% IMPORTANT: The following is UTF-8 encoded.  This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.

@INPROCEEDINGS{Bruns:1046529,
      author       = {Bruns, Benjamin},
      title        = {{M}odernizing {L}egacy {I}nfrastructure {M}onitoring:
                      {E}nhancing {P}erformance with {P}rometheus and {G}it{L}ab
                      {CI}/{CD}},
      reportid     = {FZJ-2025-03852},
      year         = {2025},
      note         = {https://zenodo.org/records/14982650},
      abstract     = {Effective monitoring of (computing) infrastructure,
                      especially in complex systems with various dependencies, is
                      crucial for ensuring high availability and early detection
                      of performance issues. This poster demonstrates the
                      integration of Prometheus and GitLab CI/CD to modernize our
                      existing infrastructure monitoring methods. As
                      infrastructure checks increase, our legacy monitoring system
                      faces growing challenges such as performance bottlenecks,
                      limited scalability, and maintenance difficulties.
                      Prometheus, with its real-time monitoring and alerting
                      capabilities, offers a scalable and flexible solution. It
                      supports both horizontal and vertical scaling, efficient
                      data storage, and a modular architecture that facilitates
                      the seamless integration of various existing monitoring
                      tools, such as specialized exporters.Using Prometheus as our
                      backend involves setting up a containerized system, creating
                      data sources and targets, and configuring (custom) metrics
                      and alerts. The use of GitLab’s CI/CD pipeline further
                      automates the building, deployment and testing processes.
                      Additionally, Grafana, when used alongside Prometheus,
                      provides a robust visualization tool to display statistics
                      and reports, such as CPU and GPU usage or file quotas. This
                      approach not only enhances efficiency and ensures timely
                      alerts for potential issues but also keeps the monitoring
                      system up-to-date and resilient. It also provides users with
                      valuable statistics through a modern and flexible backend.
                      Furthermore, containerizing the new monitoring system offers
                      significant advantages, including portability, scalability,
                      and modularization.The poster presents selected
                      infrastructure systems, directly comparing the usability and
                      performance of our legacy script-based monitoring system and
                      the new Prometheus-based monitoring system.},
      month         = {Feb},
      date          = {2025-02-25},
      organization  = {5th conference for Research Software
                       Engineering in Germany (deRSE25),
                       Karlsruhe (Germany), 25 Feb 2025 - 1
                       Mar 2025},
      subtyp        = {Other},
      cin          = {IAS-8},
      cid          = {I:(DE-Juel1)IAS-8-20210421},
      pnm          = {5112 - Cross-Domain Algorithms, Tools, Methods Labs (ATMLs)
                      and Research Groups (POF4-511)},
      pid          = {G:(DE-HGF)POF4-5112},
      typ          = {PUB:(DE-HGF)24},
      url          = {https://juser.fz-juelich.de/record/1046529},
}