November 2016 - Devel - libvirt List Archives

[libvirt] [PATCH] conf: Make scheduler formatting simpler
by Martin Kletzander 08 Dec '16

08 Dec '16

Since the great rework of how we store vcpu- and iothread-related data, we have overly complex part of code that is trying to format the scheduler tuning data in as less lines as possible by grouping settings for multiple threads. That was designed as an input syntax sugar for users, but we don't need to also use that when formatting the XML. Switching to simple enumeration makes the code nicer, shorter and more welcoming to future changes. Signed-off-by: Martin Kletzander <mkletzan(a)redhat.com> --- src/conf/domain_conf.c | 209 ++++----------------- ...l2xmlout-cputune-iothreadsched-zeropriority.xml | 7 +- .../qemuxml2xmlout-cputune-iothreadsched.xml | 7 +- 3 files changed, 43 insertions(+), 180 deletions(-) diff --git a/src/conf/domain_conf.c b/src/conf/domain_conf.c index 6e008e22e3c7..51f1ee14498a 100644 --- a/src/conf/domain_conf.c +++ b/src/conf/domain_conf.c @@ -23066,183 +23066,35 @@ virDomainDefHasCapabilitiesFeatures(virDomainDefPtr def) } -/** - * virDomainFormatSchedDef: - * @def: domain definiton - * @buf: target XML buffer - * @name: name of the target XML element - * @func: function that returns the thread scheduler parameter struct for an object - * @resourceMap: bitmap of indexes of objects that shall be formatted (used with @func) - * - * Formats one of the two scheduler tuning elements to the XML. This function - * transforms the internal representation where the scheduler info is stored - * per-object to the XML representation where the info is stored per group of - * objects. This function autogroups all the relevant scheduler configs. - * - * Returns 0 on success -1 on error. - */ -static int -virDomainFormatSchedDef(virDomainDefPtr def, - virBufferPtr buf, +static void +virDomainFormatSchedDef(virBufferPtr buf, const char *name, - virDomainThreadSchedParamPtr (*func)(virDomainDefPtr, unsigned int), - virBitmapPtr resourceMap) -{ - virBitmapPtr schedMap = NULL; - virBitmapPtr prioMap = NULL; - virDomainThreadSchedParamPtr sched; - char *tmp = NULL; - ssize_t next; - size_t i; - int ret = -1; - - /* Okay, @func should never return NULL here because it does - * so iff corresponding resource does not exists. But if it - * doesn't we should not have been called in the first place. - * But some compilers fails to see this complex reasoning and - * deduct that this code is buggy. Shut them up by checking - * for return value of sched. Even though we don't need to. - */ - - if (!(schedMap = virBitmapNew(VIR_DOMAIN_CPUMASK_LEN)) || - !(prioMap = virBitmapNew(VIR_DOMAIN_CPUMASK_LEN))) - goto cleanup; - - for (i = VIR_PROC_POLICY_NONE + 1; i < VIR_PROC_POLICY_LAST; i++) { - virBitmapClearAll(schedMap); - - /* find vcpus using a particular scheduler */ - next = -1; - while ((next = virBitmapNextSetBit(resourceMap, next)) > -1) { - sched = func(def, next); - - if (sched && sched->policy == i) - ignore_value(virBitmapSetBit(schedMap, next)); - } - - /* it's necessary to discriminate priority levels for schedulers that - * have them */ - while (!virBitmapIsAllClear(schedMap)) { - virBitmapPtr currentMap = NULL; - ssize_t nextprio; - bool hasPriority = false; - int priority = 0; - - switch ((virProcessSchedPolicy) i) { - case VIR_PROC_POLICY_NONE: - case VIR_PROC_POLICY_BATCH: - case VIR_PROC_POLICY_IDLE: - case VIR_PROC_POLICY_LAST: - currentMap = schedMap; - break; - - case VIR_PROC_POLICY_FIFO: - case VIR_PROC_POLICY_RR: - virBitmapClearAll(prioMap); - hasPriority = true; - - /* we need to find a subset of vCPUs with the given scheduler - * that share the priority */ - nextprio = virBitmapNextSetBit(schedMap, -1); - if (!(sched = func(def, nextprio))) - goto cleanup; - - priority = sched->priority; - ignore_value(virBitmapSetBit(prioMap, nextprio)); - - while ((nextprio = virBitmapNextSetBit(schedMap, nextprio)) > -1) { - sched = func(def, nextprio); - if (sched && sched->priority == priority) - ignore_value(virBitmapSetBit(prioMap, nextprio)); - } - - currentMap = prioMap; - break; - } - - /* now we have the complete group */ - if (!