unraid-tunables-tester.sh - A New Utility to Optimize unRAID md_* Tunables

[hellboy]

Hey Hellboy,

 

I'm not sure, but probably it is safe.

 

Primarily the tester is just running a parity check from the command line, so that should be safe regardless of what version is running.

 

The memory parameters that are being adjusted between runs simply affect how much memory is allocated to the process, and should be okay to tweak unless Tom has made changes to these tunables.  In fact, with v6 being 64 bit, you may be able to push these numbers much higher than ever before.  Worst case, you're still just running a non-correcting parity check, so if something happens your data shouldn't be modified. 

 

All that said, let me be clear, I am still on v5.  I only have my one production box, and I don't run beta software on it.  I have not tested this tool on v6.anything, though I think other users in here have done so.

 

And since you are asking if this is safe to run on 6b10a, my gut is telling me you are running beta on a production box with data you actually care about, something I don't advise, and in that case I really wouldn't advise running this tool either.

 

If you end up running it, be sure to share your results!

 

-Paul

 

I will let you know

 

Thanks..//

[jbartlett]

It's fine to run in 64bit UNRAID

[hellboy]

Hey Hellboy,

 

I'm not sure, but probably it is safe.

 

Primarily the tester is just running a parity check from the command line, so that should be safe regardless of what version is running.

 

The memory parameters that are being adjusted between runs simply affect how much memory is allocated to the process, and should be okay to tweak unless Tom has made changes to these tunables.  In fact, with v6 being 64 bit, you may be able to push these numbers much higher than ever before.  Worst case, you're still just running a non-correcting parity check, so if something happens your data shouldn't be modified. 

 

All that said, let me be clear, I am still on v5.  I only have my one production box, and I don't run beta software on it.  I have not tested this tool on v6.anything, though I think other users in here have done so.

 

And since you are asking if this is safe to run on 6b10a, my gut is telling me you are running beta on a production box with data you actually care about, something I don't advise, and in that case I really wouldn't advise running this tool either.

 

If you end up running it, be sure to share your results!

 

-Paul

 

Ok...

This what i got......

TunablesReport1.txt

[GHunter]

Will their be a new version of this script now that unraid 6 beta 7 dropped md_write_limit?

 

Interesting!  I had no idea that this had been changed.  I'm not sure of the impact.  I haven't played with the 6.0 beta yet, and never will as all I have is a production server.  I might do a 6.0 release candidate, but will probably wait until final. 

 

-Paul

 

Here is what I have found when using it with unRAID 6b10a. The script seems to work just fine. The disk settings only have md_num_stripes and md_sync_window as available options to change. In the disk.cfg file on your flash drive, there is still an md_write_limit value and it's default is 768. Changing the 2 available options seems to have no effect on the md_write_limit as it still has a value of 768, even if I choose really high values for md_num_stripes and md_sync_window.

 

If you upgraded from unRAID v5 and had used custom values like I did, those values are retained in the upgrade to unRAID v6. However, changing the values in the webGUI will reset the md_write_limit back to it's default value of 768. Also, the default values for all 3 of these settings in v6 are still the same as they were in v5.

 

There does seem to be a difference in the values for unRAID v5 vs. v6 so if you are running the v6 beta, I would use the script to re-calculate better values for unRAID v6.

 

Gary

[bondoo0]

One word of caution for using the script on unraid 6 with VM's.  I ran into issues where the script ran fine, but when a parity check kicked off, it would cause unraid to freeze (looked like a kernel panic, that others were able to resolve by pinning CPU's to dom0, but that didn't help in my case).  As soon as I went back to the default values the problem went away, so I'm guessing something was just pushed too far, and the machine ran out of resources during parity checks.

[brettm357]

Ran tunables and here are the results - what is the best setting I should use both best bang for buck and unthrottled seem to have same speed

TunablesReport.txt

[qtwre]

I'd like to bump this thread and say thanks so much!

