performance/readdir-ahead: keep stats of cached dentries in sync with modifications

PROBLEM:

Stats of dentries that are readdirp'd ahead can become stale due to
fops like writes, truncate etc that modify the file pointed by
dentries. When a readdir is finally wound at offset corresponding to
these entries, the iatts that are returned to the application come
from readdir-ahead's cache, which are stale by now. This problem gets
further aggravated when caching translators/modules cache and continue
to serve this stale information.

FIX:

* Store the iatt in context of the inode pointed by dentry.
* Whenever the inode pointed by dentry undergoes modification, in cbk
  of modification fop, update the iatt stored in inode-ctx to reflect
  the modification.
* When serving a readdirp response from application, update iatts of
  dentries with the iatts stored in the context of inodes pointed by
  these dentries.
* Some fops don't have valid iatts in their responses. For eg., write
  response whose data is still cached in write-behind will have zeroed
  out stat. In this case keep only ia_type and ia_gfid and reset rest
  of the iatt members to zero.
  - fuse-bridge in this case just sends "entry" information back to
    kernel and attr is not sent.
  - gfapi sets entry->inode to NULL and zeroes out the entire stat
* There is one tiny race between the entry creation and a readdirp on
  its parent dir, which could cause the inode-ctx setting and inode
  ctx reading to happen on two different inode objects. To prevent
  this, when entry->inode doesn't eqaul to linked_inode,
  - fuse-bridge is made to send only "entry" information without
    attributes
  - gfapi sets entry->inode to NULL and zeroes out the entire stat.

Change-Id: Ia27ff49a61922e88c73a1547ad8aacc9968a69df
BUG: 1390050
Updates: bz#1390050
Signed-off-by: Krutika Dhananjay <kdhananj@redhat.com>
Signed-off-by: Raghavendra G <rgowdapp@redhat.com>

3 files changed, 99 insertions, 1 deletions

diff --git a/tests/basic/afr/split-brain-healing.t b/tests/basic/afr/split-brain-healing.t
index 773a8b33b12..c80f900b909 100644
--- a/tests/basic/afr/split-brain-healing.t
+++ b/tests/basic/afr/split-brain-healing.t
@@ -76,7 +76,6 @@ do
 done
 
 BIGGER_FILE_SIZE=$(stat -c %s file1)
-
 TEST $CLI volume start $V0 force
 EXPECT_WITHIN $PROCESS_UP_TIMEOUT "1" afr_child_up_status $V0 1
 EXPECT_WITHIN $PROCESS_UP_TIMEOUT "1" afr_child_up_status $V0 3
diff --git a/tests/bugs/readdir-ahead/bug-1390050.c b/tests/bugs/readdir-ahead/bug-1390050.c
new file mode 100644
index 00000000000..5593a1d4c0c
--- /dev/null
+++ b/tests/bugs/readdir-ahead/bug-1390050.c
@@ -0,0 +1,70 @@
+#include <stdio.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <dirent.h>
+#include <string.h>
+#include <errno.h>
+
+int
+main (int argc, char *argv[])
+{
+        const char  *glfs_dir          = NULL, *filepath = NULL;
+        DIR         *dirfd             = NULL;
+        int          filefd            = 0, ret = 0;
+        struct stat  stbuf             = {0, };
+        size_t       size_before_write = 0;
+
+        glfs_dir = argv[1];
+        filepath = argv[2];
+        dirfd = opendir (glfs_dir);
+        if (dirfd == NULL) {
+                fprintf (stderr, "opening directory failed (%s)\n",
+                         strerror (errno));
+                goto err;
+        }
+
+        filefd = open (filepath, O_RDWR);
+        if (filefd < 0) {
+                fprintf (stderr, "open failed on path %s (%s)\n", filepath,
+                         strerror (errno));
+                goto err;
+        }
+
+        ret = stat (filepath, &stbuf);
+        if (ret < 0) {
+                fprintf (stderr, "stat failed on path %s (%s)\n", filepath,
+                         strerror (errno));
+                goto err;
+        }
+
+        size_before_write = stbuf.st_size;
+
+        ret = write (filefd, "testdata", strlen ("testdata123") + 1);
+        if (ret <= 0) {
+                fprintf (stderr, "write failed (%s)\n", strerror (errno));
+                goto err;
+        }
+
+        while (readdir (dirfd)) {
+                /* do nothing */
+        }
+
+        ret = stat (filepath, &stbuf);
+        if (ret < 0) {
+                fprintf (stderr, "stat failed on path %s (%s)\n",
+                         strerror (errno));
+                goto err;
+        }
+
+        if (stbuf.st_size == size_before_write) {
+                fprintf (stderr, "file size (%lu) has not changed even after "
+                         "its written to\n", stbuf.st_size);
+                goto err;
+        }
+
+        return 0;
+err:
+        return -1;
+}
diff --git a/tests/bugs/readdir-ahead/bug-1390050.t b/tests/bugs/readdir-ahead/bug-1390050.t
new file mode 100644
index 00000000000..ab1d7d4ead9
--- /dev/null
+++ b/tests/bugs/readdir-ahead/bug-1390050.t
@@ -0,0 +1,29 @@
+#!/bin/bash
+
+. $(dirname $0)/../../include.rc
+. $(dirname $0)/../../volume.rc
+. $(dirname $0)/../../fileio.rc
+
+cleanup;
+
+TEST glusterd
+
+TEST $CLI volume create $V0 $H0:$B{0..1}/$V0
+TEST $CLI volume set $V0 readdir-ahead on
+
+DIRECTORY="$M0/subdir1/subdir2"
+
+#Make sure md-cache has large timeout to hold stat from readdirp_cbk in its cache
+TEST $CLI volume set $V0 performance.md-cache-timeout 600
+TEST $CLI volume start $V0
+TEST glusterfs --volfile-server=$H0 --volfile-id=$V0 $M0
+rm -rf $M0/*
+TEST mkdir -p $DIRECTORY
+rm -rf $DIRECTORY/*
+TEST touch $DIRECTORY/file{0..10}
+rdd_tester=$(dirname $0)/rdd-tester
+TEST build_tester $(dirname $0)/bug-1390050.c -o $rdd_tester
+TEST $rdd_tester $DIRECTORY $DIRECTORY/file4
+rm -f $rdd_tester
+cleanup;
+