September 2018 - Devel - libvirt List Archives

[libvirt] [RFC PATCH 0/2] Add new mdev type for aggregated resources
by Zhenyu Wang 17 Oct '18

17 Oct '18

Current mdev device create interface depends on fixed mdev type, which get uuid from user to create instance of mdev device. If user wants to use customized number of resource for mdev device, then only can create new mdev type for that which may not be flexible. To allow to create user defined resources for mdev, this RFC trys to extend mdev create interface by adding new "instances=xxx" parameter following uuid, for target mdev type if aggregation is supported, it can create new mdev device which contains resources combined by number of instances, e.g echo "<uuid>,instances=10" > create VM manager e.g libvirt can check mdev type with "aggregation" attribute which can support this setting. And new sysfs attribute "instances" is created for each mdev device to show allocated number. Default number of 1 or no "instances" file can be used for compatibility check. This RFC trys to create new KVMGT type with minimal vGPU resources which can be combined with "instances=x" setting to allocate for user wanted resources. Zhenyu Wang (2): vfio/mdev: Add new instances parameters for mdev create drm/i915/gvt: Add new aggregation type drivers/gpu/drm/i915/gvt/gvt.c | 26 ++++++++++++--- drivers/gpu/drm/i915/gvt/gvt.h | 14 +++++--- drivers/gpu/drm/i915/gvt/kvmgt.c | 9 +++-- drivers/gpu/drm/i915/gvt/vgpu.c | 56 ++++++++++++++++++++++++++++---- drivers/s390/cio/vfio_ccw_ops.c | 3 +- drivers/vfio/mdev/mdev_core.c | 11 ++++--- drivers/vfio/mdev/mdev_private.h | 6 +++- drivers/vfio/mdev/mdev_sysfs.c | 42 ++++++++++++++++++++---- include/linux/mdev.h | 3 +- samples/vfio-mdev/mbochs.c | 3 +- samples/vfio-mdev/mdpy.c | 3 +- samples/vfio-mdev/mtty.c | 3 +- 12 files changed, 141 insertions(+), 38 deletions(-) -- 2.18.0.rc2

6 37

[libvirt] [RFC PATCH auto partition NUMA guest domains v1 0/2] auto partition guests providing the host NUMA topology
by Wim Ten Have 15 Oct '18

