zfs/cmd/ztest/ztest.c

4365 lines
111 KiB
C
Raw Normal View History

2008-11-20 20:01:55 +00:00
/*
* CDDL HEADER START
*
* The contents of this file are subject to the terms of the
* Common Development and Distribution License (the "License").
* You may not use this file except in compliance with the License.
*
* You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
* or http://www.opensolaris.org/os/licensing.
* See the License for the specific language governing permissions
* and limitations under the License.
*
* When distributing Covered Code, include this CDDL HEADER in each
* file and include the License file at usr/src/OPENSOLARIS.LICENSE.
* If applicable, add the following below this CDDL HEADER, with the
* fields enclosed by brackets "[]" replaced with your own identifying
* information: Portions Copyright [yyyy] [name of copyright owner]
*
* CDDL HEADER END
*/
/*
2009-07-02 22:44:48 +00:00
* Copyright 2009 Sun Microsystems, Inc. All rights reserved.
2008-11-20 20:01:55 +00:00
* Use is subject to license terms.
*/
/*
* The objective of this program is to provide a DMU/ZAP/SPA stress test
* that runs entirely in userland, is easy to use, and easy to extend.
*
* The overall design of the ztest program is as follows:
*
* (1) For each major functional area (e.g. adding vdevs to a pool,
* creating and destroying datasets, reading and writing objects, etc)
* we have a simple routine to test that functionality. These
* individual routines do not have to do anything "stressful".
*
* (2) We turn these simple functionality tests into a stress test by
* running them all in parallel, with as many threads as desired,
* and spread across as many datasets, objects, and vdevs as desired.
*
* (3) While all this is happening, we inject faults into the pool to
* verify that self-healing data really works.
*
* (4) Every time we open a dataset, we change its checksum and compression
* functions. Thus even individual objects vary from block to block
* in which checksum they use and whether they're compressed.
*
* (5) To verify that we never lose on-disk consistency after a crash,
* we run the entire test in a child of the main process.
* At random times, the child self-immolates with a SIGKILL.
* This is the software equivalent of pulling the power cord.
* The parent then runs the test again, using the existing
* storage pool, as many times as desired.
*
* (6) To verify that we don't have future leaks or temporal incursions,
* many of the functional tests record the transaction group number
* as part of their data. When reading old data, they verify that
* the transaction group number is less than the current, open txg.
* If you add a new test, please do this if applicable.
*
* When run with no arguments, ztest runs for about five minutes and
* produces no output if successful. To get a little bit of information,
* specify -V. To get more information, specify -VV, and so on.
*
* To turn this into an overnight stress test, use -T to specify run time.
*
* You can ask more more vdevs [-v], datasets [-d], or threads [-t]
* to increase the pool capacity, fanout, and overall stress level.
*
* The -N(okill) option will suppress kills, so each child runs to completion.
* This can be useful when you're trying to distinguish temporal incursions
* from plain old race conditions.
*/
#include <sys/zfs_context.h>
#include <sys/spa.h>
#include <sys/dmu.h>
#include <sys/txg.h>
2009-07-02 22:44:48 +00:00
#include <sys/dbuf.h>
2008-11-20 20:01:55 +00:00
#include <sys/zap.h>
#include <sys/dmu_objset.h>
#include <sys/poll.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <sys/wait.h>
#include <sys/mman.h>
#include <sys/resource.h>
#include <sys/zio.h>
#include <sys/zio_checksum.h>
#include <sys/zio_compress.h>
#include <sys/zil.h>
#include <sys/vdev_impl.h>
#include <sys/vdev_file.h>
2008-11-20 20:01:55 +00:00
#include <sys/spa_impl.h>
#include <sys/dsl_prop.h>
2009-07-02 22:44:48 +00:00
#include <sys/dsl_dataset.h>
2008-11-20 20:01:55 +00:00
#include <sys/refcount.h>
#include <stdio.h>
#include <stdio_ext.h>
#include <stdlib.h>
#include <unistd.h>
#include <signal.h>
#include <umem.h>
#include <dlfcn.h>
#include <ctype.h>
#include <math.h>
#include <sys/fs/zfs.h>
