Skip to contentSkip to conversation

numa: forbid '-numa node, mem' for 5.1 and newer machine types

PATCH Applied Igor Mammedov 3 participants 4 messages Jun 5, 2020 – Jun 23, 2020

v2 of 5 Applied Latest is v5 →

lore
Share & tools
lore
#0 lore raw

PATCH v2 1/1 numa: forbid '-numa node, mem' for 5.1 and newer machine types

Deprecation period is run out and it's a time to flip the switch introduced by cd5ff8333a. Disable legacy option for new machine types (since 5.1) and amend documentation.

'-numa node,memdev' shall be used instead of disabled option with new machine types.

---
v1:
- rebased on top of current master
- move compat mode from 4.2 to 5.0
v2:
- move deprection text to recently removed section
- pick up reviewed-bys

---
 docs/system/deprecated.rst | 37 ++++++++++++++++++++-----------------
 hw/arm/virt.c              |  2 +-
 hw/core/numa.c             |  6 ++++++
 hw/i386/pc.c               |  1 -
 hw/i386/pc_piix.c          |  1 +
 hw/i386/pc_q35.c           |  1 +
 hw/ppc/spapr.c             |  2 +-
 qemu-options.hx            |  9 +++++----
 8 files changed, 35 insertions(+), 24 deletions(-)
docs/system/deprecated.rst +20 -17
index f0061f94aa..6f717e4a1d 100644
@@ -101,23 +101,6 @@ error in the future.
 The ``-realtime mlock=on|off`` argument has been replaced by the
 ``-overcommit mem-lock=on|off`` argument.
 
-``-numa node,mem=``\ *size* (since 4.1)
-'''''''''''''''''''''''''''''''''''''''
-
-The parameter ``mem`` of ``-numa node`` is used to assign a part of
-guest RAM to a NUMA node. But when using it, it's impossible to manage specified
-RAM chunk on the host side (like bind it to a host node, setting bind policy, ...),
-so guest end-ups with the fake NUMA configuration with suboptiomal performance.
-However since 2014 there is an alternative way to assign RAM to a NUMA node
-using parameter ``memdev``, which does the same as ``mem`` and adds
-means to actualy manage node RAM on the host side. Use parameter ``memdev``
-with *memory-backend-ram* backend as an replacement for parameter ``mem``
-to achieve the same fake NUMA effect or a properly configured
-*memory-backend-file* backend to actually benefit from NUMA configuration.
-In future new machine versions will not accept the option but it will still
-work with old machine types. User can check QAPI schema to see if the legacy
-option is supported by looking at MachineInfo::numa-mem-supported property.
-
 ``-numa`` node (without memory specified) (since 4.1)
 '''''''''''''''''''''''''''''''''''''''''''''''''''''
 
@@ -512,3 +495,23 @@ long starting at 1MiB, the old command::
 can be rewritten as::
 
   qemu-nbd -t --image-opts driver=raw,offset=1M,size=100M,file.driver=qcow2,file.file.driver=file,file.file.filename=file.qcow2
+
+Command line options
+--------------------
+
+``-numa node,mem=``\ *size* (removed in 5.1)
+'''''''''''''''''''''''''''''''''''''''
+
+The parameter ``mem`` of ``-numa node`` is used to assign a part of
+guest RAM to a NUMA node. But when using it, it's impossible to manage specified
+RAM chunk on the host side (like bind it to a host node, setting bind policy, ...),
+so guest end-ups with the fake NUMA configuration with suboptiomal performance.
+However since 2014 there is an alternative way to assign RAM to a NUMA node
+using parameter ``memdev``, which does the same as ``mem`` and adds
+means to actualy manage node RAM on the host side. Use parameter ``memdev``
+with *memory-backend-ram* backend as an replacement for parameter ``mem``
+to achieve the same fake NUMA effect or a properly configured
+*memory-backend-file* backend to actually benefit from NUMA configuration.
+In future new machine versions will not accept the option but it will still
+work with old machine types. User can check QAPI schema to see if the legacy
+option is supported by looking at MachineInfo::numa-mem-supported property.
hw/arm/virt.c +1 -1
index 37462a6f78..063d4703f7 100644
@@ -2262,7 +2262,6 @@ static void virt_machine_class_init(ObjectClass *oc, void *data)
     hc->pre_plug = virt_machine_device_pre_plug_cb;
     hc->plug = virt_machine_device_plug_cb;
     hc->unplug_request = virt_machine_device_unplug_request_cb;
-    mc->numa_mem_supported = true;
     mc->nvdimm_supported = true;
     mc->auto_enable_numa_with_memhp = true;
     mc->default_ram_id = "mach-virt.ram";
@@ -2375,6 +2374,7 @@ DEFINE_VIRT_MACHINE_AS_LATEST(5, 1)
 static void virt_machine_5_0_options(MachineClass *mc)
 {
     virt_machine_5_1_options(mc);
+    mc->numa_mem_supported = true;
 }
 DEFINE_VIRT_MACHINE(5, 0)
 
