[ovs-dev,v3,1/2] ovs-numa: Non-consecutively numa nodes and cores
diff mbox series

Message ID 20200207183341.12582-2-dwilder@us.ibm.com
State New
Headers show
Series
  • Support for non-consecutive numa nodes and core ids.
Related show

Commit Message

David Wilder Feb. 7, 2020, 6:33 p.m. UTC
This change removes the assumption that numa nodes and cores are numbered
consecutively in linux.  This change is required to support some Power
systems.

An additional check has been added to verify that cores are online,
offline cores result in non-consecutively numbered cores.

I manually verified that all the exported functions defined in
ovs-numa.h function correctly with these changes on Power and amd64
systems.

Tests for dpif-netdev and pmd that define numa systems using the
--dummy-numa option have been modified to use non-consecutive numbered
nodes.

Signed-off-by: David Wilder <dwilder@us.ibm.com>
---
 lib/ovs-numa.c       | 43 ++++++++++++++++++++++++++++++++-----------
 tests/dpif-netdev.at | 12 ++++++------
 tests/pmd.at         | 20 ++++++++++----------
 3 files changed, 48 insertions(+), 27 deletions(-)

Patch
diff mbox series

diff --git a/lib/ovs-numa.c b/lib/ovs-numa.c
index 6d0a68522..ef445d282 100644
--- a/lib/ovs-numa.c
+++ b/lib/ovs-numa.c
@@ -42,16 +42,18 @@  VLOG_DEFINE_THIS_MODULE(ovs_numa);
  * This module stores the affinity information of numa nodes and cpu cores.
  * It also provides functions to bookkeep the pin of threads on cpu cores.
  *
- * It is assumed that the numa node ids and cpu core ids all start from 0 and
- * range continuously.  So, for example, if 'ovs_numa_get_n_cores()' returns N,
- * user can assume core ids from 0 to N-1 are all valid and there is a
- * 'struct cpu_core' for each id.
+ * It is assumed that the numa node ids and cpu core ids all start from 0.
+ * There is no guarantee that node and cpu ids are numbered consecutively
+ * (this is a change from earlier version of the code). So, for example,
+ * if two nodes exist with ids 0 and 8, 'ovs_numa_get_n_nodes()' will
+ * return 2, no assumption of node numbering should be made.
  *
  * NOTE, this module should only be used by the main thread.
  *
- * NOTE, the assumption above will fail when cpu hotplug is used.  In that
- * case ovs-numa will not function correctly.  For now, add a TODO entry
- * for addressing it in the future.
+ * NOTE, if cpu hotplug is used 'all_numa_nodes' and 'all_cpu_cores' must be
+ * invalidated when ever the system topology changes. Support for detecting
+ * topology changes has not been included. For now, add a TODO entry for
+ * addressing it in the future.
  *
  * TODO: Fix ovs-numa when cpu hotplug is used.
  */
@@ -169,10 +171,27 @@  discover_numa_and_core_dummy(void)
 
     free(conf);
 
-    if (max_numa_id + 1 != hmap_count(&all_numa_nodes)) {
-        ovs_fatal(0, "dummy numa contains non consecutive numa ids");
+}
+
+#ifdef __linux__
+/* Check if a cpu is detected and online */
+static int
+cpu_detected(unsigned int core_id)
+{
+    char path[PATH_MAX];
+    int len = snprintf(path,
+              sizeof(path), "/sys/devices/system/cpu/cpu%d/topology/core_id" ,
+              core_id);
+    if (len <= 0 || (unsigned)len >= sizeof(path)) {
+        return 0;
     }
+    if (access(path, F_OK) != 0) {
+        return 0;
+    }
+
+    return 1;
 }
+#endif /* __linux__ */
 
 /* Discovers all numa nodes and the corresponding cpu cores.
  * Constructs the 'struct numa_node' and 'struct cpu_core'. */
@@ -219,7 +238,9 @@  discover_numa_and_core(void)
                     unsigned core_id;
 
                     core_id = strtoul(subdir->d_name + 3, NULL, 10);
-                    insert_new_cpu_core(n, core_id);
+                    if (cpu_detected(core_id)) {
+                        insert_new_cpu_core(n, core_id);
+                    }
                 }
             }
             closedir(dir);
@@ -229,7 +250,7 @@  discover_numa_and_core(void)
         }
 
