[libvirt] [RFC PATCH v1 1/4] XML definitions for guest vNUMA and parsing routines

From: Wim ten Have <wim.ten.have(a)oracle.com&gt; This patch adds XML definitions to a guest with a vNUMA layout and contains routines to parse the same. The guest vNUMA specification looks like: <vnuma mode='host|node' distribution='contiguous|siblings|round-robin|interleave'> <memory unit='#unitsize'>size</memory> <partition nodeset='#nodes' cells='#cells'/> </vnuma> With mode='host' the guest XML is rendered to match the host's NUMA topology. With mode='node' the guest XML is rendered according to the "nodes" and "cells" attributes of the <partition> element. Signed-off-by: Wim ten Have <wim.ten.have(a)oracle.com&gt; --- docs/formatdomain.html.in | 94 +++++++ docs/schemas/domaincommon.rng | 65 +++++ src/conf/domain_conf.c | 482 +++++++++++++++++++++++++++++++++- src/conf/domain_conf.h | 2 + src/conf/numa_conf.c | 241 ++++++++++++++++- src/conf/numa_conf.h | 58 +++- src/libvirt_private.syms | 8 + 7 files changed, 932 insertions(+), 18 deletions(-) diff --git a/docs/formatdomain.html.in b/docs/formatdomain.html.in index 962766b792d3..80165f9bd896 100644 --- a/docs/formatdomain.html.in +++ b/docs/formatdomain.html.in @@ -1294,6 +1294,98 @@ </dl> + <h3><a id="elementsvNUMAPartitioning">NUMA Host or Node Partitioning</a></h3> + + <p> + With the help of the <code>vnuma</code> element, libvirt can + dynamically partition a guest domain for vNUMA by rendering its XML + into a 'host' or 'node' <a href="#elementsNUMAtopology"><code>NUMA + topology</code></a> matching model. + </p> + +<pre> +&lt;domain&gt; + ... + &lt;vnuma mode='host|node' distribution='contiguous|siblings|round-robin|interleave'&gt; + &lt;memory unit='KiB'&gt;524288&lt;/memory&gt; + &lt;partition nodeset="1-4,^3" cells="8"/&gt; + &lt;/vnuma&gt; + ... +&lt;/domain&gt; +</pre> + + <dl> + <dt><code>vnuma</code></dt> + <dd> + The attribute <code>mode</code> selects a specific rendering + method. Its value is either "host" or "node." If <code>mode</code> + is set to "host" the guest domain is automatically partitioned + to match the host NUMA topology. If <code>mode</code> + is "node," the guest domain is partitioned according to the + <code>nodeset</code> and <code>cells</code> under the + <code>vnuma</code> <code>partition</code> subelement. + <span class="since">Since 5.9</span> + + The optional attribute <code>distribution</code> selects the + guest <a href="#elementsNUMAtopology"><code>numa</code></a> + <code>cell</code> <code>cpus</code> distribution. It allows + <span class="since">Since 5.9</span> for: + <dl> + <dt><code>contiguous</code></dt> + <dd> The cpus are enumerate sequentially over the + <a href="#elementsNUMAtopology"><code>numa</code></a> defined + cells. + </dd> + <dt><code>siblings</code></dt> + <dd> The cpus are distributed over the + <a href="#elementsNUMAtopology"><code>numa</code></a> + cells matching the host CPU SMT model. + </dd> + <dt><code>round-robin</code></dt> + <dd> The cpus are distributed over the + <a href="#elementsNUMAtopology"><code>numa</code></a> + cells matching the host CPU topology. + </dd> + <dt><code>interleave</code></dt> + <dd> The cpus are interleaved one at a time over the + <a href="#elementsNUMAtopology"><code>numa</code></a> cells. + </dd> + </dl> + </dd> + + <dt><code>memory</code></dt> + <dd> + The optional subelement <code>memory</code> specifies the + memory size reserved for the guest assigned + <a href="#elementsNUMAtopology"><code>numa</code></a> cells. + <span class="since">Since 1.2.11</span>, one can use an additional + <a href="#elementsMemoryAllocation"><code>unit</code></a> + attribute to define units in which this <code>memory</code> + size is quantified. If no <code>memory</code> is specified, the + <a href="#elementsMemoryAllocation">memory</a> setting is + acquired to set this subelement documented + <a href="#elementsvNUMAPartitioning"><code>vnuma</code></a> value. + <span class="since">Since 5.9</span> + </dd> + + <dt><code>partition</code></dt> + <dd> + The optional attribute <code>partition</code> is only active when + <a href="#elementsvNUMAPartitioning"><code>vnuma</code></a> + <code>mode</code> "node" is selected and allows for defining the + active "nodeset" and "cells" to target for under the "guest" domain. + For