diff --git a/runtime/history/SUPPORT-260928-HOMELAB-BACKUP-ALERT-NOISE-ROOT-RCA-1238R1.json b/runtime/history/SUPPORT-260928-HOMELAB-BACKUP-ALERT-NOISE-ROOT-RCA-1238R1.json new file mode 100644 index 00000000..7e6e52e3 --- /dev/null +++ b/runtime/history/SUPPORT-260928-HOMELAB-BACKUP-ALERT-NOISE-ROOT-RCA-1238R1.json @@ -0,0 +1,38 @@ +{ + "schema_version": 1, + "channel": "homelab-runtime", + "command_id": "SUPPORT-260928-HOMELAB-BACKUP-ALERT-NOISE-ROOT-RCA-1238R1", + "status": "OK", + "rc": 0, + "host": "pve01", + "mode": "read-only", + "component": "homelab-backup-alert-noise-root-rca", + "started_at_utc": "2026-09-28T04:40:00Z", + "finished_at_utc": "2026-09-28T04:40:17Z", + "reference_register_checked": true, + "reference_sha256": "5a3d8e5154c41cb582a4e0aca68090be1f0138918bf82131a948df326f9d8d66", + "error_register_checked": true, + "error_register_sha256": "3b09a553ec0f527ed3afeed4753f52a74ee3036045bbfb3c685e9f8af4ba7ba0", + "command_sha256": "9ae99a8877a8c63075030326f98f8146f9c933c9cbcb7bd076b9bbcfeeb0e1a3", + "duplicate_failed_command_blocked": false, + "block_reason": null, + "execution_started": true, + "change_declared": false, + "result_contract_valid": true, + "result_contract_status": null, + "result_contract_error": null, + "command_rc": 0, + "changes_made": false, + "rollback_started": false, + "rollback_restored": null, + "mutation_outcome": "NO_MUTATION", + "sanitized": true, + "secrets_included": false, + "private_addresses_included": false, + "raw_evidence_retained_locally": true, + "raw_evidence_sha256": "9c2e7b15aaf9e4270699137f0f21aa91d7e88a1ae44c347b734ba55e3bbe2b81", + "sanitized_output_sha256": "9c2e7b15aaf9e4270699137f0f21aa91d7e88a1ae44c347b734ba55e3bbe2b81", + "output_truncated_in_json": false, + "full_sanitized_output_url": "https://git.gram1.ru/.well-known/homelab-runtime/latest.txt", + "output": "BACKUP_ALERT_NOISE_ROOT_RCA_BEGIN=true\nCOMMAND_ID=SUPPORT-260928-HOMELAB-BACKUP-ALERT-NOISE-ROOT-RCA-1238R1\nMODE=read-only\nCOMPONENT=homelab-backup-alert-noise-root-rca\nMUTATION_BOUNDARY=READ_ONLY_SYSTEMD_CONTEXT_GIT_REMOTE_PROBES_AUDIT_ALL_SOURCE_DISCOVERY_AND_HISTORICAL_CORRELATION;NO_ALERT_EXECUTION;NO_MAIL;NO_BACKUP;NO_LOCK_ACQUIRE;NO_CONFIG_WRITE;NO_SCRIPT_WRITE;NO_SYSTEMD_ACTION;NO_TIMER_CHANGE;NO_HEALTH_WRITE;NO_GIT_WRITE;NO_RETENTION;NO_DELETE;NO_RESTORE;NO_NETBIRD_SKLADCHIK_CHANGE\n=== AUTHORITY ===\nHOST=pve01\nCLUSTER_QUORATE=Yes\nRUNNER_SHA256=b248a4c32c9cc64e5747e7dce6c7fc0a23f5124a77c71ce72e27a81aceae9d2d\nSOURCE_1237_STATUS=OK\nSOURCE_1237_RC=0\nSOURCE_1237_DECISION=PASS_BACKUP_ALERT_SPAM_CURRENT_RCA_COLLECTED\nSOURCE_1237_NEXT_GATE=READ_EXACT_1237_AND_FIX_ONLY_PROVEN_ALERT_NOISE_CAUSE\n=== LIVE_IDENTITIES ===\nWRAPPER_SHA256=894f8ea346b53a3d7846dbd6eeb5b89333957eb6d7a4f2f64fd4557cae176e1c\nHELPER_SHA256=4e39404b1ddb97392645adce6280f697182cca03714d3a462d363eebce9b1860\nVZDUMP_CONF_SHA256=027e4b04852a4b83d558eb861d432b6fad4f234e12ab77d327f274d0fdedbfad\nAUDIT_SHA256=f7b936fa997bdefdd0c3c5d1d96e496888ebebc8ea85a60ed3bf5bcc9bf4962a\nALERT_SHA256=2b92cd44fc5b43decba0ea0706c4c84e1912cdc6d7b9bcb10bbf9552c98dc3f9\n=== SOURCE_BRANCH_AUTHORITY ===\nSOURCE_LOCAL_HEAD=db592a25c6ac587bf16472a6132b66698c42f663\nSOURCE_BRANCH=cr-2026-1005-backup-v2-health-alerting-remediation\nSOURCE_WORKTREE_CLEAN=true\nSOURCE_ORIGIN_SCHEME=https\nSOURCE_ORIGIN_URL_SHA256=7507b97d441d05c4e33306608cbf655e96bf2add0ec7683cc2f4e5539f64daf9\nSOURCE_REMOTE_HEAD=db592a25c6ac587bf16472a6132b66698c42f663\nSOURCE_LOCAL_REMOTE_EXACT=true\n=== SYSTEMD_UNIT_CONTEXT ===\nSYSTEMD_SHOW_BEGIN=homelab-backup-audit.service\nExecStart={ path=/usr/local/sbin/homelab-backup-audit ; argv[]=/usr/local/sbin/homelab-backup-audit scheduled ; ignore_errors=no ; start_time=[Mon 2026-09-28 07:36:16 MSK] ; stop_time=[Mon 2026-09-28 07:36:20 MSK] ; pid=2104808 ; code=exited ; status=1 }\nEnvironment=\nWorkingDirectory=\nRootDirectory=\nUser=root\nGroup=root\nDynamicUser=no\nPAMName=\nSYSTEMD_SHOW_END=homelab-backup-audit.service\nSYSTEMD_CAT_BEGIN=homelab-backup-audit.service\n# /etc/systemd/system/homelab-backup-audit.service\n[Unit]\nDescription=Homelab unified backup and DR audit\nAfter=network-online.target\nWants=network-online.target\n\n[Service]\nType=oneshot\nExecStart=/usr/local/sbin/homelab-backup-audit scheduled\nUser=root\nGroup=root\nUMask=0077\nNice=10\nIOSchedulingClass=best-effort\nIOSchedulingPriority=7\nSYSTEMD_CAT_END=homelab-backup-audit.service\nSYSTEMD_SHOW_BEGIN=homelab-alertmanager-backup-health.service\nExecStart={ path=/usr/local/sbin/homelab-alertmanager-backup-run ; argv[]=/usr/local/sbin/homelab-alertmanager-backup-run health-alert ; ignore_errors=no ; start_time=[Mon 2026-09-28 07:31:56 MSK] ; stop_time=[Mon 2026-09-28 07:32:00 MSK] ; pid=2089737 ; code=exited ; status=0 }\nEnvironment=\nWorkingDirectory=\nRootDirectory=\nUser=\nGroup=\nDynamicUser=no\nPAMName=\nSYSTEMD_SHOW_END=homelab-alertmanager-backup-health.service\nSYSTEMD_CAT_BEGIN=homelab-alertmanager-backup-health.service\n# /etc/systemd/system/homelab-alertmanager-backup-health.service\n[Unit]\nDescription=Workers2 backup health alert via existing alertmanager backup integration\nAfter=network-online.target\n\n[Service]\nType=oneshot\nExecStart=/usr/local/sbin/homelab-alertmanager-backup-run health-alert\nSYSTEMD_CAT_END=homelab-alertmanager-backup-health.service\nSYSTEM_MANAGER_ENV_RELEVANT_BEGIN\nPATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin\nSYSTEM_MANAGER_ENV_RELEVANT_END\n=== GIT_CONFIG_CONTEXT ===\nGIT_CONFIG_MODE=minimal OUT_BYTES=0 ERR_BYTES=21 OUT_SHA256=e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855 ERR_SHA256=6a8a72c20480deb7191693468ae1348ea123ecd0c5ff9baf8693dd293e9112cb\nGIT_CONFIG_MODE=nohome OUT_BYTES=0 ERR_BYTES=21 OUT_SHA256=e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855 ERR_SHA256=6a8a72c20480deb7191693468ae1348ea123ecd0c5ff9baf8693dd293e9112cb\nGIT_CONFIG_MODE=homeroot OUT_BYTES=346 ERR_BYTES=0 OUT_SHA256=9a188d2d29e9701bac3d2fe0cc4f11283f36fca0a941b1b3aeaf10d3b47fdc7e ERR_SHA256=e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855\n=== REMOTE_CONTEXT_PROBES ===\nREMOTE_PROBE=normal RC=0 HEAD=db592a25c6ac587bf16472a6132b66698c42f663 EXACT=true STDERR_BYTES=0 STDERR_SHA256=e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855\nREMOTE_PROBE=minimal RC=128 HEAD=NONE EXACT=false STDERR_BYTES=85 STDERR_SHA256=adbd757d7820290ef0868baee0cb62cc4953c3831e45981d82cb0ed5faed79cc\nREMOTE_PROBE_STDERR_BEGIN=minimal\nfatal: could not read Username for 'https://git.gram1.ru': No such device or address\nREMOTE_PROBE_STDERR_END=minimal\nREMOTE_PROBE=nohome RC=128 HEAD=NONE EXACT=false STDERR_BYTES=85 STDERR_SHA256=adbd757d7820290ef0868baee0cb62cc4953c3831e45981d82cb0ed5faed79cc\nREMOTE_PROBE_STDERR_BEGIN=nohome\nfatal: could not read Username for 'https://git.gram1.ru': No such device or address\nREMOTE_PROBE_STDERR_END=nohome\nREMOTE_PROBE=homeroot RC=0 HEAD=db592a25c6ac587bf16472a6132b66698c42f663 EXACT=true STDERR_BYTES=0 STDERR_SHA256=e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855\n=== AUDIT_ALL_CONTEXT_PROBES ===\nAUDIT_CONTEXT=minimal RC=1 SOURCE_OFFHOST_ISSUES=1 LOCK_BUSY_ISSUES=1 STDERR_BYTES=0\nAUDIT_CONTEXT_SUMMARY=minimal|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=PENDING\nISSUE|severity=MEDIUM|code=SOURCE_OFFHOST_MISSING|logical_id=-|root_cause=CR_BRANCH_SHA_NOT_EXACT\nAUDIT_CONTEXT=nohome RC=1 SOURCE_OFFHOST_ISSUES=1 LOCK_BUSY_ISSUES=1 STDERR_BYTES=0\nAUDIT_CONTEXT_SUMMARY=nohome|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=PENDING\nISSUE|severity=MEDIUM|code=SOURCE_OFFHOST_MISSING|logical_id=-|root_cause=CR_BRANCH_SHA_NOT_EXACT\nAUDIT_CONTEXT=homeroot RC=1 SOURCE_OFFHOST_ISSUES=0 LOCK_BUSY_ISSUES=1 STDERR_BYTES=0\nAUDIT_CONTEXT_SUMMARY=homeroot|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\nAUDIT_CONTEXT=normal RC=1 SOURCE_OFFHOST_ISSUES=0 LOCK_BUSY_ISSUES=1 STDERR_BYTES=0\nAUDIT_CONTEXT_SUMMARY=normal|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\nAUDIT_ALL_CONTEXT_HEALTH_NO_WRITE=true\n=== LOCK_OWNER_CORRELATION ===\nCURRENT_BACKUP_ACTIVE=activating\nCURRENT_BACKUP_MAINPID=1856481\nCURRENT_BACKUP_RESULT=success\nCURRENT_BACKUP_EXEC_STATUS=0\nhomelab-backup- 1856481 FLOCK WRITE /run/homelab-backup-heavy.lock\nCURRENT_HEAVY_FUSER= 1856481\nRAW1237_PATH=/var/lib/homelab-chat-run/raw/SUPPORT-260928-HOMELAB-BACKUP-ALERT-SPAM-CURRENT-RCA-1237R1-20260928T043051Z.log\n25:UNIT=homelab-backup-v2.service ACTIVE=activating ENABLED=static RESULT=success EXEC_MAIN_STATUS=0 MAINPID=1856481\n238:LOCK_FUSER=/run/homelab-backup-heavy.lock| 1856481\n239:LOCK_FREE=/run/homelab-backup-heavy.lock|false\n249:homelab-backup- 1856481 FLOCK WRITE /run/homelab-backup-heavy.lock\n=== AUDIT_LOCK_LOGIC_STATIC ===\nLOCK_LOOP_SOURCE_BEGIN\nfor 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\"]:\n p=pathlib.Path(lock)\n if p.exists():\n lrc,_,_=run([\"flock\",\"-n\",str(p),\"-c\",\"true\"],5)\n if lrc!=0: issues.append({\"severity\":\"HIGH\",\"code\":\"LOCK_BUSY\",\"logical_id\":lock,\"root_cause\":\"ACTIVE_OR_ORPHAN_LOCK\"})\nLOCK_LOOP_SOURCE_END\nLOCK_LOOP_CALLS=issues.append,p.exists,pathlib.Path,run,str\n=== ALERT_COUNTER_LOGIC_STATIC ===\nALERT_LOGIC|0028|if mode!=\"health-alert\": raise SystemExit(64)\nALERT_LOGIC|0029|p=subprocess.run([AUDIT,\"write-health\"],text=True,stdout=subprocess.PIPE,stderr=subprocess.PIPE)\nALERT_LOGIC|0030|if p.returncode not in (0,1): raise SystemExit(p.returncode or 75)\nALERT_LOGIC|0031|try:\nALERT_LOGIC|0032| h=json.loads(HEALTH.read_text(encoding=\"utf-8\"))\nALERT_LOGIC|0033|except Exception:\nALERT_LOGIC|0034| raise SystemExit(69)\nALERT_LOGIC|0035|issues=h.get(\"issues\") if isinstance(h.get(\"issues\"),list) else []\nALERT_LOGIC|0036|cur={key(i):i for i in issues if isinstance(i,dict)}\nALERT_LOGIC|0037|codes=set(str(i.get(\"code\",\"\")) for i in cur.values())\nALERT_LOGIC|0038|oldj={}\nALERT_LOGIC|0039|if STATE.is_file():\nALERT_LOGIC|0040| try:\nALERT_LOGIC|0041| oldj=json.loads(STATE.read_text(encoding=\"utf-8\"))\nALERT_LOGIC|0042| if not isinstance(oldj,dict): oldj={}\nALERT_LOGIC|0043| except Exception:\nALERT_LOGIC|0044| oldj={}\nALERT_LOGIC|0045|migrating=oldj.get(\"schema\")!=SCHEMA\nALERT_LOGIC|0046|prev_counts=oldj.get(\"code_counts\") if isinstance(oldj.get(\"code_counts\"),dict) and not migrating else {}\nALERT_LOGIC|0047|counts={}\nALERT_LOGIC|0048|for code in codes:\nALERT_LOGIC|0049| try: prev=int(prev_counts.get(code,0))\nALERT_LOGIC|0050| except Exception: prev=0\nALERT_LOGIC|0051| counts[code]=prev+1\nALERT_LOGIC|0052|actionable={}\nALERT_LOGIC|0053|for k,i in cur.items():\nALERT_LOGIC|0054| code=str(i.get(\"code\",\"\"))\nALERT_LOGIC|0055| need=int(THRESHOLDS.get(code,1))\nALERT_LOGIC|0056| if counts.get(code,0)>=need:\nALERT_LOGIC|0057| actionable[k]=i\nALERT_LOGIC|0058|tokens=[REDACTED]\nALERT_LOGIC|0082|STATE.parent.mkdir(parents=True,exist_ok=True)\nALERT_LOGIC|0083|tmp=STATE.with_name(STATE.name+\".tmp\")\nALERT_LOGIC|0084|payload={\nALERT_LOGIC|0085| \"schema\":SCHEMA,\nALERT_LOGIC|0086| \"updated_epoch\":int(time.time()),\nALERT_LOGIC|0087| \"issue_keys\":sorted(actionable),\nALERT_LOGIC|0088| \"notify_tokens\":[REDACTED]\nALERT_LOGIC|0089| \"raw_issue_keys\":sorted(cur),\nALERT_LOGIC|0090| \"code_counts\":{k:int(v) for k,v in sorted(counts.items())},\nALERT_LOGIC|0091| \"migration_silent\":bool(migrating)\nALERT_LOGIC|0092|}\nALERT_LOGIC|0093|tmp.write_text(json.dumps(payload,separators=(\",\",\":\"),sort_keys=True)+\"\\n\",encoding=\"utf-8\")\nALERT_LOGIC|0094|os.chmod(tmp,0o600)\nALERT_LOGIC|0095|os.replace(tmp,STATE)\n=== CANONICAL_SOURCE_CANDIDATES ===\nSOURCE_CANDIDATE|name=homelab-backup-audit|exact=false|sha256=1474c9ce58bbc1b3ae7437261d1bdb923232926fb2943c7c830253f8b284724c|path=/root/homelab-ops-cr-2026-1005/tasks/backup-v2-health-alerting-remediation-v1/assets/baseline/homelab-backup-audit\nSOURCE_CANDIDATE_TOTAL|name=homelab-backup-audit|count=1|exact_count=0\nSOURCE_CANDIDATE|name=homelab-alertmanager-backup-run|exact=true|sha256=2b92cd44fc5b43decba0ea0706c4c84e1912cdc6d7b9bcb10bbf9552c98dc3f9|path=/root/homelab-ops-cr-2026-1005/changes/CR-2026-1005/runtime/homelab-alertmanager-backup-run\nSOURCE_CANDIDATE|name=homelab-alertmanager-backup-run|exact=false|sha256=6deef30b4708a7e5b2ac0f0d98bb6b37b22d858afde994483b67baa18dffdc2a|path=/root/homelab-ops-cr-2026-1005/tasks/backup-v2-health-alerting-remediation-v1/assets/baseline/homelab-alertmanager-backup-run\nSOURCE_CANDIDATE_TOTAL|name=homelab-alertmanager-backup-run|count=2|exact_count=1\n=== SOURCE_RELEVANT_GREP ===\nchanges/CR-2026-1005/runtime/homelab-backup-audit-v2:188: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\"]:\nchanges/CR-2026-1005/runtime/homelab-backup-audit-v2:192: if lrc!