From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mailout3.w1.samsung.com (mailout3.w1.samsung.com [210.118.77.13]) by dpdk.org (Postfix) with ESMTP id 78B42378E for ; Thu, 29 Jun 2017 07:59:36 +0200 (CEST) Received: from eucas1p1.samsung.com (unknown [182.198.249.206]) by mailout3.w1.samsung.com (Oracle Communications Messaging Server 7.0.5.31.0 64bit (built May 5 2014)) with ESMTP id <0OSA006I9ONBEG70@mailout3.w1.samsung.com> for dev@dpdk.org; Thu, 29 Jun 2017 06:59:35 +0100 (BST) Received: from eusmges5.samsung.com (unknown [203.254.199.245]) by eucas1p2.samsung.com (KnoxPortal) with ESMTP id 20170629055934eucas1p230c9d3e8585626ae6661e3944506f3d1~MgjzwXJi92346623466eucas1p2Y; Thu, 29 Jun 2017 05:59:34 +0000 (GMT) Received: from eucas1p1.samsung.com ( [182.198.249.206]) by eusmges5.samsung.com (EUCPMTA) with SMTP id 94.28.25577.54794595; Thu, 29 Jun 2017 06:59:33 +0100 (BST) Received: from eusmgms2.samsung.com (unknown [182.198.249.180]) by eucas1p1.samsung.com (KnoxPortal) with ESMTP id 20170629055933eucas1p1e5eba5f07850f63f9afbd48e6ca64c42~Mgjy90sf12838328383eucas1p16; Thu, 29 Jun 2017 05:59:33 +0000 (GMT) X-AuditID: cbfec7f5-f792f6d0000063e9-5a-59549745b98a Received: from eusync4.samsung.com ( [203.254.199.214]) by eusmgms2.samsung.com (EUCPMTA) with SMTP id 49.94.20206.54794595; Thu, 29 Jun 2017 06:59:33 +0100 (BST) Received: from imaximets.rnd.samsung.ru ([106.109.129.180]) by eusync4.samsung.com (Oracle Communications Messaging Server 7.0.5.31.0 64bit (built May 5 2014)) with ESMTPA id <0OSA0003ION05H20@eusync4.samsung.com>; Thu, 29 Jun 2017 06:59:33 +0100 (BST) From: Ilya Maximets To: dev@dpdk.org, David Marchand , Sergio Gonzalez Monroy , Thomas Monjalon Cc: Heetae Ahn , Yuanhan Liu , Jianfeng Tan , Neil Horman , Yulong Pei , Bruce Richardson , Jerin Jacob , Hemant Agrawal , Ilya Maximets Date: Thu, 29 Jun 2017 08:59:19 +0300 Message-id: <1498715960-2668-2-git-send-email-i.maximets@samsung.com> X-Mailer: git-send-email 2.7.4 In-reply-to: <1498715960-2668-1-git-send-email-i.maximets@samsung.com> X-Brightmail-Tracker: H4sIAAAAAAAAA+NgFvrLIsWRmVeSWpSXmKPExsWy7djPc7qu00MiDXZ9tra4screYkVHO4vF u0/bmSymfb7NbrHy8UY2iyvtP9ktJk4yseie/YXN4lbzSTaLFROOMFp8enCCxaJlyU4mi28P vjM78Hpc7L/D6LHhRD+rx68FS1k9bvy7xeaxeM9LJo9jN6exe2x8t4PJo2/LKkaPK99XMwZw RnHZpKTmZJalFunbJXBlfGm6zlhwKbKi6fhe1gbGW+5djJwcEgImEicXbmCBsMUkLtxbz9bF yMUhJLCUUWLDm4esEM5nRommqyfYYToOLVvADJFYxigx6cZLdginmUli76XdrCBVbAI6EqdW H2EESYgILGSUaPx5ghkkwSzwhUmi41g4iC0sYCfR9Oo4G4jNIqAq8fL1JEYQm1fAVeL29QlQ 6+Qkbp7rBOvlFHCT+LJkHQvIUAmBfewSxy4/AmrgAHJkJTYdYIaod5F4eauPDcIWlnh1fAvU HBmJy5O7oXqbGSUaVl1ihHAmMEp8aV7OBFFlL3Hq5lUmiEv5JCZtm84MsYBXoqNNCKLEQ2La 1DaockeJjXMfQ71/jVFixYe3TBMYZRYwMqxiFEktLc5NTy021StOzC0uzUvXS87P3cQITBSn /x3/uoNx6TGrQ4wCHIxKPLwMa4MjhVgTy4orcw8xSnAwK4nwujeERArxpiRWVqUW5ccXleak Fh9ilOZgURLn5Tp1LUJIID2xJDU7NbUgtQgmy8TBKdXAWNgXH+EbWhjjunb/q5NPAqWm1y/Y /Dzjw82Hi4tdFZ2nGE6fs4eDn/dvSPf+PrYAJWPG6Crtt8mqKzTuHKw5YLvrspjGWZMOg/jn AlUT7hudZmY2Cfp74o+YGl/mNDv3eYwtxmZL9kmkCb/7dHlPpVRIf9WOCNeIVWk66z1W7rm8 pbnZWHKbEktxRqKhFnNRcSIAIjOY2xADAAA= X-Brightmail-Tracker: H4sIAAAAAAAAA+NgFprNIsWRmVeSWpSXmKPExsVy+t/xa7qu00MiDWbe4LC4screYkVHO4vF u0/bmSymfb7NbrHy8UY2iyvtP9ktJk4yseie/YXN4lbzSTaLFROOMFp8enCCxaJlyU4mi28P vjM78Hpc7L/D6LHhRD+rx68FS1k9bvy7xeaxeM9LJo9jN6exe2x8t4PJo2/LKkaPK99XMwZw RrnZZKQmpqQWKaTmJeenZOal2yqFhrjpWigp5CXmptoqRej6hgQpKZQl5pQCeUYGaMDBOcA9 WEnfLsEt40vTdcaCS5EVTcf3sjYw3nLvYuTkkBAwkTi0bAEzhC0mceHeerYuRi4OIYEljBKn XswDSwgJtDJJrJmUAGKzCehInFp9hBGkSERgIaPEhdVfmEEcZoEvTBJ7XuxmBakSFrCTaHp1 nA3EZhFQlXj5ehIjiM0r4Cpx+/oEdoh1chI3z3WCbeAUcJP4smQdC8S2JkaJqXNdJjDyLmBk WMUoklpanJueW2ykV5yYW1yal66XnJ+7iREYMduO/dyyg7HrXfAhRgEORiUeXoa1wZFCrIll xZW5hxglOJiVRHjdG0IihXhTEiurUovy44tKc1KLDzGaAh01kVlKNDkfGM15JfGGJobmloZG xhYW5kZGSuK8Uz9cCRcSSE8sSc1OTS1ILYLpY+LglGpg1D98L1+R80t88pWoap61tlNT/GR+ 8K9ce+7R4uPzXvx6s/euGHfFlFsHjThi+EVa709XdbxRIZDi8Pj9vD/ZJ/WbgnjrX2512Mj0 jnP3vU0tqd8Ze0/k1yyfN6EpUFePydt2xU++n7IRXjydd+pX2nGe3F6hvsZZqNOiIyppi8ZN L4eWBeuVlFiKMxINtZiLihMBq/pTJK4CAAA= X-MTR: 20000000000000000@CPGS X-CMS-MailID: 20170629055933eucas1p1e5eba5f07850f63f9afbd48e6ca64c42 X-Msg-Generator: CA X-Sender-IP: 182.198.249.180 X-Local-Sender: =?UTF-8?B?SWx5YSBNYXhpbWV0cxtTUlItVmlydHVhbGl6YXRpb24gTGFi?= =?UTF-8?B?G+yCvOyEseyghOyekBtMZWFkaW5nIEVuZ2luZWVy?= X-Global-Sender: =?UTF-8?B?SWx5YSBNYXhpbWV0cxtTUlItVmlydHVhbGl6YXRpb24gTGFi?= =?UTF-8?B?G1NhbXN1bmcgRWxlY3Ryb25pY3MbTGVhZGluZyBFbmdpbmVlcg==?= X-Sender-Code: =?UTF-8?B?QzEwG0NJU0hRG0MxMEdEMDFHRDAxMDE1NA==?= CMS-TYPE: 201P X-HopCount: 7 X-CMS-RootMailID: 20170629055933eucas1p1e5eba5f07850f63f9afbd48e6ca64c42 X-RootMTR: 20170629055933eucas1p1e5eba5f07850f63f9afbd48e6ca64c42 References: <1498559080-27331-1-git-send-email-i.maximets@samsung.com> <1498715960-2668-1-git-send-email-i.maximets@samsung.com> Subject: [dpdk-dev] [PATCH v10 1/2] mem: balanced allocation of hugepages X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 29 Jun 2017 05:59:36 -0000 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 using following schema: 1) Allocate essential hugepages: 1.1) Allocate as many hugepages from numa N to only fit requested memory for this numa. 1.2) repeat 1.1 for all numa nodes. 2) Try to map all remaining free hugepages in a round-robin fashion. 