On Sat, Apr 18, 2020 at 5:14 AM Andres Freund <andres@anarazel.de> wrote:
>
> zstd -T0 < onegbofrandom > NUL
> zstd -T0 < onegbofrandom > /dev/null
> linux host: 0.361s
> windows guest: 0.602s
>
> zstd -T0 < onegbofrandom | dd bs=1M of=NUL
> zstd -T0 < onegbofrandom | dd bs=1M of=/dev/null
> linux host: 0.454s
> windows guest: 0.802s
>
> zstd -T0 < onegbofrandom | dd bs=64k | dd bs=64k | dd bs=64k | wc -c
> linux host: 0.521s
> windows guest: 1.376s
>
>
> This suggest that pipes do have a considerably higher overhead on
> windows, but that it's not all that terrible if one takes care to use
> large buffers in each pipe element.
>
I have also done some similar experiments on my Win-7 box and the
results are as follows:
zstd -T0 < 16396 > NUL
Execution time: 2.240 s
zstd -T0 < 16396 | dd bs=1M > NUL
Execution time: 4.240 s
zstd -T0 < 16396 | dd bs=64k | dd bs=64k | dd bs=64k | wc -c
Execution time: 5.959 s
In the above tests, 16396 is a 1GB file generated via pgbench. The
above results indicate that adding more pipe chains with dd adds
significant overhead but how can we distinguish what is exact overhead
due to pipe?
--
With Regards,
Amit Kapila.
EnterpriseDB: http://www.enterprisedb.com