=0: issues.append({\"severity\":\"HIGH\",\"code\":\"LOCK_BUSY\",\"logical_id\":lock,\"root_cause\":\"ACTIVE_OR_ORPHAN_LOCK\"})\nchanges/CR-2026-1005/runtime/homelab-backup-audit-v2:292:source={\"local_head\":None,\"remote_head\":None,\"pushurl_disabled\":False}\nchanges/CR-2026-1005/runtime/homelab-backup-audit-v2:299: lrc,lo,_=run([\"git\",\"ls-remote\",fo.strip(),\"refs/heads/\"+BRANCH],30)\nchanges/CR-2026-1005/runtime/homelab-backup-audit-v2:300: if lrc==0 and lo.strip(): source[\"remote_head\"]=lo.split()[0]\nchanges/CR-2026-1005/runtime/homelab-backup-audit-v2:301:if source[\"remote_head\"]!=source[\"local_head\"]:\nchanges/CR-2026-1005/runtime/homelab-backup-audit-v2:302: issues.append({\"severity\":\"MEDIUM\",\"code\":\"SOURCE_OFFHOST_MISSING\",\"logical_id\":\"-\",\"root_cause\":\"CR_BRANCH_SHA_NOT_EXACT\"})\nchanges/CR-2026-1005/runtime/homelab-backup-audit-v2:309: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'}\")\nchanges/CR-2026-1005/runtime/homelab-backup-retention-gc:14:HEAVY_LOCK=/run/homelab-backup-heavy.lock\nchanges/CR-2026-1005/runtime/homelab-backup-retention-gc:424: exec 5>\"$LOCK\"; flock -n 5 || die GC_LOCK_BUSY 75\nchanges/CR-2026-1005/runtime/homelab-backup-retention-gc:434: exec 5>\"$LOCK\"; flock -n 5 || { printf 'GC_SCHEDULED=SKIP|reason=GC_LOCK_BUSY\\n'; return 0; }\nchanges/CR-2026-1005/runtime/homelab-backup-retention-gc:444: if ! acquire_gc_locks; then write_health \"$p1\" true 0; printf 'GC_SCHEDULED=SKIP|reason=BACKUP_LOCK_BUSY|candidates=%s|open_transactions=%s\\n' \"$count\" \"$open_tx\"; return 0; fi\nchanges/CR-2026-1005/runtime/homelab-backup-v2-app-scheduled:6:HEAVY_LOCK=/run/homelab-backup-heavy.lock\nchanges/CR-2026-1005/runtime/homelab-backup-v2-app-scheduled:19:exec 9>\"$QUEUE_LOCK\"; if ! flock -n 9; then printf 'APP_V2_SCHEDULED=SKIP|reason=APP_QUEUE_LOCK_BUSY\\n'; exit 0; fi\nchanges/CR-2026-1005/runtime/homelab-backup-v2-app-scheduled:20:exec 8>\"$HEAVY_LOCK\"; if ! flock -n 8; then printf 'APP_V2_SCHEDULED=SKIP|reason=GLOBAL_HEAVY_LOCK_BUSY\\n'; exit 0; fi\ntasks/backup-v2-health-alerting-remediation-v1/assets/baseline/homelab-backup-audit:159:flock -n 9 || die AUDIT_LOCK_BUSY 75\ntasks/backup-v2-health-alerting-remediation-v1/assets/baseline/homelab-backup-audit:422:for lock in /run/homelab-backup-heavy.lock /run/lock/homelab-vm-cloud-quorum-queue.lock /run/lock/homelab-app-cloud-quorum-queue.lock /run/lock/homelab-backup-dispatcher.lock; do\ntasks/backup-v2-health-alerting-remediation-v1/assets/baseline/homelab-backup-retention-gc:14:HEAVY_LOCK=/run/homelab-backup-heavy.lock\ntasks/backup-v2-health-alerting-remediation-v1/assets/baseline/homelab-backup-retention-gc:424: exec 5>\"$LOCK\"; flock -n 5 || die GC_LOCK_BUSY 75\ntasks/backup-v2-health-alerting-remediation-v1/assets/baseline/homelab-backup-retention-gc:434: exec 5>\"$LOCK\"; flock -n 5 || { printf 'GC_SCHEDULED=SKIP|reason=GC_LOCK_BUSY\\n'; return 0; }\ntasks/backup-v2-health-alerting-remediation-v1/assets/baseline/homelab-backup-retention-gc:444: if ! acquire_gc_locks; then write_health \"$p1\" true 0; printf 'GC_SCHEDULED=SKIP|reason=BACKUP_LOCK_BUSY|candidates=%s|open_transactions=%s\\n' \"$count\" \"$open_tx\"; return 0; fi\ntasks/snikket-vm150-rebuild-v2/assets/vm150-runtime.py:60:BACKUP_LOCKS=['/run/lock/homelab-backup-dispatcher.lock','/run/lock/homelab-vm-cloud-quorum-queue.lock','/run/homelab-backup-heavy.lock']\ntasks/snikket-vm150-rebuild-v2/assets/vm150-runtime.py:506: f.close(); die('LOCK_BUSY_'+pathlib.Path(q).name,75)\nTASK_RESULT=PASS_BACKUP_ALERT_NOISE_ROOT_RCA_COLLECTED\nDECISION=PASS_BACKUP_ALERT_NOISE_ROOT_RCA_COLLECTED\nNEXT_GATE=READ_EXACT_1238_AND_APPLY_ONLY_PROVEN_ALERT_NOISE_FIX\nHOMELAB_RESULT_CONTRACT={\"version\":1,\"command_id\":\"SUPPORT-260928-HOMELAB-BACKUP-ALERT-NOISE-ROOT-RCA-1238R1\",\"status\":\"OK\",\"changes_made\":false,\"rollback_started\":false,\"rollback_restored\":null}\n" +} diff --git a/runtime/history/SUPPORT-260928-HOMELAB-BACKUP-ALERT-NOISE-ROOT-RCA-1238R1.txt b/runtime/history/SUPPORT-260928-HOMELAB-BACKUP-ALERT-NOISE-ROOT-RCA-1238R1.txt new file mode 100644 index 00000000..2695eaf2 --- /dev/null +++ b/runtime/history/SUPPORT-260928-HOMELAB-BACKUP-ALERT-NOISE-ROOT-RCA-1238R1.txt @@ -0,0 +1,238 @@ +CHAT_OUTPUT_BEGIN +COMMAND_ID=SUPPORT-260928-HOMELAB-BACKUP-ALERT-NOISE-ROOT-RCA-1238R1 +STATUS=OK +RC=0 +HOST=pve01 +MODE=read-only +COMPONENT=homelab-backup-alert-noise-root-rca +REFERENCE_REGISTER_CHECK=OK +REFERENCE_SHA256=5a3d8e5154c41cb582a4e0aca68090be1f0138918bf82131a948df326f9d8d66 +ERROR_REGISTER_CHECK=OK +ERROR_REGISTER_SHA256=3b09a553ec0f527ed3afeed4753f52a74ee3036045bbfb3c685e9f8af4ba7ba0 +COMMAND_SHA256=9ae99a8877a8c63075030326f98f8146f9c933c9cbcb7bd076b9bbcfeeb0e1a3 +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=9c2e7b15aaf9e4270699137f0f21aa91d7e88a1ae44c347b734ba55e3bbe2b81 +SANITIZED_OUTPUT_SHA256=9c2e7b15aaf9e4270699137f0f21aa91d7e88a1ae44c347b734ba55e3bbe2b81 +OUTPUT_BEGIN +BACKUP_ALERT_NOISE_ROOT_RCA_BEGIN=true +COMMAND_ID=SUPPORT-260928-HOMELAB-BACKUP-ALERT-NOISE-ROOT-RCA-1238R1 +MODE=read-only +COMPONENT=homelab-backup-alert-noise-root-rca +MUTATION_BOUNDARY=READ_ONLY_SYSTEMD_CONTEXT_GIT_REMOTE_PROBES_AUDIT_ALL_SOURCE_DISCOVERY_AND_HISTORICAL_CORRELATION;NO_ALERT_EXECUTION;NO_MAIL;NO_BACKUP;NO_LOCK_ACQUIRE;NO_CONFIG_WRITE;NO_SCRIPT_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_1237_STATUS=OK +SOURCE_1237_RC=0 +SOURCE_1237_DECISION=PASS_BACKUP_ALERT_SPAM_CURRENT_RCA_COLLECTED +SOURCE_1237_NEXT_GATE=READ_EXACT_1237_AND_FIX_ONLY_PROVEN_ALERT_NOISE_CAUSE +=== LIVE_IDENTITIES === +WRAPPER_SHA256=894f8ea346b53a3d7846dbd6eeb5b89333957eb6d7a4f2f64fd4557cae176e1c +HELPER_SHA256=4e39404b1ddb97392645adce6280f697182cca03714d3a462d363eebce9b1860 +VZDUMP_CONF_SHA256=027e4b04852a4b83d558eb861d432b6fad4f234e12ab77d327f274d0fdedbfad +AUDIT_SHA256=f7b936fa997bdefdd0c3c5d1d96e496888ebebc8ea85a60ed3bf5bcc9bf4962a +ALERT_SHA256=2b92cd44fc5b43decba0ea0706c4c84e1912cdc6d7b9bcb10bbf9552c98dc3f9 +=== SOURCE_BRANCH_AUTHORITY === +SOURCE_LOCAL_HEAD=db592a25c6ac587bf16472a6132b66698c42f663 +SOURCE_BRANCH=cr-2026-1005-backup-v2-health-alerting-remediation +SOURCE_WORKTREE_CLEAN=true +SOURCE_ORIGIN_SCHEME=https +SOURCE_ORIGIN_URL_SHA256=7507b97d441d05c4e33306608cbf655e96bf2add0ec7683cc2f4e5539f64daf9 +SOURCE_REMOTE_HEAD=db592a25c6ac587bf16472a6132b66698c42f663 +SOURCE_LOCAL_REMOTE_EXACT=true +=== SYSTEMD_UNIT_CONTEXT === +SYSTEMD_SHOW_BEGIN=homelab-backup-audit.service +ExecStart={ path=/usr/local/sbin/homelab-backup-audit ; argv[]=/usr/local/sbin/homelab-backup-audit scheduled ; ignore_errors=no ; start_time=[Mon 2026-09-28 07:36:16 MSK] ; stop_time=[Mon 2026-09-28 07:36:20 MSK] ; pid=2104808 ; code=exited ; status=1 } +Environment= +WorkingDirectory= +RootDirectory= +User=root +Group=root +DynamicUser=no +PAMName= +SYSTEMD_SHOW_END=homelab-backup-audit.service +SYSTEMD_CAT_BEGIN=homelab-backup-audit.service +# /etc/systemd/system/homelab-backup-audit.service +[Unit] +Description=Homelab unified backup and DR audit +After=network-online.target +Wants=network-online.target + +[Service] +Type=oneshot +ExecStart=/usr/local/sbin/homelab-backup-audit scheduled +User=root +Group=root +UMask=0077 +Nice=10 +IOSchedulingClass=best-effort +IOSchedulingPriority=7 +SYSTEMD_CAT_END=homelab-backup-audit.service +SYSTEMD_SHOW_BEGIN=homelab-alertmanager-backup-health.service +ExecStart={ path=/usr/local/sbin/homelab-alertmanager-backup-run ; argv[]=/usr/local/sbin/homelab-alertmanager-backup-run health-alert ; ignore_errors=no ; start_time=[Mon 2026-09-28 07:31:56 MSK] ; stop_time=[Mon 2026-09-28 07:32:00 MSK] ; pid=2089737 ; code=exited ; status=0 } +Environment= +WorkingDirectory= +RootDirectory= +User= +Group= +DynamicUser=no +PAMName= +SYSTEMD_SHOW_END=homelab-alertmanager-backup-health.service +SYSTEMD_CAT_BEGIN=homelab-alertmanager-backup-health.service +# /etc/systemd/system/homelab-alertmanager-backup-health.service +[Unit] +Description=Workers2 backup health alert via existing alertmanager backup integration +After=network-online.target + +[Service] +Type=oneshot +ExecStart=/usr/local/sbin/homelab-alertmanager-backup-run health-alert +SYSTEMD_CAT_END=homelab-alertmanager-backup-health.service +SYSTEM_MANAGER_ENV_RELEVANT_BEGIN +PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin +SYSTEM_MANAGER_ENV_RELEVANT_END +=== GIT_CONFIG_CONTEXT === +GIT_CONFIG_MODE=minimal OUT_BYTES=0 ERR_BYTES=21 OUT_SHA256=e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855 ERR_SHA256=6a8a72c20480deb7191693468ae1348ea123ecd0c5ff9baf8693dd293e9112cb +GIT_CONFIG_MODE=nohome OUT_BYTES=0 ERR_BYTES=21 OUT_SHA256=e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855 ERR_SHA256=6a8a72c20480deb7191693468ae1348ea123ecd0c5ff9baf8693dd293e9112cb +GIT_CONFIG_MODE=homeroot OUT_BYTES=346 ERR_BYTES=0 OUT_SHA256=9a188d2d29e9701bac3d2fe0cc4f11283f36fca0a941b1b3aeaf10d3b47fdc7e ERR_SHA256=e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855 +=== REMOTE_CONTEXT_PROBES === +REMOTE_PROBE=normal RC=0 HEAD=db592a25c6ac587bf16472a6132b66698c42f663 EXACT=true STDERR_BYTES=0 STDERR_SHA256=e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855 +REMOTE_PROBE=minimal RC=128 HEAD=NONE EXACT=false STDERR_BYTES=85 STDERR_SHA256=adbd757d7820290ef0868baee0cb62cc4953c3831e45981d82cb0ed5faed79cc +REMOTE_PROBE_STDERR_BEGIN=minimal +fatal: could not read Username for 'https://git.gram1.ru': No such device or address +REMOTE_PROBE_STDERR_END=minimal +REMOTE_PROBE=nohome RC=128 HEAD=NONE EXACT=false STDERR_BYTES=85 STDERR_SHA256=adbd757d7820290ef0868baee0cb62cc4953c3831e45981d82cb0ed5faed79cc +REMOTE_PROBE_STDERR_BEGIN=nohome +fatal: could not read Username for 'https://git.gram1.ru': No such device or address +REMOTE_PROBE_STDERR_END=nohome +REMOTE_PROBE=homeroot RC=0 HEAD=db592a25c6ac587bf16472a6132b66698c42f663 EXACT=true STDERR_BYTES=0 STDERR_SHA256=e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855 +=== AUDIT_ALL_CONTEXT_PROBES === +AUDIT_CONTEXT=minimal RC=1 SOURCE_OFFHOST_ISSUES=1 LOCK_BUSY_ISSUES=1 STDERR_BYTES=0 +AUDIT_CONTEXT_SUMMARY=minimal|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=PENDING +ISSUE|severity=MEDIUM|code=SOURCE_OFFHOST_MISSING|logical_id=-|root_cause=CR_BRANCH_SHA_NOT_EXACT +AUDIT_CONTEXT=nohome RC=1 SOURCE_OFFHOST_ISSUES=1 LOCK_BUSY_ISSUES=1 STDERR_BYTES=0 +AUDIT_CONTEXT_SUMMARY=nohome|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=PENDING +ISSUE|severity=MEDIUM|code=SOURCE_OFFHOST_MISSING|logical_id=-|root_cause=CR_BRANCH_SHA_NOT_EXACT +AUDIT_CONTEXT=homeroot RC=1 SOURCE_OFFHOST_ISSUES=0 LOCK_BUSY_ISSUES=1 STDERR_BYTES=0 +AUDIT_CONTEXT_SUMMARY=homeroot|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 +AUDIT_CONTEXT=normal RC=1 SOURCE_OFFHOST_ISSUES=0 LOCK_BUSY_ISSUES=1 STDERR_BYTES=0 +AUDIT_CONTEXT_SUMMARY=normal|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 +AUDIT_ALL_CONTEXT_HEALTH_NO_WRITE=true +=== LOCK_OWNER_CORRELATION === +CURRENT_BACKUP_ACTIVE=activating +CURRENT_BACKUP_MAINPID=1856481 +CURRENT_BACKUP_RESULT=success +CURRENT_BACKUP_EXEC_STATUS=0 +homelab-backup- 1856481 FLOCK WRITE /run/homelab-backup-heavy.lock +CURRENT_HEAVY_FUSER= 1856481 +RAW1237_PATH=/var/lib/homelab-chat-run/raw/SUPPORT-260928-HOMELAB-BACKUP-ALERT-SPAM-CURRENT-RCA-1237R1-20260928T043051Z.log +25:UNIT=homelab-backup-v2.service ACTIVE=activating ENABLED=static RESULT=success EXEC_MAIN_STATUS=0 MAINPID=1856481 +238:LOCK_FUSER=/run/homelab-backup-heavy.lock| 1856481 +239:LOCK_FREE=/run/homelab-backup-heavy.lock|false +249:homelab-backup- 1856481 FLOCK WRITE /run/homelab-backup-heavy.lock +=== AUDIT_LOCK_LOGIC_STATIC === +LOCK_LOOP_SOURCE_BEGIN +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"]: + p=pathlib.Path(lock) + if p.exists(): + lrc,_,_=run(["flock","-n",str(p),"-c","true"],5) + if lrc!