Re: [QEMU PATCH 0/2] virtio-blk: writeback cache enable improvements
Il 03/07/2012 15:20, Paolo Bonzini ha scritto: > These patches let virtio-blk use the new support for toggling the cache > mode between writethrough and writeback. > > The first patch introduces a new feature bit and configuration field to > do this. The second patch disables writeback caching for guests that do > not negotiate VIRTIO_BLK_F_WCACHE (meaning that they cannot send flush > requests), so that limited or older guests are now safe wrt power losses. > VIRTIO_BLK_F_FLUSH has been introduced in Linux 2.6.32 (in 2009) and was > backported to RHEL/CentOS 5.6 (in 2010). > > The Windows drivers (which work by emulating SCSI on top of virtio-blk) > have bugs in this area, which I reported on the Red Hat Bugzilla as > bugs 837321 and 837324. With these patches they will suffer a > performance hit but gain correctness. > > Paolo Bonzini (2): > virtio-blk: support VIRTIO_BLK_F_CONFIG_WCE > virtio-blk: disable write cache if not negotiated Ping - Anthony, mst? Paolo -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: [QEMU PATCH 0/2] virtio-blk: writeback cache enable improvements
Il 23/07/2012 18:32, Paolo Bonzini ha scritto: > Il 03/07/2012 15:20, Paolo Bonzini ha scritto: >> > These patches let virtio-blk use the new support for toggling the cache >> > mode between writethrough and writeback. >> > >> > The first patch introduces a new feature bit and configuration field to >> > do this. The second patch disables writeback caching for guests that do >> > not negotiate VIRTIO_BLK_F_WCACHE (meaning that they cannot send flush >> > requests), so that limited or older guests are now safe wrt power losses. >> > VIRTIO_BLK_F_FLUSH has been introduced in Linux 2.6.32 (in 2009) and was >> > backported to RHEL/CentOS 5.6 (in 2010). >> > >> > The Windows drivers (which work by emulating SCSI on top of virtio-blk) >> > have bugs in this area, which I reported on the Red Hat Bugzilla as >> > bugs 837321 and 837324. With these patches they will suffer a >> > performance hit but gain correctness. >> > >> > Paolo Bonzini (2): >> > virtio-blk: support VIRTIO_BLK_F_CONFIG_WCE >> > virtio-blk: disable write cache if not negotiated > Ping - Anthony, mst? Ping^2, so we can switch writethrough->writeback in 1.2. Paolo -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: [QEMU PATCH 0/2] virtio-blk: writeback cache enable improvements
Am 01.08.2012 17:52, schrieb Paolo Bonzini: > Il 23/07/2012 18:32, Paolo Bonzini ha scritto: >> Il 03/07/2012 15:20, Paolo Bonzini ha scritto: These patches let virtio-blk use the new support for toggling the cache mode between writethrough and writeback. The first patch introduces a new feature bit and configuration field to do this. The second patch disables writeback caching for guests that do not negotiate VIRTIO_BLK_F_WCACHE (meaning that they cannot send flush requests), so that limited or older guests are now safe wrt power losses. VIRTIO_BLK_F_FLUSH has been introduced in Linux 2.6.32 (in 2009) and was backported to RHEL/CentOS 5.6 (in 2010). The Windows drivers (which work by emulating SCSI on top of virtio-blk) have bugs in this area, which I reported on the Red Hat Bugzilla as bugs 837321 and 837324. With these patches they will suffer a performance hit but gain correctness. Paolo Bonzini (2): virtio-blk: support VIRTIO_BLK_F_CONFIG_WCE virtio-blk: disable write cache if not negotiated >> Ping - Anthony, mst? > > Ping^2, so we can switch writethrough->writeback in 1.2. Speak now or forever hold your peace. If there are no more comments until Friday, I'll just apply it. Kevin -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html