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.
Signed-off-by: John Spray <john.spray@xxxxxxxxxx>
---
fs/ceph/mds_client.c | 13 +++++++++++++
fs/ceph/mds_client.h | 8 ++++++--
2 files changed, 19 insertions(+), 2 deletions(-)
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index dce7977..3f5bc23 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -1508,12 +1508,25 @@ void ceph_send_cap_releases(struct ceph_mds_client *mdsc,
struct ceph_mds_session *session)
{
struct ceph_msg *msg;
+ u32 *cap_barrier;
dout("send_cap_releases mds%d\n", session->s_mds);
spin_lock(&session->s_cap_lock);
while (!list_empty(&session->s_cap_releases_done)) {
msg = list_first_entry(&session->s_cap_releases_done,
struct ceph_msg, list_head);
+
+ BUG_ON(msg->front.iov_len + sizeof(*cap_barrier) > \
+ PAGE_CACHE_SIZE);
+
+ // 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.version = cpu_to_le16(2);
+ msg->hdr.compat_version = cpu_to_le16(1);
+
list_del_init(&msg->list_head);
spin_unlock(&session->s_cap_lock);
msg->hdr.front_len = cpu_to_le32(msg->front.iov_len);
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index 7b40568..b9412a8 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -92,10 +92,14 @@ 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 u32 for osd epoch barrier trailing field.
*/
#define CEPH_CAPS_PER_RELEASE ((PAGE_CACHE_SIZE - \
- sizeof(struct ceph_mds_cap_release)) / \
- sizeof(struct ceph_mds_cap_item))
+ sizeof(struct ceph_mds_cap_release) - \
+ sizeof(u32)) / \
+ sizeof(struct ceph_mds_cap_item))
/*
--
1.9.3
--
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