example; the specified <code>nodeset</code> can limit the + <a href="#elementsNUMATuning"><code>numatune</code></a> assigned + host NUMA nodes in effect under the "guest". Alternatively, + the provided <code>cells</code> attribute can define the number + of <a href="#elementsNUMAtopology"><code>numa</code></a> cells + to render. + + <span class="since">Since 5.9</span> + </dd> + </dl> + + <h3><a id="elementsNUMATuning">NUMA Node Tuning</a></h3> <pre> @@ -1755,6 +1847,8 @@ </dd> </dl> + <h3><a id="elementsNUMAtopology">NUMA topology</a></h3> + <p> Guest NUMA topology can be specified using the <code>numa</code> element. <span class="since">Since 0.9.8</span> diff --git a/docs/schemas/domaincommon.rng b/docs/schemas/domaincommon.rng index e06f892da393..227c856a362c 100644 --- a/docs/schemas/domaincommon.rng +++ b/docs/schemas/domaincommon.rng @@ -786,6 +786,10 @@ <ref name="cputune"/> </optional> + <optional> + <ref name="vnuma"/> + </optional> + <optional> <ref name="numatune"/> </optional> @@ -1062,6 +1066,67 @@ </choice> </define> + <!-- All the "host vnuma" related tunables would go in the vnuma --> + <define name="vnuma"> + <element name="vnuma"> + <optional> + <ref name="vnumaMode"/> + </optional> + <optional> + <ref name="vnumaDistribution"/> + </optional> + <interleave> + <optional> + <element name="memory"> + <ref name="scaledInteger"/> + </element> + </optional> + <optional> + <element name="partition"> + <optional> + <ref name="vnumaNodeset"/> + </optional> + <optional> + <ref name="vnumaCells"/> + </optional> + </element> + </optional> + </interleave> + </element> + </define> + + <define name="vnumaMode"> + <attribute name="mode"> + <choice> + <value>host</value> + <value>node</value> + </choice> + </attribute> + </define> + + <define name="vnumaDistribution"> + <attribute name="distribution"> + <choice> + <value>contiguous</value> + <value>siblings</value> + <value>round-robin</value> + <value>interleave</value> + </choice> + </attribute> + </define> + + <define name="vnumaNodeset"> + <attribute name='nodeset'> + <ref name='cpuset'/> + </attribute> + </define> + + <define name="vnumaCells"> + <attribute name='cells'> + <ref name="positiveInteger"/> + </attribute> + </define> + <!-- All the NUMA related tunables would go in the numatune --> <define name="numatune"> <element name="numatune"> diff --git a/src/conf/domain_conf.c b/src/conf/domain_conf.c index 317e7846ceb0..32b29740bffd 100644 --- a/src/conf/domain_conf.c +++ b/src/conf/domain_conf.c @@ -1824,6 +1824,18 @@ virDomainDefSetVcpusMax(virDomainDefPtr def, if (def->maxvcpus == maxvcpus) return 0; + if (virDomainVnumaIsEnabled(def->numa)) { + size_t nnumaCell = virDomainNumaGetNodeCount(def->numa); + + if (maxvcpus % nnumaCell) { + virReportError(VIR_ERR_CONFIG_UNSUPPORTED, + _("vNUMA: the maximum vCPU count %d is not a " + "multiple of the configured vNUMA node count %ld"), + maxvcpus, nnumaCell); + return -1; + } + } + if (def->maxvcpus < maxvcpus) { if (VIR_EXPAND_N(def->vcpus, def->maxvcpus, maxvcpus - def->maxvcpus) < 0) return -1; @@ -2067,6 +2079,394 @@ virDomainDefGetVcpusTopology(const virDomainDef *def, } +void +virDomainDefSetVcpusVnuma(virDomainDefPtr def, + size_t nvcpus) +{ + int vcpuscnt = nvcpus; + size_t cell, i; + size_t vcpu_node; + size_t nnumaCell = virDomainNumaGetNodeCount(def->numa); + + if (!nnumaCell) + return; + + /* vcpu_node represents the maximum vcpus per vNUMA + * node that theoretically could be within a set. + */ + vcpu_node = (def->maxvcpus / nnumaCell) + ((def->maxvcpus % nnumaCell) ? 1 : 0); + + for (i = 0; i < vcpu_node; i++) { + for (cell = 0; cell < nnumaCell; cell++) { + virDomainVcpuDefPtr vcpu; + size_t cid = cell * vcpu_node + i; + + if (cid >= def->maxvcpus) + break; + + vcpu = def->vcpus[cid]; + + if (vcpuscnt-- > 0) + vcpu->online = true; + else + vcpu->online = false; + + /* vCPU0 cannot be hotplugged */ + if (cid) + vcpu->hotpluggable = true; + } + } + def->individualvcpus = true; + + return; +} + + +/** + * virDomainNumaAutoconfig: vNUMA automatic host partition processing + * @def: domain definition + * @caps: host capabilities + * + * vNUMA automatic host partitioning is requested by adding the <vnuma + * mode=...