 

I've been using unRaid for a few years now having never played with those settings. My baseline with your script at the default settings (for some reason my md_sync_window is actually 288, lower than what your script says is default) was 40MB/s. After testing it's up to 99MB/s. This is while running a preclear on two drives.

 

That's an amazing improvement! I can't believe I was making due with less than half my possible speed.

[interwebtech]

I applied the Best Bang for the Buck settings. I am appalled at my disk speeds tho.

 

Tunables Report from  unRAID Tunables Tester v2.2 by Pauven

NOTE: Use the smallest set of values that produce good results. Larger values
      increase server memory use, and may cause stability issues with unRAID,
      especially if you have any add-ons or plug-ins installed.

Test | num_stripes | write_limit | sync_window |   Speed 
--- FULLY AUTOMATIC TEST PASS 1 (Rough - 20 Sample Points @ 3min Duration)---
   1  |    1408     |     768     |     512     |  65.8 MB/s 
   2  |    1536     |     768     |     640     |  66.6 MB/s 
   3  |    1664     |     768     |     768     |  66.8 MB/s 
   4  |    1920     |     896     |     896     |  66.9 MB/s 
   5  |    2176     |    1024     |    1024     |  67.2 MB/s 
   6  |    2560     |    1152     |    1152     |  67.8 MB/s 
   7  |    2816     |    1280     |    1280     |  68.8 MB/s 
   8  |    3072     |    1408     |    1408     |  69.0 MB/s 
   9  |    3328     |    1536     |    1536     |  68.5 MB/s 
  10  |    3584     |    1664     |    1664     |  69.1 MB/s 
  11  |    3968     |    1792     |    1792     |  68.9 MB/s 
  12  |    4224     |    1920     |    1920     |  69.1 MB/s 
  13  |    4480     |    2048     |    2048     |  69.0 MB/s 
  14  |    4736     |    2176     |    2176     |  69.1 MB/s 
  15  |    5120     |    2304     |    2304     |  69.0 MB/s 
  16  |    5376     |    2432     |    2432     |  68.6 MB/s 
  17  |    5632     |    2560     |    2560     |  68.9 MB/s 
  18  |    5888     |    2688     |    2688     |  69.3 MB/s 
  19  |    6144     |    2816     |    2816     |  69.4 MB/s 
  20  |    6528     |    2944     |    2944     |  69.0 MB/s 
--- Targeting Fastest Result of md_sync_window 2816 bytes for Final Pass ---
--- FULLY AUTOMATIC TEST PASS 2 (Final - 16 Sample Points @ 4min Duration)---
  21  |    5984     |    2696     |    2696     |  69.0 MB/s 
  22  |    6008     |    2704     |    2704     |  69.0 MB/s 
  23  |    6024     |    2712     |    2712     |  69.3 MB/s 
  24  |    6040     |    2720     |    2720     |  69.0 MB/s 
  25  |    6056     |    2728     |    2728     |  69.0 MB/s 
  26  |    6080     |    2736     |    2736     |  68.9 MB/s 
  27  |    6096     |    2744     |    2744     |  69.1 MB/s 
  28  |    6112     |    2752     |    2752     |  69.0 MB/s 
  29  |    6128     |    2760     |    2760     |  69.2 MB/s 
  30  |    6144     |    2768     |    2768     |  68.6 MB/s 
  31  |    6168     |    2776     |    2776     |  69.1 MB/s 
  32  |    6184     |    2784     |    2784     |  69.1 MB/s 
  33  |    6200     |    2792     |    2792     |  68.8 MB/s 
  34  |    6216     |    2800     |    2800     |  68.8 MB/s 
  35  |    6240     |    2808     |    2808     |  69.3 MB/s 
  36  |    6256     |    2816     |    2816     |  68.9 MB/s 

Completed: 2 Hrs 14 Min 4 Sec.

