[dpdk-stable] patch 'eal: clean up unused files on initialization' has been queued to LTS release 18.11.1

Kevin Traynor ktraynor at redhat.com
Fri Jan 4 14:23:51 CET 2019


Hi,

FYI, your patch has been queued to LTS release 18.11.1

Note it hasn't been pushed to http://dpdk.org/browse/dpdk-stable yet.
It will be pushed if I get no objections before 01/11/19. So please
shout if anyone has objections.

Also note that after the patch there's a diff of the upstream commit vs the
patch applied to the branch. This will indicate if there was any rebasing
needed to apply to the stable branch. If there were code changes for rebasing
(ie: not only metadata diffs), please double check that the rebase was
correctly done.

Thanks.

Kevin Traynor

---
>From 8c95205c36c6872e2a96a70bd0044d91cbe1792a Mon Sep 17 00:00:00 2001
From: Anatoly Burakov <anatoly.burakov at intel.com>
Date: Tue, 13 Nov 2018 15:54:44 +0000
Subject: [PATCH] eal: clean up unused files on initialization

[ upstream commit 0a529578f162df8b16e4eb7423e55570f3d13c97 ]

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

Reported-by: Vipin Varghese <vipin.varghese at intel.com>
Signed-off-by: Anatoly Burakov <anatoly.burakov at 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 b8152a75c..41ddb5a22 100644
--- a/lib/librte_eal/bsdapp/eal/eal.c
+++ b/lib/librte_eal/bsdapp/eal/eal.c
@@ -4,4 +4,6 @@
  */
 
+#include <dirent.h>
+#include <fnmatch.h>
 #include <stdio.h>
 #include <stdlib.h>
@@ -142,4 +144,90 @@ eal_create_runtime_dir(void)
 }
 
+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)
@@ -808,4 +896,16 @@ rte_eal_init(int argc, char **argv)
 	}
 
+	/*
+	 * 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();
 
diff --git a/lib/librte_eal/common/eal_common_proc.c b/lib/librte_eal/common/eal_common_proc.c
index 1c3f09aad..6b876590a 100644
--- a/lib/librte_eal/common/eal_common_proc.c
+++ b/lib/librte_eal/common/eal_common_proc.c
@@ -543,27 +543,4 @@ open_socket_fd(void)
 }
 
-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)
@@ -604,11 +581,4 @@ rte_mp_channel_init(void)
 	}
 
-	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);
diff --git a/lib/librte_eal/common/eal_filesystem.h b/lib/librte_eal/common/eal_filesystem.h
index 6e0331fdb..64a028db7 100644
--- a/lib/librte_eal/common/eal_filesystem.h
+++ b/lib/librte_eal/common/eal_filesystem.h
@@ -26,4 +26,7 @@ int
 eal_create_runtime_dir(void);
 
+int
+eal_clean_runtime_dir(void);
+
 #define RUNTIME_CONFIG_FNAME "config"
 static inline const char *
diff --git a/lib/librte_eal/linuxapp/eal/eal.c b/lib/librte_eal/linuxapp/eal/eal.c
index 361744d40..d252c8591 100644
--- a/lib/librte_eal/linuxapp/eal/eal.c
+++ b/lib/librte_eal/linuxapp/eal/eal.c
@@ -14,5 +14,7 @@
 #include <getopt.h>
 #include <sys/file.h>
+#include <dirent.h>
 #include <fcntl.h>
+#include <fnmatch.h>
 #include <stddef.h>
 #include <errno.h>
@@ -150,4 +152,89 @@ eal_create_runtime_dir(void)
 }
 
+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)
@@ -1097,4 +1184,16 @@ rte_eal_init(int argc, char **argv)
 	}
 
+	/*
+	 * 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();
 
-- 
2.19.0

---
  Diff of the applied patch vs upstream commit (please double-check if non-empty:
---
--- -	2019-01-04 13:23:07.672255523 +0000
+++ 0009-eal-clean-up-unused-files-on-initialization.patch	2019-01-04 13:23:07.000000000 +0000
@@ -1,8 +1,10 @@
-From 0a529578f162df8b16e4eb7423e55570f3d13c97 Mon Sep 17 00:00:00 2001
+From 8c95205c36c6872e2a96a70bd0044d91cbe1792a Mon Sep 17 00:00:00 2001
 From: Anatoly Burakov <anatoly.burakov at intel.com>
 Date: Tue, 13 Nov 2018 15:54:44 +0000
 Subject: [PATCH] eal: clean up unused files on initialization
 
+[ upstream commit 0a529578f162df8b16e4eb7423e55570f3d13c97 ]
+
 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
@@ -24,7 +26,6 @@
 before we lock them.
 
 Bugzilla ID: 106
-Cc: stable at dpdk.org
 
 Reported-by: Vipin Varghese <vipin.varghese at intel.com>
 Signed-off-by: Anatoly Burakov <anatoly.burakov at intel.com>


More information about the stable mailing list