Date: Tue, 28 Mar 2006 11:59:23 -0800 From: Julian Elischer <julian@elischer.org> To: Joe Koberg <joe@osoft.us> Cc: freebsd-hackers@freebsd.org Subject: Re: cloning a FreeBSD HDD Message-ID: <4429959B.4070209@elischer.org> In-Reply-To: <44296F41.1050209@osoft.us> References: <HCEOIFALKKLBLJPENPNOMEMNCAAA.khaled@ipbill.com> <17444.13967.998120.314837@bhuda.mired.org> <200603281139.29588.doconnor@gsoft.com.au> <200603272210.43032.soralx@cydem.org> <44296F41.1050209@osoft.us>
next in thread | previous in thread | raw e-mail | index | archive | help
Joe Koberg wrote: > soralx@cydem.org wrote: > >>> On Saturday 25 March 2006 04:42, Mike Meyer wrote: >>> >>> >>>> One thing: 1m is a bit small for modern systems. Or for not-so-modern >>>> systems. Since nothing else is running, you might as well use all the >>>> memory you've got, or as big as you can get a process to be. 128m or >>>> more is perfectly reasonable. >>>> >>> >>> It won't go any faster.. >>> >>> In a modern system the CPU is so much faster than the disk than >>> anything above about 16k would be enough. >>> >> >> >> I found 64k to be optimal (e.g, max performance) on most machines >> >> > > I heard its faster if you use two dd's; i.e: > > # dd if=/dev/ad0 bs=64k | dd of=/dev/ad1 bs=64k > > allowing read and write to proceed in parallel. that's what ddd and 'team' are for. I don't know if ddd is in the ports as it may clash inname with teh debugger ddd They internally fork and use several processes synchronised in some manner. > > Joe Koberg > joe at osoft dot us > > > _______________________________________________ > freebsd-hackers@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-hackers > To unsubscribe, send any mail to > "freebsd-hackers-unsubscribe@freebsd.org"
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?4429959B.4070209>