static char cmdname[] = "ztest";
static char *zopt_pool = cmdname;
static uint64_t zopt_vdevs = 5;
static uint64_t zopt_vdevtime;
static int zopt_ashift = SPA_MINBLOCKSHIFT;
static int zopt_mirrors = 2;
static int zopt_raidz = 4;
static int zopt_raidz_parity = 1;
static size_t zopt_vdev_size = SPA_MINDEVSIZE;
static int zopt_datasets = 7;
static int zopt_threads = 23;
static uint64_t zopt_passtime = 60; /* 60 seconds */
static uint64_t zopt_killrate = 70; /* 70% kill rate */
static int zopt_verbose = 0;
static int zopt_init = 1;
static char *zopt_dir = "/tmp";
static uint64_t zopt_time = 300; /* 5 minutes */
static int zopt_maxfaults;
typedef struct ztest_block_tag {
uint64_t bt_objset;
uint64_t bt_object;
uint64_t bt_offset;
uint64_t bt_txg;
uint64_t bt_thread;
uint64_t bt_seq;
} ztest_block_tag_t;
typedef struct ztest_args {
char za_pool[MAXNAMELEN];
spa_t *za_spa;
objset_t *za_os;
zilog_t *za_zilog;
kthread_t *za_thread;
kt_did_t za_threadid;
2008-11-20 20:01:55 +00:00
uint64_t za_instance;
uint64_t za_random;
uint64_t za_diroff;
uint64_t za_diroff_shared;
uint64_t za_zil_seq;
hrtime_t za_start;
hrtime_t za_stop;
hrtime_t za_kill;
/*
* Thread-local variables can go here to aid debugging.
*/
ztest_block_tag_t za_rbt;
ztest_block_tag_t za_wbt;
dmu_object_info_t za_doi;
dmu_buf_t *za_dbuf;
} ztest_args_t;
typedef void ztest_func_t(ztest_args_t *);
/*
* Note: these aren't static because we want dladdr() to work.
*/
ztest_func_t ztest_dmu_read_write;
2009-07-02 22:44:48 +00:00
ztest_func_t ztest_dmu_read_write_zcopy;
2008-11-20 20:01:55 +00:00
ztest_func_t ztest_dmu_write_parallel;
ztest_func_t ztest_dmu_object_alloc_free;
ztest_func_t ztest_dmu_commit_callbacks;
2008-11-20 20:01:55 +00:00
ztest_func_t ztest_zap;
ztest_func_t ztest_zap_parallel;
ztest_func_t ztest_traverse;
ztest_func_t ztest_dsl_prop_get_set;
ztest_func_t ztest_dmu_objset_create_destroy;
ztest_func_t ztest_dmu_snapshot_create_destroy;
2009-07-02 22:44:48 +00:00
ztest_func_t ztest_dsl_dataset_promote_busy;
2008-11-20 20:01:55 +00:00
ztest_func_t ztest_spa_create_destroy;
ztest_func_t ztest_fault_inject;
ztest_func_t ztest_spa_rename;
2008-11-20 20:01:55 +00:00
ztest_func_t ztest_vdev_attach_detach;
ztest_func_t ztest_vdev_LUN_growth;
ztest_func_t ztest_vdev_add_remove;
ztest_func_t ztest_vdev_aux_add_remove;
2008-11-20 20:01:55 +00:00
ztest_func_t ztest_scrub;
typedef struct ztest_info {
ztest_func_t *zi_func; /* test function */
uint64_t zi_iters; /* iterations per execution */
uint64_t *zi_interval; /* execute every <interval> seconds */
uint64_t zi_calls; /* per-pass count */
uint64_t zi_call_time; /* per-pass time */
uint64_t zi_call_total; /* cumulative total */
uint64_t zi_call_target; /* target cumulative total */
} ztest_info_t;
uint64_t zopt_always = 0; /* all the time */
uint64_t zopt_often = 1; /* every second */
uint64_t zopt_sometimes = 10; /* every 10 seconds */
uint64_t zopt_rarely = 60; /* every 60 seconds */
ztest_info_t ztest_info[] = {
{ ztest_dmu_read_write, 1, &zopt_always },
2009-07-02 22:44:48 +00:00
{ ztest_dmu_read_write_zcopy, 1, &zopt_always },
2008-11-20 20:01:55 +00:00
{ ztest_dmu_write_parallel, 30, &zopt_always },
{ ztest_dmu_object_alloc_free, 1, &zopt_always },
{ ztest_dmu_commit_callbacks, 10, &zopt_always },
2008-11-20 20:01:55 +00:00
{ ztest_zap, 30, &zopt_always },
{ ztest_zap_parallel, 100, &zopt_always },
{ ztest_dsl_prop_get_set, 1, &zopt_sometimes },
{ ztest_dmu_objset_create_destroy, 1, &zopt_sometimes },
{ ztest_dmu_snapshot_create_destroy, 1, &zopt_sometimes },
{ ztest_spa_create_destroy, 1, &zopt_sometimes },
2008-11-20 20:01:55 +00:00
{ ztest_fault_inject, 1, &zopt_sometimes },
{ ztest_spa_rename, 1, &zopt_rarely },
{ ztest_vdev_attach_detach, 1, &zopt_rarely },
{ ztest_vdev_LUN_growth, 1, &zopt_rarely },
2009-07-02 22:44:48 +00:00
{ ztest_dsl_dataset_promote_busy, 1, &zopt_rarely },
2008-11-20 20:01:55 +00:00
{ ztest_vdev_add_remove, 1, &zopt_vdevtime },
{ ztest_vdev_aux_add_remove, 1, &zopt_vdevtime },
2008-11-20 20:01:55 +00:00
{ ztest_scrub, 1, &zopt_vdevtime },
};
#define ZTEST_FUNCS (sizeof (ztest_info) / sizeof (ztest_info_t))
#define ZTEST_SYNC_LOCKS 16
/*
* The following struct is used to hold a list of uncalled commit callbacks.