15 Oct '18

From: Wim ten Have <wim.ten.have(a)oracle.com> This patch extends the guest domain administration adding support to automatically advertise the host NUMA node capabilities obtained architecture under a guest by creating a vNUMA copy. The mechanism is enabled by setting the check='numa' attribute under the CPU 'host-passthrough' topology: <cpu mode='host-passthrough' check='numa' .../> When enabled the mechanism automatically renders the host capabilities provided NUMA architecture, evenly balances the guest reserved vcpu and memory amongst its vNUMA composed cells and have the cell allocated vcpus pinned towards the host NUMA node physical cpusets. This in such way that the host NUMA topology is still in effect under the partitioned guest domain. Below example auto partitions the host 'lscpu' listed physical NUMA detail under a guest domain vNUMA description. [root@host ]# lscpu Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Byte Order: Little Endian CPU(s): 240 On-line CPU(s) list: 0-239 Thread(s) per core: 2 Core(s) per socket: 15 Socket(s): 8 NUMA node(s): 8 Vendor ID: GenuineIntel CPU family: 6 Model: 62 Model name: Intel(R) Xeon(R) CPU E7-8895 v2 @ 2.80GHz Stepping: 7 CPU MHz: 3449.555 CPU max MHz: 3600.0000 CPU min MHz: 1200.0000 BogoMIPS: 5586.28 Virtualization: VT-x L1d cache: 32K L1i cache: 32K L2 cache: 256K L3 cache: 38400K NUMA node0 CPU(s): 0-14,120-134 NUMA node1 CPU(s): 15-29,135-149 NUMA node2 CPU(s): 30-44,150-164 NUMA node3 CPU(s): 45-59,165-179 NUMA node4 CPU(s): 60-74,180-194 NUMA node5 CPU(s): 75-89,195-209 NUMA node6 CPU(s): 90-104,210-224 NUMA node7 CPU(s): 105-119,225-239 Flags: ... The guest 'anuma' without the auto partition rendering enabled reads; "<cpu mode='host-passthrough' check='none'/>" <domain type='kvm'> <name>anuma</name> <uuid>3f439f5f-1156-4d48-9491-945a2c0abc6d</uuid> <memory unit='KiB'>67108864</memory> <currentMemory unit='KiB'>67108864</currentMemory> <vcpu placement='static'>16</vcpu> <os> <type arch='x86_64' machine='pc-q35-2.11'>hvm</type> <boot dev='hd'/> </os> <features> <acpi/> <apic/> <vmport state='off'/> </features> <cpu mode='host-passthrough' check='none'/> <clock offset='utc'> <timer name='rtc' tickpolicy='catchup'/> <timer name='pit' tickpolicy='delay'/> <timer name='hpet' present='no'/> </clock> <on_poweroff>destroy</on_poweroff> <on_reboot>restart</on_reboot> <on_crash>destroy</on_crash> <pm> <suspend-to-mem enabled='no'/> <suspend-to-disk enabled='no'/> </pm> <devices> <emulator>/usr/bin/qemu-system-x86_64</emulator> <disk type='file' device='disk'> <driver name='qemu' type='qcow2'/> <source file='/var/lib/libvirt/images/anuma.qcow2'/> Enabling the auto partitioning the guest 'anuma' XML is rewritten as listed below; "<cpu mode='host-passthrough' check='numa'>" <domain type='kvm'> <name>anuma</name> <uuid>3f439f5f-1156-4d48-9491-945a2c0abc6d</uuid> <memory unit='KiB'>67108864</memory> <currentMemory unit='KiB'>67108864</currentMemory> <vcpu placement='static'>16</vcpu> <cputune> <vcpupin vcpu='0' cpuset='0-14,120-134'/> <vcpupin vcpu='1' cpuset='15-29,135-149'/> <vcpupin vcpu='2' cpuset='30-44,150-164'/> <vcpupin vcpu='3' cpuset='45-59,165-179'/> <vcpupin vcpu='4' cpuset='60-74,180-194'/> <vcpupin vcpu='5' cpuset='75-89,195-209'/> <vcpupin vcpu='6' cpuset='90-104,210-224'/> <vcpupin vcpu='7' cpuset='105-119,225-239'/> <vcpupin vcpu='8' cpuset='0-14,120-134'/> <vcpupin vcpu='9' cpuset='15-29,135-149'/> <vcpupin vcpu='10' cpuset='30-44,150-164'/> <vcpupin vcpu='11' cpuset='45-59,165-179'/> <vcpupin vcpu='12' cpuset='60-74,180-194'/> <vcpupin vcpu='13' cpuset='75-89,195-209'/> <vcpupin vcpu='14' cpuset='90-104,210-224'/> <vcpupin vcpu='15' cpuset='105-119,225-239'/> </cputune> <os> <type arch='x86_64' machine='pc-q35-2.11'>hvm</type> <boot dev='hd'/> </os> <features> <acpi/> <apic/> <vmport state='off'/> </features> <cpu mode='host-passthrough' check='numa'> <topology sockets='8' cores='1' threads='2'/> <numa> <cell id='0' cpus='0,8' memory='8388608' unit='KiB'> <distances> <sibling id='0' value='10'/> <sibling id='1' value='21'/> <sibling id='2' value='31'/> <sibling id='3' value='21'/> <sibling id='4' value='21'/> <sibling id='5' value='31'/> <sibling id='6' value='31'/> <sibling id='7' value='31'/> </distances> </cell> <cell id='1' cpus='1,9' memory='8388608' unit='KiB'> <distances> <sibling id='0' value='21'/> <sibling id='1' value='10'/> <sibling id='2' value='21'/> <sibling id='3' value='31'/> <sibling id='4' value='31'/> <sibling id='5' value='21'/> <sibling id='6' value='31'/> <sibling id='7' value='31'/> </distances> </cell> <cell id='2' cpus='2,10' memory='8388608' unit='KiB'> <distances> <sibling id='0' value='31'/> <sibling id='1' value='21'/> <sibling id='2' value='10'/> <sibling id='3' value='21'/> <sibling id='4' value='31'/> <sibling id='5' value='31'/> <sibling id='6' value='21'/> <sibling id='7' value='31'/> </distances> </cell> <cell id='3' cpus='3,11' memory='8388608' unit='KiB'> <distances> <sibling id='0' value='21'/> <sibling id='1' value='31'/> <sibling id='2' value='21'/> <sibling id='3' value='10'/> <sibling id='4' value='31'/> <sibling id='5' value='31'/> <sibling id='6' value='31'/> <sibling id='7' value='21'/> </distances> </cell> <cell id='4' cpus='4,12' memory='8388608' unit='KiB'> <distances> <sibling id='0' value='21'/> <sibling id='1' value='31'/> <sibling id='2' value='31'/> <sibling id='3' value='31'/> <sibling id='4' value='10'/> <sibling id='5' value='21'/> <sibling id='6' value='21'/> <sibling id='7' value='31'/> </distances> </cell> <cell id='5' cpus='5,13' memory='8388608' unit='KiB'> <distances> <sibling id='0' value='31'/> <sibling id='1' value='21'/> <sibling id='2' value='31'/> <sibling id='3' value='31'/> <sibling id='4' value='21'/> <sibling id='5' value='10'/> <sibling id='6' value='31'/> <sibling id='7' value='21'/> </distances> </cell> <cell id='6' cpus='6,14' memory='8388608' unit='KiB'> <distances> <sibling id='0' value='31'/> <sibling id='1' value='31'/> <sibling id='2' value='21'/> <sibling id='3' value='31'/> <sibling id='4' value='21'/> <sibling id='5' value='31'/> <sibling id='6' value='10'/> <sibling id='7' value='21'/> </distances> </cell> <cell id='7' cpus='7,15' memory='8388608' unit='KiB'> <distances> <sibling id='0' value='31'/> <sibling id='1' value='31'/> <sibling id='2' value='31'/> <sibling id='3' value='21'/> <sibling id='4' value='31'/> <sibling id='5' value='21'/> <sibling id='6' value='21'/> <sibling id='7' value='10'/> </distances> </cell> </numa> </cpu> <clock offset='utc'> <timer name='rtc' tickpolicy='catchup'/> <timer name='pit' tickpolicy='delay'/> <timer name='hpet' present='no'/> </clock> <on_poweroff>destroy</on_poweroff> <on_reboot>restart</on_reboot> <on_crash>destroy</on_crash> <pm> <suspend-to-mem enabled='no'/> <suspend-to-disk enabled='no'/> </pm> <devices> <emulator>/usr/bin/qemu-system-x86_64</emulator> <disk type='file' device='disk'> <driver name='qemu' type='qcow2'/> <source file='/var/lib/libvirt/images/anuma.qcow2'/> Finally the auto partitioned guest anuma 'lscpu' listed virtual vNUMA detail. [root@anuma ~]# lscpu Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Byte Order: Little Endian CPU(s): 16 On-line CPU(s) list: 0-15 Thread(s) per core: 2 Core(s) per socket: 1 Socket(s): 8 NUMA node(s): 8 Vendor ID: GenuineIntel CPU family: 6 Model: 62 Model name: Intel(R) Xeon(R) CPU E7-8895 v2 @ 2.80GHz Stepping: 7 CPU MHz: 2793.268 BogoMIPS: 5586.53 Virtualization: VT-x Hypervisor vendor: KVM Virtualization type: full L1d cache: 32K L1i cache: 32K L2 cache: 4096K L3 cache: 16384K NUMA node0 CPU(s): 0,8 NUMA node1 CPU(s): 1,9 NUMA node2 CPU(s): 2,10 NUMA node3 CPU(s): 3,11 NUMA node4 CPU(s): 4,12 NUMA node5 CPU(s): 5,13 NUMA node6 CPU(s): 6,14 NUMA node7 CPU(s): 7,15 Flags: ... Wim ten Have (2): domain: auto partition guests providing the host NUMA topology qemuxml2argv: add tests that exercise vNUMA auto partition topology docs/formatdomain.html.in | 7 + docs/schemas/cputypes.rng | 1 + src/conf/cpu_conf.c | 3 +- src/conf/cpu_conf.h | 1 + src/conf/domain_conf.c | 166 ++++++++++++++++++ .../cpu-host-passthrough-nonuma.args | 25 +++ .../cpu-host-passthrough-nonuma.xml | 18 ++ .../cpu-host-passthrough-numa.args | 29 +++ .../cpu-host-passthrough-numa.xml | 18 ++ tests/qemuxml2argvtest.c | 2 + 10 files changed, 269 insertions(+), 1 deletion(-) create mode 100644 tests/qemuxml2argvdata/cpu-host-passthrough-nonuma.args create mode 100644 tests/qemuxml2argvdata/cpu-host-passthrough-nonuma.xml create mode 100644 tests/qemuxml2argvdata/cpu-host-passthrough-numa.args create mode 100644 tests/qemuxml2argvdata/cpu-host-passthrough-numa.xml -- 2.17.1

