diff mbox series

[v1,RFC,1/1] linux-gen: ishm: implement huge page cache

Message ID 1535464808-30233-2-git-send-email-odpbot@yandex.ru
State Superseded
Headers show
Series [v1,RFC,1/1] linux-gen: ishm: implement huge page cache | expand

Commit Message

Github ODP bot Aug. 28, 2018, 2 p.m. UTC
From: Josep Puigdemont <josep.puigdemont@linaro.org>


With this patch, ODP will pre-allocate several huge pages at init
time. When memory is to be mapped into a huge page, one that was
pre-allocated will be used, if available, this way ODP won't have to
trap into the kernel to allocate huge pages.

The idea with this implementation is to trick ishm into thinking that
a file descriptor where to map the memory was provided, this way it
it won't try to allocate one itself. This file descriptor is one of
those previously allocated at init time. When the system is done with
this file descriptor, instead of closing it, it is put back into the
list of available huge pages, ready to be reused.

A collateral effect of this patch is that memory is not zeroed out
when it is reused.

WARNING: This patch will not work when using process mode threads.
For several reasons, this may not work when using ODP_ISHM_SINGLE_VA
either, so for this case the list of pre-allocated files is not used.

This patch should mitigate, if not solve, bug #3774:
https://bugs.linaro.org/show_bug.cgi?id=3774

To pre-allocate huge pages, define the environment variable
ODP_HP_CACHE, and possibly set it to the number of huge pages that
should be pre-allocated, setting it to -1 will reserve up to 32 huge
pages, which is currently a hard-coded limit.

example usage:
ODP_HP_CACHE=-1 ./test/validation/api/shmem/shmem_main

Signed-off-by: Josep Puigdemont <josep.puigdemont@linaro.org>

---
/** Email created from pull request 685 (joseppc:fix/cache_huge_pages)
 ** https://github.com/Linaro/odp/pull/685
 ** Patch: https://github.com/Linaro/odp/pull/685.patch
 ** Base sha: 96e6c6409bfe8e5f276f136c4e10454f112cd662
 ** Merge commit sha: 234eeff23bccdae2b1e1ca6565fef76c06ae60ca
 **/
 platform/linux-generic/odp_ishm.c | 201 +++++++++++++++++++++++++++---
 1 file changed, 187 insertions(+), 14 deletions(-)
diff mbox series

Patch

diff --git a/platform/linux-generic/odp_ishm.c b/platform/linux-generic/odp_ishm.c
index fc2f948cc..01b089d3a 100644
--- a/platform/linux-generic/odp_ishm.c
+++ b/platform/linux-generic/odp_ishm.c
@@ -164,7 +164,7 @@  typedef struct ishm_fragment {
  * will allocate both a block and a fragment.
  * Blocks contain only global data common to all processes.
  */
-typedef enum {UNKNOWN, HUGE, NORMAL, EXTERNAL} huge_flag_t;
+typedef enum {UNKNOWN, HUGE, NORMAL, EXTERNAL, CACHED} huge_flag_t;
 typedef struct ishm_block {
 	char name[ISHM_NAME_MAXLEN];    /* name for the ishm block (if any) */
 	char filename[ISHM_FILENAME_MAXLEN]; /* name of the .../odp-* file  */
@@ -238,6 +238,16 @@  typedef struct {
 } ishm_ftable_t;
 static ishm_ftable_t *ishm_ftbl;
 
+#define HP_CACHE_SIZE 32
+struct huge_page_cache {
+	uint64_t len;
+	int total; /* index in fd that's the highest allocated */
+	int idx;   /* retrieve fd[idx] to get a free file descriptor */
+	unsigned int seq_num;
+	int fd[HP_CACHE_SIZE]; /* list of file descriptors */
+};
+static struct huge_page_cache hpc;
+
 #ifndef MAP_ANONYMOUS
 #define MAP_ANONYMOUS MAP_ANON
 #endif
@@ -245,6 +255,130 @@  static ishm_ftable_t *ishm_ftbl;
 /* prototypes: */
 static void procsync(void);
 
