From 0732043d62f8b384cfbbba7a5c1f8ceb34311a2c Mon Sep 17 00:00:00 2001
From: DocTator <doc@filenotfound.org>
Date: Fri, 16 May 2025 17:00:01 -0400
Subject: [PATCH] Auto-commit from giteapush.sh at 2025-05-16 17:00:01

---
 documents/blog/minio.md                    |  77 ++++++++++++
 miscellaneous/bash/dasystemisdownyo.sh     | 130 +++++++++++++++++++++
 miscellaneous/bash/genesis_check.sh        |  24 ++++
 miscellaneous/bash/health.sh               | 107 -----------------
 miscellaneous/bash/krang_modular_health.sh | 112 ++++++++++++++++++
 miscellaneous/python/uptime_server.py      |  48 ++++++++
 6 files changed, 391 insertions(+), 107 deletions(-)
 create mode 100644 documents/blog/minio.md
 create mode 100755 miscellaneous/bash/dasystemisdownyo.sh
 create mode 100755 miscellaneous/bash/genesis_check.sh
 delete mode 100755 miscellaneous/bash/health.sh
 create mode 100755 miscellaneous/bash/krang_modular_health.sh
 create mode 100644 miscellaneous/python/uptime_server.py

diff --git a/documents/blog/minio.md b/documents/blog/minio.md
new file mode 100644
index 0000000..f9b8d58
--- /dev/null
+++ b/documents/blog/minio.md
@@ -0,0 +1,77 @@
+# MinIO: It Works, But It Hates You
+
+*By someone who survived a 150,000-file sync and lived to tell the tale.*
+
+---
+
+MinIO is fast. It's lightweight. It's compatible with Amazon S3. It’s everything you want in a self-hosted object storage system.
+
+Until you try to **use it like a filesystem**.
+
+Then it becomes the most temperamental, moody, selectively mute piece of software you've ever met.
+
+---
+
+## What I Was Trying to Do
+
+All I wanted was to migrate ~40GB of Mastodon media from local disk into a MinIO bucket. Nothing fancy. Just a clean `rclone sync` and a pat on the back.
+
+---
+
+## What Actually Happened
+
+- **Load average spiked to 33**
+- `find` froze
+- `rclone size` hung
+- `zfs snapshot` stalled so long I thought the server died
+- The MinIO **UI lied to my face** about how much data was present (5GB when `rclone` said 22GB)
+- Directory paths that looked like files. Files that were secretly directories. I saw `.meta` and `.part.1` in my dreams.
+
+---
+
+## The Root Problem
+
+MinIO is **not** a filesystem.
+
+It's a flat key-value object store that's just *pretending* to be a folder tree. And when you throw 150,000+ nested objects at it — especially from a tool like `rclone` — all the lies unravel.
+
+It keeps going, but only if:
+- You feed it one file at a time
+- You don’t ask it questions (`rclone ls`, `rclone size`, `find`, etc.)
+- You don’t use the UI expecting it to reflect reality
+
+---
+
+## The Fixes That Kept Me Sane
+
+- Switched from `rclone ls` to `rclone size` with `--json` (when it worked)
+- Cleaned up thousands of broken `.meta`/`.part.*` directories using a targeted script
+- Paused `rclone` mid-sync with `kill -STOP` to get snapshots to complete
+- Used `du -sh` instead of `find` to track usage
+- Lowered `rclone` concurrency with `--transfers=4 --checkers=4`
+- Drank water. A lot of it.
+
+---
+
+## The Moral of the Story
+
+If you're going to use MinIO for massive sync jobs, treat it like:
+
+- A **delicate black box** with fast internals but fragile mood
+- Something that **prefers to be written to, not inspected**
+- An S3 clone with boundary issues
+
+---
+
+## Final Thought
+
+MinIO *does* work. It's powerful. It’s fast. But it also absolutely hates being watched while it works.
+
+And you won't realize how much until you're 100,000 files deep, snapshot frozen, and `rclone` is telling you you're doing great — while the UI smirks and says you're at 5 gigs.
