD_B_RESTORE_DRILL_BAD","logical_id":"app-skladchik-reports-monitor","root_cause":"CANONICAL_CLOUD_B_PAYLOAD_OR_RESTORE_EVIDENCE_NOT_OK"})
|
||||||
|
291-
|
||||||
|
292:source={"local_head":None,"remote_head":None,"pushurl_disabled":False}
|
||||||
|
293-hrc,ho,_=run(["git","-C",WT,"rev-parse","HEAD"],10)
|
||||||
|
294:if hrc==0: source["local_head"]=ho.strip()
|
||||||
|
295-frc,fo,_=run(["git","-C",WT,"config","--get","remote.origin.url"],10)
|
||||||
|
296-prc,po,_=run(["git","-C",WT,"config","--get","remote.origin.pushurl"],10)
|
||||||
|
297-source["pushurl_disabled"]=(prc==0 and po.strip()=="DISABLED")
|
||||||
|
298-if frc==0 and fo.strip():
|
||||||
|
299- lrc,lo,_=run(["git","ls-remote",fo.strip(),"refs/heads/"+BRANCH],30)
|
||||||
|
300: if lrc==0 and lo.strip(): source["remote_head"]=lo.split()[0]
|
||||||
|
301:if source["remote_head"]!=source["local_head"]:
|
||||||
|
302: issues.append({"severity":"MEDIUM","code":"SOURCE_OFFHOST_MISSING","logical_id":"-","root_cause":"CR_BRANCH_SHA_NOT_EXACT"})
|
||||||
|
303-
|
||||||
|
304-status="GREEN" if not issues else "RED"
|
||||||
|
305-for t in targets:
|
||||||
|
306- print("TARGET|"+"|".join(f"{k}={v}" for k,v in t.items() if v is not None))
|
||||||
|
307-for i in issues:
|
||||||
|
308- print("ISSUE|severity={severity}|code={code}|logical_id={logical_id}|root_cause={root_cause}".format(**i))
|
||||||
|
309:print(f"SUMMARY|AUDIT_STATUS=OK|BACKUP_STATUS={status}|ACTIVE_COUNT={len(active)}|ISSUE_COUNT={len(issues)}|CLOUD_A={'OK' if cloud.get('A',{}).get('readable') else 'BAD'}|CLOUD_B={'OK' if cloud.get('B',{}).get('readable') else 'BAD'}|CLOUD_B_DRILL={'OK' if cloudb_ok else 'BAD'}|DR_PROVEN={'YES' if isinstance(dr,dict) and dr.get('status')=='SEALED' else 'NO'}|SOURCE_OFFHOST={'OK' if source['remote_head']==source['local_head'] else 'PENDING'}")
|
||||||
|
310-health={"schema":"homelab-backup-audit-v3","status":status,"generated_at_epoch":now,"targets":targets,"issues":issues,"cloud":cloud,"source":source,"cloud_b_restore_drill":cloudb_ok,"dr_proven":bool(isinstance(dr,dict) and dr.get("status")=="SEALED")}
|
||||||
|
311-if MODE in ("write-health","scheduled"):
|
||||||
|
312- for hp in HEALTHS:
|
||||||
|
313- hp.parent.mkdir(parents=True,exist_ok=True)
|
||||||
|
314- tmp=hp.with_name(hp.name+".tmp")
|
||||||
|
=== LIVE_SOURCE_HEAD_RECHECK ===
|
||||||
|
SOURCE_LOCAL_HEAD=db592a25c6ac587bf16472a6132b66698c42f663
|
||||||
|
SOURCE_BRANCH=cr-2026-1005-backup-v2-health-alerting-remediation
|
||||||
|
SOURCE_WORKTREE_CLEAN=true
|
||||||
|
SOURCE_ORIGIN_URL_SHA256=7507b97d441d05c4e33306608cbf655e96bf2add0ec7683cc2f4e5539f64daf9
|
||||||
|
SOURCE_REMOTE_ATTEMPT=1 HEAD=db592a25c6ac587bf16472a6132b66698c42f663 STDERR_BYTES=0 EXACT=true
|
||||||
|
SOURCE_REMOTE_ATTEMPT=2 HEAD=db592a25c6ac587bf16472a6132b66698c42f663 STDERR_BYTES=0 EXACT=true
|
||||||
|
SOURCE_REMOTE_ATTEMPT=3 HEAD=db592a25c6ac587bf16472a6132b66698c42f663 STDERR_BYTES=0 EXACT=true
|
||||||
|
SOURCE_REMOTE_ATTEMPT=4 HEAD=db592a25c6ac587bf16472a6132b66698c42f663 STDERR_BYTES=0 EXACT=true
|
||||||
|
SOURCE_REMOTE_ATTEMPT=5 HEAD=db592a25c6ac587bf16472a6132b66698c42f663 STDERR_BYTES=0 EXACT=true
|
||||||
|
=== CURRENT_LOCK_OWNERSHIP ===
|
||||||
|
LOCK_META=/run/homelab-backup-heavy.lock|inode=3474|600|root:root|2026-09-28 03:27:07.425060217 +0300
|
||||||
|
LOCK_FUSER=/run/homelab-backup-heavy.lock| 1856481
|
||||||
|
LOCK_FREE=/run/homelab-backup-heavy.lock|false
|
||||||
|
LOCK_META=/run/lock/homelab-backup-dispatcher.lock|inode=9|600|root:root|2026-09-28 03:27:07.423060188 +0300
|
||||||
|
LOCK_FUSER=/run/lock/homelab-backup-dispatcher.lock|
|
||||||
|
LOCK_FREE=/run/lock/homelab-backup-dispatcher.lock|true
|
||||||
|
LOCK_META=/run/lock/homelab-vm-cloud-quorum-queue.lock|inode=2944|600|root:root|2026-09-28 03:27:07.424060203 +0300
|
||||||
|
LOCK_FUSER=/run/lock/homelab-vm-cloud-quorum-queue.lock|
|
||||||
|
LOCK_FREE=/run/lock/homelab-vm-cloud-quorum-queue.lock|true
|
||||||
|
LOCK_META=/run/lock/homelab-app-cloud-quorum-queue.lock|inode=15|600|root:root|2026-09-28 03:27:07.425060217 +0300
|
||||||
|
LOCK_FUSER=/run/lock/homelab-app-cloud-quorum-queue.lock|
|
||||||
|
LOCK_FREE=/run/lock/homelab-app-cloud-quorum-queue.lock|true
|
||||||
|
homelab-backup- 1856481 FLOCK WRITE /run/homelab-backup-heavy.lock
|
||||||
|
=== ALERT_EMAIL_TIME_CORRELATION_0701_MSK ===
|
||||||
|
2026-09-28T06:19:01.361470+03:00 pve01 systemd[1]: Starting homelab-backup-v2.service - Homelab Backup V2 manifest-driven scheduler...
|
||||||
|
2026-09-28T06:36:20.418325+03:00 pve01 homelab-backup-audit[1908813]: ISSUE|severity=HIGH|code=LOCK_BUSY|logical_id=/run/homelab-backup-heavy.lock|root_cause=ACTIVE_OR_ORPHAN_LOCK
|
||||||
|
2026-09-28T06:36:20.418325+03:00 pve01 homelab-backup-audit[1908813]: SUMMARY|AUDIT_STATUS=OK|BACKUP_STATUS=RED|ACTIVE_COUNT=16|ISSUE_COUNT=1|CLOUD_A=OK|CLOUD_B=OK|CLOUD_B_DRILL=OK|DR_PROVEN=YES|SOURCE_OFFHOST=OK
|
||||||
|
2026-09-28T06:36:20.423980+03:00 pve01 systemd[1]: homelab-backup-audit.service: Main process exited, code=exited, status=1/FAILURE
|
||||||
|
2026-09-28T06:36:20.424205+03:00 pve01 systemd[1]: Failed to start homelab-backup-audit.service - Homelab unified backup and DR audit.
|
||||||
|
2026-09-28T07:06:48.299695+03:00 pve01 homelab-backup-audit[2011656]: ISSUE|severity=HIGH|code=LOCK_BUSY|logical_id=/run/homelab-backup-heavy.lock|root_cause=ACTIVE_OR_ORPHAN_LOCK
|
||||||
|
2026-09-28T07:06:48.299695+03:00 pve01 homelab-backup-audit[2011656]: SUMMARY|AUDIT_STATUS=OK|BACKUP_STATUS=RED|ACTIVE_COUNT=16|ISSUE_COUNT=1|CLOUD_A=OK|CLOUD_B=OK|CLOUD_B_DRILL=OK|DR_PROVEN=YES|SOURCE_OFFHOST=OK
|
||||||
|
2026-09-28T07:06:48.304891+03:00 pve01 systemd[1]: homelab-backup-audit.service: Main process exited, code=exited, status=1/FAILURE
|
||||||
|
2026-09-28T07:06:48.305137+03:00 pve01 systemd[1]: Failed to start homelab-backup-audit.service - Homelab unified backup and DR audit.
|
||||||
|
2026-09-28T06:15:16.319082+03:00 pve01 systemd[1]: Starting homelab-alertmanager-backup-health.service - Workers2 backup health alert via existing alertmanager backup integration...
|
||||||
|
2026-09-28T06:15:20.661916+03:00 pve01 homelab-alertmanager-backup-run[1835343]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T06:15:20.666144+03:00 pve01 systemd[1]: Finished homelab-alertmanager-backup-health.service - Workers2 backup health alert via existing alertmanager backup integration.
|
||||||
|
2026-09-28T06:30:42.414371+03:00 pve01 systemd[1]: Starting homelab-alertmanager-backup-health.service - Workers2 backup health alert via existing alertmanager backup integration...
|
||||||
|
2026-09-28T06:30:46.367196+03:00 pve01 homelab-alertmanager-backup-run[1886013]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T06:30:46.370827+03:00 pve01 systemd[1]: Finished homelab-alertmanager-backup-health.service - Workers2 backup health alert via existing alertmanager backup integration.
|
||||||
|
2026-09-28T06:46:01.347189+03:00 pve01 systemd[1]: Starting homelab-alertmanager-backup-health.service - Workers2 backup health alert via existing alertmanager backup integration...
|
||||||
|
2026-09-28T06:46:05.406037+03:00 pve01 homelab-alertmanager-backup-run[1945314]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T06:46:05.410491+03:00 pve01 systemd[1]: Finished homelab-alertmanager-backup-health.service - Workers2 backup health alert via existing alertmanager backup integration.
|
||||||
|
2026-09-28T07:01:32.217324+03:00 pve01 systemd[1]: Starting homelab-alertmanager-backup-health.service - Workers2 backup health alert via existing alertmanager backup integration...
|
||||||
|
2026-09-28T07:01:36.274466+03:00 pve01 homelab-alertmanager-backup-run[1988992]: ALERT_EMAIL_ACCEPTED=YES
|
||||||
|
2026-09-28T07:01:36.274466+03:00 pve01 homelab-alertmanager-backup-run[1988992]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T07:01:36.278152+03:00 pve01 systemd[1]: Finished homelab-alertmanager-backup-health.service - Workers2 backup health alert via existing alertmanager backup integration.
|
||||||
|
2026-09-28T07:16:37.585569+03:00 pve01 systemd[1]: Starting homelab-alertmanager-backup-health.service - Workers2 backup health alert via existing alertmanager backup integration...
|
||||||
|
2026-09-28T07:16:41.913014+03:00 pve01 homelab-alertmanager-backup-run[2048228]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T07:16:41.916768+03:00 pve01 systemd[1]: Finished homelab-alertmanager-backup-health.service - Workers2 backup health alert via existing alertmanager backup integration.