+static int hp_create_file(uint64_t len, unsigned int seq_num)
+{
+	char filename[ISHM_FILENAME_MAXLEN];
+	char dir[ISHM_FILENAME_MAXLEN];
+	int fd;
+	void *addr;
+
+	if (len <= 0) {
+		ODP_ERR("Length is wrong\n");
+		return -1;
+	}
+
+	if (!odp_global_data.hugepage_info.default_huge_page_dir) {
+		ODP_ERR("No huge page dir\n");
+		return -1;
+	}
+
+	snprintf(dir, ISHM_FILENAME_MAXLEN, "%s/%s",
+		 odp_global_data.hugepage_info.default_huge_page_dir,
+		 odp_global_data.uid);
+
+	if (mkdir(dir, 0744) != 0) {
+		if (errno != EEXIST) {
+			ODP_ERR("Failed to creatr dir: %s\n", strerror(errno));
+			return -1;
+		}
+	}
+
+	snprintf(filename, ISHM_FILENAME_MAXLEN,
+		 "%s/odp-%d-ishm_cached-%04x",
+		 dir,
+		 odp_global_data.main_pid,
+		 seq_num++);
+
+	fd = open(filename, O_RDWR | O_CREAT | O_TRUNC,
+		  S_IRUSR | S_IWUSR | S_IRGRP | S_IROTH);
+	if (fd < 0) {
+		ODP_ERR("Could not create cache file %s\n", filename);
+		return -1;
+	}
+
+	/* remove file from file system */
+	unlink(filename);
+
+	if (ftruncate(fd, len) == -1) {
+		ODP_ERR("Could not truncate file: %s\n", strerror(errno));
+		close(fd);
+		return -1;
+	}
+
+	/* commit huge page */
+	addr = _odp_ishmphy_map(fd, NULL, len, 0);
+	if (addr == NULL) {
+		/* no more pages available */
+		close(fd);
+		return -1;
+	}
+	_odp_ishmphy_unmap(addr, len, 0);
+
+	ODP_PRINT("Created HP cache file %s, fd: %d\n", filename, fd);
+
+	return fd;
+}
+
+static void hp_init(void)
+{
+	char *odp_hp_env;
+	int count;
+
+	hpc.seq_num = 0;
+	hpc.total = -1;
+	hpc.idx = -1;
+	hpc.len = odp_sys_huge_page_size();
+
+	odp_hp_env = getenv("ODP_HP_CACHE");
+	if (odp_hp_env == NULL)
+		return;
+
+	ODP_PRINT("Init HP cache\n");
+
+	count = atoi(odp_hp_env);
+	if (count < 0 || count > HP_CACHE_SIZE)
+		count = HP_CACHE_SIZE;
+
+	for (int i = 0; i < count; ++i) {
+		int fd;
+
+		fd = hp_create_file(hpc.len, hpc.seq_num++);
+		if (fd == -1)
+			break;
+		hpc.total++;
+		hpc.idx++;
+		hpc.fd[hpc.idx] = fd;
+	}
+
+	ODP_PRINT("HP cache has %d huge pages of size 0x%08" PRIx64 "\n",
+		  hpc.total, hpc.len);
+}
+
+static int hp_get_cached(uint64_t len)
+{
+	int fd;
+
+	if (hpc.idx < 0 || len != hpc.len)
+		return -1;
+
+	fd = hpc.fd[hpc.idx];
+	hpc.fd[hpc.idx--] = -1;
+
+	return fd;
+}
+
+static int hp_put_cached(int fd)
+{
+	if (hpc.idx > hpc.total) {
+		ODP_ERR("Trying to put more FD than allowed: %d\n", fd);
+		return -1;
+	}
+
+	hpc.fd[++hpc.idx] = fd;
+
+	return 0;
+}
+
 /*
  * Take a piece of the preallocated virtual space to fit "size" bytes.
  * (best fit). Size must be rounded up to an integer number of pages size.
@@ -798,8 +932,13 @@  static int block_free_internal(int block_index, int close_fd, int deregister)
 			 block_index);
 
