|
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index] [Xen-devel] [PATCH v8 21/21] xl: vNUMA support
This patch includes configuration options parser and documentation.
Please find the hunk to xl.cfg.pod.5 for more information.
Signed-off-by: Wei Liu <wei.liu2@xxxxxxxxxx>
Cc: Ian Campbell <ian.campbell@xxxxxxxxxx>
Cc: Ian Jackson <ian.jackson@xxxxxxxxxxxxx>
---
Changes in v8:
1. State all options are mandatory in manpage.
2. Rework xl config parser.
Changes in v7:
1. Fill in max_memkb with vNUMA memory settings.
2. Check vcpus specified in vnuma matches maxvcpus=.
3. Update manpage.
4. Drop Dario's reviewed-by due to above changes.
Changes in v6:
1. Disable NUMA auto-placement.
---
docs/man/xl.cfg.pod.5 | 59 +++++++++++++-
tools/libxl/xl_cmdimpl.c | 204 ++++++++++++++++++++++++++++++++++++++++++++---
2 files changed, 250 insertions(+), 13 deletions(-)
diff --git a/docs/man/xl.cfg.pod.5 b/docs/man/xl.cfg.pod.5
index 408653f..93cd7d2 100644
--- a/docs/man/xl.cfg.pod.5
+++ b/docs/man/xl.cfg.pod.5
@@ -41,8 +41,8 @@ value).
=item B<[ VALUE, VALUE, ... ]>
-A list of C<VALUES> of the above types. Lists are homogeneous and are
-not nested.
+A list of C<VALUES> of the above types. Lists can be heterogeneous and
+nested.
=back
@@ -266,6 +266,61 @@ it will crash.
=back
+=head3 Guest Virtual NUMA Configuration
+
+=over 4
+
+=item B<vnuma=[ VNODE_SPEC, VNODE_SPEC, ... ]
+
+Specify virtual NUMA configuration with positional arguments. The
+nth B<VNODE_SPEC> in the list specifies the configuration of nth
+virtual node.
+
+Each B<VNODE_SPEC> is a list, which has a form of
+"[VNODE_CONFIG_OPTION,VNODE_CONFIG_OPTION, ... ]" (without quotes).
+
+For example vnuma = [ ["pnode=0","size=512","vcpus=0-4","vdistances=10,20"] ]
+means vnode 0 is mapped to pnode 0, has 512MB ram, has vcpus 0 to 4, the
+distance to itself is 10 and the distance to vnode 1 is 20.
+
+Each B<VNODE_CONFIG_OPTION> is a quoted key=value pair. Supported
+B<VNODE_CONFIG_OPTION>s are (they are all mandatory at the moment):
+
+=over 4
+
+=item B<pnode=NUMBER>
+
+Specify which physical node this virtual node maps to.
+
+=item B<size=MBYTES>
+
+Specify the size of this virtual node. The sum of memory size of all
+vnodes will become B<maxmem=>. If B<maxmem=> is specified separately,
+a check is performed to make sure the sum of all vnode memory matches
+B<maxmem=>.
+
+=item B<vcpus=CPU-STRING>
+
+Specify which vcpus belong to this node. B<CPU-STRING> is a string
+separated by comma. You can specify range and single cpu. An example
+is "vcpus=0-5,8", which means you specify vcpu 0 to vcpu 5, and vcpu
+8.
+
+=item B<vdistances=NUMBER, NUMBER, ... >
+
+Specify virtual distance from this node to all nodes (including
+itself) with positional arguments. For example, "vdistance=10,20"
+for vnode 0 means the distance from vnode 0 to vnode 0 is 10, from
+vnode 0 to vnode 1 is 20. The number of arguments supplied must match
+the total number of vnodes.
+
+Normally you can use the values from "xl info -n" or "numactl
+--hardware" to fill in vdistance list.
+
+=back
+
+=back
+
=head3 Event Actions
=over 4
diff --git a/tools/libxl/xl_cmdimpl.c b/tools/libxl/xl_cmdimpl.c
index 5b45213..4bd84a2 100644
--- a/tools/libxl/xl_cmdimpl.c
+++ b/tools/libxl/xl_cmdimpl.c
@@ -987,13 +987,183 @@ static int parse_nic_config(libxl_device_nic *nic,
XLU_Config **config, char *to
return 0;
}
+static unsigned long parse_ulong(const char *str)
+{
+ char *endptr;
+ unsigned long val;
+
+ val = strtoul(str, &endptr, 10);
+ if (endptr == str || val == ULONG_MAX) {
+ fprintf(stderr, "xl: failed to convert \"%s\" to number\n", str);
+ exit(1);
+ }
+ return val;
+}
+
+static void parse_vnuma_config(const XLU_Config *config,
+ libxl_domain_build_info *b_info)
+{
+ libxl_physinfo physinfo;
+ uint32_t nr_nodes;
+ XLU_ConfigList *vnuma;
+ int i, j, len, num_vnuma;
+ unsigned long max_vcpus = 0, max_memkb = 0;
+ /* Temporary storage for parsed vcpus information to avoid
+ * parsing config twice. This array has num_vnuma elements.