         free(path);
-        if (!dir || !numa_supported) {
+        if (!numa_supported) {
             break;
         }
     }
diff --git a/tests/dpif-netdev.at b/tests/dpif-netdev.at
index 0aeb4e788..3a1a58276 100644
--- a/tests/dpif-netdev.at
+++ b/tests/dpif-netdev.at
@@ -94,7 +94,7 @@  m4_define([DPIF_NETDEV_DUMMY_IFACE],
                      fail-mode=secure -- \
       add-port br1 p2 -- set interface p2 type=$1 options:stream=unix:$OVS_RUNDIR/p0.sock ofport_request=2 -- \
       add-port br1 p8 -- set interface p8 ofport_request=8 type=$1 --], [], [],
-      [m4_if([$1], [dummy-pmd], [--dummy-numa="0,0,0,0,1,1,1,1"], [])])
+      [m4_if([$1], [dummy-pmd], [--dummy-numa="0,0,0,0,8,8,8,8"], [])])
    AT_CHECK([ovs-appctl vlog/set dpif:dbg dpif_netdev:dbg])
 
    AT_CHECK([ovs-ofctl add-flow br0 action=normal])
@@ -126,7 +126,7 @@  m4_define([DPIF_NETDEV_MISS_FLOW_INSTALL],
       -- set interface p1 type=$1 options:pstream=punix:$OVS_RUNDIR/p0.sock \
       -- set bridge br0 datapath-type=dummy \
                         other-config:datapath-id=1234 fail-mode=secure], [], [],
-      [m4_if([$1], [dummy-pmd], [--dummy-numa="0,0,0,0,1,1,1,1"], [])])
+      [m4_if([$1], [dummy-pmd], [--dummy-numa="0,0,0,0,8,8,8,8"], [])])
    AT_CHECK([ovs-appctl vlog/set dpif:dbg dpif_netdev:dbg])
 
    AT_CHECK([ovs-ofctl add-flow br0 action=normal])
@@ -168,7 +168,7 @@  m4_define([DPIF_NETDEV_FLOW_PUT_MODIFY],
       add-port br0 p2 -- set interface p2 type=$1 ofport_request=2 options:pstream=punix:$OVS_RUNDIR/p2.sock -- \
       set bridge br0 datapath-type=dummy \
                      other-config:datapath-id=1234 fail-mode=secure], [], [],
-      [m4_if([$1], [dummy-pmd], [--dummy-numa="0,0,0,0,1,1,1,1"], [])])
+      [m4_if([$1], [dummy-pmd], [--dummy-numa="0,0,0,0,8,8,8,8"], [])])
    AT_CHECK([ovs-appctl vlog/set dpif:file:dbg dpif_netdev:file:dbg])
 
    # Add a flow that directs some packets received on p1 to p2 and the
@@ -222,7 +222,7 @@  m4_define([DPIF_NETDEV_MISS_FLOW_DUMP],
       -- set interface p1 type=$1 options:pstream=punix:$OVS_RUNDIR/p0.sock \
       -- set bridge br0 datapath-type=dummy \
                         other-config:datapath-id=1234 fail-mode=secure], [], [],
-      [m4_if([$1], [dummy-pmd], [--dummy-numa="0,0,0,0,1,1,1,1"], [])])
+      [m4_if([$1], [dummy-pmd], [--dummy-numa="0,0,0,0,8,8,8,8"], [])])
    AT_CHECK([ovs-appctl upcall/disable-ufid], [0], [Datapath dumping tersely using UFID disabled
 ], [])
    AT_CHECK([ovs-appctl vlog/set dpif:dbg dpif_netdev:dbg])
@@ -374,7 +374,7 @@  m4_define([DPIF_NETDEV_FLOW_HW_OFFLOAD],
       set interface p1 type=$1 ofport_request=1 options:pstream=punix:$OVS_RUNDIR/p1.sock options:ifindex=1 -- \
       set bridge br0 datapath-type=dummy \
                      other-config:datapath-id=1234 fail-mode=secure], [], [],
-      [m4_if([$1], [dummy-pmd], [--dummy-numa="0,0,0,0,1,1,1,1"], [])])
+      [m4_if([$1], [dummy-pmd], [--dummy-numa="0,0,0,0,8,8,8,8"], [])])
    AT_CHECK([ovs-appctl vlog/set dpif:file:dbg dpif_netdev:file:dbg netdev_dummy:file:dbg])
 
    AT_CHECK([ovs-vsctl set Open_vSwitch . other_config:hw-offload=true])
@@ -437,7 +437,7 @@  m4_define([DPIF_NETDEV_FLOW_HW_OFFLOAD_OFFSETS],
       set interface p1 type=$1 ofport_request=1 options:pcap=p1.pcap options:ifindex=1 -- \
       set bridge br0 datapath-type=dummy \
                      other-config:datapath-id=1234 fail-mode=secure], [], [],
-      [m4_if([$1], [dummy-pmd], [--dummy-numa="0,0,0,0,1,1,1,1"], [])])
+      [m4_if([$1], [dummy-pmd], [--dummy-numa="0,0,0,0,8,8,8,8"], [])])
    AT_CHECK([ovs-appctl vlog/set dpif:file:dbg dpif_netdev:file:dbg netdev_dummy:file:dbg])
 