hw/core/numa.c +6 -0
index 316bc50d75..05be412e59 100644
@@ -117,6 +117,12 @@ static void parse_numa_node(MachineState *ms, NumaNodeOptions *node,
     }
 
     if (node->has_mem) {
+        if (!mc->numa_mem_supported) {
+            error_setg(errp, "Parameter -numa node,mem is not supported by this"
+                      " machine type. Use -numa node,memdev instead");
+            return;
+        }
+
         numa_info[nodenr].node_mem = node->mem;
         if (!qtest_enabled()) {
             warn_report("Parameter -numa node,mem is deprecated,"
hw/i386/pc.c +0 -1
index 2128f3d6fe..a86136069c 100644
@@ -1960,7 +1960,6 @@ static void pc_machine_class_init(ObjectClass *oc, void *data)
     hc->unplug = pc_machine_device_unplug_cb;
     mc->default_cpu_type = TARGET_DEFAULT_CPU_TYPE;
     mc->nvdimm_supported = true;
-    mc->numa_mem_supported = true;
     mc->default_ram_id = "pc.ram";
 
     object_class_property_add(oc, PC_MACHINE_DEVMEM_REGION_SIZE, "int",
hw/i386/pc_piix.c +1 -0
index f66e1d73ce..8955436efa 100644
@@ -438,6 +438,7 @@ static void pc_i440fx_5_0_machine_options(MachineClass *m)
     pc_i440fx_5_1_machine_options(m);
     m->alias = NULL;
     m->is_default = false;
+    m->numa_mem_supported = true;
     compat_props_add(m->compat_props, hw_compat_5_0, hw_compat_5_0_len);
     compat_props_add(m->compat_props, pc_compat_5_0, pc_compat_5_0_len);
 }
hw/i386/pc_q35.c +1 -0
index 4ba8ac8774..af6b32adb7 100644
@@ -366,6 +366,7 @@ static void pc_q35_5_0_machine_options(MachineClass *m)
 {
     pc_q35_5_1_machine_options(m);
     m->alias = NULL;
+    m->numa_mem_supported = true;
     compat_props_add(m->compat_props, hw_compat_5_0, hw_compat_5_0_len);
     compat_props_add(m->compat_props, pc_compat_5_0, pc_compat_5_0_len);
 }
hw/ppc/spapr.c +1 -1
index 3b1a5ed865..210d61d1b3 100644
@@ -4511,7 +4511,6 @@ static void spapr_machine_class_init(ObjectClass *oc, void *data)
      * in which LMBs are represented and hot-added
      */
     mc->numa_mem_align_shift = 28;
-    mc->numa_mem_supported = true;
     mc->auto_enable_numa = true;
 
     smc->default_caps.caps[SPAPR_CAP_HTM] = SPAPR_CAP_OFF;
@@ -4599,6 +4598,7 @@ static void spapr_machine_5_0_class_options(MachineClass *mc)
 {
     spapr_machine_5_1_class_options(mc);
     compat_props_add(mc->compat_props, hw_compat_5_0, hw_compat_5_0_len);
+    mc->numa_mem_supported = true;
 }
 
 DEFINE_SPAPR_MACHINE(5_0, "5.0", false);
qemu-options.hx +5 -4
index 93bde2bbc8..196f468786 100644
@@ -239,10 +239,11 @@ SRST
         -numa node,nodeid=0 -numa node,nodeid=1 \
         -numa cpu,node-id=0,socket-id=0 -numa cpu,node-id=1,socket-id=1
 
