[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

[Xen-devel] [PATCH v4 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>
Cc: Dario Faggioli <dario.faggioli@xxxxxxxxxx>
Cc: Elena Ufimtseva <ufimtseva@xxxxxxxxx>
---
Changes in v2:
1. Make vnuma_vdistances mandatory.
2. Use nested list to specify vdistances.
3. Update documentation.
---
 docs/man/xl.cfg.pod.5    |   39 ++++++++++++
 tools/libxl/xl_cmdimpl.c |  147 ++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 186 insertions(+)

diff --git a/docs/man/xl.cfg.pod.5 b/docs/man/xl.cfg.pod.5
index e2f91fc..b23bd6f 100644
--- a/docs/man/xl.cfg.pod.5
+++ b/docs/man/xl.cfg.pod.5
@@ -266,6 +266,45 @@ it will crash.
 
 =back
 
+=head3 Virtual NUMA Memory Allocation
+
+=over 4
+
+=item B<vnuma_memory=[ NUMBER, NUMBER, ... ]>
+
+Specify the size of memory covered by each virtual NUMA node. The number of
+elements in the list also implicitly defines the number of virtual NUMA nodes.
+
+The sum of all elements in this list should be equal to memory size specified
+by B<maxmem=> in guest configuration file, or B<memory=> if B<maxmem=> is not
+specified.
+
+=item B<vnuma_vcpu_map=[ NUMBER, NUMBER, ... ]>
+
+Specifiy which virutal NUMA node a specific vcpu belongs to. The number of
+elements in this list should be equal to B<maxvcpus=> in guest configuration
+file, or B<vcpus=> if B<maxvcpus=> is not specified.
+
+=item B<vnuma_pnode_map=[ NUMBER, NUMBER, ... ]>
+
+Specifiy which physical NUMA node a specific virtual NUMA node maps to. The
+number of elements in this list should be equal to the number of virtual
+NUMA nodes defined in B<vnuma_memory=>.
+
+=item B<vnuma_vdistance=[ [NUMBER, ..., NUMBER], [NUMBER, ..., NUMBER], ... ]>
+
+Two dimensional list to specify distances among nodes.
+
+The number of elements in the first dimension list equals the number of virtual
+nodes. Each element in position B<i> is a list that specifies the distances
+from node B<i> to other nodes.
+
+For example, for a guest with 2 virtual nodes, user can specify:
+
+  vnuma_vdistance = [ [10, 20], [20, 10] ]
+
+=back
+
 =head3 Event Actions
 