3 4

[libvirt] [RFC] Faster libvirtd restart with nwfilter rules
by Nikolay Shirokovskiy 12 Oct '18

12 Oct '18

Hi, all. On fat hosts which are capable to run hundreds of VMs restarting libvirtd makes it's services unavailable for a long time if VMs use network filters. In my tests each of 100 VMs has no-promisc [1] and no-mac-spoofing filters and executing virsh list right after daemon restart takes appoximately 140s if no firewalld is running (that is ebtables/iptables/ip6tables commands are used to configure kernel tables). The problem is daemon does not even start to read from client connections because state drivers are not initialized. Initialization is blocked in state drivers autostart which grabs VMs locks. And VMs locks are hold by VMs reconnection code. Each VM reloads network tables on reconnection and this reloading is serialized on updateMutex in gentech nwfilter driver. Workarounding autostart won't help much because even if state drivers will initialize listing VM won't be possible because listing VMs takes each VM lock one by one too. However managing VM that passed reconnection phase will be possible which takes same 140s in worst case. Note that this issue is only applicable if we use filters configuration that don't need ip learning. In the latter case situation is different because reconnection code spawns new thread that apply network rules only after ip is learned from traffic and this thread does not grab VM lock. As result VMs are managable but reloading filters in background takes appoximately those same 140s. I guess managing network filters during this period can have issues too. Anyway this situation does not look good so fixing the described issue by spawning threads even without ip learning does not look nice to me. What speed up is possible on conservative approach? First we can remove for test purpuses firewall ruleLock, gentech dirver updateMutex and filter object mutex which do not serve function in restart scenario. This gives 36s restart time. The speed up is archived because heavy fork/preexec steps are now run concurrently. Next we can try to reduce fork/preexec time. To estimate its contibution alone let's bring back the above locks. It turns out the most time takes fork itself and closing 8k (on my system) file descriptors in preexec. Using vfork gives 2x boost and so does dropping mass close. (I check this mass close contribution because I not quite understand the purpose of this step - libvirt typically set close-on-exec flag on it's descriptors). So this two optimizations alone can result in restart time of 30s. Unfortunately combining the above two approaches does not give boost multiple of them along. The reason is due to concurrency and high number of VMs (100) preexec boost does not have significant role and using vfork dininishes concurrency as it freezes all parent threads before execve. So dropping locks and closes gives 33s restart time and adding vfork to this gives 25s restart time. Another approach is to use --atomic-file option for ebtables (iptables/ip6tables unfortunately does not have one). The idea is to save table to file/edit file/commit table to kernel. I hoped this could give performance boost because we don't need to load/store kernel network table for a single rule update. In order to isolate approaches I also dropped all ip/ip6 updates which can not be done this way. In this approach we can not drop ruleLock in firewall because no other VM threads should change tables between save/commit. This approach gives restart time 25s. But this approach is broken anyway as we can not be sure another application doesn't change newtork table between save/commit in which case these changes will be lost. After all I think we need to move in a different direction. We can add API to all binaries and firewalld to execute many commands in one run. We can pass commands as arguments or wrote them into file which is then given to binary. Then libvirt itself can update for example bridge network table in couple of commands. The exact number depends on new API. For example if we add option to delete chains recursively and an option not to fail on NOENT error we can change table in one command (no listing current rules is required). [1] no-promisc filter <filter name='no-promisc' chain='root' priority='-750'> <uuid>6d055022-1192-4a3d-ae1f-576baa5564b6</uuid> <rule action='return' direction='in' priority='500'> <mac dstmacaddr='ff:ff:ff:ff:ff:ff'/> </rule> <rule action='return' direction='in' priority='500'> <mac dstmacaddr='$MAC'/> </rule> <rule action='return' direction='in' priority='500'> <mac dstmacaddr='33:33:00:00:00:00' dstmacmask='ff:ff:00:00:00:00'/> </rule> <rule action='drop' direction='in' priority='500'> <mac/> </rule> <rule action='return' direction='in' priority='500'> <mac dstmacaddr='01:00:5e:00:00:00' dstmacmask='ff:ff:ff:80:00:00'/> </rule> </filter>

3 6

[libvirt] [PATCH v2 1/2] add nodeset='all' for interleave mode
by Peng Hao 11 Oct '18