(tmp = virBitmapFormat(currentMap))) - goto cleanup; - - virBufferAsprintf(buf, - "<%sched %s='%s' scheduler='%s'", - name, name, tmp, - virProcessSchedPolicyTypeToString(i)); - VIR_FREE(tmp); - - if (hasPriority) - virBufferAsprintf(buf, " priority='%d'", priority); + virDomainThreadSchedParamPtr sched, + size_t id) +{ + switch (sched->policy) { + case VIR_PROC_POLICY_BATCH: + case VIR_PROC_POLICY_IDLE: + virBufferAsprintf(buf, "<%ssched " + "%ss='%zu' scheduler='%s'/>\n", + name, name, id, + virProcessSchedPolicyTypeToString(sched->policy)); + break; - virBufferAddLit(buf, "/>\n"); + case VIR_PROC_POLICY_RR: + case VIR_PROC_POLICY_FIFO: + virBufferAsprintf(buf, "<%ssched " + "%ss='%zu' scheduler='%s' priority='%d'/>\n", + name, name, id, + virProcessSchedPolicyTypeToString(sched->policy), + sched->priority); + break; - /* subtract all vCPUs that were already found */ - virBitmapSubtract(schedMap, currentMap); + case VIR_PROC_POLICY_NONE: + case VIR_PROC_POLICY_LAST: + break; } - } - - ret = 0; - cleanup: - virBitmapFree(schedMap); - virBitmapFree(prioMap); - return ret; -} - - -static int -virDomainFormatVcpuSchedDef(virDomainDefPtr def, - virBufferPtr buf) -{ - virBitmapPtr allcpumap; - int ret; - - if (virDomainDefGetVcpusMax(def) == 0) - return 0; - - if (!(allcpumap = virBitmapNew(virDomainDefGetVcpusMax(def)))) - return -1; - - virBitmapSetAll(allcpumap); - - ret = virDomainFormatSchedDef(def, buf, "vcpus", virDomainDefGetVcpuSched, - allcpumap); - - virBitmapFree(allcpumap); - return ret; -} - - -static int -virDomainFormatIOThreadSchedDef(virDomainDefPtr def, - virBufferPtr buf) -{ - virBitmapPtr threadmap; - size_t i; - int ret = -1; - - if (def->niothreadids == 0) - return 0; - - if (!(threadmap = virBitmapNewEmpty())) - return -1; - - for (i = 0; i < def->niothreadids; i++) { - if (def->iothreadids[i]->sched.policy != VIR_PROC_POLICY_NONE && - virBitmapSetBitExpand(threadmap, def->iothreadids[i]->iothread_id) < 0) - goto cleanup; - } - - if (virBitmapIsAllClear(threadmap)) { - ret = 0; - goto cleanup; - } - - ret = virDomainFormatSchedDef(def, buf, "iothreads", - virDomainDefGetIOThreadSched, threadmap); - - cleanup: - virBitmapFree(threadmap); - return ret; } @@ -23336,11 +23188,16 @@ virDomainCputuneDefFormat(virBufferPtr buf, VIR_FREE(cpumask); } - if (virDomainFormatVcpuSchedDef(def, &childrenBuf) < 0) - goto cleanup; + for (i = 0; i < def->maxvcpus; i++) { + virDomainFormatSchedDef(&childrenBuf, "vcpu", + &def->vcpus[i]->sched, i); + } - if (virDomainFormatIOThreadSchedDef(def, &childrenBuf) < 0) - goto cleanup; + for (i = 0; i < def->niothreadids; i++) { + virDomainFormatSchedDef(&childrenBuf, "iothread", + &def->iothreadids[i]->sched, + def->iothreadids[i]->iothread_id); + } if (virBufferUse(&childrenBuf)) { virBufferAddLit(buf, "<cputune>\n"); diff --git a/tests/qemuxml2xmloutdata/qemuxml2xmlout-cputune-iothreadsched-zeropriority.xml b/tests/qemuxml2xmloutdata/qemuxml2xmlout-cputune-iothreadsched-zeropriority.xml index 5616c5c8474d..794a52d57133 100644 --- a/tests/qemuxml2xmloutdata/qemuxml2xmlout-cputune-iothreadsched-zeropriority.xml +++ b/tests/qemuxml2xmloutdata/qemuxml2xmlout-cputune-iothreadsched-zeropriority.xml @@ -12,8 +12,11 @@ <vcpupin vcpu='0' cpuset='0'/> <vcpupin vcpu='1' cpuset='1'/> <emulatorpin cpuset='1'/> - <vcpusched vcpus='0-1' scheduler='fifo' priority='0'/> - <iothreadsched iothreads='1-3' scheduler='rr' priority='0'/> + <vcpusched vcpus='0' scheduler='fifo' priority='0'/> + <vcpusched vcpus='1' scheduler='fifo' priority='0'/> + <iothreadsched iothreads='1' scheduler='rr' priority='0'/> + <iothreadsched iothreads='2' scheduler='rr' priority='0'/> + <iothreadsched iothreads='3' scheduler='rr' priority='0'/> </cputune> <os> <type arch='i686' machine='pc'>hvm</type> diff --git a/tests/qemuxml2xmloutdata/qemuxml2xmlout-cputune-iothreadsched.xml b/tests/qemuxml2xmloutdata/qemuxml2xmlout-cputune-iothreadsched.xml index a0457bc62ec0..cd1dc87b524d 100644 --- a/tests/qemuxml2xmloutdata/qemuxml2xmlout-cputune-iothreadsched.xml +++ b/tests/qemuxml2xmloutdata/qemuxml2xmlout-cputune-iothreadsched.xml @@ -12,8 +12,11 @@ <vcpupin vcpu='0' cpuset='0'/> <vcpupin vcpu='1' cpuset='1'/> <emulatorpin cpuset='1'/> - <vcpusched vcpus='0-1' scheduler='fifo' priority='1'/> - <iothreadsched iothreads='1-3' scheduler='batch'/> + <vcpusched vcpus='0' scheduler='fifo' priority='1'/> + <vcpusched vcpus='1' scheduler='fifo' priority='1'/> + <iothreadsched iothreads='1' scheduler='batch'/> + <iothreadsched iothreads='2' scheduler='batch'/> + <iothreadsched iothreads='3' scheduler='batch'/> </cputune> <os> <type arch='i686' machine='pc'>hvm</type> -- 2.11.0.rc2

