Skip to content
View in the app

A better way to browse. Learn more.

Unraid

A full-screen app on your home screen with push notifications, badges and more.

To install this app on iOS and iPadOS
  1. Tap the Share icon in Safari
  2. Scroll the menu and tap Add to Home Screen.
  3. Tap Add in the top-right corner.
To install this app on Android
  1. Tap the 3-dot menu (⋮) in the top-right corner of the browser.
  2. Tap Add to Home screen or Install app.
  3. Confirm by tapping Install.

SMB Windows 7 Performance Results

Featured Replies

Per my other thread I promised running some benchmarks without, and with, an SSD cache drive. I'm running unRaid 6.3.5 on a SuperMicro server motherboard with 32GB of ECC RAM and a 4th Gen Intel quad core Xeon E3-1230L (25 watt TDP). The disk controller is an LSI 9211-8i. The drives are WD-REDs (5400rpm) including the single parity drive. The Tunable md_write_method was set to auto and all other disk settings were also the defaults.

 

The short answer: Even without a cache drive, or "turbo write" enabled, transfers run at close to gigabit ethernet speeds for anything that will fit in RAM.

 

An 11GB file from Windows 7 to an SMB unRaid share averaged about 100 MB/sec but may have been entirely cached in unRaid's RAM. The raw internal drive speed (i.e. running a Preclean) is about the same at around 100 MB/sec.

 

A 48 GB file, too large to fit in unRaid's RAM, still averaged about 81 MB/sec. Adding a sufficiently large SSD restored the speed closer to 100 MB/sec for the same file.

 

For me the 20% benefit of the cache drive, which only applies to very large files that can't be cached in RAM, isn't worth the potential data loss and other downsides of using a cache drive for the array. I also don't want to use turbo writes as the entire array (6+ drives) must be spun up for every write.

 

It might be with a few dockers/VMs running, less RAM available, multiple sources of disk I/O, etc. the non-cache performance would significantly drop while a cached array would probably still maintain more of its performance. But I'm not that far along to do that sort of testing yet. And dockers and VMs can use the cache drive to help the array maintain maximum performance. On lower power hardware, with much less RAM, the benefits of caching would likely also be higher. Likewise with a bonded or 10Gbit connection, and multiple workstations hitting the server, you also would likely gain more from caching. The good news is you can set up unRaid in a "production" environment and, if write performance does become a real-world issue, you can always add array caching later.

 

I have not tried writing a file larger than the cache drive as I'm convinced, at least for now, I don't need to cache the array. But I suspect, as someone mentioned in the other thread, it will fill the cache drive and return an error (hopefully failing gracefully).

 

So, performance wise, I'm pleased with unRaid. The parity overhead doesn't seem to be especially burdensome.

 

unraid final 48gb copy.jpg

Edited by dev_guy

And what is the problem/question/purpose now?

Edited by Zonediver

congrats mate. I suggest thread [closed]  9_9

Archived

This topic is now archived and is closed to further replies.

Account

Navigation

Search

Search

Configure browser push notifications

Chrome (Android)
  1. Tap the lock icon next to the address bar.
  2. Tap Permissions → Notifications.
  3. Adjust your preference.
Chrome (Desktop)
  1. Click the padlock icon in the address bar.
  2. Select Site settings.
  3. Find Notifications and adjust your preference.