From owner-freebsd-fs@FreeBSD.ORG Wed Jan 25 11:31:54 2012 Return-Path: Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 2084B106564A for ; Wed, 25 Jan 2012 11:31:54 +0000 (UTC) (envelope-from miconof80.list@gmail.com) Received: from mailhost.math.cnrs.fr (margauxlyon.mathrice.fr [194.167.215.28]) by mx1.freebsd.org (Postfix) with ESMTP id 917E58FC19 for ; Wed, 25 Jan 2012 11:31:53 +0000 (UTC) Received: from localhost (localhost.localdomain [127.0.0.1]) by mailhost.math.cnrs.fr (Postfix) with ESMTP id 3EE0844094; Wed, 25 Jan 2012 12:31:52 +0100 (CET) X-Virus-Scanned: amavisd-new at math.cnrs.fr Received: from mailhost.math.cnrs.fr ([127.0.0.1]) by localhost (margaux.math.cnrs.fr [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id zMuZJS2DOnOV; Wed, 25 Jan 2012 12:31:50 +0100 (CET) Received: from e4310 (e4310.lsv.ens-cachan.fr [138.231.81.249]) (using TLSv1 with cipher DHE-RSA-AES128-SHA (128/128 bits)) (No client certificate requested) by mailhost.math.cnrs.fr (Postfix) with ESMTP id E34EB4408C; Wed, 25 Jan 2012 12:31:50 +0100 (CET) Date: Wed, 25 Jan 2012 12:31:49 +0100 From: Michel Le Cocq To: Peter Maloney Message-ID: <20120125113149.GB7000@e4310> References: <201110091940.p99JeJIc095036@freefall.freebsd.org> <20120125084040.GA2831@e4310> <4F1FD252.4090403@brockmann-consult.de> <20120125110005.GA7000@e4310> <4F1FE3F1.2010301@brockmann-consult.de> MIME-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="kORqDWCi7qDJ0mEj" Content-Disposition: inline In-Reply-To: <4F1FE3F1.2010301@brockmann-consult.de> User-Agent: Mutt/1.5.21 (2010-09-15) Cc: freebsd-fs@freebsd.org Subject: Re: kern/146528: [zfs] Severe memory leak in ZFS on i386 X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 25 Jan 2012 11:31:54 -0000 --kORqDWCi7qDJ0mEj Content-Type: text/plain; charset=iso-8859-1 Content-Disposition: inline Content-Transfer-Encoding: quoted-printable ok in fact I didn't understand your first question ! I see this trouble only on my personnal i386 machine. I have also several amd64 with a lot of mem 24G or some virtual with 4G all on amd64 and they work perfectly on 8.2 since more than 1 year. -- M Peter Maloney a =E9crit: > I expected you would say it was much older, somewhere between April and > September last year. My amd64 systems (dual cpu quad core Xeon) with 48 > GB of ram have no issues like this. And my amd64 test VMs with 512M-2GB > of RAM don't have this problem either, but of course they aren't tested > the same. >=20 >=20 >=20 > On 01/25/2012 12:00 PM, Michel Le Cocq wrote: > > I recently update 1 week maybe ! > > > > Peter Maloney a =E9crit: > >> When was your 8.2-STABLE built / csup'd? > >> > >> Peter > >> > >> > >> On 01/25/2012 09:40 AM, Michel Le Cocq wrote: > >>> Hi every body, I upgrade my Freebsd 8.2-STABLE i386 to 9.0 i386. > >>> Intel(R) Atom(TM) CPU D510 @ 1.66GHz > >>> real memory =3D 4294967296 (4096 MB) > >>> avail memory =3D 3127390208 (2982 MB) > >>> > >>> I'm on a ZFS Root file systeme on 2 USB drive and 6 sata drive for > >>> data.