Significant write speed difference when encryption is on

-MG- · Jan 25, 2019

Hi All -

I'm in the process of finishing the build of a new system. I had some issues with 11.2, so I did a fresh install of 11.1U6 for now and I don't seem to have the sentry errors I was getting before that seemed to affect performance.

I don't have any data on the new system yet and already performed a burn-in of some HE6 drives that were previously used but came with a 3 year warranty. Here are the results which seem to be fairly consistent after the burn-in:

Code:

root@freenas[~]# smartctl -A /dev/da2
smartctl 6.6 2017-11-05 r4594 [FreeBSD 11.2-STABLE amd64] (local build)
Copyright (C) 2002-17, Bruce Allen, Christian Franke, www.smartmontools.org

=== START OF READ SMART DATA SECTION ===
SMART Attributes Data Structure revision number: 16
Vendor Specific SMART Attributes with Thresholds:
ID# ATTRIBUTE_NAME          FLAG     VALUE WORST THRESH TYPE      UPDATED  WHEN_FAILED RAW_VALUE
  1 Raw_Read_Error_Rate     0x000b   100   100   016    Pre-fail  Always       -       0
  2 Throughput_Performance  0x0005   132   132   054    Pre-fail  Offline      -       84
  3 Spin_Up_Time            0x0007   219   219   024    Pre-fail  Always       -       405 (Average 507)
  4 Start_Stop_Count        0x0012   100   100   000    Old_age   Always       -       82
  5 Reallocated_Sector_Ct   0x0033   100   100   005    Pre-fail  Always       -       0
  7 Seek_Error_Rate         0x000b   100   100   067    Pre-fail  Always       -       0
  8 Seek_Time_Performance   0x0005   130   130   020    Pre-fail  Offline      -       12
  9 Power_On_Hours          0x0012   096   096   000    Old_age   Always       -       32473
10 Spin_Retry_Count        0x0013   100   100   060    Pre-fail  Always       -       0
12 Power_Cycle_Count       0x0032   100   100   000    Old_age   Always       -       81
22 Helium_Level            0x0023   100   100   025    Pre-fail  Always       -       6579300
192 Power-Off_Retract_Count 0x0032   099   099   000    Old_age   Always       -       1905
193 Load_Cycle_Count        0x0012   099   099   000    Old_age   Always       -       1905
194 Temperature_Celsius     0x0002   193   193   000    Old_age   Always       -       31 (Min/Max 18/41)
196 Reallocated_Event_Count 0x0032   100   100   000    Old_age   Always       -       0
197 Current_Pending_Sector  0x0022   100   100   000    Old_age   Always       -       0
198 Offline_Uncorrectable   0x0008   100   100   000    Old_age   Offline      -       0
199 UDMA_CRC_Error_Count    0x000a   200   200   000    Old_age   Always       -       0

Within my pool I created a new dataset and made sure compression was turned off. I then executed within that dataset:

dd if=/dev/zero of=tmp.dat bs=2048k count=50k

Needless to say after seeing other posts I began to worry when after 10 minutes it did not complete. I hit Ctrl+C and found that it was transfering around 32-40MB/s. That seems really poor for what I would have expected?

I started at 10PM a replication task of a snapshot to move over my current data. I can't see the actual progress, but when I go and look at my new machine and the storage tab I can see after freshing how the data is progressing. After checking 9 hours later, it had transferred around 600GiBs.

I did not perform this same test on my current rig which is also RaidZ2 and has (6) 3TB Red drives. I will check that out.

The odd part of it all. When I go through windows and just drag and drop a file. I get ~115Mbps speed which is consistent with what I would expect from my old server. I have all the data for all my HDDs like I posted above if it is helpful.

What am I missing here?

Mlovelace · Jan 25, 2019

If your pool is actually performing 32MB/s writes in a dd test then 600GB of data in 9 hours isn't that far off the mark. You need to figure out what is wrong with the new pool, because that dd test is terrible and well below what the pool should be capable of.

