From mboxrd@z Thu Jan 1 00:00:00 1970 From: William Dauchy Subject: Re: ps stuck on cmdline reading Date: Tue, 10 Feb 2015 16:10:50 +0100 Message-ID: <20150210151050.GB17444@gandi.net> References: <20150121095808.GA18656@gandi.net> <20150203194036.GA2490@dhcp22.suse.cz> <20150205152233.GI3008@gandi.net> <20150205154558.GF19104@dhcp22.suse.cz> Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="4SFOXa2GPu3tIq4H" Return-path: Content-Disposition: inline In-Reply-To: <20150205154558.GF19104-2MMpYkNvuYDjFM9bn6wA6Q@public.gmane.org> Sender: cgroups-owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org List-ID: To: Michal Hocko Cc: William Dauchy , cgroups-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, Trond Myklebust , Anna Schumaker --4SFOXa2GPu3tIq4H Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Feb05 16:45, Michal Hocko wrote: > OK, so the memcg reclaim gets down to nfs and it wants to evict its > inode and that is waiting for the page to get unlocked. It would be > interesting to find out who is keeping the page locked. What is the nfsd > doing? Trond points me the commit 9590544 NFS: avoid deadlocks with loop-back mounted NFS filesystems. but it relies on sched commit as well, it seems hard to be backported in 3.14.x --=20 William --4SFOXa2GPu3tIq4H Content-Type: application/pgp-signature; name="signature.asc" Content-Description: Digital signature -----BEGIN PGP SIGNATURE----- Version: GnuPG v1 iEYEARECAAYFAlTaH3oACgkQ1I6eqOUidQEArQCgqjeO0jx7+R6AcKeBY3fHRaK0 x/UAoKDgcko3oO799L8cZNrFIdjmrHZp =Y8i4 -----END PGP SIGNATURE----- --4SFOXa2GPu3tIq4H--