Date: Wed, 16 Sep 2015 11:48:37 +0100 From: Igor Mozolevsky <igor@hybrid-lab.co.uk> To: Bob Bishop <rb@gid.co.uk> Cc: freebsd-hardware@freebsd.org, Konstantin Belousov <kostikbel@gmail.com>, Hackers freeBSD <freebsd-hackers@freebsd.org>, Dieter BSD <dieterbsd@gmail.com>, Andriy Gapon <avg@freebsd.org> Subject: Re: ECC support Message-ID: <CADWvR2gBDjKFRW-X6ECJaGG7tSvOgk0rTk38O1qQ0hUWjRBF_A@mail.gmail.com> In-Reply-To: <93871ADA-EDA3-481C-9959-1D371AB44479@gid.co.uk> References: <CAA3ZYrBXZn1WpHWYGJYWJDPsk7iDahCas8RhnHC4w%2Babf4w4hA@mail.gmail.com> <55F88A18.6090504@FreeBSD.org> <20150916035904.GE67105@kib.kiev.ua> <93871ADA-EDA3-481C-9959-1D371AB44479@gid.co.uk>
next in thread | previous in thread | raw e-mail | index | archive | help
On 16 September 2015 at 08:51, Bob Bishop <rb@gid.co.uk> wrote: <snip> > - You might think that as memory density increases (ie bit cell size shrinks), error rates would increase. Apparently this wasn=E2=80=99t so up = to 2009 at least, see: > > http://www.cs.toronto.edu/~bianca/papers/sigmetrics09.pdf subsection 5.1: "=E2=80=A6 Figure 6 indicates a trend towards worse error behavior for increased capacities, although this trend is not consis- tent. While in some cases the doubling of capacity has a clear negative effect (factors larger than 1 in the graph), in others it has hardly any effect (factor close to 1 in the graph). For example, for Platform A -Mfg1 and Platform F - Mfg1 doubling the capacity increases uncorrectable errors, but not correctable errors. Conversely, for Platform D - Mfg6 doubling the capacity affects correctable errors, but not uncorrectable error." There are also other environmental factors which would be more apparent in "lone-server" configuration vs well maintained and insulated data centres with very good power conditioning ;-) --=20 Igor M.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?CADWvR2gBDjKFRW-X6ECJaGG7tSvOgk0rTk38O1qQ0hUWjRBF_A>