From 2ff472bc2ac9d01181c1dbd522153934de79907f Mon Sep 17 00:00:00 2001
Message-Id: <2ff472bc2ac9d01181c1dbd522153934de79907f@dist-git>
From: Wim ten Have <wim.ten.have@oracle.com>
Date: Mon, 4 Dec 2017 13:38:47 +0100
Subject: [PATCH] numa: describe siblings distances within cells
https://bugzilla.redhat.com/show_bug.cgi?id=1454889
Add support for describing NUMA distances in a domain's <numa> <cell>
XML description.
Below is an example of a 4 node setup:
<cpu>
<numa>
<cell id='0' cpus='0-3' memory='2097152' unit='KiB'>
<distances>
<sibling id='0' value='10'/>
<sibling id='1' value='21'/>
<sibling id='2' value='31'/>
<sibling id='3' value='21'/>
</distances>
</cell>
<cell id='1' cpus='4-7' memory='2097152' unit='KiB'>
<distances>
<sibling id='0' value='21'/>
<sibling id='1' value='10'/>
<sibling id='2' value='21'/>
<sibling id='3' value='31'/>
</distances>
</cell>
<cell id='2' cpus='8-11' memory='2097152' unit='KiB'>
<distances>
<sibling id='0' value='31'/>
<sibling id='1' value='21'/>
<sibling id='2' value='10'/>
<sibling id='3' value='21'/>
</distances>
<cell id='3' cpus='12-15' memory='2097152' unit='KiB'>
<distances>
<sibling id='0' value='21'/>
<sibling id='1' value='31'/>
<sibling id='2' value='21'/>
<sibling id='3' value='10'/>
</distances>
</cell>
</numa>
</cpu>
A <cell> defines a NUMA node. <distances> describes the NUMA distance
from the <cell> to the other NUMA nodes (the <sibling>s). For example,
in above XML description, the distance between NUMA node0 <cell id='0'
...> and NUMA node2 <sibling id='2' ...> is 31.
Valid distance values are '10 <= value <= 255'. A distance value of 10
represents the distance to the node itself. A distance value of 20
represents the default value for remote nodes but other values are
possible depending on the physical topology of the system.
When distances are not fully described, any missing sibling distance
values will default to 10 for local nodes and 20 for remote nodes.
If distance is given for A -> B, then we default B -> A to the same
value instead of 20.
Signed-off-by: Wim ten Have <wim.ten.have@oracle.com>
Reviewed-by: Daniel P. Berrange <berrange@redhat.com>
Signed-off-by: Jim Fehlig <jfehlig@suse.com>
(cherry picked from commit 74119a03f184b79dcad28aa1e6f4ede6dc444998)
Signed-off-by: Michal Privoznik <mprivozn@redhat.com>
Signed-off-by: Jiri Denemark <jdenemar@redhat.com>
---
docs/formatdomain.html.in | 64 ++++++++++++++-
docs/schemas/basictypes.rng | 7 ++
docs/schemas/cputypes.rng | 18 +++++
src/conf/numa_conf.c | 191 +++++++++++++++++++++++++++++++++++++++++++-
4 files changed, 276 insertions(+), 4 deletions(-)
diff --git a/docs/formatdomain.html.in b/docs/formatdomain.html.in
index 62dd6e1ec4..a5adf5d9aa 100644
--- a/docs/formatdomain.html.in
+++ b/docs/formatdomain.html.in
@@ -1529,7 +1529,69 @@
</p>
<p>
- This guest NUMA specification is currently available only for QEMU/KVM.
+ This guest NUMA specification is currently available only for
+ QEMU/KVM and Xen.
+ </p>
+
+ <p>
+ A NUMA hardware architecture supports the notion of distances
+ between NUMA cells. <span class="since">Since 3.10.0</span> it
+ is possible to define the distance between NUMA cells using the
+ <code>distances</code> element within a NUMA <code>cell</code>
+ description. The <code>sibling</code> sub-element is used to
+ specify the distance value between sibling NUMA cells. For more
+ details, see the chapter explaining the system's SLIT (System
+ Locality Information Table) within the ACPI (Advanced
+ Configuration and Power Interface) specification.
+ </p>
+
+<pre>
+...
+<cpu>
+ ...
