ceph: periodically send perf metrics to MDSes

This will send the caps/read/write/metadata metrics to any available MDS
once per second, which will be the same as the userland client.  It will
skip the MDS sessions which don't support the metric collection, as the
MDSs will close socket connections when they get an unknown type
message.

We can disable the metric sending via the disable_send_metrics module
parameter.

[ jlayton: fix up endianness bug in ceph_mdsc_send_metrics() ]

URL: https://tracker.ceph.com/issues/43215
Signed-off-by: Xiubo Li <xiubli@redhat.com>
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>

1 files changed, 42 insertions, 0 deletions

diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index c9784eb1159a..933f5df5da7d 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -27,6 +27,9 @@
 #include <linux/ceph/auth.h>
 #include <linux/ceph/debugfs.h>
 
+static DEFINE_SPINLOCK(ceph_fsc_lock);
+static LIST_HEAD(ceph_fsc_list);
+
 /*
  * Ceph superblock operations
  *
@@ -691,6 +694,10 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt,
 	if (!fsc->wb_pagevec_pool)
 		goto fail_cap_wq;
 
+	spin_lock(&ceph_fsc_lock);
+	list_add_tail(&fsc->metric_wakeup, &ceph_fsc_list);
+	spin_unlock(&ceph_fsc_lock);
+
 	return fsc;
 
 fail_cap_wq:
@@ -717,6 +724,10 @@ static void destroy_fs_client(struct ceph_fs_client *fsc)
 {
 	dout("destroy_fs_client %p\n", fsc);
 
+	spin_lock(&ceph_fsc_lock);
+	list_del(&fsc->metric_wakeup);
+	spin_unlock(&ceph_fsc_lock);
+
 	ceph_mdsc_destroy(fsc);
 	destroy_workqueue(fsc->inode_wq);
 	destroy_workqueue(fsc->cap_wq);
@@ -1282,6 +1293,37 @@ static void __exit exit_ceph(void)
 	destroy_caches();
 }
 
+static int param_set_metrics(const char *val, const struct kernel_param *kp)
+{
+	struct ceph_fs_client *fsc;
+	int ret;
+
+	ret = param_set_bool(val, kp);
+	if (ret) {
+		pr_err("Failed to parse sending metrics switch value '%s'\n",
+		       val);
+		return ret;
+	} else if (!disable_send_metrics) {
+		// wake up all the mds clients
+		spin_lock(&ceph_fsc_lock);
+		list_for_each_entry(fsc, &ceph_fsc_list, metric_wakeup) {
+			metric_schedule_delayed(&fsc->mdsc->metric);
+		}
+		spin_unlock(&ceph_fsc_lock);
+	}
+
+	return 0;
+}
+
+static const struct kernel_param_ops param_ops_metrics = {
+	.set = param_set_metrics,
+	.get = param_get_bool,
+};
+
+bool disable_send_metrics = false;
+module_param_cb(disable_send_metrics, &param_ops_metrics, &disable_send_metrics, 0644);
+MODULE_PARM_DESC(disable_send_metrics, "Enable sending perf metrics to ceph cluster (default: on)");
+
 module_init(init_ceph);
 module_exit(exit_ceph);