> element to the guest XML. See virDomainVnumaParseXML() for + * parsing the related XML and filling the virDomainAutoPartition structure. + * + * If the virDomainAutoPartition structure is valid, libvirt takes into + * account the host hardware configuration (including maxvcpus, online + * vcpus, and memory) and creates the guest such that vcpus and memory + * are spread evenly across the host. + * + * Returns 0 on success and -1 on error. + */ +static int +virDomainNumaAutoconfig(virDomainDefPtr def, + virCapsPtr caps) +{ + int ret = -1; + virBitmapPtr nodeset = NULL; + virDomainNumaPtr numa = def->numa; + virDomainAutoPartitionPtr avnuma; + + if (!numa) + goto error; + + if (caps && + (avnuma = virDomainVnumaParseXML(numa, NULL))) { + + size_t i, j, cell; + size_t nvcpus = 0; + size_t nnumaCell = 0; + size_t vcpu_node; + unsigned long long memsizeCell = 0; + virCapsHostPtr host = &caps->host; + unsigned int threads = host->cpu->threads; + + if (!def->cpu) { + virReportError(VIR_ERR_CONFIG_UNSUPPORTED, + _("vNUMA: unable to render <vnuma> partitioning for " + "domain %s because of undefined <cpu ... /> topology."), + def->name); + goto error; + } + + if (!avnuma->nodeset) { + if (!(avnuma->nodeset = virBitmapNew(host->nnumaCell))) + goto cleanup; + + for (i = 0; i < host->nnumaCell; i++) + if (virBitmapSetBit(avnuma->nodeset, i) < 0) + goto cleanup; + } + + /* Set the vNUMA cell count */ + nnumaCell = avnuma->vcell ? avnuma->vcell : virBitmapCountBits(avnuma->nodeset); + + if (!nnumaCell) + goto cleanup; + + /* Compute the online vcpus */ + for (i = 0; i < def->maxvcpus; i++) + if (def->vcpus[i]->online) + nvcpus++; + + /* vcpu_node represents the maximum vcpus per numanode that + * theoretically could be within a set. + */ + vcpu_node = (def->maxvcpus / nnumaCell) + ((def->maxvcpus % nnumaCell) ? 1 : 0); + + /* Do the host provided "CPU topology" threads fit */ + threads = (nnumaCell % threads) ? 1 : threads; + + /* Is it possible to render the guest for vNUMA auto partition? */ + if ((def->maxvcpus % nnumaCell) || + (def->maxvcpus < (nnumaCell * threads))) { + virReportError(VIR_ERR_CONFIG_UNSUPPORTED, + _("vNUMA: %ld vcpus is insufficient to " + "arrange a vNUMA topology for %ld nodes."), + def->maxvcpus, nnumaCell); + goto error; + } + + /* Compute the memory size (memsizeCell) per arranged nnumaCell. + * If no memory for vNUMA auto partitioning was specified then + * compute its value from the total_memory configuration. + */ + if ((memsizeCell = avnuma->mem / nnumaCell) == 0) { + unsigned long long hotplugMemory = 0; + + /* Calculate the size of hotplug memory */ + for (i = 0; i < def->nmems; i++) + hotplugMemory += def->mems[i]->size; + + memsizeCell = (def->mem.total_memory - hotplugMemory) / nnumaCell; + } + + /* Under vNUMA automatic host partitioning the 'memballoon' controlled + * cur_balloon value should reflect the guest's total_memory setting. + */ + def->mem.cur_balloon = def->mem.total_memory; + + /* Correct vNUMA can only be accomplished if the number of maxvcpus + * is a multiple of the number of physical nodes. If this is not + * possible we set sockets, cores and threads to 0 so libvirt creates + * a default topology where all vcpus appear as sockets and cores and + * threads are set to 1. + */ + if (def->maxvcpus % (nnumaCell * threads)) { + VIR_WARN("Disabling guest %s auto vNUMA topology because configured " + "%ld vCPUs do not match the host's %ld NUMA nodes to produce " + "an evenly balanced CPU topology.", + def->name, def->maxvcpus, nnumaCell); + def->cpu->sockets = def->cpu->cores = def->cpu->threads = 0; + } else { + /* Below computed topology aims to align the guest's sockets, + * cores and threads with the host's topology. + */ + def->cpu->cores = def->maxvcpus / (nnumaCell * threads); + def->cpu->threads = threads; + def->cpu->sockets = nnumaCell; + } + + /* Build the vNUMA topology. The previous configuration may + * have changed entirely, so free the current NUMA allocation + * and start over from scratch. + */ + virDomainNumaFree(numa); + if (!(numa = virDomainNumaNew())) + goto error; + + /* We're clean and good to rebuild the entire guest domain + * respecting the requested vNUMA topoplogy provided by <vnuma> + * avnuma stored objects. + */ + avnuma->mem = memsizeCell * nnumaCell; + + if (!virDomainNumaSetNodeCount(numa, nnumaCell)) + goto error; + + if (!