Jomp

It's just ok at cooling drives ~35-45C when parity checking. I'm trying new fans this weekend, I'll let you know if it makes any difference.

I missed this, but it pretty much confirms the testing so far. Keep your drives from using the Marvell's exclusively and things are ok.

A parity check will be run, absolutely! I'm really putting it though some torture testing before I put data on it. After data starts going on it, like I said, MD5 checks will be made. In terms of number 2, the ASRock tech ran a windows test with my exact hard drive and on the problematic Marvell 9230, hammering the drive with I/O and then ran SMART tests with no problem. Just another datapoint.. I think many of us realize that this could be one of the best NAS boards to come around in some time! We're in the early days with it, so some growing pains seem acceptable. That being said, I think my issues were pretty isolated and specific.

I'm really looking forward to seeing the protected array speeds in the morning. The syslog looks perfect so far!

I do have smartctl enabled now! The case fans are 3 pin, so only voltage controllable, which the board doesn't do. I ordered some 4 pin PWM fans that will be controllable through the board's BIOS.

The ASRock tech seems to think its a Marvell Linux driver issue, so I don't think it's being escalated. I wouldn't hold out for a BIOS update.. I'm not 100% sure though.. I'm pretty tired from all the cable swapping, so I didn't try just 2 drives in 9230 or 1 in 2550 and 3 in 9230, etc. I'm optimistic that all 12 sata ports will work fine, it's just using the 9230 ports exclusively that seems to bring out the issues. The plan is putting 6 drives on the 2550 and 2 on the 9230 as I transfer data over and put the other 4 currently full drives in the array over the next weeks. I'm putting in 3 quieter fans and finishing the cabling this weekend. I'm tired of messing with it and I'm ready to use it!

I have Aggressive Link Power Management and Hot Swap enabled, so far with no issues. I'm obviously watching everything like a hawk, but so far so good. What errors were they giving you?

I tried SMART enabled/disabled. It made no difference. Here we go folks, solved! All these tests were done with all 4 drives doing extensive disk I/O and then SMART polling the 4 drives. I plugged 4 drives into the Intel C2550 controller, no SATA link resets/SMART read failures, works perfectly. I plugged 3 drives into Intel C2550 and 1 into Marvell SE9230, no SATA link resets/SMART read failures, works perfectly. I plugged 3 drives into Intel C2550 and 1 into Marvell SE9172, no SATA link resets/SMART read failures, works perfectly. I plugged 4 drives into Marvel SE9230, SATA link resets/SMART read failures, errors. Weird edge case, I guess. I heard back from ASRock, they didn't get back to me since they were trying to bench test the problem to replicate it. They have been responsive and awesome since then, trying to replicate it. I'm really pleased with their response, I was too quick to jump on them. This board is now a recommend from me, just don't plug your drives only into the Marvell SE9230 controller! *One caveat being I don't know what happens when all 6 Intel C2550 and all 4 Marvel SE9230 SATA ports are filled up.

Updates! So today I'm moving the drives over to the Intel chipset which doesn't appear to have the SMART bug. Since it's an 8 bay case and only 6 SATA ports are on the Intel chipset, I'll still have 2 drives on the problematic Marvell chipset. I've found that if I delete smartctl on boot up, I have no SATA reset problems, since the drives aren't being polled for SMART data by the GUI. I'm going to put smartctl on my flash drive and run it from the console only when the drives have no I/O activity. Not ideal, but a workaround none the less! I submitted a tech support request detailing my findings to ASRock, but since they don't use a ticket system, I don't know if they got it/are working on it, and I also can't add my information about it occurring on other operating systems as well. Overall, a really frustrating problem. The board itself has great performance, ECC, IPMI, 12 SATA ports, but the silly SMART problem prevents me from fully recommending it for Unraid use until (hopefully) a BIOS update comes along to fix the problem. Thankfully all my files are MD5 hashed, so I'll be keeping a close eye over everything in the coming months. I'll get some power readings after I get all 8 drives installed over the next week, since that was requested.

I installed FreeNAS (FreeBSD) and when writing to the array and issuing SMART commands, I got SMART timeouts. So there appears to be some problems with the Marvell controllers on the C2550D4I.

Force NCQ disable did not fix it. All the Marvell settings that I could find were under the Advanced tab. I can't find a way to edit hot swap or aggressive link on the marvells, just on the intel controller under the southbeidge menu.

