Date: Mon, 2 Mar 1998 17:50:17 -0500 (EST) From: "John S. Dyson" <toor@dyson.iquest.net> To: karpen@ocean.campus.luth.se (Mikael Karpberg) Cc: toor@dyson.iquest.net, current@FreeBSD.ORG Subject: Re: 3.0-RELEASE? Message-ID: <199803022250.RAA14700@dyson.iquest.net> In-Reply-To: <199803022149.WAA11674@ocean.campus.luth.se> from Mikael Karpberg at "Mar 2, 98 10:49:14 pm"
next in thread | previous in thread | raw e-mail | index | archive | help
Mikael Karpberg said: > According to John S. Dyson: > > Open Systems Networking said: > > > On Sun, 1 Mar 1998, John S. Dyson wrote: > > > > > > > I think that the *biggest* and most complex thing that will be missing > > > > will be the fine-grained SMP. It seems that we'll have ELF support, > > > > but I forget (or simply don't know) if we (they) decided that ELF will be > > > > primary or not. > > > > > > I was hoping to see SMP (in ANY form), kernel threads, RAID, and > > > softupdates, and maybe some TCP stuff, SACK, etc.. > > > But RAID, and SMP, and softupdates isn't bad. > > Can't the current model with SMP be smoothed a bit, to be more of a release > material, and we can at least have non-finegrained-locking SMP? I mean, > SMP is the big thing for 3.0, and what if there has to be a lot of frobbing > done before 3.1 comes out to make it finegrained? It's still nice to have > at least the current SMP level available. It DOES help, after all, and even > the fact that it doesn't ignore more CPUs completely might attract more > people to buy SMP machines, and from there we draw new SMP hackers. IMHO. > To make the kernel have fine-grained locking, it will be approx 6-12 man mos. These changes need to be made by people who are very knowledgeable about the entire kernel. These people are in great demand, and that would push 3.0 out into 1999. I am working on some changes to the kernel that will help SMP performance significantly, but they don't make our SMP "fine grained." This is indeed very very difficult work. > > Oh well... I'm rambling as usual. Any comments? > You *definitely* make very valid points, but 2.2.X is becoming too difficult to maintain, and people are too tempted to use -current (with negative consequences.) This is a difficult judgement call, and I don't think the decisions have been made final. -- John | Never try to teach a pig to sing, dyson@freebsd.org | it just makes you look stupid, jdyson@nc.com | and it irritates the pig. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-current" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199803022250.RAA14700>