=0: issues.append({"severity":"HIGH","code":"LOCK_BUSY","logical_id":lock,"root_cause":"ACTIVE_OR_ORPHAN_LOCK"}) +LOCK_LOOP_SOURCE_END +LOCK_LOOP_CALLS=issues.append,p.exists,pathlib.Path,run,str +=== ALERT_COUNTER_LOGIC_STATIC === +ALERT_LOGIC|0028|if mode!="health-alert": raise SystemExit(64) +ALERT_LOGIC|0029|p=subprocess.run([AUDIT,"write-health"],text=True,stdout=subprocess.PIPE,stderr=subprocess.PIPE) +ALERT_LOGIC|0030|if p.returncode not in (0,1): raise SystemExit(p.returncode or 75) +ALERT_LOGIC|0031|try: +ALERT_LOGIC|0032| h=json.loads(HEALTH.read_text(encoding="utf-8")) +ALERT_LOGIC|0033|except Exception: +ALERT_LOGIC|0034| raise SystemExit(69) +ALERT_LOGIC|0035|issues=h.get("issues") if isinstance(h.get("issues"),list) else [] +ALERT_LOGIC|0036|cur={key(i):i for i in issues if isinstance(i,dict)} +ALERT_LOGIC|0037|codes=set(str(i.get("code","")) for i in cur.values()) +ALERT_LOGIC|0038|oldj={} +ALERT_LOGIC|0039|if STATE.is_file(): +ALERT_LOGIC|0040| try: +ALERT_LOGIC|0041| oldj=json.loads(STATE.read_text(encoding="utf-8")) +ALERT_LOGIC|0042| if not isinstance(oldj,dict): oldj={} +ALERT_LOGIC|0043| except Exception: +ALERT_LOGIC|0044| oldj={} +ALERT_LOGIC|0045|migrating=oldj.get("schema")!=SCHEMA +ALERT_LOGIC|0046|prev_counts=oldj.get("code_counts") if isinstance(oldj.get("code_counts"),dict) and not migrating else {} +ALERT_LOGIC|0047|counts={} +ALERT_LOGIC|0048|for code in codes: +ALERT_LOGIC|0049| try: prev=int(prev_counts.get(code,0)) +ALERT_LOGIC|0050| except Exception: prev=0 +ALERT_LOGIC|0051| counts[code]=prev+1 +ALERT_LOGIC|0052|actionable={} +ALERT_LOGIC|0053|for k,i in cur.items(): +ALERT_LOGIC|0054| code=str(i.get("code","")) +ALERT_LOGIC|0055| need=int(THRESHOLDS.get(code,1)) +ALERT_LOGIC|0056| if counts.get(code,0)>=need: +ALERT_LOGIC|0057| actionable[k]=i +ALERT_LOGIC|0058|tokens=[REDACTED] +ALERT_LOGIC|0082|STATE.parent.mkdir(parents=True,exist_ok=True) +ALERT_LOGIC|0083|tmp=STATE.with_name(STATE.name+".tmp") +ALERT_LOGIC|0084|payload={ +ALERT_LOGIC|0085| "schema":SCHEMA, +ALERT_LOGIC|0086| "updated_epoch":int(time.time()), +ALERT_LOGIC|0087| "issue_keys":sorted(actionable), +ALERT_LOGIC|0088| "notify_tokens":[REDACTED] +ALERT_LOGIC|0089| "raw_issue_keys":sorted(cur), +ALERT_LOGIC|0090| "code_counts":{k:int(v) for k,v in sorted(counts.items())}, +ALERT_LOGIC|0091| "migration_silent":bool(migrating) +ALERT_LOGIC|0092|} +ALERT_LOGIC|0093|tmp.write_text(json.dumps(payload,separators=(",",":"),sort_keys=True)+"\n",encoding="utf-8") +ALERT_LOGIC|0094|os.chmod(tmp,0o600) +ALERT_LOGIC|0095|os.replace(tmp,STATE) +=== CANONICAL_SOURCE_CANDIDATES === +SOURCE_CANDIDATE|name=homelab-backup-audit|exact=false|sha256=1474c9ce58bbc1b3ae7437261d1bdb923232926fb2943c7c830253f8b284724c|path=/root/homelab-ops-cr-2026-1005/tasks/backup-v2-health-alerting-remediation-v1/assets/baseline/homelab-backup-audit +SOURCE_CANDIDATE_TOTAL|name=homelab-backup-audit|count=1|exact_count=0 +SOURCE_CANDIDATE|name=homelab-alertmanager-backup-run|exact=true|sha256=2b92cd44fc5b43decba0ea0706c4c84e1912cdc6d7b9bcb10bbf9552c98dc3f9|path=/root/homelab-ops-cr-2026-1005/changes/CR-2026-1005/runtime/homelab-alertmanager-backup-run +SOURCE_CANDIDATE|name=homelab-alertmanager-backup-run|exact=false|sha256=6deef30b4708a7e5b2ac0f0d98bb6b37b22d858afde994483b67baa18dffdc2a|path=/root/homelab-ops-cr-2026-1005/tasks/backup-v2-health-alerting-remediation-v1/assets/baseline/homelab-alertmanager-backup-run +SOURCE_CANDIDATE_TOTAL|name=homelab-alertmanager-backup-run|count=2|exact_count=1 +=== SOURCE_RELEVANT_GREP === +changes/CR-2026-1005/runtime/homelab-backup-audit-v2:188: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"]: +changes/CR-2026-1005/runtime/homelab-backup-audit-v2:192: if lrc!=0: issues.append({"severity":"HIGH","code":"LOCK_BUSY","logical_id":lock,"root_cause":"ACTIVE_OR_ORPHAN_LOCK"}) +changes/CR-2026-1005/runtime/homelab-backup-audit-v2:292:source={"local_head":None,"remote_head":None,"pushurl_disabled":False} +changes/CR-2026-1005/runtime/homelab-backup-audit-v2:299: lrc,lo,_=run(["git","ls-remote",fo.strip(),"refs/heads/"+BRANCH],30) +changes/CR-2026-1005/runtime/homelab-backup-audit-v2:300: if lrc==0 and lo.strip(): source["remote_head"]=lo.split()[0] +changes/CR-2026-1005/runtime/homelab-backup-audit-v2:301:if source["remote_head"]!=source["local_head"]: +changes/CR-2026-1005/runtime/homelab-backup-audit-v2:302: issues.append({"severity":"MEDIUM","code":"SOURCE_OFFHOST_MISSING","logical_id":"-","root_cause":"CR_BRANCH_SHA_NOT_EXACT"}) +changes/CR-2026-1005/runtime/homelab-backup-audit-v2:309: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'}") +changes/CR-2026-1005/runtime/homelab-backup-retention-gc:14:HEAVY_LOCK=/run/homelab-backup-heavy.lock +changes/CR-2026-1005/runtime/homelab-backup-retention-gc:424: exec 5>"$LOCK"; flock -n 5 || die GC_LOCK_BUSY 75 +changes/CR-2026-1005/runtime/homelab-backup-retention-gc:434: exec 5>"$LOCK"; flock -n 5 || { printf 'GC_SCHEDULED=SKIP|reason=GC_LOCK_BUSY\n'; return 0; } +changes/CR-2026-1005/runtime/homelab-backup-retention-gc:444: if ! acquire_gc_locks; then write_health "$p1" true 0; printf 'GC_SCHEDULED=SKIP|reason=BACKUP_LOCK_BUSY|candidates=%s|open_transactions=%s\n' "$count" "$open_tx"; return 0; fi +changes/CR-2026-1005/runtime/homelab-backup-v2-app-scheduled:6:HEAVY_LOCK=/run/homelab-backup-heavy.lock +changes/CR-2026-1005/runtime/homelab-backup-v2-app-scheduled:19:exec 9>"$QUEUE_LOCK"; if ! flock -n 9; then printf 'APP_V2_SCHEDULED=SKIP|reason=APP_QUEUE_LOCK_BUSY\n'; exit 0; fi +changes/CR-2026-1005/runtime/homelab-backup-v2-app-scheduled:20:exec 8>"$HEAVY_LOCK"; if ! flock -n 8; then printf 'APP_V2_SCHEDULED=SKIP|reason=GLOBAL_HEAVY_LOCK_BUSY\n'; exit 0; fi +tasks/backup-v2-health-alerting-remediation-v1/assets/baseline/homelab-backup-audit:159:flock -n 9 || die AUDIT_LOCK_BUSY 75 +tasks/backup-v2-health-alerting-remediation-v1/assets/baseline/homelab-backup-audit:422:for lock in /run/homelab-backup-heavy.lock /run/lock/homelab-vm-cloud-quorum-queue.lock /run/lock/homelab-app-cloud-quorum-queue.lock /run/lock/homelab-backup-dispatcher.lock; do +tasks/backup-v2-health-alerting-remediation-v1/assets/baseline/homelab-backup-retention-gc:14:HEAVY_LOCK=/run/homelab-backup-heavy.lock +tasks/backup-v2-health-alerting-remediation-v1/assets/baseline/homelab-backup-retention-gc:424: exec 5>"$LOCK"; flock -n 5 || die GC_LOCK_BUSY 75 +tasks/backup-v2-health-alerting-remediation-v1/assets/baseline/homelab-backup-retention-gc:434: exec 5>"$LOCK"; flock -n 5 || { printf 'GC_SCHEDULED=SKIP|reason=GC_LOCK_BUSY\n'; return 0; } +tasks/backup-v2-health-alerting-remediation-v1/assets/baseline/homelab-backup-retention-gc:444: if ! acquire_gc_locks; then write_health "$p1" true 0; printf 'GC_SCHEDULED=SKIP|reason=BACKUP_LOCK_BUSY|candidates=%s|open_transactions=%s\n' "$count" "$open_tx"; return 0; fi +tasks/snikket-vm150-rebuild-v2/assets/vm150-runtime.py:60:BACKUP_LOCKS=['/run/lock/homelab-backup-dispatcher.lock','/run/lock/homelab-vm-cloud-quorum-queue.lock','/run/homelab-backup-heavy.lock'] +tasks/snikket-vm150-rebuild-v2/assets/vm150-runtime.py:506: f.close(); die('LOCK_BUSY_'+pathlib.Path(q).name,75) +TASK_RESULT=PASS_BACKUP_ALERT_NOISE_ROOT_RCA_COLLECTED +DECISION=PASS_BACKUP_ALERT_NOISE_ROOT_RCA_COLLECTED +NEXT_GATE=READ_EXACT_1238_AND_APPLY_ONLY_PROVEN_ALERT_NOISE_FIX +HOMELAB_RESULT_CONTRACT={"version":1,"command_id":"SUPPORT-260928-HOMELAB-BACKUP-ALERT-NOISE-ROOT-RCA-1238R1","status":"OK","changes_made":false,"rollback_started":false,"rollback_restored":null} + +OUTPUT_END +CHAT_OUTPUT_END diff --git a/runtime/latest.json b/runtime/latest.json index df9be427..7e6e52e3 100644 --- a/runtime/latest.json +++ b/runtime/latest.json @@ -1,19 +1,19 @@ { "schema_version": 1, "channel": "homelab-runtime", - "command_id": "SUPPORT-260928-HOMELAB-BACKUP-ALERT-SPAM-CURRENT-RCA-1237R1", + "command_id": "SUPPORT-260928-HOMELAB-BACKUP-ALERT-NOISE-ROOT-RCA-1238R1", "status": "OK", "rc": 0, "host": "pve01", "mode": "read-only", - "component": "homelab-backup-alert-spam-current-rca", - "started_at_utc": "2026-09-28T04:30:51Z", - "finished_at_utc": "2026-09-28T04:34:02Z", + "component": "homelab-backup-alert-noise-root-rca", + "started_at_utc": "2026-09-28T04:40:00Z", + "finished_at_utc": "2026-09-28T04:40:17Z", "reference_register_checked": true, "reference_sha256": "5a3d8e5154c41cb582a4e0aca68090be1f0138918bf82131a948df326f9d8d66", "error_register_checked": true, "error_register_sha256": "3b09a553ec0f527ed3afeed4753f52a74ee3036045bbfb3c685e9f8af4ba7ba0", - "command_sha256": "e205fb5749bd8d2a466e79a56e8d9f3a66537e7dcbd1c635202ab6df607b736b", + "command_sha256": "9ae99a8877a8c63075030326f98f8146f9c933c9cbcb7bd076b9bbcfeeb0e1a3", "duplicate_failed_command_blocked": false, "block_reason": null, "execution_started": true, @@ -30,9 +30,9 @@ "secrets_included": false, "private_addresses_included": false, "raw_evidence_retained_locally": true, - "raw_evidence_sha256": "c64c77856d1b796c0414be59dd0089c9687ec505d26bb8b4111ab68ee967e5a2", - "sanitized_output_sha256": "c64c77856d1b796c0414be59dd0089c9687ec505d26bb8b4111ab68ee967e5a2", + "raw_evidence_sha256": "9c2e7b15aaf9e4270699137f0f21aa91d7e88a1ae44c347b734ba55e3bbe2b81", + "sanitized_output_sha256": "9c2e7b15aaf9e4270699137f0f21aa91d7e88a1ae44c347b734ba55e3bbe2b81", "output_truncated_in_json": false, "full_sanitized_output_url": "https://git.gram1.ru/.well-known/homelab-runtime/latest.txt", - "output": "BACKUP_ALERT_SPAM_CURRENT_RCA_BEGIN=true\nCOMMAND_ID=SUPPORT-260928-HOMELAB-BACKUP-ALERT-SPAM-CURRENT-RCA-1237R1\nMODE=read-only\nCOMPONENT=homelab-backup-alert-spam-current-rca\nMUTATION_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\n=== AUTHORITY ===\nHOST=pve01\nCLUSTER_QUORATE=Yes\nRUNNER_SHA256=b248a4c32c9cc64e5747e7dce6c7fc0a23f5124a77c71ce72e27a81aceae9d2d\nSOURCE_1236_STATUS=OK\nSOURCE_1236_RC=0\nSOURCE_1236_CHANGES_MADE=false\nSOURCE_1236_DECISION=HOLD_1236_V2_SERVICE_LAST_RUN_NOT_SUCCESS\nSOURCE_1236_NEXT_GATE=RECONCILE_POST_RECOVERY_SCHEDULER\nSOURCE_1236_POST_RECOVERY_V2_FAILED_COUNT=0\nSOURCE_1236_POST_RECOVERY_FRESH_HELPER_FAILED_COUNT=0\nSOURCE_1236_POST_RECOVERY_SCHEDULE_SUCCESS_COUNT=7\n=== LIVE_IDENTITIES ===\nWRAPPER_SHA256=894f8ea346b53a3d7846dbd6eeb5b89333957eb6d7a4f2f64fd4557cae176e1c\nHELPER_SHA256=4e39404b1ddb97392645adce6280f697182cca03714d3a462d363eebce9b1860\nVZDUMP_CONF_SHA256=027e4b04852a4b83d558eb861d432b6fad4f234e12ab77d327f274d0fdedbfad\nAUDIT_SHA256=f7b936fa997bdefdd0c3c5d1d96e496888ebebc8ea85a60ed3bf5bcc9bf4962a\nALERT_SCRIPT_SHA256=2b92cd44fc5b43decba0ea0706c4c84e1912cdc6d7b9bcb10bbf9552c98dc3f9\n=== CURRENT_UNIT_STATE ===\nUNIT=homelab-backup-v2.service ACTIVE=activating ENABLED=static RESULT=success EXEC_MAIN_STATUS=0 MAINPID=1856481\nUNIT=homelab-backup-v2.timer ACTIVE=active ENABLED=enabled RESULT=success EXEC_MAIN_STATUS= MAINPID=\nUNIT=homelab-backup-audit.service ACTIVE=failed ENABLED=static RESULT=exit-code EXEC_MAIN_STATUS=1 MAINPID=0\nUNIT=homelab-backup-audit.timer ACTIVE=active ENABLED=enabled RESULT=success EXEC_MAIN_STATUS= MAINPID=\nUNIT=homelab-alertmanager-backup-health.service ACTIVE=inactive ENABLED=static RESULT=success EXEC_MAIN_STATUS=0 MAINPID=0\nUNIT=homelab-alertmanager-backup-health.timer ACTIVE=active ENABLED=enabled RESULT=success EXEC_MAIN_STATUS= MAINPID=\n=== CURRENT_HEALTH_FILES ===\nHEALTH1_EXISTS=true\nHEALTH1_SHA256=d89fb55b92f2b9908e2d2d8da3b9a0d0db6d2fe84c6e6d37bcec1a86e4384222\nHEALTH1_JSON_OK=true\nHEALTH1_SCHEMA=homelab-backup-audit-v3\nHEALTH1_STATUS=RED\nHEALTH1_GENERATED_AT_EPOCH=1790568997\nHEALTH1_AGE_SECONDS=855\nHEALTH1_ISSUE_COUNT=2\nHEALTH1_ISSUE_1={\"code\":\"LOCK_BUSY\",\"logical_id\":\"/run/homelab-backup-heavy.lock\",\"root_cause\":\"ACTIVE_OR_ORPHAN_LOCK\",\"severity\":\"HIGH\"}\nHEALTH1_ISSUE_2={\"code\":\"SOURCE_OFFHOST_MISSING\",\"logical_id\":\"-\",\"root_cause\":\"CR_BRANCH_SHA_NOT_EXACT\",\"severity\":\"MEDIUM\"}\nHEALTH1_SOURCE_LOCAL_HEAD=db592a25c6ac587bf16472a6132b66698c42f663\nHEALTH1_SOURCE_REMOTE_HEAD=None\nHEALTH1_SOURCE_PUSHURL_DISABLED=true\nHEALTH1_SOURCE_EXACT=false\nHEALTH2_EXISTS=true\nHEALTH2_SHA256=d89fb55b92f2b9908e2d2d8da3b9a0d0db6d2fe84c6e6d37bcec1a86e4384222\nHEALTH2_JSON_OK=true\nHEALTH2_SCHEMA=homelab-backup-audit-v3\nHEALTH2_STATUS=RED\nHEALTH2_GENERATED_AT_EPOCH=1790568997\nHEALTH2_AGE_SECONDS=855\nHEALTH2_ISSUE_COUNT=2\nHEALTH2_ISSUE_1={\"code\":\"LOCK_BUSY\",\"logical_id\":\"/run/homelab-backup-heavy.lock\",\"root_cause\":\"ACTIVE_OR_ORPHAN_LOCK\",\"severity\":\"HIGH\"}\nHEALTH2_ISSUE_2={\"code\":\"SOURCE_OFFHOST_MISSING\",\"logical_id\":\"-\",\"root_cause\":\"CR_BRANCH_SHA_NOT_EXACT\",\"severity\":\"MEDIUM\"}\nHEALTH2_SOURCE_LOCAL_HEAD=db592a25c6ac587bf16472a6132b66698c42f663\nHEALTH2_SOURCE_REMOTE_HEAD=None\nHEALTH2_SOURCE_PUSHURL_DISABLED=true\nHEALTH2_SOURCE_EXACT=false\nHEALTH_FILES_IDENTICAL=true\nHEALTH_EPOCH_VALID=true\n=== CURRENT_ALERT_STATE ===\nALERT_STATE_EXISTS=true\nALERT_STATE_SHA256=493ce50563cb31030f2b16ff4ad722a7ac5ec211a77b2e89625491c057e8827d\nALERT_STATE_JSON_OK=true\nALERT_STATE_KEYS=code_counts,issue_keys,migration_silent,notify_tokens,raw_issue_keys,schema,updated_epoch\nALERT_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}\nALERT_STATE_SAFE_TRUNCATED=false\nALERT_STATE_FIELD_SCHEMA=\"homelab-backup-alert-state-v2\"\nALERT_STATE_FIELD_UPDATED_EPOCH=1790569001\nALERT_STATE_FIELD_ISSUE_KEYS=[\"LOCK_BUSY|/run/homelab-backup-heavy.lock|ACTIVE_OR_ORPHAN_LOCK\",\"SOURCE_OFFHOST_MISSING|-|CR_BRANCH_SHA_NOT_EXACT\"]\n=== ALERT_FILTER_SOURCE ===\nALERT_EMBEDDED_SOURCE_FOUND=true\nALERT_EMBEDDED_SOURCE_SHA256=344306105083cd8bc64e19d451f7f66c17accc43a2f413538d2f9e2687b2540e\nALERT_EMBEDDED_SOURCE_BEGIN\n0001:import sys,os,json,re,subprocess,pathlib,time\n0002:mode=sys.argv[1]\n0003:AUDIT=\"/usr/local/sbin/homelab-backup-audit\"\n0004:HEALTH=pathlib.Path(\"/var/lib/homelab-health/backup-audit-v2.json\")\n0005:STATE=pathlib.Path(\"/var/lib/homelab-alerting/backup-alert-state.json\")\n0006:USERCFG=pathlib.Path(\"/etc/pve/user.cfg\")\n0007:SCHEMA=\"homelab-backup-alert-state-v2\"\n0008:THRESHOLDS={\"RPO_BREACH\":2,\"SOURCE_OFFHOST_MISSING\":2,\"LOCK_BUSY\":3}\n0009:def recipient():\n0010: text=USERCFG.read_text(encoding=\"utf-8\",errors=\"replace\")\n0011: m=re.findall(r\"(?i)\\b[A-Z0-9._+-]+@[A-Z0-9.-]+\\.[A-Z]{2,}\\b\",text)\n0012: if len(m)!=1: raise SystemExit(65)\n0013: return m[0]\n0014:def send(subject,body):\n0015: rcpt=recipient()\n0016: msg=f\"From: h***@gram1.ru\\nTo: {rcpt}\\nSubject: {subject}\\nContent-Type: text/plain; charset=UTF-8\\n\\n{body}\\n\"\n0017: p=subprocess.run([\"/usr/sbin/sendmail\",\"-t\"],input=msg,text=True,stdout=subprocess.PIPE,stderr=subprocess.PIPE)\n0018: if p.returncode!=0: raise SystemExit(p.returncode or 75)\n0019:def key(i):\n0020: return \"|\".join(str(i.get(x,\"\")) for x in (\"code\",\"logical_id\",\"root_cause\"))\n0021:def token(i):[REDACTED]\n0022: code=str(i.get(\"code\",\"\"))\n0023: return \"group:\"+code if code in THRESHOLDS else \"issue:\"+key(i)\n0024:if mode==\"email-test\":\n0025: 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.\")\n0026: print(\"EMAIL_TEST_ACCEPTED=YES\")\n0027: raise SystemExit(0)\n0028:if mode!=\"health-alert\": raise SystemExit(64)\n0029:p=subprocess.run([AUDIT,\"write-health\"],text=True,stdout=subprocess.PIPE,stderr=subprocess.PIPE)\n0030:if p.returncode not in (0,1): raise SystemExit(p.returncode or 75)\n0031:try:\n0032: h=json.loads(HEALTH.read_text(encoding=\"utf-8\"))\n0033:except Exception:\n0034: raise SystemExit(69)\n0035:issues=h.get(\"issues\") if isinstance(h.get(\"issues\"),list) else []\n0036:cur={key(i):i for i in issues if isinstance(i,dict)}\n0037:codes=set(str(i.get(\"code\",\"\")) for i in cur.values())\n0038:oldj={}\n0039:if STATE.is_file():\n0040: try:\n0041: oldj=json.loads(STATE.read_text(encoding=\"utf-8\"))\n0042: if not isinstance(oldj,dict): oldj={}\n0043: except Exception:\n0044: oldj={}\n0045:migrating=oldj.get(\"schema\")!=SCHEMA\n0046:prev_counts=oldj.get(\"code_counts\") if isinstance(oldj.get(\"code_counts\"),dict) and not migrating else {}\n0047:counts={}\n0048:for code in codes:\n0049: try: prev=int(prev_counts.get(code,0))\n0050: except Exception: prev=0\n0051: counts[code]=prev+1\n0052:actionable={}\n0053:for k,i in cur.items():\n0054: code=str(i.get(\"code\",\"\"))\n0055: need=int(THRESHOLDS.get(code,1))\n0056: if counts.get(code,0)>=need:\n0057: actionable[k]=i\n0058:tokens=[REDACTED]\n0059:old_tokens=[REDACTED]\n0060:if not migrating:\n0061: old_tokens=[REDACTED]\n0062:added=[REDACTED]\n0063:removed=[REDACTED]\n0064:if added:\n0065: lines=[\n0066: \"Workers2 backup/DR actionable alert state changed.\",\n0067: \"\",\n0068: \"Transient debounce policy: RPO_BREACH=2 checks; SOURCE_OFFHOST_MISSING=2 checks; LOCK_BUSY=3 checks; all other issue codes=immediate.\",\n0069: \"\"\n0070: ]\n0071: for k in sorted(actionable):\n0072: i=actionable[k]\n0073: lines.append(f\"{i.get('severity','UNKNOWN')} {i.get('code','UNKNOWN')} logical_id={i.get('logical_id','-')} root_cause={i.get('root_cause','UNKNOWN')}\")\n0074: suppressed=len(cur)-len(actionable)\n0075: if suppressed:\n0076: lines.extend([\"\",f\"Suppressed transient issue(s) still below threshold: {suppressed}\"])\n0077: send(f\"[Workers2 BACKUP ALERT] {len(actionable)} actionable issue(s)\",\"\\n\".join(lines))\n0078: print(\"ALERT_EMAIL_ACCEPTED=YES\")\n0079:elif old_tokens and not tokens:[REDACTED]\n0080: send(\"[Workers2 BACKUP RECOVERY] all actionable issues cleared\",\"Workers2 backup/DR actionable audit state is clear. All previously notified actionable backup issues are cleared.\")\n0081: print(\"RECOVERY_EMAIL_ACCEPTED=YES\")\n0082:STATE.parent.mkdir(parents=True,exist_ok=True)\n0083:tmp=STATE.with_name(STATE.name+\".tmp\")\n0084:payload={\n0085: \"schema\":SCHEMA,\n0086: \"updated_epoch\":int(time.time()),\n0087: \"issue_keys\":sorted(actionable),\n0088: \"notify_tokens\":[REDACTED]\n0089: \"raw_issue_keys\":sorted(cur),\n0090: \"code_counts\":{k:int(v) for k,v in sorted(counts.items())},\n0091: \"migration_silent\":bool(migrating)\n0092:}\n0093:tmp.write_text(json.dumps(payload,separators=(\",\",\":\"),sort_keys=True)+\"\\n\",encoding=\"utf-8\")\n0094:os.chmod(tmp,0o600)\n0095:os.replace(tmp,STATE)\n0096:print(\"ALERT_FILTER_SCHEMA=\"+SCHEMA)\n0097:print(\"ALERT_RAW_ISSUE_COUNT=\"+str(len(cur)))\n0098:print(\"ALERT_ACTIONABLE_ISSUE_COUNT=\"+str(len(actionable)))\n0099:print(\"ALERT_NOTIFY_TOKEN_COUNT=[REDACTED]\n0100:print(\"ALERT_ADDED_TOKEN_COUNT=[REDACTED]\n0101:print(\"ALERT_REMOVED_TOKEN_COUNT=[REDACTED]\n0102:print(\"ALERT_SUPPRESSED_TRANSIENT_COUNT=\"+str(len(cur)-len(actionable)))\n0103:print(\"ALERT_STATE_MIGRATION_SILENT=\"+(\"true\" if migrating else \"false\"))\n0104:print(\"HEALTH_ALERT_STATE=OK\")\nALERT_EMBEDDED_SOURCE_END\n=== AUDIT_SOURCE_RELEVANT ===\n183- (\"homelab-alertmanager-backup-health.timer\",\"ALERT_TIMER_BAD\"),\n184-]:\n185- ok,a,e=unit_ok(unit)\n186- if not ok: issues.append({\"severity\":\"HIGH\",\"code\":code,\"logical_id\":unit,\"root_cause\":\"UNIT_\"+a+\"_\"+e})\n187-\n188: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\"]:\n189- p=pathlib.Path(lock)\n190- if p.exists():\n191: lrc,_,_=run([\"flock\",\"-n\",str(p),\"-c\",\"true\"],5)\n192: if lrc!=0: issues.append({\"severity\":\"HIGH\",\"code\":\"LOCK_BUSY\",\"logical_id\":lock,\"root_cause\":\"ACTIVE_OR_ORPHAN_LOCK\"})\n193-\n194-env=os.environ.copy(); env[\"HOMELAB_BACKUP_GFS_POLICY\"]=GFSP; env[\"HOMELAB_BACKUP_TARGET_REGISTRY\"]=str(REG)\n195-grc,gout,_=run([GFSH,\"validate\"],20,env)\n196-if grc!=0 or \"GFS_POLICY=OK\" not in gout:\n197- issues.append({\"severity\":\"CRITICAL\",\"code\":\"GFS_INVALID\",\"logical_id\":\"-\",\"root_cause\":\"GFS_VALIDATE_FAILED\"})\n--\n287-except Exception:\n288- cloudb_ok=False\n289-if not cloudb_ok:\n290- 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\"})\n291-\n292:source={\"local_head\":None,\"remote_head\":None,\"pushurl_disabled\":False}\n293-hrc,ho,_=run([\"git\",\"-C\",WT,\"rev-parse\",\"HEAD\"],10)\n294:if hrc==0: source[\"local_head\"]=ho.strip()\n295-frc,fo,_=run([\"git\",\"-C\",WT,\"config\",\"--get\",\"remote.origin.url\"],10)\n296-prc,po,_=run([\"git\",\"-C\",WT,\"config\",\"--get\",\"remote.origin.pushurl\"],10)\n297-source[\"pushurl_disabled\"]=(prc==0 and po.strip()==\"DISABLED\")\n298-if frc==0 and fo.strip():\n299- lrc,lo,_=run([\"git\",\"ls-remote\",fo.strip(),\"refs/heads/\"+BRANCH],30)\n300: if lrc==0 and lo.strip(): source[\"remote_head\"]=lo.split()[0]\n301:if source[\"remote_head\"]!=source[\"local_head\"]:\n302: issues.append({\"severity\":\"MEDIUM\",\"code\":\"SOURCE_OFFHOST_MISSING\",\"logical_id\":\"-\",\"root_cause\":\"CR_BRANCH_SHA_NOT_EXACT\"})\n303-\n304-status=\"GREEN\" if not issues else \"RED\"\n305-for t in targets:\n306- print(\"TARGET|\"+\"|\".join(f\"{k}={v}\" for k,v in t.items() if v is not None))\n307-for i in issues:\n308- print(\"ISSUE|severity={severity}|code={code}|logical_id={logical_id}|root_cause={root_cause}\".format(**i))\n309: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'}\")\n310-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\")}\n311-if MODE in (\"write-health\",\"scheduled\"):\n312- for hp in HEALTHS:\n313- hp.parent.mkdir(parents=True,exist_ok=True)\n314- tmp=hp.with_name(hp.name+\".tmp\")\n=== LIVE_SOURCE_HEAD_RECHECK ===\nSOURCE_LOCAL_HEAD=db592a25c6ac587bf16472a6132b66698c42f663\nSOURCE_BRANCH=cr-2026-1005-backup-v2-health-alerting-remediation\nSOURCE_WORKTREE_CLEAN=true\nSOURCE_ORIGIN_URL_SHA256=7507b97d441d05c4e33306608cbf655e96bf2add0ec7683cc2f4e5539f64daf9\nSOURCE_REMOTE_ATTEMPT=1 HEAD=db592a25c6ac587bf16472a6132b66698c42f663 STDERR_BYTES=0 EXACT=true\nSOURCE_REMOTE_ATTEMPT=2 HEAD=db592a25c6ac587bf16472a6132b66698c42f663 STDERR_BYTES=0 EXACT=true\nSOURCE_REMOTE_ATTEMPT=3 HEAD=db592a25c6ac587bf16472a6132b66698c42f663 STDERR_BYTES=0 EXACT=true\nSOURCE_REMOTE_ATTEMPT=4 HEAD=db592a25c6ac587bf16472a6132b66698c42f663 STDERR_BYTES=0 EXACT=true\nSOURCE_REMOTE_ATTEMPT=5 HEAD=db592a25c6ac587bf16472a6132b66698c42f663 STDERR_BYTES=0 EXACT=true\n=== CURRENT_LOCK_OWNERSHIP ===\nLOCK_META=/run/homelab-backup-heavy.lock|inode=3474|600|root:root|2026-09-28 03:27:07.425060217 +0300\nLOCK_FUSER=/run/homelab-backup-heavy.lock| 1856481\nLOCK_FREE=/run/homelab-backup-heavy.lock|false\nLOCK_META=/run/lock/homelab-backup-dispatcher.lock|inode=9|600|root:root|2026-09-28 03:27:07.423060188 +0300\nLOCK_FUSER=/run/lock/homelab-backup-dispatcher.lock|\nLOCK_FREE=/run/lock/homelab-backup-dispatcher.lock|true\nLOCK_META=/run/lock/homelab-vm-cloud-quorum-queue.lock|inode=2944|600|root:root|2026-09-28 03:27:07.424060203 +0300\nLOCK_FUSER=/run/lock/homelab-vm-cloud-quorum-queue.lock|\nLOCK_FREE=/run/lock/homelab-vm-cloud-quorum-queue.lock|true\nLOCK_META=/run/lock/homelab-app-cloud-quorum-queue.lock|inode=15|600|root:root|2026-09-28 03:27:07.425060217 +0300\nLOCK_FUSER=/run/lock/homelab-app-cloud-quorum-queue.lock|\nLOCK_FREE=/run/lock/homelab-app-cloud-quorum-queue.lock|true\nhomelab-backup- 1856481 FLOCK WRITE /run/homelab-backup-heavy.lock\n=== ALERT_EMAIL_TIME_CORRELATION_0701_MSK ===\n2026-09-28T06:19:01.361470+03:00 pve01 systemd[1]: Starting homelab-backup-v2.service - Homelab Backup V2 manifest-driven scheduler...