+
+MinIO: It works.  
+But it hates you.
+
+---
+
+**Filed under:** `disaster recovery`, `object storage`, `sync trauma`, `zfs`, `rclone`, `why me`
diff --git a/miscellaneous/bash/dasystemisdownyo.sh b/miscellaneous/bash/dasystemisdownyo.sh
new file mode 100755
index 0000000..c1ae1c9
--- /dev/null
+++ b/miscellaneous/bash/dasystemisdownyo.sh
@@ -0,0 +1,130 @@
+#!/bin/bash
+
+# === CONFIG ===
+REMOTE_USER="doc"
+BOT_TOKEN="8178867489:AAH0VjN7VnZSCIWasSz_y97iBLLjPJA751k"
+CHAT_ID="1559582356"
+TIMESTAMP=$(date '+%Y-%m-%d %H:%M:%S')
+LOGFILE="$HOME/krang-logs/health-$(date '+%Y%m%d-%H%M').log"
+
+SWAP_LIMIT_MB=512
+LOAD_LIMIT=4.0
+mkdir -p "$HOME/krang-logs"
+
+SERVERS=(
+  thevault.sshjunkie.com
+  zcluster.technodrome1.sshjunkie.com
+  zcluster.technodrome2.sshjunkie.com
+  shredder.sshjunkie.com
+  chatwithus.live
+  portal.genesishostingtechnologies.com
+)
+
+declare -A HOST_ROLES=(
+  [thevault]="backup zfs"
+  [zcluster.technodrome1]="postgres"
+  [zcluster.technodrome2]="postgres"
+  [shredder]="minio docker"
+  [chatwithus.live]="mastodon docker nginx"
+  [azuracast.sshjunkie.com]="azuracast docker nginx"
+)
+
+SUMMARY="📡 Krang System Health Report - $TIMESTAMP
+
+"
+
+for HOST in "${SERVERS[@]}"; do
+  SHORT_HOST=$(echo "$HOST" | cut -d'.' -f1)
+  echo "🔍 Collecting from $HOST..."
+
+  DATA=$(ssh "$REMOTE_USER@$HOST" bash -s << 'EOF'
+set -e
+HOST=$(hostname)
+MEM=$(awk '/MemAvailable/ {printf "%.1f Gi free", $2 / 1024 / 1024}' /proc/meminfo)
+SWAP_RAW=$(free -m | awk '/Swap:/ {print $3}')
+SWAP="$SWAP_RAW Mi used"
+DISK=$(df -h / | awk 'NR==2 {print $4 " free"}')
+LOAD=$(uptime | awk -F'load average:' '{print $2}' | cut -d, -f1 | xargs)
+UPTIME=$(uptime -p)
+
+# Graceful service status checks
+check_status() {
+  systemctl is-active "$1" 2>/dev/null || echo "inactive"
+}
+NGINX=$(check_status nginx)
+DOCKER=$(check_status docker)
+PGSQL=$(check_status postgresql)
+
+echo "$HOST|$MEM|$SWAP_RAW|$SWAP|$DISK|$LOAD|$UPTIME|$NGINX|$DOCKER|$PGSQL"
+EOF
+) || {
+  SUMMARY+="🖥️ $HOST
+❌ Failed to connect or run checks.
