[dpdk-dev] [PATCH] eal: clean up unused files on initialization

[Anatoly Burakov <anatoly.burakov@intel.com>]

When creating process data structures, EAL will create many files
in EAL runtime directory. Because we allow multiple secondary
processes to run, each secondary process gets their own unique
file. With many secondary processes running and exiting on the
system, runtime directory will, over time, create enormous amounts
of sockets, fbarray files and other stuff that just sits there
unused because the process that allocated it has died a long time
ago. This may lead to exhaustion of disk (or RAM) space in the
runtime directory.

Fix this by removing every unlocked file at initialization that
matches either socket or fbarray naming convention. We cannot be
sure of any other files, so we'll leave them alone. Also, remove
similar code from mp socket code.

We do it at the end of init, rather than at the beginning, because
secondary process will use primary process' data structures even
if the primary itself has died, and we don't want to remove those
before we lock them.

Bugzilla ID: 106

Cc: stable@dpdk.org

Reported-by: Vipin Varghese <vipin.varghese@intel.com>

Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
---
 lib/librte_eal/bsdapp/eal/eal.c         | 100 ++++++++++++++++++++++++
 lib/librte_eal/common/eal_common_proc.c |  30 -------
 lib/librte_eal/common/eal_filesystem.h  |   3 +
 lib/librte_eal/linuxapp/eal/eal.c       |  99 +++++++++++++++++++++++
 4 files changed, 202 insertions(+), 30 deletions(-)

diff --git a/lib/librte_eal/bsdapp/eal/eal.c b/lib/librte_eal/bsdapp/eal/eal.c
index 508cbc46f..0c43b1080 100644
--- a/lib/librte_eal/bsdapp/eal/eal.c
+++ b/lib/librte_eal/bsdapp/eal/eal.c
@@ -3,6 +3,8 @@
  * Copyright(c) 2014 6WIND S.A.
  */
 
+#include <dirent.h>
+#include <fnmatch.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <stdint.h>
@@ -141,6 +143,92 @@ eal_create_runtime_dir(void)
 	return 0;
 }
 
+static int
+eal_clean_runtime_dir(void)
+{
+	DIR *dir;
+	struct dirent *dirent;
+	int dir_fd, fd, lck_result;
+	static const char * const filters[] = {
+		"fbarray_*",
+		"mp_socket_*"
+	};
+
+	/* open directory */
+	dir = opendir(runtime_dir);
+	if (!dir) {
+		RTE_LOG(ERR, EAL, "Unable to open runtime directory %s\n",
+				runtime_dir);
+		goto error;
+	}
+	dir_fd = dirfd(dir);
+
+	/* lock the directory before doing anything, to avoid races */
+	if (flock(dir_fd, LOCK_EX) < 0) {
+		RTE_LOG(ERR, EAL, "Unable to lock runtime directory %s\n",
+			runtime_dir);
+		goto error;
+	}
+
+	dirent = readdir(dir);
+	if (!dirent) {
+		RTE_LOG(ERR, EAL, "Unable to read runtime directory %s\n",
+				runtime_dir);
+		goto error;
+	}
+
+	while (dirent != NULL) {
+		unsigned int f_idx;
+		bool skip = true;
+
+		/* skip files that don't match the patterns */
+		for (f_idx = 0; f_idx < RTE_DIM(filters); f_idx++) {
+			const char *filter = filters[f_idx];
+
+			if (fnmatch(filter, dirent->d_name, 0) == 0) {
+				skip = false;
+				break;
+			}
+		}
+		if (skip) {
+			dirent = readdir(dir);
+			continue;
+		}
+
+		/* try and lock the file */
+		fd = openat(dir_fd, dirent->d_name, O_RDONLY);
+
+		/* skip to next file */
+		if (fd == -1) {
+			dirent = readdir(dir);
+			continue;
+		}
+
+		/* non-blocking lock */
+		lck_result = flock(fd, LOCK_EX | LOCK_NB);
+
+		/* if lock succeeds, remove the file */
+		if (lck_result != -1)
+			unlinkat(dir_fd, dirent->d_name, 0);
+		close(fd);
+		dirent = readdir(dir);
+	}
+
+	/* closedir closes dir_fd and drops the lock */
+	closedir(dir);
+	return 0;
+
+error:
+	if (dir)
+		closedir(dir);
+
+	RTE_LOG(ERR, EAL, "Error while clearing runtime dir: %s\n",
+		strerror(errno));
+
+	return -1;
+}
+
+
 const char *
 rte_eal_get_runtime_dir(void)
 {
@@ -805,6 +893,18 @@ rte_eal_init(int argc, char **argv)
 		return -1;
 	}
 
+	/*
+	 * clean up unused files in runtime directory. we do this at the end of
+	 * init and not at the beginning because we want to clean stuff up
+	 * whether we are primary or secondary process, but we cannot remove
+	 * primary process' files because secondary should be able to run even
+	 * if primary process is dead.
+	 */
+	if (eal_clean_runtime_dir() < 0) {
+		rte_eal_init_alert("Cannot clear runtime directory\n");
+		return -1;
+	}
+
 	rte_eal_mcfg_complete();
 
 	/* Call each registered callback, if enabled */
diff --git a/lib/librte_eal/common/eal_common_proc.c b/lib/librte_eal/common/eal_common_proc.c
index 97663d3ba..e66d7fafb 100644
--- a/lib/librte_eal/common/eal_common_proc.c
+++ b/lib/librte_eal/common/eal_common_proc.c
@@ -542,29 +542,6 @@ open_socket_fd(void)
 	return mp_fd;
 }
 
