|
| From: | Anthony Liguori |
| Subject: | Re: [Qemu-devel] [PATCH 2/3] ui/vnc: optimize dirty bitmap tracking |
| Date: | Mon, 18 Nov 2013 08:27:21 -0800 |
On Nov 18, 2013 12:20 AM, "Peter Lieven" <address@hidden> wrote:
>
> vnc_update_client currently scans the dirty bitmap of each client
> bitwise which is a very costly operation if only few bits are dirty.
> vnc_refresh_server_surface does almost the same.
> this patch optimizes both by utilizing the heavily optimized
> function find_next_bit to find the offset of the next dirty
> bit in the dirty bitmaps.
>
> Signed-off-by: Peter Lieven <address@hidden>
Can you include performance data?
Regards,
Anthony Liguori
> ---
> ui/vnc.c | 146 ++++++++++++++++++++++++++++++++++++++------------------------
> ui/vnc.h | 3 ++
> 2 files changed, 92 insertions(+), 57 deletions(-)
>
> diff --git a/ui/vnc.c b/ui/vnc.c
> index 67b1f75..edf33be 100644
> --- a/ui/vnc.c
> +++ b/ui/vnc.c
> @@ -572,6 +572,16 @@ void *vnc_server_fb_ptr(VncDisplay *vd, int x, int y)
> ptr += x * VNC_SERVER_FB_BYTES;
> return ptr;
> }
> +/* this sets only the visible pixels of a dirty bitmap */
> +#define VNC_SET_VISIBLE_PIXELS_DIRTY(bitmap, w, h) {\
> + int x, y;\
> + memset(bitmap, 0x00, sizeof(bitmap));\
> + for (y = 0; y < h; y++) {\
> + for (x = 0; x < w / VNC_DIRTY_PIXELS_PER_BIT; x++) {\
> + set_bit(x, bitmap[y]);\
> + } \
> + } \
> + }
>
> static void vnc_dpy_switch(DisplayChangeListener *dcl,
> DisplaySurface *surface)
> @@ -597,7 +607,9 @@ static void vnc_dpy_switch(DisplayChangeListener *dcl,
> qemu_pixman_image_unref(vd->guest.fb);
> vd->guest.fb = pixman_image_ref(surface->image);
> vd->guest.format = surface->format;
> - memset(vd->guest.dirty, 0xFF, sizeof(vd->guest.dirty));
> + VNC_SET_VISIBLE_PIXELS_DIRTY(vd->guest.dirty,
> + surface_width(vd->ds),
> + surface_height(vd->ds));
>
> QTAILQ_FOREACH(vs, &vd->clients, next) {
> vnc_colordepth(vs);
> @@ -605,7 +617,9 @@ static void vnc_dpy_switch(DisplayChangeListener *dcl,
> if (vs->vd->cursor) {
> vnc_cursor_define(vs);
> }
> - memset(vs->dirty, 0xFF, sizeof(vs->dirty));
> + VNC_SET_VISIBLE_PIXELS_DIRTY(vs->dirty,
> + surface_width(vd->ds),
> + surface_height(vd->ds));
> }
> }
>
> @@ -882,6 +896,14 @@ static int vnc_update_client_sync(VncState *vs, int has_dirty)
> return ret;
> }
>
> +#define VNC_CLIENT_UPDATE_RECT() \
> + if (last_x != -1) {\
> + int h = find_and_clear_dirty_height(vs, y, last_x, x, height);\
> + n += vnc_job_add_rect(job,\
> + last_x * VNC_DIRTY_PIXELS_PER_BIT, y,\
> + (x - last_x) * VNC_DIRTY_PIXELS_PER_BIT, h);\
> + }
> +
> static int vnc_update_client(VncState *vs, int has_dirty)
> {
> if (vs->need_update && vs->csock != -1) {
> @@ -910,35 +932,32 @@ static int vnc_update_client(VncState *vs, int has_dirty)
