memseg_primary_init(void)
{
struct rte_mem_config *mcfg = rte_eal_get_configuration()->mem_config;
- int i, socket_id, hpi_idx, msl_idx = 0;
+ struct memtype {
+ uint64_t page_sz;
+ int socket_id;
+ } *memtypes = NULL;
+ int i, hpi_idx, msl_idx;
struct rte_memseg_list *msl;
- uint64_t max_mem, total_mem;
+ uint64_t max_mem, max_mem_per_type;
+ unsigned int max_seglists_per_type;
+ unsigned int n_memtypes, cur_type;
/* no-huge does not need this at all */
if (internal_config.no_hugetlbfs)
return 0;
- max_mem = (uint64_t)RTE_MAX_MEM_MB << 20;
- total_mem = 0;
+ /*
+ * figuring out amount of memory we're going to have is a long and very
+ * involved process. the basic element we're operating with is a memory
+ * type, defined as a combination of NUMA node ID and page size (so that
+ * e.g. 2 sockets with 2 page sizes yield 4 memory types in total).
+ *
+ * deciding amount of memory going towards each memory type is a
+ * balancing act between maximum segments per type, maximum memory per
+ * type, and number of detected NUMA nodes. the goal is to make sure
+ * each memory type gets at least one memseg list.
+ *
+ * the total amount of memory is limited by RTE_MAX_MEM_MB value.
+ *
+ * the total amount of memory per type is limited by either
+ * RTE_MAX_MEM_MB_PER_TYPE, or by RTE_MAX_MEM_MB divided by the number
+ * of detected NUMA nodes. additionally, maximum number of segments per
+ * type is also limited by RTE_MAX_MEMSEG_PER_TYPE. this is because for
+ * smaller page sizes, it can take hundreds of thousands of segments to
+ * reach the above specified per-type memory limits.
+ *
+ * additionally, each type may have multiple memseg lists associated
+ * with it, each limited by either RTE_MAX_MEM_MB_PER_LIST for bigger
+ * page sizes, or RTE_MAX_MEMSEG_PER_LIST segments for smaller ones.
+ *
+ * the number of memseg lists per type is decided based on the above
+ * limits, and also taking number of detected NUMA nodes, to make sure
+ * that we don't run out of memseg lists before we populate all NUMA
+ * nodes with memory.
+ *
+ * we do this in three stages. first, we collect the number of types.
+ * then, we figure out memory constraints and populate the list of
+ * would-be memseg lists. then, we go ahead and allocate the memseg
+ * lists.
+ */
- /* create memseg lists */
+ /* create space for mem types */
+ n_memtypes = internal_config.num_hugepage_sizes * rte_socket_count();
+ memtypes = calloc(n_memtypes, sizeof(*memtypes));
+ if (memtypes == NULL) {
+ RTE_LOG(ERR, EAL, "Cannot allocate space for memory types\n");
+ return -1;
+ }
+
+ /* populate mem types */
+ cur_type = 0;
for (hpi_idx = 0; hpi_idx < (int) internal_config.num_hugepage_sizes;
hpi_idx++) {
struct hugepage_info *hpi;
hpi = &internal_config.hugepage_info[hpi_idx];
hugepage_sz = hpi->hugepage_sz;
- for (i = 0; i < (int) rte_socket_count(); i++) {
- uint64_t max_type_mem, total_type_mem = 0;
- int type_msl_idx, max_segs, total_segs = 0;
-
- socket_id = rte_socket_id_by_idx(i);
+ for (i = 0; i < (int) rte_socket_count(); i++, cur_type++) {
+ int socket_id = rte_socket_id_by_idx(i);
#ifndef RTE_EAL_NUMA_AWARE_HUGEPAGES
if (socket_id > 0)
break;
#endif
+ memtypes[cur_type].page_sz = hugepage_sz;
+ memtypes[cur_type].socket_id = socket_id;
- if (total_mem >= max_mem)
- break;
-
- max_type_mem = RTE_MIN(max_mem - total_mem,
- (uint64_t)RTE_MAX_MEM_MB_PER_TYPE << 20);
- max_segs = RTE_MAX_MEMSEG_PER_TYPE;
+ RTE_LOG(DEBUG, EAL, "Detected memory type: "
+ "socket_id:%u hugepage_sz:%" PRIu64 "\n",
+ socket_id, hugepage_sz);
+ }
+ }
- type_msl_idx = 0;
- while (total_type_mem < max_type_mem &&
- total_segs < max_segs) {
- uint64_t cur_max_mem, cur_mem;
- unsigned int n_segs;
+ /* set up limits for types */
