klamath Posted July 10, 2017 Share Posted July 10, 2017 Just now, Hannibal said: Are yours dual port cards or single? And idk if you checked the link i posted... But idk what the likely hood of me getting two junk cards would be... single port, i tired to find more info on your card, seems to be only sold via that newegg link or one seller on amazon. Wondering if these are white label cards or resold tooling to other ODMs: https://www.linkedin.com/pulse/several-popular-models-10gbe-cnanic-hilda-hu Quote Link to comment
Hannibal Posted July 10, 2017 Author Share Posted July 10, 2017 Hmm... Not sure i read over that link... Would it be a bad idea if i just switched over to Intel SFP+ cards? or should i just pick up that lot of two mellanox cards and then the fiber cable and transceivers? Quote Link to comment
klamath Posted July 10, 2017 Share Posted July 10, 2017 33 minutes ago, Hannibal said: Hmm... Not sure i read over that link... Would it be a bad idea if i just switched over to Intel SFP+ cards? or should i just pick up that lot of two mellanox cards and then the fiber cable and transceivers? Id pick up those cards i linked on amazon, intel cards would work they just cost a pretty penny. Tim Quote Link to comment
Hannibal Posted July 10, 2017 Author Share Posted July 10, 2017 (edited) Sorry for the bad quality but i had to take this picture with my phone... This happened when there was no twinax cable connected... you can see it in the error it lists mlx4 which is my mellanox card.... Or i now notice it says usb disconnected im wondering if this is possibly being caused by my thumb drive unraid is installed on? or maybe it was referring to my keyboard since thats the only other usb device connected.... Edited July 10, 2017 by Hannibal Quote Link to comment
Hannibal Posted July 10, 2017 Author Share Posted July 10, 2017 Or could it possibly be the motherboard since it specifically lists my mobo under hardware name? Im at a very novice level when it comes to linux and code like this so its hard for me to determine the cause of this call trace... Quote Link to comment
klamath Posted July 10, 2017 Share Posted July 10, 2017 The fact it points out nat, mlx4 and a bunch of networking functions points to a spinlock of some kind trying to access the hardware. Seems that you are not the only one having issues: https://www.google.com/search?q=Mellanox+6801-M+crashing&oq=Mellanox+6801-M+crashing&aqs=chrome..69i57.6512j0j7&sourceid=chrome&ie=UTF-8#q=mellanox+6801-m+cable+unplugged Id return those cards and buy the used ones from amazon or intel cards. I get the feeling those might be shitty knock offs or they are cheaply manufactured cards with mellanox chipset thrown on. either way shit seems pretty broke, last ditch id still recommend ubuntu live boot and see if the problem carries over. Tim Quote Link to comment
Hannibal Posted July 10, 2017 Author Share Posted July 10, 2017 (edited) I'm actually on Ubuntu now and after I login everything freezes I can't access anything or do anything... Idk if this is due to the cards or some other issue... Edited July 10, 2017 by Hannibal Quote Link to comment
klamath Posted July 10, 2017 Share Posted July 10, 2017 Just one last hail mary, you might want to disable tso,gso etc from the card, just to rule out any type of offloading. something like this: #ethtool -K eth0 rx off tx off sg off tso off ufo off gso off gro off lro off Quote Link to comment
Hannibal Posted July 10, 2017 Author Share Posted July 10, 2017 (edited) Alright, I'm more then likely gonna order different cards as well... When I contacted the seller for refund they're English when typing was extremely broken so I think those cards came straight from China or something... I'll either go with those ones you linked or I found Intel ones for 125 a pop not sure if I wanna pay that much per card though... I just want these issues gone and my 10gb connection to work without issue... Just out of curiosity if I just got a 4 port gigabit nic and set it up for link aggregation would they're be any benefit or is 10gb nic the only way to go for large file dumps to the server? Edited July 10, 2017 by Hannibal Quote Link to comment
klamath Posted July 10, 2017 Share Posted July 10, 2017 Id hit that amazon store up, since those cards came from working servers it will assure you the things worked for a while without issue, and you cant really say no to $40. Tim Quote Link to comment
klamath Posted July 10, 2017 Share Posted July 10, 2017 1 hour ago, Hannibal said: Alright, I'm more then likely gonna order different cards as well... When I contacted the seller for refund they're English when typing was extremely broken so I think those cards came straight from China or something... I'll either go with those ones you linked or I found Intel ones for 125 a pop not sure if I wanna pay that much per card though... I just want these issues gone and my 10gb connection to work without issue... Just out of curiosity if I just got a 4 port gigabit nic and set it up for link aggregation would they're be any benefit or is 10gb nic the only way to go for large file dumps to the server? LAG is the shittiest thing ever, TCP cannot be stripped over multiple lines unless your doing round robin and if you have a out of order packet your shit is toast, RR isnt LACP compliant. TLDR, LAG is total shit for two node communication. You can do some stuff with multiple IPs and sharding of connections but for $40 is not worth it! Tim Quote Link to comment