-    '\ ``mem``\ ' assigns a given RAM amount to a node. '\ ``memdev``\ '
-    assigns RAM from a given memory backend device to a node. If
-    '\ ``mem``\ ' and '\ ``memdev``\ ' are omitted in all nodes, RAM is
-    split equally between them.
+    Legacy '\ ``mem``\ ' assigns a given RAM amount to a node (not supported
+    for 5.1 and newer machine types). '\ ``memdev``\ ' assigns RAM from
+    a given memory backend device to a node. If '\ ``mem``\ ' and
+    '\ ``memdev``\ ' are omitted in all nodes, RAM is split equally between them.
+
 
     '\ ``mem``\ ' and '\ ``memdev``\ ' are mutually exclusive.
     Furthermore, if one node uses '\ ``memdev``\ ', all of them have to
Signature · 1 line
2.18.4
#1 lore raw
Patchew URL: https://patchew.org/QEMU/[email protected]/

Patchew URL: https://patchew.org/QEMU/[email protected]/

Hi,

This series failed the asan build test. Please find the testing commands and their output below. If you have Docker installed, you can probably reproduce it locally.

=== TEST SCRIPT BEGIN ===
#!/bin/bash
export ARCH=x86_64
make docker-image-fedora V=1 NETWORK=1
time make docker-test-debug@fedora TARGET_LIST=x86_64-softmmu J=14 NETWORK=1 === TEST SCRIPT END ===

CC tools/virtiofsd/helper.o
CC tools/virtiofsd/seccomp.o

Warning, treated as error:
/tmp/qemu-test/src/docs/system/deprecated.rst:507:Title underline too short.

``-numa node,mem=``\ *size* (removed in 5.1)
---
BUNZIP2 pc-bios/edk2-i386-code.fd.bz2
BUNZIP2 pc-bios/edk2-arm-vars.fd.bz2
BUNZIP2 pc-bios/edk2-aarch64-code.fd.bz2
make: *** [Makefile:1114: .docs_system_qemu.1_docs_system_qemu-block-drivers.7_docs_system_qemu-cpu-models.7.sentinel.] Error 2
make: *** Deleting file '.docs_system_qemu.1_docs_system_qemu-block-drivers.7_docs_system_qemu-cpu-models.7.sentinel.'
make: *** Waiting for unfinished jobs....

Warning, treated as error:
/tmp/qemu-test/src/docs/system/deprecated.rst:507:Title underline too short.

``-numa node,mem=``\ *size* (removed in 5.1) '''''''''''''''''''''''''''''''''''''''
make: *** [Makefile:1103: docs/system/index.html] Error 2 Traceback (most recent call last):
File "./tests/docker/docker.py", line 665, in <module>

    sys.exit(main())

---
raise CalledProcessError(retcode, cmd)
subprocess.CalledProcessError: Command '['sudo', '-n', 'docker', 'run', '--label', 'com.qemu.instance.uuid=36f1410148bd4474ae0381f8fbdf93b6', '-u', '1003', '--security-opt', 'seccomp=unconfined', '--rm', '-e', 'TARGET_LIST=x86_64-softmmu', '-e', 'EXTRA_CONFIGURE_OPTS=', '-e', 'V=', '-e', 'J=14', '-e', 'DEBUG=', '-e', 'SHOW_ENV=', '-e', 'CCACHE_DIR=/var/tmp/ccache', '-v', '/home/patchew2/.cache/qemu-docker-ccache:/var/tmp/ccache:z', '-v', '/var/tmp/patchew-tester-tmp-f_yjtmn7/src/docker-src.2020-06-05-10.06.36.18226:/var/tmp/qemu:z,ro', 'qemu:fedora', '/var/tmp/qemu/run', 'test-debug']' returned non-zero exit status 2. filter=--filter=label=com.qemu.instance.uuid=36f1410148bd4474ae0381f8fbdf93b6
make[1]: *** [docker-run] Error 1
make[1]: Leaving directory `/var/tmp/patchew-tester-tmp-f_yjtmn7/src'
make: *** [docker-run-test-debug@fedora] Error 2

real 3m53.414s
user 0m7.982s

The full log is available at
http://patchew.org/logs/[email protected]/testing.asan/?type=message.
---
Email generated automatically by Patchew [https://patchew.org/].
Please send your feedback to [email protected]

#2 lore raw
In reply to Igor Mammedov
Patchew URL: https://patchew.org/QEMU/[email protected]/

Patchew URL: https://patchew.org/QEMU/[email protected]/

Hi,

This series failed the docker-mingw@fedora build test. Please find the testing commands and their output below. If you have Docker installed, you can probably reproduce it locally.

