Date: Tue, 5 May 2020 20:48:38 +0200 From: Ralf Mardorf <ralf.mardorf@rocketmail.com> To: freebsd-questions@freebsd.org Subject: Re: Which version of freebsd Is faster: amd64 or i386? Message-ID: <20200505204838.5b92ee09@archlinux> In-Reply-To: <4323681588671834@sas1-55829ddbd171.qloud-c.yandex.net> References: <4323681588671834@sas1-55829ddbd171.qloud-c.yandex.net>
next in thread | previous in thread | raw e-mail | index | archive | help
All those generalized question related to performance and speed are moot. Better questions are probably, why is hardware migrating from 32bit to 64bit architecture? What is the purpose of swap? Why are there new versions of file systems? A nice example, for faster is not always better: "noatime Do not update the file access time when reading from a file. This option is useful on file systems where there are large numbers of files and performance is more criti-cal than updating the file access time (which is rarely ever important). This option is currently only supported on local file systems." - https://www.freebsd.org/cgi/man.cgi?mount(8) "relatime Update inode access times relative to modify or change time. Access time is only updated if the previous access time was earlier than the current modify or change time. (Similar to noatime, but it doesn't break mutt or other applications that need to know if a file has been read since the last time it was modified.)" - http://manpages.ubuntu.com/manpages/focal/man8/mount.8.html Are such mount options still useful when using SSDs instead of spinning drives? It unlikely makes a noticeable difference when file access time gets always updated, nor would it seriously shorten lifetime of a SSD. OTOH after migrating from HDD to SSD, why editing fstab, if those options worked well for the old HDDs, while they don't have a negative impact on SSDs? You could overclock the CPU, play around with PCI latency and other critical things, to get a faster but unstable machine. You could use a text-based web browser instead of a GUI web browser, to waste less resources of a computer but to suffer from the limitations of a text-based web browser. Experts could speed up a machine by tweaking a few things, but even for experts the golden rule is "less is more" and it usually requires a lot of trial and error. Staying with less optimal defaults could save time. Ok, you want to learn, so you are asking a few questions. But IMO your questions are way too abstract. What is your domain? On one of my Linux DAWs unbinding USB ports that shared an IRQ with something important did improve performance, on the machine I'm using now it's impossible to do it, but even shared IRQs don't have a negative impact on that new machine. A shorter and quicker path could improve performance a lot, but maybe at the cost of being more vulnerable to Meltdown and Spectre. Performance is always related to the hardware and the domain. A video entertainment machine, a server ...
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20200505204838.5b92ee09>