*
* The callbacks are ordered by txg number.
*/
typedef struct ztest_cb_list {
kmutex_t zcl_callbacks_lock;
list_t zcl_callbacks;
} ztest_cb_list_t;
2008-11-20 20:01:55 +00:00
/*
* Stuff we need to share writably between parent and child.
*/
typedef struct ztest_shared {
kmutex_t zs_vdev_lock;
krwlock_t zs_name_lock;
uint64_t zs_vdev_primaries;
uint64_t zs_vdev_aux;
uint64_t zs_enospc_count;
hrtime_t zs_start_time;
hrtime_t zs_stop_time;
uint64_t zs_alloc;
uint64_t zs_space;
ztest_info_t zs_info[ZTEST_FUNCS];
kmutex_t zs_sync_lock[ZTEST_SYNC_LOCKS];
uint64_t zs_seq[ZTEST_SYNC_LOCKS];
ztest_cb_list_t zs_cb_list;
2008-11-20 20:01:55 +00:00
} ztest_shared_t;
static char ztest_dev_template[] = "%s/%s.%llua";
static char ztest_aux_template[] = "%s/%s.%s.%llu";
2008-11-20 20:01:55 +00:00
static ztest_shared_t *ztest_shared;
static int ztest_random_fd;
static int ztest_dump_core = 1;
2009-07-02 22:44:48 +00:00
static uint64_t metaslab_sz;
static boolean_t ztest_exiting;
2008-11-20 20:01:55 +00:00
extern uint64_t metaslab_gang_bang;
2009-07-02 22:44:48 +00:00
extern uint64_t metaslab_df_alloc_threshold;
2008-11-20 20:01:55 +00:00
#define ZTEST_DIROBJ 1
#define ZTEST_MICROZAP_OBJ 2
#define ZTEST_FATZAP_OBJ 3
#define ZTEST_DIROBJ_BLOCKSIZE (1 << 10)
#define ZTEST_DIRSIZE 256
static void usage(boolean_t) __NORETURN;
/*
* These libumem hooks provide a reasonable set of defaults for the allocator's
* debugging facilities.
*/
const char *
2008-12-23 00:18:07 +00:00
_umem_debug_init(void)
2008-11-20 20:01:55 +00:00
{
return ("default,verbose"); /* $UMEM_DEBUG setting */
}
const char *
_umem_logging_init(void)
{
return ("fail,contents"); /* $UMEM_LOGGING setting */
}
#define FATAL_MSG_SZ 1024
char *fatal_msg;
static void
fatal(int do_perror, char *message, ...)