Best Bang for the Buck: Test 2 with a speed of 66.6 MB/s

     Tunable (md_num_stripes): 1536
     Tunable (md_write_limit): 768
     Tunable (md_sync_window): 640

These settings will consume 78MB of RAM on your hardware.


Unthrottled values for your server came from Test 23 with a speed of 69.3 MB/s

     Tunable (md_num_stripes): 6024
     Tunable (md_write_limit): 2712
     Tunable (md_sync_window): 2712

These settings will consume 305MB of RAM on your hardware.
This is 240MB more than your current utilization of 65MB.
NOTE: Adding additional drives will increase memory consumption.

In unRAID, go to Settings > Disk Settings to set your chosen parameter values.

[dalben]

Is this script still valid for the 64bit beta versions of unRAID?

[Squid]

Is this script still valid for the 64bit beta versions of unRAID?

Yes

[Owel]

Hi, I'm on v6b14

have two Dockers and two VMs running.

 

Is it safe to run this script while these Application are running?

[itimpi]

Hi, I'm on v6b14

have two Dockers and two VMs running.

 

Is it safe to run this script while these Application are running?

Whether it is safe or not I do not see the point!    You want to run it on a system that is not running anything else as otherwise the results are likely to be inconclusive.  Therefore the dockers and VM's should really be stopped when running the script.

[dlandon]

Hi, I'm on v6b14

have two Dockers and two VMs running.

 

Is it safe to run this script while these Application are running?

 

All the script does is to set some parameters that affect a parity check and then start and stop a parity check.  It's no different than running a parity check while Dockers and VMs are running.

 

EDIT:  You will get better results with Dockers and VMs stopped.

[Owel]

I ask, because it is unclear for me, if only this script is slowed down by my application.

or the parity check also?

 

I read of scary out of memory errors.

 

So my fear is, that when the script runs while everything else is stopped, it will come up with results , which will cause an error when the applications are running an parity starts ?!

 

Can someone confirm that this fear is pointless?

[jbartlett]

In theory, if your docker/VM's are running on your cache drive, it should not affect your parity check speeds.

[trurl]

In theory, if your docker/VM's are running on your cache drive, it should not affect your parity check speeds.

Unless those docker/VM's are actively accessing array drives during the parity check, which would not be uncommon. A Plex docker, for example, could be streaming a movie from an array drive while the parity check is running.

[Squid]

Just ran into a *possible* issue with running this script. 

 

If you set the tunables to be unthrottled, you may run into cpu stall issues (not 100% proven, but on my system I can repeat the issues at will by using unthrottled settings).  I've adjusted my settings to be around 5MB/s less than unthrottled and my stall issues went away

 

http://lime-technology.com/forum/index.php?topic=38469.0

Fixed as of beta 15

[interwebtech]

New (to me) ARC-1231ML RAID controller (JBOD mode) with nice performance bump over the AOC-SASLP-MV8 it replaced.

 

Tunables Report from  unRAID Tunables Tester v2.2 by Pauven

NOTE: Use the smallest set of values that produce good results. Larger values
      increase server memory use, and may cause stability issues with unRAID,
      especially if you have any add-ons or plug-ins installed.