(nodeset = virBitmapNewCopy(avnuma->nodeset))) + goto error; + + for (cell = 0; cell < nnumaCell; cell++) { + size_t ndistances; + size_t vcell = cell % host->nnumaCell; + size_t vcpu_strt, vcpu_last, vcpu_left; + ssize_t node = 0; + unsigned int cores = def->cpu->cores; + virBitmapPtr cpumask = NULL; + virBitmapPtr vnumask = NULL; + virCapsHostNUMACell *numaCell = NULL; + + /* per NUMA cell memory size */ + virDomainNumaSetNodeMemorySize(numa, cell, memsizeCell); + + /* per NUMA cell bind memory (mode='strict') */ + if ((node = virBitmapNextSetBit(nodeset, (vcell-1))) < 0) + node = vcell - 1; + + if (node >= host->nnumaCell) { + virReportError(VIR_ERR_CONFIG_UNSUPPORTED, + _("vNUMA: domain %s defined nodeset node %ld " + "is out of range. Valid range is 0-%ld"), + def->name, node, (host->nnumaCell-1)); + goto error; + } + + if (virDomainNumatuneSetmemset(numa, cell, node, + VIR_DOMAIN_NUMATUNE_MEM_STRICT) < 0) + goto error; + + /* per NUMA cell vcpu range to mask */ + if (!(cpumask = virBitmapNew(def->maxvcpus))) + goto error; + + switch (avnuma->distribution) { + case VIR_DOMAIN_VNUMA_DISTRIBUTION_CONTIGUOUS: + /* vcpus are equally balanced from 0 to highest vcpu id + * available, keeping ranges contiguous where the maximum vcpu + * sets run from lowest vNUMA cells to highest available. + */ + vcpu_strt = cell * vcpu_node; + vcpu_last = MIN(vcpu_strt + vcpu_node, def->maxvcpus); + + for (i = vcpu_strt; i < vcpu_last; i++) { + if (virBitmapSetBitExpand(cpumask, i) < 0) { + virBitmapFree(cpumask); + goto error; + } + } + break; + + case VIR_DOMAIN_VNUMA_DISTRIBUTION_SIBLINGS: + /* Create vNUMA node vcpu ranges that represent a clean + * processor sockets/core/threads model, placing one + * socket per NUMA node. + */ + vcpu_strt = cell * cores; + vcpu_last = def->maxvcpus; + vcpu_left = def->maxvcpus / threads; + + for (i = vcpu_strt; i < vcpu_last; i += vcpu_left) { + for (j = 0; j < cores; j++) { + unsigned int id = i + j; + + if (id < def->maxvcpus && + virBitmapSetBitExpand(cpumask, id) < 0) { + virBitmapFree(cpumask); + goto error; + } + } + } + break; + + case VIR_DOMAIN_VNUMA_DISTRIBUTION_ROUNDROBIN: + /* Create vNUMA node vcpu ranges that round-robin + * interleave one core per node over the available nodes. + */ + vcpu_strt = cell * threads; + vcpu_last = def->maxvcpus; + vcpu_left = threads * nnumaCell; + + for (i = vcpu_strt; i < vcpu_last; i += vcpu_left) { + for (j = 0; j < threads; j++) { + unsigned int id = i + j; + + if (id < def->maxvcpus && + virBitmapSetBitExpand(cpumask, id) < 0) { + virBitmapFree(cpumask); + goto error; + } + } + } + break; + + case VIR_DOMAIN_VNUMA_DISTRIBUTION_INTERLEAVE: + /* Distribute vCPUs over the NUMA nodes in a round-robin, + * interleaved fashion, with one vCPU (thread) per node. + */ + def->cpu->sockets = def->cpu->cores = def->cpu->threads = 0; + for (i = cell; i < def->maxvcpus; i += nnumaCell) { + if (virBitmapSetBitExpand(cpumask, i) < 0) { + virBitmapFree(cpumask); + goto error; + } + } + break; + + default: + virReportError(VIR_ERR_CONFIG_UNSUPPORTED, "%s", + _("vNUMA: domain %s non-existent vCPU distribution requested.")); + goto error; + break; + } + + if (virDomainNumaSetNodeCpumask(numa, cell, cpumask) == NULL) + goto error; + + /* per NUMA cpus sibling vNUMA pinning */ + numaCell = host->numaCell[node]; + if (!(vnumask = virBitmapNew(nnumaCell * numaCell->ncpus))) + goto error; + + for (i = 0; i < numaCell->ncpus; i++) { + unsigned int id = numaCell->cpus[i].id; + + if (virBitmapSetBitExpand(vnumask, id) < 0) { + virBitmapFree(vnumask); + goto error; + } + } + + for (i = 0; i < def->maxvcpus; i++) { + if (virBitmapIsBitSet(cpumask, i)) { + if (!