gfapi/handleops: Introducing glfs_xreaddirplus_r() fop for handleops

Its known that readdirplus operation fetches stat as well for each of the
dirents. But often applications may need extra information, like for eg.,
NFS-Ganesha which operates on handles needs handles for each of those
dirents returned. So this would require extra calls to the backend, in this
case LOOKUP (which is very expensive operation) resulting in very low
readdir performance.

To address that introducing this new API using which applications can
make request for any extra information to be returned as part of
readdirplus response.

Currently this new api returns stat and handles as demanded by application.
The synopsis of the API is noted in glfs.h.

@todo:
* Enhance test script using this new API

Below were the perf results on single brick volume with and without
these changes -

Dataset used -
10*100 directories and each directory containing 100 empty files.

I used NFS-Ganesha application to test these changes -
>for i in {1..5}; do systemctl restart nfs-ganesha; sleep 10; mount -t nfs -o vers=4 localhost:/brick_vol /mnt; cd /mnt; echo "ITERATION$i"; date; find . > tmp-nfs.log; date; cd /; umount /mnt; sleep 2; done;

Without these changes -
ITERATION1
Mon Mar 20 17:22:26 IST 2017
Mon Mar 20 17:23:18 IST 2017
ITERATION2
Mon Mar 20 17:23:39 IST 2017
Mon Mar 20 17:24:28 IST 2017
ITERATION3
Mon Mar 20 17:24:49 IST 2017
Mon Mar 20 17:25:36 IST 2017
ITERATION4
Mon Mar 20 17:30:57 IST 2017
Mon Mar 20 17:31:37 IST 2017
ITERATION5
Mon Mar 20 17:31:57 IST 2017
Mon Mar 20 17:32:40 IST 2017
[root@dhcp35-197 /]#

On an average ~46.2 sec

With these changes applied -
ITERATION1
Mon Mar 20 17:35:03 IST 2017
Mon Mar 20 17:35:15 IST 2017
ITERATION2
Mon Mar 20 17:35:36 IST 2017
Mon Mar 20 17:35:46 IST 2017
ITERATION3
Mon Mar 20 17:36:06 IST 2017
Mon Mar 20 17:36:17 IST 2017
ITERATION4
Mon Mar 20 17:41:38 IST 2017
Mon Mar 20 17:41:49 IST 2017
ITERATION5
Mon Mar 20 17:42:10 IST 2017
Mon Mar 20 17:42:20 IST 2017

On an average ~10.8 sec

Updates #174
BUG: 1442950
Change-Id: I0f74f74dc62085ca4c4a23c38e3edc84bd850876
Signed-off-by: Soumya Koduri <skoduri@redhat.com>
Reviewed-on: https://review.gluster.org/15663
Smoke: Gluster Build System <jenkins@build.gluster.org>
NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org>
Reviewed-by: Niels de Vos <ndevos@redhat.com>
CentOS-regression: Gluster Build System <jenkins@build.gluster.org>

1 files changed, 136 insertions, 1 deletions

diff --git a/api/src/glfs-fops.c b/api/src/glfs-fops.c
index 0e5b206b98c..1bb958fc1b7 100644
--- a/api/src/glfs-fops.c
+++ b/api/src/glfs-fops.c
@@ -2792,7 +2792,7 @@ glfd_entry_next (struct glfs_fd *glfd, int plus)
 }
 
