Need an opinion on this offer

I have started to have issues with my SAS2LP cards, so went looking for a replacement.

I found the following offer:

http://www.ebay.ca/itm/IBM-M1015-46M0831-46C8933-PCI-e-Serial-ATA-300-SAS-LSI-9220-8I-LSI-9211-8I-/271971476950?hash=item3f52c365d6&autorefresh=true

The seller is agreeing to sell me 2 for $80USD each.

Can someone with a better understanding of these cards advise if there is any reason I shouldn't buy them? I don't know if there is any variation in these cards and want to make sure this is a good investment.

I am hoping someone knowledgeable can comment fairly quickly if possible.

Thanks in advance!

Sounds like a good price ... and the M1015's are very well thought of by those who are using them in UnRAID.

Personally I don't have any ... but wouldn't hesitate to buy them if I needed more ports.

I've heard that there are counterfit M1015's out there. Ask for serial #'s and email LSI to verify they are the real deal.

I have started to have issues with my SAS2LP cards, so went looking for a replacement.

What issues? The M1015 is a great card, but your statement indicates you think your two cards are no good. That makes me think there is something wrong which may not be solved by new cards. It is unlikely you have two bad cards at once.

While I don't use the SAS2LP, I would not suggest removing them without reason.

Found your thread http://lime-technology.com/forum/index.php?topic=42666.msg406633#msg406633

related http://lime-technology.com/forum/index.php?topic=42594.0

It's not clear if the trouble is a card or drive(s). Do you have a SAS expander?

I am leaning towards driver issue, because the two cases only share software. You can run from the bug by swapping to different hardware.

I have started to have issues with my SAS2LP cards, so went looking for a replacement.

 

What issues? The M1015 is a great card, but your statement indicates you think your two cards are no good. That makes me think there is something wrong which may not be solved by new cards. It is unlikely you have two bad cards at once.

 

While I don't use the SAS2LP, I would not suggest removing them without reason.

 

Found your thread http://lime-technology.com/forum/index.php?topic=42666.msg406633#msg406633

related http://lime-technology.com/forum/index.php?topic=42594.0

 

It's not clear if the trouble is a card or drive(s). Do you have a SAS expander?

 

I am leaning towards driver issue, because the two cases only share software. You can run from the bug by swapping to different hardware.

What has caused me to reconsider using the cards is two fold:

1) The issue from a few days ago you found

2) I had an issue a few months ago of multiple drives going "bad" or offline. I was in a bit of a panic thinking I had multiple failed drives, and after a couple of reboots they came back online fine and I've not had an issue since (until a few days ago).

I do understand that it's likely only one of my two cards that has gone bad, but if I am swapping one out I would rather just replace them both. I am also near capacity on both cards and will soon be looking for a third card. I am thinking of just buying three of the M1015s and be done with it.

As to your question on the SAS expander, no I don't. I have 14-15 drives across 4 backplanes on my Norco 4224 with 4 drives (or one backplane) on each port of the SAS2LPs.

I have started to have issues with my SAS2LP cards, so went looking for a replacement.

 

What issues? The M1015 is a great card, but your statement indicates you think your two cards are no good. That makes me think there is something wrong which may not be solved by new cards. It is unlikely you have two bad cards at once.

 

While I don't use the SAS2LP, I would not suggest removing them without reason.

 

Found your thread http://lime-technology.com/forum/index.php?topic=42666.msg406633#msg406633

related http://lime-technology.com/forum/index.php?topic=42594.0

 

It's not clear if the trouble is a card or drive(s). Do you have a SAS expander?

 

I am leaning towards driver issue, because the two cases only share software. You can run from the bug by swapping to different hardware.

 

What has caused me to reconsider using the cards is two fold:

 

1) The issue from a few days ago you found

2) I had an issue a few months ago of multiple drives going "bad" or offline. I was in a bit of a panic thinking I had multiple failed drives, and after a couple of reboots they came back online fine and I've not had an issue since (until a few days ago).

 

I do understand that it's likely only one of my two cards that has gone bad, but if I am swapping one out I would rather just replace them both. I am also near capacity on both cards and will soon be looking for a third card. I am thinking of just buying three of the M1015s and be done with it.

 

As to your question on the SAS expander, no I don't. I have 14-15 drives across 4 backplanes on my Norco 4224 with 4 drives (or one backplane) on each port of the SAS2LPs.

Can easily be a backplane in the Norco 4224, but my prime suspect is the driver.

Can easily be a backplane in the Norco 4224, but my prime suspect is the driver.

If it was a driver issue wouldn't everyone with the same card, using the same drive, run risk of similar issues?

Can easily be a backplane in the Norco 4224, but my prime suspect is the driver.

 

If it was a driver issue wouldn't everyone with the same card, using the same drive, run risk of similar issues?

Depends if its cpu constrained or not, as some users with single core cpu are seeing 100% cpu usage and slower speeds when previously speeds were fine and lower usage around 50% or so.

I'd think so.    The issues with the SAS2LP are indeed very strange => some work fine; others have the slowdown issue.

Did you get a chance to try connecting a standard monitor to the server just to see if having that connection had any impact?    Not a solution ... but might provide a clue that could help resolve this if it is indeed an issue with the interrupt controller (as some have suggested).

I'd think so.    The issues with the SAS2LP are indeed very strange => some work fine; others have the slowdown issue.

 

Did you get a chance to try connecting a standard monitor to the server just to see if having that connection had any impact?    Not a solution ... but might provide a clue that could help resolve this if it is indeed an issue with the interrupt controller (as some have suggested).

I don't remember seeing the suggestion. To be clear, am I just hooking up the monitor to review what's being output? Or is that actually supposed to influence behavior?

For me I am assuming I am not CPU constrained. I am running a Xeon processor with 6-7 Dockers and no VMs.

Just hooking up a monitor to see if the behavior changes.    I forget exactly where it was mentioned -- perhaps not in your thread -- but it seems the issue with the SAS2LP may be related to incorrect interrupt handling; and it is apparently different based on whether or not there are display interrupts ... so having a connected display can make a difference.

Can easily be a backplane in the Norco 4224, but my prime suspect is the driver.

 

If it was a driver issue wouldn't everyone with the same card, using the same drive, run risk of similar issues?

Check out 6.1.1, it has a change which could impact the mv_94xx driver.

Can easily be a backplane in the Norco 4224, but my prime suspect is the driver.

 

If it was a driver issue wouldn't everyone with the same card, using the same drive, run risk of similar issues?

Check out 6.1.1, it has a change which could impact the mv_94xx driver.

I've installed it, and am already running a parity check to see.

Here are the results so far:

Total size: 6 TB

Elapsed time: 3 hours, 1 minute

Current position: 1.24 TB (20.6 %)

Estimated speed: 107.7 MB/sec

Estimated finish: 12 hours, 17 minutes

Sync errors corrected: 20

I expect it to dip though and end up around the same as before.

I've gone ahead and bought the 3 M1015 cards anyways to be safe, and will swap these out and resell them. I have had enough issues (as evidenced by the 20 sync errors corrected already which are likely screwing up some of my TV shows).