qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Eduardo Habkost <ehabkost@redhat.com>
To: qemu-devel@nongnu.org
Cc: Paolo Bonzini <pbonzini@redhat.com>,
	Igor Mammedov <imammedo@redhat.com>,
	Hu Tao <hutao@cn.fujitsu.com>,
	"Michael S. Tsirkin" <mst@redhat.com>
Subject: [Qemu-devel] [PATCH v3 3/4] numa: Reject configuration if CPU appears on multiple nodes
Date: Thu, 12 Feb 2015 15:50:34 -0200	[thread overview]
Message-ID: <1423763435-3696-4-git-send-email-ehabkost@redhat.com> (raw)
In-Reply-To: <1423763435-3696-1-git-send-email-ehabkost@redhat.com>

Each CPU can appear in only one NUMA node on the NUMA config. Reject
configuration if a CPU appears in multiple nodes.

Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
---
v1 -> v2: (no changes)

v2 -> v3:
 * Rename present_cpus to seen_cpus, to make it less confusing
 * Use GString and error_report() instead of multiple fprintf() calls
---
 numa.c | 37 +++++++++++++++++++++++++++++++++++++
 1 file changed, 37 insertions(+)

diff --git a/numa.c b/numa.c
index 4139e46..712faff 100644
--- a/numa.c
+++ b/numa.c
@@ -168,6 +168,41 @@ error:
     return -1;
 }
 
+static char *enumerate_cpus(unsigned long *cpus, int max_cpus)
+{
+    int cpu;
+    bool first = true;
+    GString *s = g_string_new(NULL);
+
+    for (cpu = find_first_bit(cpus, max_cpus);
+        cpu < max_cpus;
+        cpu = find_next_bit(cpus, max_cpus, cpu + 1)) {
+        g_string_append_printf(s, "%s%d", first ? "" : " ", cpu);
+        first = false;
+    }
+    return g_string_free(s, FALSE);
+}
+
+static void validate_numa_cpus(void)
+{
+    int i;
+    DECLARE_BITMAP(seen_cpus, MAX_CPUMASK_BITS);
+
+    bitmap_zero(seen_cpus, MAX_CPUMASK_BITS);
+    for (i = 0; i < nb_numa_nodes; i++) {
+        if (bitmap_intersects(seen_cpus, numa_info[i].node_cpu,
+                              MAX_CPUMASK_BITS)) {
+            bitmap_and(seen_cpus, seen_cpus,
+                       numa_info[i].node_cpu, MAX_CPUMASK_BITS);
+            error_report("CPU(s) present in multiple NUMA nodes: %s",
+                         enumerate_cpus(seen_cpus, max_cpus));;
+            exit(1);
+        }
+        bitmap_or(seen_cpus, seen_cpus,
+                  numa_info[i].node_cpu, MAX_CPUMASK_BITS);
+    }
+}
+
 void parse_numa_opts(void)
 {
     int i;
@@ -245,6 +280,8 @@ void parse_numa_opts(void)
                 set_bit(i, numa_info[i % nb_numa_nodes].node_cpu);
             }
         }
+
+        validate_numa_cpus();
     }
 }
 
-- 
2.1.0

  parent reply	other threads:[~2015-02-12 17:50 UTC|newest]

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-02-12 17:50 [Qemu-devel] [PATCH v3 0/4] NUMA: Validate CPU configuration Eduardo Habkost
2015-02-12 17:50 ` [Qemu-devel] [PATCH v3 1/4] numa: Fix off-by-one error at MAX_CPUMASK_BITS check Eduardo Habkost
2015-02-24  6:38   ` Igor Mammedov
2015-02-12 17:50 ` [Qemu-devel] [PATCH v3 2/4] numa: Reject CPU indexes > max_cpus Eduardo Habkost
2015-02-24  6:49   ` Igor Mammedov
2015-02-12 17:50 ` Eduardo Habkost [this message]
2015-02-24  7:04   ` [Qemu-devel] [PATCH v3 3/4] numa: Reject configuration if CPU appears on multiple nodes Igor Mammedov
2015-02-12 17:50 ` [Qemu-devel] [PATCH v3 4/4] numa: Print warning if no node is assigned to a CPU Eduardo Habkost
2015-02-12 18:22   ` Paolo Bonzini
2015-02-12 23:05     ` Eduardo Habkost
2015-02-24  8:01   ` Igor Mammedov
2015-02-24 18:19     ` Eduardo Habkost
2015-02-25  8:43       ` Igor Mammedov
2015-02-23 20:10 ` [Qemu-devel] [PATCH v3 0/4] NUMA: Validate CPU configuration Eduardo Habkost

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1423763435-3696-4-git-send-email-ehabkost@redhat.com \
    --to=ehabkost@redhat.com \
    --cc=hutao@cn.fujitsu.com \
    --cc=imammedo@redhat.com \
    --cc=mst@redhat.com \
    --cc=pbonzini@redhat.com \
    --cc=qemu-devel@nongnu.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).