|
||||||
|
=== ALERT_FREQUENCY_LAST12H ===
|
||||||
|
ALERT_RUN_START_COUNT=0
|
||||||
|
ALERT_EMAIL_ACCEPTED_COUNT=3
|
||||||
|
RECOVERY_EMAIL_ACCEPTED_COUNT=0
|
||||||
|
HEALTH_ALERT_STATE_OK_COUNT=47
|
||||||
|
2026-09-27T19:32:04.991437+03:00 pve01 homelab-alertmanager-backup-run[3909103]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-27T19:47:36.328545+03:00 pve01 homelab-alertmanager-backup-run[3959645]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-27T20:02:46.359055+03:00 pve01 homelab-alertmanager-backup-run[4008840]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-27T20:18:05.225521+03:00 pve01 homelab-alertmanager-backup-run[4059785]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-27T20:33:20.585967+03:00 pve01 homelab-alertmanager-backup-run[4108890]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-27T20:48:36.460451+03:00 pve01 homelab-alertmanager-backup-run[4148152]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-27T21:04:08.100470+03:00 pve01 homelab-alertmanager-backup-run[4070]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-27T21:19:36.336976+03:00 pve01 homelab-alertmanager-backup-run[54137]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-27T21:35:05.706232+03:00 pve01 homelab-alertmanager-backup-run[104752]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-27T21:50:23.015203+03:00 pve01 homelab-alertmanager-backup-run[154365]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-27T22:05:36.461278+03:00 pve01 homelab-alertmanager-backup-run[202960]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-27T22:21:05.253758+03:00 pve01 homelab-alertmanager-backup-run[242449]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-27T22:36:15.399283+03:00 pve01 homelab-alertmanager-backup-run[292331]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-27T22:51:31.819800+03:00 pve01 homelab-alertmanager-backup-run[343850]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-27T23:06:53.759023+03:00 pve01 homelab-alertmanager-backup-run[396329]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-27T23:22:20.677831+03:00 pve01 homelab-alertmanager-backup-run[461385]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-27T23:37:36.973241+03:00 pve01 homelab-alertmanager-backup-run[513251]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-27T23:52:43.434843+03:00 pve01 homelab-alertmanager-backup-run[566888]: ALERT_EMAIL_ACCEPTED=YES
|
||||||
|
2026-09-27T23:52:43.434843+03:00 pve01 homelab-alertmanager-backup-run[566888]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T00:08:05.576769+03:00 pve01 homelab-alertmanager-backup-run[607129]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T00:23:21.212626+03:00 pve01 homelab-alertmanager-backup-run[660884]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T00:38:36.269886+03:00 pve01 homelab-alertmanager-backup-run[711652]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T00:53:55.974540+03:00 pve01 homelab-alertmanager-backup-run[762988]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T01:09:05.464301+03:00 pve01 homelab-alertmanager-backup-run[812499]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T01:24:16.127247+03:00 pve01 homelab-alertmanager-backup-run[862903]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T01:39:41.256513+03:00 pve01 homelab-alertmanager-backup-run[919688]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T01:54:54.298806+03:00 pve01 homelab-alertmanager-backup-run[958250]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T02:10:05.486220+03:00 pve01 homelab-alertmanager-backup-run[1009352]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T02:25:22.594856+03:00 pve01 homelab-alertmanager-backup-run[1058040]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T02:40:53.144072+03:00 pve01 homelab-alertmanager-backup-run[1108677]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T02:56:20.122916+03:00 pve01 homelab-alertmanager-backup-run[1157287]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T03:11:36.224287+03:00 pve01 homelab-alertmanager-backup-run[1207541]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T03:26:56.104164+03:00 pve01 homelab-alertmanager-backup-run[1267608]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T03:42:16.163161+03:00 pve01 homelab-alertmanager-backup-run[1337091]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T03:57:35.911704+03:00 pve01 homelab-alertmanager-backup-run[1388112]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T04:12:45.302638+03:00 pve01 homelab-alertmanager-backup-run[1439953]: ALERT_EMAIL_ACCEPTED=YES
|
||||||
|
2026-09-28T04:12:45.302638+03:00 pve01 homelab-alertmanager-backup-run[1439953]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T04:28:16.066840+03:00 pve01 homelab-alertmanager-backup-run[1491056]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T04:43:26.035041+03:00 pve01 homelab-alertmanager-backup-run[1543022]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T04:58:29.541024+03:00 pve01 homelab-alertmanager-backup-run[1593789]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T05:13:39.334685+03:00 pve01 homelab-alertmanager-backup-run[1645768]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T05:28:53.353807+03:00 pve01 homelab-alertmanager-backup-run[1685761]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T05:44:20.155523+03:00 pve01 homelab-alertmanager-backup-run[1736193]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T06:00:05.422013+03:00 pve01 homelab-alertmanager-backup-run[1785685]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T06:15:20.661916+03:00 pve01 homelab-alertmanager-backup-run[1835343]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T06:30:46.367196+03:00 pve01 homelab-alertmanager-backup-run[1886013]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T06:46:05.406037+03:00 pve01 homelab-alertmanager-backup-run[1945314]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T07:01:36.274466+03:00 pve01 homelab-alertmanager-backup-run[1988992]: ALERT_EMAIL_ACCEPTED=YES
|
||||||
|
2026-09-28T07:01:36.274466+03:00 pve01 homelab-alertmanager-backup-run[1988992]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T07:16:41.913014+03:00 pve01 homelab-alertmanager-backup-run[2048228]: HEALTH_ALERT_STATE=OK
|
||||||
|
=== AUDIT_FREQUENCY_LAST12H ===
|
||||||
|
AUDIT_GREEN_SUMMARY_COUNT=7
|
||||||
|
AUDIT_RED_SUMMARY_COUNT=17
|
||||||
|
AUDIT_LOCK_BUSY_ISSUE_COUNT=9
|
||||||
|
AUDIT_SOURCE_OFFHOST_ISSUE_COUNT=0
|
||||||
|
2026-09-27T19:37:02.093711+03:00 pve01 homelab-backup-audit[3923461]: SUMMARY|AUDIT_STATUS=OK|BACKUP_STATUS=RED|ACTIVE_COUNT=16|ISSUE_COUNT=12|CLOUD_A=OK|CLOUD_B=OK|CLOUD_B_DRILL=OK|DR_PROVEN=YES|SOURCE_OFFHOST=OK
|
||||||
|
2026-09-27T20:06:15.522779+03:00 pve01 homelab-backup-audit[4022565]: SUMMARY|AUDIT_STATUS=OK|BACKUP_STATUS=RED|ACTIVE_COUNT=16|ISSUE_COUNT=12|CLOUD_A=OK|CLOUD_B=OK|CLOUD_B_DRILL=OK|DR_PROVEN=YES|SOURCE_OFFHOST=OK
|
||||||
|
2026-09-27T20:36:05.450336+03:00 pve01 homelab-backup-audit[4111037]: SUMMARY|AUDIT_STATUS=OK|BACKUP_STATUS=RED|ACTIVE_COUNT=16|ISSUE_COUNT=12|CLOUD_A=OK|CLOUD_B=OK|CLOUD_B_DRILL=OK|DR_PROVEN=YES|SOURCE_OFFHOST=OK
|
||||||
|
2026-09-27T21:06:02.094425+03:00 pve01 homelab-backup-audit[16838]: SUMMARY|AUDIT_STATUS=OK|BACKUP_STATUS=RED|ACTIVE_COUNT=16|ISSUE_COUNT=12|CLOUD_A=OK|CLOUD_B=OK|CLOUD_B_DRILL=OK|DR_PROVEN=YES|SOURCE_OFFHOST=OK
|
||||||
|
2026-09-27T21:37:05.002224+03:00 pve01 homelab-backup-audit[106421]: SUMMARY|AUDIT_STATUS=OK|BACKUP_STATUS=RED|ACTIVE_COUNT=16|ISSUE_COUNT=12|CLOUD_A=OK|CLOUD_B=OK|CLOUD_B_DRILL=OK|DR_PROVEN=YES|SOURCE_OFFHOST=OK
|
||||||
|
2026-09-27T22:06:07.004513+03:00 pve01 homelab-backup-audit[203921]: SUMMARY|AUDIT_STATUS=OK|BACKUP_STATUS=RED|ACTIVE_COUNT=16|ISSUE_COUNT=12|CLOUD_A=OK|CLOUD_B=OK|CLOUD_B_DRILL=OK|DR_PROVEN=YES|SOURCE_OFFHOST=OK
|
||||||
|
2026-09-27T22:35:26.212759+03:00 pve01 homelab-backup-audit[291167]: SUMMARY|AUDIT_STATUS=OK|BACKUP_STATUS=RED|ACTIVE_COUNT=16|ISSUE_COUNT=12|CLOUD_A=OK|CLOUD_B=OK|CLOUD_B_DRILL=OK|DR_PROVEN=YES|SOURCE_OFFHOST=OK
|
||||||
|
2026-09-27T23:06:54.987894+03:00 pve01 homelab-backup-audit[395212]: SUMMARY|AUDIT_STATUS=OK|BACKUP_STATUS=RED|ACTIVE_COUNT=16|ISSUE_COUNT=11|CLOUD_A=OK|CLOUD_B=OK|CLOUD_B_DRILL=OK|DR_PROVEN=YES|SOURCE_OFFHOST=OK
|
||||||
|
2026-09-27T23:36:37.162587+03:00 pve01 homelab-backup-audit[500802]: ISSUE|severity=HIGH|code=LOCK_BUSY|logical_id=/run/homelab-backup-heavy.lock|root_cause=ACTIVE_OR_ORPHAN_LOCK
|
||||||
|
2026-09-27T23:36:37.162587+03:00 pve01 homelab-backup-audit[500802]: SUMMARY|AUDIT_STATUS=OK|BACKUP_STATUS=RED|ACTIVE_COUNT=16|ISSUE_COUNT=6|CLOUD_A=OK|CLOUD_B=OK|CLOUD_B_DRILL=OK|DR_PROVEN=YES|SOURCE_OFFHOST=OK
|
||||||
|
2026-09-28T00:06:21.135619+03:00 pve01 homelab-backup-audit[605334]: ISSUE|severity=HIGH|code=LOCK_BUSY|logical_id=/run/homelab-backup-heavy.lock|root_cause=ACTIVE_OR_ORPHAN_LOCK
|
||||||
|
2026-09-28T00:06:21.135619+03:00 pve01 homelab-backup-audit[605334]: SUMMARY|AUDIT_STATUS=OK|BACKUP_STATUS=RED|ACTIVE_COUNT=16|ISSUE_COUNT=4|CLOUD_A=OK|CLOUD_B=OK|CLOUD_B_DRILL=OK|DR_PROVEN=YES|SOURCE_OFFHOST=OK
|
||||||
|
2026-09-28T00:36:10.445081+03:00 pve01 homelab-backup-audit[707255]: ISSUE|severity=HIGH|code=LOCK_BUSY|logical_id=/run/homelab-backup-heavy.lock|root_cause=ACTIVE_OR_ORPHAN_LOCK