2 2

[libvirt] [PATCH v2 0/3] Fix case with non-root domain and hugepages
by Michal Privoznik 07 Dec '16

07 Dec '16

v2 of: https://www.redhat.com/archives/libvir-list/2016-November/msg01060.html diff to v1: - use virDomainObjGetShortName to construct hugepages path - instead of implementing virSecurityManagerSetHugepages drop it Michal Privoznik (3): virDomainObjGetShortName: take virDomainDef qemu: Create hugepage path on per domain basis security: Drop virSecurityManagerSetHugepages src/conf/domain_conf.c | 4 +- src/conf/domain_conf.h | 2 +- src/libvirt_private.syms | 1 - src/qemu/qemu_command.c | 4 +- src/qemu/qemu_conf.c | 44 +++++++++---- src/qemu/qemu_conf.h | 16 +++-- src/qemu/qemu_domain.c | 2 +- src/qemu/qemu_driver.c | 21 ++---- src/qemu/qemu_process.c | 74 ++++++++++++++++------ src/security/security_driver.h | 1 - src/security/security_manager.c | 17 ----- src/security/security_manager.h | 3 - src/security/security_stack.c | 19 ------ .../qemuxml2argv-hugepages-numa.args | 6 +- .../qemuxml2argv-hugepages-pages.args | 16 ++--- .../qemuxml2argv-hugepages-pages2.args | 2 +- .../qemuxml2argv-hugepages-pages3.args | 2 +- .../qemuxml2argv-hugepages-pages5.args | 2 +- .../qemuxml2argv-hugepages-shared.args | 14 ++-- tests/qemuxml2argvdata/qemuxml2argv-hugepages.args | 2 +- .../qemuxml2argv-memory-hotplug-dimm-addr.args | 4 +- .../qemuxml2argv-memory-hotplug-dimm.args | 4 +- 22 files changed, 136 insertions(+), 124 deletions(-) -- 2.8.4

2 6

[libvirt] [PATCH v1 00/21] Run qemu under its own namespace
by Michal Privoznik 07 Dec '16

