From owner-freebsd-fs@freebsd.org Sat Jul 9 21:01:45 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 E1ED5B76D8A for ; Sat, 9 Jul 2016 21:01:45 +0000 (UTC) (envelope-from mailinglists35@gmail.com) Received: from mail-oi0-x22b.google.com (mail-oi0-x22b.google.com [IPv6:2607:f8b0:4003:c06::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 AC3A71ED7 for ; Sat, 9 Jul 2016 21:01:45 +0000 (UTC) (envelope-from mailinglists35@gmail.com) Received: by mail-oi0-x22b.google.com with SMTP id s66so102407268oif.1 for ; Sat, 09 Jul 2016 14:01:45 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:from:date:message-id:subject:to; bh=sqmMRUxiWhtyOCprksQqQOvn5q3cyCsmxP7HnrNseEg=; b=HoK1DJuxrqhzhlXQgMgQySGOZFOW5XXUGcvRXAgTtr2Q2x4eZIQS4Kszksa7b1FhGH XRnZOMi1xfF20dHDVBaK+uSZ5crk8FD12el8cChDetW24c40ilcxs7UpmOE2KJzWLyiy cKs56G5Ex7g0fAVrmjSGG0di3toOSKUz1w6k4PRSF2xu+kvsmVNYBEPBUC9DxTRvkrL+ KfeD7MOwmJtvOWOinwTRSldFo7lYFYBCnk5K01kDUFL0Lr88Ja1fKX8hhmOHVkhkfY7Q 8YwU3qgYkk0Da7So8Dmhq+Bd7Mf809hMtQVUonFhjaopJFK1RGNsWrey8gC9sQk20RDv E9pg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20130820; h=x-gm-message-state:mime-version:from:date:message-id:subject:to; bh=sqmMRUxiWhtyOCprksQqQOvn5q3cyCsmxP7HnrNseEg=; b=QhQ1e31X2rhDH/pbqDRZ/DBPkTu8BAVEd55ZNT4sDpS0R1usds4OkH5xlNCAxNu68+ zJQ/tE72jq50Y+wvOZY/5ioAydixKQ1V2AoRyQtgCK6e+xpfVYHeDKsKTjxeBG95Whwy A8DgDeN5xv9A/Ij6KP9mdWvS3O/m7Wc27/9dVAaKV9jqrgqaxfAG4Zbd7twoNOrngN8r 39SMWoTaV4yO/iht+GJ/wjanAuekLDsHCViqpTnfD5etHVg7Txuy6FHA/k8WmcwfUp+3 1MGMsXvmyxJ51B9c6z+4pGar/NYkB8/GaH9TAvIhgbwR+TqWcQ7O6fRzHWdwNQIvAqAe JtOA== X-Gm-Message-State: ALyK8tKCtvD/4Pdo5AnMvqx+lJcEltr/BNgP42VPdn074x8zy+RtfafvmZ0M1jhX8wzDdeXnPnYR9ALq0j4JNw== X-Received: by 10.202.82.23 with SMTP id g23mr4819376oib.128.1468098104534; Sat, 09 Jul 2016 14:01:44 -0700 (PDT) MIME-Version: 1.0 Received: by 10.202.183.196 with HTTP; Sat, 9 Jul 2016 14:01:25 -0700 (PDT) From: Mailing Lists Date: Sun, 10 Jul 2016 00:01:25 +0300 Message-ID: Subject: help request for testing zfs issue To: freebsd-fs@freebsd.org Content-Type: text/plain; charset=UTF-8 X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.22 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 09 Jul 2016 21:01:46 -0000 Hi, I'm trying to learn if a zfs issue can be reproduced on freebsd. I myself have reproduced it on 10.3 and 11 beta inside a linux KVM vm, and also on linux, but don't have a separate physical fbsd installation at hand. I'd really be grateful to someone who can take some of their time to verify this. Be aware that I expect the test machine to be rebooted if the test is reproductible (or at least their zfs pools to become unavailable) so this is not for people who have their rootfs on zfs unless they want to take the risk of getting to a hang. FWIW, the test machines have less than 4Gb of ram (the test vm was tested with 1 and 3Gb) so maybe you want to limit the available ram at boot time if you have more. These are the steps that hang my pool under linux and under the fbsd vm: mount -t tmpfs -o size=2662400k tmpfs /mnt/test/ cd /mnt/test for l in `seq 0 9`; do dd bs=1M count=256 if=/dev/zero of=loop$l; done zpool create -o failmode=continue -O logbias=throughput -O atime=off -o autoreplace=on -O primarycache=metadata -O secondarycache=metadata -O compression=lz4 -m /srv/big big raidz3 /mnt/test/loop* dd if=/dev/zero of=/srv/big/file bs=4M #interrupt with ctrl-c after some Gb written ls -lh /srv/big/ du -csh /srv/big/ rm /srv/big/file zfs set compression=off big while true; do dd if=/dev/zero of=/srv/big/file bs=4M #on freebsd11 dd never complains about no free space left and just hangs and had to add count=421 rm -f /srv/big/file done Some time after many iterations (as many as 370 on an ubuntu linux machine), the pool should list write errors on it but no errors on vdev or each disk. On linux the kernel prints a message but on freebsd there is no message and you have to manually check for pool status. Please cc me on replies or directly comment on the ZoL issue tracker here https://github.com/zfsonlinux/zfs/issues/4832 Thank you in advance