Re: process creation time increases linearly with shmem

[Nick Piggin <nickpiggin@yahoo.com.au>]

Andi Kleen wrote:
>>Would it be worth trying to do something like this?
> 
> 
> Maybe. Shouldn't be very hard though - you just need to check if the VMA is 
> backed by an object and if yes don't call copy_page_range for it.
> 
> I think it just needs (untested) 
> 

I think you need to check for MAP_SHARED as well, because
MAP_PRIVATE mapping of a file could be modified in parent.

See patch I posted just now.

Also, do you need any special case for hugetlb?


> Index: linux-2.6.13-rc5-misc/kernel/fork.c
> ===================================================================
> --- linux-2.6.13-rc5-misc.orig/kernel/fork.c
> +++ linux-2.6.13-rc5-misc/kernel/fork.c
> @@ -265,7 +265,8 @@ static inline int dup_mmap(struct mm_str
>  		rb_parent = &tmp->vm_rb;
>  
>  		mm->map_count++;
> -		retval = copy_page_range(mm, current->mm, tmp);
> +		if (!file && !is_vm_hugetlb_page(vma))
> +			retval = copy_page_range(mm, current->mm, tmp);
>  		spin_unlock(&mm->page_table_lock);
>  
>  		if (tmp->vm_ops && tmp->vm_ops->open)
> 
> But I'm not sure it's a good idea in all cases. Would need a lot of 
> benchmarking  at least.
> 

Yep. I'm sure it must have come up in the past, and Linus
must have said something about best-for-most.

-- 
SUSE Labs, Novell Inc.

Send instant messages to your online friends http://au.messenger.yahoo.com