SATA Controller Cards


Recommended Posts

Where did you buy it, and how much did you pay for it?

 

Errr .. from the only Supermicro reseller in this part of the Philippines ... and too much - PHP9,550 (around USD210)!

 

Thanks for the other advices and suggestions - I'll work on those.

Link to comment

I have a question about these SATA expansion / controller cards with regard to PCI-e slots and bandwidth. I notice that typically products will follow the below trend:

 

PCI-e x1 slot = 2 port expansion cards available

PCI-e x4 slot = 4 port expansion cards available (and some 8 port)

PCI-e x8 slot = 8 port + expansion cards available

 

I understand that this is to do with bandwidth of each slot and not producing products that would be bottlenecked by each slot. However, the above does not make sense to me…

 

Why do we not have for example 4 port cards available for PCI-e x1 slots? PCI-e version 2.0 x1 slots, have a maximum bandwidth of 500 MB/s. Taking the assumption that each drive attached to this slot could be reading/writing at a theoretical 125MB/s each (max possible over gigabit ethernet) then we have:

 

500 / 125 = 4 possible drives

 

So we could have 4 hard disk drives attached to a PCI-e 2.0 x1 slot if they manufactured a card that had 4 ports. Yet we only see cards with 2 ports on x1 slots.

 

I can understand this scenario if you take into account the cards are only manufactured for PCI-e version 1.0/1.1, as then the bandwidth is halved to 250MB/s, so the above example would check out and you could have exactly 2 HDDs attached before theoretically hitting a bottleneck. Is this all it is? That nobody has bothered making a PCI-e version 2.0 x1, 4 port card? Can I assume that the reason is due to lack of demand when people can use the already out there products for x4 slots?

 

Reason I am interested, is that my motherboard has 2 separate x1 slots (PCI-e version 2.0) and I am trying to plan for the future what the maximum amount of hard disk drives I could handle is. I have on my motherboard:

8 x SATA ports

1 x 16x pci-e slot (version 2.0)

2 x 1x pci-e slot (version 2.0)

 

I think I can have 8 + 8 + 2 + 2 = 20 which nicely maximises the current licence for Pro I believe.

 

 

I honestly don't know the answer to this.  You are correct that PCIe x1 version 2.0 has plenty of bandwidth for 4 drives in the unRAID environment, and I too would like to see some PCIe x1 4 port cards.  I would assume that the bit I bolded in your quote is very likely the reason, but your guess is as good as mine.

 

It also might be the case that manufacturers produce these SATA cards with the intention of people using them within a single computer, not necessarily in a server limited by Gigabit LAN.  I'm not sure what the theoretical max read/write speeds for a drive under Windows/Linux/MacOS are, but perhaps four drives on a PCIe x1 version 2.0 slot would be bottlenecked in that scenario?  I'm just guessing here, I haven't done the math.

Link to comment

Nice price, just a bit more than the SASLP cards.  Of course the SATAIII capabilities don't matter one iota at the moment, since modern HDDs can't even saturate SATAI.  Still, a good card and very likely to replace the SASLP over time.

Link to comment

Nice price, just a bit more than the SASLP cards.  Of course the SATAIII capabilities don't matter one iota at the moment, since modern HDDs can't even saturate SATAI.  Still, a good card and very likely to replace the SASLP over time.

 

Rajahal, have you tested the SASLP for it true max speed? Here the max combined speed I could messure was less than 600MB/s.

Link to comment

Pre-clear completed, but still doesn't report any SMART data:

 

================================================================== 1.11
=                unRAID server Pre-Clear disk /dev/sdg
=               cycle 1 of 1, partition start on sector 64 
= Disk Pre-Clear-Read completed                                 DONE
= Step 1 of 10 - Copying zeros to first 2048k bytes             DONE
= Step 2 of 10 - Copying zeros to remainder of disk to clear it DONE
= Step 3 of 10 - Disk is now cleared from MBR onward.           DONE
= Step 4 of 10 - Clearing MBR bytes for partition 2,3 & 4       DONE
= Step 5 of 10 - Clearing MBR code area                         DONE
= Step 6 of 10 - Setting MBR signature bytes                    DONE
= Step 7 of 10 - Setting partition 1 to precleared state        DONE
= Step 8 of 10 - Notifying kernel we changed the partitioning   DONE
= Step 9 of 10 - Creating the /dev/disk/by* entries             DONE
= Step 10 of 10 - Verifying if the MBR is cleared.              DONE
= Disk Post-Clear-Read completed                                DONE
Elapsed Time:  5:54:19
========================================================================1.11
==    
== Disk /dev/sdg has been successfully precleared
== with a starting sector of 64
============================================================================
No SMART attributes are FAILING_NOW


   the number of sectors pending re-allocation did not change.
   the number of sectors re-allocated did not change.
SMART overall-health status =  
root@Tower:~#

