bkastner

Nothing gets changed until the very end when it asks you to change values, and then confirm. You are safe. For what it's worth I re-downloaded the txt file in the first post, and using notepad I did a search and replace of /root/mdcmd to the new path, saved it to my flash drive and then ran the script.

I had previously been getting around 95MB/sec parity check on my SAS2LP cards. I just swapped them out for M1015s and ended up with 82.6MB/sec, so decided to run the tunables script to optimize. When I ran, I got the following: Test | num_stripes | write_limit | sync_window | Speed --- FULLY AUTOMATIC TEST PASS 1 (Rough - 20 Sample Points @ 3min Duration)--- 1 | 1408 | 768 | 512 | 118.0 MB/s 2 | 1536 | 768 | 640 | 118.2 MB/s 3 | 1664 | 768 | 768 | 118.2 MB/s 4 | 1920 | 896 | 896 | 118.2 MB/s 5 | 2176 | 1024 | 1024 | 118.2 MB/s 6 | 2560 | 1152 | 1152 | 118.2 MB/s 7 | 2816 | 1280 | 1280 | 118.2 MB/s 8 | 3072 | 1408 | 1408 | 118.2 MB/s 9 | 3328 | 1536 | 1536 | 118.2 MB/s 10 | 3584 | 1664 | 1664 | 118.2 MB/s 11 | 3968 | 1792 | 1792 | 118.2 MB/s 12 | 4224 | 1920 | 1920 | 118.2 MB/s 13 | 4480 | 2048 | 2048 | 118.2 MB/s 14 | 4736 | 2176 | 2176 | 118.2 MB/s 15 | 5120 | 2304 | 2304 | 118.2 MB/s 16 | 5376 | 2432 | 2432 | 118.2 MB/s 17 | 5632 | 2560 | 2560 | 118.2 MB/s 18 | 5888 | 2688 | 2688 | 118.2 MB/s 19 | 6144 | 2816 | 2816 | 118.2 MB/s 20 | 6528 | 2944 | 2944 | 118.2 MB/s --- Targeting Fastest Result of md_sync_window 640 bytes for Final Pass --- --- FULLY AUTOMATIC TEST PASS 2 (Final - 16 Sample Points @ 4min Duration)--- 21 | 1424 | 768 | 520 | 118.2 MB/s 22 | 1440 | 768 | 528 | 118.2 MB/s 23 | 1448 | 768 | 536 | 118.2 MB/s 24 | 1456 | 768 | 544 | 118.2 MB/s 25 | 1464 | 768 | 552 | 118.2 MB/s 26 | 1472 | 768 | 560 | 118.2 MB/s 27 | 1480 | 768 | 568 | 118.2 MB/s 28 | 1488 | 768 | 576 | 118.2 MB/s 29 | 1496 | 768 | 584 | 118.2 MB/s 30 | 1504 | 768 | 592 | 118.2 MB/s 31 | 1520 | 768 | 600 | 118.3 MB/s 32 | 1528 | 768 | 608 | 118.2 MB/s 33 | 1536 | 768 | 616 | 118.3 MB/s 34 | 1544 | 768 | 624 | 118.2 MB/s 35 | 1552 | 768 | 632 | 118.3 MB/s 36 | 1560 | 768 | 640 | 118.3 MB/s Completed: 2 Hrs 9 Min 43 Sec. Best Bang for the Buck: Test 1 with a speed of 118.0 MB/s Tunable (md_num_stripes): 1408 Tunable (md_write_limit): 768 Tunable (md_sync_window): 512 These settings will consume 126MB of RAM on your hardware. Unthrottled values for your server came from Test 31 with a speed of 118.3 MB/s Tunable (md_num_stripes): 1520 Tunable (md_write_limit): 768 Tunable (md_sync_window): 600 These settings will consume 136MB of RAM on your hardware. This is -422MB less than your current utilization of 558MB. NOTE: Adding additional drives will increase memory consumption. It looks really odd that all the values are virtually identical. Does this make sense? Is there a potential issue? I wasn't necessarily expecting dramatic variations, but did expect some differences. Also, as a suggestion... it would be great if the tunables text file including the current settings for the 3 variables in it's output so they can be easily referenced again. I wasn't smart enough to write them down before making the change, but would like to have had this documented for reference in case of an issue.

I don't think everyone that has the SAS2LP card(s) have the slow parity check issue. Not sure if that's been confirmed, but Lime-Tech did respond previously in this thread and said they were able to duplicate the slow parity check speeds. I had two SAS2LP cards with a max of 60MB/sec parity check speeds. Replaced those two cards with the Dell H310 HBA card and jumped to over 110MB/sec. I'm done playing for a little bit and want to spend more time enjoying the content on the drives. No, not everyone experiences the slow parity issues, however when I posted my 95MB/sec it was suggested this is still sub-par. I honestly didn't care, and only swapped them out because one of my cards crashed and I ended up with some corrupted data (my own fault, but still). I just wanted to let people know that if they are getting 90-105MB/sec there is likely nothing wrong with the cards, and you are not really going to see an improvement by swapping them out. Some scenarios will give 150MB/sec or higher, but there are a number of other factors than just the controllers that play into this.