Edit: For a point of comparison here are the results for your same dd test on one of my raidz2 pools (no compression).

Code:

root@CLNAS02:/mnt/tank/test # dd if=/dev/zero of=tmp.dat bs=2048k count=50k
51200+0 records in
51200+0 records out
107374182400 bytes transferred in 117.847870 secs (911125351 bytes/sec)

-MG- · Jan 25, 2019

Potentially for other's to help with, here is the full report of the 8 drives I bought (2 backups). I would have to look to confirm which drives actually were pulled after testing if it was da6-7 or not.

Code:

root@freenas[~]# smartctl -A /dev/da0
smartctl 6.6 2017-11-05 r4594 [FreeBSD 11.2-STABLE amd64] (local build)
Copyright (C) 2002-17, Bruce Allen, Christian Franke, www.smartmontools.org

=== START OF READ SMART DATA SECTION ===
SMART Attributes Data Structure revision number: 16
Vendor Specific SMART Attributes with Thresholds:
ID# ATTRIBUTE_NAME          FLAG     VALUE WORST THRESH TYPE      UPDATED  WHEN_FAILED RAW_VALUE
  1 Raw_Read_Error_Rate     0x000b   100   100   016    Pre-fail  Always       -       0
  2 Throughput_Performance  0x0005   131   131   054    Pre-fail  Offline      -       87
  3 Spin_Up_Time            0x0007   230   230   024    Pre-fail  Always       -       483 (Average 384)
  4 Start_Stop_Count        0x0012   100   100   000    Old_age   Always       -       43
  5 Reallocated_Sector_Ct   0x0033   100   100   005    Pre-fail  Always       -       0
  7 Seek_Error_Rate         0x000b   100   100   067    Pre-fail  Always       -       0
  8 Seek_Time_Performance   0x0005   130   130   020    Pre-fail  Offline      -       12
  9 Power_On_Hours          0x0012   094   094   000    Old_age   Always       -       42511
 10 Spin_Retry_Count        0x0013   100   100   060    Pre-fail  Always       -       0
 12 Power_Cycle_Count       0x0032   100   100   000    Old_age   Always       -       43
 22 Helium_Level            0x0023   100   100   025    Pre-fail  Always       -       6579300
192 Power-Off_Retract_Count 0x0032   099   099   000    Old_age   Always       -       1814
193 Load_Cycle_Count        0x0012   099   099   000    Old_age   Always       -       1814
194 Temperature_Celsius     0x0002   187   187   000    Old_age   Always       -       32 (Min/Max 9/42)
196 Reallocated_Event_Count 0x0032   100   100   000    Old_age   Always       -       0
197 Current_Pending_Sector  0x0022   100   100   000    Old_age   Always       -       0
198 Offline_Uncorrectable   0x0008   100   100   000    Old_age   Offline      -       0
199 UDMA_CRC_Error_Count    0x000a   200   200   000    Old_age   Always       -       0

root@freenas[~]# smartctl -A /dev/da1
smartctl 6.6 2017-11-05 r4594 [FreeBSD 11.2-STABLE amd64] (local build)
Copyright (C) 2002-17, Bruce Allen, Christian Franke, www.smartmontools.org

