Version 2 includes the new osd epoch barrier field. This allows clients
to inform servers that their released caps may not be used until a
particular OSD map epoch.
[ jlayton: bring up to v4.10-rc3 ]
Signed-off-by: John Spray <john.spray@xxxxxxxxxx>
Signed-off-by: Jeff Layton <jlayton@xxxxxxxxxx>
---
fs/ceph/mds_client.c | 15 +++++++++++++++
fs/ceph/mds_client.h | 7 +++++--
2 files changed, 20 insertions(+), 2 deletions(-)
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 7055b499c08b..28c83454e9f6 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -1620,6 +1620,7 @@ void ceph_send_cap_releases(struct ceph_mds_client *mdsc,
struct ceph_cap *cap;
LIST_HEAD(tmp_list);
int num_cap_releases;
+ __le32 *cap_barrier;
spin_lock(&session->s_cap_lock);
again:
@@ -1637,7 +1638,11 @@ void ceph_send_cap_releases(struct ceph_mds_client *mdsc,
head = msg->front.iov_base;
head->num = cpu_to_le32(0);
msg->front.iov_len = sizeof(*head);
+
+ msg->hdr.version = cpu_to_le16(2);
+ msg->hdr.compat_version = cpu_to_le16(1);
}
+
cap = list_first_entry(&tmp_list, struct ceph_cap,
session_caps);
list_del(&cap->session_caps);
@@ -1655,6 +1660,11 @@ void ceph_send_cap_releases(struct ceph_mds_client *mdsc,
ceph_put_cap(mdsc, cap);
if (le32_to_cpu(head->num) == CEPH_CAPS_PER_RELEASE) {
+ // Append cap_barrier field
+ cap_barrier = msg->front.iov_base + msg->front.iov_len;
+ *cap_barrier = cpu_to_le32(mdsc->cap_epoch_barrier);
+ msg->front.iov_len += sizeof(*cap_barrier);
+
msg->hdr.front_len = cpu_to_le32(msg->front.iov_len);
dout("send_cap_releases mds%d %p\n", session->s_mds, msg);
ceph_con_send(&session->s_con, msg);
@@ -1670,6 +1680,11 @@ void ceph_send_cap_releases(struct ceph_mds_client *mdsc,
spin_unlock(&session->s_cap_lock);
if (msg) {
+ // Append cap_barrier field
+ cap_barrier = msg->front.iov_base + msg->front.iov_len;
+ *cap_barrier = cpu_to_le32(mdsc->cap_epoch_barrier);
+ msg->front.iov_len += sizeof(*cap_barrier);
+
msg->hdr.front_len = cpu_to_le32(msg->front.iov_len);
dout("send_cap_releases mds%d %p\n", session->s_mds, msg);
ceph_con_send(&session->s_con, msg);
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index eb8144ab4995..5da41326a0fd 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -104,10 +104,13 @@ struct ceph_mds_reply_info_parsed {
/*
* cap releases are batched and sent to the MDS en masse.
+ *
+ * Account for per-message overhead of mds_cap_release header
+ * and __le32 for osd epoch barrier trailing field.
*/
-#define CEPH_CAPS_PER_RELEASE ((PAGE_SIZE - \
+#define CEPH_CAPS_PER_RELEASE ((PAGE_SIZE - sizeof(u32) - \
sizeof(struct ceph_mds_cap_release)) / \
- sizeof(struct ceph_mds_cap_item))
+ sizeof(struct ceph_mds_cap_item))
/*
--
2.9.3
--
To unsubscribe from this list: send the line "unsubscribe ceph-devel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