11 Oct '18

sometimes we hoped that the memory of vm can be evenly distributed in all nodes according to interleave mode. But different hosts has different node number. So we add nodeset='all' for interleave mode. Signed-off-by: Peng Hao <peng.hao2(a)zte.com.cn> --- src/conf/numa_conf.c | 77 ++++++++++++++++++++++++++++++++++++------- 1 files changed, 64 insertions(+), 13 deletions(-) diff --git a/src/conf/numa_conf.c b/src/conf/numa_conf.c index 97a3ca4..a336a62 100644 --- a/src/conf/numa_conf.c +++ b/src/conf/numa_conf.c @@ -29,6 +29,9 @@ #include "virnuma.h" #include "virstring.h" +#if WITH_NUMACTL +#include <numa.h> +#endif /* * Distance definitions defined Conform ACPI 2.0 SLIT. * See include/linux/topology.h @@ -66,6 +69,7 @@ typedef virDomainNumaNode *virDomainNumaNodePtr; struct _virDomainNuma { struct { bool specified; + bool allnode; virBitmapPtr nodeset; virDomainNumatuneMemMode mode; virDomainNumatunePlacement placement; @@ -259,13 +263,21 @@ virDomainNumatuneParseXML(virDomainNumaPtr numa, tmp = virXMLPropString(node, "nodeset"); if (tmp) { - if (virBitmapParse(tmp, &nodeset, VIR_DOMAIN_CPUMASK_LEN) < 0) - goto cleanup; - - if (virBitmapIsAllClear(nodeset)) { + if (STREQ(tmp, "all") && !virNumaIsAvailable()) { virReportError(VIR_ERR_CONFIG_UNSUPPORTED, - _("Invalid value of 'nodeset': %s"), tmp); + _("Invalid nodeset=%s when numactl is not supported"), tmp); goto cleanup; + } else if (STREQ(tmp, "all") && virNumaIsAvailable()) { + numa->memory.allnode = true; + } else { + if (virBitmapParse(tmp, &nodeset, VIR_DOMAIN_CPUMASK_LEN) < 0) + goto cleanup; + + if (virBitmapIsAllClear(nodeset)) { + virReportError(VIR_ERR_CONFIG_UNSUPPORTED, + _("Invalid value of 'nodeset': %s"), tmp); + goto cleanup; + } } VIR_FREE(tmp); @@ -319,10 +331,14 @@ virDomainNumatuneFormatXML(virBufferPtr buf, virBufferAsprintf(buf, "<memory mode='%s' ", tmp); if (numatune->memory.placement == VIR_DOMAIN_NUMATUNE_PLACEMENT_STATIC) { - if (!(nodeset = virBitmapFormat(numatune->memory.nodeset))) - return -1; - virBufferAsprintf(buf, "nodeset='%s'/>\n", nodeset); - VIR_FREE(nodeset); + if (numatune->memory.allnode == true) { + virBufferAddLit(buf, "nodeset='all'/>\n"); + } else { + if (!(nodeset = virBitmapFormat(numatune->memory.nodeset))) + return -1; + virBufferAsprintf(buf, "nodeset='%s'/>\n", nodeset); + VIR_FREE(nodeset); + } } else if (numatune->memory.placement) { tmp = virDomainNumatunePlacementTypeToString(numatune->memory.placement); virBufferAsprintf(buf, "placement='%s'/>\n", tmp); @@ -489,6 +505,37 @@ virDomainNumatuneMaybeFormatNodeset(virDomainNumaPtr numatune, return 0; } +#if WITH_NUMACTL +static int +makeAllnodeBitmap(virDomainNumaPtr numa) +{ + size_t i = 0, maxnode = 0; + virBitmapPtr bitmap = NULL; + + if ((bitmap = virBitmapNew(VIR_DOMAIN_CPUMASK_LEN)) == NULL) + return -1; + virBitmapClearAll(bitmap); + maxnode = numa_max_node(); + for (i = 0; i <= maxnode; i++) { + if (virBitmapSetBit(bitmap, i) < 0) { + virBitmapFree(bitmap); + return -1; + } + } + + virBitmapFree(numa->memory.nodeset); + numa->memory.nodeset = bitmap; + + return 0; +} +#else +static int +makeAllnodeBitmap(virDomainNumaPtr numa) +{ + return -1; +} +#endif + int virDomainNumatuneSet(virDomainNumaPtr numa, bool placement_static, @@ -538,20 +585,28 @@ virDomainNumatuneSet(virDomainNumaPtr numa, } if (placement == VIR_DOMAIN_NUMATUNE_PLACEMENT_DEFAULT) { - if (numa->memory.nodeset || placement_static) + if (numa->memory.nodeset || placement_static || numa->memory.allnode) placement = VIR_DOMAIN_NUMATUNE_PLACEMENT_STATIC; else placement = VIR_DOMAIN_NUMATUNE_PLACEMENT_AUTO; } if (placement == VIR_DOMAIN_NUMATUNE_PLACEMENT_STATIC && - !numa->memory.nodeset) { + !numa->memory.nodeset && !numa->memory.allnode) { virReportError(VIR_ERR_CONFIG_UNSUPPORTED, "%s", _("nodeset for NUMA memory tuning must be set " "if 'placement' is 'static'")); goto cleanup; } + if (placement == VIR_DOMAIN_NUMATUNE_PLACEMENT_STATIC && + mode == VIR_DOMAIN_NUMATUNE_MEM_INTERLEAVE && + numa->memory.allnode && virNumaIsAvailable()) { + + if (makeAllnodeBitmap(numa) < 0) + goto cleanup; + } + /* setting nodeset when placement auto is invalid */ if (placement == VIR_DOMAIN_NUMATUNE_PLACEMENT_AUTO && numa->memory.nodeset) { -- 1.8.3.1

