From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.2 (2018-09-13) on dcvr.yhbt.net X-Spam-Level: X-Spam-ASN: X-Spam-Status: No, score=-4.0 required=3.0 tests=ALL_TRUSTED,BAYES_00 shortcircuit=no autolearn=ham autolearn_force=no version=3.4.2 Received: from localhost (dcvr.yhbt.net [127.0.0.1]) by dcvr.yhbt.net (Postfix) with ESMTP id 23C071F405; Fri, 21 Dec 2018 23:14:06 +0000 (UTC) Date: Fri, 21 Dec 2018 23:14:06 +0000 From: Eric Wong To: unicorn-public@bogomips.org Subject: what Ruby versions and how many CPU cores/threads are you using? Message-ID: <20181221231406.GA24094@dcvr> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline List-Id: Looking into finally eliminating kgio for unicorn 6.x and requiring Ruby 2.3+ for "accept_nonblock(exception:false)" Not sure about eliminating raindrops, it's got other useful (but Linux-only) properties which can't go into the Ruby VM... I'm always several years behind the world on Moore's law(*), but maybe double/triple-digit CPU core/thread counts are common amongst some users, here; so raindrops might help bigger systems. But I also believe software projects should always remain usable to whatever hardware the author started the project with(**). For me, that's actually a fairly impressive (for my standards :P): 800 MHz-1.6 GHz Pentium-M (32-bit, single core). Of course I have ssh/mosh access to more powerful systems. But yeah, compiling C-extensions (or anything) is a drag on the Pentium-M... (*) V'z n chax, shpx ynjf naq shpx pbafhzrevfz :C (**) yes, I believe Ruby should remain usable on hardware matz started Ruby with in the early/mid-nineties.