=== START OF READ SMART DATA SECTION ===
SMART Attributes Data Structure revision number: 16
Vendor Specific SMART Attributes with Thresholds:
ID# ATTRIBUTE_NAME          FLAG     VALUE WORST THRESH TYPE      UPDATED  WHEN_FAILED RAW_VALUE
  1 Raw_Read_Error_Rate     0x000b   100   100   016    Pre-fail  Always       -       0
  2 Throughput_Performance  0x0005   131   131   054    Pre-fail  Offline      -       87
  3 Spin_Up_Time            0x0007   234   234   024    Pre-fail  Always       -       391 (Average 463)
  4 Start_Stop_Count        0x0012   100   100   000    Old_age   Always       -       47
  5 Reallocated_Sector_Ct   0x0033   100   100   005    Pre-fail  Always       -       0
  7 Seek_Error_Rate         0x000b   100   100   067    Pre-fail  Always       -       0
  8 Seek_Time_Performance   0x0005   130   130   020    Pre-fail  Offline      -       12
  9 Power_On_Hours          0x0012   094   094   000    Old_age   Always       -       42281
 10 Spin_Retry_Count        0x0013   100   100   060    Pre-fail  Always       -       0
 12 Power_Cycle_Count       0x0032   100   100   000    Old_age   Always       -       47
 22 Helium_Level            0x0023   100   100   025    Pre-fail  Always       -       6579300
192 Power-Off_Retract_Count 0x0032   099   099   000    Old_age   Always       -       1821
193 Load_Cycle_Count        0x0012   099   099   000    Old_age   Always       -       1821
194 Temperature_Celsius     0x0002   176   176   000    Old_age   Always       -       34 (Min/Max 5/38)
196 Reallocated_Event_Count 0x0032   100   100   000    Old_age   Always       -       0
197 Current_Pending_Sector  0x0022   100   100   000    Old_age   Always       -       0
198 Offline_Uncorrectable   0x0008   100   100   000    Old_age   Offline      -       0
199 UDMA_CRC_Error_Count    0x000a   200   200   000    Old_age   Always       -       0


root@freenas[~]# smartctl -A /dev/da2
smartctl 6.6 2017-11-05 r4594 [FreeBSD 11.2-STABLE amd64] (local build)
Copyright (C) 2002-17, Bruce Allen, Christian Franke, www.smartmontools.org

=== START OF READ SMART DATA SECTION ===
SMART Attributes Data Structure revision number: 16
Vendor Specific SMART Attributes with Thresholds:
ID# ATTRIBUTE_NAME          FLAG     VALUE WORST THRESH TYPE      UPDATED  WHEN_FAILED RAW_VALUE
  1 Raw_Read_Error_Rate     0x000b   100   100   016    Pre-fail  Always       -       0
  2 Throughput_Performance  0x0005   132   132   054    Pre-fail  Offline      -       84
  3 Spin_Up_Time            0x0007   219   219   024    Pre-fail  Always       -       405 (Average 507)
  4 Start_Stop_Count        0x0012   100   100   000    Old_age   Always       -       82
  5 Reallocated_Sector_Ct   0x0033   100   100   005    Pre-fail  Always       -       0
  7 Seek_Error_Rate         0x000b   100   100   067    Pre-fail  Always       -       0
  8 Seek_Time_Performance   0x0005   130   130   020    Pre-fail  Offline      -       12
  9 Power_On_Hours          0x0012   096   096   000    Old_age   Always       -       32473
 10 Spin_Retry_Count        0x0013   100   100   060    Pre-fail  Always       -       0
 12 Power_Cycle_Count       0x0032   100   100   000    Old_age   Always       -       81
 22 Helium_Level            0x0023   100   100   025    Pre-fail  Always       -       6579300
192 Power-Off_Retract_Count 0x0032   099   099   000    Old_age   Always       -       1905
193 Load_Cycle_Count        0x0012   099   099   000    Old_age   Always       -       1905
194 Temperature_Celsius     0x0002   193   193   000    Old_age   Always       -       31 (Min/Max 18/41)
196 Reallocated_Event_Count 0x0032   100   100   000    Old_age   Always       -       0
197 Current_Pending_Sector  0x0022   100   100   000    Old_age   Always       -       0
198 Offline_Uncorrectable   0x0008   100   100   000    Old_age   Offline      -       0
199 UDMA_CRC_Error_Count    0x000a   200   200   000    Old_age   Always       -       0

root@freenas[~]# smartctl -A /dev/da3
smartctl 6.6 2017-11-05 r4594 [FreeBSD 11.2-STABLE amd64] (local build)
Copyright (C) 2002-17, Bruce Allen, Christian Franke, www.smartmontools.org

