The external memory functions in DPDK allow the addition of externally
access memory to malloc heaps, but with one major restriction - the
memory must be allocated to an application-created heap, not one of the
standard DPDK heaps for a NUMA node.
This restriction makes it difficult - if not impossible - to use
externally allocated memory for DPDK by default. However, even if the
restriction is relaxed, so we can add external memory to e.g. the socket
0 heap, there would be no way to guarantee that the external memory
would be used in preference to the standard DPDK hugepage memory for a
given allocation.
To give appropriately defined behaviour, a better solution is to allow
the application to explicitly swap a pair of heaps. With this one new
API in place, it allows the user to configure a new malloc heap, add
external memory to it, and then replace a standard socket heap with the
newly created one - thereby guaranteeing future allocations from the
external memory.
Signed-off-by: Bruce Richardson <bruce.richard...@intel.com>
---
lib/eal/common/malloc_heap.c | 24 ++++++++++++++++++++++++
lib/eal/include/rte_malloc.h | 34 ++++++++++++++++++++++++++++++++++
lib/eal/version.map | 2 ++
3 files changed, 60 insertions(+)
diff --git a/lib/eal/common/malloc_heap.c b/lib/eal/common/malloc_heap.c
index 4fa38fcd44..eba75111ca 100644
--- a/lib/eal/common/malloc_heap.c
+++ b/lib/eal/common/malloc_heap.c
@@ -1320,6 +1320,30 @@ malloc_heap_add_external_memory(struct malloc_heap *heap,
return 0;
}
+int
+rte_malloc_heap_swap_socket(int socket1, int socket2)
+{
+ const int h1 = malloc_socket_to_heap_id(socket1);
+ if (h1 < 0 || h1 > RTE_MAX_HEAPS)
+ return -1;
+
+ const int h2 = malloc_socket_to_heap_id(socket2);
+ if (h2 < 0 || h2 > RTE_MAX_HEAPS)
+ return -1;
+
+
+ rte_mcfg_mem_write_lock();
+ do {
+ struct rte_mem_config *mcfg =
rte_eal_get_configuration()->mem_config;
+ int tmp = mcfg->malloc_heaps[h1].socket_id;
+ mcfg->malloc_heaps[h1].socket_id =
mcfg->malloc_heaps[h2].socket_id;
+ mcfg->malloc_heaps[h2].socket_id = tmp;
+ } while (0);
+ rte_mcfg_mem_write_unlock();
+
+ return 0;
+}
+
int
malloc_heap_remove_external_memory(struct malloc_heap *heap, void *va_addr,
size_t len)
diff --git a/lib/eal/include/rte_malloc.h b/lib/eal/include/rte_malloc.h
index 54a8ac211e..df356a5efe 100644
--- a/lib/eal/include/rte_malloc.h
+++ b/lib/eal/include/rte_malloc.h
@@ -490,6 +490,40 @@ rte_malloc_heap_get_socket(const char *name);
int
rte_malloc_heap_socket_is_external(int socket_id);
+/**
+ * Swap the heaps for the given socket ids
+ *
+ * This causes the heaps for the given socket ids to be swapped, allowing
+ * external memory registered as a malloc heap to become the new default memory
+ * for a standard numa node. For example, to have allocations on socket 0 come
+ * from external memory, the following sequence of API calls can be used:
+ * @code
+ * rte_malloc_heap_create(<name>)
+ * rte_malloc_heap_memory_add(<name>,....)
+ * id = rte_malloc_heap_get_socket(<name>)
+ * rte_malloc_heap_swap_socket(0, id)
+ * @endcode
+ *
+ * Following these calls, allocations for the old memory allocated on socket 0,
+ * can be made by passing "id" as the socket_id parameter.
+ *
+ * @note: It is recommended that this function be used only after EAL
initialization,
+ * before any temporary objects are created from the DPDK heaps.
+ * @note: Since any objects allocated using rte_malloc and similar functions,
track
+ * the heaps via pointers, any already-allocated objects will be returned to
their
+ * original heaps, even after a call to this function.
+ *
+ * @param socket1
+ * The socket id of the first heap to swap
+ * @param socket2
+ * The socket id of the second heap to swap
+ * @return
+ * 0 on success, -1 on error
+ */
+__rte_experimental
+int
+rte_malloc_heap_swap_socket(int socket1, int socket2);
+
/**
* Dump statistics.
*
diff --git a/lib/eal/version.map b/lib/eal/version.map
index 7940431e5a..b06ee7219e 100644
--- a/lib/eal/version.map
+++ b/lib/eal/version.map
@@ -417,6 +417,8 @@ EXPERIMENTAL {
# added in 23.07
rte_memzone_max_get;
rte_memzone_max_set;
+
+ rte_malloc_heap_swap_socket;
};
INTERNAL {
--
2.39.2