3) Sort pages and choose the most suitable. In this case all essential memory will be allocated and all remaining pages will be fairly distributed between all requested nodes. New config option RTE_EAL_NUMA_AWARE_HUGEPAGES introduced and enabled by default for linuxapp except armv7 and dpaa2. Enabling of this option adds libnuma as a dependency for EAL. Fixes: 77988fc08dc5 ("mem: fix allocating all free hugepages") Signed-off-by: Ilya Maximets Acked-by: Sergio Gonzalez Monroy --- config/common_base | 1 + config/common_linuxapp | 1 + config/defconfig_arm-armv7a-linuxapp-gcc | 3 + config/defconfig_arm64-dpaa2-linuxapp-gcc | 3 + lib/librte_eal/linuxapp/eal/Makefile | 3 + lib/librte_eal/linuxapp/eal/eal_memory.c | 120 ++++++++++++++++++++++++++++-- mk/rte.app.mk | 3 + 7 files changed, 126 insertions(+), 8 deletions(-) diff --git a/config/common_base b/config/common_base index f6aafd1..660588a 100644 --- a/config/common_base +++ b/config/common_base @@ -103,6 +103,7 @@ 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_EAL_NUMA_AWARE_HUGEPAGES=n # # Recognize/ignore the AVX/AVX512 CPU flags for performance/power testing. diff --git a/config/common_linuxapp b/config/common_linuxapp index b3cf41b..64bef87 100644 --- a/config/common_linuxapp +++ b/config/common_linuxapp @@ -35,6 +35,7 @@ CONFIG_RTE_EXEC_ENV="linuxapp" CONFIG_RTE_EXEC_ENV_LINUXAPP=y +CONFIG_RTE_EAL_NUMA_AWARE_HUGEPAGES=y CONFIG_RTE_EAL_IGB_UIO=y CONFIG_RTE_EAL_VFIO=y CONFIG_RTE_KNI_KMOD=y diff --git a/config/defconfig_arm-armv7a-linuxapp-gcc b/config/defconfig_arm-armv7a-linuxapp-gcc index 19607eb..e06b1d4 100644 --- a/config/defconfig_arm-armv7a-linuxapp-gcc +++ b/config/defconfig_arm-armv7a-linuxapp-gcc @@ -47,6 +47,9 @@ CONFIG_RTE_ARCH_STRICT_ALIGN=y CONFIG_RTE_TOOLCHAIN="gcc" CONFIG_RTE_TOOLCHAIN_GCC=y +# NUMA is not supported on ARM +CONFIG_RTE_EAL_NUMA_AWARE_HUGEPAGES=n + # ARM doesn't have support for vmware TSC map CONFIG_RTE_LIBRTE_EAL_VMWARE_TSC_MAP_SUPPORT=n diff --git a/config/defconfig_arm64-dpaa2-linuxapp-gcc b/config/defconfig_arm64-dpaa2-linuxapp-gcc index 2304ab6..f78449d 100644 --- a/config/defconfig_arm64-dpaa2-linuxapp-gcc +++ b/config/defconfig_arm64-dpaa2-linuxapp-gcc @@ -45,6 +45,9 @@ CONFIG_RTE_CACHE_LINE_SIZE=64 CONFIG_RTE_PKTMBUF_HEADROOM=256 +# Doesn't support NUMA +CONFIG_RTE_EAL_NUMA_AWARE_HUGEPAGES=n + # # Compile Support Libraries for DPAA2 # diff --git a/lib/librte_eal/linuxapp/eal/Makefile b/lib/librte_eal/linuxapp/eal/Makefile index 640afd0..8651e27 100644 --- a/lib/librte_eal/linuxapp/eal/Makefile +++ b/lib/librte_eal/linuxapp/eal/Makefile @@ -50,6 +50,9 @@ LDLIBS += -ldl LDLIBS += -lpthread LDLIBS += -lgcc_s LDLIBS += -lrt +ifeq ($(CONFIG_RTE_EAL_NUMA_AWARE_HUGEPAGES),y) +LDLIBS += -lnuma +endif # specific to linuxapp exec-env SRCS-$(CONFIG_RTE_EXEC_ENV_LINUXAPP) := eal.c diff --git a/lib/librte_eal/linuxapp/eal/eal_memory.c b/lib/librte_eal/linuxapp/eal/eal_memory.c index e17c9cb..647d89c 100644 --- a/lib/librte_eal/linuxapp/eal/eal_memory.c +++ b/lib/librte_eal/linuxapp/eal/eal_memory.c @@ -54,6 +54,10 @@ #include #include #include +#ifdef RTE_EAL_NUMA_AWARE_HUGEPAGES +#include +#include +#endif #include #include @@ -348,6 +352,14 @@ static int huge_wrap_sigsetjmp(void) return sigsetjmp(huge_jmpenv, 1); } +#ifdef RTE_EAL_NUMA_AWARE_HUGEPAGES +/* Callback for numa library. */ +void numa_error(char *where) +{ + RTE_LOG(ERR, EAL, "%s failed: %s\n", where, strerror(errno)); +} +#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 @@ -356,18 +368,78 @@ static int huge_wrap_sigsetjmp(void) * map continguous physical blocks in contiguous virtual blocks. */ static unsigned -map_all_hugepages(struct hugepage_file *hugepg_tbl, - struct hugepage_info *hpi, int orig) +map_all_hugepages(struct hugepage_file *hugepg_tbl, struct hugepage_info *hpi, + uint64_t *essential_memory __rte_unused, int orig) { int fd; unsigned i; void *virtaddr; void *vma_addr = NULL; size_t vma_len = 0; +#ifdef RTE_EAL_NUMA_AWARE_HUGEPAGES + int node_id = -1; + int essential_prev = 0; + int oldpolicy; + struct bitmask *oldmask = numa_allocate_nodemask(); + bool have_numa = true; + unsigned long maxnode = 0; + + /* Check if kernel supports NUMA. */ + if (numa_available() != 0) { + RTE_LOG(DEBUG, EAL, "NUMA is not supported.\n"); + have_numa = false; + } + + if (orig && have_numa) { + RTE_LOG(DEBUG, EAL, "Trying to obtain current memory policy.\n"); + if (get_mempolicy(&oldpolicy, oldmask->maskp, + oldmask->size + 1, 0, 0) < 0) { + RTE_LOG(ERR, EAL, + "Failed to get current mempolicy: %s. " + "Assuming MPOL_DEFAULT.\n", strerror(errno)); + oldpolicy = MPOL_DEFAULT; + } + 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_EAL_NUMA_AWARE_HUGEPAGES + if (maxnode) { + unsigned int j; + + for (j = 0; j < maxnode; j++) + if (essential_memory[j]) + break; + + if (j == maxnode) { + node_id = (node_id + 1) % maxnode; + while (!internal_config.socket_mem[node_id]) { + node_id++; + node_id %= maxnode; + } + essential_prev = 0; + } else { + node_id = j; + essential_prev = essential_memory[j]; + + if (essential_memory[j] < hugepage_sz) + essential_memory[j] = 0; + else + essential_memory[j] -= hugepage_sz; + } + + RTE_LOG(DEBUG, EAL, + "Setting policy MPOL_PREFERRED for socket %d\n", + node_id); + numa_set_preferred(node_id); + } +#endif + if (orig) { hugepg_tbl[i].file_id = i; hugepg_tbl[i].size = hugepage_sz; @@ -422,7 +494,7 @@ map_all_hugepages(struct hugepage_file *hugepg_tbl, if (fd < 0) { RTE_LOG(DEBUG, EAL, "%s(): open failed: %s\n", __func__, strerror(errno)); - return i; + goto out; } /* map the segment, and populate page tables, @@ -433,7 +505,7 @@ map_all_hugepages(struct hugepage_file *hugepg_tbl, RTE_LOG(DEBUG, EAL, "%s(): mmap