=== TEST SCRIPT BEGIN ===
#! /bin/bash
export ARCH=x86_64
make docker-image-fedora V=1 NETWORK=1
time make docker-test-mingw@fedora J=14 NETWORK=1
=== TEST SCRIPT END ===

CC hw/display/edid-generate.o
CC blockdev.o

Warning, treated as error:
/tmp/qemu-test/src/docs/system/deprecated.rst:507:Title underline too short.

``-numa node,mem=``\ *size* (removed in 5.1)
---
CC job-qmp.o
CC os-win32.o

Warning, treated as error:
/tmp/qemu-test/src/docs/system/deprecated.rst:507:Title underline too short.

``-numa node,mem=``\ *size* (removed in 5.1)
---

  CC      qapi/qapi-commands-crypto.o
  CC      qapi/qapi-commands-introspect.o
  CC      qapi/qapi-commands-job.o

make: *** [Makefile:1114: .docs_system_qemu.1_docs_system_qemu-block-drivers.7_docs_system_qemu-cpu-models.7.sentinel.] Error 2
make: *** Deleting file '.docs_system_qemu.1_docs_system_qemu-block-drivers.7_docs_system_qemu-cpu-models.7.sentinel.'
make: *** Waiting for unfinished jobs....
make: *** [Makefile:1103: docs/system/index.html] Error 2
Traceback (most recent call last):
File "./tests/docker/docker.py", line 665, in <module>

    sys.exit(main())

---
raise CalledProcessError(retcode, cmd)
subprocess.CalledProcessError: Command '['sudo', '-n', 'docker', 'run', '--label', 'com.qemu.instance.uuid=74ef85fd49af466999d8de2438cc0177', '-u', '1003', '--security-opt', 'seccomp=unconfined', '--rm', '-e', 'TARGET_LIST=', '-e', 'EXTRA_CONFIGURE_OPTS=', '-e', 'V=', '-e', 'J=14', '-e', 'DEBUG=', '-e', 'SHOW_ENV=', '-e', 'CCACHE_DIR=/var/tmp/ccache', '-v', '/home/patchew2/.cache/qemu-docker-ccache:/var/tmp/ccache:z', '-v', '/var/tmp/patchew-tester-tmp-mlk2hjle/src/docker-src.2020-06-05-10.11.35.25260:/var/tmp/qemu:z,ro', 'qemu:fedora', '/var/tmp/qemu/run', 'test-mingw']' returned non-zero exit status 2. filter=--filter=label=com.qemu.instance.uuid=74ef85fd49af466999d8de2438cc0177
make[1]: *** [docker-run] Error 1
make[1]: Leaving directory `/var/tmp/patchew-tester-tmp-mlk2hjle/src'
make: *** [docker-run-test-mingw@fedora] Error 2

real 2m22.940s
user 0m8.002s

The full log is available at
http://patchew.org/logs/[email protected]/testing.docker-mingw@fedora/?type=message.
---
Email generated automatically by Patchew [https://patchew.org/].
Please send your feedback to [email protected]

#3 lore raw

Re: [PATCH v2] numa: forbid '-numa node,mem' for 5.1 and newer machine types

In reply to Igor Mammedov
Quoted 195 lines · Igor Mammedov

Deprecation period is run out and it's a time to flip the switch introduced by cd5ff8333a. Disable legacy option for new machine types (since 5.1) and amend documentation.

'-numa node,memdev' shall be used instead of disabled option with new machine types.