{
va_list args;
int save_errno = errno;
char buf[FATAL_MSG_SZ];
(void) fflush(stdout);
va_start(args, message);
(void) sprintf(buf, "ztest: ");
/* LINTED */
(void) vsprintf(buf + strlen(buf), message, args);
va_end(args);
if (do_perror) {
(void) snprintf(buf + strlen(buf), FATAL_MSG_SZ - strlen(buf),
": %s", strerror(save_errno));
}
(void) fprintf(stderr, "%s\n", buf);
fatal_msg = buf; /* to ease debugging */
if (ztest_dump_core)
abort();
exit(3);
}
static int
str2shift(const char *buf)
{
const char *ends = "BKMGTPEZ";
int i;
if (buf[0] == '\0')
return (0);
for (i = 0; i < strlen(ends); i++) {
if (toupper(buf[0]) == ends[i])
break;
}
if (i == strlen(ends)) {
(void) fprintf(stderr, "ztest: invalid bytes suffix: %s\n",
buf);
usage(B_FALSE);
}
if (buf[1] == '\0' || (toupper(buf[1]) == 'B' && buf[2] == '\0')) {
return (10*i);
}
(void) fprintf(stderr, "ztest: invalid bytes suffix: %s\n", buf);
usage(B_FALSE);
/* NOTREACHED */
}
static uint64_t
nicenumtoull(const char *buf)
{
char *end;
uint64_t val;
val = strtoull(buf, &end, 0);
if (end == buf) {
(void) fprintf(stderr, "ztest: bad numeric value: %s\n", buf);
usage(B_FALSE);
} else if (end[0] == '.') {
double fval = strtod(buf, &end);
fval *= pow(2, str2shift(end));
if (fval > UINT64_MAX) {
(void) fprintf(stderr, "ztest: value too large: %s\n",
buf);
usage(B_FALSE);
}
val = (uint64_t)fval;
} else {
int shift = str2shift(end);
if (shift >= 64 || (val << shift) >> shift != val) {
(void) fprintf(stderr, "ztest: value too large: %s\n",
buf);
usage(B_FALSE);
}
val <<= shift;
}
return (val);
}
static void
usage(boolean_t requested)
{
char nice_vdev_size[10];
char nice_gang_bang[10];
FILE *fp = requested ? stdout : stderr;
nicenum(zopt_vdev_size, nice_vdev_size);
nicenum(metaslab_gang_bang, nice_gang_bang);
(void) fprintf(fp, "Usage: %s\n"
"\t[-v vdevs (default: %llu)]\n"
"\t[-s size_of_each_vdev (default: %s)]\n"
"\t[-a alignment_shift (default: %d) (use 0 for random)]\n"
"\t[-m mirror_copies (default: %d)]\n"
"\t[-r raidz_disks (default: %d)]\n"
"\t[-R raidz_parity (default: %d)]\n"
"\t[-d datasets (default: %d)]\n"
"\t[-t threads (default: %d)]\n"
"\t[-g gang_block_threshold (default: %s)]\n"
"\t[-i initialize pool i times (default: %d)]\n"
"\t[-k kill percentage (default: %llu%%)]\n"
"\t[-p pool_name (default: %s)]\n"
"\t[-f file directory for vdev files (default: %s)]\n"
"\t[-V(erbose)] (use multiple times for ever more blather)\n"
"\t[-E(xisting)] (use existing pool instead of creating new one)\n"
"\t[-T time] total run time (default: %llu sec)\n"
"\t[-P passtime] time per pass (default: %llu sec)\n"
"\t[-h] (print help)\n"
"",
cmdname,
(u_longlong_t)zopt_vdevs, /* -v */
nice_vdev_size, /* -s */
zopt_ashift, /* -a */
zopt_mirrors, /* -m */
zopt_raidz, /* -r */
zopt_raidz_parity, /* -R */
zopt_datasets, /* -d */
zopt_threads, /* -t */
nice_gang_bang, /* -g */
zopt_init, /* -i */
(u_longlong_t)zopt_killrate, /* -k */
zopt_pool, /* -p */
zopt_dir, /* -f */
(u_longlong_t)zopt_time, /* -T */
(u_longlong_t)zopt_passtime); /* -P */
2008-11-20 20:01:55 +00:00
exit(requested ? 0 : 1);
