| Message ID | 20200129082715.5285-5-xiubli@redhat.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | ceph: add perf metrics support | expand |
On Wed, 2020-01-29 at 03:27 -0500, xiubli@redhat.com wrote: > From: Xiubo Li <xiubli@redhat.com> > > Grab the osdc requests' end time stamp. > > Signed-off-by: Xiubo Li <xiubli@redhat.com> > --- > include/linux/ceph/osd_client.h | 1 + > net/ceph/osd_client.c | 2 ++ > 2 files changed, 3 insertions(+) > > diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h > index 9d9f745b98a1..00a449cfc478 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); Maybe fold this patch into #6 in this series? I'd prefer to add the new field along with its first user.
On 2020/2/6 3:14, Jeff Layton wrote: > On Wed, 2020-01-29 at 03:27 -0500, xiubli@redhat.com wrote: >> From: Xiubo Li <xiubli@redhat.com> >> >> Grab the osdc requests' end time stamp. >> >> Signed-off-by: Xiubo Li <xiubli@redhat.com> >> --- >> include/linux/ceph/osd_client.h | 1 + >> net/ceph/osd_client.c | 2 ++ >> 2 files changed, 3 insertions(+) >> >> diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h >> index 9d9f745b98a1..00a449cfc478 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); > Maybe fold this patch into #6 in this series? I'd prefer to add the new > field along with its first user. Sure, will merge it. Thanks.
diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 9d9f745b98a1..00a449cfc478 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);