similar to: [PATCH] virtio_balloon: fix PFN format for virtio-1

Wei Wang wrote: > The balloon_lock was used to synchronize the access demand to elements > of struct virtio_balloon and its queue operations (please see commit > e22504296d). This prevents the concurrent run of the leak_balloon and > fill_balloon functions, thereby resulting in a deadlock issue on OOM: > > fill_balloon: take balloon_lock and wait for OOM to get some memory; >

Wei Wang wrote: > The balloon_lock was used to synchronize the access demand to elements > of struct virtio_balloon and its queue operations (please see commit > e22504296d). This prevents the concurrent run of the leak_balloon and > fill_balloon functions, thereby resulting in a deadlock issue on OOM: > > fill_balloon: take balloon_lock and wait for OOM to get some memory; >

Workqueues have clean and rich API for all basic operations. The code is usually easier and better readable. It can be easily tuned for the given purpose. In many cases, it allows to avoid an extra kernel thread. It helps to stop the growing number of them. Also there will be less thread-specific hacks all over the kernel code. It forces making the task selfcontained. There is no longer an

Workqueues have clean and rich API for all basic operations. The code is usually easier and better readable. It can be easily tuned for the given purpose. In many cases, it allows to avoid an extra kernel thread. It helps to stop the growing number of them. Also there will be less thread-specific hacks all over the kernel code. It forces making the task selfcontained. There is no longer an

Wei Wang wrote: > >> @@ -162,20 +160,20 @@ static unsigned fill_balloon(struct virtio_balloon *vb, size_t num) > >> msleep(200); > >> break; > >> } > >> - set_page_pfns(vb, vb->pfns + vb->num_pfns, page); > >> - vb->num_pages += VIRTIO_BALLOON_PAGES_PER_PAGE; > >> + set_page_pfns(vb, pfns + num_pfns, page);

Wei Wang wrote: > >> @@ -162,20 +160,20 @@ static unsigned fill_balloon(struct virtio_balloon *vb, size_t num) > >> msleep(200); > >> break; > >> } > >> - set_page_pfns(vb, vb->pfns + vb->num_pfns, page); > >> - vb->num_pages += VIRTIO_BALLOON_PAGES_PER_PAGE; > >> + set_page_pfns(vb, pfns + num_pfns, page);

The implementation of the current virtio-balloon is not very efficient, Bellow is test result of time spends on inflating the balloon to 3GB of a 4GB idle guest: a. allocating pages (6.5%, 103ms) b. sending PFNs to host (68.3%, 787ms) c. address translation (6.1%, 96ms) d. madvise (19%, 300ms) It takes about 1577ms for the whole inflating process to complete. The test shows that the bottle neck

The implementation of the current virtio-balloon is not very efficient, Bellow is test result of time spends on inflating the balloon to 3GB of a 4GB idle guest: a. allocating pages (6.5%, 103ms) b. sending PFNs to host (68.3%, 787ms) c. address translation (6.1%, 96ms) d. madvise (19%, 300ms) It takes about 1577ms for the whole inflating process to complete. The test shows that the bottle neck

> On Fri, May 20, 2016 at 05:59:46PM +0800, Liang Li wrote: > > The implementation of the current virtio-balloon is not very > > efficient, Bellow is test result of time spends on inflating the > > balloon to 3GB of a 4GB idle guest: > > > > a. allocating pages (6.5%, 103ms) > > b. sending PFNs to host (68.3%, 787ms) c. address translation (6.1%, > >

> On Fri, May 20, 2016 at 05:59:46PM +0800, Liang Li wrote: > > The implementation of the current virtio-balloon is not very > > efficient, Bellow is test result of time spends on inflating the > > balloon to 3GB of a 4GB idle guest: > > > > a. allocating pages (6.5%, 103ms) > > b. sending PFNs to host (68.3%, 787ms) c. address translation (6.1%, > >

fill_balloon doing memory allocations under balloon_lock can cause a deadlock when leak_balloon is called from virtballoon_oom_notify and tries to take same lock. To fix, split page allocation and enqueue and do allocations outside the lock. Here's a detailed analysis of the deadlock by Tetsuo Handa: In leak_balloon(), mutex_lock(&vb->balloon_lock) is called in order to serialize

fill_balloon doing memory allocations under balloon_lock can cause a deadlock when leak_balloon is called from virtballoon_oom_notify and tries to take same lock. To fix, split page allocation and enqueue and do allocations outside the lock. Here's a detailed analysis of the deadlock by Tetsuo Handa: In leak_balloon(), mutex_lock(&vb->balloon_lock) is called in order to serialize

On Wed, May 18, 2016 at 03:38:53PM +0300, Michael S. Tsirkin wrote: > Everything should be LE when using virtio-1, but > the linux balloon driver does not seem to care about that. > > Cc: stable at vger.kernel.org > Reported-by: Cornelia Huck <cornelia.huck at de.ibm.com> > Signed-off-by: Michael S. Tsirkin <mst at redhat.com> Forgot to CC stable. Please consider

On Fri, Oct 21, 2016 at 02:24:37PM +0800, Liang Li wrote: > The implementation of the current virtio-balloon is not very > efficient, the time spends on different stages of inflating > the balloon to 7GB of a 8GB idle guest: > > a. allocating pages (6.5%) > b. sending PFNs to host (68.3%) > c. address translation (6.1%) > d. madvise (19%) > > It takes about 4126ms

On Fri, Oct 21, 2016 at 02:24:37PM +0800, Liang Li wrote: > The implementation of the current virtio-balloon is not very > efficient, the time spends on different stages of inflating > the balloon to 7GB of a 8GB idle guest: > > a. allocating pages (6.5%) > b. sending PFNs to host (68.3%) > c. address translation (6.1%) > d. madvise (19%) > > It takes about 4126ms

On Fri, Mar 03, 2017 at 01:40:28PM +0800, Wei Wang wrote: > From: Liang Li <liang.z.li at intel.com> > > The implementation of the current virtio-balloon is not very > efficient, because the pages are transferred to the host one by one. > Here is the breakdown of the time in percentage spent on each > step of the balloon inflating process (inflating 7GB of an 8GB > idle

On Fri, Mar 03, 2017 at 01:40:28PM +0800, Wei Wang wrote: > From: Liang Li <liang.z.li at intel.com> > > The implementation of the current virtio-balloon is not very > efficient, because the pages are transferred to the host one by one. > Here is the breakdown of the time in percentage spent on each > step of the balloon inflating process (inflating 7GB of an 8GB > idle

Workqueues have clean and rich API for all basic operations. The code is usually easier and better readable. It can be easily tuned for the given purpose. In many cases, it allows to avoid an extra kernel thread. It helps to stop the growing number of them. Also there will be less thread-specific hacks all over the kernel code. It forces making the task selfcontained. There is no longer an

Workqueues have clean and rich API for all basic operations. The code is usually easier and better readable. It can be easily tuned for the given purpose. In many cases, it allows to avoid an extra kernel thread. It helps to stop the growing number of them. Also there will be less thread-specific hacks all over the kernel code. It forces making the task selfcontained. There is no longer an

On Thu, Apr 13, 2017 at 05:35:05PM +0800, Wei Wang wrote: > Add a new feature, VIRTIO_BALLOON_F_BALLOON_CHUNKS, which enables Let's find a better name here. VIRTIO_BALLOON_F_PAGE_CHUNK > the transfer of the ballooned (i.e. inflated/deflated) pages in > chunks to the host. > > The implementation of the previous virtio-balloon is not very > efficient, because the ballooned