Hi Nitin,
On Mon, Aug 9, 2010 at 8:26 PM, Nitin Gupta <ngupta@xxxxxxxxxx> wrote:
> Compression takes much more time than decompression. So, its quite
> wasteful in terms of both CPU cycles and memory usage to have a very
> low compressed page size threshold and thereby storing such not-so-well
> compressible pages as-is (uncompressed). So, increasing it from
> PAGE_SIZE/2 to PAGE_SIZE/8*7. A low threshold was useful when we had
> "backing swap" support where we could forward such pages to the backing
> device (applicable only when zram was used as swap disk).
>
> It is not yet configurable through sysfs but may be exported in future,
> along with threshold for average compression ratio.
>
> Signed-off-by: Nitin Gupta <ngupta@xxxxxxxxxx>
The description makes sense but lacks any real data. What kind of
workloads did you test this with? Where does it help most? How much?
Pekka
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxxx For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>