 

... and, if I invoke Smart Status from unMENU, I get:

 

SMART status Info for /dev/sdg

smartctl 5.40 2010-10-16 r3189 [i486-slackware-linux-gnu] (local build)
Copyright (C) 2002-10 by Bruce Allen, http://smartmontools.sourceforge.net

Smartctl: Device Read Identity Failed (not an ATA/ATAPI device)

A mandatory SMART command failed: exiting. To continue, add one or more '-T permissive' options.

 

However, smartctl produces a full report without any difficulty, so it would appear that preclear and unMENU are doing something odd:

 

root@Tower:~# smartctl -a /dev/sdg
smartctl 5.40 2010-10-16 r3189 [i486-slackware-linux-gnu] (local build)
Copyright (C) 2002-10 by Bruce Allen, http://smartmontools.sourceforge.net

=== START OF INFORMATION SECTION ===
Model Family:     SAMSUNG SpinPoint F3 series
Device Model:     SAMSUNG HD502HJ
Serial Number:    S20BJ90Z601039
Firmware Version: 1AJ10001
User Capacity:    500,107,862,016 bytes
Device is:        In smartctl database [for details use: -P show]
ATA Version is:   8
ATA Standard is:  ATA-8-ACS revision 6
Local Time is:    Sat May 21 11:03:44 2011 SGT
SMART support is: Available - device has SMART capability.
SMART support is: Enabled

=== START OF READ SMART DATA SECTION ===
SMART overall-health self-assessment test result: PASSED

General SMART Values:
Offline data collection status:  (0x00)	Offline data collection activity
				was never started.
				Auto Offline Data Collection: Disabled.
Self-test execution status:      (   0)	The previous self-test routine completed
				without error or no self-test has ever 
				been run.
Total time to complete Offline 
data collection: 		 (4740) seconds.
Offline data collection
capabilities: 			 (0x5b) SMART execute Offline immediate.
				Auto Offline data collection on/off support.
				Suspend Offline collection upon new
				command.
				Offline surface scan supported.
				Self-test supported.
				No Conveyance Self-test supported.
				Selective Self-test supported.
SMART capabilities:            (0x0003)	Saves SMART data before entering
				power-saving mode.
				Supports SMART auto save timer.
Error logging capability:        (0x01)	Error logging supported.
				General Purpose Logging supported.
Short self-test routine 
recommended polling time: 	 (   2) minutes.
Extended self-test routine
recommended polling time: 	 (  79) minutes.
SCT capabilities: 	       (0x003f)	SCT Status supported.
				SCT Error Recovery Control supported.
				SCT Feature Control supported.
				SCT Data Table supported.

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     0x002f   100   100   051    Pre-fail  Always       -       0
 2 Throughput_Performance  0x0026   056   056   000    Old_age   Always       -       4295
 3 Spin_Up_Time            0x0023   083   083   025    Pre-fail  Always       -       5308
 4 Start_Stop_Count        0x0032   100   100   000    Old_age   Always       -       6
 5 Reallocated_Sector_Ct   0x0033   252   252   010    Pre-fail  Always       -       0
 7 Seek_Error_Rate         0x002e   252   252   051    Old_age   Always       -       0
 8 Seek_Time_Performance   0x0024   252   252   015    Old_age   Offline      -       0
 9 Power_On_Hours          0x0032   100   100   000    Old_age   Always       -       44
10 Spin_Retry_Count        0x0032   252   252   051    Old_age   Always       -       0
11 Calibration_Retry_Count 0x0032   252   252   000    Old_age   Always       -       0
12 Power_Cycle_Count       0x0032   100   100   000    Old_age   Always       -       6
191 G-Sense_Error_Rate      0x0022   252   252   000    Old_age   Always       -       0
192 Power-Off_Retract_Count 0x0022   252   252   000    Old_age   Always       -       0
194 Temperature_Celsius     0x0002   063   058   000    Old_age   Always       -       37 (Min/Max 29/45)
195 Hardware_ECC_Recovered  0x003a   100   100   000    Old_age   Always       -       0
196 Reallocated_Event_Count 0x0032   252   252   000    Old_age   Always       -       0
197 Current_Pending_Sector  0x0032   252   252   000    Old_age   Always       -       0
198 Offline_Uncorrectable   0x0030   252   252   000    Old_age   Offline      -       0
199 UDMA_CRC_Error_Count    0x0036   200   200   000    Old_age   Always       -       0
200 Multi_Zone_Error_Rate   0x002a   100   100   000    Old_age   Always       -       0
223 Load_Retry_Count        0x0032   252   252   000    Old_age   Always       -       0
225 Load_Cycle_Count        0x0032   100   100   000    Old_age   Always       -       6

