Measuring Performance Under Failures in the LHCb Data Acquisition Network

@article{Stein2024a,
	title        = {Measuring Performance Under Failures in the LHCb Data Acquisition Network},
	author       = {Stein, Eloise and Pisani, Flavio and Colombo, Tommaso and Pelsser, Cristel},
	year         = 2024,
	month        = aug,
	journal      = {IEEE Transactions on Nuclear Science},
	volume       = {PP},
	pages        = {1--1},
	doi          = {10.1109/TNS.2024.3451177},
	abstract     = {For the Large Hadron Collider beauty (LHCb) experiment, achieving high throughput in the data acquisition (DAQ) network is crucial for supporting scientific applications. However, failures within DAQ networks can lead to significant performance degradation. In this study, we investigate the frequency, duration, and causes of failures in the LHCb DAQ network over a two-month period to illustrate how common these events are. This insight is essential for developing strategies to optimize performance during data taking periods. We further study the performance degradation upon failure. We explore the performance for two potential approaches to high-performance event building on the DAQ network: synchronized and non-synchronized designs. We use live experiments to demonstrate that a synchronized design, which carefully schedules network communications to avoid congestion, can achieve significantly better performance when the network is used at full capacity. However, this approach comes at the expense of reduced fault tolerance compared to the non-synchronized approach. This study highlights that it is essential for the network to handle failures more efficiently to sustainably maintain high data rates.},
	groups       = {International Journals and Magazines},
	keywords     = {Servers,Data acquisition,Large Hadron Collider,Bandwidth,Throughput,Sensors,Computers,data acquisition,event building,failure analysis,network fault tolerance,networks}
}