summaryrefslogtreecommitdiffstats
path: root/xlators/storage
diff options
context:
space:
mode:
authorNiels de Vos <ndevos@redhat.com>2013-06-24 14:05:58 +0200
committerVijay Bellur <vbellur@redhat.com>2013-07-03 22:34:54 -0700
commit98f62a731ca13296b937bfff14d0a2f8dfc49a54 (patch)
tree985d15b9f42c62c387abf46442b5ede8f9be672d /xlators/storage
parent37d2c255e46eea98df473fbc693931462882392e (diff)
posix: add a simple health-checker
Goal of this health-checker is to detect fatal issues of the underlying storage that is used for exporting a brick. The current implementation requires the filesystem to detect the storage error, after which it will notify the parent xlators and exit the glusterfsd (brick) process to prevent further troubles. The interval the health-check runs can be configured per volume with the storage.health-check-interval option. The default interval is 30 seconds. It is not trivial to write an automated test-case with the current prove-framework. These are the manual steps that can be done to verify the functionality: - setup a Logical Volume (/dev/bz970960/xfs) and format is as XFS for brick usage - create a volume with the one brick # gluster volume create failing_xfs glufs1:/bricks/failing_xfs/data # gluster volume start failing_xfs - mount the volume and verify the functionality - make the storage fail (use device-mapper, or pull disks) # dmsetup table .. bz970960-xfs: 0 196608 linear 7:0 2048 # echo 0 196608 error > dmsetup-error-target # dmsetup load bz970960-xfs dmsetup-error-target # dmsetup resume bz970960-xfs # dmsetup table ... bz970960-xfs: 0 196608 error - notice the errors caught by syslog: Jun 24 11:31:49 vm130-32 kernel: XFS (dm-2): metadata I/O error: block 0x0 ("xfs_buf_iodone_callbacks") error 5 buf count 512 Jun 24 11:31:49 vm130-32 kernel: XFS (dm-2): I/O Error Detected. Shutting down filesystem Jun 24 11:31:49 vm130-32 kernel: XFS (dm-2): Please umount the filesystem and rectify the problem(s) Jun 24 11:31:49 vm130-32 kernel: VFS:Filesystem freeze failed Jun 24 11:31:50 vm130-32 GlusterFS[1969]: [2013-06-24 10:31:50.500674] M [posix-helpers.c:1114:posix_health_check_thread_proc] 0-failing_xfs-posix: health-check failed, going down Jun 24 11:32:09 vm130-32 kernel: XFS (dm-2): xfs_log_force: error 5 returned. Jun 24 11:32:20 vm130-32 GlusterFS[1969]: [2013-06-24 10:32:20.508690] M [posix-helpers.c:1119:posix_health_check_thread_proc] 0-failing_xfs-posix: still alive! -> SIGTERM - these errors are in the log of the brick as well: [2013-06-24 10:31:50.500607] W [posix-helpers.c:1102:posix_health_check_thread_proc] 0-failing_xfs-posix: stat() on /bricks/failing_xfs/data returned: Input/output error [2013-06-24 10:31:50.500674] M [posix-helpers.c:1114:posix_health_check_thread_proc] 0-failing_xfs-posix: health-check failed, going down [2013-06-24 10:32:20.508690] M [posix-helpers.c:1119:posix_health_check_thread_proc] 0-failing_xfs-posix: still alive! -> SIGTERM - the glusterfsd process has exited correctly: # gluster volume status Status of volume: failing_xfs Gluster process Port Online Pid ------------------------------------------------------------------------------ Brick glufs1:/bricks/failing_xfs/data N/A N N/A NFS Server on localhost 2049 Y 1897 Change-Id: Ic247fbefb97f7e861307a5998a9a7a3ecc80aa07 BUG: 971774 Signed-off-by: Niels de Vos <ndevos@redhat.com> Reviewed-on: http://review.gluster.org/5176 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
Diffstat (limited to 'xlators/storage')
-rw-r--r--xlators/storage/posix/src/posix-helpers.c114
-rw-r--r--xlators/storage/posix/src/posix.c20
-rw-r--r--xlators/storage/posix/src/posix.h6
3 files changed, 140 insertions, 0 deletions
diff --git a/xlators/storage/posix/src/posix-helpers.c b/xlators/storage/posix/src/posix-helpers.c
index f8284d3359f..a13e0207808 100644
--- a/xlators/storage/posix/src/posix-helpers.c
+++ b/xlators/storage/posix/src/posix-helpers.c
@@ -22,6 +22,7 @@
#include <pthread.h>
#include <ftw.h>
#include <sys/stat.h>
+#include <signal.h>
#ifndef GF_BSD_HOST_OS
#include <alloca.h>
@@ -1063,3 +1064,116 @@ posix_fd_ctx_get (fd_t *fd, xlator_t *this, struct posix_fd **pfd)
return ret;
}
+
+static void *
+posix_health_check_thread_proc (void *data)
+{
+ xlator_t *this = NULL;
+ struct posix_private *priv = NULL;
+ uint32_t interval = 0;
+ int ret = -1;
+ struct stat sb = {0, };
+
+ this = data;
+ priv = this->private;
+
+ /* prevent races when the interval is updated */
+ interval = priv->health_check_interval;
+ if (interval == 0)
+ goto out;
+