\n2026-09-28T06:36:20.418325+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\n2026-09-28T06:36:20.418325+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\n2026-09-28T06:36:20.423980+03:00 pve01 systemd[1]: homelab-backup-audit.service: Main process exited, code=exited, status=1/FAILURE\n2026-09-28T06:36:20.424205+03:00 pve01 systemd[1]: Failed to start homelab-backup-audit.service - Homelab unified backup and DR audit.\n2026-09-28T07:06:48.299695+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\n2026-09-28T07:06:48.299695+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\n2026-09-28T07:06:48.304891+03:00 pve01 systemd[1]: homelab-backup-audit.service: Main process exited, code=exited, status=1/FAILURE\n2026-09-28T07:06:48.305137+03:00 pve01 systemd[1]: Failed to start homelab-backup-audit.service - Homelab unified backup and DR audit.\n2026-09-28T06:15:16.319082+03:00 pve01 systemd[1]: Starting homelab-alertmanager-backup-health.service - Workers2 backup health alert via existing alertmanager backup integration...\n2026-09-28T06:15:20.661916+03:00 pve01 homelab-alertmanager-backup-run[1835343]: HEALTH_ALERT_STATE=OK\n2026-09-28T06:15:20.666144+03:00 pve01 systemd[1]: Finished homelab-alertmanager-backup-health.service - Workers2 backup health alert via existing alertmanager backup integration.\n2026-09-28T06:30:42.414371+03:00 pve01 systemd[1]: Starting homelab-alertmanager-backup-health.service - Workers2 backup health alert via existing alertmanager backup integration...\n2026-09-28T06:30:46.367196+03:00 pve01 homelab-alertmanager-backup-run[1886013]: HEALTH_ALERT_STATE=OK\n2026-09-28T06:30:46.370827+03:00 pve01 systemd[1]: Finished homelab-alertmanager-backup-health.service - Workers2 backup health alert via existing alertmanager backup integration.\n2026-09-28T06:46:01.347189+03:00 pve01 systemd[1]: Starting homelab-alertmanager-backup-health.service - Workers2 backup health alert via existing alertmanager backup integration...\n2026-09-28T06:46:05.406037+03:00 pve01 homelab-alertmanager-backup-run[1945314]: HEALTH_ALERT_STATE=OK\n2026-09-28T06:46:05.410491+03:00 pve01 systemd[1]: Finished homelab-alertmanager-backup-health.service - Workers2 backup health alert via existing alertmanager backup integration.\n2026-09-28T07:01:32.217324+03:00 pve01 systemd[1]: Starting homelab-alertmanager-backup-health.service - Workers2 backup health alert via existing alertmanager backup integration...\n2026-09-28T07:01:36.274466+03:00 pve01 homelab-alertmanager-backup-run[1988992]: ALERT_EMAIL_ACCEPTED=YES\n2026-09-28T07:01:36.274466+03:00 pve01 homelab-alertmanager-backup-run[1988992]: HEALTH_ALERT_STATE=OK\n2026-09-28T07:01:36.278152+03:00 pve01 systemd[1]: Finished homelab-alertmanager-backup-health.service - Workers2 backup health alert via existing alertmanager backup integration.\n2026-09-28T07:16:37.585569+03:00 pve01 systemd[1]: Starting homelab-alertmanager-backup-health.service - Workers2 backup health alert via existing alertmanager backup integration...\n2026-09-28T07:16:41.913014+03:00 pve01 homelab-alertmanager-backup-run[2048228]: HEALTH_ALERT_STATE=OK\n2026-09-28T07:16:41.916768+03:00 pve01 systemd[1]: Finished homelab-alertmanager-backup-health.service - Workers2 backup health alert via existing alertmanager backup integration.\n=== ALERT_FREQUENCY_LAST12H ===\nALERT_RUN_START_COUNT=0\nALERT_EMAIL_ACCEPTED_COUNT=3\nRECOVERY_EMAIL_ACCEPTED_COUNT=0\nHEALTH_ALERT_STATE_OK_COUNT=47\n2026-09-27T19:32:04.991437+03:00 pve01 homelab-alertmanager-backup-run[3909103]: HEALTH_ALERT_STATE=OK\n2026-09-27T19:47:36.328545+03:00 pve01 homelab-alertmanager-backup-run[3959645]: HEALTH_ALERT_STATE=OK\n2026-09-27T20:02:46.359055+03:00 pve01 homelab-alertmanager-backup-run[4008840]: HEALTH_ALERT_STATE=OK\n2026-09-27T20:18:05.225521+03:00 pve01 homelab-alertmanager-backup-run[4059785]: HEALTH_ALERT_STATE=OK\n2026-09-27T20:33:20.585967+03:00 pve01 homelab-alertmanager-backup-run[4108890]: HEALTH_ALERT_STATE=OK\n2026-09-27T20:48:36.460451+03:00 pve01 homelab-alertmanager-backup-run[4148152]: HEALTH_ALERT_STATE=OK\n2026-09-27T21:04:08.100470+03:00 pve01 homelab-alertmanager-backup-run[4070]: HEALTH_ALERT_STATE=OK\n2026-09-27T21:19:36.336976+03:00 pve01 homelab-alertmanager-backup-run[54137]: HEALTH_ALERT_STATE=OK\n2026-09-27T21:35:05.706232+03:00 pve01 homelab-alertmanager-backup-run[104752]: HEALTH_ALERT_STATE=OK\n2026-09-27T21:50:23.015203+03:00 pve01 homelab-alertmanager-backup-run[154365]: HEALTH_ALERT_STATE=OK\n2026-09-27T22:05:36.461278+03:00 pve01 homelab-alertmanager-backup-run[202960]: HEALTH_ALERT_STATE=OK\n2026-09-27T22:21:05.253758+03:00 pve01 homelab-alertmanager-backup-run[242449]: HEALTH_ALERT_STATE=OK\n2026-09-27T22:36:15.399283+03:00 pve01 homelab-alertmanager-backup-run[292331]: HEALTH_ALERT_STATE=OK\n2026-09-27T22:51:31.819800+03:00 pve01 homelab-alertmanager-backup-run[343850]: HEALTH_ALERT_STATE=OK\n2026-09-27T23:06:53.759023+03:00 pve01 homelab-alertmanager-backup-run[396329]: HEALTH_ALERT_STATE=OK\n2026-09-27T23:22:20.677831+03:00 pve01 homelab-alertmanager-backup-run[461385]: HEALTH_ALERT_STATE=OK\n2026-09-27T23:37:36.973241+03:00 pve01 homelab-alertmanager-backup-run[513251]: HEALTH_ALERT_STATE=OK\n2026-09-27T23:52:43.434843+03:00 pve01 homelab-alertmanager-backup-run[566888]: ALERT_EMAIL_ACCEPTED=YES\n2026-09-27T23:52:43.434843+03:00 pve01 homelab-alertmanager-backup-run[566888]: HEALTH_ALERT_STATE=OK\n2026-09-28T00:08:05.576769+03:00 pve01 homelab-alertmanager-backup-run[607129]: HEALTH_ALERT_STATE=OK\n2026-09-28T00:23:21.212626+03:00 pve01 homelab-alertmanager-backup-run[660884]: HEALTH_ALERT_STATE=OK\n2026-09-28T00:38:36.269886+03:00 pve01 homelab-alertmanager-backup-run[711652]: HEALTH_ALERT_STATE=OK\n2026-09-28T00:53:55.974540+03:00 pve01 homelab-alertmanager-backup-run[762988]: HEALTH_ALERT_STATE=OK\n2026-09-28T01:09:05.464301+03:00 pve01 homelab-alertmanager-backup-run[812499]: HEALTH_ALERT_STATE=OK\n2026-09-28T01:24:16.127247+03:00 pve01 homelab-alertmanager-backup-run[862903]: HEALTH_ALERT_STATE=OK\n2026-09-28T01:39:41.256513+03:00 pve01 homelab-alertmanager-backup-run[919688]: HEALTH_ALERT_STATE=OK\n2026-09-28T01:54:54.298806+03:00 pve01 homelab-alertmanager-backup-run[958250]: HEALTH_ALERT_STATE=OK\n2026-09-28T02:10:05.486220+03:00 pve01 homelab-alertmanager-backup-run[1009352]: HEALTH_ALERT_STATE=OK\n2026-09-28T02:25:22.594856+03:00 pve01 homelab-alertmanager-backup-run[1058040]: HEALTH_ALERT_STATE=OK\n2026-09-28T02:40:53.144072+03:00 pve01 homelab-alertmanager-backup-run[1108677]: HEALTH_ALERT_STATE=OK\n2026-09-28T02:56:20.122916+03:00 pve01 homelab-alertmanager-backup-run[1157287]: HEALTH_ALERT_STATE=OK\n2026-09-28T03:11:36.224287+03:00 pve01 homelab-alertmanager-backup-run[1207541]: HEALTH_ALERT_STATE=OK\n2026-09-28T03:26:56.104164+03:00 pve01 homelab-alertmanager-backup-run[1267608]: HEALTH_ALERT_STATE=OK\n2026-09-28T03:42:16.163161+03:00 pve01 homelab-alertmanager-backup-run[1337091]: HEALTH_ALERT_STATE=OK\n2026-09-28T03:57:35.911704+03:00 pve01 homelab-alertmanager-backup-run[1388112]: HEALTH_ALERT_STATE=OK\n2026-09-28T04:12:45.302638+03:00 pve01 homelab-alertmanager-backup-run[1439953]: ALERT_EMAIL_ACCEPTED=YES\n2026-09-28T04:12:45.302638+03:00 pve01 homelab-alertmanager-backup-run[1439953]: HEALTH_ALERT_STATE=OK\n2026-09-28T04:28:16.066840+03:00 pve01 homelab-alertmanager-backup-run[1491056]: HEALTH_ALERT_STATE=OK\n2026-09-28T04:43:26.035041+03:00 pve01 homelab-alertmanager-backup-run[1543022]: HEALTH_ALERT_STATE=OK\n2026-09-28T04:58:29.541024+03:00 pve01 homelab-alertmanager-backup-run[1593789]: HEALTH_ALERT_STATE=OK\n2026-09-28T05:13:39.334685+03:00 pve01 homelab-alertmanager-backup-run[1645768]: HEALTH_ALERT_STATE=OK\n2026-09-28T05:28:53.353807+03:00 pve01 homelab-alertmanager-backup-run[1685761]: HEALTH_ALERT_STATE=OK\n2026-09-28T05:44:20.155523+03:00 pve01 homelab-alertmanager-backup-run[1736193]: HEALTH_ALERT_STATE=OK\n2026-09-28T06:00:05.422013+03:00 pve01 homelab-alertmanager-backup-run[1785685]: HEALTH_ALERT_STATE=OK\n2026-09-28T06:15:20.661916+03:00 pve01 homelab-alertmanager-backup-run[1835343]: HEALTH_ALERT_STATE=OK\n2026-09-28T06:30:46.367196+03:00 pve01 homelab-alertmanager-backup-run[1886013]: HEALTH_ALERT_STATE=OK\n2026-09-28T06:46:05.406037+03:00 pve01 homelab-alertmanager-backup-run[1945314]: HEALTH_ALERT_STATE=OK\n2026-09-28T07:01:36.274466+03:00 pve01 homelab-alertmanager-backup-run[1988992]: ALERT_EMAIL_ACCEPTED=YES\n2026-09-28T07:01:36.274466+03:00 pve01 homelab-alertmanager-backup-run[1988992]: HEALTH_ALERT_STATE=OK\n2026-09-28T07:16:41.913014+03:00 pve01 homelab-alertmanager-backup-run[2048228]: HEALTH_ALERT_STATE=OK\n=== AUDIT_FREQUENCY_LAST12H ===\nAUDIT_GREEN_SUMMARY_COUNT=7\nAUDIT_RED_SUMMARY_COUNT=17\nAUDIT_LOCK_BUSY_ISSUE_COUNT=9\nAUDIT_SOURCE_OFFHOST_ISSUE_COUNT=0\n2026-09-27T19:37:02.093711+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\n2026-09-27T20:06:15.522779+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\n2026-09-27T20:36:05.450336+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\n2026-09-27T21:06:02.094425+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\n2026-09-27T21:37:05.002224+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\n2026-09-27T22:06:07.004513+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\n2026-09-27T22:35:26.212759+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\n2026-09-27T23:06:54.987894+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\n2026-09-27T23:36:37.162587+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\n2026-09-27T23:36:37.162587+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\n2026-09-28T00:06:21.135619+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\n2026-09-28T00:06:21.135619+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\n2026-09-28T00:36:10.445081+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\n2026-09-28T00:36:10.445081+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\n2026-09-28T01:06:01.997372+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\n2026-09-28T01:36:02.006941+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\n2026-09-28T02:05:36.356288+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\n2026-09-28T02:36:15.265015+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\n2026-09-28T03:05:20.453132+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\n2026-09-28T03:35:20.147380+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\n2026-09-28T03:35:20.147380+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\n2026-09-28T04:06:45.928910+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\n2026-09-28T04:06:45.928910+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\n2026-09-28T04:35:20.240415+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\n2026-09-28T04:35:20.240415+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\n2026-09-28T05:05:52.974415+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\n2026-09-28T05:05:52.974415+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\n2026-09-28T05:37:02.145613+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\n2026-09-28T06:06:02.032037+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\n2026-09-28T06:36:20.418325+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\n2026-09-28T06:36:20.418325+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\n2026-09-28T07:06:48.299695+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\n2026-09-28T07:06:48.299695+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\n=== HEALTH_GENERATION_CORRELATION ===\nHEALTH_GENERATED_AT_EPOCH=1790568997\nHEALTH_CORRELATION_FROM=1790568817\nHEALTH_CORRELATION_TO=1790569177\n=== FRESH_QUIET_AUDIT ===\nQUIET_AUDIT_WAIT|attempt=1|reason=SERVICE_BUSY|active=activating|pid=1856481\nQUIET_AUDIT_WAIT|attempt=2|reason=SERVICE_BUSY|active=activating|pid=1856481\nQUIET_AUDIT_WAIT|attempt=3|reason=SERVICE_BUSY|active=activating|pid=1856481\nQUIET_AUDIT_WAIT|attempt=4|reason=SERVICE_BUSY|active=activating|pid=1856481\nQUIET_AUDIT_WAIT|attempt=5|reason=SERVICE_BUSY|active=activating|pid=1856481\nQUIET_AUDIT_WAIT|attempt=6|reason=SERVICE_BUSY|active=activating|pid=1856481\nQUIET_AUDIT_WAIT|attempt=7|reason=SERVICE_BUSY|active=activating|pid=1856481\nQUIET_AUDIT_WAIT|attempt=8|reason=SERVICE_BUSY|active=activating|pid=1856481\nQUIET_AUDIT_WAIT|attempt=9|reason=SERVICE_BUSY|active=activating|pid=1856481\nQUIET_AUDIT_WAIT|attempt=10|reason=SERVICE_BUSY|active=activating|pid=1856481\nQUIET_AUDIT_WAIT|attempt=11|reason=SERVICE_BUSY|active=activating|pid=1856481\nQUIET_AUDIT_WAIT|attempt=12|reason=SERVICE_BUSY|active=activating|pid=1856481\nQUIET_AUDIT_WAIT|attempt=13|reason=SERVICE_BUSY|active=activating|pid=1856481\nQUIET_AUDIT_WAIT|attempt=14|reason=SERVICE_BUSY|active=activating|pid=1856481\nQUIET_AUDIT_WAIT|attempt=15|reason=SERVICE_BUSY|active=activating|pid=1856481\nQUIET_AUDIT_WAIT|attempt=16|reason=SERVICE_BUSY|active=activating|pid=1856481\nQUIET_AUDIT_WAIT|attempt=17|reason=SERVICE_BUSY|active=activating|pid=1856481\nQUIET_AUDIT_WAIT|attempt=18|reason=SERVICE_BUSY|active=activating|pid=1856481\nQUIET_AUDIT_WAIT|attempt=19|reason=SERVICE_BUSY|active=activating|pid=1856481\nQUIET_AUDIT_WAIT|attempt=20|reason=SERVICE_BUSY|active=activating|pid=1856481\nQUIET_AUDIT_WAIT|attempt=21|reason=SERVICE_BUSY|active=activating|pid=1856481\nQUIET_AUDIT_WAIT|attempt=22|reason=SERVICE_BUSY|active=activating|pid=1856481\nQUIET_AUDIT_WAIT|attempt=23|reason=SERVICE_BUSY|active=activating|pid=1856481\nQUIET_AUDIT_WAIT|attempt=24|reason=SERVICE_BUSY|active=activating|pid=1856481\nQUIET_AUDIT_WAIT|attempt=25|reason=SERVICE_BUSY|active=activating|pid=1856481\nQUIET_AUDIT_WAIT|attempt=26|reason=SERVICE_BUSY|active=activating|pid=1856481\nQUIET_AUDIT_WAIT|attempt=27|reason=SERVICE_BUSY|active=activating|pid=1856481\nQUIET_AUDIT_WAIT|attempt=28|reason=SERVICE_BUSY|active=activating|pid=1856481\nQUIET_AUDIT_WAIT|attempt=29|reason=SERVICE_BUSY|active=activating|pid=1856481\nQUIET_AUDIT_WAIT|attempt=30|reason=SERVICE_BUSY|active=activating|pid=1856481\nQUIET_AUDIT_WAIT|attempt=31|reason=SERVICE_BUSY|active=activating|pid=1856481\nQUIET_AUDIT_WAIT|attempt=32|reason=SERVICE_BUSY|active=activating|pid=1856481\nQUIET_AUDIT_WAIT|attempt=33|reason=SERVICE_BUSY|active=activating|pid=1856481\nQUIET_AUDIT_WAIT|attempt=34|reason=SERVICE_BUSY|active=activating|pid=1856481\nQUIET_AUDIT_WAIT|attempt=35|reason=SERVICE_BUSY|active=activating|pid=1856481\nQUIET_AUDIT_WAIT|attempt=36|reason=SERVICE_BUSY|active=activating|pid=1856481\nFRESH_QUIET_AUDIT_RC=NO_QUIET_WINDOW\nFRESH_AUDIT_HEALTH_NO_WRITE=false\n=== CANONICAL_ALERT_SOURCE_AUTHORITY ===\nCANONICAL_ALERT_PATH=/root/homelab-ops-cr-2026-1005/tasks/backup-v2-health-alerting-remediation-v1/assets/baseline/homelab-alertmanager-backup-run\nCANONICAL_ALERT_EXISTS=true\nCANONICAL_ALERT_SHA256=6deef30b4708a7e5b2ac0f0d98bb6b37b22d858afde994483b67baa18dffdc2a\nCANONICAL_ALERT_MATCH_LIVE=false\nCANONICAL_SOURCE_HEAD=db592a25c6ac587bf16472a6132b66698c42f663\nCANONICAL_REMOTE_HEAD=db592a25c6ac587bf16472a6132b66698c42f663\nCANONICAL_SOURCE_EXACT=true\nTASK_RESULT=PASS_BACKUP_ALERT_SPAM_CURRENT_RCA_COLLECTED\nDECISION=PASS_BACKUP_ALERT_SPAM_CURRENT_RCA_COLLECTED\nNEXT_GATE=READ_EXACT_1237_AND_FIX_ONLY_PROVEN_ALERT_NOISE_CAUSE\nHOMELAB_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}\n" + "output": "BACKUP_ALERT_NOISE_ROOT_RCA_BEGIN=true\nCOMMAND_ID=SUPPORT-260928-HOMELAB-BACKUP-ALERT-NOISE-ROOT-RCA-1238R1\nMODE=read-only\nCOMPONENT=homelab-backup-alert-noise-root-rca\nMUTATION_BOUNDARY=READ_ONLY_SYSTEMD_CONTEXT_GIT_REMOTE_PROBES_AUDIT_ALL_SOURCE_DISCOVERY_AND_HISTORICAL_CORRELATION;NO_ALERT_EXECUTION;NO_MAIL;NO_BACKUP;NO_LOCK_ACQUIRE;NO_CONFIG_WRITE;NO_SCRIPT_WRITE;NO_SYSTEMD_ACTION;NO_TIMER_CHANGE;NO_HEALTH_WRITE;NO_GIT_WRITE;NO_RETENTION;NO_DELETE;NO_RESTORE;NO_NETBIRD_SKLADCHIK_CHANGE\n=== AUTHORITY ===\nHOST=pve01\nCLUSTER_QUORATE=Yes\nRUNNER_SHA256=b248a4c32c9cc64e5747e7dce6c7fc0a23f5124a77c71ce72e27a81aceae9d2d\nSOURCE_1237_STATUS=OK\nSOURCE_1237_RC=0\nSOURCE_1237_DECISION=PASS_BACKUP_ALERT_SPAM_CURRENT_RCA_COLLECTED\nSOURCE_1237_NEXT_GATE=READ_EXACT_1237_AND_FIX_ONLY_PROVEN_ALERT_NOISE_CAUSE\n=== LIVE_IDENTITIES ===\nWRAPPER_SHA256=894f8ea346b53a3d7846dbd6eeb5b89333957eb6d7a4f2f64fd4557cae176e1c\nHELPER_SHA256=4e39404b1ddb97392645adce6280f697182cca03714d3a462d363eebce9b1860\nVZDUMP_CONF_SHA256=027e4b04852a4b83d558eb861d432b6fad4f234e12ab77d327f274d0fdedbfad\nAUDIT_SHA256=f7b936fa997bdefdd0c3c5d1d96e496888ebebc8ea85a60ed3bf5bcc9bf4962a\nALERT_SHA256=2b92cd44fc5b43decba0ea0706c4c84e1912cdc6d7b9bcb10bbf9552c98dc3f9\n=== SOURCE_BRANCH_AUTHORITY ===\nSOURCE_LOCAL_HEAD=db592a25c6ac587bf16472a6132b66698c42f663\nSOURCE_BRANCH=cr-2026-1005-backup-v2-health-alerting-remediation\nSOURCE_WORKTREE_CLEAN=true\nSOURCE_ORIGIN_SCHEME=https\nSOURCE_ORIGIN_URL_SHA256=7507b97d441d05c4e33306608cbf655e96bf2add0ec7683cc2f4e5539f64daf9\nSOURCE_REMOTE_HEAD=db592a25c6ac587bf16472a6132b66698c42f663\nSOURCE_LOCAL_REMOTE_EXACT=true\n=== SYSTEMD_UNIT_CONTEXT ===\nSYSTEMD_SHOW_BEGIN=homelab-backup-audit.service\nExecStart={ path=/usr/local/sbin/homelab-backup-audit ; argv[]=/usr/local/sbin/homelab-backup-audit scheduled ; ignore_errors=no ; start_time=[Mon 2026-09-28 07:36:16 MSK] ; stop_time=[Mon 2026-09-28 07:36:20 MSK] ; pid=2104808 ; code=exited ; status=1 }\nEnvironment=\nWorkingDirectory=\nRootDirectory=\nUser=root\nGroup=root\nDynamicUser=no\nPAMName=\nSYSTEMD_SHOW_END=homelab-backup-audit.service\nSYSTEMD_CAT_BEGIN=homelab-backup-audit.service\n# /etc/systemd/system/homelab-backup-audit.service\n[Unit]\nDescription=Homelab unified backup and DR audit\nAfter=network-online.target\nWants=network-online.target\n\n[Service]\nType=oneshot\nExecStart=/usr/local/sbin/homelab-backup-audit scheduled\nUser=root\nGroup=root\nUMask=0077\nNice=10\nIOSchedulingClass=best-effort\nIOSchedulingPriority=7\nSYSTEMD_CAT_END=homelab-backup-audit.service\nSYSTEMD_SHOW_BEGIN=homelab-alertmanager-backup-health.service\nExecStart={ path=/usr/local/sbin/homelab-alertmanager-backup-run ; argv[]=/usr/local/sbin/homelab-alertmanager-backup-run health-alert ; ignore_errors=no ; start_time=[Mon 2026-09-28 07:31:56 MSK] ; stop_time=[Mon 2026-09-28 07:32:00 MSK] ; pid=2089737 ; code=exited ; status=0 }\nEnvironment=\nWorkingDirectory=\nRootDirectory=\nUser=\nGroup=\nDynamicUser=no\nPAMName=\nSYSTEMD_SHOW_END=homelab-alertmanager-backup-health.service\nSYSTEMD_CAT_BEGIN=homelab-alertmanager-backup-health.service\n# /etc/systemd/system/homelab-alertmanager-backup-health.service\n[Unit]\nDescription=Workers2 backup health alert via existing alertmanager backup integration\nAfter=network-online.target\n\n[Service]\nType=oneshot\nExecStart=/usr/local/sbin/homelab-alertmanager-backup-run health-alert\nSYSTEMD_CAT_END=homelab-alertmanager-backup-health.service\nSYSTEM_MANAGER_ENV_RELEVANT_BEGIN\nPATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin\nSYSTEM_MANAGER_ENV_RELEVANT_END\n=== GIT_CONFIG_CONTEXT ===\nGIT_CONFIG_MODE=minimal OUT_BYTES=0 ERR_BYTES=21 OUT_SHA256=e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855 ERR_SHA256=6a8a72c20480deb7191693468ae1348ea123ecd0c5ff9baf8693dd293e9112cb\nGIT_CONFIG_MODE=nohome OUT_BYTES=0 ERR_BYTES=21 OUT_SHA256=e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855 ERR_SHA256=6a8a72c20480deb7191693468ae1348ea123ecd0c5ff9baf8693dd293e9112cb\nGIT_CONFIG_MODE=homeroot OUT_BYTES=346 ERR_BYTES=0 OUT_SHA256=9a188d2d29e9701bac3d2fe0cc4f11283f36fca0a941b1b3aeaf10d3b47fdc7e ERR_SHA256=e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855\n=== REMOTE_CONTEXT_PROBES ===\nREMOTE_PROBE=normal RC=0 HEAD=db592a25c6ac587bf16472a6132b66698c42f663 EXACT=true STDERR_BYTES=0 STDERR_SHA256=e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855\nREMOTE_PROBE=minimal RC=128 HEAD=NONE EXACT=false STDERR_BYTES=85 STDERR_SHA256=adbd757d7820290ef0868baee0cb62cc4953c3831e45981d82cb0ed5faed79cc\nREMOTE_PROBE_STDERR_BEGIN=minimal\nfatal: could not read Username for 'https://git.gram1.ru': No such device or address\nREMOTE_PROBE_STDERR_END=minimal\nREMOTE_PROBE=nohome RC=128 HEAD=NONE EXACT=false STDERR_BYTES=85 STDERR_SHA256=adbd757d7820290ef0868baee0cb62cc4953c3831e45981d82cb0ed5faed79cc\nREMOTE_PROBE_STDERR_BEGIN=nohome\nfatal: could not read Username for 'https://git.gram1.ru': No such device or address\nREMOTE_PROBE_STDERR_END=nohome\nREMOTE_PROBE=homeroot RC=0 HEAD=db592a25c6ac587bf16472a6132b66698c42f663 EXACT=true STDERR_BYTES=0 STDERR_SHA256=e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855\n=== AUDIT_ALL_CONTEXT_PROBES ===\nAUDIT_CONTEXT=minimal RC=1 SOURCE_OFFHOST_ISSUES=1 LOCK_BUSY_ISSUES=1 STDERR_BYTES=0\nAUDIT_CONTEXT_SUMMARY=minimal|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=PENDING\nISSUE|severity=MEDIUM|code=SOURCE_OFFHOST_MISSING|logical_id=-|root_cause=CR_BRANCH_SHA_NOT_EXACT\nAUDIT_CONTEXT=nohome RC=1 SOURCE_OFFHOST_ISSUES=1 LOCK_BUSY_ISSUES=1 STDERR_BYTES=0\nAUDIT_CONTEXT_SUMMARY=nohome|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=PENDING\nISSUE|severity=MEDIUM|code=SOURCE_OFFHOST_MISSING|logical_id=-|root_cause=CR_BRANCH_SHA_NOT_EXACT\nAUDIT_CONTEXT=homeroot RC=1 SOURCE_OFFHOST_ISSUES=0 LOCK_BUSY_ISSUES=1 STDERR_BYTES=0\nAUDIT_CONTEXT_SUMMARY=homeroot|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\nAUDIT_CONTEXT=normal RC=1 SOURCE_OFFHOST_ISSUES=0 LOCK_BUSY_ISSUES=1 STDERR_BYTES=0\nAUDIT_CONTEXT_SUMMARY=normal|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\nAUDIT_ALL_CONTEXT_HEALTH_NO_WRITE=true\n=== LOCK_OWNER_CORRELATION ===\nCURRENT_BACKUP_ACTIVE=activating\nCURRENT_BACKUP_MAINPID=1856481\nCURRENT_BACKUP_RESULT=success\nCURRENT_BACKUP_EXEC_STATUS=0\nhomelab-backup- 1856481 FLOCK WRITE /run/homelab-backup-heavy.lock\nCURRENT_HEAVY_FUSER= 1856481\nRAW1237_PATH=/var/lib/homelab-chat-run/raw/SUPPORT-260928-HOMELAB-BACKUP-ALERT-SPAM-CURRENT-RCA-1237R1-20260928T043051Z.log\n25:UNIT=homelab-backup-v2.service ACTIVE=activating ENABLED=static RESULT=success EXEC_MAIN_STATUS=0 MAINPID=1856481\n238:LOCK_FUSER=/run/homelab-backup-heavy.lock| 1856481\n239:LOCK_FREE=/run/homelab-backup-heavy.lock|false\n249:homelab-backup- 1856481 FLOCK WRITE /run/homelab-backup-heavy.lock\n=== AUDIT_LOCK_LOGIC_STATIC ===\nLOCK_LOOP_SOURCE_BEGIN\nfor 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\"]:\n p=pathlib.Path(lock)\n if p.exists():\n lrc,_,_=run([\"flock\",\"-n\",str(p),\"-c\",\"true\"],5)\n if lrc!