I wanted to provide an update on my situation. I was not one of the users who had real performance issues with the cards, but did have drives go offline after one of my controllers crashed, and so I decided to swap out my SAS2LP cards with M1015 cards. While I was getting around 95 MB/sec on an overall parity check there were a few comments that this was still not great and should have been better. I've run 5 minute tests on the SAS2LP card and the new M1015s: SAS2LP Total size: 6 TB Elapsed time: 5 minutes Current position: 32.7 GB (0.5 %) Estimated speed: 111.6 MB/sec Estimated finish: 14 hours, 51 minutes M1015 Total size: 6 TB Elapsed time: 5 minutes Current position: 40.6 GB (0.7 %) Estimated speed: 119.2 MB/sec Estimated finish: 13 hours, 53 minutes As you can see there is a bit of a speed pickup, but it does fluctuate (as I am sure the SAS2LP did). I will post final parity check results as well once complete, and then I am going to re-run tunables to see what it does. For this initial test I did nothing but replace the cards and cables (the originals were too short). However, on the surface, it appears that based on my system and drives I was pretty close to where I should be on the SAS2LP cards.

For TV shows I let SAB/SB manage, but movies I manage manually. I tend to vet each movie to ensure it's English language default and strip other languages and sub titles. For these I use Media Companion to scrape. I do this so that I can confirm each movie is identified correctly as well as I can add backgrounds for those movies missing them as well as set tags on some movies. I use Kodi on the TVs at home and have a filter for movies for my daughter. I use MC to set the tag so that they get caught by the filter. MC is free and continuously updated, which is great. I've had a few issues over the years but have been able to report to the developer and work with them to resolve. It's worked great for me.

I don't think so. Many, including myself, were getting 95-100MB/sec with these cards.

How are you trying to get there? For me it is Main->Cache Devices, and then click on Cache and finally the Attributes tab. It eventually showed up. It seems current pending sectors were delaying it showing any of the smart sections for a while, not even the headers with the retrieving information message. That's not a good sign, for that drive! Try a SMART short test. If it shows SMART has not failed, take it offline (unassign as Cache drive) and Preclear it a couple of times. Out of curiosity - would it be valuable to schedule monthly SMART short tests on drives and send notifications - or something along those lines? Would this help give us a heads up if a drive is starting to have issues before it actually causes a drive failure? I don't remember if anything like this exists, and have done zero research - just an idea off the top of my head, so thought I would post before it slips away.

I missed that, but it sounds like a special case of the SAS2LP issue, an extreme case! You actually helped me diagnose this specific issue: http://lime-technology.com/forum/index.php?topic=42666.0

Before you do anything you should post diagnostics. I had the same issue - one drive fell offline while doing a parity check testing for this issue. I ran SMART tests which were all fine on the drive, and it was suggested I remove the drive, start the array, stop the array and re-add the drive to get it rebuilt. I posted diagnostics as requested, but got impatient and started the rebuild. Diagnostics ended up saying the SAS2LP card crashed and forced the drive offline. It also started "correcting parity" I would have been better to re-add the drive and do a new config, but had started the rebuild. I ended up with 28 parity corrections which may have written bad data to my drive instead of trusting the data that was on it. It's 4TB of TV shows, so hundreds of episodes, and I have no idea where the potential corruption is. This was the final straw that caused me to look at another controller. I can handle slower parity checks (though again mine are not bad), but controller crashes, drives being thrown offline, potential data loss... these I can't handle.

Once I get the new cards flashed and installed I will run a new parity check and post the results. I am rather curious now to see the difference as well. If I can't get the two Dell H310's at work they are on Ebay brand new shipped from the US from a good reputable vendor. BTW, where are you grabbing the IBM M1050's from? I am getting them from ebay: 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 I offered the guy $80USD/per for 3 and he accepted. I only had to pay shipping once for the 3 cards, with tracking, so it ended up being $255USD for the 3 cards. He was selling 7, and still has 3 available. I am supposed to get them on Thursday, so I can confirm if they are good once I have them in my hands. I know it's a risk (someone mentioned there are fake ones out there), but with ebay, paypal and AMEX protection I figured I was covered in case something went wrong. Good deal. $80 for three, when he is selling them each for $95? Can't beat that. I'd rather have the SAS connectors at the rear of the card instead of pointing up in the air. I agree, but since I am in a Norco 4224 case I have a ton of head space, so am not too concerned there. I could see it being an issue with smaller cases though as those SAS connectors only have so much give and having to do a quick 90 degree turn in a small case could be frustrating. And for clarity it's $80 per card, not $80 for three (just in case someone else tries to hit him up for some of the remaining and is expecting an insane deal).

6.1.1 Getting about 20MB/sec right now at 47% complete. Is this issue new to 6.1.1? Or were you having issues on 6.1 (or 6.0.1 if you were running that).

Others can likely comment better, but it appears to be primarily a SAS2LP issue. Some reported much better success with the SASLP and moving to the SAS2LP card introduced the slow downs. Out of curiosity, are you on 6.1 or 6.1.1? There was a "fix" or feature removal in 6.1.1 that was supposed to help with the issue, though I didn't see any real difference personally - though I appear to be on the high-end of the scale with minimal slow-down compared to many others.

