On Thu, 06 Nov 2008, Mel Gorman wrote: > > We just want to provide an interface suitable for people that writing > allocators or are porting parts of their application to use hugepages where > it is sensible. The former should be already coding to not waste any memory > and the latter should be helped as much as possible by defaulting to behaviour > whose performance does not suck. >
I tend to agree with Mel here, the purpose of libhugetlbfs is to make huge pages easy and attractive to use. I think that having such a serious performance hit when using get_huge_pages with no explanation is likely to turn developers off. Even if the need for some thought when using get_huge_pages is documented I doubt that the average developer is going to look at libhuge source or man pages when hunting for performance problems. That being said, I understand that the function name might imply that it is a simple interface for grabbing memory backed by huge pages. Perhaps a new function should be introduced and use of get_huge_pages deprecated unless you know what you are getting into. Eric
signature.asc
Description: Digital signature
------------------------------------------------------------------------- This SF.Net email is sponsored by the Moblin Your Move Developer's challenge Build the coolest Linux based applications with Moblin SDK & win great prizes Grand prize is a trip for two to an Open Source event anywhere in the world http://moblin-contest.org/redirect.php?banner_id=100&url=/
_______________________________________________ Libhugetlbfs-devel mailing list Libhugetlbfs-devel@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/libhugetlbfs-devel
