Date: Thu, 3 May 2007 07:09:07 +0300 From: Kostik Belousov <kostikbel@gmail.com> To: Rick Macklem <rmacklem@uoguelph.ca> Cc: Craig Boston <craig@xfoil.gank.org>, Pawel Jakub Dawidek <pjd@freebsd.org>, freebsd-fs@freebsd.org, freebsd-current@freebsd.org, Robert Watson <rwatson@freebsd.org>, Kris Kennaway <kris@obsecurity.org> Subject: Re: ZFS committed to the FreeBSD base. Message-ID: <20070503040907.GK2441@deviant.kiev.zoral.com.ua> In-Reply-To: <Pine.GSO.4.63.0705021717500.13892@muncher> References: <20070410003505.GA8189@nowhere> <46365F76.7090708@infidyne.com> <20070430213043.GF67738@garage.freebsd.pl> <463665F2.8090605@infidyne.com> <46373CAD.6000502@infidyne.com> <Pine.GSO.4.63.0705011033410.23282@muncher> <20070501160213.GA496@xor.obsecurity.org> <Pine.GSO.4.63.0705011630010.15295@muncher> <20070502154934.E30345@fledge.watson.org> <Pine.GSO.4.63.0705021717500.13892@muncher>
next in thread | previous in thread | raw e-mail | index | archive | help
--Vwmj/TXzE7NEH899 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Wed, May 02, 2007 at 05:28:04PM -0400, Rick Macklem wrote: >=20 >=20 > On Wed, 2 May 2007, Robert Watson wrote: > [stuff snipped]=20 > > > >Historically, such panics have been a result of one of two things: > > > >(1) An immediate resource leak in UMA(9) or malloc(9) allocated memory. > > > >(2) Mis-tuning of a resource limit, perhaps due to sizing the limit base= d=20 > >on > > solely physical memory size, not taking available kernel address space > > into account. > > > >mti_stats reports only on malloc(9), you need to also look at uma(9),=20 > >since many frequently allocated types are allocated directly with the sl= ab=20 > >allocator, and not from kernel malloc. Take a look at the output of "sh= ow=20 > >uma" or "show malloc" in DDB, or respectively "vmstat -z" and "vmstat -m= "=20 > >on a core or on a live system. malloc(9) is actually implemented using= =20 > >two different back-ends: UMA-managed fixed size memory buckets for small= =20 > >allocations, and direct page allocation for large allocations. >=20 > Ok, it does appear I'm leaking NAMEIs. "vmstat -z", which I didn't know > about, was the trick. Handling lookup name buffers is also port specific, > so it wouldn't have shown up in the other ports. >=20 > So, forget what I said w.r.t. a MALLOC bug and thanks for the help. I > should be able to locate the leak pretty easily with "vmstat -z". I fixed two NAMI zone leaks in the last 2-3 month. One was in the nfs server (shall be present in 6.2-RELEASE, AFAIR), second was in UFS snapshotting code, and is MFCed several days ago. --Vwmj/TXzE7NEH899 Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.7 (FreeBSD) iD8DBQFGOWBjC3+MBN1Mb4gRArLlAJwLnxwBeDgtpPM02z46i/XXKE3wqQCfZWqG 8R3zc+4s7voa0bqTtixr5yY= =OghD -----END PGP SIGNATURE----- --Vwmj/TXzE7NEH899--
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20070503040907.GK2441>