+"
+  continue
+}
+
+  IFS='|' read -r H MEM SWAP_MB SWAP_HUMAN DISK LOAD1 UPTIME_STATUS NGINX_STATUS DOCKER_STATUS PGSQL_STATUS <<< "$DATA"
+  ROLES="${HOST_ROLES[$SHORT_HOST]}"
+  ALERTS=""
+
+  if [[ -n "$SWAP_MB" && "$SWAP_MB" =~ ^[0-9]+$ && "$SWAP_MB" -gt "$SWAP_LIMIT_MB" ]]; then
+    ALERTS+="⚠️ HIGH SWAP ($SWAP_HUMAN)
+"
+  fi
+
+  if [[ -n "$LOAD1" ]]; then
+    LOAD_HIGH=$(awk "BEGIN {print ($LOAD1 > $LOAD_LIMIT) ? 1 : 0}")
+    [ "$LOAD_HIGH" -eq 1 ] && ALERTS+="⚠️ HIGH LOAD ($LOAD1)
+"
+  fi
+
+  [[ "$ROLES" == *"nginx"* && "$NGINX_STATUS" != "active" ]] && ALERTS+="❌ NGINX not running
+"
+  [[ "$ROLES" == *"docker"* && "$DOCKER_STATUS" != "active" ]] && ALERTS+="❌ Docker not running
+"
+  [[ "$ROLES" == *"postgres"* && "$PGSQL_STATUS" != "active" ]] && ALERTS+="❌ PostgreSQL not running
+"
+
+  ALERTS_MSG=""
+  [ -n "$ALERTS" ] && ALERTS_MSG="🚨 ALERTS:
+$ALERTS"
+
+  SUMMARY+="🖥️ $H
+• Mem: $MEM
+• Swap: $SWAP_HUMAN
+• Disk: $DISK
+• Load: ${LOAD1:-Unavailable}
+• Uptime: $UPTIME_STATUS
+• Roles: ${ROLES:-none}
+$ALERTS_MSG
+"
+done
+
+# === KRANG CLOCK ACCURACY CHECK ===
+NTP_RESULT=$(ntpdate -q time.google.com 2>&1)
+OFFSET=$(echo "$NTP_RESULT" | awk '/offset/ {print $10}')
+if [[ "$OFFSET" =~ ^-?[0-9.]+$ ]]; then
+  OFFSET_MS=$(awk "BEGIN {printf "%.0f", $OFFSET * 1000}")
+  if (( OFFSET_MS > 500 || OFFSET_MS < -500 )); then
+    CORRECTION=$(ntpdate -u time.google.com 2>&1)
+    SUMMARY+="🛠️ Auto-corrected Krang clock via ntpdate: $CORRECTION
+"
+    SUMMARY+="🕰️ Krang Clock Offset: ${OFFSET_MS}ms — ⚠️ OUT OF SYNC
+"
+  else
+    SUMMARY+="🕰️ Krang Clock Offset: ${OFFSET_MS}ms — ✅ SYNCHRONIZED
+"
+  fi
+else
+  SUMMARY+="🕰️ Krang Clock Check: ❌ FAILED to retrieve offset.
+"
+fi
+
+# Log to file
+echo -e "$SUMMARY" > "$LOGFILE"
+
+# Send to Telegram
+curl -s -X POST https://api.telegram.org/bot$BOT_TOKEN/sendMessage \
+     -d chat_id="$CHAT_ID" \
+     -d text="$SUMMARY"
diff --git a/miscellaneous/bash/genesis_check.sh b/miscellaneous/bash/genesis_check.sh
new file mode 100755
index 0000000..d1ab702
--- /dev/null
+++ b/miscellaneous/bash/genesis_check.sh
@@ -0,0 +1,24 @@
+#!/bin/bash
+mkdir -p /var/log/genesis_uptime
+
+declare -A services=(
+  [radio]="https://genesis-radio.net"
+  [mastodon]="https://chatwithus.live"
+  [minio]="https://console.sshjunkie.com"
+  [azura]="https://portal.genesishostingtechnologies.com"
+  [teamtalk]="http://tt.themediahub.org"
+  [directadmin]="https://da.genesishostingtechnologies.com"
+)
+
+timestamp=$(date -u +"%Y-%m-%dT%H:%M:%S")
+
+for service in "${!services[@]}"
+do
+  url=${services[$service]}
+  curl --head --silent --max-time 10 "$url" >/dev/null
+  if [ $? -eq 0 ]; then
+    echo "$timestamp,up" >> "/var/log/genesis_uptime/$service.log"
+  else
+    echo "$timestamp,down" >> "/var/log/genesis_uptime/$service.log"
+  fi
+done
diff --git a/miscellaneous/bash/health.sh b/miscellaneous/bash/health.sh
deleted file mode 100755
index 07efab7..0000000
--- a/miscellaneous/bash/health.sh
+++ /dev/null
@@ -1,107 +0,0 @@
-#!/bin/bash
-
-# List of servers (replace these with your actual server hostnames or IPs)
-servers=("thevault.sshjunkie.com" "zcluster.technodrome1.sshjunkie.com" "zcluster.technodrome2.sshjunkie.com" "shredder.sshjunkie.com" "root@chatwithus.live")  # Add as many servers as needed
-
-# Define log file
-log_file="/home/doc/system_health_report_$(date +%F).log"
-
-# Telegram Bot API Token and Chat ID
-BOT_TOKEN="8178867489:AAH0VjN7VnZSCIWasSz_y97iBLLjPJA751k"
-CHAT_ID="1559582356"
