search for: sg_in

...#39;re not using are enqueued * at vb_dev_info->pages list. @@ -373,6 +378,49 @@ static void update_balloon_stats(struct virtio_balloon *vb) pages_to_bytes(available)); } +static void update_free_pages_stats(struct virtio_balloon *vb, + unsigned long req_id) +{ + struct scatterlist sg_in, sg_out; + unsigned long pfn = 0, bmap_len, max_pfn; + struct virtqueue *vq = vb->misc_vq; + struct balloon_bmap_hdr *hdr = vb->bmap_hdr; + int ret = 1; + + max_pfn = get_max_pfn(); + mutex_lock(&vb->balloon_lock); + while (pfn < max_pfn) { + memset(vb->page_bitmap, 0, vb->bm...

...'re not using are enqueued * at vb_dev_info->pages list. @@ -552,6 +554,63 @@ static void update_balloon_stats(struct virtio_balloon *vb) pages_to_bytes(available)); } +static void send_unused_pages_info(struct virtio_balloon *vb, + unsigned long req_id) +{ + struct scatterlist sg_in; + unsigned long pfn = 0, bmap_len, pfn_limit, last_pfn, nr_pfn; + struct virtqueue *vq = vb->req_vq; + struct virtio_balloon_resp_hdr *hdr = vb->resp_hdr; + int ret = 1, used_nr_bmap = 0, i; + + if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_PAGE_BITMAP) && + vb->nr_page_bm...

...= cpu_to_le16(req_id); + if (!done) + hdr->flag = BALLOON_FLAG_CONT; + else + hdr->flag = BALLOON_FLAG_DONE; + + if (pos > 0 || done) + send_resp_data(vb, vq, true); + +} + +static void send_unused_pages(struct virtio_balloon *vb, + unsigned long req_id) +{ + struct scatterlist sg_in; + unsigned int pos = 0; + struct virtqueue *vq = vb->host_req_vq; + int ret, order; + struct zone *zone = NULL; + bool part_fill = false; + + mutex_lock(&vb->balloon_lock); + + for (order = MAX_ORDER - 1; order >= 0; order--) { + ret = record_unused_pages(&zone, order, vb->res...

The current QEMU live migration implementation mark the all the guest's RAM pages as dirtied in the ram bulk stage, all these pages will be processed and that takes quit a lot of CPU cycles. >From guest's point of view, it doesn't care about the content in free pages. We can make use of this fact and skip processing the free pages in the ram bulk stage, it can save a lot CPU cycles

The current QEMU live migration implementation mark the all the guest's RAM pages as dirtied in the ram bulk stage, all these pages will be processed and that takes quit a lot of CPU cycles. >From guest's point of view, it doesn't care about the content in free pages. We can make use of this fact and skip processing the free pages in the ram bulk stage, it can save a lot CPU cycles

...'re not using are enqueued * at vb_dev_info->pages list. @@ -551,6 +555,58 @@ static void update_balloon_stats(struct virtio_balloon *vb) pages_to_bytes(available)); } +static void send_unused_pages_info(struct virtio_balloon *vb, + unsigned long req_id) +{ + struct scatterlist sg_in; + unsigned long pos = 0; + struct virtqueue *vq = vb->req_vq; + struct virtio_balloon_resp_hdr *hdr = vb->resp_hdr; + int ret, order; + + mutex_lock(&vb->balloon_lock); + + for (order = MAX_ORDER - 1; order >= 0; order--) { + pos = 0; + ret = get_unused_pages(vb->resp_data, +...

...AGES; + hdr->id = req_id; + if (!done) + hdr->flag = BALLOON_FLAG_CONT; + else + hdr->flag = BALLOON_FLAG_DONE; + + if (pos > 0 || done) + send_resp_data(vb, vq, true); + +} + +static void send_unused_pages(struct virtio_balloon *vb, + unsigned long req_id) +{ + struct scatterlist sg_in; + unsigned int pos = 0; + struct virtqueue *vq = vb->host_req_vq; + int ret, order; + struct zone *zone = NULL; + bool part_fill = false; + + mutex_lock(&vb->balloon_lock); + + for (order = MAX_ORDER - 1; order >= 0; order--) { + ret = mark_unused_pages(&zone, order, vb->resp_...

...pages list. > @@ -373,6 +378,49 @@ static void update_balloon_stats(struct virtio_balloon *vb) > pages_to_bytes(available)); > } > > +static void update_free_pages_stats(struct virtio_balloon *vb, why _stats? > + unsigned long req_id) > +{ > + struct scatterlist sg_in, sg_out; > + unsigned long pfn = 0, bmap_len, max_pfn; > + struct virtqueue *vq = vb->misc_vq; > + struct balloon_bmap_hdr *hdr = vb->bmap_hdr; > + int ret = 1; > + > + max_pfn = get_max_pfn(); > + mutex_lock(&vb->balloon_lock); > + while (pfn < max_pfn) { &g...