}
static uint64_t
ztest_random(uint64_t range)
{
uint64_t r;
if (range == 0)
return (0);
if (read(ztest_random_fd, &r, sizeof (r)) != sizeof (r))
fatal(1, "short read from /dev/urandom");
return (r % range);
}
2009-01-15 21:59:39 +00:00
/* ARGSUSED */
2008-11-20 20:01:55 +00:00
static void
ztest_record_enospc(char *s)
{
ztest_shared->zs_enospc_count++;
}
static void
process_options(int argc, char **argv)
{
int opt;
uint64_t value;
/* By default, test gang blocks for blocks 32K and greater */
metaslab_gang_bang = 32 << 10;
while ((opt = getopt(argc, argv,
"v:s:a:m:r:R:d:t:g:i:k:p:f:VET:P:h")) != EOF) {
2008-11-20 20:01:55 +00:00
value = 0;
switch (opt) {
case 'v':
case 's':
case 'a':
case 'm':
case 'r':
case 'R':
case 'd':
case 't':
case 'g':
case 'i':
case 'k':
case 'T':
case 'P':
value = nicenumtoull(optarg);
}
switch (opt) {
case 'v':
zopt_vdevs = value;
break;
case 's':
zopt_vdev_size = MAX(SPA_MINDEVSIZE, value);
break;
case 'a':
zopt_ashift = value;
break;
case 'm':
zopt_mirrors = value;
break;
case 'r':
zopt_raidz = MAX(1, value);
break;
case 'R':
zopt_raidz_parity = MIN(MAX(value, 1), 2);
break;
case 'd':
zopt_datasets = MAX(1, value);
break;
case 't':
zopt_threads = MAX(1, value);
break;
case 'g':
metaslab_gang_bang = MAX(SPA_MINBLOCKSIZE << 1, value);
break;
case 'i':
zopt_init = value;
break;
case 'k':
zopt_killrate = value;
break;
case 'p':
zopt_pool = strdup(optarg);
break;
case 'f':
zopt_dir = strdup(optarg);
break;
case 'V':
zopt_verbose++;
break;
case 'E':
zopt_init = 0;
break;
case 'T':
zopt_time = value;
break;
case 'P':
zopt_passtime = MAX(1, value);
break;
case 'h':
usage(B_TRUE);
break;
case '?':
default:
usage(B_FALSE);
break;
}
}
zopt_raidz_parity = MIN(zopt_raidz_parity, zopt_raidz - 1);
zopt_vdevtime = (zopt_vdevs > 0 ? zopt_time / zopt_vdevs : UINT64_MAX);
zopt_maxfaults = MAX(zopt_mirrors, 1) * (zopt_raidz_parity + 1) - 1;
}
static uint64_t
ztest_get_ashift(void)
{
if (zopt_ashift == 0)
return (SPA_MINBLOCKSHIFT + ztest_random(3));
return (zopt_ashift);
}
static nvlist_t *
make_vdev_file(char *path, char *aux, size_t size, uint64_t ashift)
2008-11-20 20:01:55 +00:00
{
char pathbuf[MAXPATHLEN];
2008-11-20 20:01:55 +00:00
uint64_t vdev;
nvlist_t *file;
if (ashift == 0)
ashift = ztest_get_ashift();
if (path == NULL) {
path = pathbuf;
if (aux != NULL) {
vdev = ztest_shared->zs_vdev_aux;
(void) sprintf(path, ztest_aux_template,
zopt_dir, zopt_pool, aux, vdev);
} else {
vdev = ztest_shared->zs_vdev_primaries++;
(void) sprintf(path, ztest_dev_template,
zopt_dir, zopt_pool, vdev);
}
}
2008-11-20 20:01:55 +00:00
if (size != 0) {
int fd = open(path, O_RDWR | O_CREAT | O_TRUNC, 0666);
2008-11-20 20:01:55 +00:00
if (fd == -1)
fatal(1, "can't open %s", path);
2008-11-20 20:01:55 +00:00
if (ftruncate(fd, size) != 0)
fatal(1, "can't ftruncate %s", path);
2008-11-20 20:01:55 +00:00
(void) close(fd);
}
VERIFY(nvlist_alloc(&file, NV_UNIQUE_NAME, 0) == 0);
VERIFY(nvlist_add_string(file, ZPOOL_CONFIG_TYPE, VDEV_TYPE_FILE) == 0);
VERIFY(nvlist_add_string(file, ZPOOL_CONFIG_PATH, path) == 0);