Test | num_stripes | write_limit | sync_window |   Speed 
--- FULLY AUTOMATIC TEST PASS 1 (Rough - 20 Sample Points @ 3min Duration)---
   1  |    1408     |     768     |     512     |  98.8 MB/s 
   2  |    1536     |     768     |     640     |  93.9 MB/s 
   3  |    1664     |     768     |     768     |  75.1 MB/s 
   4  |    1920     |     896     |     896     |  72.6 MB/s 
   5  |    2176     |    1024     |    1024     |  73.0 MB/s 
   6  |    2560     |    1152     |    1152     |  72.9 MB/s 
   7  |    2816     |    1280     |    1280     |  72.9 MB/s 
   8  |    3072     |    1408     |    1408     |  74.2 MB/s 
   9  |    3328     |    1536     |    1536     |  73.3 MB/s 
  10  |    3584     |    1664     |    1664     |  72.6 MB/s 
  11  |    3968     |    1792     |    1792     |  73.6 MB/s 
  12  |    4224     |    1920     |    1920     |  72.6 MB/s 
  13  |    4480     |    2048     |    2048     |  72.8 MB/s 
  14  |    4736     |    2176     |    2176     |  71.6 MB/s 
  15  |    5120     |    2304     |    2304     |  73.0 MB/s 
  16  |    5376     |    2432     |    2432     |  71.7 MB/s 
  17  |    5632     |    2560     |    2560     |  73.0 MB/s 
  18  |    5888     |    2688     |    2688     |  74.3 MB/s 
  19  |    6144     |    2816     |    2816     |  73.1 MB/s 
  20  |    6528     |    2944     |    2944     |  71.6 MB/s 
--- Targeting Fastest Result of md_sync_window 512 bytes for Special Pass ---
--- FULLY AUTOMATIC TEST PASS 1b (Rough - 4 Sample Points @ 3min Duration)---
  21  |    896     |     768     |     128     |  57.0 MB/s 
  22  |    1024     |     768     |     256     |  74.0 MB/s 
  23  |    1280     |     768     |     384     |  85.5 MB/s 
  24  |    1408     |     768     |     512     |  90.5 MB/s 
--- Targeting Fastest Result of md_sync_window 512 bytes for Final Pass ---
--- FULLY AUTOMATIC TEST PASS 2 (Final - 16 Sample Points @ 4min Duration)---
  25  |    1288     |     768     |     392     |  86.1 MB/s 
  26  |    1296     |     768     |     400     |  85.6 MB/s 
  27  |    1304     |     768     |     408     |  86.6 MB/s 
  28  |    1312     |     768     |     416     |  87.1 MB/s 
  29  |    1320     |     768     |     424     |  87.5 MB/s 
  30  |    1328     |     768     |     432     |  88.3 MB/s 
  31  |    1336     |     768     |     440     |  88.3 MB/s 
  32  |    1344     |     768     |     448     |  88.6 MB/s 
  33  |    1360     |     768     |     456     |  88.8 MB/s 
  34  |    1368     |     768     |     464     |  89.2 MB/s 
  35  |    1376     |     768     |     472     |  89.4 MB/s 
  36  |    1384     |     768     |     480     |  89.4 MB/s 
  37  |    1392     |     768     |     488     |  90.2 MB/s 
  38  |    1400     |     768     |     496     |  89.9 MB/s 
  39  |    1408     |     768     |     504     |  90.7 MB/s 
  40  |    1416     |     768     |     512     |  90.9 MB/s 

Completed: 2 Hrs 24 Min 48 Sec.

Best Bang for the Buck: Test 1 with a speed of 98.8 MB/s

     Tunable (md_num_stripes): 1408
     Tunable (md_write_limit): 768
     Tunable (md_sync_window): 512

These settings will consume 71MB of RAM on your hardware.


Unthrottled values for your server came from Test 40 with a speed of 90.9 MB/s

     Tunable (md_num_stripes): 1416
     Tunable (md_write_limit): 768
     Tunable (md_sync_window): 512

These settings will consume 71MB of RAM on your hardware.
This is -7MB less than your current utilization of 78MB.
NOTE: Adding additional drives will increase memory consumption.

In unRAID, go to Settings > Disk Settings to set your chosen parameter values.

 

I applied the Best Bang for the Buck settings. I am appalled at my disk speeds tho.

 

Tunables Report from  unRAID Tunables Tester v2.2 by Pauven

NOTE: Use the smallest set of values that produce good results. Larger values
      increase server memory use, and may cause stability issues with unRAID,
      especially if you have any add-ons or plug-ins installed.

