Date: Mon, 17 Apr 2023 20:38:50 +0100 From: Steve O'Hara-Smith <steve@sohara.org> To: questions@freebsd.org Subject: Re: Docker Message-ID: <20230417203850.94d1e2abb3851fdd41b5330d@sohara.org> In-Reply-To: <f73ef99d-7fa9-ed58-2ce7-80aa26462f79@tundraware.com> References: <20230329053443.6ADA6B6AFED5@dhcp-8e64.meeting.ietf.org> <6002f636-310b-a9fd-b82f-346618976983@timpreston.net> <CA%2B1FSigV_pPwVW%2BDd8WZYGcNQVt7%2BYOcsnJFoRhS6jL5A636pg@mail.gmail.com> <20230412150350.12f97eb2c9dd566b8c8702d2@sohara.org> <CA%2B1FSihVPCQ6tp8u=aqnLyyOPpCMrnhYGcC8bCUgRbFHTdY5sA@mail.gmail.com> <1535315680.2770963.1681309684072@mail.yahoo.com> <20230412155252.5e38ea4728bd52dc798852fc@sohara.org> <1d0a7ed1-9330-49df-9b66-9ee4387de511@app.fastmail.com> <78F4160A-2D26-4A22-9139-A9132FC42688@ellael.org> <20230417133223.3ef5e26c.freebsd@edvax.de> <CA%2B1FSihn%2BB6LTUm7gof6Nd=niL5=dMvQ46HUv=NJ2%2BNhcLS7RQ@mail.gmail.com> <989A99FE-5DA3-4346-B886-32F8E64BA6F0@nimnet.asn.au> <8714f66b-cd2a-2dd3-67ba-9313522ee1b6@tundrawar e.com> <1096316421.4975742.1681752853038@mail.yahoo.com> <e77a0575-2 38d-9ae7-2301-81e82d38a5be@tundraware.com> <1751079266.5066266.1681758046058@mail.yahoo.com> <f73ef99d-7fa9-ed58-2ce7-80aa26462f79@tundraware.com>
next in thread | previous in thread | raw e-mail | index | archive | help
On Mon, 17 Apr 2023 14:11:12 -0500 Tim Daneliuk <tundra@tundraware.com> wrote: > This model is not useful for everything. There have been > attempts, for example, to decompose the FreeBSD kernel itself into > a set of loosely coupled services coordinated via message > passing. If memory services, this was the intent of > DragonflyBSD but I'm not certain of that. Not DragonflyBSD but the Mach kernel is a message passing microkernel and is used in MacOS with a largely FreeBSD based set of unix userland and of course Aqua. DragonflyBSD is something else, it's still monolithic but it handles SMP very differently to FreeBSD (this being the point of departure of the project). The original plan to move to message passing as the basis for native SSI clustering fell by the wayside very early in favour of extremely efficient SMP and the Hammer filesystem. Judging by benchmarks of systems with large numbers of CPUs they have managed to make the kernel scale extremely well. -- Steve O'Hara-Smith <steve@sohara.org>
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20230417203850.94d1e2abb3851fdd41b5330d>