...pages list. > @@ -373,6 +378,49 @@ static void update_balloon_stats(struct virtio_balloon *vb) > pages_to_bytes(available)); > } > > +static void update_free_pages_stats(struct virtio_balloon *vb, why _stats? > + unsigned long req_id) > +{ > + struct scatterlist sg_in, sg_out; > + unsigned long pfn = 0, bmap_len, max_pfn; > + struct virtqueue *vq = vb->misc_vq; > + struct balloon_bmap_hdr *hdr = vb->bmap_hdr; > + int ret = 1; > + > + max_pfn = get_max_pfn(); > + mutex_lock(&vb->balloon_lock); > + while (pfn < max_pfn) { &g...

...iver +//----------------------------------------------------------------------------- + +static ssize_t +virtio_buf_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + char tmp_buf[MAX_DATA_SIZE]; + int retval; + struct scatterlist sg_in, sg_out; + struct scatterlist *request[2]; + /* cast dev into a virtio_device */ + struct virtio_device *vdev = dev_to_virtio(dev); + struct virtexample_info *vi = vdev->priv; + + /* copy the user buffer since it is a const buffer */ + sprintf(tmp_buf, "%s", buf); + + /*...

This patch series implements two optimizations: 1) transfer pages in chuncks between the guest and host; 2) transfer the guest unused pages to the host so that they can be skipped to migrate in live migration. Please read each patch commit log for details. Changes: v7->v8: 1) Use only one chunk format, instead of two. 2) re-write the virtio-balloon implementation patch. 3) commit changes 4)

This patch series implements two optimizations: 1) transfer pages in chuncks between the guest and host; 2) transfer the guest unused pages to the host so that they can be skipped to migrate in live migration. Please read each patch commit log for details. Changes: v7->v8: 1) Use only one chunk format, instead of two. 2) re-write the virtio-balloon implementation patch. 3) commit changes 4)

...->vdev->dev, "%s: chunk %d of unknown pages\n", __func__, type); @@ -686,28 +708,139 @@ static void update_balloon_size_func(struct work_struct *work) queue_work(system_freezable_wq, work); } +static void miscq_in_hdr_add(struct virtio_balloon *vb) +{ + struct scatterlist sg_in; + + sg_init_one(&sg_in, vb->miscq_in_hdr, + sizeof(struct virtio_balloon_miscq_hdr)); + if (virtqueue_add_inbuf(vb->miscq, &sg_in, 1, vb->miscq_in_hdr, + GFP_KERNEL) < 0) { + __virtio_clear_bit(vb->vdev, + VIRTIO_BALLOON_F_MISC_VQ); + dev_warn(&vb->vd...

On 11/30/2016 12:43 AM, Liang Li wrote: > +static void send_unused_pages_info(struct virtio_balloon *vb, > + unsigned long req_id) > +{ > + struct scatterlist sg_in; > + unsigned long pos = 0; > + struct virtqueue *vq = vb->req_vq; > + struct virtio_balloon_resp_hdr *hdr = vb->resp_hdr; > + int ret, order; > + > + mutex_lock(&vb->balloon_lock); > + > + for (order = MAX_ORDER - 1; order >= 0; order--) { I scratched my he...

On 11/30/2016 12:43 AM, Liang Li wrote: > +static void send_unused_pages_info(struct virtio_balloon *vb, > + unsigned long req_id) > +{ > + struct scatterlist sg_in; > + unsigned long pos = 0; > + struct virtqueue *vq = vb->req_vq; > + struct virtio_balloon_resp_hdr *hdr = vb->resp_hdr; > + int ret, order; > + > + mutex_lock(&vb->balloon_lock); > + > + for (order = MAX_ORDER - 1; order >= 0; order--) { I scratched my he...

This patchset is for kernel and contains two parts of change to the virtio-balloon. One is the change for speeding up the inflating & deflating process, the main idea of this optimization is to use bitmap to send the page information to host instead of the PFNs, to reduce the overhead of virtio data transmission, address translation and madvise(). This can help to improve the performance by

This patchset is for kernel and contains two parts of change to the virtio-balloon. One is the change for speeding up the inflating & deflating process, the main idea of this optimization is to use bitmap to send the page information to host instead of the PFNs, to reduce the overhead of virtio data transmission, address translation and madvise(). This can help to improve the performance by

This patch set contains two parts of changes to the virtio-balloon. One is the change for speeding up the inflating & deflating process, the main idea of this optimization is to use bitmap to send the page information to host instead of the PFNs, to reduce the overhead of virtio data transmission, address translation and madvise(). This can help to improve the performance by about 85%.

This patch set contains two parts of changes to the virtio-balloon. One is the change for speeding up the inflating & deflating process, the main idea of this optimization is to use bitmap to send the page information to host instead of the PFNs, to reduce the overhead of virtio data transmission, address translation and madvise(). This can help to improve the performance by about 85%.

This patch set contains two parts of changes to the virtio-balloon. One is the change for speeding up the inflating & deflating process, the main idea of this optimization is to use bitmap to send the page information to host instead of the PFNs, to reduce the overhead of virtio data transmission, address translation and madvise(). This can help to improve the performance by about 85%.