> Marco Peereboom wrote: >> You are right about how awful all this stuff is. Man it seems like you >> should use an os that suits your goals a little better. I have heard >> that Linux offers awesome performance. >> > > > based on the manner in which you routinely complain and provide zero > deliverables, i must say that marco's suggestion is spot on. please join > the ranks of all the rest of the feature-hungry talentless morons and > just give up. if you have not figured out that you are a member of this > group already you need to flash your brain bios so there is some hope of > working around the parts that are obviously not working right. > > if you send another whining email about things that have already been > discussed on this list i worry that you will break the misc@openbsd.org > mailserver. don't be that guy.
That is total crap. I wrote Marco personaly, provided all informations and asked if he needs further benchmarks or what-so-ever. Please do not line up to the lines of people critic me without knowing what I did off-list. It's like the PF bug you know? You write a developer.. you receive no answer and the patch which gets released does not even fix the affected codebase but add's a "workaround". But related to the svnd it should be something YOU should be able to confirm too. Also others confirmed the existence of the issue as well (+me). http://groups.google.com.ua/group/mailing.openbsd.bugs/browse_thread/thread/0348c42850b1732e http://archives.neohapsis.com/archives/openbsd/2008-06/1740.html And so on... I even wrote Marco personaly so stop the rant. :-) I gonna do again a bonnie++ benchmark and again I will post my DMESG and again that will solve nothing. But the benchmark will take some hours anyway. Everybody should be able to confirm that the write speed is not "slower". It seriously feels like PIO MODE 3-4 and fsck brings you a lot "biowait" complains. And that is HW indipendent here so the svnd-Code suffers from some kind of a bug. How do I come to that awesome analyse? I browsed the mailinglist archives and found complains by svnd users just after 4.2 Example: http://kerneltrap.org/mailarchive/openbsd-misc/2007/11/14/412688/thread#mid-412688 And IF crypto IS slower and IF i just have to life with it: How come softraid0 using a more complex and slower algorithm is faster then the svnd and svnd gets slower and slower each release... But as I said: Gonna benchmark (again..) but that takes time... Kind regards, Sebastian
