NetBSD-Users archive

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index][Old Index]

Re: Slow read(2) and write(2) syscalls



On my VirtualBox 6.1.6 guest running -current amd64 I get:

$  time cat 80mb > /dev/null
cat 80mb > /dev/null  0.00s user 0.02s system 98% cpu 0.021 total

I presume you used /dev/zero by mistake - it is usually just a source
of zeros. But with it the result is similar:

$ time cat 80mb > /dev/zero
cat 80mb > /dev/zero  0.00s user 0.01s system 97% cpu 0.011 total

The results are identical for virtual disks attached to SATA and SCSI
controllers; the physical storage is an M.2 SATA disk drive.


On Wed, 29 Apr 2020 at 07:19, Sad Clouds <cryintothebluesky%gmail.com@localhost> wrote:
>
> On Wed, 29 Apr 2020 06:57:28 +0200
> Roland Illig <roland.illig%gmx.de@localhost> wrote:
>
> > How can I further research where this artificial delay comes from, and
> > finally fix it?
>
> I've always experienced slow disk I/O with NetBSD on VirtualBox, even
> with fast SSD disks. Not sure if this is a NetBSD bug, or some
> interaction with VirtualBox layers. See this post:
>
> https://mail-index.netbsd.org/netbsd-users/2018/03/18/msg020524.html
>
> I believe there is DTrace for NetBSD, so if you have the time you can
> profile kernel paths and see where the latency comes from.



-- 
----


Home | Main Index | Thread Index | Old Index