2008-11-20 20:01:55 +00:00
VERIFY(nvlist_add_uint64(file, ZPOOL_CONFIG_ASHIFT, ashift) == 0);
return (file);
}
static nvlist_t *
make_vdev_raidz(char *path, char *aux, size_t size, uint64_t ashift, int r)
2008-11-20 20:01:55 +00:00
{
nvlist_t *raidz, **child;
int c;
if (r < 2)
return (make_vdev_file(path, aux, size, ashift));
2008-11-20 20:01:55 +00:00
child = umem_alloc(r * sizeof (nvlist_t *), UMEM_NOFAIL);
for (c = 0; c < r; c++)
child[c] = make_vdev_file(path, aux, size, ashift);
2008-11-20 20:01:55 +00:00
VERIFY(nvlist_alloc(&raidz, NV_UNIQUE_NAME, 0) == 0);
VERIFY(nvlist_add_string(raidz, ZPOOL_CONFIG_TYPE,
VDEV_TYPE_RAIDZ) == 0);
VERIFY(nvlist_add_uint64(raidz, ZPOOL_CONFIG_NPARITY,
zopt_raidz_parity) == 0);
VERIFY(nvlist_add_nvlist_array(raidz, ZPOOL_CONFIG_CHILDREN,
child, r) == 0);
for (c = 0; c < r; c++)
nvlist_free(child[c]);
umem_free(child, r * sizeof (nvlist_t *));
return (raidz);
}
static nvlist_t *
make_vdev_mirror(char *path, char *aux, size_t size, uint64_t ashift,
int r, int m)
2008-11-20 20:01:55 +00:00
{
nvlist_t *mirror, **child;
int c;
if (m < 1)
return (make_vdev_raidz(path, aux, size, ashift, r));
2008-11-20 20:01:55 +00:00
child = umem_alloc(m * sizeof (nvlist_t *), UMEM_NOFAIL);
for (c = 0; c < m; c++)
child[c] = make_vdev_raidz(path, aux, size, ashift, r);
2008-11-20 20:01:55 +00:00
VERIFY(nvlist_alloc(&mirror, NV_UNIQUE_NAME, 0) == 0);
VERIFY(nvlist_add_string(mirror, ZPOOL_CONFIG_TYPE,
VDEV_TYPE_MIRROR) == 0);
VERIFY(nvlist_add_nvlist_array(mirror, ZPOOL_CONFIG_CHILDREN,
child, m) == 0);
for (c = 0; c < m; c++)
nvlist_free(child[c]);
umem_free(child, m * sizeof (nvlist_t *));
return (mirror);
}
static nvlist_t *
make_vdev_root(char *path, char *aux, size_t size, uint64_t ashift,
int log, int r, int m, int t)
2008-11-20 20:01:55 +00:00
{
nvlist_t *root, **child;
int c;
ASSERT(t > 0);
child = umem_alloc(t * sizeof (nvlist_t *), UMEM_NOFAIL);
for (c = 0; c < t; c++) {
child[c] = make_vdev_mirror(path, aux, size, ashift, r, m);
VERIFY(nvlist_add_uint64(child[c], ZPOOL_CONFIG_IS_LOG,
log) == 0);
}
2008-11-20 20:01:55 +00:00
VERIFY(nvlist_alloc(&root, NV_UNIQUE_NAME, 0) == 0);
VERIFY(nvlist_add_string(root, ZPOOL_CONFIG_TYPE, VDEV_TYPE_ROOT) == 0);
VERIFY(nvlist_add_nvlist_array(root, aux ? aux : ZPOOL_CONFIG_CHILDREN,
2008-11-20 20:01:55 +00:00
child, t) == 0);
for (c = 0; c < t; c++)
nvlist_free(child[c]);
umem_free(child, t * sizeof (nvlist_t *));
return (root);
}
static void
ztest_set_random_blocksize(objset_t *os, uint64_t object, dmu_tx_t *tx)
{
int bs = SPA_MINBLOCKSHIFT +
ztest_random(SPA_MAXBLOCKSHIFT - SPA_MINBLOCKSHIFT + 1);
int ibs = DN_MIN_INDBLKSHIFT +
ztest_random(DN_MAX_INDBLKSHIFT - DN_MIN_INDBLKSHIFT + 1);
int error;
error = dmu_object_set_blocksize(os, object, 1ULL << bs, ibs, tx);
if (error) {
char osname[300];
dmu_objset_name(os, osname);
fatal(0, "dmu_object_set_blocksize('%s', %llu, %d, %d) = %d",
osname, object, 1 << bs, ibs, error);
}
}
static uint8_t
ztest_random_checksum(void)
{
uint8_t checksum;
do {
checksum = ztest_random(ZIO_CHECKSUM_FUNCTIONS);
