Messages in this thread | | | From | KOSAKI Motohiro <> | Subject | Re: [RFC] mlock: release mmap_sem every 256 faulted pages | Date | Wed, 1 Dec 2010 13:42:07 +0900 (JST) |
| |
minor additionl comments.
> + /* > + * Limit batch size to 256 pages in order to reduce > + * mmap_sem hold time. > + */ > + nfault = nstart + 256 * PAGE_SIZE;
You made 256 pages batch and __mlock_vma_pages_range() has 16 pages another batch. Can we unify this two batch?
Plus, PeterZ implemeted mutex contention detect method (see "[PATCH 18/21] mutex: Provide mutex_is_contended"). now you can easily implemnt akpm proposed efficient batching.
Thanks.
> + > + /* > + * Now fault in a batch of pages. We need to check the vma > + * flags again, as we've not been holding mmap_sem. > + */ > + if ((vma->vm_flags & (VM_DONTEXPAND | VM_RESERVED)) || > + is_vm_hugetlb_page(vma) || vma == get_gate_vma(current)) { > + if (nfault < nend) > + nend = nfault; > + make_pages_present(nstart, nend); > + } else if (vma->vm_flags & VM_LOCKED) { > + if (nfault < nend) > + nend = nfault; > + error = __mlock_vma_pages_range(vma, nstart, nend); > + } > + up: > + up_read(&mm->mmap_sem); > + if (error) > + return __mlock_posix_error_return(error); > + } > + return 0; > +}
| |