=== START OF READ SMART DATA SECTION ===
SMART Attributes Data Structure revision number: 16
Vendor Specific SMART Attributes with Thresholds:
ID# ATTRIBUTE_NAME          FLAG     VALUE WORST THRESH TYPE      UPDATED  WHEN_FAILED RAW_VALUE
  1 Raw_Read_Error_Rate     0x000b   100   100   016    Pre-fail  Always       -       0
  2 Throughput_Performance  0x0005   132   132   054    Pre-fail  Offline      -       86
  3 Spin_Up_Time            0x0007   226   226   024    Pre-fail  Always       -       440 (Average 442)
  4 Start_Stop_Count        0x0012   100   100   000    Old_age   Always       -       45
  5 Reallocated_Sector_Ct   0x0033   100   100   005    Pre-fail  Always       -       0
  7 Seek_Error_Rate         0x000b   100   100   067    Pre-fail  Always       -       0
  8 Seek_Time_Performance   0x0005   130   130   020    Pre-fail  Offline      -       12
  9 Power_On_Hours          0x0012   094   094   000    Old_age   Always       -       42519
 10 Spin_Retry_Count        0x0013   100   100   060    Pre-fail  Always       -       0
 12 Power_Cycle_Count       0x0032   100   100   000    Old_age   Always       -       45
 22 Helium_Level            0x0023   100   100   025    Pre-fail  Always       -       6579300
192 Power-Off_Retract_Count 0x0032   099   099   000    Old_age   Always       -       1802
193 Load_Cycle_Count        0x0012   099   099   000    Old_age   Always       -       1802
194 Temperature_Celsius     0x0002   187   187   000    Old_age   Always       -       32 (Min/Max 4/36)
196 Reallocated_Event_Count 0x0032   100   100   000    Old_age   Always       -       0
197 Current_Pending_Sector  0x0022   100   100   000    Old_age   Always       -       0
198 Offline_Uncorrectable   0x0008   100   100   000    Old_age   Offline      -       0
199 UDMA_CRC_Error_Count    0x000a   200   200   000    Old_age   Always       -       0

root@freenas[~]# smartctl -A /dev/da6
smartctl 6.6 2017-11-05 r4594 [FreeBSD 11.2-STABLE amd64] (local build)
Copyright (C) 2002-17, Bruce Allen, Christian Franke, www.smartmontools.org

=== START OF READ SMART DATA SECTION ===
SMART Attributes Data Structure revision number: 16
Vendor Specific SMART Attributes with Thresholds:
ID# ATTRIBUTE_NAME          FLAG     VALUE WORST THRESH TYPE      UPDATED  WHEN_FAILED RAW_VALUE
  1 Raw_Read_Error_Rate     0x000b   100   100   016    Pre-fail  Always       -       0
  2 Throughput_Performance  0x0005   131   131   054    Pre-fail  Offline      -       87
  3 Spin_Up_Time            0x0007   253   253   024    Pre-fail  Always       -       343 (Average 375)
  4 Start_Stop_Count        0x0012   100   100   000    Old_age   Always       -       42
  5 Reallocated_Sector_Ct   0x0033   100   100   005    Pre-fail  Always       -       0
  7 Seek_Error_Rate         0x000b   100   100   067    Pre-fail  Always       -       0
  8 Seek_Time_Performance   0x0005   130   130   020    Pre-fail  Offline      -       12
  9 Power_On_Hours          0x0012   094   094   000    Old_age   Always       -       42940
 10 Spin_Retry_Count        0x0013   100   100   060    Pre-fail  Always       -       0
 12 Power_Cycle_Count       0x0032   100   100   000    Old_age   Always       -       42
 22 Helium_Level            0x0023   100   100   025    Pre-fail  Always       -       6579300
192 Power-Off_Retract_Count 0x0032   099   099   000    Old_age   Always       -       1827
193 Load_Cycle_Count        0x0012   099   099   000    Old_age   Always       -       1827
194 Temperature_Celsius     0x0002   200   200   000    Old_age   Always       -       30 (Min/Max 1/38)
196 Reallocated_Event_Count 0x0032   100   100   000    Old_age   Always       -       0
197 Current_Pending_Sector  0x0022   100   100   000    Old_age   Always       -       0
198 Offline_Uncorrectable   0x0008   100   100   000    Old_age   Offline      -       0
199 UDMA_CRC_Error_Count    0x000a   200   200   000    Old_age   Always       -       0