Test | num_stripes | write_limit | sync_window |   Speed 
--- FULLY AUTOMATIC TEST PASS 1 (Rough - 20 Sample Points @ 3min Duration)---
   1  |    1408     |     768     |     512     |  65.8 MB/s 
   2  |    1536     |     768     |     640     |  66.6 MB/s 
   3  |    1664     |     768     |     768     |  66.8 MB/s 
   4  |    1920     |     896     |     896     |  66.9 MB/s 
   5  |    2176     |    1024     |    1024     |  67.2 MB/s 
   6  |    2560     |    1152     |    1152     |  67.8 MB/s 
   7  |    2816     |    1280     |    1280     |  68.8 MB/s 
   8  |    3072     |    1408     |    1408     |  69.0 MB/s 
   9  |    3328     |    1536     |    1536     |  68.5 MB/s 
  10  |    3584     |    1664     |    1664     |  69.1 MB/s 
  11  |    3968     |    1792     |    1792     |  68.9 MB/s 
  12  |    4224     |    1920     |    1920     |  69.1 MB/s 
  13  |    4480     |    2048     |    2048     |  69.0 MB/s 
  14  |    4736     |    2176     |    2176     |  69.1 MB/s 
  15  |    5120     |    2304     |    2304     |  69.0 MB/s 
  16  |    5376     |    2432     |    2432     |  68.6 MB/s 
  17  |    5632     |    2560     |    2560     |  68.9 MB/s 
  18  |    5888     |    2688     |    2688     |  69.3 MB/s 
  19  |    6144     |    2816     |    2816     |  69.4 MB/s 
  20  |    6528     |    2944     |    2944     |  69.0 MB/s 
--- Targeting Fastest Result of md_sync_window 2816 bytes for Final Pass ---
--- FULLY AUTOMATIC TEST PASS 2 (Final - 16 Sample Points @ 4min Duration)---
  21  |    5984     |    2696     |    2696     |  69.0 MB/s 
  22  |    6008     |    2704     |    2704     |  69.0 MB/s 
  23  |    6024     |    2712     |    2712     |  69.3 MB/s 
  24  |    6040     |    2720     |    2720     |  69.0 MB/s 
  25  |    6056     |    2728     |    2728     |  69.0 MB/s 
  26  |    6080     |    2736     |    2736     |  68.9 MB/s 
  27  |    6096     |    2744     |    2744     |  69.1 MB/s 
  28  |    6112     |    2752     |    2752     |  69.0 MB/s 
  29  |    6128     |    2760     |    2760     |  69.2 MB/s 
  30  |    6144     |    2768     |    2768     |  68.6 MB/s 
  31  |    6168     |    2776     |    2776     |  69.1 MB/s 
  32  |    6184     |    2784     |    2784     |  69.1 MB/s 
  33  |    6200     |    2792     |    2792     |  68.8 MB/s 
  34  |    6216     |    2800     |    2800     |  68.8 MB/s 
  35  |    6240     |    2808     |    2808     |  69.3 MB/s 
  36  |    6256     |    2816     |    2816     |  68.9 MB/s 

Completed: 2 Hrs 14 Min 4 Sec.

Best Bang for the Buck: Test 2 with a speed of 66.6 MB/s

     Tunable (md_num_stripes): 1536
     Tunable (md_write_limit): 768
     Tunable (md_sync_window): 640

These settings will consume 78MB of RAM on your hardware.


Unthrottled values for your server came from Test 23 with a speed of 69.3 MB/s

     Tunable (md_num_stripes): 6024
     Tunable (md_write_limit): 2712
     Tunable (md_sync_window): 2712

These settings will consume 305MB of RAM on your hardware.
This is 240MB more than your current utilization of 65MB.
NOTE: Adding additional drives will increase memory consumption.

In unRAID, go to Settings > Disk Settings to set your chosen parameter values.