07 Dec '16

Finally. This is full implementation of my RFC: https://www.redhat.com/archives/libvir-list/2016-November/msg00691.html The first two patches were posted separately, but since they lack review I'm sending them here too because they are important for the feature: https://www.redhat.com/archives/libvir-list/2016-November/msg01060.html All of these patches: a) can be found on my github: https://github.com/zippy2/libvirt/tree/qemu_container_v2 b) pass my basic testing: - run domain with device passthrough - device hot(un-)plug (disks, RNGs, chardevs, PCI/USB) c) seem to add negligible overhead to domain startup process Michal Privoznik (21): qemu: Create hugepage path on per domain basis security: Implement virSecurityManagerSetHugepages virprocess: Introduce virProcessSetupPrivateMountNS virfile: Introduce virFileSetupDev virfile: Introduce ACL helpers virusb: Introduce virUSBDeviceGetPath virscsi: Introduce virSCSIDeviceGetPath qemu_cgroup: Expose defaultDeviceACL qemu: Spawn qemu under mount namespace qemu: Prepare disks when starting a domain qemu: Prepare hostdevs when starting a domain qemu: Prepare chardevs when starting a domain qemu: Prepare TPM when starting a domain qemu: Prepare inputs when starting a domain qemu: Prepare RNGs when starting a domain qemu: Enter the namespace on relabelling qemu: Manage /dev entry on disk hotplug qemu: Manage /dev entry on hostdev hotplug qemu: Manage /dev entry on chardev hotplug qemu: Manage /dev entry on RNG hotplug qemu: Let users opt-out from containerization configure.ac | 12 +- src/Makefile.am | 7 +- src/libvirt_private.syms | 9 + src/lxc/lxc_container.c | 20 +- src/lxc/lxc_controller.c | 32 +- src/qemu/libvirtd_qemu.aug | 1 + src/qemu/qemu.conf | 8 + src/qemu/qemu_cgroup.c | 2 +- src/qemu/qemu_cgroup.h | 1 + src/qemu/qemu_command.c | 4 +- src/qemu/qemu_conf.c | 50 +- src/qemu/qemu_conf.h | 18 +- src/qemu/qemu_domain.c | 1147 ++++++++++++++++++++ src/qemu/qemu_domain.h | 42 + src/qemu/qemu_driver.c | 24 +- src/qemu/qemu_hotplug.c | 90 +- src/qemu/qemu_process.c | 53 +- src/qemu/qemu_security.c | 208 ++++ src/qemu/qemu_security.h | 55 + src/qemu/test_libvirtd_qemu.aug.in | 1 + src/security/security_dac.c | 11 + src/security/security_selinux.c | 10 + src/util/virfile.c | 153 +++ src/util/virfile.h | 17 + src/util/virprocess.c | 38 + src/util/virprocess.h | 2 + src/util/virscsi.c | 6 + src/util/virscsi.h | 1 + src/util/virusb.c | 5 + src/util/virusb.h | 1 + .../qemuxml2argv-hugepages-numa.args | 4 +- .../qemuxml2argv-hugepages-pages.args | 14 +- .../qemuxml2argv-hugepages-pages2.args | 2 +- .../qemuxml2argv-hugepages-pages3.args | 2 +- .../qemuxml2argv-hugepages-pages5.args | 2 +- .../qemuxml2argv-hugepages-shared.args | 12 +- tests/qemuxml2argvdata/qemuxml2argv-hugepages.args | 2 +- .../qemuxml2argv-memory-hotplug-dimm-addr.args | 4 +- .../qemuxml2argv-memory-hotplug-dimm.args | 4 +- 39 files changed, 1933 insertions(+), 141 deletions(-) create mode 100644 src/qemu/qemu_security.c create mode 100644 src/qemu/qemu_security.h -- 2.8.4

2 44

[libvirt] [PATCH 0/6] Qemu: s390: Cpu Model Support
by Jason J. Herne 07 Dec '16

07 Dec '16

This patch set enables cpu model support for s390. The user can now set exact cpu models, query supported models via virsh domcapabilities, and use host-model and host-passthrough modes. The end result is that migration is safer because Qemu will perform runnability checking on the destination host and quit with an error if the guest's cpu model is not supported. Big Thanks for Jiri and Eduardo for being patient and answering our questions while we figured out what we were doing! Collin L. Walling (5): s390: Stop reporting "host" for host model qemu: qmp query-cpu-model-expansion command qemu-caps: Get host model directly from Qemu when available qemu: migration: warn if migrating with host-passthrough qemu: command: Support new cpu feature argument syntax Jason J. Herne (1): s390: Cpu driver support for update and compare po/POTFILES.in | 1 + src/cpu/cpu_s390.c | 61 ++++++++++++++++++++---- src/qemu/qemu_capabilities.c | 109 +++++++++++++++++++++++++++++++++++++++++-- src/qemu/qemu_capabilities.h | 1 + src/qemu/qemu_command.c | 10 +++- src/qemu/qemu_migration.c | 4 ++ src/qemu/qemu_monitor.c | 60 ++++++++++++++++++++++++ src/qemu/qemu_monitor.h | 22 +++++++++ src/qemu/qemu_monitor_json.c | 94 +++++++++++++++++++++++++++++++++++++ src/qemu/qemu_monitor_json.h | 6 +++ 10 files changed, 353 insertions(+), 15 deletions(-) -- 1.9.1

