migrate_pages internals: lazy copy
Hi list, Does the "migrate_pages" syscall migrate memory pages in a *lazy* manner? if not, is there another syscall or patch that does it? Regards,
On Fri, 19 Jan 2018 13:57:18 -0500, Karaoui mohamed lamine said:
Does the "migrate_pages" syscall migrate memory pages in a *lazy* manner? if not, is there another syscall or patch that does it?
man 2 migrate_pages says: RETURN VALUE On success migrate_pages() returns the number of pages that could not be moved (i.e., a return of zero means that all pages were successfully moved). On error, it returns -1, and sets errno to indicate the error. which implies that it doesn't return until an attempt has been made to migrate all relevant pages. And that rules out lazy migration. What problem are you trying to solve by doing it in a lazy manner?
Hi Vladis, Thanks for this response. I was trying to use the Clavis scheduler: http://clavis.sourceforge.net/ In this scheduler they go through an important effort to migrate only currently used pages of a thread (using AMD IBS hardware counters). This could be implemented more neatly using page tables at the kernel level... Regards, 2018-01-19 14:26 GMT-05:00 <valdis.kletnieks@vt.edu>:
On Fri, 19 Jan 2018 13:57:18 -0500, Karaoui mohamed lamine said:
Does the "migrate_pages" syscall migrate memory pages in a *lazy* manner? if not, is there another syscall or patch that does it?
man 2 migrate_pages says:
RETURN VALUE On success migrate_pages() returns the number of pages that could not be moved (i.e., a return of zero means that all pages were successfully moved). On error, it returns -1, and sets errno to indicate the error.
which implies that it doesn't return until an attempt has been made to migrate all relevant pages. And that rules out lazy migration.
What problem are you trying to solve by doing it in a lazy manner?
participants (2)
-
Karaoui mohamed lamine -
valdis.kletnieks＠vt.edu