3 5

[libvirt] [PATCH 00/30] syntax: Remove spaces after casts
by Martin Kletzander 11 Oct '18

11 Oct '18

3 54

[libvirt] [ocaml] reset and resync the libvirt-ocaml repository
by Pino Toscano 10 Oct '18

10 Oct '18

Hi, for reasons mostly lost in the history, after the libvirt-ocaml repository was converted to git, it was not used by its main author (Rich Jones); the development continued on Rich's git, at http://git.annexia.org/?p=ocaml-libvirt.git;a=summary After a talk with Rich, we agreed that it was better to move the development back to libvirt.org, just like all the other bindings. There are two problems however: 1) the first 38 commits have an bad author/committer date, and this is also the reason why the existing libvirt-ocaml is not mirrored on github 2) the top 3 commits on libvirt-ocaml were not integrated back to Rich's ocaml-libvirt, and maybe their content might not be totally OK (I will let Rich comment more on this) While rewriting history is bad, - most probably there are not many users of libvirt-ocaml around, - the repository itself is very small (< 500k), - in general it will better to have a working repository So what I'm proposing is to replace the libvirt-ocaml repository with a fixed version of Rich's ocaml-libvirt, and directly on the git hosting side (i.e. not using force-push on the current one). Rich has already commit access for libvirt, so there are no problems to keep his maintainer role on it. Once done, we can notify users in this list about it. What do you think? Is it an acceptable path forward? -- Pino Toscano

4 6

[libvirt] [PATCHv2 0/4] Introduce x86 RDT (CMT&MBM) host capability
by Wang Huaqiang 09 Oct '18