(def->vcpus[i]->cpumask = virBitmapNewCopy(vnumask))) + goto error; + } + } + virBitmapFree(vnumask); + + /* per NUMA cell sibling distances */ + numaCell = host->numaCell[node]; + switch (avnuma->mode) { + case VIR_DOMAIN_VNUMA_MODE_HOST: + ndistances = numaCell->nsiblings; + break; + + case VIR_DOMAIN_VNUMA_MODE_NODE: + ndistances = 1; + if (avnuma->vcell) + vcell = cell; + else + if (virBitmapClearBit(nodeset, node) < 0) + goto error; + + break; + + default: + goto error; + } + + /* Set vNUMA distances */ + if (ndistances > 1) { + if (virDomainNumaSetNodeDistanceCount(numa, + vcell, + ndistances) < 0) { + virReportError(VIR_ERR_INTERNAL_ERROR, + _("vNUMA: domain %s failed to render a " + "matching vNUMA node distances set, defined " + "vNUMA nodes %ld build on %ld host nodes."), + def->name, nnumaCell, ndistances); + goto error; + } + + for (i = 0; i < ndistances; i++) { + unsigned int distance = numaCell->siblings[i].distance; + + if (virDomainNumaSetNodeDistance(numa, cell, i, distance) != distance) + goto error; + } + } + } + + /* We're done - enable the vNUMA marker */ + virDomainVnumaSetEnabled(numa, avnuma); + + /* Adjust the new created vNUMA description */ + def->numa = numa; + + /* per NUMA cpus sibling vNUMA hotplugging directives */ + virDomainDefSetVcpusVnuma(def, virDomainDefGetVcpus(def)); + } + cleanup: + + ret = 0; + + error: + virBitmapFree(nodeset); + return ret; +} + + virDomainDiskDefPtr virDomainDiskDefNew(virDomainXMLOptionPtr xmlopt) { @@ -10510,6 +10910,38 @@ virDomainDefSetMemoryTotal(virDomainDefPtr def, } +/** + * virDomainDefSetNUMAMemoryTotal: + * @def: domain definition + * @size: size to set + * @caps: host capabilities + * + * A frontend to set the total memory size in @def. If the guest's + * configured "total_memory" setting and the requested "size" differ, + * call virDomainNumaAutoconfig() to evenly distribute the additional + * memory across all vNUMA nodes. + */ +int +virDomainDefSetNUMAMemoryTotal(virDomainDefPtr def, + unsigned long long size, + virCapsPtr caps) +{ + bool DoNumaAutoConfig = (def->mem.total_memory != size); + + if (DoNumaAutoConfig) { + if (virDomainVnumaSetMemory(def->numa, size) < 0) + return -1; + + if (virDomainNumaAutoconfig(def, caps)) + return -1; + + if (virDomainDefPostParseMemory(def, VIR_DOMAIN_DEF_PARSE_ABI_UPDATE) < 0) + return -1; + } + return 0; +} + + /** * virDomainDefGetMemoryTotal: * @def: domain definition @@ -18809,7 +19241,8 @@ virDomainIOThreadSchedParse(xmlNodePtr node, static int virDomainVcpuParse(virDomainDefPtr def, xmlXPathContextPtr ctxt, - virDomainXMLOptionPtr xmlopt) + virDomainXMLOptionPtr xmlopt, + bool IsAvNUMA) { int n; xmlNodePtr vcpuNode; @@ -18876,6 +19309,15 @@ virDomainVcpuParse(virDomainDefPtr def, if (virDomainDefSetVcpusMax(def, maxvcpus, xmlopt) < 0) return -1; + /* If vNUMA applies def->numa is reinitialized later */ + if (IsAvNUMA) { + + if (virDomainDefSetVcpus(def, vcpus) < 0) + return -1; + + return 0; + } + if ((n = virXPathNodeSet("./vcpus/vcpu", ctxt, &nodes)) < 0) return -1; @@ -19746,6 +20188,7 @@ virDomainDefParseXML(xmlDocPtr xml, char *netprefix = NULL; g_autofree xmlNodePtr *nodes = NULL; g_autofree char *tmp = NULL; + bool IsAvNUMA; if (flags & VIR_DOMAIN_DEF_PARSE_VALIDATE_SCHEMA) { g_autofree char *schema = NULL; @@ -19871,6 +20314,8 @@ virDomainDefParseXML(xmlDocPtr xml, } VIR_FREE(tmp); + IsAvNUMA = virDomainVnumaParseXML(def->numa, ctxt) ? true : false; + tmp = virXPathString("string(./memoryBacking/source/@type)", ctxt); if (tmp) { if ((def->mem.source = virDomainMemorySourceTypeFromString(tmp)) <= 0) { @@ -19986,7 +20431,7 @@ virDomainDefParseXML(xmlDocPtr xml, &def->mem.swap_hard_limit) < 0) goto error; - if (virDomainVcpuParse(def, ctxt, xmlopt) < 0) + if (virDomainVcpuParse(def, ctxt, xmlopt, IsAvNUMA) < 0) goto error; if (virDomainDefParseIOThreads(def, ctxt) < 0) @@ -20059,14 +20504,16 @@ virDomainDefParseXML(xmlDocPtr xml, goto error; } - if ((n = virXPathNodeSet("./cputune/vcpupin", ctxt, &nodes)) < 0) - goto error; - - for (i = 0; i < n; i++) { - if (virDomainVcpuPinDefParseXML(def, nodes[i])) + if (!IsAvNUMA) { + if ((n = virXPathNodeSet("./cputune/vcpupin", ctxt, &nodes)) < 0) goto error; + + for (i = 0; i < n; i++) { + if (virDomainVcpuPinDefParseXML(def, nodes[i])) + goto error; + } + VIR_FREE(nodes); } - VIR_FREE(nodes); if ((n = virXPathNodeSet("./cputune/emulatorpin", ctxt, &nodes)) < 0) { virReportError(VIR_ERR_INTERNAL_ERROR, "%s", @@ -20173,6 +20620,10 @@ virDomainDefParseXML(xmlDocPtr xml, if (virDomainNumaDefCPUParseXML(def->numa, ctxt) < 0) goto error; + /* Check and update the guest's XML vNUMA topology if needed */ + if (virDomainNumaAutoconfig(def, caps)) + goto error; + if (virDomainNumaGetCPUCountTotal(def->numa) > virDomainDefGetVcpusMax(def)) { virReportError(VIR_ERR_INTERNAL_ERROR, "%s", _("Number of CPUs in <numa> exceeds the" @@ -20186,10 +20637,11 @@ virDomainDefParseXML(xmlDocPtr xml, goto