 =over 4
diff --git a/tools/libxl/xl_cmdimpl.c b/tools/libxl/xl_cmdimpl.c
index 0b02a6c..107b552 100644
--- a/tools/libxl/xl_cmdimpl.c
+++ b/tools/libxl/xl_cmdimpl.c
@@ -977,6 +977,151 @@ 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)
+{
+    int i, j;
+    XLU_ConfigList *vnuma_memory, *vnuma_vcpu_map, *vnuma_pnode_map,
+        *vnuma_vdistances;
+    int num_vnuma_memory, num_vnuma_vcpu_map, num_vnuma_pnode_map,
+        num_vnuma_vdistances;
+    const char *buf;
+    libxl_physinfo physinfo;
+    uint32_t nr_nodes;
+    unsigned long val;
+    char *ep;
+
+    libxl_physinfo_init(&physinfo);
+    if (libxl_get_physinfo(ctx, &physinfo) != 0) {
+        libxl_physinfo_dispose(&physinfo);
+        fprintf(stderr, "libxl_physinfo failed.\n");
+        exit(1);
+    }
+    nr_nodes = physinfo.nr_nodes;
+    libxl_physinfo_dispose(&physinfo);
+
+    if (xlu_cfg_get_list(config, "vnuma_memory", &vnuma_memory,
+                         &num_vnuma_memory, 1))
+        return;              /* No vnuma config */
+
+    b_info->num_vnuma_nodes = num_vnuma_memory;
+    b_info->vnuma_nodes = xmalloc(num_vnuma_memory * 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 = xmalloc(b_info->num_vnuma_nodes * sizeof(uint32_t));
+        p->num_distances = b_info->num_vnuma_nodes;
+    }
+
+    for (i = 0; i < b_info->num_vnuma_nodes; i++) {
+        buf = xlu_cfg_get_listitem(vnuma_memory, i);
+        val = strtoul(buf, &ep, 10);
+        if (ep == buf) {
+            fprintf(stderr, "xl: Invalid argument parsing vnuma memory: %s\n", 
buf);
+            exit(1);
+        }
+        b_info->vnuma_nodes[i].memkb = val << 10;
+    }
+
+    if (xlu_cfg_get_list(config, "vnuma_vcpu_map", &vnuma_vcpu_map,
+                         &num_vnuma_vcpu_map, 1)) {
+        fprintf(stderr, "No vcpu to vnode map specified\n");
+        exit(1);
+    }
+
+    i = 0;
+    while (i < b_info->max_vcpus &&
+           (buf = xlu_cfg_get_listitem(vnuma_vcpu_map, i)) != NULL) {
+        val = strtoul(buf, &ep, 10);
+        if (ep == buf) {
+            fprintf(stderr, "xl: Invalid argument parsing vcpu map: %s\n", 
buf);
+            exit(1);
+        }
+        if (val >= num_vnuma_memory) {
+            fprintf(stderr, "xl: Invalid vnode number specified: %lu\n", val);
+            exit(1);
+        }
+        libxl_bitmap_set(&b_info->vnuma_nodes[val].vcpus, i);
+        i++;
+    }
+
+    if (i != b_info->max_vcpus) {
+        fprintf(stderr, "xl: Not enough elements in vnuma_vcpu_map, provided 
%d, required %d\n",
+                i + 1, b_info->max_vcpus);
+        exit(1);
+    }
+
+    if (xlu_cfg_get_list(config, "vnuma_pnode_map", &vnuma_pnode_map,
+                         &num_vnuma_pnode_map, 1)) {
+        fprintf(stderr, "No vnode to pnode map specified\n");
+        exit(1);
+    }
+
+    i = 0;
+    while (i < num_vnuma_pnode_map &&
+           (buf = xlu_cfg_get_listitem(vnuma_pnode_map, i)) != NULL) {
+        val = strtoul(buf, &ep, 10);
+        if (ep == buf) {
+            fprintf(stderr, "xl: Invalid argument parsing vnode to pnode map: 
%s\n", buf);
+            exit(1);
+        }
+        if (val >= nr_nodes) {
+            fprintf(stderr, "xl: Invalid pnode number specified: %lu\n", val);
+            exit(1);
+        }
+
+        b_info->vnuma_nodes[i].pnode = val;
+
+        i++;
+    }
+
+    if (i != b_info->num_vnuma_nodes) {
+        fprintf(stderr, "xl: Not enough elements in vnuma_vnode_map, provided 
%d, required %d\n",
+                i + 1, b_info->num_vnuma_nodes);
+        exit(1);
+    }
+
+    if (!xlu_cfg_get_list(config, "vnuma_vdistances", &vnuma_vdistances,
+                          &num_vnuma_vdistances, 1)) {
+        if (num_vnuma_vdistances != num_vnuma_memory) {
+            fprintf(stderr, "xl: Required %d sub-lists in vnuma_vdistances but 
provided %d\n",
+                    num_vnuma_memory, num_vnuma_vdistances);
+            exit(1);
+        }
+
+        for (i = 0; i < num_vnuma_vdistances; i++) {
+            const XLU_ConfigValue *tmp;
+            const XLU_ConfigList *sublist;
+
+            tmp = xlu_cfg_get_listitem2(vnuma_vdistances, i);
+            if (xlu_cfg_value_type(tmp) != XLU_LIST) {
+                fprintf(stderr, "xl: Expecting list in vnuma_vdistance\n");
+                exit(1);
+            }
+            sublist = xlu_cfg_value_get_list(tmp);
+            for (j = 0;
+                 (buf = xlu_cfg_get_listitem(sublist, j)) != NULL;
+                 j++) {
+                val = strtoul(buf, &ep, 10);
+                if (ep == buf) {
+                    fprintf(stderr, "xl: Invalid argument parsing vdistances 
map: %s\n", buf);
+                    exit(1);
+                }
+
+                b_info->vnuma_nodes[i].distances[j] = val;
+            }
+        }
+
+    } else {
+        fprintf(stderr, "xl: No vnuma_vdistances specified.\n");
+        exit(1);
+    }
+}
+
 static void parse_config_data(const char *config_source,
                               const char *config_data,
                               int config_len,
@@ -1167,6 +1312,8 @@ 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;
 
-- 
1.7.10.4


_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel


 


Rackspace

Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.