[RFC,6/7] hostmem: Allow for specifying a ThreadContext for preallocation

Commit Message

David Hildenbrand July 21, 2022, 12:07 p.m. UTC

Let's allow for specifying a thread context via the "prealloc-context"
property. When set, preallcoation threads will be crated via the
thread context -- inheriting the same CPU affinity as the thread
context.

Pinning preallcoation threads to CPUs can heavily increase performance
in NUMA setups, because, preallocation from a CPU close to the target
NUMA node(s) is faster then preallocation from a CPU further remote,
simply because of memory bandwidth for initializing memory with zeroes.
This is especially relevant for very large VMs backed by huge/gigantic
pages, whereby preallocation is mandatory.

Signed-off-by: David Hildenbrand <[e-mail]>
---
 backends/hostmem.c       | 12 +++++++++---
 include/sysemu/hostmem.h |  2 ++
 qapi/qom.json            |  4 ++++
 3 files changed, 15 insertions(+), 3 deletions(-)

Patch

diff --git a/backends/hostmem.c b/backends/hostmem.c
index 46bd4cc494..5e730fd7c0 100644
--- a/backends/hostmem.c
+++ b/backends/hostmem.c
@@ -232,8 +232,8 @@  static void host_memory_backend_set_prealloc(Object *obj, bool value,
         void *ptr = memory_region_get_ram_ptr(&backend->mr);
         uint64_t sz = memory_region_size(&backend->mr);
 
-        qemu_prealloc_mem(fd, ptr, sz, backend->prealloc_threads, NULL,
-                          &local_err);
+        qemu_prealloc_mem(fd, ptr, sz, backend->prealloc_threads,
+                          backend->prealloc_context, &local_err);
         if (local_err) {
             error_propagate(errp, local_err);
             return;
@@ -395,7 +395,8 @@  host_memory_backend_memory_complete(UserCreatable *uc, Error **errp)
          */
         if (backend->prealloc) {
             qemu_prealloc_mem(memory_region_get_fd(&backend->mr), ptr, sz,
-                              backend->prealloc_threads, NULL, &local_err);
+                              backend->prealloc_threads,
+                              backend->prealloc_context, &local_err);
             if (local_err) {
                 goto out;
             }
@@ -503,6 +504,11 @@  host_memory_backend_class_init(ObjectClass *oc, void *data)
         NULL, NULL);
     object_class_property_set_description(oc, "prealloc-threads",
         "Number of CPU threads to use for prealloc");
+    object_class_property_add_link(oc, "prealloc-context",
+        TYPE_THREAD_CONTEXT, offsetof(HostMemoryBackend, prealloc_context),
+        object_property_allow_set_link, OBJ_PROP_LINK_STRONG);
+    object_class_property_set_description(oc, "prealloc-context",
+        "Context to use for creating CPU threads for preallocation");
     object_class_property_add(oc, "size", "int",
         host_memory_backend_get_size,
         host_memory_backend_set_size,
diff --git a/include/sysemu/hostmem.h b/include/sysemu/hostmem.h
index 9ff5c16963..39326f1d4f 100644
--- a/include/sysemu/hostmem.h
+++ b/include/sysemu/hostmem.h
@@ -18,6 +18,7 @@ 
 #include "qom/object.h"
 #include "exec/memory.h"
 #include "qemu/bitmap.h"
+#include "qemu/thread-context.h"
 
 #define TYPE_MEMORY_BACKEND "memory-backend"
 OBJECT_DECLARE_TYPE(HostMemoryBackend, HostMemoryBackendClass,
@@ -66,6 +67,7 @@  struct HostMemoryBackend {
     bool merge, dump, use_canonical_path;
     bool prealloc, is_mapped, share, reserve;
     uint32_t prealloc_threads;
+    ThreadContext *prealloc_context;
     DECLARE_BITMAP(host_nodes, MAX_NODES + 1);
     HostMemPolicy policy;
 
diff --git a/qapi/qom.json b/qapi/qom.json
index d36bf3355f..9caa1a60e3 100644
--- a/qapi/qom.json
+++ b/qapi/qom.json
@@ -578,6 +578,9 @@ 
 #
 # @prealloc-threads: number of CPU threads to use for prealloc (default: 1)
 #
+# @prealloc-context: context to use for creation of preallocation threads
+#                    (default: none) (since 7.2)
+#
 # @share: if false, the memory is private to QEMU; if true, it is shared
 #         (default: false)
 #
@@ -608,6 +611,7 @@ 
             '*policy': 'HostMemPolicy',
             '*prealloc': 'bool',
             '*prealloc-threads': 'uint32',
+            '*prealloc-context': 'str',
             '*share': 'bool',
             '*reserve': 'bool',
             'size': 'size',