Optimize screendump
When running kvm-autotest, fputc() is often the second highest (sometimes #1)
function showing up in a profile. This is due to fputc() locking the file
for every byte written.
Optimize by buffering a line's worth of pixels and writing that out in a
single call.
Reviewed-by: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
diff --git a/hw/vga.c b/hw/vga.c
index 124295a..0f54734 100644
--- a/hw/vga.c
+++ b/hw/vga.c
@@ -2346,15 +2346,19 @@
uint32_t v;
int y, x;
uint8_t r, g, b;
+ int ret;
+ char *linebuf, *pbuf;
f = fopen(filename, "wb");
if (!f)
return -1;
fprintf(f, "P6\n%d %d\n%d\n",
ds->width, ds->height, 255);
+ linebuf = qemu_malloc(ds->width * 3);
d1 = ds->data;
for(y = 0; y < ds->height; y++) {
d = d1;
+ pbuf = linebuf;
for(x = 0; x < ds->width; x++) {
if (ds->pf.bits_per_pixel == 32)
v = *(uint32_t *)d;
@@ -2366,13 +2370,16 @@
(ds->pf.gmax + 1);
b = ((v >> ds->pf.bshift) & ds->pf.bmax) * 256 /
(ds->pf.bmax + 1);
- fputc(r, f);
- fputc(g, f);
- fputc(b, f);
+ *pbuf++ = r;
+ *pbuf++ = g;
+ *pbuf++ = b;
d += ds->pf.bytes_per_pixel;
}
d1 += ds->linesize;
+ ret = fwrite(linebuf, 1, pbuf - linebuf, f);
+ (void)ret;
}
+ qemu_free(linebuf);
fclose(f);
return 0;
}