09 Oct '18

This series of patches introduced the x86 Cache Monitoring Technology (CMT) to libvirt by interacting with kernel resource control (resctrl) interface. CMT is one of the Intel(R) x86 CPU feature which belongs to the Resource Director Technology (RDT). CMT reports the occupancy of the last level cache, which is shared by all CPU cores. In v1 series, we are introducing CMT for libvirt, including reporting host capability and creating CMT groups. Introducing host capability is pretty much a well self-contained step, we only cover this step in this series. As an extension of v1, MBM capability is also introduced. These patches will not cover the part of creating CMT groups, which will be subsequent patches. We have serval discussion about the enabling of CMT, please refer to following links for the RFCs. RFCv3 https://www.redhat.com/archives/libvir-list/2018-August/msg01213.html RFCv2 https://www.redhat.com/archives/libvir-list/2018-July/msg00409.html https://www.redhat.com/archives/libvir-list/2018-July/msg01241.html RFCv1 https://www.redhat.com/archives/libvir-list/2018-June/msg00674.html 1. About reason why CMT is necessary for libvirt? The perf events of 'CMT, MBML, MBMT' have been phased out since Linux kernel commit c39a0e2c8850f08249383f2425dbd8dbe4baad69, in libvirt the perf based cmt,mbm will not work with the latest linux kernel. These patches add CMT feature to libvirt through kernel resctrlfs interface. 2. Interfaces for CMT from the high level. CMT, CAT, MBM and MBA are orthogonal features, each could works independently. If 'CMT' is enabled in host, then a 'cache monitor' is introduced for cache, which is role is monitoring the last level cache utilization of target system process. Cache monitor capabilities is shown under element <cache>. 'MBM', a monitor named memory bandwidth monitor is introduced, for role of monitoring memory bandwidth utilization. The capability information block is located under <memory bandwidth> element. 2.1 Query the host capability of CMT. The element 'monitor' represents the host capabilities of CMT. The explanations of involved attributes: - 'maxMonitors': denotes the maximum monitoring groups could be created, which is limited by the number of hardware 'RMID'. - 'reuseThreshold': An adjustable value affects the final reuse of resources used by monitor. After the action of removing a monitor, the kernel may not release all hardware resources that monitor used immediately if the cache occupancy value associated with 'removed' monitor is above this threshold. Once the cache occupancy is below this threshold, the underlying hardware resource will be reclaimed and be put into the resource pool for next reusing. - 'llc_occupancy': a feature of CMT, reporting the last level cache occupancy information. - 'mbm_total_bytes': a feature of MBM, reporting total memory bandwidth utilization, in bytes, including local memory and remote memory for multi-node system. - 'mbm_local_bytes': a feature of MBM, reporting only local memory bandwidth utilization. # virsh capabilities ... <cache> <bank id='0' level='3' type='both' size='15' unit='MiB' cpus='0-5'> <control granularity='768' min='1536' unit='KiB' type='both' maxAllocs='4'/> </bank> <bank id='1' level='3' type='both' size='15' unit='MiB' cpus='6-11'> <control granularity='768' min='1536' unit='KiB' type='both' maxAllocs='4'/> </bank> + <monitor level='3' reuseThreshold='270336' maxMonitors='176'> + <feature name='llc_occupancy'/> + </monitor> </cache> <memory_bandwidth> <node id='0' cpus='0-5'> <control granularity='10' min ='10' maxAllocs='4'/> </node> <node id='1' cpus='6-11'> <control granularity='10' min ='10' maxAllocs='4'/> </node> + <monitor maxMonitors='176'> + <feature name='mbm_total_bytes'/> + <feature name='mbm_local_bytes'/> + </monitor> </memory_bandwidth> ... </host> Changes since v1: - Introduced MBM capability. - Capability layout changed * Moved <monitor> from cahe <bank> to <cache> * Renamed <Threshold> to <reuseThreshold> - Document for 'reuseThreshold' changed. - Introduced API virResctrlInfoGetMonitorPrefix - Added more tests, covering standalone CMT, fake new feature. - Creating CMT resource control group will be subsequent job. Wang Huaqiang (4): util: Introduce monitor capability interface conf: Refactor cache bank capability structure conf: Refactor memory bandwidth capability structure conf: Introduce RDT monitor host capability docs/schemas/capability.rng | 37 +++- src/conf/capabilities.c | 126 ++++++++--- src/conf/capabilities.h | 24 ++- src/libvirt_private.syms | 2 + src/util/virresctrl.c | 240 +++++++++++++++++++++ src/util/virresctrl.h | 62 ++++++ .../resctrl/info/L3_MON/max_threshold_occupancy | 1 + .../resctrl/info/L3_MON/mon_features | 1 + .../resctrl/info/L3_MON/num_rmids | 1 + .../linux-resctrl-cmt/resctrl/manualres/cpus | 1 + .../linux-resctrl-cmt/resctrl/manualres/schemata | 1 + .../linux-resctrl-cmt/resctrl/manualres/tasks | 0 .../linux-resctrl-cmt/resctrl/schemata | 1 + tests/vircaps2xmldata/linux-resctrl-cmt/system | 1 + .../resctrl/info/L3/cbm_mask | 1 + .../resctrl/info/L3/min_cbm_bits | 1 + .../resctrl/info/L3/num_closids | 1 + .../resctrl/info/L3_MON/max_threshold_occupancy | 1 + .../resctrl/info/L3_MON/mon_features | 10 + .../resctrl/info/L3_MON/num_rmids | 1 + .../resctrl/info/MB/bandwidth_gran | 1 + .../resctrl/info/MB/min_bandwidth | 1 + .../resctrl/info/MB/num_closids | 1 + .../resctrl/manualres/cpus | 1 + .../resctrl/manualres/schemata | 1 + .../resctrl/manualres/tasks | 0 .../linux-resctrl-fake-feature/resctrl/schemata | 1 + .../linux-resctrl-fake-feature/system | 1 + .../resctrl/info/L3_MON/max_threshold_occupancy | 1 + .../linux-resctrl/resctrl/info/L3_MON/mon_features | 3 + .../linux-resctrl/resctrl/info/L3_MON/num_rmids | 1 + .../vircaps2xmldata/vircaps-x86_64-resctrl-cmt.xml | 53 +++++ .../vircaps-x86_64-resctrl-fake-feature.xml | 73 +++++++ tests/vircaps2xmldata/vircaps-x86_64-resctrl.xml | 7 + tests/vircaps2xmltest.c | 2 + 35 files changed, 624 insertions(+), 36 deletions(-) create mode 100644 tests/vircaps2xmldata/linux-resctrl-cmt/resctrl/info/L3_MON/max_threshold_occupancy create mode 100644 tests/vircaps2xmldata/linux-resctrl-cmt/resctrl/info/L3_MON/mon_features create mode 100644 tests/vircaps2xmldata/linux-resctrl-cmt/resctrl/info/L3_MON/num_rmids create mode 100644 tests/vircaps2xmldata/linux-resctrl-cmt/resctrl/manualres/cpus create mode 100644 tests/vircaps2xmldata/linux-resctrl-cmt/resctrl/manualres/schemata create mode 100644 tests/vircaps2xmldata/linux-resctrl-cmt/resctrl/manualres/tasks create mode 100644 tests/vircaps2xmldata/linux-resctrl-cmt/resctrl/schemata create mode 120000 tests/vircaps2xmldata/linux-resctrl-cmt/system create mode 100644 tests/vircaps2xmldata/linux-resctrl-fake-feature/resctrl/info/L3/cbm_mask create mode 100644 tests/vircaps2xmldata/linux-resctrl-fake-feature/resctrl/info/L3/min_cbm_bits create mode 100644 tests/vircaps2xmldata/linux-resctrl-fake-feature/resctrl/info/L3/num_closids create mode 100644 tests/vircaps2xmldata/linux-resctrl-fake-feature/resctrl/info/L3_MON/max_threshold_occupancy create mode 100644 tests/vircaps2xmldata/linux-resctrl-fake-feature/resctrl/info/L3_MON/mon_features create mode 100644 tests/vircaps2xmldata/linux-resctrl-fake-feature/resctrl/info/L3_MON/num_rmids create mode 100644 tests/vircaps2xmldata/linux-resctrl-fake-feature/resctrl/info/MB/bandwidth_gran create mode 100644 tests/vircaps2xmldata/linux-resctrl-fake-feature/resctrl/info/MB/min_bandwidth create mode 100644 tests/vircaps2xmldata/linux-resctrl-fake-feature/resctrl/info/MB/num_closids create mode 100644 tests/vircaps2xmldata/linux-resctrl-fake-feature/resctrl/manualres/cpus create mode 100644 tests/vircaps2xmldata/linux-resctrl-fake-feature/resctrl/manualres/schemata create mode 100644 tests/vircaps2xmldata/linux-resctrl-fake-feature/resctrl/manualres/tasks create mode 100644 tests/vircaps2xmldata/linux-resctrl-fake-feature/resctrl/schemata create mode 120000 tests/vircaps2xmldata/linux-resctrl-fake-feature/system create mode 100644 tests/vircaps2xmldata/linux-resctrl/resctrl/info/L3_MON/max_threshold_occupancy create mode 100644 tests/vircaps2xmldata/linux-resctrl/resctrl/info/L3_MON/mon_features create mode 100644 tests/vircaps2xmldata/linux-resctrl/resctrl/info/L3_MON/num_rmids create mode 100644 tests/vircaps2xmldata/vircaps-x86_64-resctrl-cmt.xml create mode 100644 tests/vircaps2xmldata/vircaps-x86_64-resctrl-fake-feature.xml -- 2.7.4

4 13

[libvirt] [PATCH v2] qemu: agent: Avoid agentError when closing the QEMU agent
by Wang Yechao 08 Oct '18