    AT_CHECK([ovs-vsctl set Open_vSwitch . other_config:hw-offload=true])
diff --git a/tests/pmd.at b/tests/pmd.at
index 5b612f88f..94e7a0a11 100644
--- a/tests/pmd.at
+++ b/tests/pmd.at
@@ -362,7 +362,7 @@  OVS_VSWITCHD_START(
   [add-port br0 p1 -- set Interface p1 type=dummy-pmd ofport_request=1 options:n_rxq=2 -- \
    add-port br0 p2 -- set Interface p2 type=dummy-pmd ofport_request=2 options:n_rxq=2 -- \
    set Open_vSwitch . other_config:pmd-cpu-mask=3
-], [], [], [--dummy-numa 0,1])
+], [], [], [--dummy-numa 0,8])
 AT_CHECK([ovs-appctl vlog/set dpif:dbg dpif_netdev:dbg])
 
 AT_CHECK([ovs-ofctl add-flow br0 action=controller])
@@ -399,13 +399,13 @@  NXT_PACKET_IN2 (xid=0x0): cookie=0x0 total_len=106 in_port=2 (via action) data_l
 icmp,vlan_tci=0x0000,dl_src=50:54:00:00:00:09,dl_dst=50:54:00:00:00:0a,nw_src=10.0.0.2,nw_dst=10.0.0.1,nw_tos=0,nw_ecn=0,nw_ttl=64,icmp_type=8,icmp_code=0 icmp_csum:13fc
 ])
 
-AT_CHECK([ovs-vsctl set Interface p2 options:numa_id=1])
+AT_CHECK([ovs-vsctl set Interface p2 options:numa_id=8])
 
 AT_CHECK([ovs-appctl dpif-netdev/pmd-rxq-show | parse_pmd_rxq_show], [0], [dnl
 p1 0 0 0
 p1 1 0 0
-p2 0 1 1
-p2 1 1 1
+p2 0 8 1
+p2 1 8 1
 ])
 
 AT_CHECK([ovs-ofctl monitor br0 65534 invalid_ttl --detach --no-chdir --pidfile 2> ofctl_monitor.log])
@@ -584,7 +584,7 @@  AT_CLEANUP
 
 AT_SETUP([PMD - rxq affinity - NUMA])
 OVS_VSWITCHD_START(
-  [], [], [], [--dummy-numa 0,0,0,1,1])
+  [], [], [], [--dummy-numa 0,0,0,8,8])
 AT_CHECK([ovs-appctl vlog/set dpif:dbg dpif_netdev:dbg])
 
 AT_CHECK([ovs-ofctl add-flow br0 actions=controller])
@@ -604,15 +604,15 @@  AT_CHECK([ovs-vsctl set Interface p1 other_config:pmd-rxq-affinity="0:3,1:4"])
 dnl We moved the queues to different numa node. Expecting threads on
 dnl NUMA node 1 to be created.
 AT_CHECK([ovs-appctl dpif-netdev/pmd-rxq-show | parse_pmd_rxq_show], [0], [dnl
-p1 0 1 3
-p1 1 1 4
+p1 0 8 3
+p1 1 8 4
 ])
 
 AT_CHECK([ovs-vsctl set Interface p1 other_config:pmd-rxq-affinity="0:3,1:1"])
 
 dnl Queues splitted between NUMA nodes.
 AT_CHECK([ovs-appctl dpif-netdev/pmd-rxq-show | parse_pmd_rxq_show], [0], [dnl
-p1 0 1 3
+p1 0 8 3
 p1 1 0 1
 ])
 
@@ -628,10 +628,10 @@  p1 1
 
 AT_CHECK([ovs-vsctl set Interface p1 other_config:pmd-rxq-affinity='0:3'])
 
-dnl We explicitly requesting NUMA node 1 for queue 0.
+dnl We explicitly requesting NUMA node 8 for queue 0.
 dnl Queue 1 should be polled by thread from NUMA node 0.
 AT_CHECK([ovs-appctl dpif-netdev/pmd-rxq-show | parse_pmd_rxq_show | cut -f 1,2,3 -d ' '], [0], [dnl
-p1 0 1
+p1 0 8
 p1 1 0
 ])