Date: Sat, 13 Jul 2013 19:48:14 +0300 From: Konstantin Belousov <kostikbel@gmail.com> To: Ian FREISLICH <ianf@clue.co.za> Cc: freebsd-current@freebsd.org Subject: Re: Filesystem wedges caused by r251446 Message-ID: <20130713164814.GM91021@kib.kiev.ua> In-Reply-To: <E1Uy2r2-0003r7-0x@clue.co.za> References: <20130713054220.GJ91021@kib.kiev.ua> <20130712201051.GI91021@kib.kiev.ua> <201307110923.06548.jhb@freebsd.org> <201307091202.24493.jhb@freebsd.org> <E1UufRq-0001sg-HG@clue.co.za> <E1UxEWB-0000il-21@clue.co.za> <E1Uxhoe-0000d9-Sc@clue.co.za> <E1Uxkyo-0002mE-MJ@clue.co.za> <E1Uxuy4-0003KB-OZ@clue.co.za> <E1Uy2r2-0003r7-0x@clue.co.za>
next in thread | previous in thread | raw e-mail | index | archive | help
--V9aszxPoayjYMR8r Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Sat, Jul 13, 2013 at 06:39:28PM +0200, Ian FREISLICH wrote: > Konstantin Belousov wrote: > > > Yes. This state of affairs doesn't happen on r251445 and further > > > testing on my side shows it doesn't hapen on all my amd64 servers. > > > It appears that this particular server type (Dell R200) running > > > amd64 with geom_mirror is affected. I will have to test further > > > by destroying the mirror and removing it from the kernel and see > > > if I can still reproduce the issue. Perhaps r251446 exposes > > > insufficient locking on opperations affecting these variables. > > No. The lorunningspace is constant for the system lifetime. > > It can only be changed by the sysctl vfs.lorunningspace. > > Look into /etc/sysctl.conf or scripts which apply sysctl settings. >=20 > Wipes egg from face. >=20 > /etc/sysctl.conf: >=20 > vfs.hirunningspace=3D4194304 >=20 > So, then did r251446 actually start using this value or did other > values get significantly tuned up? I recall now setting this nearly > a year ago when we did our ZFS tuning and it was a four fold increase > on the defaults. r251446 optimized the wakeups by only doing wakeups when runningbufspace actually crossed the lorunningspace. Before, wakeups were performed always on the runningbufspace changes. For ZFS, these settings are completely irrelevant, ZFS does not use buffer cache. --V9aszxPoayjYMR8r Content-Type: application/pgp-signature -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.20 (FreeBSD) iQIcBAEBAgAGBQJR4YTNAAoJEJDCuSvBvK1BNi4P/0wsjlnSlpPtxr4JBaANzOLg NaRIT0ClVuXFF176Bm+mre1MMkCgq4Y6phxnwEk0Iab7Ml0Bfjp+9gDJjmNT3DN0 xledgFQkcM7G8yWqRVepsadWrUkJdNH7xcvb5ZqN89m7sxfaOeVvCmCDGAu3oAj5 iSOy9MkTCeH0OrOxgIN3DI1r8dqWELjOx0NTKVujPF1KvOFgBqSkLZUU/aQQaVad zxGI7h5pt7C73MT6HDsnQWcte4Cm2moigLZy4S3uS1WMeKP55dFZl/yKq69WOcvX Tv10IT+WpdxJz8apO42oTo/vbFS2vMh3D5G4kJVUTAj2eO9uagPbRkL/xW1og/Cw 0xWCDYnIzNB42DLz//S30wCvmzijWOldufu2AZsmnrO+IPm0niTgHPU6BR1oZD4i Ex3Yrqx+bxrRniAlaxGNmRNeoR8LZercVrzmRBQ3p5mExzYhYOJg3iblTsAHXPCs MpqXiHt/TfzT/a+AnD16Mr1+kTzjTmt2/tawHpp6ITjjmBVUQrYdF7USv95mHE5V cP6V2PBEgbEAjkLAi9J/mJw4PQq0wYrFIQVJlbQ3/5Xhwx2LNBeqokJMtHBdQT16 Y9k8hQuhST14HZOfRPoZ8zhPy+if/JsTDS1kE/ij93tU+gLl6ryoKNp7TjLB68vx eqrvkJucZK7bLwRr1S6f =aDN7 -----END PGP SIGNATURE----- --V9aszxPoayjYMR8r--
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20130713164814.GM91021>