SMART Error Log Version: 1
No Errors Logged

SMART Self-test log structure revision number 1
Num  Test_Description    Status                  Remaining  LifeTime(hours)  LBA_of_first_error
# 1  Short offline       Completed without error       00%        19         -
# 2  Extended offline    Completed without error       00%        15         -
# 3  Short offline       Completed without error       00%        14         -
# 4  Short offline       Completed without error       00%        14         -
# 5  Short offline       Completed without error       00%        14         -
# 6  Short offline       Completed without error       00%        14         -

Note: selective self-test log revision number (0) not 1 implies that no selective self-test has ever been run
SMART Selective self-test log data structure revision number 0
Note: revision number not 1 implies that no selective self-test has ever been run
SPAN  MIN_LBA  MAX_LBA  CURRENT_TEST_STATUS
   1        0        0  Completed [00% left] (0-65535)
   2        0        0  Not_testing
   3        0        0  Not_testing
   4        0        0  Not_testing
   5        0        0  Not_testing
Selective self-test flags (0x0):
 After scanning selected spans, do NOT read-scan remainder of disk.
If Selective self-test is pending on power-up, resume after 0 minute delay.

root@Tower:~# 

Link to comment
I will download the alternate firmwares from the SM site, and experiment to see whether there is any noticeable change from using the IT firmware.

 

I've been unsuccessful in flashing the IT firmware - as I've posted in another thread, there seems to be some incompatibility between my mobo and the flash program.  However, since the syslog entry tells me that the card is running in IT mode, I'll ignore this for the time being.

 

I have now moved three data drives onto the L8i interface and the system rebooted and came up perfectly.  All seems to be well, except for the SMART/temperature readings in preclear and unMENU.  However, temperatures are still available in the standard browser interface.

 

Everytime a drive is spun down, I get an ioctl error in the syslog but, according to the UI, the drive is still spun down (I have each drive assigned to its own spinup group).  I'm just downloading the new test firmware to see whether the situation is resolved with Tom's latest change.

 

Anyway, as far as I can determine, the Supermicro AOC-USAS2-L8i controller is pretty well compatible with unRAID (but not with all add-ons).

 

I'm pleased that I have the Supermicro 'UIO' card layout.  The main chip/heatsink on the card does seem to get quite warm, so it's good that it is on top rather than underneath.  Also, this orientation puts the heatsink directly in line with the cpu fan in my system.  Oh, and it's also very easy to see the onboard leds for drive activity/fault, looking through the viewing panel on the side cover, or through the top fan aperture.

Link to comment
Everytime a drive is spun down, I get an ioctl error in the syslog but, according to the UI, the drive is still spun down (I have each drive assigned to its own spinup group).  I'm just downloading the new test firmware to see whether the situation is resolved with Tom's latest change.

 

I can confirm that, for me at least, all spindown problems relating to the AOC USAS2 L8i appear to be resolved with the latest 'testing' version of unRAID.

Link to comment
I have now moved three data drives onto the L8i interface and the system rebooted and came up perfectly.  All seems to be well, except for the SMART/temperature readings in preclear and unMENU.  However, temperatures are still available in the standard browser interface.

 

The reason for the SMART failures appears to be due to to the fact that the smartctl command is being issued with the device switch '-d ata'.  This appears to be accepted by standard sata devices/drivers, but the hba/mpt2sas driver appears to complain.  Leaving the device switch at auto '-d auto', or setting it to scsi to ata translation '-d sat', appears to work fine for both standard on-board sata interfaces and the hba interfaces.  I guess that '-d sat' would fail on a legacy ata/ide interface.  I wonder why preclear and unMENU use the '-d ata' switch ... I'm sure that there was a good reason!

