[systemd-devel] bootchart issues on slow hardware

[Kok, Auke-jan H]

On Mon, Mar 18, 2013 at 2:50 PM, Kok, Auke-jan H
<auke-jan.h.kok at intel.com> wrote:
> On Mon, Mar 18, 2013 at 11:57 AM, Reindl Harald <h.reindl at thelounge.net> wrote:
>>
>>
>> Am 18.03.2013 19:45, schrieb Kay Sievers:
>>> I put an SSD in that crappy box today; it's down from 25 to 7 sec on
>>> the otherwise identical system. :)
>>>
>>> So I'll not need to debug any rotating media issues, I don't have any
>>> of them again. :)
>>
>> this is nice for you
>>
>> but keep in mind that for professional environments for many
>> years SSD is no option for some TB of data and even if
>> the price falls down you have to calculate redundancy for
>> RAID10 environemnts which can not be raplced by a SSD
>> due lack of relieability and no real-world expierience
>> how long they run and how you detect errors before it is
>> too late
>
> I'm of the same mindset.
>
> For some time to come, many people will continue to purchase lower end
> systems without SSD's, and we want to offer them a compelling OS that
> outperforms the competitors in all aspects, including boot time.
>
> So, I consider the bad performance on non-SSD's a bug, and I'm looking
> at trying to find a solution.

For those with spinning drives with ext3/4 (NOT btrfs), please test
the patch I just posted - it should make a modest difference.

While I'm not certain the total boot time will improve (the numbers
don't show a significant difference there), it seems to have a major
effect at making udev and mount finish a lot faster - on my test
system things like low level dbus services started 5-7 seconds
earlier.

Auke