3 16

[libvirt] Libvirt domain event usage and consistency
by Roman Mohr 07 Dec '16

07 Dec '16

Hi, I recently started to use the libvirt domain events. With them I increase the responsiveness of my VM state wachers. In general it works pretty well. I just listen to the events and do a periodic resync to cope with missed events. While watching the events I ran into a few interesting situations I wanted to share. The points 1-3 describe some minor issues or irregularities. Point 4 is about the fact that domain and state updates are not versioned which makes it very hard to stay in sync with libvirt when using events. My libvirt version is 1.2.18.4. 1) Event order seems to be weird on startup: When listening for VM lifecycle events I get this order: {"event_type": "Started", "timestamp": "2016-11-25T11:59:53.209326Z", "reason": "Booted", "domain_name": "generic", "domain_id": "8ff7047b-fb46-44ff-a4c6-7c20c73ab86e"} {"event_type": "Defined", "timestamp": "2016-11-25T11:59:53.435530Z", "reason": "Added", "domain_name": "generic", "domain_id": "8ff7047b-fb46-44ff-a4c6-7c20c73ab86e"} It is strange that a VM already boots before it is defined. Is this the intended order? 2) Defining a VM with VIR_DOMAIN_START_PAUSED gives me this event order {"event_type": "Defined", "timestamp": "2016-11-25T12:02:44.037817Z", "reason": "Added", "domain_name": "core_node", "domain_id": "b9906489-6d5b-40f8-a742-ca71b2b84277"} {"event_type": "Resumed", "timestamp": "2016-11-25T12:02:44.813104Z", "reason": "Unpaused", "domain_name": "core_node", "domain_id": "b9906489-6d5b-40f8-a742-ca71b2b84277"} {"event_type": "Started", "timestamp": "2016-11-25T12:02:44.813733Z", "reason": "Booted", "domain_name": "core_node", "domain_id": "b9906489-6d5b-40f8-a742-ca71b2b84277"} This boot-order makes it hard to track active domains by listening to life-cycle events. One could theoretically still always fetch the VM state in the event callback and check the state, but if the state is not immediately transferred with the event itself, it can already be outdated, so this might be racy (intransparent for the libvirt bindings user), and as described in (3) currently not even possible. In general the real existing events seem to differ quite significantly from the described life-cycle in [1]. 3) "Defined" event is triggered before the domain is completely defined {"event_type": "Defined", "timestamp": "2016-11-25T12:02:44.037817Z", "reason": "Added", "domain_name": "core_node", "domain_id": "b9906489-6d5b-40f8-a742-ca71b2b84277"} {"event_type": "Resumed", "timestamp": "2016-11-25T12:02:44.813104Z", "reason": "Unpaused", "domain_name": "core_node", "domain_id": "b9906489-6d5b-40f8-a742-ca71b2b84277"} {"event_type": "Started", "timestamp": "2016-11-25T12:02:44.813733Z", "reason": "Booted", "domain_name": "core_node", "domain_id": "b9906489-6d5b-40f8-a742-ca71b2b84277"} When I try to process the first event and do a xmldump I get: Event: [Code-42] [Domain-10] Domain not found: no domain with matching uuid 'b9906489-6d5b-40f8-a742-ca71b2b84277' (core_node) So it seems like I get the event before the domain is completely ready. 4) There libvirt domain description is not versioned I would expect that every time I update a domainxml (update from third party entity), or an event is generated (update from libvirt), that the resource version of a Domain is increased and that I get this resource version when I do a xmldump or when I get an event. Without this there is afaik no way to stay in sync with libvirt, even if you do regular polling of all domains. The main issue here is that I can never know if events in the queue arrived before my latest domain resync or after it. Also not that this is not about delivery guarantees of events. It is just about having a consistent view of a VM and the individual event. If I have resource versions, I can decide if an event is still interesting for me or not, which is exactly what I need to solve the syncing problem above. When I do a complete relisting of all domains to syn, I know which version I got and I can then see on every event if it is newer or older. If along side with the event, the domain xml, the VM state, and the resource version would be sent to a client, it would be even better. Then, whenever there is a new event for a VM in the queue, I can be sure that this domainxml I see is the one which triggered the event. This xml is then a complete representation for this revision number. Would be nice to hear your thoughts to these points. Best Regards, Roman [1] https://wiki.libvirt.org/page/VM_lifecycle#States_that_a_guest_domain_can_b…

3 10

[libvirt] [PATCH v5 0/2] List only online cpus for vcpupin/emulatorpin when vcpu placement static
by Nitesh Konkar 06 Dec '16