Hannibal Posted July 10, 2017 Author Share Posted July 10, 2017 Alright im just going to end up snagging those cards off amazon then... should i worry about the fiber or just use my current twinax cable? Quote Link to comment
klamath Posted July 10, 2017 Share Posted July 10, 2017 Can never hurt to have a backup. 1 Quote Link to comment
Hannibal Posted July 10, 2017 Author Share Posted July 10, 2017 2 minutes ago, klamath said: Can never hurt to have a backup. Good point Quote Link to comment
Hannibal Posted July 11, 2017 Author Share Posted July 11, 2017 when i turn my unraid server back on after removing the card should i let the parity check go through or is it ok to cancel it since it literally just completed one less than like 6 hours ago due to that call trace issue ive been having... Quote Link to comment
klamath Posted July 11, 2017 Share Posted July 11, 2017 4 minutes ago, Hannibal said: when i turn my unraid server back on after removing the card should i let the parity check go through or is it ok to cancel it since it literally just completed one less than like 6 hours ago due to that call trace issue ive been having... So I would let it run NON CORRECTING parity check, I was having issues with my unraid server a few months ago, same issues with freezing etc, turns out let a correcting parity check run and it fucked up a ton of files, 1200 "errors" it found. blake2 confirmed unraid corrupted the files. Not sure why unraid had a bug up its ass but i avoided 6.4+ since then. Tim Quote Link to comment
Hannibal Posted July 11, 2017 Author Share Posted July 11, 2017 (edited) oh... well... every parity check that has ran lately due to the call traces i was having im more then sure were correcting parity checks but yet its never found any errors... but ok i will let it run... just will have to go without plex for a little whilte... since the parity check stops the shares from being accessible... Also i moved over to ubuntu 16.04 from windows 10 runs so much smoother than windows ever did.... Edited July 11, 2017 by Hannibal Quote Link to comment
klamath Posted July 11, 2017 Share Posted July 11, 2017 1 minute ago, Hannibal said: oh... well... every parity check that has ran lately due to the errors i was having im more then sure were correcting parity checks but yet its never found any errors... but ok i will let it run... just will have to go without plex for a little whilte... since the parity check stops the shares from being accessible... Also i moved over to ubuntu 16.04 from windows 10 runs so much smoother than windows ever did.... The shares should be visible during a parity check.... Quote Link to comment
Hannibal Posted July 11, 2017 Author Share Posted July 11, 2017 yeah they're deff not give me a few mins and i will post a screen shot of what it says during a parity check... or is this because the parity checks i was running were correcting parity checks? Quote Link to comment
klamath Posted July 11, 2017 Share Posted July 11, 2017 5 minutes ago, Hannibal said: yeah they're deff not give me a few mins and i will post a screen shot of what it says during a parity check... or is this because the parity checks i was running were correcting parity checks? shouldn't make a difference either way. Quote Link to comment
Hannibal Posted July 11, 2017 Author Share Posted July 11, 2017 welp.... NVM apparently im just an idiot lol... do dockers still work during parity check? Quote Link to comment
klamath Posted July 11, 2017 Share Posted July 11, 2017 1 minute ago, Hannibal said: welp.... NVM apparently im just an idiot lol... do dockers still work during parity check? not sure, docker/containers are for losers, real IT people run VMs. Quote Link to comment
Hannibal Posted July 11, 2017 Author Share Posted July 11, 2017 lol alright fair enough... well thank you for all the help again... ill be picking up those cards you linked for me hopefully that cures my issues... Quote Link to comment
Hannibal Posted July 12, 2017 Author Share Posted July 12, 2017 Did some digging around as far i can tell the cards i have are 10Gtek cards with mellanox controllers on them.... I've ordered new cards just waiting for them to get here... Quote Link to comment
Hannibal Posted July 20, 2017 Author Share Posted July 20, 2017 update: got new cards connection is rock solid no issues like the previous cards had but my transfer speeds are abysmal... tried to transfer a 11GB file and only saw a max of 80 Mb/s... Quote Link to comment
Recommended Posts
Join the conversation
You can post now and register later. If you have an account, sign in now to post with your account.
Note: Your post will require moderator approval before it will be visible.