Once I get the new cards flashed and installed I will run a new parity check and post the results. I am rather curious now to see the difference as well. If I can't get the two Dell H310's at work they are on Ebay brand new shipped from the US from a good reputable vendor. BTW, where are you grabbing the IBM M1050's from? I am getting them from ebay: 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 I offered the guy $80USD/per for 3 and he accepted. I only had to pay shipping once for the 3 cards, with tracking, so it ended up being $255USD for the 3 cards. He was selling 7, and still has 3 available. I am supposed to get them on Thursday, so I can confirm if they are good once I have them in my hands. I know it's a risk (someone mentioned there are fake ones out there), but with ebay, paypal and AMEX protection I figured I was covered in case something went wrong.

Once I get the new cards flashed and installed I will run a new parity check and post the results. I am rather curious now to see the difference as well.

As a side note, any time you are looking at buying/replacing a CPU it's worth checking out http://www.cpubenchmark.net/ This site rates every CPU on the planet and allows you to compare relative performance between CPUs to understand how much faster a given CPU is, and whether it's worth the cost increase. It takes all the guess work out of buying a new CPU as you will know exactly how much faster it is than your current one (or others you are comparing against). Any time I am buying a CPU I set a rough budget and then use this site to determine which CPU to purchase. the only thing it doesn't show you is CPU feature sets, so I use ark.intel.com for that (since I only buy Intel). AMD likely has a similar site to detail CPU features. This may also help with garycase's suggestion. If you can find a Haswell cpu/board that gives good bang for the buck it may be a worthwhile investment.

I am XFS across the board, and completed a parity check this morning after upgrading to 6.1.1 Last checked on Mon 07 Sep 2015 08:45:41 AM EDT (today), finding 28 errors. Duration: 17 hours, 33 minutes, 40 seconds. Average speed: 94.9 MB/sec This was my one on 6.1.0 on Sept 1st: Last checked on Tue 01 Sep 2015 05:45:14 PM EDT (yesterday), finding 0 errors. Duration: 17 hours, 45 minutes, 13 seconds. Average speed: 93.9 MB/sec So, fractionally faster, but not much. I have M1015s that will arrive later this week. Once I swap them out I will do another parity check and see how it goes with only swapping out the controllers.

I'm sorry, I've long been financially limited, never had a SAS card, so no help at all to you. Hopefully others will have advice. I'm also hoping damage was light or non-existent (as in only some unused disk space affected)? Thanks Rob. I had 100MB free on a 4TB drive, so am doubtful I will be that lucky. Also, it was entirely TV episodes, so who knows when I will stumble across the corrupted files (if I ever do). It's life, and mostly self-inflicted, so life just moves on. I appreciate your assistance and willingness to help.

Now that's interesting! We recently had a user (3blackdots) with a 9485 that had the Marvell bug (no drives seen), post is here with my bug confirmation after it. A few posts up, user opentoe had a 9480 where the drives showed up, but parity checks were very slow, summary post is here. This seems like 2 strikes against Marvell now. Would it be useful to get them involved? Their reputation is at stake here, going to 'strike out' with unRAID users, if they can't give us a correction/patch or configuration change. Ironic. Without even seeing these posts yet I started a parity check earlier. I stopped it since it was going terribly slow. 60MB/sec or less. Should be in the 100+ range on my system. I have two SAS2 cards. All drives on both cards. Not using any of the mainboards SATA connections. Right now I'm running that tunable script so I don't want to touch the server. Both cards are attached to Norco 4224 blackplanes. I would even buy a couple other brand cards, but if I do that would want to get, compatible and good performing cards. Even for test purposes I would do it, but need to find the cards available somewhere online. I have a nearly identical setup to you and just bought 3 M1015 cards to replace my 2 SAS2 cards (which were almost full). I've had better experience than most with the SAS2LP cards, but it's at a point of minor issues (the last likely causing data issues as I got impatient), so I am done with the cards. I found M1015 cards in Canada for $80US/piece so took the plunge. Even with the exchange rate it's still a pretty good deal I think.

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).

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.

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

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. 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!

No, there is no one to blame but myself. I just get impatient. Honestly, I appreciate all that you and the other moderators and helpful forum members do. So, since I am now 26.5% into the rebuild, should I just let it finish? Also, if I was to look to replace the SAS2LP cards, what would you suggest? I've seen a lot of comments around the M1015 as a preferred card, but wanted to confirm if that would be the recommended replacement. I've had pretty good luck with the SAS2LP cards so far, but with other people's issues, and now my flakiness I think I want to look into another card that can manage 8 drives (per card). I'd appreciate any suggestions you may have.

Ahh... crap. So, I waited for a few hours, but not knowing how long it would take for someone to review my logs I got impatient and started the rebuild as per the original suggestion. I wasn't expecting this result. I am 15.6% into the rebuild as of this moment, so am guessing I am committed to it. This card is actually the 9480 card (I had posted details in the SAS2LP thread on my cards and both were 9480s). This sucks....