Re: [zfs-discuss] zfs reliability under xen
On Sun, May 17, 2009 at 02:16:01PM +0300, Ahmed Kamal wrote: I am wondering whether the reliability of solaris/zfs is still guaranteed if I will be running zfs not directly over real hardware, but over Xen virtualization ? The plan is to assign physical raw access to the disks to the xen guest. I remember zfs having problems with hardware that lies about disk write ordering, wonder how that is handled over Xen, or if that issue has been completely resolved You can read the frontend sources here: http://src.opensolaris.org/source/xref/onnv/onnv-gate/usr/src/uts/common/xen/io/xdf.c If both dom0 and domU are Solaris, then any disk cache flushes are passed through via FLUSH_DISKCACHE. If the dom0 is Linux, then we attempt to emulate a flush by using WRITE_BARRIER (annoyingly, this requires us to write a block as well, so in this case, we cache one). In the backend (xdb or xpvtap), we pass along the flush request, either via an in kernel flush: 683 (void) ldi_ioctl(vdp-xs_ldi_hdl, 684 DKIOCFLUSHWRITECACHE, NULL, FKIOCTL, kcred, NULL); or via VDFlush() in the VirtualBox code we use (which essentially ends up as an fsync()). Thus as long as the ioctl and/or fsync are obeyed, things should be good. Hope that's clearer. regards john ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
[zfs-discuss] Dreadful lofi read performance on snv_111
On snv_111 OpenSolaris. heaped is snv_101b, both ZFS: # mount -F hsfs /rpool/dc/media/OpenSolaris.iso /mnt # ptime cp /mnt/boot/boot_archive /var/tmp real 3:31.453461873 user0.003283729 sys 0.376784567 # mount -F hsfs /net/heaped/export/netimage/opensolaris/vnc-fix.iso /mnt2 # ptime cp /mnt2/boot/boot_archive /var/tmp real1.442180764 user0.004013447 sys 0.442550604 # mount -F hsfs /net/localhost/rpool/dc/media/OpenSolaris.iso /mnt3 # ptime cp /mnt3/boot/boot_archive /var/tmp real 3:41.182920499 user0.004244172 sys 0.430159730 I see a couple of bugs about lofi performance like 6382683, but I'm not sure if this related, it seems to be a newer issue. Any ideas? regards john ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] Dreadful lofi read performance on snv_111
On Mon, Apr 06, 2009 at 04:46:12PM +0700, Fajar A. Nugraha wrote: On Mon, Apr 6, 2009 at 4:41 PM, John Levon john.le...@sun.com wrote: I see a couple of bugs about lofi performance like 6382683, but I'm not sure if this related, it seems to be a newer issue. Isn't it 6806627? http://opensolaris.org/jive/thread.jspa?threadID=98043tstart=0 Ah, I thought that made 111, but it sounds like it's going in the respin instead - should have checked. thanks john ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] xVM GRUB entry incorrect with ZFS root
On Thu, Aug 28, 2008 at 09:25:14AM -0700, Trevor Watson wrote: Looking at the GRUB menu, it appears as though the flags -B $ZFS-BOOTFS are needed to be passed to the kernel. Is this something I can add to: kernel$ /boot/$ISADIR/xen.gz or is there some other mechanism required for booting Solaris xVM from ZFS ? You need to add it to the next line ($module ...). This was a bug that's now fixed in the latest LU regards john ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] [caiman-discuss] swap dump on ZFS volume
On Mon, Jun 30, 2008 at 04:19:15PM -0700, Jeff Bonwick wrote: (2) In a virtualized environment, a better way to get a crash dump would be to snapshot the VM. This would require a little bit of host/guest cooperation, in that the installer (or dumpadm) would have to know that it's operating in a VM, and the kernel would need some way to notify the VM that it just panicked. Both of these ought to be doable. This is trivial with xVM, btw: just make the panic routine call HYPERVISOR_shutdown(SHUTDOWN_crash); and dom0 will automatically create a full crash dump for the domain, which is readably directly in MDB. As a refinement you might want to only do this if a (suitable) place to crash dump isn't available. regards john ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss