From owner-freebsd-hackers@freebsd.org Sat Jul 25 18:21:24 2015 Return-Path: Delivered-To: freebsd-hackers@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id A93E39ABA4E for ; Sat, 25 Jul 2015 18:21:24 +0000 (UTC) (envelope-from deco33000@yandex.com) Received: from forward20h.cmail.yandex.net (forward20h.cmail.yandex.net [87.250.230.162]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client CN "forwards.mail.yandex.net", Issuer "Certum Level IV CA" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id 59440E97; Sat, 25 Jul 2015 18:21:23 +0000 (UTC) (envelope-from deco33000@yandex.com) Received: from web23h.yandex.ru (web23h.yandex.ru [IPv6:2a02:6b8:0:f05::33]) by forward20h.cmail.yandex.net (Yandex) with ESMTP id CBCDF21B65; Sat, 25 Jul 2015 21:21:13 +0300 (MSK) Received: from 127.0.0.1 (localhost [127.0.0.1]) by web23h.yandex.ru (Yandex) with ESMTP id 40915E604D2; Sat, 25 Jul 2015 21:21:13 +0300 (MSK) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=yandex.com; s=mail; t=1437848473; bh=adqvYmo7C0EAZjcvhhpY4aPm/3+XaYhJsa4UZDbwVZc=; h=From:To:Cc:In-Reply-To:References:Subject:Date; b=F7wTXRSQrpTuPgQKWMwl/IVC72Al9Y/IF8EhOuo09zAJFsANTmD38y7c8jTrU/uCN gHa/PX68g+664vITRzrwLN2gUT8eYZvERLT4Nq83xPze+q49U9mLH3S+nZC50wbfI6 zHJotOTy0hgErm0KLfxup9stmzUBLcK1/+BxTzaE= Received: by web23h.yandex.ru with HTTP; Sat, 25 Jul 2015 21:21:12 +0300 From: deco33000@yandex.com To: Ian Lepore Cc: "freebsd-hackers@freebsd.org" In-Reply-To: <1437840321.48814.10.camel@freebsd.org> References: <1226791437830729@web8g.yandex.ru> <1408761437838413@web20h.yandex.ru> <1437840321.48814.10.camel@freebsd.org> Subject: Re: Timekeeping between two hardclocks MIME-Version: 1.0 Message-Id: <810331437848472@web23h.yandex.ru> X-Mailer: Yamail [ http://yandex.ru ] 5.0 Date: Sat, 25 Jul 2015 20:21:12 +0200 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset=koi8-r X-BeenThere: freebsd-hackers@freebsd.org X-Mailman-Version: 2.1.20 Precedence: list List-Id: Technical Discussions relating to FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 25 Jul 2015 18:21:24 -0000 Thanks Ian, I read the freebsd7 source. I think i understand the rollovers, the deltas and so on. As far as event timers are concerned : we cannot handle timers inferior to the current kernel timing resolution right ? If it is 1ms, one cannot ask a timer to be processed EXACTLY at 0.5ms. It will have to wait the next interrupt to be handled. So, I guess I am pretty correct when I say that we have to wait for the hardware interrupt to check for new events. Because otherwise we have no point of reference (are we really at 0.5ms or 0.478ms or 0.51ms?).. I am sorry if I don't get it faster, but the devil is in the details in this context :) --š Jog