root@freenas[~]# smartctl -A /dev/da7
smartctl 6.6 2017-11-05 r4594 [FreeBSD 11.2-STABLE amd64] (local build)
Copyright (C) 2002-17, Bruce Allen, Christian Franke, www.smartmontools.org

=== START OF READ SMART DATA SECTION ===
SMART Attributes Data Structure revision number: 16
Vendor Specific SMART Attributes with Thresholds:
ID# ATTRIBUTE_NAME          FLAG     VALUE WORST THRESH TYPE      UPDATED  WHEN_FAILED RAW_VALUE
  1 Raw_Read_Error_Rate     0x000b   100   100   016    Pre-fail  Always       -       0
  2 Throughput_Performance  0x0005   132   132   054    Pre-fail  Offline      -       84
  3 Spin_Up_Time            0x0007   236   236   024    Pre-fail  Always       -       399 (Average 445)
  4 Start_Stop_Count        0x0012   100   100   000    Old_age   Always       -       39
  5 Reallocated_Sector_Ct   0x0033   100   100   005    Pre-fail  Always       -       0
  7 Seek_Error_Rate         0x000b   100   100   067    Pre-fail  Always       -       0
  8 Seek_Time_Performance   0x0005   130   130   020    Pre-fail  Offline      -       12
  9 Power_On_Hours          0x0012   094   094   000    Old_age   Always       -       43098
 10 Spin_Retry_Count        0x0013   100   100   060    Pre-fail  Always       -       0
 12 Power_Cycle_Count       0x0032   100   100   000    Old_age   Always       -       39
 22 Helium_Level            0x0023   100   100   025    Pre-fail  Always       -       6579300
192 Power-Off_Retract_Count 0x0032   099   099   000    Old_age   Always       -       1870
193 Load_Cycle_Count        0x0012   099   099   000    Old_age   Always       -       1870
194 Temperature_Celsius     0x0002   200   200   000    Old_age   Always       -       30 (Min/Max 4/36)
196 Reallocated_Event_Count 0x0032   100   100   000    Old_age   Always       -       0
197 Current_Pending_Sector  0x0022   100   100   000    Old_age   Always       -       0
198 Offline_Uncorrectable   0x0008   100   100   000    Old_age   Offline      -       0
199 UDMA_CRC_Error_Count    0x000a   200   200   000    Old_age   Always       -       0

Chris Moore · Jan 25, 2019

-MG- said:
Potentially for other's to help with, here is the full report of the 8 drives I bought (2 backups). I would have to look to confirm which drives actually were pulled after testing if it was da6-7 or not.

The information about hardware in your signature is a bit confusing and incomplete. Can you give exact details of the hardware these drives are connected to and how the drives are connected to the system? You appear to be focused on the drives when it could be another link in the chain that is making it slow.

-MG- · Jan 25, 2019

Chris Moore said:
The information about hardware in your signature is a bit confusing and incomplete. Can you give exact details of the hardware these drives are connected to and how the drives are connected to the system? You appear to be focused on the drives when it could be another link in the chain that is making it slow.

Good point.

I think Dell server itself is pretty straight forward already by giving CPU and total of 256GB of ram. I used one of the PCI-E 3.0 slots for the Dell H200E HBA card I got on eBay. It appeared to already be in IT mode as far as I could tell, but I wasn't able to access the card from the Dell server boot. Candidly, I know very little about what if anything would need to be done in the card's settings. I know it has version 7 of its firmware on it.