 		/* close the related fd */
-		if (close_fd)
-			close(ishm_proctable->entry[proc_index].fd);
+		if (close_fd) {
+			int fd = ishm_proctable->entry[proc_index].fd;
+			if (block->huge == CACHED)
+				hp_put_cached(fd);
+			else
+				close(fd);
+		}
 
 		/* remove entry from process local table: */
 		last = ishm_proctable->nb_entries - 1;
@@ -910,6 +1049,7 @@  int _odp_ishm_reserve(const char *name, uint64_t size, int fd,
 		new_block->huge = EXTERNAL;
 	} else {
 		new_block->external_fd = 0;
+		new_block->huge = UNKNOWN;
 	}
 
 	/* Otherwise, Try first huge pages when possible and needed: */
@@ -927,17 +1067,37 @@  int _odp_ishm_reserve(const char *name, uint64_t size, int fd,
 
 		/* roundup to page size */
 		len = (size + (page_hp_size - 1)) & (-page_hp_size);
-		addr = do_map(new_index, len, hp_align, flags, HUGE, &fd);
-
-		if (addr == NULL) {
-			if (!huge_error_printed) {
-				ODP_ERR("No huge pages, fall back to normal "
-					"pages. "
-					"check: /proc/sys/vm/nr_hugepages.\n");
-				huge_error_printed = 1;
+		if (!(flags & _ODP_ISHM_SINGLE_VA)) {
+			/* try pre-allocated pages */
+			fd = hp_get_cached(len);
+			if (fd != -1) {
+				/* do as if user provided a fd */
+				new_block->external_fd = 1;
+				addr = do_map(new_index, len, hp_align, flags,
+					      CACHED, &fd);
+				if (addr == NULL) {
+					ODP_ERR("Could not use cached file %d\n",
+						fd);
+					hp_put_cached(fd);
+					fd = -1;
+				} else {
+					new_block->huge = CACHED;
+				}
+			}
+		}
+		if (fd == -1) {
+			addr = do_map(new_index, len, hp_align, flags, HUGE, &fd);
+
+			if (addr == NULL) {
+				if (!huge_error_printed) {
+					ODP_ERR("No huge pages, fall back to normal "
+						"pages. "
+						"check: /proc/sys/vm/nr_hugepages.\n");
+					huge_error_printed = 1;
+				}
+			} else {
+				new_block->huge = HUGE;
 			}
-		} else {
-			new_block->huge = HUGE;
 		}
 	}
 
@@ -961,8 +1121,12 @@  int _odp_ishm_reserve(const char *name, uint64_t size, int fd,
 
 	/* if neither huge pages or normal pages works, we cannot proceed: */
 	if ((fd < 0) || (addr == NULL) || (len == 0)) {
-		if ((!new_block->external_fd) && (fd >= 0))
+		if (new_block->external_fd) {
+			if (new_block->huge == CACHED)
+				hp_put_cached(fd);
+		} else if (fd >= 0) {
 			close(fd);
+		}
 		delete_file(new_block);
 		odp_spinlock_unlock(&ishm_tbl->lock);
 		ODP_ERR("_ishm_reserve failed.\n");
@@ -1564,6 +1728,9 @@  int _odp_ishm_init_global(const odp_init_t *init)
 	/* get ready to create pools: */
 	_odp_ishm_pool_init();
 
+	/* init cache files */
+	hp_init();
+
 	return 0;
 
 init_glob_err4:
@@ -1776,6 +1943,9 @@  int _odp_ishm_status(const char *title)
 		case EXTERNAL:
 			huge = 'E';
 			break;
+		case CACHED:
+			huge = 'C';
+			break;
 		default:
 			huge = '?';
 		}
@@ -1896,6 +2066,9 @@  void _odp_ishm_print(int block_index)
 	case EXTERNAL:
 		str = "external";
 		break;
+	case CACHED:
+		str = "cached";
+		break;
 	default:
 		str = "??";
 	}