|
||||||
|
2026-09-28T00:36:10.445081+03:00 pve01 homelab-backup-audit[707255]: SUMMARY|AUDIT_STATUS=OK|BACKUP_STATUS=RED|ACTIVE_COUNT=16|ISSUE_COUNT=2|CLOUD_A=OK|CLOUD_B=OK|CLOUD_B_DRILL=OK|DR_PROVEN=YES|SOURCE_OFFHOST=OK
|
||||||
|
2026-09-28T01:06:01.997372+03:00 pve01 homelab-backup-audit[799187]: SUMMARY|AUDIT_STATUS=OK|BACKUP_STATUS=GREEN|ACTIVE_COUNT=16|ISSUE_COUNT=0|CLOUD_A=OK|CLOUD_B=OK|CLOUD_B_DRILL=OK|DR_PROVEN=YES|SOURCE_OFFHOST=OK
|
||||||
|
2026-09-28T01:36:02.006941+03:00 pve01 homelab-backup-audit[906059]: SUMMARY|AUDIT_STATUS=OK|BACKUP_STATUS=GREEN|ACTIVE_COUNT=16|ISSUE_COUNT=0|CLOUD_A=OK|CLOUD_B=OK|CLOUD_B_DRILL=OK|DR_PROVEN=YES|SOURCE_OFFHOST=OK
|
||||||
|
2026-09-28T02:05:36.356288+03:00 pve01 homelab-backup-audit[995508]: SUMMARY|AUDIT_STATUS=OK|BACKUP_STATUS=GREEN|ACTIVE_COUNT=16|ISSUE_COUNT=0|CLOUD_A=OK|CLOUD_B=OK|CLOUD_B_DRILL=OK|DR_PROVEN=YES|SOURCE_OFFHOST=OK
|
||||||
|
2026-09-28T02:36:15.265015+03:00 pve01 homelab-backup-audit[1094502]: SUMMARY|AUDIT_STATUS=OK|BACKUP_STATUS=GREEN|ACTIVE_COUNT=16|ISSUE_COUNT=0|CLOUD_A=OK|CLOUD_B=OK|CLOUD_B_DRILL=OK|DR_PROVEN=YES|SOURCE_OFFHOST=OK
|
||||||
|
2026-09-28T03:05:20.453132+03:00 pve01 homelab-backup-audit[1192518]: SUMMARY|AUDIT_STATUS=OK|BACKUP_STATUS=GREEN|ACTIVE_COUNT=16|ISSUE_COUNT=0|CLOUD_A=OK|CLOUD_B=OK|CLOUD_B_DRILL=OK|DR_PROVEN=YES|SOURCE_OFFHOST=OK
|
||||||
|
2026-09-28T03:35:20.147380+03:00 pve01 homelab-backup-audit[1320691]: ISSUE|severity=HIGH|code=LOCK_BUSY|logical_id=/run/homelab-backup-heavy.lock|root_cause=ACTIVE_OR_ORPHAN_LOCK
|
||||||
|
2026-09-28T03:35:20.147380+03:00 pve01 homelab-backup-audit[1320691]: SUMMARY|AUDIT_STATUS=OK|BACKUP_STATUS=RED|ACTIVE_COUNT=16|ISSUE_COUNT=1|CLOUD_A=OK|CLOUD_B=OK|CLOUD_B_DRILL=OK|DR_PROVEN=YES|SOURCE_OFFHOST=OK
|
||||||
|
2026-09-28T04:06:45.928910+03:00 pve01 homelab-backup-audit[1424254]: ISSUE|severity=HIGH|code=LOCK_BUSY|logical_id=/run/homelab-backup-heavy.lock|root_cause=ACTIVE_OR_ORPHAN_LOCK
|
||||||
|
2026-09-28T04:06:45.928910+03:00 pve01 homelab-backup-audit[1424254]: SUMMARY|AUDIT_STATUS=OK|BACKUP_STATUS=RED|ACTIVE_COUNT=16|ISSUE_COUNT=1|CLOUD_A=OK|CLOUD_B=OK|CLOUD_B_DRILL=OK|DR_PROVEN=YES|SOURCE_OFFHOST=OK
|
||||||
|
2026-09-28T04:35:20.240415+03:00 pve01 homelab-backup-audit[1514892]: ISSUE|severity=HIGH|code=LOCK_BUSY|logical_id=/run/homelab-backup-heavy.lock|root_cause=ACTIVE_OR_ORPHAN_LOCK
|
||||||
|
2026-09-28T04:35:20.240415+03:00 pve01 homelab-backup-audit[1514892]: SUMMARY|AUDIT_STATUS=OK|BACKUP_STATUS=RED|ACTIVE_COUNT=16|ISSUE_COUNT=1|CLOUD_A=OK|CLOUD_B=OK|CLOUD_B_DRILL=OK|DR_PROVEN=YES|SOURCE_OFFHOST=OK
|
||||||
|
2026-09-28T05:05:52.974415+03:00 pve01 homelab-backup-audit[1617767]: ISSUE|severity=HIGH|code=LOCK_BUSY|logical_id=/run/homelab-backup-heavy.lock|root_cause=ACTIVE_OR_ORPHAN_LOCK
|
||||||
|
2026-09-28T05:05:52.974415+03:00 pve01 homelab-backup-audit[1617767]: SUMMARY|AUDIT_STATUS=OK|BACKUP_STATUS=RED|ACTIVE_COUNT=16|ISSUE_COUNT=1|CLOUD_A=OK|CLOUD_B=OK|CLOUD_B_DRILL=OK|DR_PROVEN=YES|SOURCE_OFFHOST=OK
|
||||||
|
2026-09-28T05:37:02.145613+03:00 pve01 homelab-backup-audit[1720751]: SUMMARY|AUDIT_STATUS=OK|BACKUP_STATUS=GREEN|ACTIVE_COUNT=16|ISSUE_COUNT=0|CLOUD_A=OK|CLOUD_B=OK|CLOUD_B_DRILL=OK|DR_PROVEN=YES|SOURCE_OFFHOST=OK
|
||||||
|
2026-09-28T06:06:02.032037+03:00 pve01 homelab-backup-audit[1807928]: SUMMARY|AUDIT_STATUS=OK|BACKUP_STATUS=GREEN|ACTIVE_COUNT=16|ISSUE_COUNT=0|CLOUD_A=OK|CLOUD_B=OK|CLOUD_B_DRILL=OK|DR_PROVEN=YES|SOURCE_OFFHOST=OK
|
||||||
|
2026-09-28T06:36:20.418325+03:00 pve01 homelab-backup-audit[1908813]: ISSUE|severity=HIGH|code=LOCK_BUSY|logical_id=/run/homelab-backup-heavy.lock|root_cause=ACTIVE_OR_ORPHAN_LOCK
|
||||||
|
2026-09-28T06:36:20.418325+03:00 pve01 homelab-backup-audit[1908813]: SUMMARY|AUDIT_STATUS=OK|BACKUP_STATUS=RED|ACTIVE_COUNT=16|ISSUE_COUNT=1|CLOUD_A=OK|CLOUD_B=OK|CLOUD_B_DRILL=OK|DR_PROVEN=YES|SOURCE_OFFHOST=OK
|
||||||
|
2026-09-28T07:06:48.299695+03:00 pve01 homelab-backup-audit[2011656]: ISSUE|severity=HIGH|code=LOCK_BUSY|logical_id=/run/homelab-backup-heavy.lock|root_cause=ACTIVE_OR_ORPHAN_LOCK
|
||||||
|
2026-09-28T07:06:48.299695+03:00 pve01 homelab-backup-audit[2011656]: SUMMARY|AUDIT_STATUS=OK|BACKUP_STATUS=RED|ACTIVE_COUNT=16|ISSUE_COUNT=1|CLOUD_A=OK|CLOUD_B=OK|CLOUD_B_DRILL=OK|DR_PROVEN=YES|SOURCE_OFFHOST=OK
|
||||||
|
=== HEALTH_GENERATION_CORRELATION ===
|
||||||
|
HEALTH_GENERATED_AT_EPOCH=1790568997
|
||||||
|
HEALTH_CORRELATION_FROM=1790568817
|
||||||
|
HEALTH_CORRELATION_TO=1790569177
|
||||||
|
=== FRESH_QUIET_AUDIT ===
|
||||||
|
QUIET_AUDIT_WAIT|attempt=1|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=2|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=3|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=4|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=5|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=6|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=7|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=8|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=9|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=10|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=11|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=12|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=13|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=14|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=15|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=16|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=17|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=18|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=19|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=20|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=21|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=22|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=23|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=24|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=25|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=26|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=27|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=28|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=29|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=30|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=31|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=32|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=33|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=34|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=35|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=36|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
FRESH_QUIET_AUDIT_RC=NO_QUIET_WINDOW
|
||||||
|
FRESH_AUDIT_HEALTH_NO_WRITE=false
|
||||||
|
=== CANONICAL_ALERT_SOURCE_AUTHORITY ===
|
||||||
|
CANONICAL_ALERT_PATH=/root/homelab-ops-cr-2026-1005/tasks/backup-v2-health-alerting-remediation-v1/assets/baseline/homelab-alertmanager-backup-run
|
||||||
|
CANONICAL_ALERT_EXISTS=true
|
||||||
|
CANONICAL_ALERT_SHA256=6deef30b4708a7e5b2ac0f0d98bb6b37b22d858afde994483b67baa18dffdc2a
|
||||||
|
CANONICAL_ALERT_MATCH_LIVE=false
|
||||||
|
CANONICAL_SOURCE_HEAD=db592a25c6ac587bf16472a6132b66698c42f663
|
||||||
|
CANONICAL_REMOTE_HEAD=db592a25c6ac587bf16472a6132b66698c42f663
|
||||||
|
CANONICAL_SOURCE_EXACT=true
|
||||||
|
TASK_RESULT=PASS_BACKUP_ALERT_SPAM_CURRENT_RCA_COLLECTED
|
||||||
|
DECISION=PASS_BACKUP_ALERT_SPAM_CURRENT_RCA_COLLECTED
|
||||||
|
NEXT_GATE=READ_EXACT_1237_AND_FIX_ONLY_PROVEN_ALERT_NOISE_CAUSE
|
||||||
|
HOMELAB_RESULT_CONTRACT={"version":1,"command_id":"SUPPORT-260928-HOMELAB-BACKUP-ALERT-SPAM-CURRENT-RCA-1237R1","status":"OK","changes_made":false,"rollback_started":false,"rollback_restored":null}
|
||||||
|
|
||||||
|
OUTPUT_END
|
||||||
|
CHAT_OUTPUT_END
|
||||||
+8
-8
File diff suppressed because one or more lines are too long
+415
-84
@@ -1,15 +1,15 @@
|
|||||||
CHAT_OUTPUT_BEGIN
|
CHAT_OUTPUT_BEGIN
|
||||||
COMMAND_ID=SUPPORT-260928-HOMELAB-BACKUP-V2-FINAL-ACCEPTANCE-CLOSEOUT-1236R1
|
COMMAND_ID=SUPPORT-260928-HOMELAB-BACKUP-ALERT-SPAM-CURRENT-RCA-1237R1
|
||||||
STATUS=OK
|
STATUS=OK
|
||||||
RC=0
|
RC=0
|
||||||
HOST=pve01
|
HOST=pve01
|
||||||
MODE=read-only
|
MODE=read-only
|
||||||
COMPONENT=homelab-backup-v2-final-acceptance-closeout
|
COMPONENT=homelab-backup-alert-spam-current-rca
|
||||||
REFERENCE_REGISTER_CHECK=OK
|
REFERENCE_REGISTER_CHECK=OK
|
||||||
REFERENCE_SHA256=5a3d8e5154c41cb582a4e0aca68090be1f0138918bf82131a948df326f9d8d66
|
REFERENCE_SHA256=5a3d8e5154c41cb582a4e0aca68090be1f0138918bf82131a948df326f9d8d66
|
||||||
ERROR_REGISTER_CHECK=OK
|
ERROR_REGISTER_CHECK=OK
|
||||||
ERROR_REGISTER_SHA256=3b09a553ec0f527ed3afeed4753f52a74ee3036045bbfb3c685e9f8af4ba7ba0
|
ERROR_REGISTER_SHA256=3b09a553ec0f527ed3afeed4753f52a74ee3036045bbfb3c685e9f8af4ba7ba0
|
||||||
COMMAND_SHA256=ae0922db9c4c4ecb922eff1bc2dbc83ca34800f18e36edd72d9ff12921aff878
|
COMMAND_SHA256=e205fb5749bd8d2a466e79a56e8d9f3a66537e7dcbd1c635202ab6df607b736b
|
||||||
DUPLICATE_FAILED_COMMAND_BLOCKED=false
|
DUPLICATE_FAILED_COMMAND_BLOCKED=false
|
||||||
EXECUTION_STARTED=true
|
EXECUTION_STARTED=true
|
||||||
CHANGE_DECLARED=false
|
CHANGE_DECLARED=false
|
||||||
@@ -24,101 +24,432 @@ MUTATION_OUTCOME=NO_MUTATION
|
|||||||
SANITIZED=yes
|
SANITIZED=yes
|
||||||
SECRETS_INCLUDED=no
|
SECRETS_INCLUDED=no