} while (zio_checksum_table[checksum].ci_zbt);
if (checksum == ZIO_CHECKSUM_OFF)
checksum = ZIO_CHECKSUM_ON;
return (checksum);
}
static uint8_t
ztest_random_compress(void)
{
return ((uint8_t)ztest_random(ZIO_COMPRESS_FUNCTIONS));
}
static int
2009-01-15 21:59:39 +00:00
ztest_replay_create(objset_t *os, lr_create_t *lr, boolean_t byteswap)
2008-11-20 20:01:55 +00:00
{
dmu_tx_t *tx;
int error;
if (byteswap)
byteswap_uint64_array(lr, sizeof (*lr));
tx = dmu_tx_create(os);
dmu_tx_hold_bonus(tx, DMU_NEW_OBJECT);
2009-01-15 21:59:39 +00:00
error = dmu_tx_assign(tx, TXG_WAIT);
2008-11-20 20:01:55 +00:00
if (error) {
dmu_tx_abort(tx);
return (error);
}
error = dmu_object_claim(os, lr->lr_doid, lr->lr_mode, 0,
DMU_OT_NONE, 0, tx);
ASSERT3U(error, ==, 0);
dmu_tx_commit(tx);
if (zopt_verbose >= 5) {
char osname[MAXNAMELEN];
dmu_objset_name(os, osname);
(void) printf("replay create of %s object %llu"
" in txg %llu = %d\n",
osname, (u_longlong_t)lr->lr_doid,
2009-01-15 21:59:39 +00:00
(u_longlong_t)dmu_tx_get_txg(tx), error);
2008-11-20 20:01:55 +00:00
}
return (error);
}
static int
2009-01-15 21:59:39 +00:00
ztest_replay_remove(objset_t *os, lr_remove_t *lr, boolean_t byteswap)
2008-11-20 20:01:55 +00:00
{
dmu_tx_t *tx;
int error;
if (byteswap)
byteswap_uint64_array(lr, sizeof (*lr));
tx = dmu_tx_create(os);
dmu_tx_hold_free(tx, lr->lr_doid, 0, DMU_OBJECT_END);
2009-01-15 21:59:39 +00:00
error = dmu_tx_assign(tx, TXG_WAIT);
2008-11-20 20:01:55 +00:00
if (error) {
dmu_tx_abort(tx);
return (error);
}
error = dmu_object_free(os, lr->lr_doid, tx);
dmu_tx_commit(tx);
return (error);
}
zil_replay_func_t *ztest_replay_vector[TX_MAX_TYPE] = {
2008-12-23 00:18:07 +00:00
NULL, /* 0 no such transaction type */
2008-12-23 00:50:44 +00:00
(zil_replay_func_t *)ztest_replay_create,/* TX_CREATE */
2008-12-23 00:18:07 +00:00
NULL, /* TX_MKDIR */
NULL, /* TX_MKXATTR */
NULL, /* TX_SYMLINK */
2008-12-23 00:50:44 +00:00
(zil_replay_func_t *)ztest_replay_remove,/* TX_REMOVE */
2008-12-23 00:18:07 +00:00
NULL, /* TX_RMDIR */
NULL, /* TX_LINK */
NULL, /* TX_RENAME */
NULL, /* TX_WRITE */
NULL, /* TX_TRUNCATE */
NULL, /* TX_SETATTR */
NULL, /* TX_ACL */
2008-11-20 20:01:55 +00:00
};
/*
* Verify that we can't destroy an active pool, create an existing pool,
* or create a pool with a bad vdev spec.
*/
void
ztest_spa_create_destroy(ztest_args_t *za)
{
int error;
spa_t *spa;
nvlist_t *nvroot;
/*
* Attempt to create using a bad file.
*/
nvroot = make_vdev_root("/dev/bogus", NULL, 0, 0, 0, 0, 0, 1);
error = spa_create("ztest_bad_file", nvroot, NULL, NULL, NULL);
2008-11-20 20:01:55 +00:00
nvlist_free(nvroot);
if (error != ENOENT)
fatal(0, "spa_create(bad_file) = %d", error);
/*
* Attempt to create using a bad mirror.
*/
nvroot = make_vdev_root("/dev/bogus", NULL, 0, 0, 0, 0, 2, 1);
error = spa_create("ztest_bad_mirror", nvroot, NULL, NULL, NULL);
2008-11-20 20:01:55 +00:00
nvlist_free(nvroot);
if (error != ENOENT)
fatal(0, "spa_create(bad_mirror) = %d", error);
/*
* Attempt to create an existing pool. It shouldn't matter
* what's in the nvroot; we should fail with EEXIST.