-TELEGRAM_API="https://api.telegram.org/bot$BOT_TOKEN/sendMessage"
-
-# Function to escape Markdown special characters
-escape_markdown() {
-    echo "$1" | sed 's/\([_*[]\)/\\\1/g'  # Escape _, *, [, and ]
-}
-
-# Function to send the report to Telegram
-send_to_telegram() {
-    local message=$1
-    local chunk_size=4096
-    local start=0
-    local end=$chunk_size
-
-    while [ ${#message} -gt $start ]; do
-        chunk="${message:$start:$chunk_size}"
-        curl -s -X POST $TELEGRAM_API \
-            -d chat_id=$CHAT_ID \
-            -d text="$chunk" \
-            -d parse_mode="Markdown"
-        start=$end
-        end=$((start + chunk_size))
-    done
-}
-
-# Function to run the checks on each server
-check_health() {
-    server=$1
-    server_report="=== Health Check for $server ===\n"
-
-    # Memory Usage (summary)
-    memory_output=$(ssh $server "free -h")
-    free_memory=$(echo "$memory_output" | awk 'NR==2 {print $4}')
-    if [[ "$free_memory" < "1.0Gi" ]]; then
-        server_report+="Memory: Low memory available! Only $free_memory free, consider adding more RAM.\n"
-    else
-        server_report+="Memory: Sufficient memory available ($free_memory free).\n"
-    fi
-
-    # Swap Usage (summary)
-    swap_output=$(ssh $server "swapon -s")
-    swap_used=$(echo "$swap_output" | awk '{if(NR>1) print $3}')
-    if [[ "$swap_used" > "1Gi" ]]; then
-        server_report+="Swap: High swap usage ($swap_used used). This may indicate memory pressure.\n"
-    else
-        server_report+="Swap: Minimal swap usage ($swap_used used).\n"
-    fi
-
-    # CPU Load (summary)
-    cpu_output=$(ssh $server "uptime")
-    load_avg=$(echo "$cpu_output" | awk '{print $10}' | sed 's/,//')
-    if (( $(echo "$load_avg > 2.0" | bc -l) )); then
-        server_report+="CPU Load: High load average ($load_avg). Check if any processes are consuming too much CPU.\n"
-    else
-        server_report+="CPU Load: Normal load average ($load_avg).\n"
-    fi
-
-    # Disk Space (summary)
-    disk_output=$(ssh $server "df -h")
-    disk_free=$(echo "$disk_output" | grep -v 'tmpfs' | grep -v 'Filesystem' | awk '{print $4}' | sed 's/[A-Za-z]*//g' | head -n 1)
-    if [[ "$disk_free" < "10G" ]]; then
-        server_report+="Disk Space: Low disk space! Only $disk_free free. Consider cleaning up or adding storage.\n"
-    else
-        server_report+="Disk Space: Sufficient disk space ($disk_free free).\n"
-    fi
-
-    # Service Check (example: check if Apache is running)
-    apache_status=$(ssh $server "systemctl is-active apache2")
-    if [[ "$apache_status" == "active" ]]; then
-        server_report+="Apache: Running normally.\n"
-    else
-        server_report+="Apache: Not running. Check service logs for issues.\n"
-    fi
-
-    # Additional Checks (summary: disk I/O, uptime)
-    iostat_output=$(ssh $server "iostat | head -n 2")  # Get summary of disk I/O
-    uptime_output=$(ssh $server "uptime")
-    server_report+="Disk I/O: $iostat_output\n"
-    server_report+="Uptime: $uptime_output\n"
-
-    # Escape Markdown special characters
-    escaped_report=$(escape_markdown "$server_report")
-
-    # Send the server-specific summary to Telegram
-    send_to_telegram "$escaped_report"
-
-    # Separator for readability in log file
-    echo -e "\n=====================\n" >> $log_file
-}
-
-# Main loop to go through each server
-for server in "${servers[@]}"; do
-    check_health $server
-done
-
-echo "Health check completed. Reports sent to Telegram and saved to $log_file."
