LU-14798 lnet: RMDA infrastructure updates

Add infrastructure to force RDMA for payloads < 4K.
Add infrastructure to extract the first page in a
payload. Useful for determining the type of the payload
to be transmitted.

Signed-off-by: Amir Shehata <ashehata@whamcloud.com>
Change-Id: Id7dc26c83f00dadd26feca94fc4d8233872650d3
Lustre-change: https://review.whamcloud.com/37453
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Wang Shilong <wshilong@ddn.com>
Whamcloud-bug-id: EX-773
Reviewed-on: https://review.whamcloud.com/44109
Tested-by: jenkins <devops@whamcloud.com>
Reviewed-by: Wang Shilong <wshilong@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>

diff --git a/lnet/include/lnet/lib-lnet.h b/lnet/include/lnet/lib-lnet.h
index 358cb63..b419f9e 100644 (file)
--- a/lnet/include/lnet/lib-lnet.h
+++ b/lnet/include/lnet/lib-lnet.h
@@ -784,6 +784,7 @@ void lnet_me_unlink(struct lnet_me *me);
 void lnet_md_unlink(struct lnet_libmd *md);
 void lnet_md_deconstruct(struct lnet_libmd *lmd, struct lnet_event *ev);
 struct page *lnet_kvaddr_to_page(unsigned long vaddr);
+struct page *lnet_get_first_page(struct lnet_libmd *md, unsigned int offset);
 int lnet_cpt_of_md(struct lnet_libmd *md, unsigned int offset);
 
 unsigned int lnet_get_lnd_timeout(void);

diff --git a/lnet/include/lnet/lib-types.h b/lnet/include/lnet/lib-types.h
index d671fb0..b8e2a2e 100644 (file)
--- a/lnet/include/lnet/lib-types.h
+++ b/lnet/include/lnet/lib-types.h
@@ -125,6 +125,8 @@ struct lnet_msg {
        enum lnet_msg_hstatus   msg_health_status;
        /* This is a recovery message */
        bool                    msg_recovery;
+       /* force an RDMA even if the message size is < 4K */
+       bool                    msg_rdma_force;
        /* the number of times a transmission has been retried */
        int                     msg_retry_count;
        /* flag to indicate that we do not want to resend this message */

diff --git a/lnet/klnds/o2iblnd/o2iblnd_cb.c b/lnet/klnds/o2iblnd/o2iblnd_cb.c
index 9fd0baa..b96e0e8 100644 (file)
--- a/lnet/klnds/o2iblnd/o2iblnd_cb.c
+++ b/lnet/klnds/o2iblnd/o2iblnd_cb.c
@@ -1653,7 +1653,7 @@ kiblnd_send(struct lnet_ni *ni, void *private, struct lnet_msg *lntmsg)
 
                 /* is the REPLY message too small for RDMA? */
                nob = offsetof(struct kib_msg, ibm_u.immediate.ibim_payload[lntmsg->msg_md->md_length]);
-                if (nob <= IBLND_MSG_SIZE)
+                if (nob <= IBLND_MSG_SIZE && !lntmsg->msg_rdma_force)
                         break;                  /* send IMMEDIATE */
 
                tx = kiblnd_get_idle_tx(ni, target.nid);
@@ -1700,7 +1700,7 @@ kiblnd_send(struct lnet_ni *ni, void *private, struct lnet_msg *lntmsg)
         case LNET_MSG_PUT:
                 /* Is the payload small enough not to need RDMA? */
                nob = offsetof(struct kib_msg, ibm_u.immediate.ibim_payload[payload_nob]);
-                if (nob <= IBLND_MSG_SIZE)
+                if (nob <= IBLND_MSG_SIZE && !lntmsg->msg_rdma_force)
                         break;                  /* send IMMEDIATE */
 
                tx = kiblnd_get_idle_tx(ni, target.nid);

diff --git a/lnet/lnet/lib-md.c b/lnet/lnet/lib-md.c
index 550b233..68da79e 100644 (file)
--- a/lnet/lnet/lib-md.c
+++ b/lnet/lnet/lib-md.c
@@ -104,10 +104,9 @@ lnet_kvaddr_to_page(unsigned long vaddr)
 }
 EXPORT_SYMBOL(lnet_kvaddr_to_page);
 
-int
-lnet_cpt_of_md(struct lnet_libmd *md, unsigned int offset)
+struct page *
+lnet_get_first_page(struct lnet_libmd *md, unsigned int offset)
 {
-       int cpt = CFS_CPT_ANY;
        unsigned int niov;
        struct bio_vec *kiov;
 
@@ -120,7 +119,7 @@ lnet_cpt_of_md(struct lnet_libmd *md, unsigned int offset)
                md = lnet_handle2md(&md->md_bulk_handle);
 
        if (!md || md->md_niov == 0)
-               return CFS_CPT_ANY;
+               return NULL;
 
        kiov = md->md_kiov;
        niov = md->md_niov;
@@ -131,12 +130,28 @@ lnet_cpt_of_md(struct lnet_libmd *md, unsigned int offset)
                kiov++;
                if (niov == 0) {
                        CERROR("offset %d goes beyond kiov\n", offset);
-                       goto out;
+                       return NULL;
                }
        }
 
-       cpt = cfs_cpt_of_node(lnet_cpt_table(),
-                             page_to_nid(kiov->bv_page));
+       return kiov->bv_page;
+}
+
+int
+lnet_cpt_of_md(struct lnet_libmd *md, unsigned int offset)
+{
+       struct page *page;
+       int cpt = CFS_CPT_ANY;
+
+       page = lnet_get_first_page(md, offset);
+       if (!page) {
+               CDEBUG(D_NET, "Couldn't resolve first page of md %p with offset %u\n",
+                       md, offset);
+               goto out;
+       }
+
+       cpt = cfs_cpt_of_node(lnet_cpt_table(), page_to_nid(page));
+
 out:
        return cpt;
 }