Analyzing Linux on a Supercomputer

Diomidis Spinellis

doi:10.1109/MS.2024.3512732

Analyzing Linux on a Supercomputer

Diomidis Spinellis^*

^*Corresponding author for this work

Software Engineering

Research output: Contribution to journal › Article › Scientific › peer-review

6 Downloads (Pure)

Abstract

The C preprocessor, a key element of the language, has become a liability due to its lack of integration with modern language semantics. This column describes the analysis of the C preprocessor usage in the Linux kernel, comprising 20 million lines of code, using the CScout refactoring browser. Processing limitations led to a solution leveraging a supercomputer’s parallel processing capabilities. The analysis divided the kernel’s source files across 32 supercomputer nodes and implemented a binary tournament database merging strategy. Initial efforts revealed multiple difficulties. Resolving them involved several false starts involving recursive SQL statements, an SQLite extension, and the GraphViz connected components tool. After a number of redesigns guided by stress-testing, the analysis finished in just 32 hours rather than a week, using 374 CPU hours and 640 GiB RAM on the supercomputer’s nodes.

Original language	English
Pages (from-to)	18-23
Number of pages	6
Journal	IEEE Software
Volume	42
Issue number	2
DOIs	https://doi.org/10.1109/MS.2024.3512732
Publication status	Published - 2025

Bibliographical note

Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care

Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Access to Document

10.1109/MS.2024.3512732

Analyzing_Linux_on_a_SupercomputerFinal published version, 2.23 MB

Cite this

@article{1adeaee5e8ff45fb934db37471c81fa1,

title = "Analyzing Linux on a Supercomputer",

abstract = "The C preprocessor, a key element of the language, has become a liability due to its lack of integration with modern language semantics. This column describes the analysis of the C preprocessor usage in the Linux kernel, comprising 20 million lines of code, using the CScout refactoring browser. Processing limitations led to a solution leveraging a supercomputer{\textquoteright}s parallel processing capabilities. The analysis divided the kernel{\textquoteright}s source files across 32 supercomputer nodes and implemented a binary tournament database merging strategy. Initial efforts revealed multiple difficulties. Resolving them involved several false starts involving recursive SQL statements, an SQLite extension, and the GraphViz connected components tool. After a number of redesigns guided by stress-testing, the analysis finished in just 32 hours rather than a week, using 374 CPU hours and 640 GiB RAM on the supercomputer{\textquoteright}s nodes.",

author = "Diomidis Spinellis",

note = "Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.",

year = "2025",

doi = "10.1109/MS.2024.3512732",

language = "English",

volume = "42",

pages = "18--23",

journal = "IEEE Software",

issn = "0740-7459",

publisher = "IEEE",

number = "2",

}

TY - JOUR

T1 - Analyzing Linux on a Supercomputer

AU - Spinellis, Diomidis

N1 - Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

PY - 2025

Y1 - 2025

N2 - The C preprocessor, a key element of the language, has become a liability due to its lack of integration with modern language semantics. This column describes the analysis of the C preprocessor usage in the Linux kernel, comprising 20 million lines of code, using the CScout refactoring browser. Processing limitations led to a solution leveraging a supercomputer’s parallel processing capabilities. The analysis divided the kernel’s source files across 32 supercomputer nodes and implemented a binary tournament database merging strategy. Initial efforts revealed multiple difficulties. Resolving them involved several false starts involving recursive SQL statements, an SQLite extension, and the GraphViz connected components tool. After a number of redesigns guided by stress-testing, the analysis finished in just 32 hours rather than a week, using 374 CPU hours and 640 GiB RAM on the supercomputer’s nodes.

AB - The C preprocessor, a key element of the language, has become a liability due to its lack of integration with modern language semantics. This column describes the analysis of the C preprocessor usage in the Linux kernel, comprising 20 million lines of code, using the CScout refactoring browser. Processing limitations led to a solution leveraging a supercomputer’s parallel processing capabilities. The analysis divided the kernel’s source files across 32 supercomputer nodes and implemented a binary tournament database merging strategy. Initial efforts revealed multiple difficulties. Resolving them involved several false starts involving recursive SQL statements, an SQLite extension, and the GraphViz connected components tool. After a number of redesigns guided by stress-testing, the analysis finished in just 32 hours rather than a week, using 374 CPU hours and 640 GiB RAM on the supercomputer’s nodes.

UR - https://www.scopus.com/pages/publications/105000946379

U2 - 10.1109/MS.2024.3512732

DO - 10.1109/MS.2024.3512732

M3 - Article

AN - SCOPUS:105000946379

SN - 0740-7459

VL - 42

SP - 18

EP - 23

JO - IEEE Software

JF - IEEE Software

IS - 2

ER -

Analyzing Linux on a Supercomputer

Abstract

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this