diff --git a/miscellaneous/bash/krang_modular_health.sh b/miscellaneous/bash/krang_modular_health.sh
new file mode 100755
index 0000000..7b781e3
--- /dev/null
+++ b/miscellaneous/bash/krang_modular_health.sh
@@ -0,0 +1,112 @@
+#!/bin/bash
+
+# === CONFIG ===
+REMOTE_USER="doc"
+BOT_TOKEN="8178867489:AAH0VjN7VnZSCIWasSz_y97iBLLjPJA751k"
+CHAT_ID="1559582356"
+TIMESTAMP=$(date '+%Y-%m-%d %H:%M:%S')
+LOGFILE="$HOME/krang-logs/health-$(date '+%Y%m%d-%H%M').log"
+
+# Thresholds
+SWAP_LIMIT_MB=512
+LOAD_LIMIT=4.0
+
+mkdir -p "$HOME/krang-logs"
+
+SERVERS=(
+  thevault.sshjunkie.com
+  zcluster.technodrome1.sshjunkie.com
+  zcluster.technodrome2.sshjunkie.com
+  shredder.sshjunkie.com
+  chatwithus.live
+)
+
+SUMMARY="📡 Krang System Health Report - $TIMESTAMP
+
+"
+
+for HOST in "${SERVERS[@]}"; do
+  echo "🔍 Collecting from $HOST..."
+
+  DATA=$(ssh "$REMOTE_USER@$HOST" bash -s << 'EOF'
+HOST=$(hostname)
+MEM=$(awk '/MemAvailable/ {printf "%.1f Gi free", $2 / 1024 / 1024}' /proc/meminfo)
+SWAP_RAW=$(free -m | awk '/Swap:/ {print $3}')
+SWAP="$SWAP_RAW Mi used"
+DISK=$(df -h / | awk 'NR==2 {print $4 " free"}')
+LOAD=$(uptime | awk -F'load average:' '{print $2}' | cut -d, -f1 | xargs)
+UPTIME=$(uptime -p)
+
+# Optional service checks
+NGINX=$(systemctl is-active nginx 2>/dev/null)
+DOCKER=$(systemctl is-active docker 2>/dev/null)
+PGSQL=$(systemctl is-active postgresql 2>/dev/null || systemctl is-active postgresql@14-main 2>/dev/null)
+
+echo "$HOST|$MEM|$SWAP_RAW|$SWAP|$DISK|$LOAD|$UPTIME|$NGINX|$DOCKER|$PGSQL"
+EOF
+)
+
+  IFS='|' read -r H MEM SWAP_MB SWAP_HUMAN DISK LOAD1 UPTIME_STATUS NGINX_STATUS DOCKER_STATUS PGSQL_STATUS <<< "$DATA"
+
+  ALERTS=""
+  if (( SWAP_MB > SWAP_LIMIT_MB )); then
+    ALERTS+="⚠️ HIGH SWAP ($SWAP_HUMAN)
+"
+  fi
+
+  LOAD_INT=$(awk "BEGIN {print ($LOAD1 > $LOAD_LIMIT) ? 1 : 0}")
+  if [ "$LOAD_INT" -eq 1 ]; then
+    ALERTS+="⚠️ HIGH LOAD ($LOAD1)
+"
+  fi
+
+  [ "$NGINX_STATUS" != "active" ] && ALERTS+="❌ NGINX not running
+"
+  [ "$DOCKER_STATUS" != "active" ] && ALERTS+="❌ Docker not running
+"
+  [ "$PGSQL_STATUS" != "active" ] && ALERTS+="❌ PostgreSQL not running
+"
+
+  ALERTS_MSG=""
+  [ -n "$ALERTS" ] && ALERTS_MSG="🚨 ALERTS:
+$ALERTS"
+
+  SUMMARY+="🖥️ $H
+• Mem: $MEM
+• Swap: $SWAP_HUMAN
+• Disk: $DISK
+• Load: $LOAD1
+• Uptime: $UPTIME_STATUS
+$ALERTS_MSG
+"
+done
+
+# === KRANG CLOCK ACCURACY CHECK ===
+NTP_RESULT=$(ntpdate -q time.google.com 2>&1)