08 Oct '18

After calling qemuAgentClose(), it is still possible for the QEMU Agent I/O event callback to get invoked. This will trigger an agent error because mon->fd has been set to -1 at this point. Then vm->privateData->agentError is always 'true' except that restart libvirtd or restart qemu-guest-agent process in guest. Silently ignore the case where mon->fd is -1, likewise for mon->watch being zero. Signed-off-by: Wang Yechao <wang.yechao255(a)zte.com.cn> --- v1 patch: https://www.redhat.com/archives/libvir-list/2018-September/msg01382.html Changes in v2: - do not set agentError, let agent state as disconnected instead of error. --- src/qemu/qemu_agent.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/src/qemu/qemu_agent.c b/src/qemu/qemu_agent.c index 97ad0e7..d842b0e 100644 --- a/src/qemu/qemu_agent.c +++ b/src/qemu/qemu_agent.c @@ -530,6 +530,9 @@ static void qemuAgentUpdateWatch(qemuAgentPtr mon) VIR_EVENT_HANDLE_HANGUP | VIR_EVENT_HANDLE_ERROR; + if (!mon->watch) + return; + if (mon->lastError.code == VIR_ERR_OK) { events |= VIR_EVENT_HANDLE_READABLE; @@ -555,6 +558,12 @@ qemuAgentIO(int watch, int fd, int events, void *opaque) VIR_DEBUG("Agent %p I/O on watch %d fd %d events %d", mon, watch, fd, events); #endif + if (mon->fd == -1 || mon->watch == 0) { + virObjectUnlock(mon); + virObjectUnref(mon); + return; + } + if (mon->fd != fd || mon->watch != watch) { if (events & (VIR_EVENT_HANDLE_HANGUP | VIR_EVENT_HANDLE_ERROR)) eof = true; @@ -788,8 +797,10 @@ void qemuAgentClose(qemuAgentPtr mon) virObjectLock(mon); if (mon->fd >= 0) { - if (mon->watch) + if (mon->watch) { virEventRemoveHandle(mon->watch); + mon->watch = 0; + } VIR_FORCE_CLOSE(mon->fd); } -- 1.8.3.1

4 4

[libvirt] [PATCH 00/11] qemu: Improve / cleanup QEMU binary handling
by Andrea Bolognani 08 Oct '18

08 Oct '18

This is the output of 'virsh capabilities' on my laptop: <guest> <os_type>hvm</os_type> <arch name='x86_64'> <wordsize>64</wordsize> <emulator>/usr/bin/qemu-system-x86_64</emulator> <machine maxCpus='255'>pc-i440fx-3.0</machine> <machine canonical='pc-i440fx-3.0' maxCpus='255'>pc</machine> <machine maxCpus='288'>pc-q35-3.0</machine> <machine canonical='pc-q35-3.0' maxCpus='288'>q35</machine>  <domain type='qemu'/> <domain type='kvm'> <emulator>/usr/bin/qemu-kvm</emulator> <machine maxCpus='255'>pc-i440fx-3.0</machine> <machine canonical='pc-i440fx-3.0' maxCpus='255'>pc</machine> <machine maxCpus='288'>pc-q35-3.0</machine> <machine canonical='pc-q35-3.0' maxCpus='288'>q35</machine>  </domain> </arch>  </guest> Notice how all machine types are listed twice, and how we report that qemu-system-x86_64 for TCG guests qemu-kvm must be used for KVM guests - which is inaccurate, since the former can run KVM guests just fine. After this series, the output is much more reasonable: <guest> <os_type>hvm</os_type> <arch name='x86_64'> <wordsize>64</wordsize> <emulator>/usr/bin/qemu-system-x86_64</emulator> <machine maxCpus='255'>pc-i440fx-3.0</machine> <machine canonical='pc-i440fx-3.0' maxCpus='255'>pc</machine> <machine maxCpus='288'>pc-q35-3.0</machine> <machine canonical='pc-q35-3.0' maxCpus='288'>q35</machine>  <domain type='qemu'/> <domain type='kvm'/> </arch>  </guest> As a bonus the code gets *simpler* in the process instead of more complicated, and we even get to shave off ~100 lines! Yay! Andrea Bolognani (11): qemu: Move comments to virQEMUCapsGuestIsNative() qemu: Don't duplicate binary name in capabilities qemu: Move armv7l-on-aarch64 special case qemu: Stop looking after finding the first binary qemu: Expect a single binary in virQEMUCapsInitGuest() qemu: Remove unnecessary variables qemu: Don't look for "qemu-kvm" and "kvm" binaries qemu: Simplify QEMU binary search qemu: Rename qemubinCaps => qemuCaps qemu: Refactor virQEMUCapsCacheLookupByArch() qemu: Prefer qemu-system-* binaries src/qemu/qemu_capabilities.c | 170 +++++++----------- src/qemu/qemu_capabilities.h | 4 +- .../qemucaps2xmloutdata/caps_1.5.3.x86_64.xml | 4 +- .../qemucaps2xmloutdata/caps_1.6.0.x86_64.xml | 4 +- .../qemucaps2xmloutdata/caps_1.7.0.x86_64.xml | 4 +- .../qemucaps2xmloutdata/caps_2.1.1.x86_64.xml | 4 +- .../caps_2.10.0.aarch64.xml | 4 +- .../qemucaps2xmloutdata/caps_2.10.0.ppc64.xml | 4 +- .../qemucaps2xmloutdata/caps_2.10.0.s390x.xml | 4 +- .../caps_2.10.0.x86_64.xml | 4 +- .../qemucaps2xmloutdata/caps_2.11.0.s390x.xml | 4 +- .../caps_2.11.0.x86_64.xml | 4 +- .../caps_2.12.0.aarch64.xml | 4 +- .../qemucaps2xmloutdata/caps_2.12.0.ppc64.xml | 4 +- .../qemucaps2xmloutdata/caps_2.12.0.s390x.xml | 4 +- .../caps_2.12.0.x86_64.xml | 4 +- .../qemucaps2xmloutdata/caps_2.4.0.x86_64.xml | 4 +- .../qemucaps2xmloutdata/caps_2.5.0.x86_64.xml | 4 +- .../caps_2.6.0.aarch64.xml | 4 +- .../qemucaps2xmloutdata/caps_2.6.0.ppc64.xml | 4 +- .../qemucaps2xmloutdata/caps_2.6.0.x86_64.xml | 4 +- .../qemucaps2xmloutdata/caps_2.7.0.s390x.xml | 4 +- .../qemucaps2xmloutdata/caps_2.7.0.x86_64.xml | 4 +- .../qemucaps2xmloutdata/caps_2.8.0.s390x.xml | 4 +- .../qemucaps2xmloutdata/caps_2.8.0.x86_64.xml | 4 +- .../qemucaps2xmloutdata/caps_2.9.0.ppc64.xml | 4 +- .../qemucaps2xmloutdata/caps_2.9.0.s390x.xml | 4 +- .../qemucaps2xmloutdata/caps_2.9.0.x86_64.xml | 4 +- .../qemucaps2xmloutdata/caps_3.0.0.ppc64.xml | 4 +- .../qemucaps2xmloutdata/caps_3.0.0.x86_64.xml | 4 +- tests/qemucaps2xmltest.c | 2 - 31 files changed, 97 insertions(+), 191 deletions(-) -- 2.17.1