=20 > >>> > >>> # zpool list > >>> NAME SIZE ALLOC FREE CAP DEDUP HEALTH ALTROOT > >>> data 931G 254G 677G 27% 1.00x ONLINE - > >>> stock 74.5G 12.4G 62.1G 16% 1.00x ONLINE - > >>> tank 696G 574G 122G 82% 1.00x ONLINE - > >>> zroot 3.66G 2.49G 1.17G 67% 1.00x ONLINE - > >>> > >>> Before upgrade, I must use some mana things in my /boot/loader.conf > >>> > >>> vm.kmem_size=3D"330M" > >>> vm.kmem_size_max=3D"330M" > >>> vfs.zfs.arc_max=3D"40M" > >>> vfs.zfs.vdev.cache.size=3D"5M" > >>> =09 > >>> With this config my server was not so stable. > >>> > >>> Some days it work perfectly, some others it freeze with kmem_malloc > >>> kmem_map too small.=20 > >>> Without this mana it freeze really often. > >>> > >>> The thing which make me upgrade is that after one of this crash after > >>> reboot it won't mount my data pool which was at 99% of his CAP. The > >>> only way I find to boot is to disconnect the pools drive and export > >>> it. > >>> > >>> Now I'm on exactly the same host after upgrade to 9.0 and it seems to > >>> work really really better (3 days up with out any trouble). > >>> > >>> -- > >>> M > >>> > >>> Garrett Cooper a =E9crit: > >>>> The following reply was made to PR kern/146528; it has been noted by= GNATS. > >>>> > >>>> From: Garrett Cooper > >>>> To: bug-followup@FreeBSD.org, EdwinGuy@GMail.com > >>>> Cc: =20 > >>>> Subject: Re: kern/146528: [zfs] Severe memory leak in ZFS on i386 > >>>> Date: Sun, 9 Oct 2011 12:34:00 -0700 > >>>> > >>>> Could you please try upgrading to 8.2-STABLE or 9.0 and see if the > >>>> issue persists with ZFS v28? > >>>> -Garrett > >>>> _______________________________________________ > >>>> freebsd-fs@freebsd.org mailing list > >>>> http://lists.freebsd.org/mailman/listinfo/freebsd-fs > >>>> To unsubscribe, send any mail to "freebsd-fs-unsubscribe@freebsd.org" --kORqDWCi7qDJ0mEj Content-Type: application/pgp-signature; name="signature.asc" Content-Description: Digital signature -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.11 (GNU/Linux) iQIcBAEBAgAGBQJPH+gkAAoJENZipdjc3yzpaPkP/j6vSSmRYCQphAPaNXW4ukBx CmxfodLacYOub61orHEIvuOu08/EUzXDYtG96pIJYI8MCsg6urNowgYjbHxl1A7P cXpg0SCaYvoX0rTbtYPQGKeHxxo9SK1aArYI5HrWP3UKNpuPxC8FsqYKYq+3cSsr DCcY7k2LnbuJVsLDZanqsRPCa71W6LsUgfARIY+L+3GVfxgai5J9PaEWq/EkvJds +/UX0C44wiig3f60eMzb6E/TUPlPnJuPxKEWCJP2q2hu746BKKS/bDV3ThMd2sKG CFgq7WbGuvvwvLXFQDBkjoU8Zbxo6Dm8xQm89jqh0zTx9fy8p6Zha3Mafr4sIfeR 25vdxwmCbPv38c5S/uOdBStocaG54KhbvR4JUONnKs8wZRMEkjjgkIT49Yp76BkA osqhFsl5HY4KIR3sHvH/NxqzFBzvoFWXhHGL4y5QefNLLxiGsTwRxZGqW2mv72wu 4jChE1/KOoTAgREcEr8jdxjSUpxFqkpoowy2Y1TEnwB5No9D4rQVcqgLH9bKQ861 qBKxVBs6QoaIywZw7fGX7neoZdUnyh8huTdFOec2vLbq0yJyUZ8Lv79omqNQT2HU Q3yDPOn6j9UUi3XRcKdtjP0Xt5rO7D/ke8+NCN8XignQNyKQiza8PmOcoQDmnF/2 326BSzFbAVBKhS7sl2B1 =WUht -----END PGP SIGNATURE----- --kORqDWCi7qDJ0mEj--