Date: Tue, 01 Dec 2015 01:24:30 +0000 From: bugzilla-noreply@freebsd.org To: freebsd-fs@FreeBSD.org Subject: [Bug 194513] zfs recv hangs in state kmem arena Message-ID: <bug-194513-3630-wewBivBaSe@https.bugs.freebsd.org/bugzilla/> In-Reply-To: <bug-194513-3630@https.bugs.freebsd.org/bugzilla/> References: <bug-194513-3630@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=194513 mgoroff@quorum.net changed: What |Removed |Added ---------------------------------------------------------------------------- CC| |mgoroff@quorum.net --- Comment #13 from mgoroff@quorum.net --- We are encountering what appears to be the same issue on a large production server running 10.2-RELEASE. The machine has 128G of RAM and vfs.zfs.arc_max is set to 100G. I have a zfs recv currently stuck waiting on kmem arena. When this problem occurs, the ARC starts rapidly shrinking down to vfs.zfs.arc_min (13G in our case) but the process will remain blocked for a long period of time (hours) even though top shows free memory at 104G. ps -l for the process shows: UID PID PPID CPU PRI NI VSZ RSS MWCHAN STAT TT TIME COMMAND 0 37892 37814 0 20 0 42248 3428 kmem are D 1 0:04.16 zfs recv -u -d ezdata2 while procstat -kk -p 37892 shows: PID TID COMM TDNAME KSTACK 37892 101149 zfs - mi_switch+0xe1 sleepq_wait+0x3a _cv_wait+0x16d vmem_xalloc+0x568 vmem_alloc+0x3d kmem_malloc+0x33 uma_large_malloc+0x49 malloc+0x43 dmu_recv_stream+0x114 zfs_ioc_recv+0x955 zfsdev_ioctl+0x5ca devfs_ioctl_f+0x139 kern_ioctl+0x255 sys_ioctl+0x140 amd64_syscall+0x357 Xfast_syscall+0xfb -- 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-194513-3630-wewBivBaSe>