All the drives are on the Marvels. I can't find many Marvel sata settings. You can enable/disable SMART, set sata/IDE mode on two of the ports and that's about it. The Intel sata has far more options.

When I transfer a file to the protected array and use the menu at the same time, I'm getting sata resets. So there we have it, any disk activity and the use of webgui causes sata link resets.

To those following this train wreck, here is what I posted in my support thread: To add some more datapoints: It happens during a parity check as well. Pretty much any parity operation with reads or writes combined with menu activity causes sata resets. I tried Dynamix and it freezes sata links on every page load versus the more intermittent limetech webgui. Is it something with the SMART queries during high use operations? These are the controllers giving me issues: Marvell SE9172: 2 x SATA3 6.0 Gb/s - Marvell SE9230: 4 x SATA3 6.0 Gb/s I'll try menu presses during a protected write next to see if a less intense I/O operation causes the sata resets.

To add some more datapoints: It happens during a parity check as well. Pretty much any parity operation with reads or writes combined with menu activity causes sata resets. I tried Dynamix and it freezes sata links on every page load versus the more intermittent limetech webgui. Is it something with the SMART queries during high use operations? These are the controllers giving me issues: Marvell SE9172: 2 x SATA3 6.0 Gb/s - Marvell SE9230: 4 x SATA3 6.0 Gb/s I'll try menu presses during a protected write next to see if a less intense I/O operation causes the sata resets.

Four drives on one controller shouldn't be causing link resets. It's also happening regardless of SATA cables. I think it has something to do with the intense writing/reading during the sync, rather than just a check. It's a weird one. I'll let this sync complete and see if it happens during a parity check. I'm narrowing it down!

I have a weird one. During my build (http://lime-technology.com/forum/index.php?topic=32647.15), everything went great on my first parity sync that I ran overnight. The next day, I decided to run another one and I got SATA link reset errors. I changed cables and they were still occurring. So through a process of elimination and a little but of luck, I narrowed it down to the webgui, of all things. So if I start a parity sync and leave everything alone, it will complete without any SATA link resets. If I start a parity sync and pull up the webgui, and click between the tabs on the menu bar (Main, Users, Settings, Utilities) it will eventually freeze the webgui for ~10 seconds and the log will show a SATA hard link reset. Sometimes it takes ~3 tab clicks, sometimes up to ~20. Weird. What in the heck could be going on? Edit: It happens on 5.0.5 and 6.0beta 4 log4.txt

Ok, so here is a weird datapoint and I think the root cause. I didn't touch anything for ~20 minutes while the parity sync is running and no sata resets (like when I let the parity sync run over night) but when I start refreshing things in the webgui during a parity sync (clicking between different tabs like settings, users, etc) boom, the webgui freezes for many seconds and sata resets. Strange. *Edit after more testing: It happens in both 5.0.5 and 6.0 Beta 4. Everything is solid with no sata resets until I start clicking around the webgui during a parity sync and then like magic, sata resets. I don't think it's related to cables at all. dmacias, can you click around the webgui dusting a parity sync and see if you can replicate this on your board?

Not good. With the OEM asrock cables, I'm still getting resets, ideas? log3.txt

I'm getting them on multiple drives, the Marvell 6.0G controller. I'm using the OEM cables now, running a parity sync. These were the newegg cables: http://www.newegg.com/Product/Product.aspx?Item=N82E16812422635 It turns out the monoprice cables are printed the same, had the same connectors, so I didn't even try them.

I'm getting these resets too, which is causing problems, obviously. I'm using these: http://www.newegg.com/Product/Product.aspx?Item=N82E16812422635 Trying these monoprice cables that I have next. http://www.monoprice.com/mobile/Product/Details/8778

Ewww. Parity sync threw write errors all over the place, unlike the first time. SMART is fine on the drive throwing the errors. I'm disabling hot swap like previously advised and retying. log2.txt

I've attached the log. So far, everything seems to be in line and the C2550D4I is working great. The only thing I changed in BIOS was to disable Aggressive Link Power Management. I'm running one more parity sync and then I'll write some files to the protected array to check out protected speeds later today. Any requests in terms of the motherboard? 4x4TB parity sync: md: sync done. time=30933sec log.txt

Cruising! I'll update with the total party sync speed tomorrow, upload the log, test real-world transfer speeds, etc..