A common approach to improve memory access in NUMA machines exploits operating system (OS) page protection mechanisms to induce faults to determine which pages are accessed by what thread, so as to move the thread and its working-set of pages to the same NUMA node. However, existing proposals do not fully fit the requirements of truly multi-thread applications with non-partitioned accesses to virtual pages. In fact, these proposals exploit (induced) faults on a same page-table for all the threads of a same process to determine the access pattern. Hence, the fault by one thread (and the consequent re-opening of the access to the corresponding page) would mask those by other threads on the same page. This may lead to inaccuracy in the estimation of the working-set of individual threads. We overcome this drawback by presenting a lightweight operating system support for Linux, referred to as multi-view address space, explicitly targeting accuracy of per-thread working-set estimation in truly multi-thread applications with non-partitioned accesses, and an associated thread/data migration policy. Our solution is fully transparent to user-space code. It is embedded in a Linux/x86_64 module that installs any required modification to the original kernel image by solely relying on dynamic patching. A motivated case study in the context of HPC is also presented for an assessment of our proposal.
OS-Based NUMA Optimization: Tackling the Case of Truly Multi-thread Applications with Non-partitioned Virtual Page Accesses / Gennaro, Ilaria Di; Pellegrini, Alessandro; Quaglia, Francesco. - STAMPA. - (2016), pp. 291-300. (Intervento presentato al convegno 16th IEEE/ACM International Symposium on Cluster, Cloud, and Grid Computing, CCGrid 2016 tenutosi a Cartagena de Indias; Colombia) [10.1109/CCGrid.2016.91].
OS-Based NUMA Optimization: Tackling the Case of Truly Multi-thread Applications with Non-partitioned Virtual Page Accesses
Gennaro, Ilaria Di
;PELLEGRINI, ALESSANDRO;QUAGLIA, Francesco
2016
Abstract
A common approach to improve memory access in NUMA machines exploits operating system (OS) page protection mechanisms to induce faults to determine which pages are accessed by what thread, so as to move the thread and its working-set of pages to the same NUMA node. However, existing proposals do not fully fit the requirements of truly multi-thread applications with non-partitioned accesses to virtual pages. In fact, these proposals exploit (induced) faults on a same page-table for all the threads of a same process to determine the access pattern. Hence, the fault by one thread (and the consequent re-opening of the access to the corresponding page) would mask those by other threads on the same page. This may lead to inaccuracy in the estimation of the working-set of individual threads. We overcome this drawback by presenting a lightweight operating system support for Linux, referred to as multi-view address space, explicitly targeting accuracy of per-thread working-set estimation in truly multi-thread applications with non-partitioned accesses, and an associated thread/data migration policy. Our solution is fully transparent to user-space code. It is embedded in a Linux/x86_64 module that installs any required modification to the original kernel image by solely relying on dynamic patching. A motivated case study in the context of HPC is also presented for an assessment of our proposal.File | Dimensione | Formato | |
---|---|---|---|
DiGennaro_Postprint_OS-Based-NUMA_2016.pdf
accesso aperto
Note: https://ieeexplore.ieee.org/document/7515701
Tipologia:
Documento in Post-print (versione successiva alla peer review e accettata per la pubblicazione)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
302.18 kB
Formato
Adobe PDF
|
302.18 kB | Adobe PDF | |
DiGennaro_OS-Based-NUMA_2016.pdf
solo gestori archivio
Tipologia:
Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
322.19 kB
Formato
Adobe PDF
|
322.19 kB | Adobe PDF | Contatta l'autore |
DiGennaro_Frontespizio-indice_OS-Based-NUMA_2016.pdf
solo gestori archivio
Tipologia:
Altro materiale allegato
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
616.88 kB
Formato
Adobe PDF
|
616.88 kB | Adobe PDF | Contatta l'autore |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.