resalloc v5.6

• Bugfixes:

  • The Watcher thread no longer fails in the case of random database
    exceptions, such as "database is locked." It now simply retries, ensuring
    the cluster remains well-maintained (cleanup of dead machines works
    properly).

  • The Web-UI now sorts the list of Pools alphabetically (PR #161).

resalloc v5.5

• Bugfixes:

  • Previous versions of the Resalloc Web-UI loaded the pools.yaml
    configuration file. In cases of configuration issues, they attempted to
    log problematic details into a log file owned by resalloc-server
    (var/log/resallocserver). Such attempts resulted in file permission
    problems. The Web-UI logic has been modified to no longer read
    pools.yaml and to rely solely on the database. In the future, we have
    to implement a completely separate configuration for the Web-UI and cease
    loading server.yaml, which should not be readable by Apache either, for
    instance.

resalloc v5.4

• Bugfixes:

  • The agent-spawner workers now ignore the output from shell command hooks
    (redirects them to /dev/null to avoid SIGPIPE)

  • The agent-spawner server now correctly base64-encodes the ticket data.

  • The agent-spawner package now requires up2date python3-copr-common for
    fixed get_redis_connection() method.

  • The resalloc's tags/tags_on_demand configuration was cleaned up to
    allow users to keep them unspecified, several useful warnings
    related to tag misconfiguration were added.

resalloc v5.3

- The helper scripts have been moved from resalloc-server to the
  resalloc-helpers (sub)package.  Cloud drivers that rely on those
  scripts might be usable without the resalloc-server package and its
  transitive dependencies.

resalloc v5.2

New in v5.2:

• New Features

  • Added a new convenience script, /bin/resalloc-wait-for-ssh. This script
    is useful for cloud drivers that want to actively wait until the VMs
    (resources) become available on SSH.

  • The /bin/resalloc-check-vm-ip now optionally accepts the $SSH_USER
    environment variable if checking root-SSH isn't possible. Users can use
    cmd_livecheck: SSH_USER=centos resalloc-check-vm-ip.

• Bug Fixes

  • Compatibility fix with SQLAlchemy v2.

  • The $AGENT_SPAWNER_RESOURCE_DATA variable content is now base64 encoded.

  • The resalloc-agent-spawner package now correctly specifies all the
    required runtime dependencies.

  • The survive_server_restart client option now ignores all possible
    server socket errors, avoiding unexpected client interrupts.

resalloc v5.1

New in v5.1:

• New Features:

  • A new concept of "agent-like" resources has been implemented. A new
    resalloc-agent-spawner daemon (shipped in resalloc-agent-spawner
    package) converges the number of agents (tickets opened against the
    resalloc server) according to the current state of the external system
    (e.g., according to the wishes of the OpenScanHub, software based on the
    Kobo framework). This feature is now provided in "beta" quality.

  • The resalloc ticket-check now raises a WARNING for non-existing ticket
    IDs. The API has been appropriately fixed so that even clients with the
    .survive_server_restart option won't indefinitely hang on a non-existing
    ticket ID.

• Bugfixes:

  • Web browsing the pools has been fixed to prevent users from encountering
    500 errors. For more information, see
    fedora-copr/copr#2882

  • The resalloc-selinux package has dropped the RPM dependency on
    resalloc-webui.

  • A bug in the "on-demand" resources concept has been fixed so that even a
    single ticket can no longer trigger the allocation of multiple resources.

  • A traceback bug-fix has been added to the "cleanup resource orphans"
    logic, addressing cases when no resource has yet started in the configured
    pool. A user-friendly warning is now raised instead.

resalloc v5.0

• New features

  • A new concept of "on-demand" ticket tags has been introduced. These
    on-demand tags, when assigned to tickets, trigger an "on-demand"
    resource allocation in the corresponding pools, rather than
    pre-allocating them in advance.

  • The README file has been significantly rewritten by Jakub Kadlčík in
    markdown format.

  • The number of "livecheck" attempts before a resource is deleted is
    now configurable through the "livecheck_attempts" option.

Resalloc v4.9

New in v4.9:

• New features

  • Resources that fail the livecheck are terminated, even though they
    have some ticket assigned. Such a ticket goes to FAILED state.

  • We use the SPDX-formatted license.

Resalloc v4.8

New in v4.8:

• New features:

  • Better logging support: Exceptions are logged to 'main.log', the
    default log_level=info is made useful, more readable messages, log
    entries contain PID, TID and thread name.

  • Stopped using 'sqlalchemy.pool.NullPool' for connecting to database,
    and use the default. That is NullPool anyway for SQLite backend, and
    QueuePool(pool_size=5) for the PostgreSQL backend:
    https://docs.sqlalchemy.org/en/14/core/pooling.html#sqlalchemy.pool.NullPool

  • A new PostgreSQL index to speedup resalloc-maint ticket-list command.

Resalloc v4.7

New in v4.7:

• Bugfixes:

  • the new mechanism for cleaning orphaned resources was cleaning also
    resources in STARTING/DELETING/RELEASING states.