Date: Wed, 04 Dec 2019 17:23:12 +0000 From: bugzilla-noreply@freebsd.org To: bugs@FreeBSD.org Subject: [Bug 242427] pmap_remove() sometimes is very slow causing 10+ minutes long reboots Message-ID: <bug-242427-227-qMBeX3rcdT@https.bugs.freebsd.org/bugzilla/> In-Reply-To: <bug-242427-227@https.bugs.freebsd.org/bugzilla/> References: <bug-242427-227@https.bugs.freebsd.org/bugzilla/>
next in thread | previous in thread | raw e-mail | index | archive | help
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=3D242427 --- Comment #4 from Peter Eriksson <pen@lysator.liu.se> --- (In reply to Peter Eriksson from comment #3) Before someone asks - yes, in theory since I'm using the "if (time_second-t0>0)" check, then it _could_ be just coincidence and that the clock steps 1s just between the two reads of time_second. However, it is consistent (all 4 levels of calls return 1 (and they read the time spent separately) - and I see it printed 14 times), and the loop in keg_drain rep= orts 14 seconds - so I doubt that it would be the case. Not all the time atleast= ... :-) > kmem_unback: pmap_remove(kernel_pmap, 18446741877714755584, 1844674187771= 4767872) took 1 seconds > kmem_free: kmem_unback(kmem_object, 18446741877714755584, 12288) took 1 s= econds > page_free: kmem_free(kmem_arena, 18446741877714755584, 12288) took 1 seco= nds > keg_free_slab: keg->uk_freef(mem) {page_free} took 1 seconds (The four lines above is repeated 14 times, with different addresses of cou= rse) > keg_drain: while-keg_free_slab-loop took 14 seconds [20021 loops, 14 slow= calls] --=20 You are receiving this mail because: You are the assignee for the bug.=
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?bug-242427-227-qMBeX3rcdT>