cifs: distribute channels across interfaces based on speed

Today, if the server interfaces RSS capable, we simply
choose the fastest interface to setup a channel. This is not
a scalable approach, and does not make a lot of attempt to
distribute the connections.

This change does a weighted distribution of channels across
all the available server interfaces, where the weight is
a function of the advertised interface speed.

Also make sure that we don't mix rdma and non-rdma for channels.

Signed-off-by: Shyam Prasad N <sprasad@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>

3 files changed, 88 insertions, 14 deletions

diff --git a/fs/smb/client/cifs_debug.c b/fs/smb/client/cifs_debug.c
index 772d4226957f..5596c9f30ccb 100644
--- a/fs/smb/client/cifs_debug.c
+++ b/fs/smb/client/cifs_debug.c
@@ -284,6 +284,8 @@ static int cifs_debug_data_proc_show(struct seq_file *m, void *v)
 	struct cifs_ses *ses;
 	struct cifs_tcon *tcon;
 	struct cifs_server_iface *iface;
+	size_t iface_weight = 0, iface_min_speed = 0;
+	struct cifs_server_iface *last_iface = NULL;
 	int c, i, j;
 
 	seq_puts(m,
@@ -549,11 +551,25 @@ skip_rdma:
 					   "\tLast updated: %lu seconds ago",
 					   ses->iface_count,
 					   (jiffies - ses->iface_last_update) / HZ);
+
+			last_iface = list_last_entry(&ses->iface_list,
+						     struct cifs_server_iface,
+						     iface_head);
+			iface_min_speed = last_iface->speed;
+
 			j = 0;
 			list_for_each_entry(iface, &ses->iface_list,
 						 iface_head) {
 				seq_printf(m, "\n\t%d)", ++j);
 				cifs_dump_iface(m, iface);
+
+				iface_weight = iface->speed / iface_min_speed;
+				seq_printf(m, "\t\tWeight (cur,total): (%zu,%zu)"
+					   "\n\t\tAllocated channels: %u\n",
+					   iface->weight_fulfilled,
+					   iface_weight,
+					   iface->num_channels);
+
 				if (is_ses_using_iface(ses, iface))
 					seq_puts(m, "\t\t[CONNECTED]\n");
 			}
diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h
index eae138040edf..30763c68cc39 100644
--- a/fs/smb/client/cifsglob.h
+++ b/fs/smb/client/cifsglob.h
@@ -969,6 +969,8 @@ struct cifs_server_iface {
 	struct list_head iface_head;
 	struct kref refcount;
 	size_t speed;
+	size_t weight_fulfilled;
+	unsigned int num_channels;
 	unsigned int rdma_capable : 1;
 	unsigned int rss_capable : 1;
 	unsigned int is_active : 1; /* unset if non existent */
diff --git a/fs/smb/client/sess.c b/fs/smb/client/sess.c
index d13a24613710..336b64d93e41 100644
--- a/fs/smb/client/sess.c
+++ b/fs/smb/client/sess.c
@@ -179,7 +179,9 @@ int cifs_try_adding_channels(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses)
 	int left;
 	int rc = 0;
 	int tries = 0;
+	size_t iface_weight = 0, iface_min_speed = 0;
 	struct cifs_server_iface *iface = NULL, *niface = NULL;
+	struct cifs_server_iface *last_iface = NULL;
 
 	spin_lock(&ses->chan_lock);
 
@@ -207,21 +209,11 @@ int cifs_try_adding_channels(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses)
 	}
 	spin_unlock(&ses->chan_lock);
 
-	/*
-	 * Keep connecting to same, fastest, iface for all channels as
-	 * long as its RSS. Try next fastest one if not RSS or channel
-	 * creation fails.
-	 */
-	spin_lock(&ses->iface_lock);
-	iface = list_first_entry(&ses->iface_list, struct cifs_server_iface,
-				 iface_head);
-	spin_unlock(&ses->iface_lock);
-
 	while (left > 0) {
 
 		tries++;
 		if (tries > 3*ses->chan_max) {
-			cifs_dbg(FYI, "too many channel open attempts (%d channels left to open)\n",
+			cifs_dbg(VFS, "too many channel open attempts (%d channels left to open)\n",
 				 left);
 			break;
 		}
@@ -229,17 +221,35 @@ int cifs_try_adding_channels(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses)
 		spin_lock(&ses->iface_lock);
 		if (!ses->iface_count) {
 			spin_unlock(&ses->iface_lock);
+			cifs_dbg(VFS, "server %s does not advertise interfaces\n",
+				      ses->server->hostname);
 			break;
 		}
 