06 Dec '16

Currently when the vcpu placement is static and cpuset is not specified, CPU Affinity shows 0.. CPUMAX. This patchset will result in display of only online CPU's under CPU Affinity on linux. Fixes the following Bug: virsh dumpxml Fedora <domain type='kvm' id='4'> <name>Fedora</name> <uuid>aecf3e5e-6f9a-42a3-9d6a-223a75569a66</uuid> <maxMemory slots='32' unit='KiB'>3145728</maxMemory> <memory unit='KiB'>524288</memory> <currentMemory unit='KiB'>524288</currentMemory> <vcpu placement='static' current='8'>160</vcpu> <resource> <partition>/machine</partition> </resource> ..................... ....................... ......................... <memballoon model='virtio'> <alias name='balloon0'/> <address type='pci' domain='0x0000' bus='0x00' slot='0x06' function='0x0'/> </memballoon> </devices> <seclabel type='dynamic' model='dac' relabel='yes'> <label>+0:+0</label> <imagelabel>+0:+0</imagelabel> </seclabel> </domain> lscpu Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Byte Order: Little Endian CPU(s): 8 On-line CPU(s) list: 0-2,4-7 Off-line CPU(s) list: 3 Thread(s) per core: 1 Core(s) per socket: 7 Socket(s): 1 .......... .......... NUMA node0 CPU(s): 0-2,4-7 NUMA node1 CPU(s): cat /sys/devices/system/cpu/online 0-2,4-7 Before Patch virsh vcpupin Fedora VCPU: CPU Affinity ---------------------------------- 0: 0-7 1: 0-7 ... ... 158: 0-7 159: 0-7 virsh emulatorpin Fedora emulator: CPU Affinity ---------------------------------- *: 0-7 After Patch virsh vcpupin Fedora VCPU: CPU Affinity ---------------------------------- 0: 0-2,4-7 1: 0-2,4-7 ... ... 158: 0-2,4-7 159: 0-2,4-7 virsh emulatorpin Fedora emulator: CPU Affinity ---------------------------------- *: 0-2,4-7 Nitesh Konkar (2): conf: List only online cpus for virsh vcpupin conf: List only online cpus for virsh emulatorpin src/conf/domain_conf.c | 6 ++++++ src/qemu/qemu_driver.c | 5 +++++ 2 files changed, 11 insertions(+) -- 2.1.0

3 7

[libvirt] [RFC PATCH] cgroup: Use system reported "unlimited" value for comparison
by Viktor Mihajlovski 06 Dec '16

