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.

[Solved] Extremely slow writes/reads, possibly after parity swap

Featured Replies

Greetings!

I have been experiencing extremely slow writes and reads from my unRAID system, I believe after completing a parity swap. I had to replace a failing data disk, and in the process moved to a larger parity drive (from 2TB to 3TB). Ever since, it seems that when a file is being written to the array, write speeds are slow, and reads are also affected (i.e. playing videos via Kodi results in pausing and stopping).

 

As of this morning, a mover job has been trying to move approximately 80GB from cache to the array. From looking at the syslog, it looks like some writes take a few minutes, while others take 30+ minutes, for files that should be similar in size.

 

I've attached a diagnostics archive from early this morning.

 

I am running unRAID 6.1.4.

 

Any help is appreciated. I cannot figure out anything other than the array writes being the issue, but no obvious cause.

 

Thanks,

Dave

 

UPDATE:

The parity drive ended up being a shucked WD Green sold as new by a 3rd-party Amazon seller. After replacing it with a new drive, I have not experienced any more issues. Thanks johnnie.black for the support!

tower-diagnostics-20161129-0514.zip

  • Community Expert

There was a kernel oops, you should reboot and see if performance goes back to normal.

 

Hopefully this was a one time thing but if it happens again you'll need to investigate it further.

  • Author

I'll go for a reboot tonight, now that a pre-clear is complete.

Thanks,

Dave

  • Author

I rebooted the server this morning, and was able to replicate the issues again. I copied a ~700MB file from my cache drive to the array, which took approximately 30 minutes. I did this on the server, with mc, so this is not a network issue. During this copy, I had a video playing on a remote Kodi system, which again suffered from stuttering and buffering.

 

I'm attaching logs from during and after the transfer, in case they may show something between the two.

 

Thanks!

Dave

tower-diagnostics-20161201-1150_AfterXfer.zip

tower-diagnostics-20161201-1126_DuringXfer.zip

  • Community Expert

I'm not seeing anything out of the ordinary, did you try copying to a different disk? Is the parity check speed normal?

 

P.S.: you do have a disk with a pending sector, not related to this issue but worth checking.

 

Device Model:     WDC WD20EZRX-00D8PB0
Serial Number:    WD-WCC4MPTAE2H7

  5 Reallocated_Sector_Ct   0x0033   200   200   140    Pre-fail  Always       -       1
196 Reallocated_Event_Count 0x0032   199   199   000    Old_age   Always       -       1
197 Current_Pending_Sector  0x0032   200   200   000    Old_age   Always       -       1

  • Author

Thanks for the reply.

 

For the copies, I'm going from a directory in /mnt/cache to a directory in /mnt/user. Would it be wise to try to copy direct to each disk (/mnt/diskN)?

 

I will kick off a parity check. To be honest, I can't recall what "normal" speed would be for my system, so I can report back with the results.

 

Thanks for the note on the drive. I have a precleared drive ready to go.

 

Dave

  • Community Expert

For the copies, I'm going from a directory in /mnt/cache to a directory in /mnt/user. Would it be wise to try to copy direct to each disk (/mnt/diskN)?

 

Yes, try 2 different disks using /mnt/diskX

  • Author

Interestingly, now that I have done a parity check, I cannot recreate the issue. I've tried copying files to all disks discretely, as well as to the  array, and I am not seeing the issue.

 

I will test some more tomorrow.

 

Thanks for all the help.

Dave

  • Author

This morning I discovered that my parity drive is now showing 31,000+ errors in the Main WebUI. So, my uneducated guess is my new parity drive may be failing/failed?

 

I found my syslog is full of:

Tower kernel: md: disk0 read error, sector=3641072456

 

Oh, and I now see SMART for the disk shows:

197	Current pending sector	0x0032	200	200	000	Old age	Always	-	26
198	Offline uncorrectable	0x0030	200	200	000	Old age	Offline	-	26

 

Can I just get a confirmation that all I need to do is remove and replace the parity drive, and the rebuild will be automatic? I have a pre-cleared drive ready to go already. Is this just a matter of changing the drive assignment through the WebUI?

 

Thanks,

Dave

tower-diagnostics-20161203-0909.zip

  • Community Expert

Can I just get a confirmation that all I need to do is remove and replace the parity drive, and the rebuild will be automatic? I have a pre-cleared drive ready to go already. Is this just a matter of changing the drive assignment through the WebUI?

 

Yes.

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.