+ <numa>
+ <cell id='0' cpus='0,4-7' memory='512000' unit='KiB'>
+ <distances>
+ <sibling id='0' value='10'/>
+ <sibling id='1' value='21'/>
+ <sibling id='2' value='31'/>
+ <sibling id='3' value='41'/>
+ </distances>
+ </cell>
+ <cell id='1' cpus='1,8-10,12-15' memory='512000' unit='KiB' memAccess='shared'>
+ <distances>
+ <sibling id='0' value='21'/>
+ <sibling id='1' value='10'/>
+ <sibling id='2' value='21'/>
+ <sibling id='3' value='31'/>
+ </distances>
+ </cell>
+ <cell id='2' cpus='2,11' memory='512000' unit='KiB' memAccess='shared'>
+ <distances>
+ <sibling id='0' value='31'/>
+ <sibling id='1' value='21'/>
+ <sibling id='2' value='10'/>
+ <sibling id='3' value='21'/>
+ </distances>
+ </cell>
+ <cell id='3' cpus='3' memory='512000' unit='KiB'>
+ <distances>
+ <sibling id='0' value='41'/>
+ <sibling id='1' value='31'/>
+ <sibling id='2' value='21'/>
+ <sibling id='3' value='10'/>
+ </distances>
+ </cell>
+ </numa>
+ ...
+</cpu>
+...</pre>
+
+ <p>
+ Describing distances between NUMA cells is currently only supported
+ by Xen. If no <code>distances</code> are given to describe
+ the SLIT data between different cells, it will default to a scheme
+ using 10 for local and 20 for remote distances.
</p>
<h3><a id="elementsEvents">Events configuration</a></h3>
diff --git a/docs/schemas/basictypes.rng b/docs/schemas/basictypes.rng
index 1ea667cdf6..1a18cd31b1 100644
--- a/docs/schemas/basictypes.rng
+++ b/docs/schemas/basictypes.rng
@@ -77,6 +77,13 @@
</choice>
</define>
+ <define name="numaDistanceValue">
+ <data type="unsignedInt">
+ <param name="minInclusive">10</param>
+ <param name="maxInclusive">255</param>
+ </data>
+ </define>
+
<define name="pciaddress">
<optional>
<attribute name="domain">
diff --git a/docs/schemas/cputypes.rng b/docs/schemas/cputypes.rng
index 3eef16abce..c45b6dfb28 100644
--- a/docs/schemas/cputypes.rng
+++ b/docs/schemas/cputypes.rng
@@ -129,6 +129,24 @@
</choice>
</attribute>
</optional>
+ <optional>
+ <element name="distances">
+ <oneOrMore>
+ <ref name="numaDistance"/>
+ </oneOrMore>
+ </element>
+ </optional>
+ </element>
+ </define>
+
+ <define name="numaDistance">
+ <element name="sibling">
+ <attribute name="id">
+ <ref name="unsignedInt"/>
+ </attribute>
+ <attribute name="value">
+ <ref name="numaDistanceValue"/>
+ </attribute>
</element>
</define>
diff --git a/src/conf/numa_conf.c b/src/conf/numa_conf.c
index b71dc012c5..5fbcc72041 100644
--- a/src/conf/numa_conf.c
+++ b/src/conf/numa_conf.c
@@ -29,6 +29,15 @@
#include "virnuma.h"
#include "virstring.h"
+/*
+ * Distance definitions defined Conform ACPI 2.0 SLIT.