5 21

[libvirt] [RFC v2 00/16] Add vhost-user-gpu support
by marcandre.lureau＠redhat.com 05 Oct '18

05 Oct '18

From: Marc-André Lureau <marcandre.lureau(a)redhat.com> Hi, This series of patches add support for running a virtio GPU in a seperate process, using vhost-user. The QEMU series "[PATCH v4 00/29] vhost-user for input & GPU" is still under review, and will hopefully land in 3.1. There are several benefits of running the GPU process in an external process, since Mesa is rather heavy on the qemu main loop, and may block for a while or crash. I observe x5 performance improvements with Unigine Heaven 4 benchmark. The external GPU process is started with one end of the vhost-user socket pair, the other end is given to a QEMU chardev. It is also added to the emulator cgroup to restrict its CPU usage. vhost-user requires shared VM memory. The first patches ease and improve shared memory setup, by using memfd. They could be considered seperatly, but that's the setup I'd recommend with vhost-user-gpu. Review welcome! RFCv2: - add new memfd memroyBacking source type - drop the implicit shared memory NUMA setup approach, explicit now required - rebased Marc-André Lureau (16): qemu: add memory-backend-memfd capability check qemu: add memfd memory backing qemu: add vhost-user-gpu capabilities checks domain: add "vhost-user" video type qemu: fill the vhost-user video type capability qemu: check that qemu is vhost-user-vga capable qemu: vhost-user is valid as non-primary video device qemu: validate vhost-user video model qemu: add qemuSecurityStartVhostUserGPU helper qemu: add vhost-user-gpu helper unit qemu: restrict 'virgl=' option to 'virtio' video type qemu: set default address type on vhost-user video model qemu: start/stop the vhost-user-gpu external device qemu: build vhost-user-backend for vhost-user-gpu qemu: build vhost-user-gpu video device arguments tests: add vhost-user-gpu xml2argv tests docs/formatdomain.html.in | 11 +- docs/schemas/domaincommon.rng | 2 + src/conf/device_conf.h | 1 + src/conf/domain_conf.c | 7 +- src/conf/domain_conf.h | 2 + src/qemu/Makefile.inc.am | 2 + src/qemu/qemu_capabilities.c | 8 + src/qemu/qemu_capabilities.h | 3 + src/qemu/qemu_command.c | 135 ++++++-- src/qemu/qemu_domain.c | 8 +- src/qemu/qemu_domain_address.c | 4 +- src/qemu/qemu_extdevice.c | 47 ++- src/qemu/qemu_process.c | 6 +- src/qemu/qemu_security.c | 48 +++ src/qemu/qemu_security.h | 6 + src/qemu/qemu_vhost_user_gpu.c | 318 ++++++++++++++++++ src/qemu/qemu_vhost_user_gpu.h | 48 +++ tests/domaincapsschemadata/full.xml | 1 + .../caps_2.12.0.aarch64.xml | 1 + .../caps_2.12.0.ppc64.xml | 1 + .../caps_2.12.0.s390x.xml | 1 + .../caps_2.12.0.x86_64.xml | 1 + .../qemucapabilitiesdata/caps_3.0.0.ppc64.xml | 1 + .../caps_3.0.0.riscv32.xml | 1 + .../caps_3.0.0.riscv64.xml | 1 + .../caps_3.0.0.x86_64.xml | 1 + tests/qemuxml2argvdata/memfd-memory-numa.args | 27 ++ tests/qemuxml2argvdata/memfd-memory-numa.xml | 33 ++ .../vhost-user-gpu-secondary.args | 33 ++ .../vhost-user-gpu-secondary.xml | 44 +++ tests/qemuxml2argvdata/vhost-user-vga.args | 30 ++ tests/qemuxml2argvdata/vhost-user-vga.xml | 41 +++ tests/qemuxml2argvtest.c | 15 + 33 files changed, 849 insertions(+), 39 deletions(-) create mode 100644 src/qemu/qemu_vhost_user_gpu.c create mode 100644 src/qemu/qemu_vhost_user_gpu.h create mode 100644 tests/qemuxml2argvdata/memfd-memory-numa.args create mode 100644 tests/qemuxml2argvdata/memfd-memory-numa.xml create mode 100644 tests/qemuxml2argvdata/vhost-user-gpu-secondary.args create mode 100644 tests/qemuxml2argvdata/vhost-user-gpu-secondary.xml create mode 100644 tests/qemuxml2argvdata/vhost-user-vga.args create mode 100644 tests/qemuxml2argvdata/vhost-user-vga.xml -- 2.19.0.rc0.48.gb9dfa238d5

4 21