|
||||||
PRIVATE_ADDRESSES_INCLUDED=no
|
PRIVATE_ADDRESSES_INCLUDED=no
|
||||||
RAW_EVIDENCE_SHA256=92d863c807a78fd412105892222e8b6204cabb0751fc53ff09613fbe11d0394c
|
RAW_EVIDENCE_SHA256=c64c77856d1b796c0414be59dd0089c9687ec505d26bb8b4111ab68ee967e5a2
|
||||||
SANITIZED_OUTPUT_SHA256=92d863c807a78fd412105892222e8b6204cabb0751fc53ff09613fbe11d0394c
|
SANITIZED_OUTPUT_SHA256=c64c77856d1b796c0414be59dd0089c9687ec505d26bb8b4111ab68ee967e5a2
|
||||||
OUTPUT_BEGIN
|
OUTPUT_BEGIN
|
||||||
BACKUP_V2_FINAL_ACCEPTANCE_CLOSEOUT_BEGIN=true
|
BACKUP_ALERT_SPAM_CURRENT_RCA_BEGIN=true
|
||||||
COMMAND_ID=SUPPORT-260928-HOMELAB-BACKUP-V2-FINAL-ACCEPTANCE-CLOSEOUT-1236R1
|
COMMAND_ID=SUPPORT-260928-HOMELAB-BACKUP-ALERT-SPAM-CURRENT-RCA-1237R1
|
||||||
MODE=read-only
|
MODE=read-only
|
||||||
COMPONENT=homelab-backup-v2-final-acceptance-closeout
|
COMPONENT=homelab-backup-alert-spam-current-rca
|
||||||
MUTATION_BOUNDARY=FINAL_OBSERVATIONAL_ACCEPTANCE_ONLY;NO_BACKUP;NO_PERSISTENT_LOCK_OWNERSHIP;NO_CONFIG_WRITE;NO_WRAPPER_WRITE;NO_RELEASE_WRITE;NO_SYSTEMD_ACTION;NO_TIMER_CHANGE;NO_AUDIT_HEALTH_WRITE;NO_RETENTION;NO_DELETE;NO_RESTORE;NO_MAIL;NO_GIT_WRITE;NO_NETBIRD_SKLADCHIK_CHANGE
|
MUTATION_BOUNDARY=READ_ONLY_ALERT_HEALTH_STATE_SOURCE_JOURNAL_LOCK_AND_QUIET_AUDIT;NO_ALERT_EXECUTION;NO_MAIL;NO_BACKUP;NO_CONFIG_WRITE;NO_WRAPPER_WRITE;NO_RELEASE_WRITE;NO_SYSTEMD_ACTION;NO_TIMER_CHANGE;NO_HEALTH_WRITE;NO_GIT_WRITE;NO_RETENTION;NO_DELETE;NO_RESTORE;NO_NETBIRD_SKLADCHIK_CHANGE
|
||||||
=== SOURCE_AUTHORITY ===
|
=== AUTHORITY ===
|
||||||
HOST=pve01
|
HOST=pve01
|
||||||
CLUSTER_QUORATE=Yes
|
CLUSTER_QUORATE=Yes
|
||||||
RUNNER_SHA256=b248a4c32c9cc64e5747e7dce6c7fc0a23f5124a77c71ce72e27a81aceae9d2d
|
RUNNER_SHA256=b248a4c32c9cc64e5747e7dce6c7fc0a23f5124a77c71ce72e27a81aceae9d2d
|
||||||
SOURCE_1235_STATUS=OK
|
SOURCE_1236_STATUS=OK
|
||||||
SOURCE_1235_RC=0
|
SOURCE_1236_RC=0
|
||||||
SOURCE_1235_DECISION=PASS_LOCK_AWARE_RPO_RECOVERY_GREEN
|
SOURCE_1236_CHANGES_MADE=false
|
||||||
SOURCE_1235_NEXT_GATE=FINAL_BACKUP_ACCEPTANCE_CLOSEOUT
|
SOURCE_1236_DECISION=HOLD_1236_V2_SERVICE_LAST_RUN_NOT_SUCCESS
|
||||||
SOURCE_1235_FINAL_AUDIT_RC=0
|
SOURCE_1236_NEXT_GATE=RECONCILE_POST_RECOVERY_SCHEDULER
|
||||||
SOURCE_1235_FINAL_ISSUE_COUNT=0
|
SOURCE_1236_POST_RECOVERY_V2_FAILED_COUNT=0
|
||||||
SOURCE_1235_FINAL_RPO_COUNT=0
|
SOURCE_1236_POST_RECOVERY_FRESH_HELPER_FAILED_COUNT=0
|
||||||
SOURCE_1235_FINAL_NON_RPO_COUNT=0
|
SOURCE_1236_POST_RECOVERY_SCHEDULE_SUCCESS_COUNT=7
|
||||||
SOURCE_1235_TARGETED_REFRESH_COUNT=11
|
=== LIVE_IDENTITIES ===
|
||||||
SOURCE_1235_SUCCESS_MAIL_POLICY_ACCEPTED=true
|
|
||||||
SOURCE_1235_RECOVERY_END_EPOCH=1790545685
|
|
||||||
=== LIVE_IMMUTABLE_IDENTITIES ===
|
|
||||||
WRAPPER_SHA256=894f8ea346b53a3d7846dbd6eeb5b89333957eb6d7a4f2f64fd4557cae176e1c
|
WRAPPER_SHA256=894f8ea346b53a3d7846dbd6eeb5b89333957eb6d7a4f2f64fd4557cae176e1c
|
||||||
HELPER_SHA256=4e39404b1ddb97392645adce6280f697182cca03714d3a462d363eebce9b1860
|
HELPER_SHA256=4e39404b1ddb97392645adce6280f697182cca03714d3a462d363eebce9b1860
|
||||||
VZDUMP_CONF_SHA256=027e4b04852a4b83d558eb861d432b6fad4f234e12ab77d327f274d0fdedbfad
|
VZDUMP_CONF_SHA256=027e4b04852a4b83d558eb861d432b6fad4f234e12ab77d327f274d0fdedbfad
|
||||||
AUDIT_SHA256=f7b936fa997bdefdd0c3c5d1d96e496888ebebc8ea85a60ed3bf5bcc9bf4962a
|
AUDIT_SHA256=f7b936fa997bdefdd0c3c5d1d96e496888ebebc8ea85a60ed3bf5bcc9bf4962a
|
||||||
RELEASE_META=500:root:root
|
ALERT_SCRIPT_SHA256=2b92cd44fc5b43decba0ea0706c4c84e1912cdc6d7b9bcb10bbf9552c98dc3f9
|
||||||
RELEASE_FILESET=entry504.py fresh_lxc_helper.py lxc_adapter.py producer_exec_helper.py qemu_adapter.py scheduler_adapter.py
|
=== CURRENT_UNIT_STATE ===
|
||||||
RELEASE_FILESET_EXPECTED=entry504.py fresh_lxc_helper.py lxc_adapter.py producer_exec_helper.py qemu_adapter.py scheduler_adapter.py
|
|
||||||
RELEASE_FILE=fresh_lxc_helper.py SHA256=4e39404b1ddb97392645adce6280f697182cca03714d3a462d363eebce9b1860 META=400:root:root
|
|
||||||
RELEASE_FILE=producer_exec_helper.py SHA256=b3b97099bcd7126670f866e81faae6a42a96d869d9989e6a67f6ea6c871c90b3 META=400:root:root
|
|
||||||
RELEASE_FILE=lxc_adapter.py SHA256=3fa7d194010d76f7c8bc95035ae8876262e9337903e310f45f45df88c266dc8d META=400:root:root
|
|
||||||
RELEASE_FILE=qemu_adapter.py SHA256=1906db42bd34bbe85eb46fd9797b3572d46e0a41c29d1c29be5f9df5e448f15b META=400:root:root
|
|
||||||
RELEASE_FILE=scheduler_adapter.py SHA256=a6f67159a64067773323f028126e3109e15cf17a8142cea5e6129970f1d4da96 META=400:root:root
|
|
||||||
RELEASE_FILE=entry504.py SHA256=ca6876fa9c3b1465b045344a8ad46962de16972c7dadc4ac6257c7d225047793 META=400:root:root
|
|
||||||
=== ROLLBACK_AUTHORITY ===
|
|
||||||
ROLLBACK_PATH=/var/lib/homelab-change-rollback/SUPPORT-260927-HOMELAB-BACKUP-NOTIFICATION-COMPAT-HOTFIX-1230R1/homelab-backup-v2.before
|
|
||||||
ROLLBACK_EXISTS=true
|
|
||||||
ROLLBACK_SHA256=5077444065c732451cb84898680f62361b21a24ef9eb4f191253e82ead524ea2
|
|
||||||
=== CANONICAL_SOURCE_AUTHORITY ===
|
|
||||||
SOURCE_HEAD=db592a25c6ac587bf16472a6132b66698c42f663
|
|
||||||
SOURCE_BRANCH=cr-2026-1005-backup-v2-health-alerting-remediation
|
|
||||||
SOURCE_REMOTE_HEAD=db592a25c6ac587bf16472a6132b66698c42f663
|
|
||||||
SOURCE_WORKTREE_CLEAN=true
|
|
||||||
=== UNIT_AND_TIMER_CURRENT ===
|
|
||||||
UNIT=homelab-backup-v2.service ACTIVE=activating ENABLED=static RESULT=success EXEC_MAIN_STATUS=0 MAINPID=1856481
|
UNIT=homelab-backup-v2.service ACTIVE=activating ENABLED=static RESULT=success EXEC_MAIN_STATUS=0 MAINPID=1856481
|
||||||
UNIT=homelab-backup-v2.timer ACTIVE=active ENABLED=enabled RESULT=success EXEC_MAIN_STATUS= MAINPID=
|
UNIT=homelab-backup-v2.timer ACTIVE=active ENABLED=enabled RESULT=success EXEC_MAIN_STATUS= MAINPID=
|
||||||
UNIT=homelab-backup-audit.service ACTIVE=failed ENABLED=static RESULT=exit-code EXEC_MAIN_STATUS=1 MAINPID=0
|
UNIT=homelab-backup-audit.service ACTIVE=failed ENABLED=static RESULT=exit-code EXEC_MAIN_STATUS=1 MAINPID=0
|
||||||
UNIT=homelab-backup-audit.timer ACTIVE=active ENABLED=enabled RESULT=success EXEC_MAIN_STATUS= MAINPID=
|
UNIT=homelab-backup-audit.timer ACTIVE=active ENABLED=enabled RESULT=success EXEC_MAIN_STATUS= MAINPID=
|
||||||
=== POST_RECOVERY_SCHEDULER_JOURNAL ===
|
UNIT=homelab-alertmanager-backup-health.service ACTIVE=inactive ENABLED=static RESULT=success EXEC_MAIN_STATUS=0 MAINPID=0
|
||||||
2026-09-28T01:12:52.217428+03:00 pve01 systemd[1]: Starting homelab-backup-v2.service - Homelab Backup V2 manifest-driven scheduler...
|
UNIT=homelab-alertmanager-backup-health.timer ACTIVE=active ENABLED=enabled RESULT=success EXEC_MAIN_STATUS= MAINPID=
|
||||||
2026-09-28T01:25:14.480529+03:00 pve01 homelab-backup-v2[815211]: SCHEDULE_TARGET=xf-codevipe
|
=== CURRENT_HEALTH_FILES ===
|
||||||
2026-09-28T01:25:14.480529+03:00 pve01 homelab-backup-v2[815211]: SCHEDULE_RESULT=SUCCESS
|
HEALTH1_EXISTS=true
|
||||||
2026-09-28T01:25:14.488885+03:00 pve01 systemd[1]: Finished homelab-backup-v2.service - Homelab Backup V2 manifest-driven scheduler.
|
HEALTH1_SHA256=d89fb55b92f2b9908e2d2d8da3b9a0d0db6d2fe84c6e6d37bcec1a86e4384222
|
||||||
2026-09-28T01:49:49.378146+03:00 pve01 systemd[1]: Starting homelab-backup-v2.service - Homelab Backup V2 manifest-driven scheduler...
|
HEALTH1_JSON_OK=true
|
||||||
2026-09-28T02:03:38.623364+03:00 pve01 homelab-backup-v2[943938]: SCHEDULE_TARGET=xf-zakrutim
|
HEALTH1_SCHEMA=homelab-backup-audit-v3
|
||||||
2026-09-28T02:03:38.623364+03:00 pve01 homelab-backup-v2[943938]: SCHEDULE_RESULT=SUCCESS
|
HEALTH1_STATUS=RED
|
||||||
2026-09-28T02:03:38.630266+03:00 pve01 systemd[1]: Finished homelab-backup-v2.service - Homelab Backup V2 manifest-driven scheduler.
|
HEALTH1_GENERATED_AT_EPOCH=1790568997
|
||||||
2026-09-28T02:29:32.216618+03:00 pve01 systemd[1]: Starting homelab-backup-v2.service - Homelab Backup V2 manifest-driven scheduler...
|
HEALTH1_AGE_SECONDS=855
|
||||||
2026-09-28T02:29:49.327002+03:00 pve01 homelab-backup-v2[1072063]: SCHEDULE_TARGET=vm210
|
HEALTH1_ISSUE_COUNT=2
|
||||||
2026-09-28T02:30:55.417267+03:00 pve01 homelab-backup-v2[1072063]: SCHEDULE_RESULT=SUCCESS
|
HEALTH1_ISSUE_1={"code":"LOCK_BUSY","logical_id":"/run/homelab-backup-heavy.lock","root_cause":"ACTIVE_OR_ORPHAN_LOCK","severity":"HIGH"}
|
||||||
2026-09-28T02:30:55.424354+03:00 pve01 systemd[1]: Finished homelab-backup-v2.service - Homelab Backup V2 manifest-driven scheduler.
|
HEALTH1_ISSUE_2={"code":"SOURCE_OFFHOST_MISSING","logical_id":"-","root_cause":"CR_BRANCH_SHA_NOT_EXACT","severity":"MEDIUM"}
|
||||||
2026-09-28T03:01:22.218704+03:00 pve01 systemd[1]: Starting homelab-backup-v2.service - Homelab Backup V2 manifest-driven scheduler...
|
HEALTH1_SOURCE_LOCAL_HEAD=db592a25c6ac587bf16472a6132b66698c42f663
|
||||||
2026-09-28T03:01:54.164165+03:00 pve01 homelab-backup-v2[1179144]: SCHEDULE_TARGET=vm211
|
HEALTH1_SOURCE_REMOTE_HEAD=None
|
||||||
2026-09-28T03:03:04.842495+03:00 pve01 homelab-backup-v2[1179144]: SCHEDULE_RESULT=SUCCESS
|
HEALTH1_SOURCE_PUSHURL_DISABLED=true
|
||||||
2026-09-28T03:03:04.849383+03:00 pve01 systemd[1]: Finished homelab-backup-v2.service - Homelab Backup V2 manifest-driven scheduler.
|
HEALTH1_SOURCE_EXACT=false
|
||||||
2026-09-28T03:34:32.216619+03:00 pve01 systemd[1]: Starting homelab-backup-v2.service - Homelab Backup V2 manifest-driven scheduler...
|
HEALTH2_EXISTS=true
|
||||||
2026-09-28T05:14:16.727192+03:00 pve01 homelab-backup-v2[1320207]: SCHEDULE_TARGET=xf-dsmods
|
HEALTH2_SHA256=d89fb55b92f2b9908e2d2d8da3b9a0d0db6d2fe84c6e6d37bcec1a86e4384222
|
||||||
2026-09-28T05:14:16.727192+03:00 pve01 homelab-backup-v2[1320207]: SCHEDULE_RESULT=SUCCESS
|
HEALTH2_JSON_OK=true
|
||||||
2026-09-28T05:14:16.733465+03:00 pve01 systemd[1]: Finished homelab-backup-v2.service - Homelab Backup V2 manifest-driven scheduler.
|
HEALTH2_SCHEMA=homelab-backup-audit-v3
|
||||||
2026-09-28T05:14:16.735708+03:00 pve01 systemd[1]: Starting homelab-backup-v2.service - Homelab Backup V2 manifest-driven scheduler...
|
HEALTH2_STATUS=RED
|
||||||
2026-09-28T05:24:43.293853+03:00 pve01 homelab-backup-v2[1647429]: SCHEDULE_TARGET=xf-kingofwolk
|
HEALTH2_GENERATED_AT_EPOCH=1790568997
|
||||||
2026-09-28T05:24:43.293853+03:00 pve01 homelab-backup-v2[1647429]: SCHEDULE_RESULT=SUCCESS
|
HEALTH2_AGE_SECONDS=855
|
||||||
2026-09-28T05:24:43.300102+03:00 pve01 systemd[1]: Finished homelab-backup-v2.service - Homelab Backup V2 manifest-driven scheduler.
|
HEALTH2_ISSUE_COUNT=2
|
||||||
2026-09-28T05:45:12.220837+03:00 pve01 systemd[1]: Starting homelab-backup-v2.service - Homelab Backup V2 manifest-driven scheduler...
|
HEALTH2_ISSUE_1={"code":"LOCK_BUSY","logical_id":"/run/homelab-backup-heavy.lock","root_cause":"ACTIVE_OR_ORPHAN_LOCK","severity":"HIGH"}
|
||||||
2026-09-28T05:52:51.548422+03:00 pve01 homelab-backup-v2[1737475]: SCHEDULE_TARGET=xf-newfi
|
HEALTH2_ISSUE_2={"code":"SOURCE_OFFHOST_MISSING","logical_id":"-","root_cause":"CR_BRANCH_SHA_NOT_EXACT","severity":"MEDIUM"}
|
||||||
2026-09-28T05:52:51.548422+03:00 pve01 homelab-backup-v2[1737475]: SCHEDULE_RESULT=SUCCESS
|
HEALTH2_SOURCE_LOCAL_HEAD=db592a25c6ac587bf16472a6132b66698c42f663
|
||||||
2026-09-28T05:52:51.557165+03:00 pve01 systemd[1]: Finished homelab-backup-v2.service - Homelab Backup V2 manifest-driven scheduler.
|
HEALTH2_SOURCE_REMOTE_HEAD=None
|
||||||
|
HEALTH2_SOURCE_PUSHURL_DISABLED=true
|
||||||
|
HEALTH2_SOURCE_EXACT=false
|
||||||
|
HEALTH_FILES_IDENTICAL=true
|
||||||
|
HEALTH_EPOCH_VALID=true
|
||||||
|
=== CURRENT_ALERT_STATE ===
|
||||||
|
ALERT_STATE_EXISTS=true
|
||||||
|
ALERT_STATE_SHA256=493ce50563cb31030f2b16ff4ad722a7ac5ec211a77b2e89625491c057e8827d
|
||||||
|
ALERT_STATE_JSON_OK=true
|
||||||
|
ALERT_STATE_KEYS=code_counts,issue_keys,migration_silent,notify_tokens,raw_issue_keys,schema,updated_epoch
|
||||||
|
ALERT_STATE_SAFE_JSON={"code_counts":{"LOCK_BUSY":4,"SOURCE_OFFHOST_MISSING":263},"issue_keys":["LOCK_BUSY|/run/homelab-backup-heavy.lock|ACTIVE_OR_ORPHAN_LOCK","SOURCE_OFFHOST_MISSING|-|CR_BRANCH_SHA_NOT_EXACT"],"migration_silent":false,"notify_tokens":"[REDACTED]","raw_issue_keys":["LOCK_BUSY|/run/homelab-backup-heavy.lock|ACTIVE_OR_ORPHAN_LOCK","SOURCE_OFFHOST_MISSING|-|CR_BRANCH_SHA_NOT_EXACT"],"schema":"homelab-backup-alert-state-v2","updated_epoch":1790569001}
|
||||||
|
ALERT_STATE_SAFE_TRUNCATED=false
|
||||||
|
ALERT_STATE_FIELD_SCHEMA="homelab-backup-alert-state-v2"
|
||||||
|
ALERT_STATE_FIELD_UPDATED_EPOCH=1790569001
|
||||||
|
ALERT_STATE_FIELD_ISSUE_KEYS=["LOCK_BUSY|/run/homelab-backup-heavy.lock|ACTIVE_OR_ORPHAN_LOCK","SOURCE_OFFHOST_MISSING|-|CR_BRANCH_SHA_NOT_EXACT"]
|
||||||
|
=== ALERT_FILTER_SOURCE ===
|
||||||
|
ALERT_EMBEDDED_SOURCE_FOUND=true
|
||||||
|
ALERT_EMBEDDED_SOURCE_SHA256=344306105083cd8bc64e19d451f7f66c17accc43a2f413538d2f9e2687b2540e
|
||||||
|
ALERT_EMBEDDED_SOURCE_BEGIN
|
||||||
|
0001:import sys,os,json,re,subprocess,pathlib,time
|
||||||
|
0002:mode=sys.argv[1]
|
||||||
|
0003:AUDIT="/usr/local/sbin/homelab-backup-audit"
|
||||||
|
0004:HEALTH=pathlib.Path("/var/lib/homelab-health/backup-audit-v2.json")
|
||||||
|
0005:STATE=pathlib.Path("/var/lib/homelab-alerting/backup-alert-state.json")
|
||||||
|
0006:USERCFG=pathlib.Path("/etc/pve/user.cfg")
|
||||||
|
0007:SCHEMA="homelab-backup-alert-state-v2"
|
||||||
|
0008:THRESHOLDS={"RPO_BREACH":2,"SOURCE_OFFHOST_MISSING":2,"LOCK_BUSY":3}
|
||||||
|
0009:def recipient():
|
||||||
|
0010: text=USERCFG.read_text(encoding="utf-8",errors="replace")
|
||||||
|
0011: m=re.findall(r"(?i)\b[A-Z0-9._+-]+@[A-Z0-9.-]+\.[A-Z]{2,}\b",text)
|
||||||
|
0012: if len(m)!=1: raise SystemExit(65)
|
||||||
|
0013: return m[0]
|
||||||
|
0014:def send(subject,body):
|
||||||
|
0015: rcpt=recipient()
|
||||||
|
0016: msg=f"From: h***@gram1.ru\nTo: {rcpt}\nSubject: {subject}\nContent-Type: text/plain; charset=UTF-8\n\n{body}\n"
|
||||||
|
0017: p=subprocess.run(["/usr/sbin/sendmail","-t"],input=msg,text=True,stdout=subprocess.PIPE,stderr=subprocess.PIPE)
|
||||||
|
0018: if p.returncode!=0: raise SystemExit(p.returncode or 75)
|
||||||
|
0019:def key(i):
|
||||||
|
0020: return "|".join(str(i.get(x,"")) for x in ("code","logical_id","root_cause"))
|
||||||
|
0021:def token(i):[REDACTED]
|
||||||
|
0022: code=str(i.get("code",""))
|
||||||
|
0023: return "group:"+code if code in THRESHOLDS else "issue:"+key(i)
|
||||||
|
0024:if mode=="email-test":
|
||||||
|
0025: send("Workers2 backup alerting test","Workers2 backup/DR alerting route test. If you received this, the local MTA accepted the controlled test generated during backup closure.")
|
||||||
|
0026: print("EMAIL_TEST_ACCEPTED=YES")
|
||||||
|
0027: raise SystemExit(0)
|
||||||
|
0028:if mode!="health-alert": raise SystemExit(64)
|
||||||
|
0029:p=subprocess.run([AUDIT,"write-health"],text=True,stdout=subprocess.PIPE,stderr=subprocess.PIPE)
|
||||||
|
0030:if p.returncode not in (0,1): raise SystemExit(p.returncode or 75)
|
||||||
|
0031:try:
|
||||||
|
0032: h=json.loads(HEALTH.read_text(encoding="utf-8"))
|
||||||
|
0033:except Exception:
|
||||||
|
0034: raise SystemExit(69)
|
||||||
|
0035:issues=h.get("issues") if isinstance(h.get("issues"),list) else []
|
||||||
|
0036:cur={key(i):i for i in issues if isinstance(i,dict)}
|
||||||
|
0037:codes=set(str(i.get("code","")) for i in cur.values())
|
||||||
|
0038:oldj={}
|
||||||
|
0039:if STATE.is_file():
|
||||||
|
0040: try:
|
||||||
|
0041: oldj=json.loads(STATE.read_text(encoding="utf-8"))
|
||||||
|
0042: if not isinstance(oldj,dict): oldj={}
|
||||||
|
0043: except Exception:
|
||||||
|
0044: oldj={}
|
||||||
|
0045:migrating=oldj.get("schema")!=SCHEMA
|
||||||
|
0046:prev_counts=oldj.get("code_counts") if isinstance(oldj.get("code_counts"),dict) and not migrating else {}
|
||||||
|
0047:counts={}
|
||||||
|
0048:for code in codes:
|
||||||
|
0049: try: prev=int(prev_counts.get(code,0))
|
||||||
|
0050: except Exception: prev=0
|
||||||
|
0051: counts[code]=prev+1
|
||||||
|
0052:actionable={}
|
||||||
|
0053:for k,i in cur.items():
|
||||||
|
0054: code=str(i.get("code",""))
|
||||||
|
0055: need=int(THRESHOLDS.get(code,1))
|
||||||
|
0056: if counts.get(code,0)>=need:
|
||||||
|
0057: actionable[k]=i
|
||||||
|
0058:tokens=[REDACTED]
|
||||||
|
0059:old_tokens=[REDACTED]
|
||||||
|
0060:if not migrating:
|
||||||
|
0061: old_tokens=[REDACTED]
|
||||||
|
0062:added=[REDACTED]
|
||||||
|
0063:removed=[REDACTED]
|
||||||
|
0064:if added:
|
||||||
|
0065: lines=[
|
||||||
|
0066: "Workers2 backup/DR actionable alert state changed.",
|
||||||
|
0067: "",
|
||||||
|
0068: "Transient debounce policy: RPO_BREACH=2 checks; SOURCE_OFFHOST_MISSING=2 checks; LOCK_BUSY=3 checks; all other issue codes=immediate.",
|
||||||
|
0069: ""
|
||||||
|
0070: ]
|
||||||
|
0071: for k in sorted(actionable):
|
||||||
|
0072: i=actionable[k]
|
||||||
|
0073: lines.append(f"{i.get('severity','UNKNOWN')} {i.get('code','UNKNOWN')} logical_id={i.get('logical_id','-')} root_cause={i.get('root_cause','UNKNOWN')}")
|
||||||
|
0074: suppressed=len(cur)-len(actionable)
|
||||||
|
0075: if suppressed:
|
||||||
|
0076: lines.extend(["",f"Suppressed transient issue(s) still below threshold: {suppressed}"])
|
||||||
|
0077: send(f"[Workers2 BACKUP ALERT] {len(actionable)} actionable issue(s)","\n".join(lines))
|
||||||
|
0078: print("ALERT_EMAIL_ACCEPTED=YES")
|
||||||
|
0079:elif old_tokens and not tokens:[REDACTED]
|
||||||
|
0080: send("[Workers2 BACKUP RECOVERY] all actionable issues cleared","Workers2 backup/DR actionable audit state is clear. All previously notified actionable backup issues are cleared.")
