From owner-freebsd-hackers@freebsd.org Thu Nov 30 20:40:31 2017 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 21B32DB99E6 for ; Thu, 30 Nov 2017 20:40:31 +0000 (UTC) (envelope-from markjdb@gmail.com) Received: from mail-qk0-x22b.google.com (mail-qk0-x22b.google.com [IPv6:2607:f8b0:400d:c09::22b]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (Client CN "smtp.gmail.com", Issuer "Google Internet Authority G2" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id CFBE174531 for ; Thu, 30 Nov 2017 20:40:30 +0000 (UTC) (envelope-from markjdb@gmail.com) Received: by mail-qk0-x22b.google.com with SMTP id 63so10615950qke.0 for ; Thu, 30 Nov 2017 12:40:30 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20161025; h=sender:date:from:to:cc:subject:message-id:references:mime-version :content-disposition:in-reply-to:user-agent; bh=PIwX4BsvBXP5pvZpE4+4d46Nz0EwR++655JTG2gbmV4=; b=ZDu33e2rIp2ua0HnuW8Ds9Rs7o3Nm9KPQ1+W0kJ8er17O4FYRYkDKP09RzB/+B+cXf lWvQzaynBUY2UcCxQOMqqtIg6llD5dENx4SAkA2a276gINIzXWyjqwbKXgth0hAKZ3Lt ioZ7JzQxQRO/Ev2ryW0Xgrw+1GZ4D26fEiimdiuo/cvUMyydQg1vJEtWUZ7VxYZGWUVw 2uXKv+nt8FqTkN43hnkmnufQ/8w7XsoJA14rlMupQKEOu69fXwUNj9iu855D2cBRGigL lFmAETclOSivZp2HsxU6eIlfrGuMcvmYVH9aOl4uRJudmMUEA+Ykfgi1Tvjjx8wLAOQt eV/Q== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:sender:date:from:to:cc:subject:message-id :references:mime-version:content-disposition:in-reply-to:user-agent; bh=PIwX4BsvBXP5pvZpE4+4d46Nz0EwR++655JTG2gbmV4=; b=YZChjBrLCSoqWudjAzLHm8HUMmCaSYsRj5Fvvttvcltyr/832vsry5Pez5mwq46T2X OyIyxmuU4cPsz46IziiJ6iQC8s0k+hPDsLx7dNmtliabcU1tqRwPzKOuh6ifue1vhiM5 41MgS+d8xelrpWsyS/lHGV+zv1Z6Ex+imZEHvVJSyzm4kfclubgvIxZ/RJe7GVCWN9oK zxmM8FXxSGjVGGGonuHKQiAcVNT52pL3Xty+pOSntYRehkNvO4ugTT5HGE0iiR2XoVhl 1Ct5tz0sBchxV6x9IccG2x9h9C5+zh88PqZK8QFSEeZ3PKT5rbzVziCVoRu95muUSVhb fBGg== X-Gm-Message-State: AKGB3mJeiC1GC2YLuqvvEpGVybfE/NmvulSetaYRAcrhFyEy18RvZwJR zgbRfeY70ZcLPRg6p0K0rbFWYg== X-Google-Smtp-Source: AGs4zMbr/hqNro5JJ0yh07xkc1b3dYLS2ZdO+IR5i5nEKKoSxeM8WrE1neveYTG5ZfRQ/bvttkPl1g== X-Received: by 10.55.145.135 with SMTP id t129mr4305090qkd.205.1512074429731; Thu, 30 Nov 2017 12:40:29 -0800 (PST) Received: from raichu (toroon0560w-lp140-01-69-159-38-22.dsl.bell.ca. [69.159.38.22]) by smtp.gmail.com with ESMTPSA id v17sm2718678qkl.36.2017.11.30.12.40.28 (version=TLS1_2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128/128); Thu, 30 Nov 2017 12:40:28 -0800 (PST) Sender: Mark Johnston Date: Thu, 30 Nov 2017 15:40:23 -0500 From: Mark Johnston To: Andre Albsmeier Cc: freebsd-hackers@freebsd.org Subject: Re: gmirror synchronising is very slow due to frequent metadata updates Message-ID: <20171130204023.GA21606@raichu> References: <20171119103241.GA20588@voyager> <20171120033828.GA1959@bish> <20171120053409.GA57536@gate> <20171121173813.GB4126@raichu> <20171130145810.GA90581@gate> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20171130145810.GA90581@gate> User-Agent: Mutt/1.9.1 (2017-09-22) X-BeenThere: freebsd-hackers@freebsd.org X-Mailman-Version: 2.1.25 Precedence: list List-Id: Technical Discussions relating to FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 30 Nov 2017 20:40:31 -0000 On Thu, Nov 30, 2017 at 03:58:10PM +0100, Andre Albsmeier wrote: > On Tue, 21-Nov-2017 at 12:38:13 -0500, Mark Johnston wrote: > > On Mon, Nov 20, 2017 at 06:34:09AM +0100, Andre Albsmeier wrote: > > > On Sun, 19-Nov-2017 at 22:38:28 -0500, Mark Johnston wrote: > > > > We should probably decrease the update interval based on the size of a > > > > mirror. For mirrors larger than say, 1GB, we might just update the > > > > metadata block once per 1% of the synchronization operation's progress. > > > > > > I think best would be to have it updated every seconds. > > > I think of very fast or very slow drives, or drives which are used > > > heavily during rebuild (where the effective rebuild speed is quite > > > low)... > > > > I think that's reasonable. Could you give the patch below a try? It adds > > I am some more weeks in the jungle with nothing more than two > notebooks so trying your patch will be a bit hard (and, call > me a coward, I won't do this on my mirror'ed machines 8000 km > away ;-)). Fair enough! :) > > Apart from that it looks quite simple and seems to do all what > we need (my impression as a non-kernel hacker). Maybe someone > else can review it and we just give it a try? I tested it myself and committed the change as r326409.