Hi, I created a POSIX container and mounted at /mnt/dfuse on the client node, and ran the following command: ``` # echo "foo" > /mnt/dfuse/bar # cat /mnt/dfuse/bar ``` But it gives me the following

Hi there, I have posted all the DUG presentations on the wiki (seehttps://wiki.hpdd.intel.com/display/DC/DUG20) We need some more time for the video recordings that will be published on our

Note that the time for DUG listed in the SC2020 schedule is not correct. Please use the webex info below.

Just a reminder that the DUG’20 is tomorrow. Hope to see you there! Cheers, Johann From:<daos@daos.groups.io> on behalf of "Lombardi, Johann" <johann.lombardi@...> Reply-To:

Did you find a workaround for this problem ? I am experiencing the same problem when trying to setup on an ubuntu 20.04.1 OS. Commands I tried to run: $ Git clone

Thanks for your help. I have tried the ubuntu and leap dockerfiles too. Leap worked fine. The ubuntu one failed with a similar error when compiling acl_dump_test. I leave a snippet of the error

The logic in utils/sl for scons should be detecting that the libfabric version installed is not suitable automatically and building a suitable version. I’m trying it locally to see what is going

Yes you need a later version of libfabric; preferably 1.11. But you need a libfabric that supports ABI 1.3 (FABRIC 1.3 )

The dockerfile I am taking from master is installing libfabric 1.7 in the image. Should I modify the scons script in order to replace the libfabric version?

What version of libfabric are you using? Try using libfabric >= 1.11 /usr/prereq/dev/mercury/lib/libna.so.2: undefined reference to `fi_dupinfo@...' /usr/prereq/dev/mercury/lib/libna.so.2:

Hello, I am finding a similar error also when trying to build the DAOS docker image. wget https://raw.githubusercontent.com/daos-stack/daos/master/utils/docker/Dockerfile.centos.7 docker build

Hi there, FYI, we have posted several tutorial videos on the newly created DAOS YouTube channel (seehttps://www.youtube.com/channel/UCVP4e_UTnSJg15Cm80UtNwg). This includes how to install RPMs,

We have recently learned of a serious issue affecting systems with Apache Pass DCPM modules. The ipmctl utility (versions 02.00.00.3809 through 02.00.00.3816) was released with a bug that can cause

Hi Alex, That’s good info, I’ll give it a go. We were hoping to avoid customizing the stack in this particular environment unless required, and this definitely qualifies. Thanks

Hi Ari, Is it possible for you to install more recent MOFED on your system? In the past we’ve had issues with MOFEDs older than 4.7; locally we’ve been using MOFED 5.0.2. Thanks, ~~Alex.

Tom thanks! Unfortunately I couldn't reproduce this behaviour on v1.0.1 with bdev_exclude Also we've checked the NVMeF initiator on pure SPDK and it's connects remote target. So daos_nvme.conf

Thanks for the feedback and agreed, the workaround I was to be sure the sysctl settings were applied for same logical subnet, I tried them in a few combinations (output is in previous email). Other

Ari, You say this looks different from the stuff in the spring, but unless you've noticed a difference in the specific error messages, this looks (at a high level) identical to me. The issue in the

Hi, We’ve been testing DAOS functionality in our lab and have had success running IOR with 8 clients with & without POSIX containers with single IO instance and single HCA within one server with

I realise that the problem is the bdev_exclude devices are already bound to UIO at the time that DAOS starts and are not actively unbound by SPDK setup script. 0000:00:04.1 (8086 2021): Already using