[mobias1313]

I used the unthrottled settings instead of the best bang for your buck. Is there any reason I should switch to the best bang for your buck? I have 12GB of RAM and only use MariaDB, Cache_Dirs, and APCUPSD. I am pretty sure I have more than enough RAM to swing the additional memory consumption. Opinions? Thoughts?

 

Tunables Report from  unRAID Tunables Tester v2.2 by Pauven

NOTE: Use the smallest set of values that produce good results. Larger values
      increase server memory use, and may cause stability issues with unRAID,
      especially if you have any add-ons or plug-ins installed.

Test | num_stripes | write_limit | sync_window |   Speed 
--- FULLY AUTOMATIC TEST PASS 1 (Rough - 20 Sample Points @ 3min Duration)---
   1  |    1408     |     768     |     512     | 120.8 MB/s 
   2  |    1536     |     768     |     640     | 121.4 MB/s 
   3  |    1664     |     768     |     768     | 121.3 MB/s 
   4  |    1920     |     896     |     896     | 121.6 MB/s 
   5  |    2176     |    1024     |    1024     | 121.8 MB/s 
   6  |    2560     |    1152     |    1152     | 121.9 MB/s 
   7  |    2816     |    1280     |    1280     | 121.9 MB/s 
   8  |    3072     |    1408     |    1408     | 122.1 MB/s 
   9  |    3328     |    1536     |    1536     | 122.1 MB/s 
  10  |    3584     |    1664     |    1664     | 122.1 MB/s 
  11  |    3968     |    1792     |    1792     | 122.2 MB/s 
  12  |    4224     |    1920     |    1920     | 122.1 MB/s 
  13  |    4480     |    2048     |    2048     | 122.1 MB/s 
  14  |    4736     |    2176     |    2176     | 122.2 MB/s 
  15  |    5120     |    2304     |    2304     | 122.1 MB/s 
  16  |    5376     |    2432     |    2432     | 122.1 MB/s 
  17  |    5632     |    2560     |    2560     | 122.2 MB/s 
  18  |    5888     |    2688     |    2688     | 122.0 MB/s 
  19  |    6144     |    2816     |    2816     | 122.2 MB/s 
  20  |    6528     |    2944     |    2944     | 122.1 MB/s 
--- Targeting Fastest Result of md_sync_window 1792 bytes for Final Pass ---
--- FULLY AUTOMATIC TEST PASS 2 (Final - 16 Sample Points @ 4min Duration)---
  21  |    3712     |    1672     |    1672     | 122.3 MB/s 
  22  |    3728     |    1680     |    1680     | 122.1 MB/s 
  23  |    3744     |    1688     |    1688     | 122.2 MB/s 
  24  |    3768     |    1696     |    1696     | 122.1 MB/s 
  25  |    3784     |    1704     |    1704     | 122.3 MB/s 
  26  |    3800     |    1712     |    1712     | 122.3 MB/s 
  27  |    3816     |    1720     |    1720     | 122.2 MB/s 
  28  |    3840     |    1728     |    1728     | 122.2 MB/s 
  29  |    3856     |    1736     |    1736     | 122.2 MB/s 
  30  |    3872     |    1744     |    1744     | 122.2 MB/s 
  31  |    3888     |    1752     |    1752     | 122.3 MB/s 
  32  |    3904     |    1760     |    1760     | 122.3 MB/s 
  33  |    3928     |    1768     |    1768     | 122.2 MB/s 
  34  |    3944     |    1776     |    1776     | 122.1 MB/s 
  35  |    3960     |    1784     |    1784     | 122.2 MB/s 
  36  |    3976     |    1792     |    1792     | 122.3 MB/s 

Completed: 2 Hrs 7 Min 25 Sec.

Best Bang for the Buck: Test 1 with a speed of 120.8 MB/s

     Tunable (md_num_stripes): 1408
     Tunable (md_write_limit): 768
     Tunable (md_sync_window): 512

These settings will consume 77MB of RAM on your hardware.


