[systemd-devel] Antw: Re: device enumeration by systemd user instances

Greg Kroah-Hartman gregkh at linuxfoundation.org
Mon Jul 29 07:10:31 UTC 2019


On Mon, Jul 29, 2019 at 08:57:26AM +0200, Ulrich Windl wrote:
> >>> Greg KH <gregkh at linuxfoundation.org> schrieb am 25.07.2019 um 17:45 in
> Nachricht <20190725154555.GA6487 at kroah.com>:
> > On Thu, Jul 25, 2019 at 05:29:33PM +0200, Pawel Szewczyk wrote:
> >> On 7/17/19 23:14, Greg KH wrote:
> >> > 
> >> > 100ms seems like a really long time, what exactly is it doing during
> >> > that time?  Is the kernel spending too much time regenerating the
> >> > uevents?
> >> > 
> >> > How many devices are you talking about?  Any chance to see what really
> >> > is happening here by running perf to see where the hot-spots are?
> >> 
> >> There are ~80 devices being enumerated and 1ms per device still seem a 
> >> little too long. Note, that we are running this on arm architecture.
> 
> I wonder: Doesn't that depend on the individual devices? I can
> remember that "Scanning the SCSI bus" in HP-UX had always been a
> matter of minutes...

This _after_ the devices are all found by the kernel, not before :)

And odds are, if this is a random ARM device, these are all platform
devices and there should not be any bus scannning time involved by the
kernel as all of the device information is available in the DT file
ahead of time.

thanks,

greg k-h


More information about the systemd-devel mailing list