+ * See include/linux/topology.h
+ */
+#define LOCAL_DISTANCE 10
+#define REMOTE_DISTANCE 20
+/* SLIT entry value is a one-byte unsigned integer. */
+#define UNREACHABLE 255
+
#define VIR_FROM_THIS VIR_FROM_DOMAIN
VIR_ENUM_IMPL(virDomainNumatuneMemMode,
@@ -48,6 +57,8 @@ VIR_ENUM_IMPL(virDomainMemoryAccess, VIR_DOMAIN_MEMORY_ACCESS_LAST,
"shared",
"private")
+typedef struct _virDomainNumaDistance virDomainNumaDistance;
+typedef virDomainNumaDistance *virDomainNumaDistancePtr;
typedef struct _virDomainNumaNode virDomainNumaNode;
typedef virDomainNumaNode *virDomainNumaNodePtr;
@@ -66,6 +77,12 @@ struct _virDomainNuma {
virBitmapPtr nodeset; /* host memory nodes where this guest node resides */
virDomainNumatuneMemMode mode; /* memory mode selection */
virDomainMemoryAccess memAccess; /* shared memory access configuration */
+
+ struct _virDomainNumaDistance {
+ unsigned int value; /* locality value for node i->j or j->i */
+ unsigned int cellid;
+ } *distances; /* remote node distances */
+ size_t ndistances;
} *mem_nodes; /* guest node configuration */
size_t nmem_nodes;
@@ -686,6 +703,144 @@ virDomainNumatuneNodesetIsAvailable(virDomainNumaPtr numatune,
}
+static int
+virDomainNumaDefNodeDistanceParseXML(virDomainNumaPtr def,
+ xmlXPathContextPtr ctxt,
+ unsigned int cur_cell)
+{
+ int ret = -1;
+ int sibling;
+ char *tmp = NULL;
+ xmlNodePtr *nodes = NULL;
+ size_t i, ndistances = def->nmem_nodes;
+
+ if (!ndistances)
+ return 0;
+
+ /* check if NUMA distances definition is present */
+ if (!virXPathNode("./distances[1]", ctxt))
+ return 0;
+
+ if ((sibling = virXPathNodeSet("./distances[1]/sibling", ctxt, &nodes)) <= 0) {
+ virReportError(VIR_ERR_XML_ERROR, "%s",
+ _("NUMA distances defined without siblings"));
+ goto cleanup;
+ }
+
+ for (i = 0; i < sibling; i++) {
+ virDomainNumaDistancePtr ldist, rdist;
+ unsigned int sibling_id, sibling_value;
+
+ /* siblings are in order of parsing or explicitly numbered */
+ if (!(tmp = virXMLPropString(nodes[i], "id"))) {
+ virReportError(VIR_ERR_XML_ERROR,
+ _("Missing 'id' attribute in NUMA "
+ "distances under 'cell id %d'"),
+ cur_cell);
+ goto cleanup;
+ }
+
+ /* The "id" needs to be applicable */
+ if (virStrToLong_uip(tmp, NULL, 10, &sibling_id) < 0) {
+ virReportError(VIR_ERR_XML_ERROR,
+ _("Invalid 'id' attribute in NUMA "
+ "distances for sibling: '%s'"),
+ tmp);
+ goto cleanup;
+ }
+ VIR_FREE(tmp);
+
+ /* The "id" needs to be within numa/cell range */
+ if (sibling_id >= ndistances) {
+ virReportError(VIR_ERR_XML_ERROR,
+ _("'sibling_id %d' does not refer to a "
+ "valid cell within NUMA 'cell id %d'"),
+ sibling_id, cur_cell);
+ goto cleanup;
+ }
+
+ /* We need a locality value. Check and correct
+ * distance to local and distance to remote node.
+ */
+ if (!(tmp = virXMLPropString(nodes[i], "value"))) {
+ virReportError(VIR_ERR_XML_ERROR,
+ _("Missing 'value' attribute in NUMA distances "
+ "under 'cell id %d' for 'sibling id %d'"),
+ cur_cell, sibling_id);
+ goto cleanup;
+ }
+
+ /* The "value" needs to be applicable */
+ if (virStrToLong_uip(tmp, NULL, 10, &sibling_value) < 0) {
+ virReportError(VIR_ERR_XML_ERROR,
+ _("'value %s' is invalid for "
+ "'sibling id %d' under NUMA 'cell id %d'"),
+ tmp, sibling_id, cur_cell);
+ goto cleanup;
+ }
+ VIR_FREE(tmp);
+
+ /* Assure LOCAL_DISTANCE <= "value" <= UNREACHABLE
+ * and correct LOCAL_DISTANCE setting if such applies.
