ceph: add read/write latency metric support

Calculate the latency for OSD read requests. Add a new r_end_stamp
field to struct ceph_osd_request that will hold the time of that
the reply was received. Use that to calculate the RTT for each call,
and divide the sum of those by number of calls to get averate RTT.

Keep a tally of RTT for OSD writes and number of calls to track average
latency of OSD writes.

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

1 files changed, 20 insertions, 0 deletions

diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 6f4678d98df7..01ad09733ac7 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -11,10 +11,12 @@
 #include <linux/task_io_accounting_ops.h>
 #include <linux/signal.h>
 #include <linux/iversion.h>
+#include <linux/ktime.h>
 
 #include "super.h"
 #include "mds_client.h"
 #include "cache.h"
+#include "metric.h"
 #include <linux/ceph/osd_client.h>
 #include <linux/ceph/striper.h>
 
@@ -216,6 +218,9 @@ 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->r_start_latency,
+				 req->r_end_latency, rc);
+
 	ceph_osdc_put_request(req);
 	dout("readpages result %d\n", rc);
 	return rc;
@@ -299,6 +304,7 @@ 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 +342,10 @@ unlock:
 		put_page(page);
 		bytes -= PAGE_SIZE;
 	}
+
+	ceph_update_read_latency(&fsc->mdsc->metric, req->r_start_latency,
+				 req->r_end_latency, rc);
+
 	kfree(osd_data->pages);
 }
 
@@ -643,6 +653,9 @@ static int ceph_sync_writepages(struct ceph_fs_client *fsc,
 	if (!rc)
 		rc = ceph_osdc_wait_request(osdc, req);
 
+	ceph_update_write_latency(&fsc->mdsc->metric, req->r_start_latency,
+				  req->r_end_latency, rc);
+
 	ceph_osdc_put_request(req);
 	if (rc == 0)
 		rc = len;
@@ -794,6 +807,9 @@ static void writepages_finish(struct ceph_osd_request *req)
 		ceph_clear_error_write(ci);
 	}
 
+	ceph_update_write_latency(&fsc->mdsc->metric, req->r_start_latency,
+				  req->r_end_latency, rc);
+
 	/*
 	 * We lost the cache cap, need to truncate the page before
 	 * it is unlocked, otherwise we'd truncate it later in the
@@ -1852,6 +1868,10 @@ int ceph_uninline_data(struct file *filp, struct page *locked_page)
 	err = ceph_osdc_start_request(&fsc->client->osdc, req, false);
 	if (!err)
 		err = ceph_osdc_wait_request(&fsc->client->osdc, req);
+
+	ceph_update_write_latency(&fsc->mdsc->metric, req->r_start_latency,
+				  req->r_end_latency, err);
+
 out_put:
 	ceph_osdc_put_request(req);
 	if (err == -ECANCELED)