I am chronicling a thread of my life to improve my self-knowledge and improve my memory. This has a lot to do with computers.

Public school came easy for me and I failed to develop good study habits. I was good in math and science and enrolled in the School of Engineering at The Ohio State University. I scraped through Electrical Engineering, Mechanical Engineering, Industral Engineering before finishing in Computer Science.

In the late 1970’s, I finally found my passion – personal computing. I learned to progam in Basic on a DEC PDP11 at Tulsa Junior College. I learned how to use the Time Sharing Option (TSO) at Cities Service Oil Company. I got an Atari 800 and I could play games and write Basic programs at home. I was a single father and treasured early Saturday and Sunday mornings when it was just me and my Atari.

I used TSO far more than the stated restrictions and soon became the local expert. With no special privileges, I triggered a bug that deleted the VSAM master catalog that took down the IBM mainframe computer. This affected hundreds of active Cities Service workers and got me a visit to Systems Engineering to explain what I was doing when the system went down. It also got me a new job as Timesharing Coordinator. That started my journey through many versions of operating system software.

To be continued…

Cool Things I’m Doing with Alexa

1. Voice update of shopping list
2. “Alexa, good morning” to start my lights-on routine early
3. “Alexa, good night” to start my lights-off routine early
4. “Alexa, goodbye” to turn off the lights and start robovac
5. “Alexa, hello” to turn on the lights and send robovac home
6. Announce when washer or dryer is done
7. Turn on humidifier when humidity is low
8. Turn on diffuser as part of “good morning”
9. Turn off diffuser after two hours
10. Announce when the garage door opens
11. Set lights to low, medium or maximum brightness
12. Turn yard light on at sunset and off at sunrise
13. Announce “hello” at sunset and sunrise
14. My garage door closes after two hours

Yes, you can absolutely use a 256GB and two 512GB devices for Ceph storage in your Proxmox cluster — but there are a few things to consider for performance and redundancy! Let’s break this down.

✅ Ceph doesn’t require identical drives:

• Ceph treats each device as an OSD (Object Storage Daemon), and the cluster will balance data across them.
• Mixed drive sizes are fine, but Ceph’s performance and usable capacity will be influenced by the smallest drive and overall distribution.

⚠️ Capacity imbalance:

• Since Ceph tries to evenly distribute objects across all OSDs, the smaller 256GB drive will fill up faster than the two 512GB drives.
• Once the 256GB device reaches capacity, Ceph won’t be able to place new data on it, even if the larger drives have space — this could cause cluster warnings or degraded performance.

⭐️ Workarounds:

1. Weighting OSDs:
   • In Ceph, you can set the weight of each OSD to reflect its capacity — this helps the cluster balance data more intelligently.
   • Example: Assign a weight of 1.0 to the 512GB drives and 0.5 to the 256GB drive.
2. Separate pools:
   • If performance or balance becomes a concern, you could create different storage pools — one for the 256GB drive and another for the 512GB drives — though this adds complexity.

✨ Redundancy and performance:

• Ceph replication or erasure coding will still work, but keep in mind that losing the smaller drive would affect the cluster more quickly since it’s likely to fill up first.
• If you’re running 3-replica redundancy, the cluster will ensure data is distributed across all three nodes, even with mismatched drive sizes.

👉 Bottom line: It’ll work fine, but adjusting the OSD weights in Proxmox (via the Ceph GUI or CLI) would help avoid issues. I can walk you through setting that up if you’d like! 🚀

Let’s get your Ceph OSD weights adjusted! I’ll break this down step-by-step.

✅ Step 1: Check current OSDs and weights

1. Open Proxmox Web GUI.
2. Navigate to Datacenter → Ceph → OSD.
3. Here, you should see your three OSDs (one for each drive). Take note of their IDs.

👉 Alternatively, from the Proxmox shell:

ceph osd tree

This shows the OSDs, their weights, and which nodes they’re on.

✅ Step 2: Set the OSD weights

The goal:

• Set the two 512GB devices to a weight of 1.0.
• Set the 256GB device to a weight of 0.5 (reflecting its smaller capacity).

👉 From the Proxmox shell on any node:

ceph osd crush reweight osd.<ID_of_256GB_drive> 0.5
ceph osd crush reweight osd.<ID_of_512GB_drive_1> 1.0
ceph osd crush reweight osd.<ID_of_512GB_drive_2> 1.0

✅ To confirm the changes:

ceph osd tree

You should now see the updated weights.

✅ Step 3: Monitor Ceph health

1. Check the Ceph health status:

ceph health

2. Make sure there are no warnings like “near full OSD” or “backfilling issues.” Ceph should automatically rebalance the data across your drives based on the new weights.

✅ Step 4: Automate monitoring (optional)

Since the 256GB drive could still fill up faster, you might want to set up Proxmox alerts to notify you if the drive is getting close to full.