+ */
+ if ((sibling_value < LOCAL_DISTANCE ||
+ sibling_value > UNREACHABLE) ||
+ (sibling_id == cur_cell &&
+ sibling_value != LOCAL_DISTANCE) ||
+ (sibling_id != cur_cell &&
+ sibling_value == LOCAL_DISTANCE)) {
+ virReportError(VIR_ERR_XML_ERROR,
+ _("'value %d' is invalid for "
+ "'sibling id %d' under NUMA 'cell id %d'"),
+ sibling_value, sibling_id, cur_cell);
+ goto cleanup;
+ }
+
+ /* Apply the local / remote distance */
+ ldist = def->mem_nodes[cur_cell].distances;
+ if (!ldist) {
+ if (VIR_ALLOC_N(ldist, ndistances) < 0)
+ goto cleanup;
+
+ ldist[cur_cell].value = LOCAL_DISTANCE;
+ ldist[cur_cell].cellid = cur_cell;
+ def->mem_nodes[cur_cell].ndistances = ndistances;
+ }
+
+ ldist[sibling_id].cellid = sibling_id;
+ ldist[sibling_id].value = sibling_value;
+ def->mem_nodes[cur_cell].distances = ldist;
+
+ /* Apply symmetry if none given */
+ rdist = def->mem_nodes[sibling_id].distances;
+ if (!rdist) {
+ if (VIR_ALLOC_N(rdist, ndistances) < 0)
+ goto cleanup;
+
+ rdist[sibling_id].value = LOCAL_DISTANCE;
+ rdist[sibling_id].cellid = sibling_id;
+ def->mem_nodes[sibling_id].ndistances = ndistances;
+ }
+
+ rdist[cur_cell].cellid = cur_cell;
+ if (!rdist[cur_cell].value)
+ rdist[cur_cell].value = sibling_value;
+ def->mem_nodes[sibling_id].distances = rdist;
+ }
+
+ ret = 0;
+
+ cleanup:
+ if (ret) {
+ for (i = 0; i < ndistances; i++)
+ VIR_FREE(def->mem_nodes[i].distances);
+ }
+ VIR_FREE(nodes);
+ VIR_FREE(tmp);
+
+ return ret;
+}
+
int
virDomainNumaDefCPUParseXML(virDomainNumaPtr def,
xmlXPathContextPtr ctxt)
@@ -694,7 +849,7 @@ virDomainNumaDefCPUParseXML(virDomainNumaPtr def,
xmlNodePtr oldNode = ctxt->node;
char *tmp = NULL;
int n;
- size_t i;
+ size_t i, j;
int ret = -1;
/* check if NUMA definition is present */
@@ -712,7 +867,6 @@ virDomainNumaDefCPUParseXML(virDomainNumaPtr def,
def->nmem_nodes = n;
for (i = 0; i < n; i++) {
- size_t j;
int rc;
unsigned int cur_cell = i;
@@ -788,6 +942,10 @@ virDomainNumaDefCPUParseXML(virDomainNumaPtr def,
def->mem_nodes[cur_cell].memAccess = rc;
VIR_FREE(tmp);
}
+
+ /* Parse NUMA distances info */
+ if (virDomainNumaDefNodeDistanceParseXML(def, ctxt, cur_cell) < 0)
+ goto cleanup;
}
ret = 0;
@@ -815,6 +973,8 @@ virDomainNumaDefCPUFormatXML(virBufferPtr buf,
virBufferAddLit(buf, "<numa>\n");
virBufferAdjustIndent(buf, 2);
for (i = 0; i < ncells; i++) {
+ int ndistances;
+
memAccess = virDomainNumaGetNodeMemoryAccessMode(def, i);
if (!(cpustr = virBitmapFormat(virDomainNumaGetNodeCpumask(def, i))))
@@ -829,7 +989,32 @@ virDomainNumaDefCPUFormatXML(virBufferPtr buf,
if (memAccess)
virBufferAsprintf(buf, " memAccess='%s'",
virDomainMemoryAccessTypeToString(memAccess));
- virBufferAddLit(buf, "/>\n");
+
+ ndistances = def->mem_nodes[i].ndistances;
+ if (!ndistances) {
+ virBufferAddLit(buf, "/>\n");
+ } else {
+ size_t j;
+ virDomainNumaDistancePtr distances = def->mem_nodes[i].distances;
+
+ virBufferAddLit(buf, ">\n");
+ virBufferAdjustIndent(buf, 2);
+ virBufferAddLit(buf, "<distances>\n");
+ virBufferAdjustIndent(buf, 2);
+ for (j = 0; j < ndistances; j++) {
+ if (distances[j].value) {
+ virBufferAddLit(buf, "<sibling");
+ virBufferAsprintf(buf, " id='%d'", distances[j].cellid);
+ virBufferAsprintf(buf, " value='%d'", distances[j].value);
+ virBufferAddLit(buf, "/>\n");
+ }
+ }
+ virBufferAdjustIndent(buf, -2);
+ virBufferAddLit(buf, "</distances>\n");
+ virBufferAdjustIndent(buf, -2);
+ virBufferAddLit(buf, "</cell>\n");
+ }
+
VIR_FREE(cpustr);
}
virBufferAdjustIndent(buf, -2);
--
2.15.1