From there, the DAS came with 1 meter SFF-8088 to SFF-8088 cable to cross connect the Lenovo storage array:

https://www.amazon.com/gp/product/B00LSQOY6G/ref=oh_aui_search_asin_title?ie=UTF8&psc=1

All I did was load the drive's in the caddy's, shoved them in the system, powered it up and did nothing from there. FreeNAS installation was able to see all of the drives in the Lenovo storage and I had no problems or errors once installed. Just the performance issues referenced. The Lenovo array backplane is a SAS 6 Gbps expander and will support 6 Gbps of bandwidth.

I should add that in that array are the 6 HGST drives there plus the 2 SSD's for Jails, etc.

Would I need to try to accomplish flashing the HBA card?

https://forums.freenas.org/index.php?threads/crossflash-dell-h200e-to-lsi-9200-8e.41307/

Mlovelace · Jan 25, 2019

-MG- said:
I know it has version 7 of its firmware on it.

We've identified our first problem. You need to flash that card to the LSI IT firmware version 20.00.07.00

This should get you started: https://blog.michael.kuron-germany....dell-perc-h200-to-lsi-9211-8i/comment-page-1/

Chris Moore · Jan 25, 2019

-MG- said:
I know it has version 7 of its firmware on it.

It needs a firmware update. There is certainly a newer firmware for that card even if it doesn't need to change mode. Firmware versions in a SAS controller can make a significant difference in performance.

In RAIDz2, each vdev would present performance roughly equivalent to the performance of the slowest single drive in the vdev. Only having one vdev, that would mean the six drives would perform as if it were one drive, but it should be faster than what you have described.
When those drives were new, they were supposed to be able to handle a sustained transfer of 177MB/sec.
https://www.storagereview.com/hgst_ultrastar_helium_6tb_enterprise_hard_drive_review

I would suggest the firmware update on the SAS controller as the first step in testing.

Mlovelace · Jan 25, 2019

Chris Moore said:
In RAIDz2, each vdev would present performance roughly equivalent to the performance of the slowest single drive in the vdev. Only having one vdev, that would mean the six drives would perform as if it were one drive

This depends on the use case of the pool...

Pool Geometry
If small random IOPS are of primary importance, mirrored vdevs will outperform raidz vdevs. Read IOPS on mirrors will scale with the number of drives in each mirror while raidz vdevs will each be limited to the IOPS of the slowest drive.

If sequential writes are of primary importance, raidz will outperform mirrored vdevs. Sequential write throughput increases linearly with the number of data disks in raidz while writes are limited to the slowest drive in mirrored vdevs. Sequential read performance should be roughly the same on each.

Both IOPS and throughput will increase by the respective sums of the IOPS and throughput of each top level vdev, regardless of whether they are raidz or mirrors.

Chris Moore · Jan 25, 2019

Mlovelace said:
Pool Geometry

I get it.

Mlovelace · Jan 25, 2019

Chris Moore said:
I get it.

I have no doubt you are well versed in pool goemetry / use case. I figured it could be useful for non-freenas veterans to stumble across when designing their pools.

-MG- · Jan 25, 2019

Mlovelace said:
We've identified our first problem. You need to flash that card to the LSI IT firmware version 20.00.07.00

This should get you started: https://blog.michael.kuron-germany....dell-perc-h200-to-lsi-9211-8i/comment-page-1/

Got any advice why the server is throwing a general protection error when I run the sas2flash.efi file.

Type: General Protection Fault (13) Source: Software (UEFI0011) on BSP

****Nevermind on this. I finally got another computer to boot up with EFI. What I did not know and some guides don't tell you are that you need to create an efi folder and then a boot folder and place the bootx64.efi there.

That looks like /efi/boot/bootx64.efi

I couldn't figure out why it would not boot from the USB. Currently updating firmware now.

-MG- · Jan 25, 2019

I successfully got the firmware to version 20.00.07.00.

After reinstalling and running the same dd test as above. No change to my speeds.

