On 06.03.2017 04:35, L A Walsh wrote:
That just sounds too slow to be real -- i.e. you are talking about 146KB/s... and that's not even over a network.
*suspicious* -- wondering about presence of delay loops to discourage people dumping logs...
The SLES bug we opened was investigated by SUSE developers and one comment said something along "the data format heavily favours writes over reads" and that they profiled it and it was taking huge amounts of time hashing database entries for whatever reason. During that 8+ hours, it is 100% occupying one processor core (which is a very tiny fraction of the available CPUs on those systems. This is not a matter of "the machine is slow" or such, it is not easily possible to buy significantly faster machines than the ones we are using. I'll see if it gets better once we can update a few of those boxes to SLES12SP2. The "systemctl status takes a few seconds due to retrieving the log" is on relatively slow machines, Pentium M with rotating rust laptop HDD or my home server, a 3GHz core2 duo with a 2TB 2.5" HDD as main storage (ssd+bcache backed nowadays to make exactly those issues a bit less annyoing). -- Stefan Seyfried "For a successful technology, reality must take precedence over public relations, for nature cannot be fooled." -- Richard Feynman -- To unsubscribe, e-mail: opensuse-factory+unsubscribe@opensuse.org To contact the owner, e-mail: opensuse-factory+owner@opensuse.org