👉 Check OSD utilization:

ceph osd df

⭐ Why this works:

• Ceph uses the CRUSH algorithm to distribute data — weights help guide how much data each OSD should hold relative to the others.
• By lowering the weight on the 256GB OSD, you’re telling Ceph to store less data there, preventing it from filling up before the larger drives.

🚀 Need help fine-tuning Ceph pools, redundancy, or troubleshooting warnings? Let me know how the rebalancing goes!

Let’s create a simple automation to switch between performance and powersave modes on your Proxmox servers based on the time of day! Here’s how you can set it up:

✅ Step 1: Install cpufrequtils

First, ensure you have cpufrequtils installed on each Proxmox node:

sudo apt update
sudo apt install cpufrequtils

✅ Step 2: Create the scripts

✨ Script 1: Set performance mode (for daytime)

sudo nano /usr/local/bin/cpu_performance.sh

Add this:

#!/bin/bash
bash -c 'for((i=0;i<$(nproc);i++)); do cpufreq-set -c $i -g performance; done'

Save and exit.

✨ Script 2: Set powersave mode (for nighttime)

sudo nano /usr/local/bin/cpu_powersave.sh

Add this:

#!/bin/bash
bash -c 'for((i=0;i<$(nproc);i++)); do cpufreq-set -c $i -g powersave; done'

✅ Step 3: Make scripts executable

sudo chmod +x /usr/local/bin/cpu_performance.sh
sudo chmod +x /usr/local/bin/cpu_powersave.sh

✅ Step 4: Add cron jobs

Edit your crontab:

sudo crontab -e

Add these lines (adjust times as needed):

0 8 * * * /usr/local/bin/cpu_performance.sh  # Set to performance at 8 AM
0 22 * * * /usr/local/bin/cpu_powersave.sh    # Set to powersave at 10 PM

✅ Step 5: Verify

Check the CPU governor:

cat /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor

This setup keeps your servers snappy when you’re using them and more power-efficient overnight! Let me know if you’d like to fine-tune it further—maybe add logging or a health check? 🚀

You can use rsync with the --delete option to synchronize two drives and remove any extra files from the target drive that aren’t on the source drive! Let’s break it down.

✅ Basic command:

rsync -av --delete /path/to/source/ /path/to/target/

✨ Explanation:

• -a (archive): Preserves symbolic links, file permissions, modification times, and more.
• -v (verbose): Shows what’s happening during the sync.
• --delete: Removes files from the target that no longer exist in the source.
  • Important: Use with care—this option deletes extra files on the target!

✅ Dry run (recommended before running for real):

rsync -av --delete --dry-run /path/to/source/ /path/to/target/

This shows what would happen without making any changes.

✅ Excluding files:
If you want to avoid deleting certain files on the target:

rsync -av --delete --exclude='folder_or_file_to_keep' /path/to/source/ /path/to/target/

✅ Logging the sync:

rsync -av --delete /path/to/source/ /path/to/target/ --log-file=/path/to/rsync.log

✅ Automating with a cron job:
Edit your crontab with crontab -e and add:

0 2 * * * rsync -a --delete /path/to/source/ /path/to/target/

This runs the sync daily at 2 AM.

Would you like to fine-tune it, like setting up email notifications if the sync fails? I can help with that too! 🚀

Some of the best Proxmox videos are a series provided by Jay LaCroix on the Learn Linux TV YouTube channel. I followed along with the videos on my own Proxmox server. There was so much good information that rather than take notes, I decided to work through the entire series then repeat while taking notes.

Virtual Machines (VMs)

When defining VM, discard (for ssd) and qemu agent should be checked
use scsi hard disk for Windows
cloud-init

sudo apt install qemu-guest-agent
sudo systemctl start qemu-guest-agent
sudo systemctl status qemu-guest-agent
sudo systemctl enable qemu-guest-agent

sudo systemctl s qemu-guest-agent

Windows VMs

For disk, use SCSI bus and cache write back and discard for ssd

Templates

When creating a template there needs to be some tidying up:

sudo apt clean
sudo apt autoremove
sudo rm /etc/ssh/ssh_host_*
sudo truncate -s 0 /etc/machine-id
verify that: /var/lib/dbus/machine-id -> /etc/machine-id
sudo apt install cloud-init
sudo poweroff
add Cloud-Init drive to template hardware
edit cloud-init to add user, password and SSH public key

clone CT template with Mode: Full Clone
cloud-init not available for containers
sudo dpkg-reconfigure openssh-server
change /etc/hosts
change /etc/hostname

Containers

Proxmox uses linux containers or LXCs (lex-see)

The user created in a container is root so you need to add your own user:

adduser lynn
usermod -aG sudo lynn

One limitation of containers is that live migration is not supported. The container must be stopped before migrating it to a different node.

Firewall

Todo

Command Line

qm list
qm start 101
qm stop 101
qm reboot 101
qm reset 101 (last resort)
qm stop 101 (last resort)

Ubuntu Server Template Checklist

install nano
install up.sh