error; } - if (virDomainNumatuneParseXML(def->numa, - def->placement_mode == - VIR_DOMAIN_CPU_PLACEMENT_MODE_STATIC, - ctxt) < 0) + if (!virDomainVnumaIsEnabled(def->numa) && + (virDomainNumatuneParseXML(def->numa, + def->placement_mode == + VIR_DOMAIN_CPU_PLACEMENT_MODE_STATIC, + ctxt) < 0)) goto error; if (virDomainNumatuneHasPlacementAuto(def->numa) && @@ -28496,6 +28948,9 @@ virDomainDefFormatInternalSetRootName(virDomainDefPtr def, if (virDomainMemtuneFormat(buf, &def->mem) < 0) goto error; + if (virDomainVnumaFormatXML(buf, def->numa) < 0) + goto error; + if (virDomainCpuDefFormat(buf, def) < 0) goto error; @@ -29148,6 +29603,9 @@ virDomainSaveConfig(const char *configDir, { g_autofree char *xml = NULL; + if (virDomainNumaAutoconfig(def, caps) < 0) + return -1; + if (!(xml = virDomainDefFormat(def, caps, VIR_DOMAIN_DEF_FORMAT_SECURE))) return -1; diff --git a/src/conf/domain_conf.h b/src/conf/domain_conf.h index 5a17acedf299..0db77d9247a1 100644 --- a/src/conf/domain_conf.h +++ b/src/conf/domain_conf.h @@ -2535,6 +2535,7 @@ struct _virDomainDef { unsigned long long virDomainDefGetMemoryInitial(const virDomainDef *def); void virDomainDefSetMemoryTotal(virDomainDefPtr def, unsigned long long size); +int virDomainDefSetNUMAMemoryTotal(virDomainDefPtr def, unsigned long long size, virCapsPtr caps); unsigned long long virDomainDefGetMemoryTotal(const virDomainDef *def); bool virDomainDefHasMemoryHotplug(const virDomainDef *def); @@ -2816,6 +2817,7 @@ int virDomainDefSetVcpusMax(virDomainDefPtr def, bool virDomainDefHasVcpusOffline(const virDomainDef *def); unsigned int virDomainDefGetVcpusMax(const virDomainDef *def); int virDomainDefSetVcpus(virDomainDefPtr def, unsigned int vcpus); +void virDomainDefSetVcpusVnuma(virDomainDefPtr def, size_t vcpus); unsigned int virDomainDefGetVcpus(const virDomainDef *def); virBitmapPtr virDomainDefGetOnlineVcpumap(const virDomainDef *def); virDomainVcpuDefPtr virDomainDefGetVcpu(virDomainDefPtr def, unsigned int vcpu) diff --git a/src/conf/numa_conf.c b/src/conf/numa_conf.c index 6720d5620d1d..8e6ef4008b8d 100644 --- a/src/conf/numa_conf.c +++ b/src/conf/numa_conf.c @@ -45,6 +45,20 @@ VIR_ENUM_IMPL(virDomainNumatuneMemMode, "interleave", ); +VIR_ENUM_IMPL(virDomainVnumaMode, + VIR_DOMAIN_VNUMA_MODE_LAST, + "host", + "node", +); + +VIR_ENUM_IMPL(virDomainVnumaDistribution, + VIR_DOMAIN_VNUMA_DISTRIBUTION_LAST, + "contiguous", + "siblings", + "round-robin", + "interleave", +); + VIR_ENUM_IMPL(virDomainNumatunePlacement, VIR_DOMAIN_NUMATUNE_PLACEMENT_LAST, "default", @@ -90,6 +104,7 @@ struct _virDomainNuma { size_t nmem_nodes; /* Future NUMA tuning related stuff should go here. */ + virDomainAutoPartitionPtr avnuma; }; @@ -353,6 +368,156 @@ virDomainNumatuneFormatXML(virBufferPtr buf, return 0; } +int +virDomainVnumaFormatXML(virBufferPtr buf, + virDomainNumaPtr numa) +{ + char *nodeset = NULL; + if (numa && virDomainVnumaIsEnabled(numa)) { + + virBufferAddLit(buf, "<vnuma"); + virBufferAsprintf(buf, " mode='%s'", + virDomainVnumaModeTypeToString(numa->avnuma->mode)); + virBufferAsprintf(buf, " distribution='%s'", + virDomainVnumaDistributionTypeToString(numa->avnuma->distribution)); + virBufferAddLit(buf, ">\n"); + + virBufferAdjustIndent(buf, 2); + virBufferAsprintf(buf, "<memory unit='KiB'>%llu</memory>\n", + numa->avnuma->mem); + + + if (numa->avnuma->mode == VIR_DOMAIN_VNUMA_MODE_NODE) { + if ((nodeset = virBitmapFormat(numa->avnuma->nodeset))) { + virBufferAsprintf(buf, "<partition nodeset='%s'", nodeset); + VIR_FREE(nodeset); + } + + if (numa->avnuma->vcell) + virBufferAsprintf(buf, " cells='%u'", numa->avnuma->vcell); + virBufferAddLit(buf, "/>\n"); + } + virBufferAdjustIndent(buf, -2); + + virBufferAddLit(buf, "</vnuma>\n"); + } + + return 0; +} + +virDomainAutoPartitionPtr +virDomainVnumaParseXML(virDomainNumaPtr numa, + xmlXPathContextPtr ctxt) +{ + int ret = -1; + char *tmp = NULL; + xmlNodePtr node, oldnode; + virDomainAutoPartitionPtr avnuma = NULL; + + if (!numa) + return NULL; + + if (!ctxt) + return avnuma = numa->avnuma; + + oldnode = ctxt->node; + node = virXPathNode("./vnuma[1]", ctxt); + if (node) { + int mode = -1; + int distribution = VIR_DOMAIN_VNUMA_DISTRIBUTION_CONTIGUOUS; + unsigned int maxvcell = 0; + unsigned long long mem = 0L; + virBitmapPtr nodeset = NULL; + + if (!virXMLNodeNameEqual(node, "vnuma")) { + virReportError(VIR_ERR_XML_ERROR, "%s", + _("domain definition does not contain expected 'vnuma' element")); + goto cleanup; + } + + if (VIR_ALLOC(avnuma) < 0) + goto cleanup; + + /* There has to be a valid vnuma mode setting */ + if (!