> width = MIN(pixman_image_get_width(vd->server), vs->client_width);
> height = MIN(pixman_image_get_height(vd->server), vs->client_height);
>
> - for (y = 0; y < height; y++) {
> + y = 0;
> + for (;;) {
> int x;
> int last_x = -1;
> - for (x = 0; x < width / VNC_DIRTY_PIXELS_PER_BIT; x++) {
> + unsigned long offset = find_next_bit((unsigned long *) &vs->dirty,
> + height * VNC_DIRTY_BITS_PER_LINE(vs),
> + y * VNC_DIRTY_BITS_PER_LINE(vs));
> + if (offset == height * VNC_DIRTY_BITS_PER_LINE(vs)) {
> + /* no more dirty bits */
> + break;
> + }
> + y = offset / VNC_DIRTY_BITS_PER_LINE(vs);
> +
> + for (x = offset % VNC_DIRTY_BITS_PER_LINE(vs);
> + x < width / VNC_DIRTY_PIXELS_PER_BIT; x++) {
> if (test_and_clear_bit(x, vs->dirty[y])) {
> if (last_x == -1) {
> last_x = x;
> }
> } else {
> - if (last_x != -1) {
> - int h = find_and_clear_dirty_height(vs, y, last_x, x,
> - height);
> -
> - n += vnc_job_add_rect(job,
> - last_x * VNC_DIRTY_PIXELS_PER_BIT,
> - y,
> - (x - last_x) * VNC_DIRTY_PIXELS_PER_BIT,
> - h);
> - }
> + VNC_CLIENT_UPDATE_RECT();
> last_x = -1;
> }
> }
> - if (last_x != -1) {
> - int h = find_and_clear_dirty_height(vs, y, last_x, x, height);
> - n += vnc_job_add_rect(job, last_x * VNC_DIRTY_PIXELS_PER_BIT,
> - y,
> - (x - last_x) * VNC_DIRTY_PIXELS_PER_BIT,
> - h);
> - }
> + VNC_CLIENT_UPDATE_RECT();
> + y++;
> }
>
> vnc_job_push(job);
> @@ -2676,8 +2695,8 @@ static int vnc_refresh_server_surface(VncDisplay *vd)
> int width = pixman_image_get_width(vd->guest.fb);
> int height = pixman_image_get_height(vd->guest.fb);
> int y;
> - uint8_t *guest_row;
> - uint8_t *server_row;
> + uint8_t *guest_row0 = NULL, *server_row0;
> + int guest_stride, server_stride;
> int cmp_bytes;
> VncState *vs;
> int has_dirty = 0;
> @@ -2702,44 +2721,57 @@ static int vnc_refresh_server_surface(VncDisplay *vd)
> if (vd->guest.format != VNC_SERVER_FB_FORMAT) {
> int width = pixman_image_get_width(vd->server);
> tmpbuf = qemu_pixman_linebuf_create(VNC_SERVER_FB_FORMAT, width);
> - }
> - guest_row = (uint8_t *)pixman_image_get_data(vd->guest.fb);
> - server_row = (uint8_t *)pixman_image_get_data(vd->server);
> - for (y = 0; y < height; y++) {
> - if (!bitmap_empty(vd->guest.dirty[y], VNC_DIRTY_BITS)) {
> - int x;
> - uint8_t *guest_ptr;
> - uint8_t *server_ptr;
> + } else {
> + guest_row0 = (uint8_t *)pixman_image_get_data(vd->guest.fb);
> + }
> + server_row0 = (uint8_t *)pixman_image_get_data(vd->server);
> + guest_stride = pixman_image_get_stride(vd->guest.fb);
> + server_stride = pixman_image_get_stride(vd->server);
> +
> + y = 0;
> + for (;;) {
> + int x;
> + uint8_t *guest_ptr, *server_ptr;
> + unsigned long offset = find_next_bit((unsigned long *) &vd->guest.dirty,
> + height * VNC_DIRTY_BITS_PER_LINE(&vd->guest),
> + y * VNC_DIRTY_BITS_PER_LINE(&vd->guest));
