From 7b3971ad0152eb1bb89a982333970118a6bd4922 Mon Sep 17 00:00:00 2001
From: Pranith Kumar K <pkarampu@redhat.com>
Date: Wed, 4 Sep 2019 12:06:34 +0530
Subject: cluster/ec: Fail fsync/flush for files on update size/version failure

Problem:
If update size/version is not successful on the file, updates on the
same stripe could lead to data corruptions if the earlier un-aligned
write is not successful on all the bricks. Application won't have
any knowledge of this because update size/version happens in the
background.

Fix:
Fail fsync/flush on fds that are opened before update-size-version
went bad.

fixes: bz#1748836
Change-Id: I9d323eddcda703bd27d55f340c4079d76e06e492
Signed-off-by: Pranith Kumar K <pkarampu@redhat.com>
---
 tests/basic/ec/ec-badfd.c | 124 ++++++++++++++++++++++++++++++++++++++++++++++
 tests/basic/ec/ec-badfd.t |  26 ++++++++++
 2 files changed, 150 insertions(+)
 create mode 100644 tests/basic/ec/ec-badfd.c
 create mode 100755 tests/basic/ec/ec-badfd.t

(limited to 'tests/basic')

diff --git a/tests/basic/ec/ec-badfd.c b/tests/basic/ec/ec-badfd.c
new file mode 100644
index 00000000000..8be23c10eaf
--- /dev/null
+++ b/tests/basic/ec/ec-badfd.c
@@ -0,0 +1,124 @@
+#include <stdio.h>
+#include <fcntl.h>
+#include <unistd.h>
+#include <time.h>
+#include <limits.h>
+#include <string.h>
+#include <stdlib.h>
+#include <errno.h>
+#include <glusterfs/api/glfs.h>
+#include <glusterfs/api/glfs-handles.h>
+
+int
+fill_iov(struct iovec *iov, char fillchar, int count)
+{
+    int ret = -1;
+
+    iov->iov_base = malloc(count + 1);
+    if (iov->iov_base == NULL) {
+        return ret;
+    } else {
+        iov->iov_len = count;
+        ret = 0;
+    }
+    memset(iov->iov_base, fillchar, count);
+    memset(iov->iov_base + count, '\0', 1);
+
+    return ret;
+}
+
+int
+write_sync(glfs_t *fs, glfs_fd_t *glfd, int char_count)
+{
+    ssize_t ret = -1;
+    int flags = O_RDWR;
+    struct iovec iov = {0};
+
+    ret = fill_iov(&iov, 'a', char_count);
+    if (ret) {
+        fprintf(stderr, "failed to create iov");
+        goto out;
+    }
+
+    ret = glfs_pwritev(glfd, &iov, 1, 0, flags);
+out:
+    if (ret < 0) {
+        fprintf(stderr, "glfs_pwritev failed, %d", errno);
+    }
+    return ret;
+}
+
+int
+main(int argc, char *argv[])
+{
+    glfs_t *fs = NULL;
+    glfs_fd_t *fd = NULL;
+    int ret = 1;
+    char volume_cmd[4096] = {0};
+
+    if (argc != 4) {
+        fprintf(stderr, "Syntax: %s <host> <volname> <file>\n", argv[0]);
+        return 1;
+    }
+
+    fs = glfs_new(argv[2]);
+    if (!fs) {
+        fprintf(stderr, "glfs_new: returned NULL\n");
+        return 1;
+    }
+
+    ret = glfs_set_volfile_server(fs, "tcp", argv[1], 24007);
+    if (ret != 0) {
+        fprintf(stderr, "glfs_set_volfile_server: returned %d\n", ret);
+        goto out;
+    }
+    ret = glfs_set_logging(fs, "/tmp/ec-badfd.log", 7);
+    if (ret != 0) {
+        fprintf(stderr, "glfs_set_logging: returned %d\n", ret);
+        goto out;
+    }
+    ret = glfs_init(fs);
+    if (ret != 0) {
+        fprintf(stderr, "glfs_init: returned %d\n", ret);
+        goto out;
+    }
+
+    fd = glfs_open(fs, argv[3], O_RDWR);
+    if (fd == NULL) {
+        fprintf(stderr, "glfs_open: returned NULL\n");
+        goto out;
+    }
+
+    ret = write_sync(fs, fd, 16);
+    if (ret < 0) {
+        fprintf(stderr, "write_sync failed\n");
+    }
+
+    snprintf(volume_cmd, sizeof(volume_cmd),
+             "gluster --mode=script volume stop %s", argv[2]);
+    /*Stop the volume so that update-size-version fails*/
+    system(volume_cmd);
+    sleep(8); /* 3 seconds more than eager-lock-timeout*/
+    snprintf(volume_cmd, sizeof(volume_cmd),
+             "gluster --mode=script volume start %s", argv[2]);
+    system(volume_cmd);
+    sleep(8); /*wait for bricks to come up*/
+    ret = glfs_fsync(fd, NULL, NULL);
+    if (ret == 0) {
+        fprintf(stderr, "fsync succeeded on a BADFD\n");
+        exit(1);
+    }
+
+    ret = glfs_close(fd);
+    if (ret == 0) {
+        fprintf(stderr, "flush succeeded on a BADFD\n");
+        exit(1);
+    }
+    ret = 0;
+
+out:
+    unlink("/tmp/ec-badfd.log");
+    glfs_fini(fs);
+
+    return ret;
+}
diff --git a/tests/basic/ec/ec-badfd.t b/tests/basic/ec/ec-badfd.t
new file mode 100755
index 00000000000..56feb47f115
--- /dev/null
+++ b/tests/basic/ec/ec-badfd.t
@@ -0,0 +1,26 @@
+#!/bin/bash
+
+. $(dirname $0)/../../include.rc
+. $(dirname $0)/../../volume.rc
+
+cleanup;
+
+TEST glusterd
+TEST pidof glusterd
+
+TEST $CLI volume create $V0 disperse 6 redundancy 2 $H0:$B0/${V0}{1..6}
+TEST $CLI volume set $V0 performance.write-behind off
+TEST $CLI volume set $V0 disperse.eager-lock-timeout 5
+
+TEST $CLI volume start $V0
+EXPECT 'Started' volinfo_field $V0 'Status'
+
+TEST $GFS -s $H0 --volfile-id $V0 $M0
+EXPECT_WITHIN $CHILD_UP_TIMEOUT "6" ec_child_up_count $V0 0
+TEST touch $M0/file
+
+TEST build_tester $(dirname $0)/ec-badfd.c -lgfapi -Wall -O2
+TEST $(dirname $0)/ec-badfd $H0 $V0 /file
+cleanup_tester $(dirname ${0})/ec-badfd
+
+cleanup;
-- 
cgit