IML 5.1.0
We are pleased to announce general availability of IML 5.1.0
IML 5.1 adds support for Lustre 2.12.3 and features a number of enhancements and bugfixes.
General documentation can be found here.
Issues can be reported here.
Changes from 5.0 can be found here
How to get it
IML 5 can be installed as a set of RPMs via Fedora Copr.
To install the software via RPM, follow these steps.
To upgrade from IEEL 2.4.x / 3.1.x, IML 4.0.x or IML 5 to IML 5.1 follow these steps.
Upgrades from IEEL versions need to upgrade to IML 4 then IML 5.
For instance:
- Upgrading from IEEL 2.4 to IML 5, perform an upgrade from IEEL 2.4 -> IML 4.0.10 -> IML 5.1
- Upgrading from IEEL 3.1 to IML 5, perform an upgrade from IEEL 3.1 -> IML 4.0.10 -> IML 5.1
Features
-
Adds ability to fully deploy storage servers in parallel with the IML CLI. Example:
iml add --hosts mds[1,2],oss[1,2] --profile base_managed_patchless
This will deploy managed servers to each node in the hostlist expression.
Enhancements
- Lustre 2.12.3 support
- Managed Mellanox server support (#955)
- Introduction of Rust plugin framework for messaging between manager and agents.
- Introduction of
iml
cli on the manager node. - Introduction of
iml-agent
cli on the agent nodes. - Improve CPU utilization on the IML manager node (#1040)
- Refresh the filesystem page using WebAssembly (#1072)
- Switch from using F# for device-scanner to Rust (#236)
Bugfixes
- Ensure
chronyd
is stopped andntpd
is running in managed mode (#1008) - Keep IML fs state available if MDT0 is mounted (#1023)
- Fix re-register of existing profile (#1086)
- Only show zpool on volumes page when backed by mpath (#742)
- Wait for incoming device data on manager side (#1036)
Known Issues
These are known issues that are being actively worked. Fixes will be pushed to the IML 5 repo as they land.
- Rabbitmq may not start upon reboot (#480)
- Workaround If the manager is not running upon reboot, issue the following command to restart rabbitmq and all IML services:
systemctl restart iml-manager.target
- Workaround If the manager is not running upon reboot, issue the following command to restart rabbitmq and all IML services:
- ZFS backed nodes may not reboot upon power loss
- Workaround Boot the node
- New OSTs need to be added via cli (#1101)
- Workaround Use the
chroma
cli on the manager node to add new OSTs. Ex:
chroma --username=<USERNAME> --password=<PASSWORD> ost-add --filesystem=<FS_NAME> <HOST_NAME>:<DEV_PATH>
- Workaround Use the