+ gf_log (this->name, GF_LOG_DEBUG, "health-check thread started, "
+ "interval = %d seconds", interval);
+
+ while (1) {
+ /* aborting sleep() is a request to exit this thread, sleep()
+ * will normally not return when cancelled */
+ ret = sleep (interval);
+ if (ret > 0)
+ break;
+
+ /* prevent thread errors while doing the health-check(s) */
+ pthread_setcancelstate (PTHREAD_CANCEL_DISABLE, NULL);
+
+ /* Do the health-check, it should be moved to its own function
+ * in case it gets more complex. */
+ ret = stat (priv->base_path, &sb);
+ if (ret < 0) {
+ gf_log (this->name, GF_LOG_WARNING,
+ "stat() on %s returned: %s", priv->base_path,
+ strerror (errno));
+ goto abort;
+ }
+
+ pthread_setcancelstate (PTHREAD_CANCEL_ENABLE, NULL);
+ }
+
+out:
+ gf_log (this->name, GF_LOG_DEBUG, "health-check thread exiting");
+
+ LOCK (&priv->lock);
+ {
+ priv->health_check_active = _gf_false;
+ }
+ UNLOCK (&priv->lock);
+
+ return NULL;
+
+abort:
+ /* health-check failed */
+ gf_log (this->name, GF_LOG_EMERG, "health-check failed, going down");
+ xlator_notify (this->parents->xlator, GF_EVENT_CHILD_DOWN, this);
+
+ ret = sleep (30);
+ if (ret == 0) {
+ gf_log (this->name, GF_LOG_EMERG, "still alive! -> SIGTERM");
+ kill (getpid(), SIGTERM);
+ }
+
+ ret = sleep (30);
+ if (ret == 0) {
+ gf_log (this->name, GF_LOG_EMERG, "still alive! -> SIGKILL");
+ kill (getpid(), SIGKILL);
+ }
+
+ return NULL;
+}
+
+void
+posix_spawn_health_check_thread (xlator_t *xl)
+{
+ struct posix_private *priv = NULL;
+ int ret = -1;
+
+ priv = xl->private;
+
+ LOCK (&priv->lock);
+ {
+ /* cancel the running thread */
+ if (priv->health_check_active == _gf_true) {
+ pthread_cancel (priv->health_check);
+ priv->health_check_active = _gf_false;
+ }
+
+ /* prevent scheduling a check in a tight loop */
+ if (priv->health_check_interval == 0)
+ goto unlock;
+
+ ret = pthread_create (&priv->health_check, NULL,
+ posix_health_check_thread_proc, xl);
+ if (ret < 0) {
+ priv->health_check_interval = 0;
+ priv->health_check_active = _gf_false;
+ gf_log (xl->name, GF_LOG_ERROR,
+ "unable to setup health-check thread: %s",
+ strerror (errno));
+ goto unlock;
+ }
+
+ /* run the thread detached, resources will be freed on exit */
+ pthread_detach (priv->health_check);
+ priv->health_check_active = _gf_true;
+ }
+unlock:
+ UNLOCK (&priv->lock);
+}
diff --git a/xlators/storage/posix/src/posix.c b/xlators/storage/posix/src/posix.c
index 05101fd3177..399c94bf095 100644
--- a/xlators/storage/posix/src/posix.c
+++ b/xlators/storage/posix/src/posix.c
@@ -23,6 +23,7 @@
#include <pthread.h>
#include <ftw.h>
#include <sys/stat.h>
+#include <signal.h>
#ifndef GF_BSD_HOST_OS
#include <alloca.h>
@@ -4320,6 +4321,10 @@ reconfigure (xlator_t *this, dict_t *options)
" fallback to <hostname>:<export>");
}
+ GF_OPTION_RECONF ("health-check-interval", priv->health_check_interval,
+ options, uint32, out);
+ posix_spawn_health_check_thread (this);
+
ret = 0;
out:
return ret;
@@ -4690,6 +4695,12 @@ init (xlator_t *this)
" fallback to <hostname>:<export>");
}
+ _private->health_check_active = _gf_false;
+ GF_OPTION_INIT ("health-check-interval",
+ _private->health_check_interval, uint32, out);
+ if (_private->health_check_interval)
+ posix_spawn_health_check_thread (this);
+
pthread_mutex_init (&_private->janitor_lock, NULL);
pthread_cond_init (&_private->janitor_cond, NULL);
INIT_LIST_HEAD (&_private->janitor_fds);
@@ -4815,5 +4826,14 @@ struct volume_options options[] = {
.description = "return glusterd's node-uuid in pathinfo xattr"
" string instead of hostname"
},
+ {
+ .key = {"health-check-interval"},
+ .type = GF_OPTION_TYPE_INT,
+ .min = 0,
+ .default_value = "30",
+ .validate = GF_OPT_VALIDATE_MIN,
+ .description = "Interval in seconds for a filesystem health check, "
+ "set to 0 to disable"
+ },
{ .key = {NULL} }
};
diff --git a/xlators/storage/posix/src/posix.h b/xlators/storage/posix/src/posix.h
index 2cee1905f78..22340370e2c 100644
--- a/xlators/storage/posix/src/posix.h
+++ b/xlators/storage/posix/src/posix.h
@@ -127,6 +127,11 @@ struct posix_private {
/* node-uuid in pathinfo xattr */
gf_boolean_t node_uuid_pathinfo;
+
+ /* seconds to sleep between health checks */
+ uint32_t health_check_interval;
+ pthread_t health_check;
+ gf_boolean_t health_check_active;
};
typedef struct {
@@ -178,4 +183,5 @@ gf_boolean_t posix_special_xattr (char **pattern, char *key);
void
__posix_fd_set_odirect (fd_t *fd, struct posix_fd *pfd, int opflags,
off_t offset, size_t size);
+void posix_spawn_health_check_thread (xlator_t *this);
#endif /* _POSIX_H */