+ */
+ struct vcpu_range_parsed {
+ unsigned long start, end;
+ } *vcpu_range_parsed;
+
+ libxl_physinfo_init(&physinfo);
+ if (libxl_get_physinfo(ctx, &physinfo) != 0) {
+ libxl_physinfo_dispose(&physinfo);
+ fprintf(stderr, "libxl_get_physinfo failed\n");
+ exit(1);
+ }
+
+ nr_nodes = physinfo.nr_nodes;
+ libxl_physinfo_dispose(&physinfo);
+
+ if (xlu_cfg_get_list(config, "vnuma", &vnuma, &num_vnuma, 1))
+ return;
+
+ b_info->num_vnuma_nodes = num_vnuma;
+ b_info->vnuma_nodes = xcalloc(num_vnuma, sizeof(libxl_vnode_info));
+ vcpu_range_parsed = xcalloc(num_vnuma, sizeof(*vcpu_range_parsed));
+
+ for (i = 0; i < b_info->num_vnuma_nodes; i++) {
+ libxl_vnode_info *p = &b_info->vnuma_nodes[i];
+
+ libxl_vnode_info_init(p);
+ p->distances = xcalloc(b_info->num_vnuma_nodes,
+ sizeof(*p->distances));
+ p->num_distances = b_info->num_vnuma_nodes;
+ }
+
+ for (i = 0; i < num_vnuma; i++) {
+ XLU_ConfigValue *vnode_spec, *conf_option;
+ XLU_ConfigList *vnode_config_list;
+ int conf_count;
+ libxl_vnode_info *p = &b_info->vnuma_nodes[i];
+
+ vnode_spec = xlu_cfg_get_listitem2(vnuma, i);
+ assert(vnode_spec);
+
+ xlu_cfg_value_get_list(config, vnode_spec, &vnode_config_list, 0);
+ if (!vnode_config_list) {
+ fprintf(stderr, "xl: cannot get vnode config option list\n");
+ exit(1);
+ }
+
+ for (conf_count = 0;
+ (conf_option =
+ xlu_cfg_get_listitem2(vnode_config_list, conf_count));
+ conf_count++) {
+
+ if (xlu_cfg_value_type(conf_option) == XLU_STRING) {
+ char *buf, *option_untrimmed, *value_untrimmed;
+ char *option, *value;
+ unsigned long val;
+
+ xlu_cfg_value_get_string(config, conf_option, &buf, 0);
+
+ if (!buf) continue;
+
+ if (split_string_into_pair(buf, "=",
+ &option_untrimmed,
+ &value_untrimmed)) {
+ fprintf(stderr, "xl: failed to split \"%s\" into pair\n",
+ buf);
+ exit(1);
+ }
+ trim(isspace, option_untrimmed, &option);
+ trim(isspace, value_untrimmed, &value);
+
+ if (!strcmp("pnode", option)) {
+ val = parse_ulong(value);
+ if (val >= nr_nodes) {
+ fprintf(stderr,
+ "xl: invalid pnode number: %lu\n", val);
+ exit(1);
+ }
+ p->pnode = val;
+ libxl_defbool_set(&b_info->numa_placement, false);
+ } else if (!strcmp("size", option)) {
+ val = parse_ulong(value);
+ p->memkb = val << 10;
+ max_memkb += p->memkb;
+ } else if (!strcmp("vcpus", option)) {
+ libxl_string_list cpu_spec_list;
+ unsigned long s, e;
+
+ split_string_into_string_list(value, ",", &cpu_spec_list);
+ len = libxl_string_list_length(&cpu_spec_list);
+
+ for (j = 0; j < len; j++)
+ parse_range(cpu_spec_list[j], &s, &e);
+
+ vcpu_range_parsed[i].start = s;
+ vcpu_range_parsed[i].end = e;
+ max_vcpus += (e - s + 1);
+ libxl_string_list_dispose(&cpu_spec_list);
+ } else if (!strcmp("vdistances", option)) {
+ libxl_string_list vdist;
+
+ split_string_into_string_list(value, ",", &vdist);
+ len = libxl_string_list_length(&vdist);
+
+ for (j = 0; j < len; j++) {
+ val = parse_ulong(value);
+ p->distances[j] = val;
+ }
+ libxl_string_list_dispose(&vdist);
+ }
+ free(option);
+ free(value);
+ free(option_untrimmed);
+ free(value_untrimmed);
+ }
+ }
+ }
+
