Date: Fri, 23 Dec 2011 12:01:33 +0100 From: "O. Hartmann" <ohartman@mail.zedat.fu-berlin.de> To: Daniel Kalchev <daniel@digsys.bg> Cc: freebsd-performance@freebsd.org, freebsd-current@freebsd.org, Igor Mozolevsky <igor@hybrid-lab.co.uk> Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server Message-ID: <4EF45F8D.9030404@mail.zedat.fu-berlin.de> In-Reply-To: <4EF444BB.9090400@digsys.bg> References: <xf5fxrkpagw2qf65tk9y2njf.1324492907631@email.android.com> <4EF25468.9040204@gmail.com> <CAOjFWZ7%2Bx61QPB-cO5ppWwY-nCRFvs9P76H_SO%2BCSL41APLwsA@mail.gmail.com> <CADWvR2jVPkLrM686Xhk12U0poV7CCqB3LF_ZbTPTHFKjt%2BdP=g@mail.gmail.com> <4EF2C613.3020609@digsys.bg> <CADWvR2jQMcOrPEzU5Ug4TRp9hxvD6qOVTZYjqqozarA-%2B-DsQw@mail.gmail.com> <4EF3D68C.2060803@zedat.fu-berlin.de> <4EF444BB.9090400@digsys.bg>
next in thread | previous in thread | raw e-mail | index | archive | help
On 12/23/11 10:07, Daniel Kalchev wrote: > > > On 23.12.11 03:17, O. Hartmann wrote: >> Or even look at the thread regarding to SCHED_ULE. Why has a user, >> experiencing really worse performance with SCHED_ULE, in a nearly >> scientific manner some engineer the fault? I'd expect the developer or >> care-taking engineer taking care in a more user friendly manner. > > You remember that those developers are not paid to do what they do? > You remember that nobody has sold you this OS and promised support in > whatever form? Well, as far as I know, the FreeBSD project is funding people doing a certain work! So, the implied opposit, FreeBSD is developed "free" isn't true. > > Still, this issue is discussed publicly and experiments are being made, > I guess also new code is being experimented. > If you are interested in the outcome, just follow the discussion. If you > can help with something and you are willing, please do. There will be > good solution to the SCHED_ULE shortcomings. > > FreeBSD is unique group of people, who all sit on their eggs, be it eggs > they themselves produced, or they inherited one way or another. These > people include all the developers and most of the system administrators > and users of FreeBSD. There is no "they" and "us". What I am in this terminology? I can hardly write some scientific code for my science, I'm able to patch software a bit, that has been developed only for Linux these days (ISIS3 from the USGS, for instance, but I do not dare to publish the crap of port I produced since it is not "professional"). I'm with FreeBSD now since 1996/97. I'm still with the system, although I desperately need scientific grade compilers or GPGPU support. So, even if Linux offers me a really much more convenient way to do my work, I stayed with FreeBSD since there is no real alternative in terms of cleaness of the system. I have also to administer an Ubuntu and Suse server and I feel not amused by this script hell that covers the real system just to get kiddies or Windows-Admins into the "admin-position". And, I dare to put some critics herein! Since I see that FreeBSD is "free", why not trying to make it better and more towards perfect? > > If your preference for the OS is different, you might feel more > comfortable in choosing another OS, probably a commercial OS with > support from the vendor. This is nonesense, you know that, regarding to my case. > >> If a benchmark reveals some severe weak points in FreeBSD and I have >> to read about obscure tweaks of non documented sysctl, then this OS >> would be a no-go if I was a manager to make decissions. > > Luckily, managers do not care about knobs or how difficult it is for the > system administrator to achieve specific goal. All they care is the > bottom line in general and in short therm the goals they have set. No > sane manager will care about benchmarks, as long as he gets what he wants. Well, in real world and beyond this armchair polemics, managers at last do the decissions. Those people dropping math, physics, with no glue to how things work in nature get a degree in law, business and whatsowever and then decide. In my eyes, those are enemies of every development and progress, but this is polemics, too. I faced this many times and it is hard to convince those people not taking care of knobs. But as an admin myself, I need to know about knobs and if essential knobs are not documented, than there is a potential gone for the OS in question. Look at FreeBSD and the problem of how well sysctls and their working are documented. It needs to be fixed. > > Back, to the Phoronix benchmarks. There has already been communication. > Phoronix were given advices on how to better do some things on FreeBSD > (which will make the quality of their benchmarks better and therefore > more trusted). Phoronix has made their updated test suite available to > FreeBSD users (that include developers) to try on their own hardware. By > the way, it is in /usr/ports/benchmarks/phoronix-test-suite. Yes, everyone interseted in this thread and communicating is aware of that fact. > > Linux and FreeBSD are not enemies, they both solve the same problems > with different means. > > Daniel
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?4EF45F8D.9030404>