+		if (!iface)
+			iface = list_first_entry(&ses->iface_list, struct cifs_server_iface,
+						 iface_head);
+		last_iface = list_last_entry(&ses->iface_list, struct cifs_server_iface,
+					     iface_head);
+		iface_min_speed = last_iface->speed;
+
 		list_for_each_entry_safe_from(iface, niface, &ses->iface_list,
 				    iface_head) {
+			/* do not mix rdma and non-rdma interfaces */
+			if (iface->rdma_capable != ses->server->rdma)
+				continue;
+
 			/* skip ifaces that are unusable */
 			if (!iface->is_active ||
 			    (is_ses_using_iface(ses, iface) &&
-			     !iface->rss_capable)) {
+			     !iface->rss_capable))
+				continue;
+
+			/* check if we already allocated enough channels */
+			iface_weight = iface->speed / iface_min_speed;
+
+			if (iface->weight_fulfilled >= iface_weight)
 				continue;
-			}
 
 			/* take ref before unlock */
 			kref_get(&iface->refcount);
@@ -256,10 +266,21 @@ int cifs_try_adding_channels(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses)
 				continue;
 			}
 
-			cifs_dbg(FYI, "successfully opened new channel on iface:%pIS\n",
+			iface->num_channels++;
+			iface->weight_fulfilled++;
+			cifs_dbg(VFS, "successfully opened new channel on iface:%pIS\n",
 				 &iface->sockaddr);
 			break;
 		}
+
+		/* reached end of list. reset weight_fulfilled and start over */
+		if (list_entry_is_head(iface, &ses->iface_list, iface_head)) {
+			list_for_each_entry(iface, &ses->iface_list, iface_head)
+				iface->weight_fulfilled = 0;
+			spin_unlock(&ses->iface_lock);
+			iface = NULL;
+			continue;
+		}
 		spin_unlock(&ses->iface_lock);
 
 		left--;
@@ -278,8 +299,10 @@ int
 cifs_chan_update_iface(struct cifs_ses *ses, struct TCP_Server_Info *server)
 {
 	unsigned int chan_index;
+	size_t iface_weight = 0, iface_min_speed = 0;
 	struct cifs_server_iface *iface = NULL;
 	struct cifs_server_iface *old_iface = NULL;
+	struct cifs_server_iface *last_iface = NULL;
 	int rc = 0;
 
 	spin_lock(&ses->chan_lock);
@@ -299,13 +322,34 @@ cifs_chan_update_iface(struct cifs_ses *ses, struct TCP_Server_Info *server)
 	spin_unlock(&ses->chan_lock);
 
 	spin_lock(&ses->iface_lock);
+	if (!ses->iface_count) {
+		spin_unlock(&ses->iface_lock);
+		cifs_dbg(VFS, "server %s does not advertise interfaces\n", ses->server->hostname);
+		return 0;
+	}
+
+	last_iface = list_last_entry(&ses->iface_list, struct cifs_server_iface,
+				     iface_head);
+	iface_min_speed = last_iface->speed;
+
 	/* then look for a new one */
 	list_for_each_entry(iface, &ses->iface_list, iface_head) {
+		/* do not mix rdma and non-rdma interfaces */
+		if (iface->rdma_capable != server->rdma)
+			continue;
+
 		if (!iface->is_active ||
 		    (is_ses_using_iface(ses, iface) &&
 		     !iface->rss_capable)) {
 			continue;
 		}
+
+		/* check if we already allocated enough channels */
+		iface_weight = iface->speed / iface_min_speed;
+
+		if (iface->weight_fulfilled >= iface_weight)
+			continue;
+
 		kref_get(&iface->refcount);
 		break;
 	}
@@ -321,10 +365,22 @@ cifs_chan_update_iface(struct cifs_ses *ses, struct TCP_Server_Info *server)
 		cifs_dbg(FYI, "replacing iface: %pIS with %pIS\n",
 			 &old_iface->sockaddr,
 			 &iface->sockaddr);
+
+		old_iface->num_channels--;
+		if (old_iface->weight_fulfilled)
+			old_iface->weight_fulfilled--;
+		iface->num_channels++;
+		iface->weight_fulfilled++;
+
 		kref_put(&old_iface->refcount, release_iface);
 	} else if (old_iface) {
 		cifs_dbg(FYI, "releasing ref to iface: %pIS\n",
 			 &old_iface->sockaddr);
+
+		old_iface->num_channels--;
+		if (old_iface->weight_fulfilled)
+			old_iface->weight_fulfilled--;
+
 		kref_put(&old_iface->refcount, release_iface);
 	} else {
 		WARN_ON(!iface);