[PATCH v6 4/5] 9pfs: T_readdir latency optimization

[Christian Schoenebeck]

Make top half really top half and bottom half really bottom half:

Each T_readdir request handling is hopping between threads (main
I/O thread and background I/O driver threads) several times for
every individual directory entry, which sums up to huge latencies
for handling just a single T_readdir request.

Instead of doing that, collect now all required directory entries
(including all potentially required stat buffers for each entry) in
one rush on a background I/O thread from fs driver by calling the
previously added function v9fs_co_readdir_many() instead of
v9fs_co_readdir(), then assemble the entire resulting network
response message for the readdir request on main I/O thread. The
fs driver is still aborting the directory entry retrieval loop
(on the background I/O thread inside of v9fs_co_readdir_many())
as soon as it would exceed the client's requested maximum R_readdir
response size. So this will not introduce a performance penalty on
another end.

Signed-off-by: Christian Schoenebeck <address@hidden>
---
 hw/9pfs/9p.c | 122 +++++++++++++++++++++++----------------------------
 1 file changed, 55 insertions(+), 67 deletions(-)

diff --git a/hw/9pfs/9p.c b/hw/9pfs/9p.c
index 43584aca41..8283a3cfbb 100644
--- a/hw/9pfs/9p.c
+++ b/hw/9pfs/9p.c
@@ -971,30 +971,6 @@ static int coroutine_fn fid_to_qid(V9fsPDU *pdu, 
V9fsFidState *fidp,
     return 0;
 }
 
-static int coroutine_fn dirent_to_qid(V9fsPDU *pdu, V9fsFidState *fidp,
-                                      struct dirent *dent, V9fsQID *qidp)
-{
-    struct stat stbuf;
-    V9fsPath path;
-    int err;
-
-    v9fs_path_init(&path);
-
-    err = v9fs_co_name_to_path(pdu, &fidp->path, dent->d_name, &path);
-    if (err < 0) {
-        goto out;
-    }
-    err = v9fs_co_lstat(pdu, &path, &stbuf);
-    if (err < 0) {
-        goto out;
-    }
-    err = stat_to_qid(pdu, &stbuf, qidp);
-
-out:
-    v9fs_path_free(&path);
-    return err;
-}
-
 V9fsPDU *pdu_alloc(V9fsState *s)
 {
     V9fsPDU *pdu = NULL;
@@ -2337,6 +2313,18 @@ size_t v9fs_readdir_response_size(V9fsString *name)
     return 24 + v9fs_string_size(name);
 }
 
+static void v9fs_free_dirents(struct V9fsDirEnt *e)
+{
+    struct V9fsDirEnt *next = NULL;
+
+    for (; e; e = next) {
+        next = e->next;
+        g_free(e->dent);
+        g_free(e->st);
+        g_free(e);
+    }
+}
+
 static int coroutine_fn v9fs_do_readdir(V9fsPDU *pdu, V9fsFidState *fidp,
                                         int32_t max_count)
 {
@@ -2345,54 +2333,53 @@ static int coroutine_fn v9fs_do_readdir(V9fsPDU *pdu, 
V9fsFidState *fidp,
     V9fsString name;
     int len, err = 0;
     int32_t count = 0;
-    off_t saved_dir_pos;
     struct dirent *dent;
+    struct stat *st;
+    struct V9fsDirEnt *entries = NULL;
 
-    /* save the directory position */
-    saved_dir_pos = v9fs_co_telldir(pdu, fidp);
-    if (saved_dir_pos < 0) {
-        return saved_dir_pos;
-    }
-
-    while (1) {
-        v9fs_readdir_lock(&fidp->fs.dir);
+    /*
+     * inode remapping requires the device id, which in turn might be
+     * different for different directory entries, so if inode remapping is
+     * enabled we have to make a full stat for each directory entry
+     */
+    const bool dostat = pdu->s->ctx.export_flags & V9FS_REMAP_INODES;
 
-        err = v9fs_co_readdir(pdu, fidp, &dent);
-        if (err || !dent) {
-            break;
-        }
-        v9fs_string_init(&name);
-        v9fs_string_sprintf(&name, "%s", dent->d_name);
-        if ((count + v9fs_readdir_response_size(&name)) > max_count) {
-            v9fs_readdir_unlock(&fidp->fs.dir);
+    /*
+     * Fetch all required directory entries altogether on a background IO
+     * thread from fs driver. We don't want to do that for each entry
+     * individually, because hopping between threads (this main IO thread
+     * and background IO driver thread) would sum up to huge latencies.
+     */
+    count = v9fs_co_readdir_many(pdu, fidp, &entries, max_count, dostat);
+    if (count < 0) {
+        err = count;
+        count = 0;
+        goto out;
+    }
+    count = 0;
 
-            /* Ran out of buffer. Set dir back to old position and return */
-            v9fs_co_seekdir(pdu, fidp, saved_dir_pos);
-            v9fs_string_free(&name);
-            return count;
-        }
+    for (struct V9fsDirEnt *e = entries; e; e = e->next) {
+        dent = e->dent;
 
         if (pdu->s->ctx.export_flags & V9FS_REMAP_INODES) {
-            /*
-             * dirent_to_qid() implies expensive stat call for each entry,
-             * we must do that here though since inode remapping requires
-             * the device id, which in turn might be different for
-             * different entries; we cannot make any assumption to avoid
-             * that here.
-             */
-            err = dirent_to_qid(pdu, fidp, dent, &qid);
+            st = e->st;
+            /* e->st should never be NULL, but just to be sure */
+            if (!st) {
+                err = -1;
+                break;
+            }
+
+            /* remap inode */
+            err = stat_to_qid(pdu, st, &qid);
             if (err < 0) {
-                v9fs_readdir_unlock(&fidp->fs.dir);
-                v9fs_co_seekdir(pdu, fidp, saved_dir_pos);
-                v9fs_string_free(&name);
-                return err;
+                break;
             }
         } else {
             /*
              * Fill up just the path field of qid because the client uses
              * only that. To fill the entire qid structure we will have
              * to stat each dirent found, which is expensive. For the
-             * latter reason we don't call dirent_to_qid() here. Only drawback
+             * latter reason we don't call stat_to_qid() here. Only drawback
              * is that no multi-device export detection of stat_to_qid()
              * would be done and provided as error to the user here. But
              * user would get that error anyway when accessing those
@@ -2405,25 +2392,26 @@ static int coroutine_fn v9fs_do_readdir(V9fsPDU *pdu, 
V9fsFidState *fidp,
             qid.version = 0;
         }
 
+        v9fs_string_init(&name);
+        v9fs_string_sprintf(&name, "%s", dent->d_name);
+
         /* 11 = 7 + 4 (7 = start offset, 4 = space for storing count) */
         len = pdu_marshal(pdu, 11 + count, "Qqbs",
                           &qid, dent->d_off,
                           dent->d_type, &name);
 
-        v9fs_readdir_unlock(&fidp->fs.dir);
+        v9fs_string_free(&name);
 
         if (len < 0) {
-            v9fs_co_seekdir(pdu, fidp, saved_dir_pos);
-            v9fs_string_free(&name);
-            return len;
+            err = len;
+            break;
         }
+
         count += len;
-        v9fs_string_free(&name);
-        saved_dir_pos = dent->d_off;
     }
 
-    v9fs_readdir_unlock(&fidp->fs.dir);
-
+out:
+    v9fs_free_dirents(entries);
     if (err < 0) {
         return err;
     }
-- 
2.20.1