+OFFSET=$(echo "$NTP_RESULT" | awk '/offset/ {print $10}')
+OFFSET_MS=$(awk "BEGIN {printf "%.0f", $OFFSET * 1000}")
+
+if [[ -n "$OFFSET_MS" ]]; then
+  if (( OFFSET_MS > 500 || OFFSET_MS < -500 )); then
+    # Auto-correct the system clock
+    CORRECTION=$(ntpdate -u time.google.com 2>&1)
+    SUMMARY+="🛠️ Auto-corrected Krang clock via ntpdate: $CORRECTION
+"
+    SUMMARY+="🕰️ Krang Clock Offset: ${OFFSET_MS}ms — ⚠️ OUT OF SYNC
+"
+  else
+    SUMMARY+="🕰️ Krang Clock Offset: ${OFFSET_MS}ms — ✅ SYNCHRONIZED
+"
+  fi
+else
+  SUMMARY+="🕰️ Krang Clock Check: ❌ FAILED to retrieve offset.
+"
+fi
+
+# Log to file
+echo -e "$SUMMARY" > "$LOGFILE"
+
+# Send to Telegram
+curl -s -X POST https://api.telegram.org/bot$BOT_TOKEN/sendMessage \
+     -d chat_id="$CHAT_ID" \
+     -d text="$SUMMARY"
diff --git a/miscellaneous/python/uptime_server.py b/miscellaneous/python/uptime_server.py
new file mode 100644
index 0000000..e89acb3
--- /dev/null
+++ b/miscellaneous/python/uptime_server.py
@@ -0,0 +1,48 @@
+from flask import Flask, jsonify
+import os
+import json
+from datetime import datetime, timedelta
+
+app = Flask(__name__)
+
+LOG_DIR = "/var/log/genesis_uptime"
+CHECK_WINDOW_HOURS = 24
+
+SERVICES = {
+    "radio": "https://genesis-radio.net",
+    "mastodon": "https://chatwithus.live",
+    "minio": "https://console.sshjunkie.com",
+    "azura": "https://portal.genesishostingtechnologies.com",
+    "teamtalk": "http://tt.themediahub.org",
+    "directadmin": "https://da.genesishostingtechnologies.com"
+}
+
+@app.route("/api/uptime/<service>")
+def get_uptime(service):
+    log_path = os.path.join(LOG_DIR, f"{service}.log")
+    if not os.path.exists(log_path):
+        return jsonify({"uptime": "n/a"}), 404
+
+    now = datetime.utcnow()
+    window_start = now - timedelta(hours=CHECK_WINDOW_HOURS)
+
+    total = 0
+    up = 0
+
+    with open(log_path, "r") as f:
+        for line in f:
+            try:
+                timestamp_str, status = line.strip().split(",")
+                timestamp = datetime.strptime(timestamp_str, "%Y-%m-%dT%H:%M:%S")
+                if timestamp >= window_start:
+                    total += 1
+                    if status == "up":
+                        up += 1
+            except Exception:
+                continue
+
+    uptime_percent = round((up / total) * 100, 2) if total > 0 else 0.0
+    return jsonify({"uptime": uptime_percent})
+
+if __name__ == "__main__":
+    app.run(host="0.0.0.0", port=5000)