+ /* User has specified maxvcpus= */
+ if (b_info->max_vcpus != 0 && b_info->max_vcpus != max_vcpus) {
+ fprintf(stderr, "xl: vnuma vcpus and maxvcpus= mismatch\n");
+ exit(1);
+ } else
+ b_info->max_vcpus = max_vcpus;
+
+ /* User has specified maxmem= */
+ if (b_info->max_memkb != LIBXL_MEMKB_DEFAULT &&
+ b_info->max_memkb != max_memkb) {
+ fprintf(stderr, "xl: maxmem and vnuma memory size mismatch\n");
+ exit(1);
+ } else
+ b_info->max_memkb = max_memkb;
+
+ for (i = 0; i < b_info->num_vnuma_nodes; i++) {
+ libxl_vnode_info *p = &b_info->vnuma_nodes[i];
+ int cpu;
+
+ libxl_cpu_bitmap_alloc(ctx, &p->vcpus, b_info->max_vcpus);
+ libxl_bitmap_set_none(&p->vcpus);
+ for (cpu = vcpu_range_parsed[i].start;
+ cpu <= vcpu_range_parsed[i].end;
+ cpu++)
+ libxl_bitmap_set(&p->vcpus, cpu);
+ }
+
+ free(vcpu_range_parsed);
+}
+
static void parse_config_data(const char *config_source,
const char *config_data,
int config_len,
libxl_domain_config *d_config)
{
const char *buf;
- long l;
+ long l, vcpus = 0;
XLU_Config *config;
XLU_ConfigList *cpus, *vbds, *nics, *pcis, *cvfbs, *cpuids, *vtpms;
XLU_ConfigList *channels, *ioports, *irqs, *iomem, *viridian;
@@ -1080,9 +1250,14 @@ static void parse_config_data(const char *config_source,
if (!xlu_cfg_get_long (config, "extratime", &l, 0))
b_info->sched_params.extratime = l;
- if (!xlu_cfg_get_long (config, "vcpus", &l, 0)) {
- b_info->max_vcpus = l;
+ if (!xlu_cfg_get_long (config, "memory", &l, 0))
+ b_info->target_memkb = l * 1024;
+
+ if (!xlu_cfg_get_long (config, "maxmem", &l, 0))
+ b_info->max_memkb = l * 1024;
+ if (!xlu_cfg_get_long (config, "vcpus", &l, 0)) {
+ vcpus = l;
if (libxl_cpu_bitmap_alloc(ctx, &b_info->avail_vcpus, l)) {
fprintf(stderr, "Unable to allocate cpumap\n");
exit(1);
@@ -1095,6 +1270,21 @@ static void parse_config_data(const char *config_source,
if (!xlu_cfg_get_long (config, "maxvcpus", &l, 0))
b_info->max_vcpus = l;
+ parse_vnuma_config(config, b_info);
+
+ /* Set max_memkb to target_memkb and max_vcpus to avail_vcpus if
+ * they are not set by user specified config option or vnuma.
+ */
+ if (b_info->max_memkb == LIBXL_MEMKB_DEFAULT)
+ b_info->max_memkb = b_info->target_memkb;
+ if (b_info->max_vcpus == 0)
+ b_info->max_vcpus = vcpus;
+
+ if (b_info->max_vcpus < vcpus) {
+ fprintf(stderr, "xl: maxvcpus < vcpus\n");
+ exit(1);
+ }
+
buf = NULL;
if (!xlu_cfg_get_list (config, "cpus", &cpus, &num_cpus, 1) ||
!xlu_cfg_get_string (config, "cpus", &buf, 0))
@@ -1105,14 +1295,6 @@ static void parse_config_data(const char *config_source,
!xlu_cfg_get_string (config, "cpus_soft", &buf, 0))
parse_vcpu_affinity(b_info, cpus, buf, num_cpus, false);
- if (!xlu_cfg_get_long (config, "memory", &l, 0)) {
- b_info->max_memkb = l * 1024;
- b_info->target_memkb = b_info->max_memkb;
- }
-
- if (!xlu_cfg_get_long (config, "maxmem", &l, 0))
- b_info->max_memkb = l * 1024;
-
libxl_defbool_set(&b_info->claim_mode, claim_mode);
if (xlu_cfg_get_string (config, "on_poweroff", &buf, 0))
--
1.9.1
_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel
|
 |
Lists.xenproject.org is hosted with RackSpace, monitoring our |