diff mbox series

[v7,3/5] ceph: add global read latency metric support

Message ID 20200219033851.6548-4-xiubli@redhat.com (mailing list archive)
State New, archived
Headers show
Series ceph: add perf metrics support | expand

Commit Message

Xiubo Li Feb. 19, 2020, 3:38 a.m. UTC
From: Xiubo Li <xiubli@redhat.com>

It will calculate the latency for the read osd requests, which only
include the time cousumed by network and the ceph osd.

item          total       sum_lat(us)     avg_lat(us)
-----------------------------------------------------
read          1036        848000          818

URL: https://tracker.ceph.com/issues/43215
Signed-off-by: Xiubo Li <xiubli@redhat.com>
---
 fs/ceph/addr.c                  |  6 ++++++
 fs/ceph/debugfs.c               | 11 +++++++++++
 fs/ceph/file.c                  | 13 +++++++++++++
 fs/ceph/mds_client.c            | 14 ++++++++++++++
 fs/ceph/metric.h                | 20 ++++++++++++++++++++
 include/linux/ceph/osd_client.h |  1 +
 net/ceph/osd_client.c           |  2 ++
 7 files changed, 67 insertions(+)
diff mbox series

Patch

diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 6f4678d98df7..16573a13ffee 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -216,6 +216,8 @@  static int ceph_sync_readpages(struct ceph_fs_client *fsc,
 	if (!rc)
 		rc = ceph_osdc_wait_request(osdc, req);
 
+	ceph_update_read_latency(&fsc->mdsc->metric, req, rc);
+
 	ceph_osdc_put_request(req);
 	dout("readpages result %d\n", rc);
 	return rc;
@@ -299,6 +301,7 @@  static int ceph_readpage(struct file *filp, struct page *page)
 static void finish_read(struct ceph_osd_request *req)
 {
 	struct inode *inode = req->r_inode;
+	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
 	struct ceph_osd_data *osd_data;
 	int rc = req->r_result <= 0 ? req->r_result : 0;
 	int bytes = req->r_result >= 0 ? req->r_result : 0;
@@ -336,6 +339,9 @@  static void finish_read(struct ceph_osd_request *req)
 		put_page(page);
 		bytes -= PAGE_SIZE;
 	}
+
+	ceph_update_read_latency(&fsc->mdsc->metric, req, rc);
+
 	kfree(osd_data->pages);
 }
 
diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c
index c83e52bd9961..d814a3a27611 100644
--- a/fs/ceph/debugfs.c
+++ b/fs/ceph/debugfs.c
@@ -129,7 +129,18 @@  static int metric_show(struct seq_file *s, void *p)
 	struct ceph_fs_client *fsc = s->private;
 	struct ceph_mds_client *mdsc = fsc->mdsc;
 	int i, nr_caps = 0;
+	s64 total, sum, avg = 0;
 
+	seq_printf(s, "item          total       sum_lat(us)     avg_lat(us)\n");
+	seq_printf(s, "-----------------------------------------------------\n");
+
+	total = percpu_counter_sum(&mdsc->metric.total_reads);
+	sum = percpu_counter_sum(&mdsc->metric.read_latency_sum);
+	sum = jiffies_to_usecs(sum);
+	avg = total ? sum / total : 0;
+	seq_printf(s, "%-14s%-12lld%-16lld%lld\n", "read", total, sum, avg);
+
+	seq_printf(s, "\n");
 	seq_printf(s, "item          total           miss            hit\n");
 	seq_printf(s, "-------------------------------------------------\n");
 
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index b1b5aa35d25f..96e35935b764 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -660,6 +660,9 @@  static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *to,
 		ret = ceph_osdc_start_request(osdc, req, false);
 		if (!ret)
 			ret = ceph_osdc_wait_request(osdc, req);
+
+		ceph_update_read_latency(&fsc->mdsc->metric, req, ret);
+
 		ceph_osdc_put_request(req);
 
 		i_size = i_size_read(inode);
@@ -798,6 +801,8 @@  static void ceph_aio_complete_req(struct ceph_osd_request *req)
 	struct inode *inode = req->r_inode;
 	struct ceph_aio_request *aio_req = req->r_priv;
 	struct ceph_osd_data *osd_data = osd_req_op_extent_osd_data(req, 0);
+	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
+	struct ceph_client_metric *metric = &fsc->mdsc->metric;
 
 	BUG_ON(osd_data->type != CEPH_OSD_DATA_TYPE_BVECS);
 	BUG_ON(!osd_data->num_bvecs);
@@ -805,6 +810,10 @@  static void ceph_aio_complete_req(struct ceph_osd_request *req)
 	dout("ceph_aio_complete_req %p rc %d bytes %u\n",
 	     inode, rc, osd_data->bvec_pos.iter.bi_size);
 
