PCIe Hot-Plug Support Standardization Challenges in ATCA

Throughout the past decade, the advanced telecommunications computing architecture (ATCA) solidified its position as one of the main switched-based crate standards for advanced physics instrumentation, offering not only high performance characteristics in data throughput, channel density, or power supply/dissipation capabilities but also special features for high availability (HA), required for the latest and upcoming large-scale endeavors, as is the case of ITER. Hot swap is one of the main HA features in ATCA, allowing for boards to be replaced in a crate (shelf), without powering off the whole system. Platforms using the peripheral component interconnect express (PCIe) protocol on the fabric interface must be complemented, at the software level, with the PCIe hot-plug native feature, currently not specified for the ATCA form-factor. From a customized hot-plug support implementation for ATCA node boards, this article presents an implementation extension for hub boards, allowing hot-plug of PCIe switching devices, without causing bus enumeration problems. This article further addresses the main issues concerning an eventual standardization of PCIe hot-plug support in ATCA, such as the implementability of hot-plug elements and the generation and management of hot-plug events, aiming to stimulate the discussion within the PCI Industrial Computer Manufacturers Group (PICMG) community toward a long-overdue standardized solution for hot-plug in ATCA.