Here is the actual dd test results:

Code:

root@freenas:/mnt/Mia/test # dd if=/dev/zero of=tmp.dat bs=2048k count=50k
3522+0 records in
3521+0 records out
7384072192 bytes transferred in 134.643735 secs (54841558 bytes/sec)
root@freenas:/mnt/Mia/test # dd of=/dev/zero if=tmp.dat bs=2048k count=50k
3522+0 records in
3522+0 records out
7386169344 bytes transferred in 1.810822 secs (4078904183 bytes/sec)

This is one of the faster write tests. The read test is crazy fast. I'll restart so its not sitting in ARC.

a test data set in the SSD mirror produces writes of 443 MB/s

-MG- · Jan 26, 2019

The read after restart produced:

Code:

22725632000 bytes transferred in 42.416206 secs (535777100 bytes/sec)

That seems consistent with what I should expect right?

Mlovelace · Jan 26, 2019

-MG- said:
The read after restart produced:

Code:
22725632000 bytes transferred in 42.416206 secs (535777100 bytes/sec)

That seems consistent with what I should expect right?

With a single raidz2 vdev of 6 drives this seems about right.

I'm not at work so I can't throw a system together to compare, but on my home system (raidz1 w/4disks) I got: ~ 320MB/s writes

Code:

root@homenas:/mnt/tank/test # dd if=/dev/zero of=tmp.dat bs=2048k count=50k
51200+0 records in
51200+0 records out
107374182400 bytes transferred in 321.254560 secs (334233956 bytes/sec)

-MG- · Jan 26, 2019

Based on that, with everything else so far appearing normal. I thought maybe there is a single drive on the verge of failing. Since there is no data on it yet. I destroyed the array and just setup each drive as its own volume and ran dd from uncompressed data set in each one. Did not do a read test, but all writes were ~204-220 MB/s rates.

I do understand it could be something else. I’m just focusing on what I understand at this point.

-MG- · Jan 26, 2019

I'm not sure what changed or if this was self inflicted, but after making recreating the single raidz2 vdev of 6 drives and just used the dataset that get's created automatically. I turned compression off and turned share type to windows (don't know what it was before. maybe unix?). I ran my dd command and got this result:

Code:

root@freenas:/mnt/Mia # dd if=/dev/zero of=tmp.dat bs=2048k count=50k
^C45944+0 records in
45943+0 records out
96349454336 bytes transferred in 289.715872 secs (332565329 bytes/sec)

UPDATE: Forgot I did not encrypt the new volume. When I re-create it and check encryption speeds slow way down again.

Code:

root@freenas:/mnt/Mia # dmesg | grep aes
aesni0: <AES-CBC,AES-XTS,AES-GCM,AES-ICM> on motherboard

I'm now researching AES-NI from this thread:

https://forums.freenas.org/index.php?threads/encryption-performance-benchmarks.12157/

-MG- · Jan 26, 2019

As a follow up to my post. My bios clearly shows AES-NI enabled, but I'm not confident that message in my last post shows its active. I found another post where @cyberjock talked about powerd setting, mine is and was disabled.

Important Announcement for the TrueNAS Community.

Significant write speed difference when encryption is on

-MG-

Explorer

Mlovelace

Guru

-MG-

Explorer

Chris Moore

Hall of Famer

-MG-

Explorer

Mlovelace

Guru

Chris Moore

Hall of Famer

Mlovelace

Guru

Chris Moore

Hall of Famer

Mlovelace

Guru

-MG-

Explorer

-MG-

Explorer

-MG-

Explorer

Mlovelace

Guru

-MG-

Explorer

-MG-

Explorer

-MG-

Explorer

Similar threads

Important Announcement for the TrueNAS Community.

Significant write speed difference when encryption is on

Explorer

Guru

Explorer

Hall of Famer

Explorer

Guru

Hall of Famer

Guru

Hall of Famer

Guru

Explorer

Explorer

Explorer

Guru

Explorer

Explorer

Explorer

Important Announcement for the TrueNAS Community.

Related topics on forums.truenas.com for thread: "Significant write speed difference when encryption is on"

Similar threads