=0: issues.append({\"severity\":\"HIGH\",\"code\":\"LOCK_BUSY\",\"logical_id\":lock,\"root_cause\":\"ACTIVE_OR_ORPHAN_LOCK\"})\nLOCK_LOOP_SOURCE_END\nLOCK_LOOP_CALLS=issues.append,p.exists,pathlib.Path,run,str\n=== ALERT_COUNTER_LOGIC_STATIC ===\nALERT_LOGIC|0028|if mode!=\"health-alert\": raise SystemExit(64)\nALERT_LOGIC|0029|p=subprocess.run([AUDIT,\"write-health\"],text=True,stdout=subprocess.PIPE,stderr=subprocess.PIPE)\nALERT_LOGIC|0030|if p.returncode not in (0,1): raise SystemExit(p.returncode or 75)\nALERT_LOGIC|0031|try:\nALERT_LOGIC|0032| h=json.loads(HEALTH.read_text(encoding=\"utf-8\"))\nALERT_LOGIC|0033|except Exception:\nALERT_LOGIC|0034| raise SystemExit(69)\nALERT_LOGIC|0035|issues=h.get(\"issues\") if isinstance(h.get(\"issues\"),list) else []\nALERT_LOGIC|0036|cur={key(i):i for i in issues if isinstance(i,dict)}\nALERT_LOGIC|0037|codes=set(str(i.get(\"code\",\"\")) for i in cur.values())\nALERT_LOGIC|0038|oldj={}\nALERT_LOGIC|0039|if STATE.is_file():\nALERT_LOGIC|0040| try:\nALERT_LOGIC|0041| oldj=json.loads(STATE.read_text(encoding=\"utf-8\"))\nALERT_LOGIC|0042| if not isinstance(oldj,dict): oldj={}\nALERT_LOGIC|0043| except Exception:\nALERT_LOGIC|0044| oldj={}\nALERT_LOGIC|0045|migrating=oldj.get(\"schema\")!=SCHEMA\nALERT_LOGIC|0046|prev_counts=oldj.get(\"code_counts\") if isinstance(oldj.get(\"code_counts\"),dict) and not migrating else {}\nALERT_LOGIC|0047|counts={}\nALERT_LOGIC|0048|for code in codes:\nALERT_LOGIC|0049| try: prev=int(prev_counts.get(code,0))\nALERT_LOGIC|0050| except Exception: prev=0\nALERT_LOGIC|0051| counts[code]=prev+1\nALERT_LOGIC|0052|actionable={}\nALERT_LOGIC|0053|for k,i in cur.items():\nALERT_LOGIC|0054| code=str(i.get(\"code\",\"\"))\nALERT_LOGIC|0055| need=int(THRESHOLDS.get(code,1))\nALERT_LOGIC|0056| if counts.get(code,0)>=need:\nALERT_LOGIC|0057| actionable[k]=i\nALERT_LOGIC|0058|tokens=[REDACTED]\nALERT_LOGIC|0082|STATE.parent.mkdir(parents=True,exist_ok=True)\nALERT_LOGIC|0083|tmp=STATE.with_name(STATE.name+\".tmp\")\nALERT_LOGIC|0084|payload={\nALERT_LOGIC|0085| \"schema\":SCHEMA,\nALERT_LOGIC|0086| \"updated_epoch\":int(time.time()),\nALERT_LOGIC|0087| \"issue_keys\":sorted(actionable),\nALERT_LOGIC|0088| \"notify_tokens\":[REDACTED]\nALERT_LOGIC|0089| \"raw_issue_keys\":sorted(cur),\nALERT_LOGIC|0090| \"code_counts\":{k:int(v) for k,v in sorted(counts.items())},\nALERT_LOGIC|0091| \"migration_silent\":bool(migrating)\nALERT_LOGIC|0092|}\nALERT_LOGIC|0093|tmp.write_text(json.dumps(payload,separators=(\",\",\":\"),sort_keys=True)+\"\\n\",encoding=\"utf-8\")\nALERT_LOGIC|0094|os.chmod(tmp,0o600)\nALERT_LOGIC|0095|os.replace(tmp,STATE)\n=== CANONICAL_SOURCE_CANDIDATES ===\nSOURCE_CANDIDATE|name=homelab-backup-audit|exact=false|sha256=1474c9ce58bbc1b3ae7437261d1bdb923232926fb2943c7c830253f8b284724c|path=/root/homelab-ops-cr-2026-1005/tasks/backup-v2-health-alerting-remediation-v1/assets/baseline/homelab-backup-audit\nSOURCE_CANDIDATE_TOTAL|name=homelab-backup-audit|count=1|exact_count=0\nSOURCE_CANDIDATE|name=homelab-alertmanager-backup-run|exact=true|sha256=2b92cd44fc5b43decba0ea0706c4c84e1912cdc6d7b9bcb10bbf9552c98dc3f9|path=/root/homelab-ops-cr-2026-1005/changes/CR-2026-1005/runtime/homelab-alertmanager-backup-run\nSOURCE_CANDIDATE|name=homelab-alertmanager-backup-run|exact=false|sha256=6deef30b4708a7e5b2ac0f0d98bb6b37b22d858afde994483b67baa18dffdc2a|path=/root/homelab-ops-cr-2026-1005/tasks/backup-v2-health-alerting-remediation-v1/assets/baseline/homelab-alertmanager-backup-run\nSOURCE_CANDIDATE_TOTAL|name=homelab-alertmanager-backup-run|count=2|exact_count=1\n=== SOURCE_RELEVANT_GREP ===\nchanges/CR-2026-1005/runtime/homelab-backup-audit-v2:188: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\"]:\nchanges/CR-2026-1005/runtime/homelab-backup-audit-v2:192: if lrc!=0: issues.append({\"severity\":\"HIGH\",\"code\":\"LOCK_BUSY\",\"logical_id\":lock,\"root_cause\":\"ACTIVE_OR_ORPHAN_LOCK\"})\nchanges/CR-2026-1005/runtime/homelab-backup-audit-v2:292:source={\"local_head\":None,\"remote_head\":None,\"pushurl_disabled\":False}\nchanges/CR-2026-1005/runtime/homelab-backup-audit-v2:299: lrc,lo,_=run([\"git\",\"ls-remote\",fo.strip(),\"refs/heads/\"+BRANCH],30)\nchanges/CR-2026-1005/runtime/homelab-backup-audit-v2:300: if lrc==0 and lo.strip(): source[\"remote_head\"]=lo.split()[0]\nchanges/CR-2026-1005/runtime/homelab-backup-audit-v2:301:if source[\"remote_head\"]!=source[\"local_head\"]:\nchanges/CR-2026-1005/runtime/homelab-backup-audit-v2:302: issues.append({\"severity\":\"MEDIUM\",\"code\":\"SOURCE_OFFHOST_MISSING\",\"logical_id\":\"-\",\"root_cause\":\"CR_BRANCH_SHA_NOT_EXACT\"})\nchanges/CR-2026-1005/runtime/homelab-backup-audit-v2:309: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'}\")\nchanges/CR-2026-1005/runtime/homelab-backup-retention-gc:14:HEAVY_LOCK=/run/homelab-backup-heavy.lock\nchanges/CR-2026-1005/runtime/homelab-backup-retention-gc:424: exec 5>\"$LOCK\"; flock -n 5 || die GC_LOCK_BUSY 75\nchanges/CR-2026-1005/runtime/homelab-backup-retention-gc:434: exec 5>\"$LOCK\"; flock -n 5 || { printf 'GC_SCHEDULED=SKIP|reason=GC_LOCK_BUSY\\n'; return 0; }\nchanges/CR-2026-1005/runtime/homelab-backup-retention-gc:444: if ! acquire_gc_locks; then write_health \"$p1\" true 0; printf 'GC_SCHEDULED=SKIP|reason=BACKUP_LOCK_BUSY|candidates=%s|open_transactions=%s\\n' \"$count\" \"$open_tx\"; return 0; fi\nchanges/CR-2026-1005/runtime/homelab-backup-v2-app-scheduled:6:HEAVY_LOCK=/run/homelab-backup-heavy.lock\nchanges/CR-2026-1005/runtime/homelab-backup-v2-app-scheduled:19:exec 9>\"$QUEUE_LOCK\"; if ! flock -n 9; then printf 'APP_V2_SCHEDULED=SKIP|reason=APP_QUEUE_LOCK_BUSY\\n'; exit 0; fi\nchanges/CR-2026-1005/runtime/homelab-backup-v2-app-scheduled:20:exec 8>\"$HEAVY_LOCK\"; if ! flock -n 8; then printf 'APP_V2_SCHEDULED=SKIP|reason=GLOBAL_HEAVY_LOCK_BUSY\\n'; exit 0; fi\ntasks/backup-v2-health-alerting-remediation-v1/assets/baseline/homelab-backup-audit:159:flock -n 9 || die AUDIT_LOCK_BUSY 75\ntasks/backup-v2-health-alerting-remediation-v1/assets/baseline/homelab-backup-audit:422:for lock in /run/homelab-backup-heavy.lock /run/lock/homelab-vm-cloud-quorum-queue.lock /run/lock/homelab-app-cloud-quorum-queue.lock /run/lock/homelab-backup-dispatcher.lock; do\ntasks/backup-v2-health-alerting-remediation-v1/assets/baseline/homelab-backup-retention-gc:14:HEAVY_LOCK=/run/homelab-backup-heavy.lock\ntasks/backup-v2-health-alerting-remediation-v1/assets/baseline/homelab-backup-retention-gc:424: exec 5>\"$LOCK\"; flock -n 5 || die GC_LOCK_BUSY 75\ntasks/backup-v2-health-alerting-remediation-v1/assets/baseline/homelab-backup-retention-gc:434: exec 5>\"$LOCK\"; flock -n 5 || { printf 'GC_SCHEDULED=SKIP|reason=GC_LOCK_BUSY\\n'; return 0; }\ntasks/backup-v2-health-alerting-remediation-v1/assets/baseline/homelab-backup-retention-gc:444: if ! acquire_gc_locks; then write_health \"$p1\" true 0; printf 'GC_SCHEDULED=SKIP|reason=BACKUP_LOCK_BUSY|candidates=%s|open_transactions=%s\\n' \"$count\" \"$open_tx\"; return 0; fi\ntasks/snikket-vm150-rebuild-v2/assets/vm150-runtime.py:60:BACKUP_LOCKS=['/run/lock/homelab-backup-dispatcher.lock','/run/lock/homelab-vm-cloud-quorum-queue.lock','/run/homelab-backup-heavy.lock']\ntasks/snikket-vm150-rebuild-v2/assets/vm150-runtime.py:506: f.close(); die('LOCK_BUSY_'+pathlib.Path(q).name,75)\nTASK_RESULT=PASS_BACKUP_ALERT_NOISE_ROOT_RCA_COLLECTED\nDECISION=PASS_BACKUP_ALERT_NOISE_ROOT_RCA_COLLECTED\nNEXT_GATE=READ_EXACT_1238_AND_APPLY_ONLY_PROVEN_ALERT_NOISE_FIX\nHOMELAB_RESULT_CONTRACT={\"version\":1,\"command_id\":\"SUPPORT-260928-HOMELAB-BACKUP-ALERT-NOISE-ROOT-RCA-1238R1\",\"status\":\"OK\",\"changes_made\":false,\"rollback_started\":false,\"rollback_restored\":null}\n" } diff --git a/runtime/latest.txt b/runtime/latest.txt index ca8bc20f..2695eaf2 100644 --- a/runtime/latest.txt +++ b/runtime/latest.txt @@ -1,15 +1,15 @@ CHAT_OUTPUT_BEGIN -COMMAND_ID=SUPPORT-260928-HOMELAB-BACKUP-ALERT-SPAM-CURRENT-RCA-1237R1 +COMMAND_ID=SUPPORT-260928-HOMELAB-BACKUP-ALERT-NOISE-ROOT-RCA-1238R1 STATUS=OK RC=0 HOST=pve01 MODE=read-only -COMPONENT=homelab-backup-alert-spam-current-rca +COMPONENT=homelab-backup-alert-noise-root-rca REFERENCE_REGISTER_CHECK=OK REFERENCE_SHA256=5a3d8e5154c41cb582a4e0aca68090be1f0138918bf82131a948df326f9d8d66 ERROR_REGISTER_CHECK=OK ERROR_REGISTER_SHA256=3b09a553ec0f527ed3afeed4753f52a74ee3036045bbfb3c685e9f8af4ba7ba0 -COMMAND_SHA256=e205fb5749bd8d2a466e79a56e8d9f3a66537e7dcbd1c635202ab6df607b736b +COMMAND_SHA256=9ae99a8877a8c63075030326f98f8146f9c933c9cbcb7bd076b9bbcfeeb0e1a3 DUPLICATE_FAILED_COMMAND_BLOCKED=false EXECUTION_STARTED=true CHANGE_DECLARED=false @@ -24,432 +24,215 @@ MUTATION_OUTCOME=NO_MUTATION SANITIZED=yes SECRETS_INCLUDED=no PRIVATE_ADDRESSES_INCLUDED=no -RAW_EVIDENCE_SHA256=c64c77856d1b796c0414be59dd0089c9687ec505d26bb8b4111ab68ee967e5a2 -SANITIZED_OUTPUT_SHA256=c64c77856d1b796c0414be59dd0089c9687ec505d26bb8b4111ab68ee967e5a2 +RAW_EVIDENCE_SHA256=9c2e7b15aaf9e4270699137f0f21aa91d7e88a1ae44c347b734ba55e3bbe2b81 +SANITIZED_OUTPUT_SHA256=9c2e7b15aaf9e4270699137f0f21aa91d7e88a1ae44c347b734ba55e3bbe2b81 OUTPUT_BEGIN -BACKUP_ALERT_SPAM_CURRENT_RCA_BEGIN=true -COMMAND_ID=SUPPORT-260928-HOMELAB-BACKUP-ALERT-SPAM-CURRENT-RCA-1237R1 +BACKUP_ALERT_NOISE_ROOT_RCA_BEGIN=true +COMMAND_ID=SUPPORT-260928-HOMELAB-BACKUP-ALERT-NOISE-ROOT-RCA-1238R1 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 +COMPONENT=homelab-backup-alert-noise-root-rca +MUTATION_BOUNDARY=READ_ONLY_SYSTEMD_CONTEXT_GIT_REMOTE_PROBES_AUDIT_ALL_SOURCE_DISCOVERY_AND_HISTORICAL_CORRELATION;NO_ALERT_EXECUTION;NO_MAIL;NO_BACKUP;NO_LOCK_ACQUIRE;NO_CONFIG_WRITE;NO_SCRIPT_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 +SOURCE_1237_STATUS=OK +SOURCE_1237_RC=0 +SOURCE_1237_DECISION=PASS_BACKUP_ALERT_SPAM_CURRENT_RCA_COLLECTED +SOURCE_1237_NEXT_GATE=READ_EXACT_1237_AND_FIX_ONLY_PROVEN_ALERT_NOISE_CAUSE === 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 === +ALERT_SHA256=2b92cd44fc5b43decba0ea0706c4c84e1912cdc6d7b9bcb10bbf9552c98dc3f9 +=== SOURCE_BRANCH_AUTHORITY === SOURCE_LOCAL_HEAD=db592a25c6ac587bf16472a6132b66698c42f663 SOURCE_BRANCH=cr-2026-1005-backup-v2-health-alerting-remediation SOURCE_WORKTREE_CLEAN=true +SOURCE_ORIGIN_SCHEME=https 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 +SOURCE_REMOTE_HEAD=db592a25c6ac587bf16472a6132b66698c42f663 +SOURCE_LOCAL_REMOTE_EXACT=true +=== SYSTEMD_UNIT_CONTEXT === +SYSTEMD_SHOW_BEGIN=homelab-backup-audit.service +ExecStart={ path=/usr/local/sbin/homelab-backup-audit ; argv[]=/usr/local/sbin/homelab-backup-audit scheduled ; ignore_errors=no ; start_time=[Mon 2026-09-28 07:36:16 MSK] ; stop_time=[Mon 2026-09-28 07:36:20 MSK] ; pid=2104808 ; code=exited ; status=1 } +Environment= +WorkingDirectory= +RootDirectory= +User=root +Group=root +DynamicUser=no +PAMName= +SYSTEMD_SHOW_END=homelab-backup-audit.service +SYSTEMD_CAT_BEGIN=homelab-backup-audit.service +# /etc/systemd/system/homelab-backup-audit.service +[Unit] +Description=Homelab unified backup and DR audit +After=network-online.target +Wants=network-online.target + +[Service] +Type=oneshot +ExecStart=/usr/local/sbin/homelab-backup-audit scheduled +User=root +Group=root +UMask=0077 +Nice=10 +IOSchedulingClass=best-effort +IOSchedulingPriority=7 +SYSTEMD_CAT_END=homelab-backup-audit.service +SYSTEMD_SHOW_BEGIN=homelab-alertmanager-backup-health.service +ExecStart={ path=/usr/local/sbin/homelab-alertmanager-backup-run ; argv[]=/usr/local/sbin/homelab-alertmanager-backup-run health-alert ; ignore_errors=no ; start_time=[Mon 2026-09-28 07:31:56 MSK] ; stop_time=[Mon 2026-09-28 07:32:00 MSK] ; pid=2089737 ; code=exited ; status=0 } +Environment= +WorkingDirectory= +RootDirectory= +User= +Group= +DynamicUser=no +PAMName= +SYSTEMD_SHOW_END=homelab-alertmanager-backup-health.service +SYSTEMD_CAT_BEGIN=homelab-alertmanager-backup-health.service +# /etc/systemd/system/homelab-alertmanager-backup-health.service +[Unit] +Description=Workers2 backup health alert via existing alertmanager backup integration +After=network-online.target + +[Service] +Type=oneshot +ExecStart=/usr/local/sbin/homelab-alertmanager-backup-run health-alert +SYSTEMD_CAT_END=homelab-alertmanager-backup-health.service +SYSTEM_MANAGER_ENV_RELEVANT_BEGIN +PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin +SYSTEM_MANAGER_ENV_RELEVANT_END +=== GIT_CONFIG_CONTEXT === +GIT_CONFIG_MODE=minimal OUT_BYTES=0 ERR_BYTES=21 OUT_SHA256=e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855 ERR_SHA256=6a8a72c20480deb7191693468ae1348ea123ecd0c5ff9baf8693dd293e9112cb +GIT_CONFIG_MODE=nohome OUT_BYTES=0 ERR_BYTES=21 OUT_SHA256=e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855 ERR_SHA256=6a8a72c20480deb7191693468ae1348ea123ecd0c5ff9baf8693dd293e9112cb +GIT_CONFIG_MODE=homeroot OUT_BYTES=346 ERR_BYTES=0 OUT_SHA256=9a188d2d29e9701bac3d2fe0cc4f11283f36fca0a941b1b3aeaf10d3b47fdc7e ERR_SHA256=e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855 +=== REMOTE_CONTEXT_PROBES === +REMOTE_PROBE=normal RC=0 HEAD=db592a25c6ac587bf16472a6132b66698c42f663 EXACT=true STDERR_BYTES=0 STDERR_SHA256=e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855 +REMOTE_PROBE=minimal RC=128 HEAD=NONE EXACT=false STDERR_BYTES=85 STDERR_SHA256=adbd757d7820290ef0868baee0cb62cc4953c3831e45981d82cb0ed5faed79cc +REMOTE_PROBE_STDERR_BEGIN=minimal +fatal: could not read Username for 'https://git.gram1.ru': No such device or address +REMOTE_PROBE_STDERR_END=minimal +REMOTE_PROBE=nohome RC=128 HEAD=NONE EXACT=false STDERR_BYTES=85 STDERR_SHA256=adbd757d7820290ef0868baee0cb62cc4953c3831e45981d82cb0ed5faed79cc +REMOTE_PROBE_STDERR_BEGIN=nohome +fatal: could not read Username for 'https://git.gram1.ru': No such device or address +REMOTE_PROBE_STDERR_END=nohome +REMOTE_PROBE=homeroot RC=0 HEAD=db592a25c6ac587bf16472a6132b66698c42f663 EXACT=true STDERR_BYTES=0 STDERR_SHA256=e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855 +=== AUDIT_ALL_CONTEXT_PROBES === +AUDIT_CONTEXT=minimal RC=1 SOURCE_OFFHOST_ISSUES=1 LOCK_BUSY_ISSUES=1 STDERR_BYTES=0 +AUDIT_CONTEXT_SUMMARY=minimal|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=PENDING +ISSUE|severity=MEDIUM|code=SOURCE_OFFHOST_MISSING|logical_id=-|root_cause=CR_BRANCH_SHA_NOT_EXACT +AUDIT_CONTEXT=nohome RC=1 SOURCE_OFFHOST_ISSUES=1 LOCK_BUSY_ISSUES=1 STDERR_BYTES=0 +AUDIT_CONTEXT_SUMMARY=nohome|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=PENDING +ISSUE|severity=MEDIUM|code=SOURCE_OFFHOST_MISSING|logical_id=-|root_cause=CR_BRANCH_SHA_NOT_EXACT +AUDIT_CONTEXT=homeroot RC=1 SOURCE_OFFHOST_ISSUES=0 LOCK_BUSY_ISSUES=1 STDERR_BYTES=0 +AUDIT_CONTEXT_SUMMARY=homeroot|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 +AUDIT_CONTEXT=normal RC=1 SOURCE_OFFHOST_ISSUES=0 LOCK_BUSY_ISSUES=1 STDERR_BYTES=0 +AUDIT_CONTEXT_SUMMARY=normal|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 +AUDIT_ALL_CONTEXT_HEALTH_NO_WRITE=true +=== LOCK_OWNER_CORRELATION === +CURRENT_BACKUP_ACTIVE=activating +CURRENT_BACKUP_MAINPID=1856481 +CURRENT_BACKUP_RESULT=success +CURRENT_BACKUP_EXEC_STATUS=0 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} +CURRENT_HEAVY_FUSER= 1856481 +RAW1237_PATH=/var/lib/homelab-chat-run/raw/SUPPORT-260928-HOMELAB-BACKUP-ALERT-SPAM-CURRENT-RCA-1237R1-20260928T043051Z.log +25:UNIT=homelab-backup-v2.service ACTIVE=activating ENABLED=static RESULT=success EXEC_MAIN_STATUS=0 MAINPID=1856481 +238:LOCK_FUSER=/run/homelab-backup-heavy.lock| 1856481 +239:LOCK_FREE=/run/homelab-backup-heavy.lock|false +249:homelab-backup- 1856481 FLOCK WRITE /run/homelab-backup-heavy.lock +=== AUDIT_LOCK_LOGIC_STATIC === +LOCK_LOOP_SOURCE_BEGIN +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"]: + p=pathlib.Path(lock) + if p.exists(): + lrc,_,_=run(["flock","-n",str(p),"-c","true"],5) + if lrc!=0: issues.append({"severity":"HIGH","code":"LOCK_BUSY","logical_id":lock,"root_cause":"ACTIVE_OR_ORPHAN_LOCK"}) +LOCK_LOOP_SOURCE_END +LOCK_LOOP_CALLS=issues.append,p.exists,pathlib.Path,run,str +=== ALERT_COUNTER_LOGIC_STATIC === +ALERT_LOGIC|0028|if mode!="health-alert": raise SystemExit(64) +ALERT_LOGIC|0029|p=subprocess.run([AUDIT,"write-health"],text=True,stdout=subprocess.PIPE,stderr=subprocess.PIPE) +ALERT_LOGIC|0030|if p.returncode not in (0,1): raise SystemExit(p.returncode or 75) +ALERT_LOGIC|0031|try: +ALERT_LOGIC|0032| h=json.loads(HEALTH.read_text(encoding="utf-8")) +ALERT_LOGIC|0033|except Exception: +ALERT_LOGIC|0034| raise SystemExit(69) +ALERT_LOGIC|0035|issues=h.get("issues") if isinstance(h.get("issues"),list) else [] +ALERT_LOGIC|0036|cur={key(i):i for i in issues if isinstance(i,dict)} +ALERT_LOGIC|0037|codes=set(str(i.get("code","")) for i in cur.values()) +ALERT_LOGIC|0038|oldj={} +ALERT_LOGIC|0039|if STATE.is_file(): +ALERT_LOGIC|0040| try: +ALERT_LOGIC|0041| oldj=json.loads(STATE.read_text(encoding="utf-8")) +ALERT_LOGIC|0042| if not isinstance(oldj,dict): oldj={} +ALERT_LOGIC|0043| except Exception: +ALERT_LOGIC|0044| oldj={} +ALERT_LOGIC|0045|migrating=oldj.get("schema")!=SCHEMA +ALERT_LOGIC|0046|prev_counts=oldj.get("code_counts") if isinstance(oldj.get("code_counts"),dict) and not migrating else {} +ALERT_LOGIC|0047|counts={} +ALERT_LOGIC|0048|for code in codes: +ALERT_LOGIC|0049| try: prev=int(prev_counts.get(code,0)) +ALERT_LOGIC|0050| except Exception: prev=0 +ALERT_LOGIC|0051| counts[code]=prev+1 +ALERT_LOGIC|0052|actionable={} +ALERT_LOGIC|0053|for k,i in cur.items(): +ALERT_LOGIC|0054| code=str(i.get("code","")) +ALERT_LOGIC|0055| need=int(THRESHOLDS.get(code,1)) +ALERT_LOGIC|0056| if counts.get(code,0)>=need: +ALERT_LOGIC|0057| actionable[k]=i +ALERT_LOGIC|0058|tokens=[REDACTED] +ALERT_LOGIC|0082|STATE.parent.mkdir(parents=True,exist_ok=True) +ALERT_LOGIC|0083|tmp=STATE.with_name(STATE.name+".tmp") +ALERT_LOGIC|0084|payload={ +ALERT_LOGIC|0085| "schema":SCHEMA, +ALERT_LOGIC|0086| "updated_epoch":int(time.time()), +ALERT_LOGIC|0087| "issue_keys":sorted(actionable), +ALERT_LOGIC|0088| "notify_tokens":[REDACTED] +ALERT_LOGIC|0089| "raw_issue_keys":sorted(cur), +ALERT_LOGIC|0090| "code_counts":{k:int(v) for k,v in sorted(counts.items())}, +ALERT_LOGIC|0091| "migration_silent":bool(migrating) +ALERT_LOGIC|0092|} +ALERT_LOGIC|0093|tmp.write_text(json.dumps(payload,separators=(",",":"),sort_keys=True)+"\n",encoding="utf-8") +ALERT_LOGIC|0094|os.chmod(tmp,0o600) +ALERT_LOGIC|0095|os.replace(tmp,STATE) +=== CANONICAL_SOURCE_CANDIDATES === +SOURCE_CANDIDATE|name=homelab-backup-audit|exact=false|sha256=1474c9ce58bbc1b3ae7437261d1bdb923232926fb2943c7c830253f8b284724c|path=/root/homelab-ops-cr-2026-1005/tasks/backup-v2-health-alerting-remediation-v1/assets/baseline/homelab-backup-audit +SOURCE_CANDIDATE_TOTAL|name=homelab-backup-audit|count=1|exact_count=0 +SOURCE_CANDIDATE|name=homelab-alertmanager-backup-run|exact=true|sha256=2b92cd44fc5b43decba0ea0706c4c84e1912cdc6d7b9bcb10bbf9552c98dc3f9|path=/root/homelab-ops-cr-2026-1005/changes/CR-2026-1005/runtime/homelab-alertmanager-backup-run +SOURCE_CANDIDATE|name=homelab-alertmanager-backup-run|exact=false|sha256=6deef30b4708a7e5b2ac0f0d98bb6b37b22d858afde994483b67baa18dffdc2a|path=/root/homelab-ops-cr-2026-1005/tasks/backup-v2-health-alerting-remediation-v1/assets/baseline/homelab-alertmanager-backup-run +SOURCE_CANDIDATE_TOTAL|name=homelab-alertmanager-backup-run|count=2|exact_count=1 +=== SOURCE_RELEVANT_GREP === +changes/CR-2026-1005/runtime/homelab-backup-audit-v2:188: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"]: +changes/CR-2026-1005/runtime/homelab-backup-audit-v2:192: if lrc!=0: issues.append({"severity":"HIGH","code":"LOCK_BUSY","logical_id":lock,"root_cause":"ACTIVE_OR_ORPHAN_LOCK"}) +changes/CR-2026-1005/runtime/homelab-backup-audit-v2:292:source={"local_head":None,"remote_head":None,"pushurl_disabled":False} +changes/CR-2026-1005/runtime/homelab-backup-audit-v2:299: lrc,lo,_=run(["git","ls-remote",fo.strip(),"refs/heads/"+BRANCH],30) +changes/CR-2026-1005/runtime/homelab-backup-audit-v2:300: if lrc==0 and lo.strip(): source["remote_head"]=lo.split()[0] +changes/CR-2026-1005/runtime/homelab-backup-audit-v2:301:if source["remote_head"]!=source["local_head"]: +changes/CR-2026-1005/runtime/homelab-backup-audit-v2:302: issues.append({"severity":"MEDIUM","code":"SOURCE_OFFHOST_MISSING","logical_id":"-","root_cause":"CR_BRANCH_SHA_NOT_EXACT"}) +changes/CR-2026-1005/runtime/homelab-backup-audit-v2:309: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'}") +changes/CR-2026-1005/runtime/homelab-backup-retention-gc:14:HEAVY_LOCK=/run/homelab-backup-heavy.lock +changes/CR-2026-1005/runtime/homelab-backup-retention-gc:424: exec 5>"$LOCK"; flock -n 5 || die GC_LOCK_BUSY 75 +changes/CR-2026-1005/runtime/homelab-backup-retention-gc:434: exec 5>"$LOCK"; flock -n 5 || { printf 'GC_SCHEDULED=SKIP|reason=GC_LOCK_BUSY\n'; return 0; } +changes/CR-2026-1005/runtime/homelab-backup-retention-gc:444: if ! acquire_gc_locks; then write_health "$p1" true 0; printf 'GC_SCHEDULED=SKIP|reason=BACKUP_LOCK_BUSY|candidates=%s|open_transactions=%s\n' "$count" "$open_tx"; return 0; fi +changes/CR-2026-1005/runtime/homelab-backup-v2-app-scheduled:6:HEAVY_LOCK=/run/homelab-backup-heavy.lock +changes/CR-2026-1005/runtime/homelab-backup-v2-app-scheduled:19:exec 9>"$QUEUE_LOCK"; if ! flock -n 9; then printf 'APP_V2_SCHEDULED=SKIP|reason=APP_QUEUE_LOCK_BUSY\n'; exit 0; fi +changes/CR-2026-1005/runtime/homelab-backup-v2-app-scheduled:20:exec 8>"$HEAVY_LOCK"; if ! flock -n 8; then printf 'APP_V2_SCHEDULED=SKIP|reason=GLOBAL_HEAVY_LOCK_BUSY\n'; exit 0; fi +tasks/backup-v2-health-alerting-remediation-v1/assets/baseline/homelab-backup-audit:159:flock -n 9 || die AUDIT_LOCK_BUSY 75 +tasks/backup-v2-health-alerting-remediation-v1/assets/baseline/homelab-backup-audit:422:for lock in /run/homelab-backup-heavy.lock /run/lock/homelab-vm-cloud-quorum-queue.lock /run/lock/homelab-app-cloud-quorum-queue.lock /run/lock/homelab-backup-dispatcher.lock; do +tasks/backup-v2-health-alerting-remediation-v1/assets/baseline/homelab-backup-retention-gc:14:HEAVY_LOCK=/run/homelab-backup-heavy.lock +tasks/backup-v2-health-alerting-remediation-v1/assets/baseline/homelab-backup-retention-gc:424: exec 5>"$LOCK"; flock -n 5 || die GC_LOCK_BUSY 75 +tasks/backup-v2-health-alerting-remediation-v1/assets/baseline/homelab-backup-retention-gc:434: exec 5>"$LOCK"; flock -n 5 || { printf 'GC_SCHEDULED=SKIP|reason=GC_LOCK_BUSY\n'; return 0; } +tasks/backup-v2-health-alerting-remediation-v1/assets/baseline/homelab-backup-retention-gc:444: if ! acquire_gc_locks; then write_health "$p1" true 0; printf 'GC_SCHEDULED=SKIP|reason=BACKUP_LOCK_BUSY|candidates=%s|open_transactions=%s\n' "$count" "$open_tx"; return 0; fi +tasks/snikket-vm150-rebuild-v2/assets/vm150-runtime.py:60:BACKUP_LOCKS=['/run/lock/homelab-backup-dispatcher.lock','/run/lock/homelab-vm-cloud-quorum-queue.lock','/run/homelab-backup-heavy.lock'] +tasks/snikket-vm150-rebuild-v2/assets/vm150-runtime.py:506: f.close(); die('LOCK_BUSY_'+pathlib.Path(q).name,75) +TASK_RESULT=PASS_BACKUP_ALERT_NOISE_ROOT_RCA_COLLECTED +DECISION=PASS_BACKUP_ALERT_NOISE_ROOT_RCA_COLLECTED +NEXT_GATE=READ_EXACT_1238_AND_APPLY_ONLY_PROVEN_ALERT_NOISE_FIX +HOMELAB_RESULT_CONTRACT={"version":1,"command_id":"SUPPORT-260928-HOMELAB-BACKUP-ALERT-NOISE-ROOT-RCA-1238R1","status":"OK","changes_made":false,"rollback_started":false,"rollback_restored":null} OUTPUT_END CHAT_OUTPUT_END