 
-static struct dirent *
+struct dirent *
 glfs_readdirbuf_get (struct glfs_fd *glfd)
 {
         struct dirent *buf = NULL;
@@ -4608,3 +4608,138 @@ out:
 invalid_fs:
         return ret;
 }
+
+/*
+ * Given glfd of a directory, this function does readdirp and returns
+ * xstat along with dirents.
+ */
+int
+pub_glfs_xreaddirplus_r (struct glfs_fd *glfd, uint32_t flags,
+                         struct glfs_xreaddirp_stat **xstat_p,
+                         struct dirent *ext,
+                         struct dirent **res)
+{
+        int              ret = -1;
+        gf_dirent_t     *entry = NULL;
+        struct dirent   *buf = NULL;
+        struct glfs_xreaddirp_stat *xstat = NULL;
+
+        DECLARE_OLD_THIS;
+        __GLFS_ENTRY_VALIDATE_FD (glfd, invalid_fs);
+
+        GF_REF_GET (glfd);
+
+        GF_VALIDATE_OR_GOTO (THIS->name, xstat_p, out);
+        GF_VALIDATE_OR_GOTO (THIS->name, res, out);
+
+        errno = 0;
+
+        if (ext)
+                buf = ext;
+        else
+                buf = glfs_readdirbuf_get (glfd);
+
+        if (!buf)
+                goto out;
+
+        xstat = GF_CALLOC(1, sizeof(struct glfs_xreaddirp_stat),
+                          glfs_mt_xreaddirp_stat_t);
+
+        if (!xstat)
+                goto out;
+
+        /* this is readdirplus operation */
+        entry = glfd_entry_next (glfd, 1);
+
+        /* XXX: Ideally when we reach EOD, errno should have been
+         * set to ENOENT. But that doesn't seem to be the case.
+         *
+         * The only way to confirm if its EOD at this point is that
+         * errno == 0 and entry == NULL
+         */
+        if (errno)
+                goto out;
+
+        if (!entry) {
+                /* reached EOD, ret = 0  */
+                ret = 0;
+                *res = NULL;
+                goto out;
+        }
+
+        *res = buf;
+        gf_dirent_to_dirent (entry, buf);
+
+        if (flags & GFAPI_XREADDIRP_STAT) {
+                glfs_iatt_to_stat (glfd->fs, &entry->d_stat, &xstat->st);
+                xstat->flags_handled |= GFAPI_XREADDIRP_STAT;
+        }
+
+        if ((flags & GFAPI_XREADDIRP_HANDLE) &&
+                /* skip . and .. */
+                strcmp(buf->d_name, ".")
+                     && strcmp(buf->d_name, "..")) {
+
+                /* Now create object.
+                 * We can use "glfs_h_find_handle" as well as inodes would have
+                 * already got linked as part of 'gf_link_inodes_from_dirent' */
+                xstat->object = glfs_h_create_from_handle (glfd->fs,
+                                                        entry->d_stat.ia_gfid,
+                                                        GFAPI_HANDLE_LENGTH,
+                                                        NULL);
+
+                if (xstat->object) { /* success */
+                        /* note: xstat->object->inode->ref is taken
+                         * This shall be unref'ed when application does
+                         * glfs_free(xstat) */
+                        xstat->flags_handled |= GFAPI_XREADDIRP_HANDLE;
+                }
+        }
+
+        ret = xstat->flags_handled;
+        *xstat_p = xstat;
+
+out:
+        gf_msg_debug (THIS->name, 0,
+                      "xreaddirp- requested_flags (%x) , processed_flags (%x)",
+                      flags, xstat->flags_handled);
+
+        GF_REF_PUT (glfd);
+
+        if (ret < 0) {
+                gf_msg (THIS->name, GF_LOG_WARNING, errno,
+                        API_MSG_XREADDIRP_R_FAILED,
+                        "glfs_x_readdirp_r failed - reason (%s)",
+                        strerror(errno));
+
+                if (xstat)
+                        glfs_free (xstat);
+        }
+
+        __GLFS_EXIT_FS;
+
+        return ret;
+
+invalid_fs:
+        return -1;
+}
+GFAPI_SYMVER_PUBLIC_DEFAULT(glfs_xreaddirplus_r, 3.11.0);
+
+struct stat*
+pub_glfs_xreaddirplus_get_stat (struct glfs_xreaddirp_stat *xstat)
+{
+        GF_VALIDATE_OR_GOTO ("glfs_xreaddirplus_get_stat", xstat, out);
+
+        if (!xstat->flags_handled & GFAPI_XREADDIRP_STAT)
+                gf_msg (THIS->name, GF_LOG_ERROR, errno,
+                        LG_MSG_INVALID_ARG,
+                        "GFAPI_XREADDIRP_STAT is not set. Flags"
+                        "handled for xstat(%p) are (%x)",
+                        xstat, xstat->flags_handled);
+        return &xstat->st;
+
+out:
+        return NULL;
+}
+GFAPI_SYMVER_PUBLIC_DEFAULT(glfs_xreaddirplus_get_stat, 3.11.0);
+