(tmp = virXMLPropString(node, "mode"))) { + virReportError(VIR_ERR_CONFIG_UNSUPPORTED, "%s", + _("No vNUMA 'mode' specified for automatic host partitioning")); + goto cleanup; + } + + if ((mode = virDomainVnumaModeTypeFromString(tmp)) < 0) { + virReportError(VIR_ERR_CONFIG_UNSUPPORTED, + _("Unsupported automatic vNUMA partitioning mode '%s'"), tmp); + goto cleanup; + } + VIR_FREE(tmp); + + /* If specified get the vcpu 'distribution' type */ + if ((tmp = virXMLPropString(node, "distribution")) && + (distribution = virDomainVnumaDistributionTypeFromString(tmp)) < 0) { + virReportError(VIR_ERR_CONFIG_UNSUPPORTED, + _("Unsupported automatic vNUMA partitioning distribution '%s'"), tmp); + goto cleanup; + } + VIR_FREE(tmp); + + /* Obtain the designated <vnuma mode='node' attributes */ + ctxt->node = node; + switch (mode) { + case VIR_DOMAIN_VNUMA_MODE_NODE: + if ((node = virXPathNode("./partition[1]", ctxt))) { + + /* Get the host <partition> nodeset='#nodeset' for <numatune> */ + if ((tmp = virXMLPropString(node, "nodeset"))) { + if (virBitmapParse(tmp, &nodeset, VIR_DOMAIN_CPUMASK_LEN) < 0) + goto cleanup; + VIR_FREE(tmp); + } + + /* Get the fictitious <partition> cells='#count' attribute */ + if ((tmp = virXMLPropString(node, "cells"))) { + if (virStrToLong_ui(tmp, NULL, 10, &maxvcell) < 0) { + virReportError(VIR_ERR_XML_ERROR, "%s", + _("maximum vcpus count must be an integer")); + goto cleanup; + } + VIR_FREE(tmp); + } + } + break; + + case VIR_DOMAIN_VNUMA_MODE_HOST: + default: + break; + } + + /* Get the <memory> size to render the <numa> nodes with */ + if (virDomainParseMemory("./memory[1]", NULL, ctxt, + &mem, false, true) < 0) + goto cleanup; + + /* We're set and good to go */ + avnuma->mode = mode; + avnuma->distribution = distribution; + avnuma->nodeset = nodeset; + avnuma->mem = mem; + avnuma->vcell = maxvcell; + + numa->avnuma = avnuma; + } + ret = 0; + + cleanup: + if (ret) { + VIR_FREE(tmp); + VIR_FREE(avnuma); + avnuma = NULL; + } + ctxt->node = oldnode; + + return avnuma; +} + void virDomainNumaFree(virDomainNumaPtr numa) { @@ -572,6 +737,76 @@ virDomainNumatuneSet(virDomainNumaPtr numa, return ret; } +int +virDomainNumatuneSetmemset(virDomainNumaPtr numa, + size_t cell, + size_t node, + int mode) +{ + int ret = -1; + virDomainNumaNodePtr mem_node = &numa->mem_nodes[cell]; + + /* Get out if this is under control of numad! */ + if (numa->memory.specified) + goto cleanup; + + /* Get out if numa does not apply */ + if (cell > numa->nmem_nodes) + goto cleanup; + + /* Get out if mode is out of range */ + if (mode < 0 || mode >= VIR_DOMAIN_NUMATUNE_MEM_LAST) { + virReportError(VIR_ERR_CONFIG_UNSUPPORTED, + _("Unsupported numatune mode '%d'"), + mode); + goto cleanup; + } + + /* Force the numatune/memset setting */ + if (!(mem_node->nodeset = virBitmapNew(numa->nmem_nodes)) || + virBitmapSetBitExpand(mem_node->nodeset, node) < 0) { + virBitmapFree(mem_node->nodeset); + goto cleanup; + } + mem_node->mode = mode; + + ret = 0; + + cleanup: + return ret; +} + +bool +virDomainVnumaIsEnabled(virDomainNumaPtr numa) +{ + if (numa && numa->avnuma) + return numa->avnuma->specified; + + return false; +} + +void +virDomainVnumaSetEnabled(virDomainNumaPtr numa, + virDomainAutoPartitionPtr avnuma) +{ + if (numa && avnuma) { + numa->avnuma = avnuma; + numa->avnuma->specified = true; + } +} + +int +virDomainVnumaSetMemory(virDomainNumaPtr numa, + unsigned long long size) +{ + if (!numa) + return -1; + + numa->avnuma->mem = size; + + return 0; +} + static bool virDomainNumaNodesEqual(virDomainNumaPtr n1, virDomainNumaPtr n2) @@ -1273,7 +1508,7 @@ virDomainNumaSetNodeDistance(virDomainNumaPtr numa, } -size_t +int virDomainNumaSetNodeDistanceCount(virDomainNumaPtr numa, size_t node, size_t ndistances) @@ -1285,11 +1520,11 @@ virDomainNumaSetNodeDistanceCount(virDomainNumaPtr numa, virReportError(VIR_ERR_INTERNAL_ERROR, _("Cannot alter an existing nmem_nodes distances set for node: %zu"), node); - return 0; + return -1; } if (VIR_ALLOC_N(distances, ndistances) < 