[dpdk-dev] [PATCH v2] mem: balanced allocation of hugepages

[Ilya Maximets <i.maximets@samsung.com>]

Currently EAL allocates hugepages one by one not paying
attention from which NUMA node allocation was done.

Such behaviour leads to allocation failure if number of
available hugepages for application limited by cgroups
or hugetlbfs and memory requested not only from the first
socket.

Example:
	# 90 x 1GB hugepages availavle in a system

	cgcreate -g hugetlb:/test
	# Limit to 32GB of hugepages
	cgset -r hugetlb.1GB.limit_in_bytes=34359738368 test
	# Request 4GB from each of 2 sockets
	cgexec -g hugetlb:test testpmd --socket-mem=4096,4096 ...

	EAL: SIGBUS: Cannot mmap more hugepages of size 1024 MB
	EAL: 32 not 90 hugepages of size 1024 MB allocated
	EAL: Not enough memory available on socket 1!
	     Requested: 4096MB, available: 0MB
	PANIC in rte_eal_init():
	Cannot init memory

	This happens beacause all allocated pages are
	on socket 0.

Fix this issue by setting mempolicy MPOL_PREFERRED for each
hugepage to one of requested nodes in a round-robin fashion.
In this case all allocated pages will be fairly distributed
between all requested nodes.

New config option RTE_LIBRTE_EAL_NUMA_AWARE_HUGEPAGES
introduced and disabled by default because of external
dependency from libnuma.

Fixes: 77988fc08dc5 ("mem: fix allocating all free hugepages")

Signed-off-by: Ilya Maximets <i.maximets@samsung.com>
---

Version 2:
	* rebased (fuzz in Makefile)

 config/common_base                       |  1 +
 lib/librte_eal/Makefile                  |  4 ++
 lib/librte_eal/linuxapp/eal/eal_memory.c | 65 ++++++++++++++++++++++++++++++++
 mk/rte.app.mk                            |  3 ++
 4 files changed, 73 insertions(+)

diff --git a/config/common_base b/config/common_base
index 5f2ad94..09782ff 100644
--- a/config/common_base
+++ b/config/common_base
@@ -102,6 +102,7 @@ CONFIG_RTE_EAL_ALWAYS_PANIC_ON_ERROR=n
 CONFIG_RTE_EAL_IGB_UIO=n
 CONFIG_RTE_EAL_VFIO=n
 CONFIG_RTE_MALLOC_DEBUG=n
+CONFIG_RTE_LIBRTE_EAL_NUMA_AWARE_HUGEPAGES=n
 
 # Default driver path (or "" to disable)
 CONFIG_RTE_EAL_PMD_PATH=""
diff --git a/lib/librte_eal/Makefile b/lib/librte_eal/Makefile
index 5690bb4..e5f552a 100644
--- a/lib/librte_eal/Makefile
+++ b/lib/librte_eal/Makefile
@@ -37,4 +37,8 @@ DEPDIRS-linuxapp := common
 DIRS-$(CONFIG_RTE_EXEC_ENV_BSDAPP) += bsdapp
 DEPDIRS-bsdapp := common
 
+ifeq ($(CONFIG_RTE_LIBRTE_EAL_NUMA_AWARE_HUGEPAGES),y)
+LDLIBS += -lnuma
+endif
+
 include $(RTE_SDK)/mk/rte.subdir.mk
diff --git a/lib/librte_eal/linuxapp/eal/eal_memory.c b/lib/librte_eal/linuxapp/eal/eal_memory.c
index 657c6f4..8cb7432 100644
--- a/lib/librte_eal/linuxapp/eal/eal_memory.c
+++ b/lib/librte_eal/linuxapp/eal/eal_memory.c
@@ -83,6 +83,9 @@
 #include <sys/time.h>
 #include <signal.h>
 #include <setjmp.h>
+#ifdef RTE_LIBRTE_EAL_NUMA_AWARE_HUGEPAGES
+#include <numaif.h>
+#endif
 
 #include <rte_log.h>
 #include <rte_memory.h>
@@ -377,6 +380,21 @@ static int huge_wrap_sigsetjmp(void)
 	return sigsetjmp(huge_jmpenv, 1);
 }
 
