From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:40787) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1dkvTe-00081m-Ho for qemu-devel@nongnu.org; Thu, 24 Aug 2017 12:59:31 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1dkvTZ-0004qL-Ly for qemu-devel@nongnu.org; Thu, 24 Aug 2017 12:59:30 -0400 Received: from mx1.redhat.com ([209.132.183.28]:46284) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1dkvTZ-0004og-C0 for qemu-devel@nongnu.org; Thu, 24 Aug 2017 12:59:25 -0400 Date: Thu, 24 Aug 2017 17:59:11 +0100 From: "Dr. David Alan Gilbert" Message-ID: <20170824165910.GD2737@work-vm> References: <20170628190047.26159-1-dgilbert@redhat.com> <20170628190047.26159-3-dgilbert@redhat.com> <20170710100323.GA21344@pxdev.xzpeter.org> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20170710100323.GA21344@pxdev.xzpeter.org> Subject: Re: [Qemu-devel] [RFC 02/29] migrate: Update ram_block_discard_range for shared List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Peter Xu Cc: qemu-devel@nongnu.org, a.perevalov@samsung.com, marcandre.lureau@redhat.com, maxime.coquelin@redhat.com, mst@redhat.com, quintela@redhat.com, lvivier@redhat.com, aarcange@redhat.com * Peter Xu (peterx@redhat.com) wrote: > On Wed, Jun 28, 2017 at 08:00:20PM +0100, Dr. David Alan Gilbert (git) wrote: > > From: "Dr. David Alan Gilbert" > > > > The choice of call to discard a block is getting more complicated > > for other cases. We use fallocate PUNCH_HOLE in any file cases; > > it works for both hugepage and for tmpfs. > > We use the DONTNEED for non-hugepage cases either where they're > > anonymous or where they're private. > > > > Care should be taken when trying other backing files. > > > > Signed-off-by: Dr. David Alan Gilbert > > --- > > exec.c | 28 ++++++++++++++++------------ > > trace-events | 3 +++ > > 2 files changed, 19 insertions(+), 12 deletions(-) > > > > diff --git a/exec.c b/exec.c > > index 69fc5c9b07..4e61226a16 100644 > > --- a/exec.c > > +++ b/exec.c > > @@ -3557,6 +3557,7 @@ int ram_block_discard_range(RAMBlock *rb, uint64_t start, size_t length) > > } > > > > if ((start + length) <= rb->used_length) { > > + bool need_madvise, need_fallocate; > > uint8_t *host_endaddr = host_startaddr + length; > > if ((uintptr_t)host_endaddr & (rb->page_size - 1)) { > > error_report("ram_block_discard_range: Unaligned end address: %p", > > @@ -3566,23 +3567,26 @@ int ram_block_discard_range(RAMBlock *rb, uint64_t start, size_t length) > > > > errno = ENOTSUP; /* If we are missing MADVISE etc */ > > > > - if (rb->page_size == qemu_host_page_size) { > > -#if defined(CONFIG_MADVISE) > > - /* Note: We need the madvise MADV_DONTNEED behaviour of definitely > > - * freeing the page. > > - */ > > - ret = madvise(host_startaddr, length, MADV_DONTNEED); > > -#endif > > - } else { > > - /* Huge page case - unfortunately it can't do DONTNEED, but > > - * it can do the equivalent by FALLOC_FL_PUNCH_HOLE in the > > - * huge page file. > > - */ > > + /* The logic here is messy; > > + * madvise DONTNEED fails for hugepages > > + * fallocate works on hugepages and shmem > > + */ > > + need_madvise = (rb->page_size == qemu_host_page_size) && > > + (rb->fd == -1 || !(rb->flags & RAM_SHARED)); > > + need_fallocate = rb->fd != -1; > > + if (ret == -1 && need_fallocate) { > > (ret will always be -1 when reach here?) Yes, I was just making the code independent of order. > > #ifdef CONFIG_FALLOCATE_PUNCH_HOLE > > ret = fallocate(rb->fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, > > start, length); > > #endif > > } > > + if (need_madvise && (!need_fallocate || (ret == 0))) { > > +#if defined(CONFIG_MADVISE) > > + ret = madvise(host_startaddr, length, MADV_DONTNEED); > > +#endif > > + } > > + trace_ram_block_discard_range(rb->idstr, host_startaddr, > > + need_madvise, need_fallocate, ret); > > How about make the check easier by: > > if (rb->page_size != qemu_host_page_size || > rb->flags & RAM_SHARED) { > /* Either huge pages or shared memory will contain rb->fd */ > assert(rb->fd); > fallocate(rb->fd, ...); > } else { > madvise(); > } I've reworked this. There are situations where you want both (I think!) - for shared memory, that's not a hugepage, you do an fallocate to clear the underlying storage, and then do an madvise to force the local mappings to be cleared. Dave > Thanks, > > -- > Peter Xu -- Dr. David Alan Gilbert / dgilbert@redhat.com / Manchester, UK