From owner-freebsd-fs@freebsd.org Sat Nov 12 10:44:37 2016 Return-Path: Delivered-To: freebsd-fs@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 4BCBFC3C540 for ; Sat, 12 Nov 2016 10:44:37 +0000 (UTC) (envelope-from lev@FreeBSD.org) Received: from onlyone.friendlyhosting.spb.ru (onlyone.friendlyhosting.spb.ru [IPv6:2a01:4f8:201:6350::2]) by mx1.freebsd.org (Postfix) with ESMTP id 17C681D1E; Sat, 12 Nov 2016 10:44:37 +0000 (UTC) (envelope-from lev@FreeBSD.org) Received: from [IPv6:2001:470:923f:2:5c87:58af:6791:eb29] (unknown [IPv6:2001:470:923f:2:5c87:58af:6791:eb29]) (Authenticated sender: lev@serebryakov.spb.ru) by onlyone.friendlyhosting.spb.ru (Postfix) with ESMTPSA id EA63E235; Sat, 12 Nov 2016 13:44:34 +0300 (MSK) Reply-To: lev@FreeBSD.org Subject: Re: ZFS L2ARC checksum errors after compression References: <921575537.20161029143626@serebryakov.spb.ru> <3dae7691-fcd1-b3b9-445c-b81d6f0cdc52@FreeBSD.org> <3bd7cb79-ec5a-3b7c-0642-24a7b1f001e6@FreeBSD.org> To: Andriy Gapon , freebsd-fs From: Lev Serebryakov Organization: FreeBSD Message-ID: <5826F293.7020408@FreeBSD.org> Date: Sat, 12 Nov 2016 13:44:35 +0300 User-Agent: Mozilla/5.0 (Windows NT 10.0; WOW64; rv:38.0) Gecko/20100101 Thunderbird/38.5.0 MIME-Version: 1.0 In-Reply-To: <3bd7cb79-ec5a-3b7c-0642-24a7b1f001e6@FreeBSD.org> Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: 7bit X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.23 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 12 Nov 2016 10:44:37 -0000 > because of the confusing variable names I made a mistake in the patch that I > offered you. Could you please try a new slight different patch? > Also, I think that there could be another problem in addition to the one that I > see. But I am quite busy at the moment, no time to investigate. Maybe on the > weekend or some time next week. Nope. Second version of patch doesn't help either. Still unrealistic high compression ratio (ALLOC/SIZE, slightly less than 2 on mostly uncompresseable data), 16.0E of FREE since ALLOC becomes greater than SIZE and lot of checksum errors since the same moment. -- // Lev Serebryakov AKA Black Lion