|
||||||
|
0081: print("RECOVERY_EMAIL_ACCEPTED=YES")
|
||||||
|
0082:STATE.parent.mkdir(parents=True,exist_ok=True)
|
||||||
|
0083:tmp=STATE.with_name(STATE.name+".tmp")
|
||||||
|
0084:payload={
|
||||||
|
0085: "schema":SCHEMA,
|
||||||
|
0086: "updated_epoch":int(time.time()),
|
||||||
|
0087: "issue_keys":sorted(actionable),
|
||||||
|
0088: "notify_tokens":[REDACTED]
|
||||||
|
0089: "raw_issue_keys":sorted(cur),
|
||||||
|
0090: "code_counts":{k:int(v) for k,v in sorted(counts.items())},
|
||||||
|
0091: "migration_silent":bool(migrating)
|
||||||
|
0092:}
|
||||||
|
0093:tmp.write_text(json.dumps(payload,separators=(",",":"),sort_keys=True)+"\n",encoding="utf-8")
|
||||||
|
0094:os.chmod(tmp,0o600)
|
||||||
|
0095:os.replace(tmp,STATE)
|
||||||
|
0096:print("ALERT_FILTER_SCHEMA="+SCHEMA)
|
||||||
|
0097:print("ALERT_RAW_ISSUE_COUNT="+str(len(cur)))
|
||||||
|
0098:print("ALERT_ACTIONABLE_ISSUE_COUNT="+str(len(actionable)))
|
||||||
|
0099:print("ALERT_NOTIFY_TOKEN_COUNT=[REDACTED]
|
||||||
|
0100:print("ALERT_ADDED_TOKEN_COUNT=[REDACTED]
|
||||||
|
0101:print("ALERT_REMOVED_TOKEN_COUNT=[REDACTED]
|
||||||
|
0102:print("ALERT_SUPPRESSED_TRANSIENT_COUNT="+str(len(cur)-len(actionable)))
|
||||||
|
0103:print("ALERT_STATE_MIGRATION_SILENT="+("true" if migrating else "false"))
|
||||||
|
0104:print("HEALTH_ALERT_STATE=OK")
|
||||||
|
ALERT_EMBEDDED_SOURCE_END
|
||||||
|
=== AUDIT_SOURCE_RELEVANT ===
|
||||||
|
183- ("homelab-alertmanager-backup-health.timer","ALERT_TIMER_BAD"),
|
||||||
|
184-]:
|
||||||
|
185- ok,a,e=unit_ok(unit)
|
||||||
|
186- if not ok: issues.append({"severity":"HIGH","code":code,"logical_id":unit,"root_cause":"UNIT_"+a+"_"+e})
|
||||||
|
187-
|
||||||
|
188:for lock in ["/run/homelab-backup-heavy.lock","/run/lock/homelab-app-cloud-quorum-queue.lock","/run/lock/homelab-vm-cloud-quorum-queue.lock","/run/lock/homelab-backup-dispatcher.lock"]:
|
||||||
|
189- p=pathlib.Path(lock)
|
||||||
|
190- if p.exists():
|
||||||
|
191: lrc,_,_=run(["flock","-n",str(p),"-c","true"],5)
|
||||||
|
192: if lrc!=0: issues.append({"severity":"HIGH","code":"LOCK_BUSY","logical_id":lock,"root_cause":"ACTIVE_OR_ORPHAN_LOCK"})
|
||||||
|
193-
|
||||||
|
194-env=os.environ.copy(); env["HOMELAB_BACKUP_GFS_POLICY"]=GFSP; env["HOMELAB_BACKUP_TARGET_REGISTRY"]=str(REG)
|
||||||
|
195-grc,gout,_=run([GFSH,"validate"],20,env)
|
||||||
|
196-if grc!=0 or "GFS_POLICY=OK" not in gout:
|
||||||
|
197- issues.append({"severity":"CRITICAL","code":"GFS_INVALID","logical_id":"-","root_cause":"GFS_VALIDATE_FAILED"})
|
||||||
|
--
|
||||||
|
287-except Exception:
|
||||||
|
288- cloudb_ok=False
|
||||||
|
289-if not cloudb_ok:
|
||||||
|
290- issues.append({"severity":"CRITICAL","code":"CLOUD_B_RESTORE_DRILL_BAD","logical_id":"app-skladchik-reports-monitor","root_cause":"CANONICAL_CLOUD_B_PAYLOAD_OR_RESTORE_EVIDENCE_NOT_OK"})
|
||||||
|
291-
|
||||||
|
292:source={"local_head":None,"remote_head":None,"pushurl_disabled":False}
|
||||||
|
293-hrc,ho,_=run(["git","-C",WT,"rev-parse","HEAD"],10)
|
||||||
|
294:if hrc==0: source["local_head"]=ho.strip()
|
||||||
|
295-frc,fo,_=run(["git","-C",WT,"config","--get","remote.origin.url"],10)
|
||||||
|
296-prc,po,_=run(["git","-C",WT,"config","--get","remote.origin.pushurl"],10)
|
||||||
|
297-source["pushurl_disabled"]=(prc==0 and po.strip()=="DISABLED")
|
||||||
|
298-if frc==0 and fo.strip():
|
||||||
|
299- lrc,lo,_=run(["git","ls-remote",fo.strip(),"refs/heads/"+BRANCH],30)
|
||||||
|
300: if lrc==0 and lo.strip(): source["remote_head"]=lo.split()[0]
|
||||||
|
301:if source["remote_head"]!=source["local_head"]:
|
||||||
|
302: issues.append({"severity":"MEDIUM","code":"SOURCE_OFFHOST_MISSING","logical_id":"-","root_cause":"CR_BRANCH_SHA_NOT_EXACT"})
|
||||||
|
303-
|
||||||
|
304-status="GREEN" if not issues else "RED"
|
||||||
|
305-for t in targets:
|
||||||
|
306- print("TARGET|"+"|".join(f"{k}={v}" for k,v in t.items() if v is not None))
|
||||||
|
307-for i in issues:
|
||||||
|
308- print("ISSUE|severity={severity}|code={code}|logical_id={logical_id}|root_cause={root_cause}".format(**i))
|
||||||
|
309:print(f"SUMMARY|AUDIT_STATUS=OK|BACKUP_STATUS={status}|ACTIVE_COUNT={len(active)}|ISSUE_COUNT={len(issues)}|CLOUD_A={'OK' if cloud.get('A',{}).get('readable') else 'BAD'}|CLOUD_B={'OK' if cloud.get('B',{}).get('readable') else 'BAD'}|CLOUD_B_DRILL={'OK' if cloudb_ok else 'BAD'}|DR_PROVEN={'YES' if isinstance(dr,dict) and dr.get('status')=='SEALED' else 'NO'}|SOURCE_OFFHOST={'OK' if source['remote_head']==source['local_head'] else 'PENDING'}")
|
||||||
|
310-health={"schema":"homelab-backup-audit-v3","status":status,"generated_at_epoch":now,"targets":targets,"issues":issues,"cloud":cloud,"source":source,"cloud_b_restore_drill":cloudb_ok,"dr_proven":bool(isinstance(dr,dict) and dr.get("status")=="SEALED")}
|
||||||
|
311-if MODE in ("write-health","scheduled"):
|
||||||
|
312- for hp in HEALTHS:
|
||||||
|
313- hp.parent.mkdir(parents=True,exist_ok=True)
|
||||||
|
314- tmp=hp.with_name(hp.name+".tmp")
|
||||||
|
=== LIVE_SOURCE_HEAD_RECHECK ===
|
||||||
|
SOURCE_LOCAL_HEAD=db592a25c6ac587bf16472a6132b66698c42f663
|
||||||
|
SOURCE_BRANCH=cr-2026-1005-backup-v2-health-alerting-remediation
|
||||||
|
SOURCE_WORKTREE_CLEAN=true
|
||||||
|
SOURCE_ORIGIN_URL_SHA256=7507b97d441d05c4e33306608cbf655e96bf2add0ec7683cc2f4e5539f64daf9
|
||||||
|
SOURCE_REMOTE_ATTEMPT=1 HEAD=db592a25c6ac587bf16472a6132b66698c42f663 STDERR_BYTES=0 EXACT=true
|
||||||
|
SOURCE_REMOTE_ATTEMPT=2 HEAD=db592a25c6ac587bf16472a6132b66698c42f663 STDERR_BYTES=0 EXACT=true
|
||||||
|
SOURCE_REMOTE_ATTEMPT=3 HEAD=db592a25c6ac587bf16472a6132b66698c42f663 STDERR_BYTES=0 EXACT=true
|
||||||
|
SOURCE_REMOTE_ATTEMPT=4 HEAD=db592a25c6ac587bf16472a6132b66698c42f663 STDERR_BYTES=0 EXACT=true
|
||||||
|
SOURCE_REMOTE_ATTEMPT=5 HEAD=db592a25c6ac587bf16472a6132b66698c42f663 STDERR_BYTES=0 EXACT=true
|
||||||
|
=== CURRENT_LOCK_OWNERSHIP ===
|
||||||
|
LOCK_META=/run/homelab-backup-heavy.lock|inode=3474|600|root:root|2026-09-28 03:27:07.425060217 +0300
|
||||||
|
LOCK_FUSER=/run/homelab-backup-heavy.lock| 1856481
|
||||||
|
LOCK_FREE=/run/homelab-backup-heavy.lock|false
|
||||||
|
LOCK_META=/run/lock/homelab-backup-dispatcher.lock|inode=9|600|root:root|2026-09-28 03:27:07.423060188 +0300
|
||||||
|
LOCK_FUSER=/run/lock/homelab-backup-dispatcher.lock|
|
||||||
|
LOCK_FREE=/run/lock/homelab-backup-dispatcher.lock|true
|
||||||
|
LOCK_META=/run/lock/homelab-vm-cloud-quorum-queue.lock|inode=2944|600|root:root|2026-09-28 03:27:07.424060203 +0300
|
||||||
|
LOCK_FUSER=/run/lock/homelab-vm-cloud-quorum-queue.lock|
|
||||||
|
LOCK_FREE=/run/lock/homelab-vm-cloud-quorum-queue.lock|true
|
||||||
|
LOCK_META=/run/lock/homelab-app-cloud-quorum-queue.lock|inode=15|600|root:root|2026-09-28 03:27:07.425060217 +0300
|
||||||
|
LOCK_FUSER=/run/lock/homelab-app-cloud-quorum-queue.lock|
|
||||||
|
LOCK_FREE=/run/lock/homelab-app-cloud-quorum-queue.lock|true
|
||||||
|
homelab-backup- 1856481 FLOCK WRITE /run/homelab-backup-heavy.lock
|
||||||
|
=== ALERT_EMAIL_TIME_CORRELATION_0701_MSK ===
|
||||||
2026-09-28T06:19:01.361470+03:00 pve01 systemd[1]: Starting homelab-backup-v2.service - Homelab Backup V2 manifest-driven scheduler...
|
2026-09-28T06:19:01.361470+03:00 pve01 systemd[1]: Starting homelab-backup-v2.service - Homelab Backup V2 manifest-driven scheduler...
|
||||||
POST_RECOVERY_V2_START_COUNT=8
|
2026-09-28T06:36:20.418325+03:00 pve01 homelab-backup-audit[1908813]: ISSUE|severity=HIGH|code=LOCK_BUSY|logical_id=/run/homelab-backup-heavy.lock|root_cause=ACTIVE_OR_ORPHAN_LOCK
|
||||||
POST_RECOVERY_V2_FINISHED_COUNT=7
|
2026-09-28T06:36:20.418325+03:00 pve01 homelab-backup-audit[1908813]: SUMMARY|AUDIT_STATUS=OK|BACKUP_STATUS=RED|ACTIVE_COUNT=16|ISSUE_COUNT=1|CLOUD_A=OK|CLOUD_B=OK|CLOUD_B_DRILL=OK|DR_PROVEN=YES|SOURCE_OFFHOST=OK
|
||||||
POST_RECOVERY_V2_FAILED_COUNT=0
|
2026-09-28T06:36:20.423980+03:00 pve01 systemd[1]: homelab-backup-audit.service: Main process exited, code=exited, status=1/FAILURE
|
||||||
POST_RECOVERY_FRESH_HELPER_FAILED_COUNT=0
|
2026-09-28T06:36:20.424205+03:00 pve01 systemd[1]: Failed to start homelab-backup-audit.service - Homelab unified backup and DR audit.
|
||||||
POST_RECOVERY_SCHEDULE_SUCCESS_COUNT=7
|
2026-09-28T07:06:48.299695+03:00 pve01 homelab-backup-audit[2011656]: ISSUE|severity=HIGH|code=LOCK_BUSY|logical_id=/run/homelab-backup-heavy.lock|root_cause=ACTIVE_OR_ORPHAN_LOCK
|
||||||
POST_RECOVERY_SCHEDULE_DEFER_COUNT=0
|
2026-09-28T07:06:48.299695+03:00 pve01 homelab-backup-audit[2011656]: SUMMARY|AUDIT_STATUS=OK|BACKUP_STATUS=RED|ACTIVE_COUNT=16|ISSUE_COUNT=1|CLOUD_A=OK|CLOUD_B=OK|CLOUD_B_DRILL=OK|DR_PROVEN=YES|SOURCE_OFFHOST=OK
|
||||||
V2_SERVICE_RESULT=success
|
2026-09-28T07:06:48.304891+03:00 pve01 systemd[1]: homelab-backup-audit.service: Main process exited, code=exited, status=1/FAILURE
|
||||||
V2_SERVICE_EXEC_MAIN_STATUS=0
|
2026-09-28T07:06:48.305137+03:00 pve01 systemd[1]: Failed to start homelab-backup-audit.service - Homelab unified backup and DR audit.
