On Fri, 29 Apr 2005, Tzahi Fadida wrote: > I can't reboot or unmount in the middle of the query. > option 3 sounds good. its for debugging and benchmarking. > but not just, I am doing only sequential access on some of my > algorithms and OScaching is useless and it seems I can't use huge > relations to defeat the cache replacement > (since the operation I am doing is very long). > I am caching myself inside the algorithm, the OS caching > is just wasting memory and does not know whats best > for my algorithm.
and yet, that's what you've got, because the linux kernel people still think they know better how to handle your memory for you ;) > Is there a file system out there > that I could disable its caching when mounting? a google search resulted the link i sent yesterday. > I have seen some unfamiliar ones but I prefer something in > the kernel source. > Can you give me some direction on where I can change the code > to disable caching? not realy, since this is spread over both the VFS and the file-system-specific code, and is not localized to a small pat of the code. choose the file system you want to "de-cache", and whenever it uses 'struct page', make sure to invalidate and release the page after its contents were used. you'll still have buffer heads, but they are used to handle meta-data for the FS, not file data nor directory contents - and i imagine you don't want to disable caching that data. note that you also certainly don't want to have every access to a file update its inode's access time/modification time with real disk access - this will make your tests crawl too slowly... -- guy "For world domination - press 1, or dial 0, and please hold, for the creator." -- nob o. dy ================================================================= To unsubscribe, send mail to [EMAIL PROTECTED] with the word "unsubscribe" in the message body, e.g., run the command echo unsubscribe | mail [EMAIL PROTECTED]