0) - return 0; + return -1; numa->mem_nodes[node].distances = distances; numa->mem_nodes[node].ndistances = ndistances; diff --git a/src/conf/numa_conf.h b/src/conf/numa_conf.h index e76a09c20cdc..bdc1deb6e143 100644 --- a/src/conf/numa_conf.h +++ b/src/conf/numa_conf.h @@ -32,6 +32,9 @@ typedef struct _virDomainNuma virDomainNuma; typedef virDomainNuma *virDomainNumaPtr; +typedef struct _virDomainAutoPartition virDomainAutoPartition; +typedef virDomainAutoPartition *virDomainAutoPartitionPtr; + typedef enum { VIR_DOMAIN_NUMATUNE_PLACEMENT_DEFAULT = 0, VIR_DOMAIN_NUMATUNE_PLACEMENT_STATIC, @@ -43,6 +46,24 @@ typedef enum { VIR_ENUM_DECL(virDomainNumatunePlacement); VIR_ENUM_DECL(virDomainNumatuneMemMode); +typedef enum { + VIR_DOMAIN_VNUMA_MODE_HOST = 0, + VIR_DOMAIN_VNUMA_MODE_NODE, + + VIR_DOMAIN_VNUMA_MODE_LAST +} virDomainVnumaMode; +VIR_ENUM_DECL(virDomainVnumaMode); + +typedef enum { + VIR_DOMAIN_VNUMA_DISTRIBUTION_CONTIGUOUS = 0, + VIR_DOMAIN_VNUMA_DISTRIBUTION_SIBLINGS, + VIR_DOMAIN_VNUMA_DISTRIBUTION_ROUNDROBIN, + VIR_DOMAIN_VNUMA_DISTRIBUTION_INTERLEAVE, + + VIR_DOMAIN_VNUMA_DISTRIBUTION_LAST +} virDomainVnumaDistribution; +VIR_ENUM_DECL(virDomainVnumaDistribution); + typedef enum { VIR_DOMAIN_MEMORY_ACCESS_DEFAULT = 0, /* No memory access defined */ VIR_DOMAIN_MEMORY_ACCESS_SHARED, /* Memory access is set as shared */ @@ -52,6 +73,14 @@ typedef enum { } virDomainMemoryAccess; VIR_ENUM_DECL(virDomainMemoryAccess); +struct _virDomainAutoPartition { + bool specified; /* Auto vNUMA active */ + int mode; /* Auto vNUMA mode */ + int distribution; /* Auto vNUMA distribution */ + unsigned long long mem; /* Auto vNUMA total memory */ + unsigned int vcell; /* Auto vNUMA node Cell */ + virBitmapPtr nodeset; /* Auto vNUMA host nodes where this guest node resides */ +}; virDomainNumaPtr virDomainNumaNew(void); void virDomainNumaFree(virDomainNumaPtr numa); @@ -67,9 +96,19 @@ int virDomainNumatuneParseXML(virDomainNumaPtr numa, int virDomainNumatuneFormatXML(virBufferPtr buf, virDomainNumaPtr numatune) ATTRIBUTE_NONNULL(1); +virDomainAutoPartitionPtr virDomainVnumaParseXML(virDomainNumaPtr numa, + xmlXPathContextPtr ctxt) + ATTRIBUTE_NONNULL(1); + +int virDomainVnumaFormatXML(virBufferPtr buf, virDomainNumaPtr numa) + ATTRIBUTE_NONNULL(1); + /* * Getters */ +bool virDomainVnumaIsEnabled(virDomainNumaPtr numa) + ATTRIBUTE_NONNULL(1); + int virDomainNumatuneGetMode(virDomainNumaPtr numatune, int cellid, virDomainNumatuneMemMode *mode); @@ -134,6 +173,19 @@ int virDomainNumatuneSet(virDomainNumaPtr numa, virBitmapPtr nodeset) ATTRIBUTE_NONNULL(1); +void virDomainVnumaSetEnabled(virDomainNumaPtr numa, + virDomainAutoPartitionPtr avnuma) + ATTRIBUTE_NONNULL(1) ATTRIBUTE_NONNULL(2); +int virDomainVnumaSetMemory(virDomainNumaPtr numa, + unsigned long long size) + ATTRIBUTE_NONNULL(1); + +int virDomainNumatuneSetmemset(virDomainNumaPtr numa, + size_t cell, + size_t node, + int mode) + ATTRIBUTE_NONNULL(1); + size_t virDomainNumaSetNodeCount(virDomainNumaPtr numa, size_t nmem_nodes) ATTRIBUTE_NONNULL(1); @@ -149,9 +201,9 @@ int virDomainNumaSetNodeDistance(virDomainNumaPtr numa, unsigned int value) ATTRIBUTE_NONNULL(1); -size_t virDomainNumaSetNodeDistanceCount(virDomainNumaPtr numa, - size_t node, - size_t ndistances) +int virDomainNumaSetNodeDistanceCount(virDomainNumaPtr numa, + size_t node, + size_t ndistances) ATTRIBUTE_NONNULL(1); virBitmapPtr virDomainNumaSetNodeCpumask(virDomainNumaPtr numa, diff --git a/src/libvirt_private.syms b/src/libvirt_private.syms index 17977229d18f..7f7c3fdeafaa 100644 --- a/src/libvirt_private.syms +++ b/src/libvirt_private.syms @@ -311,8 +311,10 @@ virDomainDefParseNode; virDomainDefParseString; virDomainDefPostParse; virDomainDefSetMemoryTotal; +virDomainDefSetNUMAMemoryTotal; virDomainDefSetVcpus; virDomainDefSetVcpusMax; +virDomainDefSetVcpusVnuma; virDomainDefValidate; virDomainDefVcpuOrderClear; virDomainDeleteConfig; @@ -828,7 +830,13 @@ virDomainNumatuneParseXML; virDomainNumatunePlacementTypeFromString; virDomainNumatunePlacementTypeToString; virDomainNumatuneSet; +virDomainNumatuneSetmemset; virDomainNumatuneSpecifiedMaxNode; +virDomainVnumaFormatXML; +virDomainVnumaIsEnabled; +virDomainVnumaParseXML; +virDomainVnumaSetEnabled; +virDomainVnumaSetMemory; # conf/nwfilter_conf.h -- 2.21.0