06 Dec '16

With kernel 3.18 (since commit 3e32cb2e0a12b6915056ff04601cf1bb9b44f967) the "unlimited" value for cgroup memory limits has changed once again as its byte value is now computed from a page counter. The new "unlimited" value reported by the cgroup fs is therefore 2**51-1 pages which is (VIR_DOMAIN_MEMORY_PARAM_UNLIMITED - 3072). This results e.g. in virsh memtune displaying 9007199254740988 instead of unlimited for the limits. This patch uses the value of memory.limit_in_bytes from the cgroup memory root which is the system's "real" unlimited value for comparison. See also libvirt commit 231656bbeb9e4d3bedc44362784c35eee21cf0f4 for the history for kernel 3.12 and before. I've tested this on F24 with the following configurations: - no memory cgroup controller mounted - memory cgroup controller mounted but not configured for libvirt - memory cgroup controller mounted and configured The first two fail as expected (and as before), the third case works as expected. Testing on other kernel versions highly welcome! Not perfect yet in that we still provide a fallback to the old value. We might consider failing right away if we can't get the system value. I'd be inclined to do that, since we're probably facing principal cgroup issues in this case. Further, it's not the most efficient implementation. Obviously, the unlimited value can be read once and cached. However, I'd like to see the question above resolved first. Signed-off-by: Viktor Mihajlovski <mihajlov(a)linux.vnet.ibm.com> --- src/util/vircgroup.c | 61 ++++++++++++++++++++++++++++++++++++++++++++++------ 1 file changed, 55 insertions(+), 6 deletions(-) diff --git a/src/util/vircgroup.c b/src/util/vircgroup.c index f151193..969dca5 100644 --- a/src/util/vircgroup.c +++ b/src/util/vircgroup.c @@ -2452,6 +2452,40 @@ virCgroupGetBlkioDeviceWeight(virCgroupPtr group, } +/* + * Retrieve the "memory.limit_in_bytes" value from the memory controller + * root dir. This value cannot be modified by userspace and therefore + * is the maximum limit value supported by cgroups on the local system. + */ +static int +virCgroupGetMemoryUnlimited(unsigned long long int * mem_unlimited) +{ + int ret = -1; + virCgroupPtr group; + + if (VIR_ALLOC(group)) + goto cleanup; + + if (virCgroupDetectMounts(group)) + goto cleanup; + + if (!group->controllers[VIR_CGROUP_CONTROLLER_MEMORY].mountPoint) + goto cleanup; + + if (VIR_STRDUP(group->controllers[VIR_CGROUP_CONTROLLER_MEMORY].placement, + "/.") < 0) + goto cleanup; + + ret = virCgroupGetValueU64(group, + VIR_CGROUP_CONTROLLER_MEMORY, + "memory.limit_in_bytes", + mem_unlimited); + cleanup: + virCgroupFree(&group); + return ret; +} + + /** * virCgroupSetMemory: * @@ -2534,6 +2568,7 @@ int virCgroupGetMemoryHardLimit(virCgroupPtr group, unsigned long long *kb) { long long unsigned int limit_in_bytes; + long long unsigned int unlimited_in_bytes; int ret = -1; if (virCgroupGetValueU64(group, @@ -2541,9 +2576,13 @@ virCgroupGetMemoryHardLimit(virCgroupPtr group, unsigned long long *kb) "memory.limit_in_bytes", &limit_in_bytes) < 0) goto cleanup; - *kb = limit_in_bytes >> 10; - if (*kb > VIR_DOMAIN_MEMORY_PARAM_UNLIMITED) + if (virCgroupGetMemoryUnlimited(&unlimited_in_bytes) < 0) + unlimited_in_bytes = VIR_DOMAIN_MEMORY_PARAM_UNLIMITED << 10; + + if (limit_in_bytes == unlimited_in_bytes) *kb = VIR_DOMAIN_MEMORY_PARAM_UNLIMITED; + else + *kb = limit_in_bytes >> 10; ret = 0; cleanup: @@ -2596,6 +2635,7 @@ int virCgroupGetMemorySoftLimit(virCgroupPtr group, unsigned long long *kb) { long long unsigned int limit_in_bytes; + long long unsigned int unlimited_in_bytes; int ret = -1; if (virCgroupGetValueU64(group, @@ -2603,9 +2643,13 @@ virCgroupGetMemorySoftLimit(virCgroupPtr group, unsigned long long *kb) "memory.soft_limit_in_bytes", &limit_in_bytes) < 0) goto cleanup; - *kb = limit_in_bytes >> 10; - if (*kb > VIR_DOMAIN_MEMORY_PARAM_UNLIMITED) + if (virCgroupGetMemoryUnlimited(&unlimited_in_bytes) < 0) + unlimited_in_bytes = VIR_DOMAIN_MEMORY_PARAM_UNLIMITED << 10; + + if (limit_in_bytes == unlimited_in_bytes) *kb = VIR_DOMAIN_MEMORY_PARAM_UNLIMITED; + else + *kb = limit_in_bytes >> 10; ret = 0; cleanup: @@ -2658,6 +2702,7 @@ int virCgroupGetMemSwapHardLimit(virCgroupPtr group, unsigned long long *kb) { long long unsigned int limit_in_bytes; + long long unsigned int unlimited_in_bytes; int ret = -1; if (virCgroupGetValueU64(group, @@ -2665,9 +2710,13 @@ virCgroupGetMemSwapHardLimit(virCgroupPtr group, unsigned long long *kb) "memory.memsw.limit_in_bytes", &limit_in_bytes) < 0) goto cleanup; - *kb = limit_in_bytes >> 10; - if (*kb > VIR_DOMAIN_MEMORY_PARAM_UNLIMITED) + if (virCgroupGetMemoryUnlimited(&unlimited_in_bytes) < 0) + unlimited_in_bytes = VIR_DOMAIN_MEMORY_PARAM_UNLIMITED << 10; + + if (limit_in_bytes == unlimited_in_bytes) *kb = VIR_DOMAIN_MEMORY_PARAM_UNLIMITED; + else + *kb = limit_in_bytes >> 10; ret = 0; cleanup: -- 1.9.1

2 3

[libvirt] [PATCH] Add support for parsing -vga virtio
by Nehal J Wani 06 Dec '16

06 Dec '16

Since a94f0c5c qemu supports '-vga virtio'. Libvirt also supports it since 21373feb. This patch enables libvirt to parse the qemu-argv: virsh domxml-from-native qemu-argv <(echo '/usr/bin/qemu-system-x86_64 -vga virtio') Signed-off-by: Nehal J Wani <nehaljw.kkd1(a)gmail.com> --- src/qemu/qemu_command.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/qemu/qemu_command.c b/src/qemu/qemu_command.c index 4a5fce3..d92bf9d 100644 --- a/src/qemu/qemu_command.c +++ b/src/qemu/qemu_command.c @@ -100,7 +100,7 @@ VIR_ENUM_IMPL(qemuVideo, VIR_DOMAIN_VIDEO_TYPE_LAST, "", /* don't support vbox */ "qxl", "", /* don't support parallels */ - "" /* no need for virtio */); + "virtio"); VIR_ENUM_DECL(qemuDeviceVideo) -- 2.7.4