|
||||||
V2_SERVICE_ACTIVE=activating
|
2026-09-28T06:15:16.319082+03:00 pve01 systemd[1]: Starting homelab-alertmanager-backup-health.service - Workers2 backup health alert via existing alertmanager backup integration...
|
||||||
BACKUP_PROJECT_COMPLETE=false
|
2026-09-28T06:15:20.661916+03:00 pve01 homelab-alertmanager-backup-run[1835343]: HEALTH_ALERT_STATE=OK
|
||||||
TASK_RESULT=HOLD_BACKUP_V2_FINAL_ACCEPTANCE_CLOSEOUT
|
2026-09-28T06:15:20.666144+03:00 pve01 systemd[1]: Finished homelab-alertmanager-backup-health.service - Workers2 backup health alert via existing alertmanager backup integration.
|
||||||
DECISION=HOLD_1236_V2_SERVICE_LAST_RUN_NOT_SUCCESS
|
2026-09-28T06:30:42.414371+03:00 pve01 systemd[1]: Starting homelab-alertmanager-backup-health.service - Workers2 backup health alert via existing alertmanager backup integration...
|
||||||
NEXT_GATE=RECONCILE_POST_RECOVERY_SCHEDULER
|
2026-09-28T06:30:46.367196+03:00 pve01 homelab-alertmanager-backup-run[1886013]: HEALTH_ALERT_STATE=OK
|
||||||
HOMELAB_RESULT_CONTRACT={"version":1,"command_id":"SUPPORT-260928-HOMELAB-BACKUP-V2-FINAL-ACCEPTANCE-CLOSEOUT-1236R1","status":"OK","changes_made":false,"rollback_started":false,"rollback_restored":null}
|
2026-09-28T06:30:46.370827+03:00 pve01 systemd[1]: Finished homelab-alertmanager-backup-health.service - Workers2 backup health alert via existing alertmanager backup integration.
|
||||||
|
2026-09-28T06:46:01.347189+03:00 pve01 systemd[1]: Starting homelab-alertmanager-backup-health.service - Workers2 backup health alert via existing alertmanager backup integration...
|
||||||
|
2026-09-28T06:46:05.406037+03:00 pve01 homelab-alertmanager-backup-run[1945314]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T06:46:05.410491+03:00 pve01 systemd[1]: Finished homelab-alertmanager-backup-health.service - Workers2 backup health alert via existing alertmanager backup integration.
|
||||||
|
2026-09-28T07:01:32.217324+03:00 pve01 systemd[1]: Starting homelab-alertmanager-backup-health.service - Workers2 backup health alert via existing alertmanager backup integration...
|
||||||
|
2026-09-28T07:01:36.274466+03:00 pve01 homelab-alertmanager-backup-run[1988992]: ALERT_EMAIL_ACCEPTED=YES
|
||||||
|
2026-09-28T07:01:36.274466+03:00 pve01 homelab-alertmanager-backup-run[1988992]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T07:01:36.278152+03:00 pve01 systemd[1]: Finished homelab-alertmanager-backup-health.service - Workers2 backup health alert via existing alertmanager backup integration.
|
||||||
|
2026-09-28T07:16:37.585569+03:00 pve01 systemd[1]: Starting homelab-alertmanager-backup-health.service - Workers2 backup health alert via existing alertmanager backup integration...
|
||||||
|
2026-09-28T07:16:41.913014+03:00 pve01 homelab-alertmanager-backup-run[2048228]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T07:16:41.916768+03:00 pve01 systemd[1]: Finished homelab-alertmanager-backup-health.service - Workers2 backup health alert via existing alertmanager backup integration.
|
||||||
|
=== ALERT_FREQUENCY_LAST12H ===
|
||||||
|
ALERT_RUN_START_COUNT=0
|
||||||
|
ALERT_EMAIL_ACCEPTED_COUNT=3
|
||||||
|
RECOVERY_EMAIL_ACCEPTED_COUNT=0
|
||||||
|
HEALTH_ALERT_STATE_OK_COUNT=47
|
||||||
|
2026-09-27T19:32:04.991437+03:00 pve01 homelab-alertmanager-backup-run[3909103]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-27T19:47:36.328545+03:00 pve01 homelab-alertmanager-backup-run[3959645]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-27T20:02:46.359055+03:00 pve01 homelab-alertmanager-backup-run[4008840]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-27T20:18:05.225521+03:00 pve01 homelab-alertmanager-backup-run[4059785]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-27T20:33:20.585967+03:00 pve01 homelab-alertmanager-backup-run[4108890]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-27T20:48:36.460451+03:00 pve01 homelab-alertmanager-backup-run[4148152]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-27T21:04:08.100470+03:00 pve01 homelab-alertmanager-backup-run[4070]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-27T21:19:36.336976+03:00 pve01 homelab-alertmanager-backup-run[54137]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-27T21:35:05.706232+03:00 pve01 homelab-alertmanager-backup-run[104752]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-27T21:50:23.015203+03:00 pve01 homelab-alertmanager-backup-run[154365]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-27T22:05:36.461278+03:00 pve01 homelab-alertmanager-backup-run[202960]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-27T22:21:05.253758+03:00 pve01 homelab-alertmanager-backup-run[242449]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-27T22:36:15.399283+03:00 pve01 homelab-alertmanager-backup-run[292331]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-27T22:51:31.819800+03:00 pve01 homelab-alertmanager-backup-run[343850]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-27T23:06:53.759023+03:00 pve01 homelab-alertmanager-backup-run[396329]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-27T23:22:20.677831+03:00 pve01 homelab-alertmanager-backup-run[461385]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-27T23:37:36.973241+03:00 pve01 homelab-alertmanager-backup-run[513251]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-27T23:52:43.434843+03:00 pve01 homelab-alertmanager-backup-run[566888]: ALERT_EMAIL_ACCEPTED=YES
|
||||||
|
2026-09-27T23:52:43.434843+03:00 pve01 homelab-alertmanager-backup-run[566888]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T00:08:05.576769+03:00 pve01 homelab-alertmanager-backup-run[607129]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T00:23:21.212626+03:00 pve01 homelab-alertmanager-backup-run[660884]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T00:38:36.269886+03:00 pve01 homelab-alertmanager-backup-run[711652]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T00:53:55.974540+03:00 pve01 homelab-alertmanager-backup-run[762988]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T01:09:05.464301+03:00 pve01 homelab-alertmanager-backup-run[812499]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T01:24:16.127247+03:00 pve01 homelab-alertmanager-backup-run[862903]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T01:39:41.256513+03:00 pve01 homelab-alertmanager-backup-run[919688]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T01:54:54.298806+03:00 pve01 homelab-alertmanager-backup-run[958250]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T02:10:05.486220+03:00 pve01 homelab-alertmanager-backup-run[1009352]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T02:25:22.594856+03:00 pve01 homelab-alertmanager-backup-run[1058040]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T02:40:53.144072+03:00 pve01 homelab-alertmanager-backup-run[1108677]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T02:56:20.122916+03:00 pve01 homelab-alertmanager-backup-run[1157287]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T03:11:36.224287+03:00 pve01 homelab-alertmanager-backup-run[1207541]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T03:26:56.104164+03:00 pve01 homelab-alertmanager-backup-run[1267608]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T03:42:16.163161+03:00 pve01 homelab-alertmanager-backup-run[1337091]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T03:57:35.911704+03:00 pve01 homelab-alertmanager-backup-run[1388112]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T04:12:45.302638+03:00 pve01 homelab-alertmanager-backup-run[1439953]: ALERT_EMAIL_ACCEPTED=YES
|
||||||
|
2026-09-28T04:12:45.302638+03:00 pve01 homelab-alertmanager-backup-run[1439953]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T04:28:16.066840+03:00 pve01 homelab-alertmanager-backup-run[1491056]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T04:43:26.035041+03:00 pve01 homelab-alertmanager-backup-run[1543022]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T04:58:29.541024+03:00 pve01 homelab-alertmanager-backup-run[1593789]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T05:13:39.334685+03:00 pve01 homelab-alertmanager-backup-run[1645768]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T05:28:53.353807+03:00 pve01 homelab-alertmanager-backup-run[1685761]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T05:44:20.155523+03:00 pve01 homelab-alertmanager-backup-run[1736193]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T06:00:05.422013+03:00 pve01 homelab-alertmanager-backup-run[1785685]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T06:15:20.661916+03:00 pve01 homelab-alertmanager-backup-run[1835343]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T06:30:46.367196+03:00 pve01 homelab-alertmanager-backup-run[1886013]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T06:46:05.406037+03:00 pve01 homelab-alertmanager-backup-run[1945314]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T07:01:36.274466+03:00 pve01 homelab-alertmanager-backup-run[1988992]: ALERT_EMAIL_ACCEPTED=YES
|
||||||
|
2026-09-28T07:01:36.274466+03:00 pve01 homelab-alertmanager-backup-run[1988992]: HEALTH_ALERT_STATE=OK
|
||||||
|
2026-09-28T07:16:41.913014+03:00 pve01 homelab-alertmanager-backup-run[2048228]: HEALTH_ALERT_STATE=OK
|
||||||
|
=== AUDIT_FREQUENCY_LAST12H ===
|
||||||
|
AUDIT_GREEN_SUMMARY_COUNT=7
|
||||||
|
AUDIT_RED_SUMMARY_COUNT=17
|
||||||
|
AUDIT_LOCK_BUSY_ISSUE_COUNT=9
|
||||||
|
AUDIT_SOURCE_OFFHOST_ISSUE_COUNT=0
|
||||||
|
2026-09-27T19:37:02.093711+03:00 pve01 homelab-backup-audit[3923461]: SUMMARY|AUDIT_STATUS=OK|BACKUP_STATUS=RED|ACTIVE_COUNT=16|ISSUE_COUNT=12|CLOUD_A=OK|CLOUD_B=OK|CLOUD_B_DRILL=OK|DR_PROVEN=YES|SOURCE_OFFHOST=OK
|
||||||
|
2026-09-27T20:06:15.522779+03:00 pve01 homelab-backup-audit[4022565]: SUMMARY|AUDIT_STATUS=OK|BACKUP_STATUS=RED|ACTIVE_COUNT=16|ISSUE_COUNT=12|CLOUD_A=OK|CLOUD_B=OK|CLOUD_B_DRILL=OK|DR_PROVEN=YES|SOURCE_OFFHOST=OK
|
||||||
|