> + if (offset == height * VNC_DIRTY_BITS_PER_LINE(&vd->guest)) {
> + /* no more dirty bits */
> + break;
> + }
> + y = offset / VNC_DIRTY_BITS_PER_LINE(&vd->guest);
>
> - if (vd->guest.format != VNC_SERVER_FB_FORMAT) {
> - qemu_pixman_linebuf_fill(tmpbuf, vd->guest.fb, width, 0, y);
> - guest_ptr = (uint8_t *)pixman_image_get_data(tmpbuf);
> - } else {
> - guest_ptr = guest_row;
> - }
> - server_ptr = server_row;
> + server_ptr = server_row0 + y * server_stride;
>
> - for (x = 0; x + VNC_DIRTY_PIXELS_PER_BIT - 1 < width;
> - x += VNC_DIRTY_PIXELS_PER_BIT, guest_ptr += cmp_bytes,
> - server_ptr += cmp_bytes) {
> - if (!test_and_clear_bit((x / VNC_DIRTY_PIXELS_PER_BIT),
> - vd->guest.dirty[y])) {
> - continue;
> - }
> - if (memcmp(server_ptr, guest_ptr, cmp_bytes) == 0) {
> - continue;
> - }
> - memcpy(server_ptr, guest_ptr, cmp_bytes);
> - if (!vd->non_adaptive)
> - vnc_rect_updated(vd, x, y, &tv);
> - QTAILQ_FOREACH(vs, &vd->clients, next) {
> - set_bit((x / VNC_DIRTY_PIXELS_PER_BIT), vs->dirty[y]);
> - }
> - has_dirty++;
> + if (vd->guest.format != VNC_SERVER_FB_FORMAT) {
> + qemu_pixman_linebuf_fill(tmpbuf, vd->guest.fb, width, 0, y);
> + guest_ptr = (uint8_t *)pixman_image_get_data(tmpbuf);
> + } else {
> + guest_ptr = guest_row0 + y * guest_stride;
> + }
> +
> + for (x = offset % VNC_DIRTY_BITS_PER_LINE(&vd->guest);
> + x + VNC_DIRTY_PIXELS_PER_BIT - 1 < width;
> + x += VNC_DIRTY_PIXELS_PER_BIT, guest_ptr += cmp_bytes,
> + server_ptr += cmp_bytes) {
> + if (!test_and_clear_bit((x / VNC_DIRTY_PIXELS_PER_BIT),
> + vd->guest.dirty[y])) {
> + continue;
> + }
> + if (memcmp(server_ptr, guest_ptr, cmp_bytes) == 0) {
> + continue;
> + }
> + memcpy(server_ptr, guest_ptr, cmp_bytes);
> + if (!vd->non_adaptive) {
> + vnc_rect_updated(vd, x, y, &tv);
> }
> + QTAILQ_FOREACH(vs, &vd->clients, next) {
> + set_bit((x / VNC_DIRTY_PIXELS_PER_BIT), vs->dirty[y]);
> + }
> + has_dirty++;
> }
> - guest_row += pixman_image_get_stride(vd->guest.fb);
> - server_row += pixman_image_get_stride(vd->server);
> +
> + y++;
> }
> qemu_pixman_image_unref(tmpbuf);
> return has_dirty;
> diff --git a/ui/vnc.h b/ui/vnc.h
> index 4a8f33c..82c8ea8 100644
> --- a/ui/vnc.h
> +++ b/ui/vnc.h
> @@ -88,6 +88,9 @@ typedef void VncSendHextileTile(VncState *vs,
> /* VNC_DIRTY_BITS is the number of bits in the dirty bitmap. */
> #define VNC_DIRTY_BITS (VNC_MAX_WIDTH / VNC_DIRTY_PIXELS_PER_BIT)
>
> +/* VNC_DIRTY_BITS_PER_LINE might be greater than VNC_DIRTY_BITS due to alignment */
> +#define VNC_DIRTY_BITS_PER_LINE(x) (sizeof((x)->dirty) / VNC_MAX_HEIGHT * BITS_PER_BYTE)
> +
> #define VNC_STAT_RECT 64
> #define VNC_STAT_COLS (VNC_MAX_WIDTH / VNC_STAT_RECT)
> #define VNC_STAT_ROWS (VNC_MAX_HEIGHT / VNC_STAT_RECT)
> --
> 1.7.9.5
>
>
| [Prev in Thread] | Current Thread | [Next in Thread] |