+#ifdef RTE_LIBRTE_EAL_NUMA_AWARE_HUGEPAGES
+#ifndef ULONG_SIZE
+#define ULONG_SIZE sizeof(unsigned long)
+#endif
+#ifndef ULONG_BITS
+#define ULONG_BITS (ULONG_SIZE * CHAR_BIT)
+#endif
+#ifndef DIV_ROUND_UP
+#define DIV_ROUND_UP(n, d) (((n) + (d) - 1) / (d))
+#endif
+#ifndef BITS_TO_LONGS
+#define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, ULONG_SIZE)
+#endif
+#endif
+
 /*
  * Mmap all hugepages of hugepage table: it first open a file in
  * hugetlbfs, then mmap() hugepage_sz data in it. If orig is set, the
@@ -393,10 +411,48 @@ map_all_hugepages(struct hugepage_file *hugepg_tbl,
 	void *virtaddr;
 	void *vma_addr = NULL;
 	size_t vma_len = 0;
+#ifdef RTE_LIBRTE_EAL_NUMA_AWARE_HUGEPAGES
+	unsigned long nodemask[BITS_TO_LONGS(RTE_MAX_NUMA_NODES)] = {0UL};
+	unsigned long maxnode = 0;
+	int node_id = -1;
+
+	for (i = 0; i < RTE_MAX_NUMA_NODES; i++)
+		if (internal_config.socket_mem[i])
+			maxnode = i + 1;
+#endif
 
 	for (i = 0; i < hpi->num_pages[0]; i++) {
 		uint64_t hugepage_sz = hpi->hugepage_sz;
 
+#ifdef RTE_LIBRTE_EAL_NUMA_AWARE_HUGEPAGES
+		if (maxnode) {
+			node_id = (node_id + 1) % RTE_MAX_NUMA_NODES;
+			while (!internal_config.socket_mem[node_id])
+				node_id = (node_id + 1) % RTE_MAX_NUMA_NODES;
+
+			nodemask[node_id / ULONG_BITS] =
+						1UL << (node_id % ULONG_BITS);
+
+			RTE_LOG(DEBUG, EAL,
+				"Setting policy MPOL_PREFERRED for socket %d\n",
+				node_id);
+			/*
+			 * Due to old linux kernel bug (feature?) we have to
+			 * increase maxnode by 1. It will be unconditionally
+			 * decreased back to normal value inside the syscall
+			 * handler.
+			 */
+			if (set_mempolicy(MPOL_PREFERRED,
+					  nodemask, maxnode + 1) < 0) {
+				RTE_LOG(ERR, EAL,
+					"Failed to set policy MPOL_PREFERRED: "
+					"%s\n", strerror(errno));
+				return i;
+			}
+
+			nodemask[node_id / ULONG_BITS] = 0UL;
+		}
+#endif
 		if (orig) {
 			hugepg_tbl[i].file_id = i;
 			hugepg_tbl[i].size = hugepage_sz;
@@ -507,6 +563,10 @@ map_all_hugepages(struct hugepage_file *hugepg_tbl,
 		vma_len -= hugepage_sz;
 	}
 
+#ifdef RTE_LIBRTE_EAL_NUMA_AWARE_HUGEPAGES
+	if (maxnode && set_mempolicy(MPOL_DEFAULT, NULL, 0) < 0)
+		RTE_LOG(ERR, EAL, "Failed to set mempolicy MPOL_DEFAULT\n");
+#endif
 	return i;
 }
 
@@ -591,6 +651,11 @@ find_numasocket(struct hugepage_file *hugepg_tbl, struct hugepage_info *hpi)
 			if (hugepg_tbl[i].orig_va == va) {
 				hugepg_tbl[i].socket_id = socket_id;
 				hp_count++;
+#ifdef RTE_LIBRTE_EAL_NUMA_AWARE_HUGEPAGES
+				RTE_LOG(DEBUG, EAL,
+					"Hugepage %s is on socket %d\n",
+					hugepg_tbl[i].filepath, socket_id);
+#endif
 			}
 		}
 	}
diff --git a/mk/rte.app.mk b/mk/rte.app.mk
index 4c659e9..ca8e5fe 100644
--- a/mk/rte.app.mk
+++ b/mk/rte.app.mk
@@ -173,6 +173,9 @@ ifeq ($(CONFIG_RTE_BUILD_SHARED_LIB),n)
 # The static libraries do not know their dependencies.
 # So linking with static library requires explicit dependencies.
 _LDLIBS-$(CONFIG_RTE_LIBRTE_EAL)            += -lrt
+ifeq ($(CONFIG_RTE_LIBRTE_EAL_NUMA_AWARE_HUGEPAGES),y)
+_LDLIBS-$(CONFIG_RTE_LIBRTE_EAL)            += -lnuma
+endif
 _LDLIBS-$(CONFIG_RTE_LIBRTE_SCHED)          += -lm
 _LDLIBS-$(CONFIG_RTE_LIBRTE_SCHED)          += -lrt
 _LDLIBS-$(CONFIG_RTE_LIBRTE_METER)          += -lm
-- 
2.7.4