Date: Wed, 16 Apr 2008 08:45:56 -0400 From: Robert Huff <roberthuff@rcn.com> To: "Stanislav Antic" <lists.stanislav.antic@gmail.com> Cc: freebsd-questions@freebsd.org Subject: Re: How to switch scheduler on 7.0? Message-ID: <18437.62724.679769.189650@jerusalem.litteratus.org> In-Reply-To: <282f7f940804152334m1c03d300xffd8e3c350c22822@mail.gmail.com> References: <200804152159.46589.daniel.tourde@spray.se> <alpine.BSF.1.10.0804160027060.2352@duane.dbq.yournetplus.com> <18437.34871.726719.679184@jerusalem.litteratus.org> <282f7f940804152332y4f5cadfdob9d3957dcb265a57@mail.gmail.com> <282f7f940804152334m1c03d300xffd8e3c350c22822@mail.gmail.com>
next in thread | previous in thread | raw e-mail | index | archive | help
Stanislav Antic writes: > > ULE has substantial improvements over BSD for multiprocessor > > hardware. > > > Does ULE works better on a single CPU machines? I an not an expert; however, based on material reported here: In terms of perforance, ULE and BSD are equivalent on UP machines - BSD works better in some cases, ULE in others. If I had to put money down, I'd give a very slight advantage to ULE. Measured by stability, ULE is a moderate win. Absent specific cases to the contrary, one reason to go with ULE is that it where future development is focused. That's not to say BSD is being kicked off the train, exactly, just that it won't be the target for the latest and greatest. More qualified voices will please tell what I have remembered wrong. Robert Huff
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?18437.62724.679769.189650>