Unthrottled values for your server came from Test 21 with a speed of 122.3 MB/s

     Tunable (md_num_stripes): 3712
     Tunable (md_write_limit): 1672
     Tunable (md_sync_window): 1672

These settings will consume 203MB of RAM on your hardware.
This is 126MB more than your current utilization of 77MB.
NOTE: Adding additional drives will increase memory consumption.

In unRAID, go to Settings > Disk Settings to set your chosen parameter values.

[tcharron]

I'm not sure I understand what this script is doing in the second pass.

 

Take the results that are posted in the reply before this one.  The first pass identifies a sync_window of 1792 as optimal (test # 11).  The second pass examines the range between test 10 and test 11 (sync_window 1672-1792) more closely.  Why doesn't it also look at the range of 1792-1920?  Isn't the optimal spot as likely to be beyond 1792 as before it?

 

Also, just a nit, but the range selection has "1-14" in it.  That should be "1-19" now, with the addition of ranges up to 2944.

[enetec]

I'm not sure I understand what this script is doing in the second pass.

 

Take the results that are posted in the reply before this one.  The first pass identifies a sync_window of 1792 as optimal (test # 11).  The second pass examines the range between test 10 and test 11 (sync_window 1672-1792) more closely.  Why doesn't it also look at the range of 1792-1920?  Isn't the optimal spot as likely to be beyond 1792 as before it?

...

 

In fact I prefer fine tuning manually after first pass... 

 

Great tool anyway... I think this should be sticky too +1 

 

Only one answer... I've got the impression that fine tuning give great gains on systems with mixed data disks and little gains on systems with identical data disks... Could it be this way?

[opentoe]

I'm not sure I understand what this script is doing in the second pass.

 

Take the results that are posted in the reply before this one.  The first pass identifies a sync_window of 1792 as optimal (test # 11).  The second pass examines the range between test 10 and test 11 (sync_window 1672-1792) more closely.  Why doesn't it also look at the range of 1792-1920?  Isn't the optimal spot as likely to be beyond 1792 as before it?

...

 

In fact I prefer fine tuning manually after first pass... 

 

Great tool anyway... I think this should be sticky too +1 

 

Only one answer... I've got the impression that fine tuning give great gains on systems with mixed data disks and little gains on systems with identical data disks... Could it be this way?

 

Was pointed to this thread and to run this script. I ran it last night, it completed. It gave me back three suggestions to try.

md_num_stripes

md_write_limit

md_sync_window

 

Looked at the webgui in Unraid V6 and only two of the options were there.

num_stripes and sync_window. There is another setting there called poll_attributes, but no write_limit. Is this test accurate now? Should I just keep poll_attributes default and change the other two settings?

 

[opentoe]

I ran the script after I made the changes it recommended and the results were slower! I don't believe it works too well. Unless I got the whole procedure wrong here.

 

First time I ran the script I took all the defaults. Gave me the numbers, which only two are available to change with V6, so I changed them. Rebooted the server and ran the script again and the results were 10MB/sec slower. I think I just want to go back to the original numbers.

[dlandon]

You can edit the /flash/config/disk.cfg and change all three parameters.  I don't know why they can't all three be changed in the webgui.

 

Don't give up so easily.  The script helped me improve my parity checks a lot.  I went from about 80MB/sec to about 115MB/sec.  Try to change all three in the disk.cfg file and test again.

[opentoe]

You can edit the /flash/config/disk.cfg and change all three parameters.  I don't know why they can't all three be changed in the webgui.

 

Don't give up so easily.  The script helped me improve my parity checks a lot.  I went from about 80MB/sec to about 115MB/sec.  Try to change all three in the disk.cfg file and test again.

 

I'll give it another try. I'll revert all back to defaults and try again. The default test only takes less then an hour so I'll give it shot.