+	/* r_start_stamp == 0 means the request was not submitted */
+	if (req->r_start_stamp && !aio_req->write)
+		ceph_update_read_latency(metric, req, rc);
+
 	if (rc == -EOLDSNAPC) {
 		struct ceph_aio_work *aio_work;
 		BUG_ON(!aio_req->write);
@@ -933,6 +942,7 @@  ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
 	struct inode *inode = file_inode(file);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
+	struct ceph_client_metric *metric = &fsc->mdsc->metric;
 	struct ceph_vino vino;
 	struct ceph_osd_request *req;
 	struct bio_vec *bvecs;
@@ -1049,6 +1059,9 @@  ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
 		if (!ret)
 			ret = ceph_osdc_wait_request(&fsc->client->osdc, req);
 
+		if (!write)
+			ceph_update_read_latency(metric, req, ret);
+
 		size = i_size_read(inode);
 		if (!write) {
 			if (ret == -ENOENT)
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 4993ccaceefe..b7ada9cde4f8 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -4184,8 +4184,20 @@  static int ceph_mdsc_metric_init(struct ceph_client_metric *metric)
 	if (ret)
 		goto err_i_caps_mis;
 
+	ret = percpu_counter_init(&metric->total_reads, 0, GFP_KERNEL);
+	if (ret)
+		goto err_total_reads;
+
+	ret = percpu_counter_init(&metric->read_latency_sum, 0, GFP_KERNEL);
+	if (ret)
+		goto err_read_latency_sum;
+
 	return 0;
 
+err_read_latency_sum:
+	percpu_counter_destroy(&metric->total_reads);
+err_total_reads:
+	percpu_counter_destroy(&metric->i_caps_mis);
 err_i_caps_mis:
 	percpu_counter_destroy(&metric->i_caps_hit);
 err_i_caps_hit:
@@ -4533,6 +4545,8 @@  void ceph_mdsc_destroy(struct ceph_fs_client *fsc)
 
 	ceph_mdsc_stop(mdsc);
 
+	percpu_counter_destroy(&mdsc->metric.read_latency_sum);
+	percpu_counter_destroy(&mdsc->metric.total_reads);
 	percpu_counter_destroy(&mdsc->metric.i_caps_mis);
 	percpu_counter_destroy(&mdsc->metric.i_caps_hit);
 	percpu_counter_destroy(&mdsc->metric.d_lease_mis);
diff --git a/fs/ceph/metric.h b/fs/ceph/metric.h
index e2fceb38a924..afea44a3794b 100644
--- a/fs/ceph/metric.h
+++ b/fs/ceph/metric.h
@@ -2,6 +2,8 @@ 
 #ifndef _FS_CEPH_MDS_METRIC_H
 #define _FS_CEPH_MDS_METRIC_H
 
+#include <linux/ceph/osd_client.h>
+
 /* This is the global metrics */
 struct ceph_client_metric {
 	atomic64_t            total_dentries;
@@ -10,5 +12,23 @@  struct ceph_client_metric {
 
 	struct percpu_counter i_caps_hit;
 	struct percpu_counter i_caps_mis;
+
+	struct percpu_counter total_reads;
+	struct percpu_counter read_latency_sum;
 };
+
+static inline void ceph_update_read_latency(struct ceph_client_metric *m,
+					    struct ceph_osd_request *req,
+					    int rc)
+{
+	if (!m || !req)
+		return;
+
+	if (rc >= 0 || rc == -ENOENT || rc == -ETIMEDOUT) {
+		s64 latency = req->r_end_stamp - req->r_start_stamp;
+
+		percpu_counter_inc(&m->total_reads);
+		percpu_counter_add(&m->read_latency_sum, latency);
+	}
+}
 #endif /* _FS_CEPH_MDS_METRIC_H */
diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index 9d9f745b98a1..02ff3a302d26 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -213,6 +213,7 @@  struct ceph_osd_request {
 	/* internal */
 	unsigned long r_stamp;                /* jiffies, send or check time */
 	unsigned long r_start_stamp;          /* jiffies */
+	unsigned long r_end_stamp;            /* jiffies */
 	int r_attempts;
 	u32 r_map_dne_bound;
 
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 8ff2856e2d52..108c9457d629 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -2389,6 +2389,8 @@  static void finish_request(struct ceph_osd_request *req)
 	WARN_ON(lookup_request_mc(&osdc->map_checks, req->r_tid));
 	dout("%s req %p tid %llu\n", __func__, req, req->r_tid);
 
+	req->r_end_stamp = jiffies;
+
 	if (req->r_osd)
 		unlink_request(req->r_osd, req);
 	atomic_dec(&osdc->num_requests);