+ max_mem = (uint64_t)RTE_MAX_MEM_MB << 20;
+ max_mem_per_type = RTE_MIN((uint64_t)RTE_MAX_MEM_MB_PER_TYPE << 20,
+ max_mem / n_memtypes);
+ /*
+ * limit maximum number of segment lists per type to ensure there's
+ * space for memseg lists for all NUMA nodes with all page sizes
+ */
+ max_seglists_per_type = RTE_MAX_MEMSEG_LISTS / n_memtypes;
- if (msl_idx >= RTE_MAX_MEMSEG_LISTS) {
- RTE_LOG(ERR, EAL,
- "No more space in memseg lists, please increase %s\n",
- RTE_STR(CONFIG_RTE_MAX_MEMSEG_LISTS));
- return -1;
- }
+ if (max_seglists_per_type == 0) {
+ RTE_LOG(ERR, EAL, "Cannot accommodate all memory types, please increase %s\n",
+ RTE_STR(CONFIG_RTE_MAX_MEMSEG_LISTS));
+ return -1;
+ }
- msl = &mcfg->memsegs[msl_idx++];
+ /* go through all mem types and create segment lists */
+ msl_idx = 0;
+ for (cur_type = 0; cur_type < n_memtypes; cur_type++) {
+ unsigned int cur_seglist, n_seglists, n_segs;
+ unsigned int max_segs_per_type, max_segs_per_list;
+ struct memtype *type = &memtypes[cur_type];
+ uint64_t max_mem_per_list, pagesz;
+ int socket_id;
- cur_max_mem = max_type_mem - total_type_mem;
+ pagesz = type->page_sz;
+ socket_id = type->socket_id;
- cur_mem = get_mem_amount(hugepage_sz,
- cur_max_mem);
- n_segs = cur_mem / hugepage_sz;
+ /*
+ * we need to create segment lists for this type. we must take
+ * into account the following things:
+ *
+ * 1. total amount of memory we can use for this memory type
+ * 2. total amount of memory per memseg list allowed
+ * 3. number of segments needed to fit the amount of memory
+ * 4. number of segments allowed per type
+ * 5. number of segments allowed per memseg list
+ * 6. number of memseg lists we are allowed to take up
+ */
- if (alloc_memseg_list(msl, hugepage_sz, n_segs,
- socket_id, type_msl_idx))
- return -1;
+ /* calculate how much segments we will need in total */
+ max_segs_per_type = max_mem_per_type / pagesz;
+ /* limit number of segments to maximum allowed per type */
+ max_segs_per_type = RTE_MIN(max_segs_per_type,
+ (unsigned int)RTE_MAX_MEMSEG_PER_TYPE);
+ /* limit number of segments to maximum allowed per list */
+ max_segs_per_list = RTE_MIN(max_segs_per_type,
+ (unsigned int)RTE_MAX_MEMSEG_PER_LIST);
+
+ /* calculate how much memory we can have per segment list */
+ max_mem_per_list = RTE_MIN(max_segs_per_list * pagesz,
+ (uint64_t)RTE_MAX_MEM_MB_PER_LIST << 20);
+
+ /* calculate how many segments each segment list will have */
+ n_segs = RTE_MIN(max_segs_per_list, max_mem_per_list / pagesz);
+
+ /* calculate how many segment lists we can have */
+ n_seglists = RTE_MIN(max_segs_per_type / n_segs,
+ max_mem_per_type / max_mem_per_list);
+
+ /* limit number of segment lists according to our maximum */
+ n_seglists = RTE_MIN(n_seglists, max_seglists_per_type);
+
+ RTE_LOG(DEBUG, EAL, "Creating %i segment lists: "
+ "n_segs:%i socket_id:%i hugepage_sz:%" PRIu64 "\n",
+ n_seglists, n_segs, socket_id, pagesz);
+
+ /* create all segment lists */
+ for (cur_seglist = 0; cur_seglist < n_seglists; cur_seglist++) {
+ if (msl_idx >= RTE_MAX_MEMSEG_LISTS) {
+ RTE_LOG(ERR, EAL,
+ "No more space in memseg lists, please increase %s\n",
+ RTE_STR(CONFIG_RTE_MAX_MEMSEG_LISTS));
+ return -1;
+ }
+ msl = &mcfg->memsegs[msl_idx++];
- total_segs += msl->memseg_arr.len;
- total_type_mem = total_segs * hugepage_sz;
- type_msl_idx++;
+ if (alloc_memseg_list(msl, pagesz, n_segs,
+ socket_id, cur_seglist))
+ return -1;
- if (alloc_va_space(msl)) {
- RTE_LOG(ERR, EAL, "Cannot allocate VA space for memseg list\n");
- return -1;
- }
+ if (alloc_va_space(msl)) {
+ RTE_LOG(ERR, EAL, "Cannot allocate VA space for memseg list\n");
+ return -1;
}
- total_mem += total_type_mem;
}
}
return 0;
git.droids-corp.org / dpdk.git / commitdiff