Editing Openai/690f5a8f-e6b0-800f-9707-b301528ae1f3 (section)

==  ==

{| class="wikitable"
|-
! 
! 
|-
| 
| 
|-
| 
| 
|-
| 
| 
|-
| 
| 
|-
| 
| 
|}

Would you like me to show a sample /etc/fstab entry for this setup, so it auto-mounts correctly on boot?


'''Prompt:'''
When you create a folder to a mergerfs volume, doesn't it automatically generate that same folder on all drives?

'''ChatGPT:'''
Excellent observation — and this is where MergerFS behavior can be unintuitive if you haven’t dug into how it handles new directories.

The short answer is:

<blockquote></blockquote>

It only creates the folder on one underlying drive, according to the create policy you’ve set.

Let’s break this down clearly:

===  ===

When you do something like:

<syntaxhighlight lang="bash">
mkdir /mnt/pool/NVR

</syntaxhighlight>

MergerFS decides which drive gets the real /NVR folder based on your category.create policy.

So for example:

* With category.create=eplfs (existing path, least free space): * It looks for drives that already have the parent path (in this case /mnt/diskX/) * Among those, it picks the one with the least free space (i.e. the fullest) * It creates /mnt/diskX/NVR only on that drive

No other disks get the folder until something explicitly creates it there later.

===  ===

If /NVR exists on multiple drives already (e.g. /mnt/disk1/NVR, /mnt/disk2/NVR, /mnt/disk3/NVR), then:

* MergerFS will see all those paths as “existing”.
* When writing to /mnt/pool/NVR/..., it must check all drives to find where it can place files — and that can spin up all drives.

So you want to avoid that situation for your power-saving goal.

===  ===

# Make sure only the first drive has the folder initially: <syntaxhighlight lang="bash"> mkdir /mnt/disk1/NVR </syntaxhighlight> (Don’t create /NVR on the others yet.)
# Mount MergerFS with: <syntaxhighlight lang="bash"> mergerfs /mnt/disk* /mnt/pool -o defaults,use_ino,category.create=eplfs,moveonenospc=true,cache.files=off,dropcacheonclose=true </syntaxhighlight>
# Now when Reolink writes to /mnt/pool/NVR, it’ll create and fill files only on /mnt/disk1/NVR.
# When disk1 fills up: <syntaxhighlight lang="bash"> mkdir /mnt/disk2/NVR </syntaxhighlight> Then MergerFS starts writing new files there.
# disk1 can now spin down completely.

===  ===

Imagine 3 disks:

<pre>
/mnt/disk1/
/mnt/disk2/
/mnt/disk3/

</pre>

Mount:

<syntaxhighlight lang="bash">
mergerfs /mnt/disk* /mnt/pool -o category.create=eplfs

</syntaxhighlight>

Then run:

<syntaxhighlight lang="bash">
mkdir /mnt/pool/NVR

</syntaxhighlight>

Check each:

<syntaxhighlight lang="bash">
ls /mnt/disk*/NVR

</syntaxhighlight>

You’ll see:

<pre>
/mnt/disk1/NVR
ls: cannot access '/mnt/disk2/NVR': No such file or directory
ls: cannot access '/mnt/disk3/NVR': No such file or directory

</pre>

So only one got created.

===  ===

{| class="wikitable"
|-
! 
! 
|-
| 
| 
|-
| 
| 
|-
| 
| 
|}

Would you like me to show a script that automatically creates <code>/NVR</code> on the next drive once the current one is full (so you never have to do it manually)?


'''Prompt:'''
yes please show that script

'''ChatGPT:'''
Perfect 👍 — here’s a simple, reliable script that automatically creates the /NVR folder on the next drive only when the current drive is nearly full.
This keeps your MergerFS pool running smoothly and allows older drives to sleep.