 

Ah, on preclear, there is a -D option to supress the use of '-d ata', and a -d option to override the '-d ata' with another device type. ..... Yes, both options work fine, ie: 'preclear_disk.sh -D /dev/sdd', or 'preclear_disk.sh -d sat /dev/sdd'

 

So, the question remains ... why was the '-d ata' added?  Perhaps the default should be altered to not use '-d' on the smartctl command (which defaults to auto), and let users specify the '-d ata' option when/where necessary.

 

I'm now off to find whether there is a similar control/override for unMENU .....

Link to comment

I have now moved three data drives onto the L8i interface and the system rebooted and came up perfectly.  All seems to be well, except for the SMART/temperature readings in preclear and unMENU.  However, temperatures are still available in the standard browser interface.

 

The reason for the SMART failures appears to be due to to the fact that the smartctl command is being issued with the device switch '-d ata'.  This appears to be accepted by standard sata devices/drivers, but the hba/mpt2sas driver appears to complain.  Leaving the device switch at auto '-d auto', or setting it to scsi to ata translation '-d sat', appears to work fine for both standard on-board sata interfaces and the hba interfaces.  I guess that '-d sat' would fail on a legacy ata/ide interface.  I wonder why preclear and unMENU use the '-d ata' switch ... I'm sure that there was a good reason!

 

Ah, on preclear, there is a -D option to supress the use of '-d ata', and a -d option to override the '-d ata' with another device type. ..... Yes, both options work fine, ie: 'preclear_disk.sh -D /dev/sdd', or 'preclear_disk.sh -d sat /dev/sdd'

 

So, the question remains ... why was the '-d ata' added?  Perhaps the default should be altered to not use '-d' on the smartctl command (which defaults to auto), and let users specify the '-d ata' option when/where necessary.

 

I'm now off to find whether there is a similar control/override for unMENU .....

The "-d ata" option WAS mandatory at one point. Apparently smartctl has evolved to where it now works without it on some hardware.

 

I'll have to see if it works on my older server without it.  Obviously, a config variable is in order.

 

Joe L.

Link to comment
The "-d ata" option WAS mandatory at one point.

 

Was this on sdx devices or only on hdx devices?  I can't see why the "-d ata" should have ever been needed for sata drives.

 

If, as I suspect, it was only needed on pata devices then, perhaps, it should be made dependent on the device type (hdx/sdx) specification.

Link to comment

I'm confused.  Are you using some beta version of preclear?

 

Not that I'm aware of.

 

The current version is 1.9, yet you appear to be using version 1.11.

 

I'm using the version I downloaded from here.

 

Nevermind, I misread the preclear thread.  My mistake.

Link to comment
So, the question remains ... why was the '-d ata' added?  Perhaps the default should be altered to not use '-d' on the smartctl command (which defaults to auto), and let users specify the '-d ata' option when/where necessary.

 

I'm now off to find whether there is a similar control/override for unMENU .....

 

As an experiment, I've commented out all the occurrences of '-d ata' from the unMENU code.  As far as I can tell, this has made unMENU and the LSI SAS2008 based controller fully compatible (or is it the mpt2sas driver?) - I now get temperatures reported and I can successfully obtain SMART reports.

Link to comment

Do you know which controller is compatible with 3TB drives?

 

I found this posted on the Australian Overclockers forum:

I also emailed Supermicro support and they confirmed the AOC-USAS-L8i (LSI 1068E) does NOT support 3TB drives but the AOC-USAS2-L8i will (LSI SAS2008).

 

From this, I take it that any of the SAS2008-based cards should support drives over 2.2TB.  Perhaps, in a couple of years, I'll be able to obtain a 3TB drive in Philippines, and test it out!  OTOH, if anyone would like to send me a drive, I'll report back!

Link to comment

Is there a difference between IBM ServeRAID BR10i SAS/SATA Controller models:

 

Model Number: 44E8688

Model Number: 44E8689

Model Number: 44E8690

 

??

 

Will these boards also work as at slower link PCIe x4 although defined as PCIe x8.

 

Link to comment
  • JorgeB unpinned and locked this topic
Guest
This topic is now closed to further replies.