From mboxrd@z Thu Jan  1 00:00:00 1970
From: Wei Liu <wei.liu2@citrix.com>
Subject: [PATCH v5 24/24] xl: vNUMA support
Date: Thu, 12 Feb 2015 19:44:54 +0000
Message-ID: <1423770294-9779-25-git-send-email-wei.liu2@citrix.com>
References: <1423770294-9779-1-git-send-email-wei.liu2@citrix.com>
Mime-Version: 1.0
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: 7bit
Return-path: <xen-devel-bounces@lists.xen.org>
In-Reply-To: <1423770294-9779-1-git-send-email-wei.liu2@citrix.com>
List-Unsubscribe: <http://lists.xen.org/cgi-bin/mailman/options/xen-devel>,
	<mailto:xen-devel-request@lists.xen.org?subject=unsubscribe>
List-Post: <mailto:xen-devel@lists.xen.org>
List-Help: <mailto:xen-devel-request@lists.xen.org?subject=help>
List-Subscribe: <http://lists.xen.org/cgi-bin/mailman/listinfo/xen-devel>,
	<mailto:xen-devel-request@lists.xen.org?subject=subscribe>
Sender: xen-devel-bounces@lists.xen.org
Errors-To: xen-devel-bounces@lists.xen.org
To: xen-devel@lists.xen.org
Cc: Wei Liu <wei.liu2@citrix.com>, ian.campbell@citrix.com, andrew.cooper3@citrix.com, dario.faggioli@citrix.com, ian.jackson@eu.citrix.com, JBeulich@suse.com, ufimtseva@gmail.com
List-Id: xen-devel@lists.xenproject.org

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@citrix.com>
Cc: Ian Campbell <ian.campbell@citrix.com>
Cc: Ian Jackson <ian.jackson@eu.citrix.com>
---
Changes in v5:
1. New syntax for vNUMA configuration.
---
 docs/man/xl.cfg.pod.5    |  54 ++++++++++++++++++
 tools/libxl/xl_cmdimpl.c | 139 ++++++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 192 insertions(+), 1 deletion(-)

diff --git a/docs/man/xl.cfg.pod.5 b/docs/man/xl.cfg.pod.5
index 408653f..2a27b1c 100644
--- a/docs/man/xl.cfg.pod.5
+++ b/docs/man/xl.cfg.pod.5
@@ -266,6 +266,60 @@ 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_SPECE> 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 string. Supported
+B<VNODE_CONFIG_OPTION>s are:
+
+=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 must match B<maxmem=> (or B<memory=> if B<maxmem=> is not
+specified).
+
+=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 ec7fb2d..f52daf9 100644
--- a/tools/libxl/xl_cmdimpl.c
+++ b/tools/libxl/xl_cmdimpl.c
@@ -158,7 +158,6 @@ struct domain_create {
 };
 
 
-static uint32_t find_domain(const char *p) __attribute__((warn_unused_result));
 static uint32_t find_domain(const char *p)
 {
     uint32_t domid;
@@ -989,6 +988,142 @@ static int parse_nic_config(libxl_device_nic *nic, XLU_Config **config, char *to
     return 0;
 }
 
+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;
+
+
+    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));
+
+    for (i = 0; i < b_info->num_vnuma_nodes; i++) {
+        libxl_vnode_info *p = &b_info->vnuma_nodes[i];
+
+        libxl_vnode_info_init(p);
+        libxl_cpu_bitmap_alloc(ctx, &p->vcpus, b_info->max_vcpus);
+        libxl_bitmap_set_none(&p->vcpus);
+        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;
+                char *endptr;
+                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);
+
+#define ABORT_IF_FAILED(str)                                            \
+                do {                                                    \
+                    if (endptr == value || val == ULONG_MAX) {          \
+                        fprintf(stderr,                                 \
+                                "xl: failed to convert \"%s\" to number\n", \
+                                (str));                                 \
+                        exit(1);                                        \
+                    }                                                   \
+                } while (0)
+
+                if (!strcmp("pnode", option)) {
+                    val = strtoul(value, &endptr, 10);
+                    ABORT_IF_FAILED(value);
+                    if (val >= nr_nodes) {
+                        fprintf(stderr,
+                                "xl: invalid pnode number: %lu\n", val);
+                        exit(1);
+                    }
+                    p->pnode = val;
+                } else if (!strcmp("size", option)) {
+                    val = strtoul(value, &endptr, 10);
+                    ABORT_IF_FAILED(value);
+                    p->memkb = val << 10;
+                } else if (!strcmp("vcpus", option)) {
+                    libxl_string_list cpu_spec_list;
+                    int cpu;
+                    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);
+                        for (cpu = s; cpu <=e; cpu++)
+                            libxl_bitmap_set(&p->vcpus, cpu);
+                    }
+                    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 = strtoul(vdist[j], &endptr, 10);
+                        ABORT_IF_FAILED(vdist[j]);
+                        p->distances[j] = val;
+                    }
+                    libxl_string_list_dispose(&vdist);
+                }
+#undef ABORT_IF_FAILED
+                free(option);
+                free(value);
+                free(option_untrimmed);
+                free(value_untrimmed);
+            }
+        }
+    }
+}
+
 static void parse_config_data(const char *config_source,
                               const char *config_data,
                               int config_len,
@@ -1179,6 +1314,8 @@ static void parse_config_data(const char *config_source,
         }
     }
 
+    parse_vnuma_config(config, b_info);
+
     if (!xlu_cfg_get_long(config, "rtc_timeoffset", &l, 0))
         b_info->rtc_timeoffset = l;
 
-- 
1.9.1