2026-09-27T20:36:05.450336+03:00 pve01 homelab-backup-audit[4111037]: SUMMARY|AUDIT_STATUS=OK|BACKUP_STATUS=RED|ACTIVE_COUNT=16|ISSUE_COUNT=12|CLOUD_A=OK|CLOUD_B=OK|CLOUD_B_DRILL=OK|DR_PROVEN=YES|SOURCE_OFFHOST=OK
|
||||||
|
2026-09-27T21:06:02.094425+03:00 pve01 homelab-backup-audit[16838]: SUMMARY|AUDIT_STATUS=OK|BACKUP_STATUS=RED|ACTIVE_COUNT=16|ISSUE_COUNT=12|CLOUD_A=OK|CLOUD_B=OK|CLOUD_B_DRILL=OK|DR_PROVEN=YES|SOURCE_OFFHOST=OK
|
||||||
|
2026-09-27T21:37:05.002224+03:00 pve01 homelab-backup-audit[106421]: SUMMARY|AUDIT_STATUS=OK|BACKUP_STATUS=RED|ACTIVE_COUNT=16|ISSUE_COUNT=12|CLOUD_A=OK|CLOUD_B=OK|CLOUD_B_DRILL=OK|DR_PROVEN=YES|SOURCE_OFFHOST=OK
|
||||||
|
2026-09-27T22:06:07.004513+03:00 pve01 homelab-backup-audit[203921]: SUMMARY|AUDIT_STATUS=OK|BACKUP_STATUS=RED|ACTIVE_COUNT=16|ISSUE_COUNT=12|CLOUD_A=OK|CLOUD_B=OK|CLOUD_B_DRILL=OK|DR_PROVEN=YES|SOURCE_OFFHOST=OK
|
||||||
|
2026-09-27T22:35:26.212759+03:00 pve01 homelab-backup-audit[291167]: SUMMARY|AUDIT_STATUS=OK|BACKUP_STATUS=RED|ACTIVE_COUNT=16|ISSUE_COUNT=12|CLOUD_A=OK|CLOUD_B=OK|CLOUD_B_DRILL=OK|DR_PROVEN=YES|SOURCE_OFFHOST=OK
|
||||||
|
2026-09-27T23:06:54.987894+03:00 pve01 homelab-backup-audit[395212]: SUMMARY|AUDIT_STATUS=OK|BACKUP_STATUS=RED|ACTIVE_COUNT=16|ISSUE_COUNT=11|CLOUD_A=OK|CLOUD_B=OK|CLOUD_B_DRILL=OK|DR_PROVEN=YES|SOURCE_OFFHOST=OK
|
||||||
|
2026-09-27T23:36:37.162587+03:00 pve01 homelab-backup-audit[500802]: ISSUE|severity=HIGH|code=LOCK_BUSY|logical_id=/run/homelab-backup-heavy.lock|root_cause=ACTIVE_OR_ORPHAN_LOCK
|
||||||
|
2026-09-27T23:36:37.162587+03:00 pve01 homelab-backup-audit[500802]: SUMMARY|AUDIT_STATUS=OK|BACKUP_STATUS=RED|ACTIVE_COUNT=16|ISSUE_COUNT=6|CLOUD_A=OK|CLOUD_B=OK|CLOUD_B_DRILL=OK|DR_PROVEN=YES|SOURCE_OFFHOST=OK
|
||||||
|
2026-09-28T00:06:21.135619+03:00 pve01 homelab-backup-audit[605334]: ISSUE|severity=HIGH|code=LOCK_BUSY|logical_id=/run/homelab-backup-heavy.lock|root_cause=ACTIVE_OR_ORPHAN_LOCK
|
||||||
|
2026-09-28T00:06:21.135619+03:00 pve01 homelab-backup-audit[605334]: SUMMARY|AUDIT_STATUS=OK|BACKUP_STATUS=RED|ACTIVE_COUNT=16|ISSUE_COUNT=4|CLOUD_A=OK|CLOUD_B=OK|CLOUD_B_DRILL=OK|DR_PROVEN=YES|SOURCE_OFFHOST=OK
|
||||||
|
2026-09-28T00:36:10.445081+03:00 pve01 homelab-backup-audit[707255]: ISSUE|severity=HIGH|code=LOCK_BUSY|logical_id=/run/homelab-backup-heavy.lock|root_cause=ACTIVE_OR_ORPHAN_LOCK
|
||||||
|
2026-09-28T00:36:10.445081+03:00 pve01 homelab-backup-audit[707255]: SUMMARY|AUDIT_STATUS=OK|BACKUP_STATUS=RED|ACTIVE_COUNT=16|ISSUE_COUNT=2|CLOUD_A=OK|CLOUD_B=OK|CLOUD_B_DRILL=OK|DR_PROVEN=YES|SOURCE_OFFHOST=OK
|
||||||
|
2026-09-28T01:06:01.997372+03:00 pve01 homelab-backup-audit[799187]: SUMMARY|AUDIT_STATUS=OK|BACKUP_STATUS=GREEN|ACTIVE_COUNT=16|ISSUE_COUNT=0|CLOUD_A=OK|CLOUD_B=OK|CLOUD_B_DRILL=OK|DR_PROVEN=YES|SOURCE_OFFHOST=OK
|
||||||
|
2026-09-28T01:36:02.006941+03:00 pve01 homelab-backup-audit[906059]: SUMMARY|AUDIT_STATUS=OK|BACKUP_STATUS=GREEN|ACTIVE_COUNT=16|ISSUE_COUNT=0|CLOUD_A=OK|CLOUD_B=OK|CLOUD_B_DRILL=OK|DR_PROVEN=YES|SOURCE_OFFHOST=OK
|
||||||
|
2026-09-28T02:05:36.356288+03:00 pve01 homelab-backup-audit[995508]: SUMMARY|AUDIT_STATUS=OK|BACKUP_STATUS=GREEN|ACTIVE_COUNT=16|ISSUE_COUNT=0|CLOUD_A=OK|CLOUD_B=OK|CLOUD_B_DRILL=OK|DR_PROVEN=YES|SOURCE_OFFHOST=OK
|
||||||
|
2026-09-28T02:36:15.265015+03:00 pve01 homelab-backup-audit[1094502]: SUMMARY|AUDIT_STATUS=OK|BACKUP_STATUS=GREEN|ACTIVE_COUNT=16|ISSUE_COUNT=0|CLOUD_A=OK|CLOUD_B=OK|CLOUD_B_DRILL=OK|DR_PROVEN=YES|SOURCE_OFFHOST=OK
|
||||||
|
2026-09-28T03:05:20.453132+03:00 pve01 homelab-backup-audit[1192518]: SUMMARY|AUDIT_STATUS=OK|BACKUP_STATUS=GREEN|ACTIVE_COUNT=16|ISSUE_COUNT=0|CLOUD_A=OK|CLOUD_B=OK|CLOUD_B_DRILL=OK|DR_PROVEN=YES|SOURCE_OFFHOST=OK
|
||||||
|
2026-09-28T03:35:20.147380+03:00 pve01 homelab-backup-audit[1320691]: ISSUE|severity=HIGH|code=LOCK_BUSY|logical_id=/run/homelab-backup-heavy.lock|root_cause=ACTIVE_OR_ORPHAN_LOCK
|
||||||
|
2026-09-28T03:35:20.147380+03:00 pve01 homelab-backup-audit[1320691]: SUMMARY|AUDIT_STATUS=OK|BACKUP_STATUS=RED|ACTIVE_COUNT=16|ISSUE_COUNT=1|CLOUD_A=OK|CLOUD_B=OK|CLOUD_B_DRILL=OK|DR_PROVEN=YES|SOURCE_OFFHOST=OK
|
||||||
|
2026-09-28T04:06:45.928910+03:00 pve01 homelab-backup-audit[1424254]: ISSUE|severity=HIGH|code=LOCK_BUSY|logical_id=/run/homelab-backup-heavy.lock|root_cause=ACTIVE_OR_ORPHAN_LOCK
|
||||||
|
2026-09-28T04:06:45.928910+03:00 pve01 homelab-backup-audit[1424254]: SUMMARY|AUDIT_STATUS=OK|BACKUP_STATUS=RED|ACTIVE_COUNT=16|ISSUE_COUNT=1|CLOUD_A=OK|CLOUD_B=OK|CLOUD_B_DRILL=OK|DR_PROVEN=YES|SOURCE_OFFHOST=OK
|
||||||
|
2026-09-28T04:35:20.240415+03:00 pve01 homelab-backup-audit[1514892]: ISSUE|severity=HIGH|code=LOCK_BUSY|logical_id=/run/homelab-backup-heavy.lock|root_cause=ACTIVE_OR_ORPHAN_LOCK
|
||||||
|
2026-09-28T04:35:20.240415+03:00 pve01 homelab-backup-audit[1514892]: SUMMARY|AUDIT_STATUS=OK|BACKUP_STATUS=RED|ACTIVE_COUNT=16|ISSUE_COUNT=1|CLOUD_A=OK|CLOUD_B=OK|CLOUD_B_DRILL=OK|DR_PROVEN=YES|SOURCE_OFFHOST=OK
|
||||||
|
2026-09-28T05:05:52.974415+03:00 pve01 homelab-backup-audit[1617767]: ISSUE|severity=HIGH|code=LOCK_BUSY|logical_id=/run/homelab-backup-heavy.lock|root_cause=ACTIVE_OR_ORPHAN_LOCK
|
||||||
|
2026-09-28T05:05:52.974415+03:00 pve01 homelab-backup-audit[1617767]: SUMMARY|AUDIT_STATUS=OK|BACKUP_STATUS=RED|ACTIVE_COUNT=16|ISSUE_COUNT=1|CLOUD_A=OK|CLOUD_B=OK|CLOUD_B_DRILL=OK|DR_PROVEN=YES|SOURCE_OFFHOST=OK
|
||||||
|
2026-09-28T05:37:02.145613+03:00 pve01 homelab-backup-audit[1720751]: SUMMARY|AUDIT_STATUS=OK|BACKUP_STATUS=GREEN|ACTIVE_COUNT=16|ISSUE_COUNT=0|CLOUD_A=OK|CLOUD_B=OK|CLOUD_B_DRILL=OK|DR_PROVEN=YES|SOURCE_OFFHOST=OK
|
||||||
|
2026-09-28T06:06:02.032037+03:00 pve01 homelab-backup-audit[1807928]: SUMMARY|AUDIT_STATUS=OK|BACKUP_STATUS=GREEN|ACTIVE_COUNT=16|ISSUE_COUNT=0|CLOUD_A=OK|CLOUD_B=OK|CLOUD_B_DRILL=OK|DR_PROVEN=YES|SOURCE_OFFHOST=OK
|
||||||
|
2026-09-28T06:36:20.418325+03:00 pve01 homelab-backup-audit[1908813]: ISSUE|severity=HIGH|code=LOCK_BUSY|logical_id=/run/homelab-backup-heavy.lock|root_cause=ACTIVE_OR_ORPHAN_LOCK
|
||||||
|
2026-09-28T06:36:20.418325+03:00 pve01 homelab-backup-audit[1908813]: SUMMARY|AUDIT_STATUS=OK|BACKUP_STATUS=RED|ACTIVE_COUNT=16|ISSUE_COUNT=1|CLOUD_A=OK|CLOUD_B=OK|CLOUD_B_DRILL=OK|DR_PROVEN=YES|SOURCE_OFFHOST=OK
|
||||||
|
2026-09-28T07:06:48.299695+03:00 pve01 homelab-backup-audit[2011656]: ISSUE|severity=HIGH|code=LOCK_BUSY|logical_id=/run/homelab-backup-heavy.lock|root_cause=ACTIVE_OR_ORPHAN_LOCK
|
||||||
|
2026-09-28T07:06:48.299695+03:00 pve01 homelab-backup-audit[2011656]: SUMMARY|AUDIT_STATUS=OK|BACKUP_STATUS=RED|ACTIVE_COUNT=16|ISSUE_COUNT=1|CLOUD_A=OK|CLOUD_B=OK|CLOUD_B_DRILL=OK|DR_PROVEN=YES|SOURCE_OFFHOST=OK
|
||||||
|
=== HEALTH_GENERATION_CORRELATION ===
|
||||||
|
HEALTH_GENERATED_AT_EPOCH=1790568997
|
||||||
|
HEALTH_CORRELATION_FROM=1790568817
|
||||||
|
HEALTH_CORRELATION_TO=1790569177
|
||||||
|
=== FRESH_QUIET_AUDIT ===
|
||||||
|
QUIET_AUDIT_WAIT|attempt=1|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=2|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=3|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=4|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=5|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=6|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=7|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=8|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=9|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=10|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=11|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=12|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=13|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=14|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=15|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=16|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=17|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=18|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=19|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=20|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=21|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=22|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=23|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=24|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=25|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=26|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=27|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=28|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=29|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=30|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=31|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=32|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=33|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=34|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=35|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
QUIET_AUDIT_WAIT|attempt=36|reason=SERVICE_BUSY|active=activating|pid=1856481
|
||||||
|
FRESH_QUIET_AUDIT_RC=NO_QUIET_WINDOW
|
||||||
|
FRESH_AUDIT_HEALTH_NO_WRITE=false
|
||||||
|
=== CANONICAL_ALERT_SOURCE_AUTHORITY ===
|
||||||
|
CANONICAL_ALERT_PATH=/root/homelab-ops-cr-2026-1005/tasks/backup-v2-health-alerting-remediation-v1/assets/baseline/homelab-alertmanager-backup-run
|
||||||
|
CANONICAL_ALERT_EXISTS=true
|
||||||
|
CANONICAL_ALERT_SHA256=6deef30b4708a7e5b2ac0f0d98bb6b37b22d858afde994483b67baa18dffdc2a
|
||||||
|
CANONICAL_ALERT_MATCH_LIVE=false
|
||||||
|
CANONICAL_SOURCE_HEAD=db592a25c6ac587bf16472a6132b66698c42f663
|
||||||
|
CANONICAL_REMOTE_HEAD=db592a25c6ac587bf16472a6132b66698c42f663
|
||||||
|
CANONICAL_SOURCE_EXACT=true
|
||||||
|
TASK_RESULT=PASS_BACKUP_ALERT_SPAM_CURRENT_RCA_COLLECTED
|
||||||
|
DECISION=PASS_BACKUP_ALERT_SPAM_CURRENT_RCA_COLLECTED
|
||||||
|
NEXT_GATE=READ_EXACT_1237_AND_FIX_ONLY_PROVEN_ALERT_NOISE_CAUSE
|
||||||
|
HOMELAB_RESULT_CONTRACT={"version":1,"command_id":"SUPPORT-260928-HOMELAB-BACKUP-ALERT-SPAM-CURRENT-RCA-1237R1","status":"OK","changes_made":false,"rollback_started":false,"rollback_restored":null}
|
||||||
|
|
||||||
OUTPUT_END
|
OUTPUT_END
|
||||||
CHAT_OUTPUT_END
|
CHAT_OUTPUT_END
|
||||||
|
|||||||
Reference in New Issue
Block a user