First off, here's my config:

 

unRaid: unRAID Server 5.0-rc12a

Case: Norco 4224

CPU: Intel Xeon E3-1240 (Sandy Bridge)

MB: Supermicro X9SCM-IIF

RAM: 4 x Hynix DDR3-1333 8GB ECC CL9 (on memory list for the X9SCM-IIF)

PSU: SeaSonic X Series X-850 850W 80 PLUS GOLD

HBA1: IBM M1015 (Port 0 - cascade to RES2SV240; Port 1 - 4X SAS2 ports)

HBA2: Intel RES2SV240 SAS Expander (Ports 0&1 - cascade from M1015s, Ports 2-5 - 16X SAS2 ports)

HBA3 : IBM M1015 (Port 0 - cascade to RES2SV240; Port 1 - 4xSAS2 ports not used)

 

 

This is a new build, I put it together on the weekend, flashed the M1015's to IT FW, and updated the RES2SV240 FW to the latest to address issues some people have with large drives. The only plugin is SimpleFeatures.

 

The preclear phase 1 read speed is fine, anywhere from 100 to 150MB per second.

 

Write speed though is horrible, just 500KB per second.

 

First I thought it was because I was doing multiple preclears in parallel, but I rebooted the server and did just one and I still get the same performance.

 

Screenshot attached of the preclear_disk.sh status.

 

So I looked in the syslog and I see the following coming out about once a second, I have to think this is either contributing or point to the root cause. However it's been a while since I used linux and other than it looks like I have a problem I don't know what it's telling me.

 

Any suggestions would be appreciated. Thanks.

 

May 14 18:56:19 ShepStor1 emhttp: shcmd (146528): rmmod md-mod |& logger

May 14 18:56:19 ShepStor1 emhttp: shcmd (146529): modprobe md-mod super=/boot/config/super.dat slots=24 |& logger

May 14 18:56:19 ShepStor1 emhttp: shcmd (146530): udevadm settle

May 14 18:56:19 ShepStor1 kernel: md: unRAID driver removed

May 14 18:56:19 ShepStor1 kernel: md: unRAID driver 2.1.6 installed

May 14 18:56:19 ShepStor1 kernel: read_file: error 2 opening /boot/config/super.dat

May 14 18:56:19 ShepStor1 kernel: md: could not read superblock from /boot/config/super.dat

May 14 18:56:19 ShepStor1 kernel: md: initializing superblock

May 14 18:56:19 ShepStor1 emhttp: Device inventory:

May 14 18:56:19 ShepStor1 emhttp: Samsung_SSD_840_Series_S14LNEACC52826D (sda) 488386584

May 14 18:56:19 ShepStor1 emhttp: WDC_WD30EFRX-68AX9N0_WD-WMC1T3252356 (sdb) 2930266584

May 14 18:56:19 ShepStor1 emhttp: ST3000DM001-1CH166_Z1F295KQ (sdc) 2930266584

May 14 18:56:19 ShepStor1 emhttp: WDC_WD2002FAEX-007BA0_WD-WCAY01453895 (sdd) 1953514584

May 14 18:56:19 ShepStor1 emhttp: WDC_WD4001FAEX-00MJRA0_WD-WCC130249430 (sde) 3907018584

May 14 18:56:19 ShepStor1 emhttp: ST3000DM001-1CH166_Z1F28ACG (sdf) 2930266584

May 14 18:56:19 ShepStor1 emhttp: WDC_WD20EFRX-68AX9N0_WD-WMC301199624 (sdg) 1953514584

May 14 18:56:19 ShepStor1 emhttp: WDC_WD30EFRX-68AX9N0_WD-WMC1T3261441 (sdh) 2930266584

May 14 18:56:19 ShepStor1 emhttp: WDC_WD20EFRX-68AX9N0_WD-WMC301231304 (sdj) 1953514584

May 14 18:56:19 ShepStor1 emhttp: shcmd (146531): /usr/local/sbin/emhttp_event driver_loaded

May 14 18:56:19 ShepStor1 emhttp_event: driver_loaded

May 14 18:56:20 ShepStor1 kernel: mdcmd (1): import 0 0,0

May 14 18:56:20 ShepStor1 kernel: mdcmd (2): import 1 0,0

May 14 18:56:20 ShepStor1 kernel: mdcmd (3): import 2 0,0

May 14 18:56:20 ShepStor1 kernel: mdcmd (4): import 3 0,0

May 14 18:56:20 ShepStor1 kernel: mdcmd (5): import 4 0,0

May 14 18:56:20 ShepStor1 kernel: mdcmd (6): import 5 0,0

May 14 18:56:20 ShepStor1 kernel: mdcmd (7): import 6 0,0

May 14 18:56:20 ShepStor1 kernel: mdcmd (: import 7 0,0

May 14 18:56:20 ShepStor1 kernel: mdcmd (9): import 8 0,0

May 14 18:56:20 ShepStor1 kernel: mdcmd (10): import 9 0,0

May 14 18:56:20 ShepStor1 kernel: mdcmd (11): import 10 0,0

May 14 18:56:20 ShepStor1 kernel: mdcmd (12): import 11 0,0

May 14 18:56:20 ShepStor1 kernel: mdcmd (13): import 12 0,0

May 14 18:56:20 ShepStor1 kernel: mdcmd (14): import 13 0,0

May 14 18:56:20 ShepStor1 kernel: mdcmd (15): import 14 0,0

May 14 18:56:20 ShepStor1 kernel: mdcmd (16): import 15 0,0

May 14 18:56:20 ShepStor1 kernel: mdcmd (17): import 16 0,0

May 14 18:56:20 ShepStor1 kernel: mdcmd (18): import 17 0,0

May 14 18:56:20 ShepStor1 kernel: mdcmd (19): import 18 0,0

May 14 18:56:20 ShepStor1 kernel: mdcmd (20): import 19 0,0

May 14 18:56:20 ShepStor1 kernel: mdcmd (21): import 20 0,0

May 14 18:56:20 ShepStor1 kernel: mdcmd (22): import 21 0,0

May 14 18:56:20 ShepStor1 kernel: mdcmd (23): import 22 0,0

May 14 18:56:20 ShepStor1 kernel: mdcmd (24): import 23 0,0

Looks like your array is not started which is what you are seeing in the syslog snippet.  It would help to post a full syslog.

 

 

Thanks for the info; I attached the start of the syslog, the full log is too huge. Note that I didn't start the array because I didn't have any disks to assign, none cleared in advance. I'll re-read the manual see if I am doing something wrong.

 

syslog.txt

Well, after doing more research I found the thread about issues with the current kernel when using more than 4Gig ram, so I used the 4G boot option on unRaid and am now writing in the preclear at ~140Mb/s.

 

I have marked this issue solved.