---
v1:
- rebased on top of current master
- move compat mode from 4.2 to 5.0
v2:
- move deprection text to recently removed section
- pick up reviewed-bys

---
 docs/system/deprecated.rst | 37 ++++++++++++++++++++-----------------
 hw/arm/virt.c              |  2 +-
 hw/core/numa.c             |  6 ++++++
 hw/i386/pc.c               |  1 -
 hw/i386/pc_piix.c          |  1 +
 hw/i386/pc_q35.c           |  1 +
 hw/ppc/spapr.c             |  2 +-
 qemu-options.hx            |  9 +++++----
 8 files changed, 35 insertions(+), 24 deletions(-)
docs/system/deprecated.rst +20 -17
index f0061f94aa..6f717e4a1d 100644
@@ -101,23 +101,6 @@ error in the future.
 The ``-realtime mlock=on|off`` argument has been replaced by the
 ``-overcommit mem-lock=on|off`` argument.
 
-``-numa node,mem=``\ *size* (since 4.1)
-'''''''''''''''''''''''''''''''''''''''
-
-The parameter ``mem`` of ``-numa node`` is used to assign a part of
-guest RAM to a NUMA node. But when using it, it's impossible to manage specified
-RAM chunk on the host side (like bind it to a host node, setting bind policy, ...),
-so guest end-ups with the fake NUMA configuration with suboptiomal performance.
-However since 2014 there is an alternative way to assign RAM to a NUMA node
-using parameter ``memdev``, which does the same as ``mem`` and adds
-means to actualy manage node RAM on the host side. Use parameter ``memdev``
-with *memory-backend-ram* backend as an replacement for parameter ``mem``
-to achieve the same fake NUMA effect or a properly configured
-*memory-backend-file* backend to actually benefit from NUMA configuration.
-In future new machine versions will not accept the option but it will still
-work with old machine types. User can check QAPI schema to see if the legacy
-option is supported by looking at MachineInfo::numa-mem-supported property.
-
 ``-numa`` node (without memory specified) (since 4.1)
 '''''''''''''''''''''''''''''''''''''''''''''''''''''
 
@@ -512,3 +495,23 @@ long starting at 1MiB, the old command::
 can be rewritten as::
 
   qemu-nbd -t --image-opts driver=raw,offset=1M,size=100M,file.driver=qcow2,file.file.driver=file,file.file.filename=file.qcow2
+
+Command line options
+--------------------
+
+``-numa node,mem=``\ *size* (removed in 5.1)
+'''''''''''''''''''''''''''''''''''''''
+
+The parameter ``mem`` of ``-numa node`` is used to assign a part of
+guest RAM to a NUMA node. But when using it, it's impossible to manage specified
+RAM chunk on the host side (like bind it to a host node, setting bind policy, ...),
+so guest end-ups with the fake NUMA configuration with suboptiomal performance.
+However since 2014 there is an alternative way to assign RAM to a NUMA node
+using parameter ``memdev``, which does the same as ``mem`` and adds
+means to actualy manage node RAM on the host side. Use parameter ``memdev``
+with *memory-backend-ram* backend as an replacement for parameter ``mem``
+to achieve the same fake NUMA effect or a properly configured
+*memory-backend-file* backend to actually benefit from NUMA configuration.
+In future new machine versions will not accept the option but it will still
+work with old machine types. User can check QAPI schema to see if the legacy
+option is supported by looking at MachineInfo::numa-mem-supported property.
hw/arm/virt.c +1 -1
index 37462a6f78..063d4703f7 100644
@@ -2262,7 +2262,6 @@ static void virt_machine_class_init(ObjectClass *oc, void *data)
     hc->pre_plug = virt_machine_device_pre_plug_cb;
     hc->plug = virt_machine_device_plug_cb;
     hc->unplug_request = virt_machine_device_unplug_request_cb;
-    mc->numa_mem_supported = true;
     mc->nvdimm_supported = true;
     mc->auto_enable_numa_with_memhp = true;
     mc->default_ram_id = "mach-virt.ram";
@@ -2375,6 +2374,7 @@ DEFINE_VIRT_MACHINE_AS_LATEST(5, 1)
 static void virt_machine_5_0_options(MachineClass *mc)
 {
     virt_machine_5_1_options(mc);
+    mc->numa_mem_supported = true;
 }
 DEFINE_VIRT_MACHINE(5, 0)
 
hw/core/numa.c +6 -0
index 316bc50d75..05be412e59 100644
@@ -117,6 +117,12 @@ static void parse_numa_node(MachineState *ms, NumaNodeOptions *node,
     }
 
