Re: 10.6.2 issues with F_NOCACHE?
Re: 10.6.2 issues with F_NOCACHE?
- Subject: Re: 10.6.2 issues with F_NOCACHE?
- From: Godfrey van der Linden <email@hidden>
- Date: Thu, 04 Feb 2010 21:23:15 +1100
Unfortunately the mmap won't really help you as it will map the entire file into memory at some stage.
Have you written a test case, just a little program that walks the files multiple times both with F_NOCACHE and without it? top will give you a feel for how the memory system is progressing.
Cheers
Godfrey
On 2010-02-04, at 5:16 PM, Jens Alfke wrote:
>
> On Feb 3, 2010, at 8:53 PM, Marc Van Olmen wrote:
>
>> Not sure important: my memory pointer that i pass into the read, is an offset in a section of a big memory blob allocated with malloc.
>
> Have you considered memory-mapping the file instead? That way you won't be allocating VM backing store for the copy of the file in the heap.
>
>> * Any suggestion on how trace this issue better? Is there a way I can trace when a read data is being added to the disk cache for example?
>
> I usually use the fs_usage tool for things like this. (You can probably get similar data from Instruments, but I'm an old fogey and I've never really been able to figure out how to get Instruments to tell me anything useful...)
_______________________________________________
Do not post admin requests to the list. They will be ignored.
Darwin-dev mailing list (email@hidden)
Help/Unsubscribe/Update your Subscription:
This email sent to email@hidden