SoftRoCE / rxe-dev

Development Repository for RXE
Other
128 stars 55 forks source link

ib device rex0 not found even though i load the rdma_rxe , and the sh:echo: I/O error #49

Open btlcmr0702 opened 7 years ago

btlcmr0702 commented 7 years ago

hi,i followed the step to finish configuration of SoftRoCE , but i met some problems i can't fix.

  1. the problem abt I/O error? btl@ubuntu:~$ sudo rxe_cfg start sh: echo: I/O error sh: echo: I/O error sh: echo: I/O error sh: echo: I/O error Use of uninitialized value $rmtu in string at /bin/rxe_cfg line 371. Name Link Driver Speed NMTU IPv4_addr RDEV RMTU
    eth0 yes e1000 1500 114.212.22.35 rxe0

2.i can't add device because the I/O error btl@ubuntu:~$ sudo rxe_cfg add enp5s0 sh: echo: I/O error

3.i have rxe0 device, but it says IB device rxe0 not found btl@ubuntu:~$ sudo rxe_cfg status Use of uninitialized value $rmtu in string at /bin/rxe_cfg line 371. Name Link Driver Speed NMTU IPv4_addr RDEV RMTU
eth0 yes e1000 1500 114.212.22.35 rxe0
btl@ubuntu:~$ ibv_devices libibverbs: Warning: couldn't load driver 'rxe': librxe-rdmav2.so: cannot open shared object file: No such file or directory libibverbs: Warning: no userspace device-specific driver found for /sys/class/infiniband_verbs/uverbs0 device node GUID



here are some info abt my configuration btl@ubuntu:~$ ls /sys/class/infiniband rxe0 btl@ubuntu:~$ lsmod | grep rxe rdma_rxe 102400 0 ip6_udp_tunnel 16384 1 rdma_rxe udp_tunnel 16384 1 rdma_rxe ib_core 208896 6 rdma_cm,ib_cm,iw_cm,ib_uverbs,rdma_rxe,rdma_ucm btl@ubuntu:~$ uname -r 4.7.0-rc3+


i will wait for some replies, thank u ~

monis410 commented 7 years ago

please uninstall and than install librxe-dev and let me know what happens Make sure you have the latest code (head should be 227e3c49b6e423c066e1e1887fe30c8261f63cbd)

btlcmr0702 commented 7 years ago

hi,thank u for the replies i check out the version and it is the latest code btl@ubuntu:~/librxe-dev$ git log commit 227e3c49b6e423c066e1e1887fe30c8261f63cbd

and then i delete the old librxe-dev , install a new one by git clone https://github.com/SoftRoCE/librxe-dev.git but it seems doesn't work, the problem will happen just like before

monis410 commented 7 years ago

Hi any chance that we schedule an online session? we can do it with google hangout

thanks

btlcmr0702 commented 7 years ago

wow,really thank u :) i didn't think this problem would be so troublesome that need a session. if it is convenient to u,maybe we can have a session tomorrow and i will inform u in advance.

monis410 commented 7 years ago

sure, please coordinate via email monis@mellanox.com

btlcmr0702 commented 7 years ago

ok, i have send a request on hangout , if u r free u could accept it and we can have a session

monis410 commented 7 years ago

I received the invitation but it is unfortunately in a language I don't speak (Chinese?). Can you please send me an email from your private mail account to which I can reply?

mcfatealan commented 7 years ago

Met the same problem today. I tried to copy /usr/lib64/librxe-rdmav2.so to /usr/lib/librxe-rdmav2.so, and the problem seemed to be solved?

sbates130272 commented 7 years ago

Hi

I am confirming a similar issue. The librxe* files are getting installed in /usr/lib64 and I think they need to be installed in /usr/lib on certain systems. If I copy or symlink the files over then things work great for me!

Stephen

mcfatealan commented 7 years ago

@sbates130272 seems still having problems even walking around this issue?

sbates130272 commented 7 years ago

No. If I copy or symlink the files over then everything works well.