2 2

[libvirt] [REPOST PATCH v2 0/9] Add group_name support for <iotune>
by John Ferlan 05 Dec '16

05 Dec '16

This is just a REPOST of the v2 series: http://www.redhat.com/archives/libvir-list/2016-November/msg00363.html The only difference being updating to the current top of tree of commit id '0b4c3bd30'. I did *not* add the NEWS change yet as that's newer than this, but will update NEWS with this once/if this is ACK'd using whatever format becomes agreed upon for the file contents/formatting options. John Ferlan (9): include: Add new "group_name" definition for iotune throttling caps: Add new capability for the iotune group name qemu: Adjust maxparams logic for qemuDomainGetBlockIoTune qemu: Alter qemuMonitorJSONSetBlockIoThrottle command logic qemu: Adjust various bool BlockIoTune set_ values into mask qemu: Add support for parsing iotune group setting conf: Add support for blkiotune group_name option qemu: Add the group name option to the iotune command line virsh: Add group name to blkdeviotune output docs/formatdomain.html.in | 11 ++ docs/schemas/domaincommon.rng | 5 + include/libvirt/libvirt-domain.h | 15 ++ src/conf/domain_conf.c | 10 ++ src/conf/domain_conf.h | 1 + src/qemu/qemu_capabilities.c | 2 + src/qemu/qemu_capabilities.h | 1 + src/qemu/qemu_command.c | 13 ++ src/qemu/qemu_driver.c | 177 +++++++++++++-------- src/qemu/qemu_monitor.c | 2 + src/qemu/qemu_monitor.h | 1 + src/qemu/qemu_monitor_json.c | 97 ++++++----- src/qemu/qemu_monitor_json.h | 1 + tests/qemucapabilitiesdata/caps_2.4.0.x86_64.xml | 1 + tests/qemucapabilitiesdata/caps_2.5.0.x86_64.xml | 1 + .../caps_2.6.0-gicv2.aarch64.xml | 1 + .../caps_2.6.0-gicv3.aarch64.xml | 1 + tests/qemucapabilitiesdata/caps_2.6.0.ppc64le.xml | 1 + tests/qemucapabilitiesdata/caps_2.6.0.x86_64.xml | 1 + tests/qemucapabilitiesdata/caps_2.7.0.x86_64.xml | 1 + tests/qemumonitorjsontest.c | 88 +++++++--- .../qemuxml2argv-blkdeviotune-group-num.args | 32 ++++ .../qemuxml2argv-blkdeviotune-group-num.xml | 61 +++++++ tests/qemuxml2argvtest.c | 4 + .../qemuxml2xmlout-blkdeviotune-group-num.xml | 1 + tests/qemuxml2xmltest.c | 1 + tools/virsh-domain.c | 17 ++ tools/virsh.pod | 5 +- 28 files changed, 428 insertions(+), 124 deletions(-) create mode 100644 tests/qemuxml2argvdata/qemuxml2argv-blkdeviotune-group-num.args create mode 100644 tests/qemuxml2argvdata/qemuxml2argv-blkdeviotune-group-num.xml create mode 120000 tests/qemuxml2xmloutdata/qemuxml2xmlout-blkdeviotune-group-num.xml -- 2.7.4

2 26

[libvirt] [PATCH] cpu: Add support for pku and ospke Intel features for Memory Protection Keys
by Lin Ma 05 Dec '16

05 Dec '16

qemu commit: f74eefe0 https://lwn.net/Articles/667156/ Signed-off-by: Lin Ma <lma(a)suse.com> --- src/cpu/cpu_map.xml | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/src/cpu/cpu_map.xml b/src/cpu/cpu_map.xml index 6da8321..dca5720 100644 --- a/src/cpu/cpu_map.xml +++ b/src/cpu/cpu_map.xml @@ -255,6 +255,13 @@ <cpuid eax_in='0x07' ebx='0x10000000'/> </feature> + <feature name='pku'> + <cpuid eax_in='0x07' ecx='0x00000008'/> + </feature> + <feature name='ospke'> + <cpuid eax_in='0x07' ecx='0x00000010'/> + </feature> +  <feature name='xsaveopt'> <cpuid eax_in='0x0d' ecx_in='0x01' eax='0x00000001'/> -- 2.9.2

2 1