     if (node->has_mem) {
+        if (!mc->numa_mem_supported) {
+            error_setg(errp, "Parameter -numa node,mem is not supported by this"
+                      " machine type. Use -numa node,memdev instead");
+            return;
+        }
+
         numa_info[nodenr].node_mem = node->mem;
         if (!qtest_enabled()) {
             warn_report("Parameter -numa node,mem is deprecated,"
hw/i386/pc.c +0 -1
index 2128f3d6fe..a86136069c 100644
@@ -1960,7 +1960,6 @@ static void pc_machine_class_init(ObjectClass *oc, void *data)
     hc->unplug = pc_machine_device_unplug_cb;
     mc->default_cpu_type = TARGET_DEFAULT_CPU_TYPE;
     mc->nvdimm_supported = true;
-    mc->numa_mem_supported = true;
     mc->default_ram_id = "pc.ram";
 
     object_class_property_add(oc, PC_MACHINE_DEVMEM_REGION_SIZE, "int",
hw/i386/pc_piix.c +1 -0
index f66e1d73ce..8955436efa 100644
@@ -438,6 +438,7 @@ static void pc_i440fx_5_0_machine_options(MachineClass *m)
     pc_i440fx_5_1_machine_options(m);
     m->alias = NULL;
     m->is_default = false;
+    m->numa_mem_supported = true;
     compat_props_add(m->compat_props, hw_compat_5_0, hw_compat_5_0_len);
     compat_props_add(m->compat_props, pc_compat_5_0, pc_compat_5_0_len);
 }
hw/i386/pc_q35.c +1 -0
index 4ba8ac8774..af6b32adb7 100644
@@ -366,6 +366,7 @@ static void pc_q35_5_0_machine_options(MachineClass *m)
 {
     pc_q35_5_1_machine_options(m);
     m->alias = NULL;
+    m->numa_mem_supported = true;
     compat_props_add(m->compat_props, hw_compat_5_0, hw_compat_5_0_len);
     compat_props_add(m->compat_props, pc_compat_5_0, pc_compat_5_0_len);
 }
hw/ppc/spapr.c +1 -1
index 3b1a5ed865..210d61d1b3 100644
@@ -4511,7 +4511,6 @@ static void spapr_machine_class_init(ObjectClass *oc, void *data)
      * in which LMBs are represented and hot-added
      */
     mc->numa_mem_align_shift = 28;
-    mc->numa_mem_supported = true;
     mc->auto_enable_numa = true;
 
     smc->default_caps.caps[SPAPR_CAP_HTM] = SPAPR_CAP_OFF;
@@ -4599,6 +4598,7 @@ static void spapr_machine_5_0_class_options(MachineClass *mc)
 {
     spapr_machine_5_1_class_options(mc);
     compat_props_add(mc->compat_props, hw_compat_5_0, hw_compat_5_0_len);
+    mc->numa_mem_supported = true;
 }
 
 DEFINE_SPAPR_MACHINE(5_0, "5.0", false);
qemu-options.hx +0 -2
index 93bde2bbc8..196f468786 100644
@@ -239,10 +239,11 @@ SRST
         -numa node,nodeid=0 -numa node,nodeid=1 \
         -numa cpu,node-id=0,socket-id=0 -numa cpu,node-id=1,socket-id=1
 
-    '\ ``mem``\ ' assigns a given RAM amount to a node. '\ ``memdev``\ '
-    assigns RAM from a given memory backend device to a node. If

qemu-options.hx SRST · line 249

Quoted 10 lines
qemu-options.hx +5 -2
-    '\ ``mem``\ ' and '\ ``memdev``\ ' are omitted in all nodes, RAM is
-    split equally between them.
+    Legacy '\ ``mem``\ ' assigns a given RAM amount to a node (not supported
+    for 5.1 and newer machine types). '\ ``memdev``\ ' assigns RAM from
+    a given memory backend device to a node. If '\ ``mem``\ ' and
+    '\ ``memdev``\ ' are omitted in all nodes, RAM is split equally between them.
+
 
     '\ ``mem``\ ' and '\ ``memdev``\ ' are mutually exclusive.
     Furthermore, if one node uses '\ ``memdev``\ ', all of them have to

Queued, thanks.

Paolo