failed: %s\n", __func__, strerror(errno)); close(fd); - return i; + goto out; } if (orig) { @@ -458,7 +530,12 @@ map_all_hugepages(struct hugepage_file *hugepg_tbl, munmap(virtaddr, hugepage_sz); close(fd); unlink(hugepg_tbl[i].filepath); - return i; +#ifdef RTE_EAL_NUMA_AWARE_HUGEPAGES + if (maxnode) + essential_memory[node_id] = + essential_prev; +#endif + goto out; } *(int *)virtaddr = 0; } @@ -469,7 +546,7 @@ map_all_hugepages(struct hugepage_file *hugepg_tbl, RTE_LOG(DEBUG, EAL, "%s(): Locking file failed:%s \n", __func__, strerror(errno)); close(fd); - return i; + goto out; } close(fd); @@ -478,6 +555,22 @@ map_all_hugepages(struct hugepage_file *hugepg_tbl, vma_len -= hugepage_sz; } +out: +#ifdef RTE_EAL_NUMA_AWARE_HUGEPAGES + if (maxnode) { + RTE_LOG(DEBUG, EAL, + "Restoring previous memory policy: %d\n", oldpolicy); + if (oldpolicy == MPOL_DEFAULT) { + numa_set_localalloc(); + } else if (set_mempolicy(oldpolicy, oldmask->maskp, + oldmask->size + 1) < 0) { + RTE_LOG(ERR, EAL, "Failed to restore mempolicy: %s\n", + strerror(errno)); + numa_set_localalloc(); + } + } + numa_free_cpumask(oldmask); +#endif return i; } @@ -562,6 +655,11 @@ 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_EAL_NUMA_AWARE_HUGEPAGES + RTE_LOG(DEBUG, EAL, + "Hugepage %s is on socket %d\n", + hugepg_tbl[i].filepath, socket_id); +#endif } } } @@ -1000,6 +1098,11 @@ rte_eal_hugepage_init(void) huge_register_sigbus(); + /* make a copy of socket_mem, needed for balanced allocation. */ + for (i = 0; i < RTE_MAX_NUMA_NODES; i++) + memory[i] = internal_config.socket_mem[i]; + + /* map all hugepages and sort them */ for (i = 0; i < (int)internal_config.num_hugepage_sizes; i ++){ unsigned pages_old, pages_new; @@ -1017,7 +1120,8 @@ rte_eal_hugepage_init(void) /* map all hugepages available */ pages_old = hpi->num_pages[0]; - pages_new = map_all_hugepages(&tmp_hp[hp_offset], hpi, 1); + pages_new = map_all_hugepages(&tmp_hp[hp_offset], hpi, + memory, 1); if (pages_new < pages_old) { RTE_LOG(DEBUG, EAL, "%d not %d hugepages of size %u MB allocated\n", @@ -1060,7 +1164,7 @@ rte_eal_hugepage_init(void) sizeof(struct hugepage_file), cmp_physaddr); /* remap all hugepages */ - if (map_all_hugepages(&tmp_hp[hp_offset], hpi, 0) != + if (map_all_hugepages(&tmp_hp[hp_offset], hpi, NULL, 0) != hpi->num_pages[0]) { RTE_LOG(ERR, EAL, "Failed to remap %u MB pages\n", (unsigned)(hpi->hugepage_sz / 0x100000)); diff --git a/mk/rte.app.mk b/mk/rte.app.mk index bcaf1b3..4fe22d1 100644 --- a/mk/rte.app.mk +++ b/mk/rte.app.mk @@ -186,6 +186,9 @@ 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 ($(CONFIG_RTE_EXEC_ENV_LINUXAPP)$(CONFIG_RTE_EAL_NUMA_AWARE_HUGEPAGES),yy) +_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