-static int
-unlink_sockets(const char *filter)
-{
-	int dir_fd;
-	DIR *mp_dir;
-	struct dirent *ent;
-
-	mp_dir = opendir(mp_dir_path);
-	if (!mp_dir) {
-		RTE_LOG(ERR, EAL, "Unable to open directory %s\n", mp_dir_path);
-		return -1;
-	}
-	dir_fd = dirfd(mp_dir);
-
-	while ((ent = readdir(mp_dir))) {
-		if (fnmatch(filter, ent->d_name, 0) == 0)
-			unlinkat(dir_fd, ent->d_name, 0);
-	}
-
-	closedir(mp_dir);
-	return 0;
-}
-
 int
 rte_mp_channel_init(void)
 {
@@ -603,13 +580,6 @@ rte_mp_channel_init(void)
 		return -1;
 	}
 
-	if (rte_eal_process_type() == RTE_PROC_PRIMARY &&
-			unlink_sockets(mp_filter)) {
-		RTE_LOG(ERR, EAL, "failed to unlink mp sockets\n");
-		close(dir_fd);
-		return -1;
-	}
-
 	if (open_socket_fd() < 0) {
 		close(dir_fd);
 		return -1;
diff --git a/lib/librte_eal/common/eal_filesystem.h b/lib/librte_eal/common/eal_filesystem.h
index b3e8ae5ea..1528282cf 100644
--- a/lib/librte_eal/common/eal_filesystem.h
+++ b/lib/librte_eal/common/eal_filesystem.h
@@ -25,6 +25,9 @@
 int
 eal_create_runtime_dir(void);
 
+int
+eal_clean_runtime_dir(void);
+
 /* returns runtime dir */
 const char *
 rte_eal_get_runtime_dir(void);
diff --git a/lib/librte_eal/linuxapp/eal/eal.c b/lib/librte_eal/linuxapp/eal/eal.c
index 361744d40..a1bc02dfa 100644
--- a/lib/librte_eal/linuxapp/eal/eal.c
+++ b/lib/librte_eal/linuxapp/eal/eal.c
@@ -13,7 +13,9 @@
 #include <syslog.h>
 #include <getopt.h>
 #include <sys/file.h>
+#include <dirent.h>
 #include <fcntl.h>
+#include <fnmatch.h>
 #include <stddef.h>
 #include <errno.h>
 #include <limits.h>
@@ -149,6 +151,91 @@ eal_create_runtime_dir(void)
 	return 0;
 }
 
+int
+eal_clean_runtime_dir(void)
+{
+	DIR *dir;
+	struct dirent *dirent;
+	int dir_fd, fd, lck_result;
+	static const char * const filters[] = {
+		"fbarray_*",
+		"mp_socket_*"
+	};
+
+	/* open directory */
+	dir = opendir(runtime_dir);
+	if (!dir) {
+		RTE_LOG(ERR, EAL, "Unable to open runtime directory %s\n",
+				runtime_dir);
+		goto error;
+	}
+	dir_fd = dirfd(dir);
+
+	/* lock the directory before doing anything, to avoid races */
+	if (flock(dir_fd, LOCK_EX) < 0) {
+		RTE_LOG(ERR, EAL, "Unable to lock runtime directory %s\n",
+			runtime_dir);
+		goto error;
+	}
+
+	dirent = readdir(dir);
+	if (!dirent) {
+		RTE_LOG(ERR, EAL, "Unable to read runtime directory %s\n",
+				runtime_dir);
+		goto error;
+	}
+
+	while (dirent != NULL) {
+		unsigned int f_idx;
+		bool skip = true;
+
+		/* skip files that don't match the patterns */
+		for (f_idx = 0; f_idx < RTE_DIM(filters); f_idx++) {
+			const char *filter = filters[f_idx];
+
+			if (fnmatch(filter, dirent->d_name, 0) == 0) {
+				skip = false;
+				break;
+			}
+		}
+		if (skip) {
+			dirent = readdir(dir);
+			continue;
+		}
+
+		/* try and lock the file */
+		fd = openat(dir_fd, dirent->d_name, O_RDONLY);
+
+		/* skip to next file */
+		if (fd == -1) {
+			dirent = readdir(dir);
+			continue;
+		}
+
+		/* non-blocking lock */
+		lck_result = flock(fd, LOCK_EX | LOCK_NB);
+
+		/* if lock succeeds, remove the file */
+		if (lck_result != -1)
+			unlinkat(dir_fd, dirent->d_name, 0);
+		close(fd);
+		dirent = readdir(dir);
+	}
+
+	/* closedir closes dir_fd and drops the lock */
+	closedir(dir);
+	return 0;
+
+error:
+	if (dir)
+		closedir(dir);
+
+	RTE_LOG(ERR, EAL, "Error while clearing runtime dir: %s\n",
+		strerror(errno));
+
+	return -1;
+}
+
 const char *
 rte_eal_get_runtime_dir(void)
 {
@@ -1096,6 +1183,18 @@ rte_eal_init(int argc, char **argv)
 		return -1;
 	}
 
+	/*
+	 * clean up unused files in runtime directory. we do this at the end of
+	 * init and not at the beginning because we want to clean stuff up
+	 * whether we are primary or secondary process, but we cannot remove
+	 * primary process' files because secondary should be able to run even
+	 * if primary process is dead.
+	 */
+	if (eal_clean_runtime_dir() < 0) {
+		rte_eal_init_alert("Cannot clear runtime directory\n");
+		return -1;
+	}
+
 	rte_eal_mcfg_complete();
 
 	/* Call each registered callback, if enabled */
-- 
2.17.1