*/
rw_enter(&ztest_shared->zs_name_lock, RW_READER);
nvroot = make_vdev_root("/dev/bogus", NULL, 0, 0, 0, 0, 0, 1);
error = spa_create(za->za_pool, nvroot, NULL, NULL, NULL);
2008-11-20 20:01:55 +00:00
nvlist_free(nvroot);
if (error != EEXIST)
fatal(0, "spa_create(whatever) = %d", error);
error = spa_open(za->za_pool, &spa, FTAG);
if (error)
fatal(0, "spa_open() = %d", error);
error = spa_destroy(za->za_pool);
if (error != EBUSY)
fatal(0, "spa_destroy() = %d", error);
spa_close(spa, FTAG);
rw_exit(&ztest_shared->zs_name_lock);
2008-11-20 20:01:55 +00:00
}
static vdev_t *
vdev_lookup_by_path(vdev_t *vd, const char *path)
{
vdev_t *mvd;
int c;
if (vd->vdev_path != NULL && strcmp(path, vd->vdev_path) == 0)
return (vd);
for (c = 0; c < vd->vdev_children; c++)
if ((mvd = vdev_lookup_by_path(vd->vdev_child[c], path)) !=
NULL)
return (mvd);
return (NULL);
}
2008-11-20 20:01:55 +00:00
/*
* Verify that vdev_add() works as expected.
*/
void
ztest_vdev_add_remove(ztest_args_t *za)
{
spa_t *spa = za->za_spa;
uint64_t leaves = MAX(zopt_mirrors, 1) * zopt_raidz;
nvlist_t *nvroot;
int error;
mutex_enter(&ztest_shared->zs_vdev_lock);
2008-11-20 20:01:55 +00:00
spa_config_enter(spa, SCL_VDEV, FTAG, RW_READER);
2008-11-20 20:01:55 +00:00
ztest_shared->zs_vdev_primaries =
spa->spa_root_vdev->vdev_children * leaves;
spa_config_exit(spa, SCL_VDEV, FTAG);
2008-11-20 20:01:55 +00:00
/*
* Make 1/4 of the devices be log devices.
*/
nvroot = make_vdev_root(NULL, NULL, zopt_vdev_size, 0,
2008-11-20 20:01:55 +00:00
ztest_random(4) == 0, zopt_raidz, zopt_mirrors, 1);
error = spa_vdev_add(spa, nvroot);
nvlist_free(nvroot);
mutex_exit(&ztest_shared->zs_vdev_lock);
2008-11-20 20:01:55 +00:00
if (error == ENOSPC)
ztest_record_enospc("spa_vdev_add");
else if (error != 0)
fatal(0, "spa_vdev_add() = %d", error);
}
/*
* Verify that adding/removing aux devices (l2arc, hot spare) works as expected.
*/
void
ztest_vdev_aux_add_remove(ztest_args_t *za)
2008-11-20 20:01:55 +00:00
{
spa_t *spa = za->za_spa;
vdev_t *rvd = spa->spa_root_vdev;
spa_aux_vdev_t *sav;
char *aux;
uint64_t guid = 0;
int error;
2008-11-20 20:01:55 +00:00
if (ztest_random(2) == 0) {
sav = &spa->spa_spares;
aux = ZPOOL_CONFIG_SPARES;
} else {
sav = &spa->spa_l2cache;
aux = ZPOOL_CONFIG_L2CACHE;
}
mutex_enter(&ztest_shared->zs_vdev_lock);
spa_config_enter(spa, SCL_VDEV, FTAG, RW_READER);
if (sav->sav_count != 0 && ztest_random(4) == 0) {
/*
* Pick a random device to remove.
*/
guid = sav->sav_vdevs[ztest_random(sav->sav_count)]->vdev_guid;
} else {
/*
* Find an unused device we can add.
*/
ztest_shared->zs_vdev_aux = 0;
for (;;) {
char path[MAXPATHLEN];
int c;
(void) sprintf(path, ztest_aux_template, zopt_dir,
zopt_pool, aux, ztest_shared->zs_vdev_aux);
for (c = 0; c < sav->sav_count; c++)
if (strcmp(sav->sav_vdevs[c]->vdev_path,
path) == 0)
break;
if (c == sav->sav_count &&
vdev_lookup_by_path(rvd, path) == NULL)
break;
ztest_shared->zs_vdev_aux++;
2008-11-20 20:01:55 +00:00
}
}
spa_config_exit(spa, SCL_VDEV, FTAG);
2008-11-20 20:01:55 +00:00
if (guid == 0) {
/*
* Add a new device.
*/
nvlist_t *nvroot = make_vdev_root(NULL, aux,
(zopt_vdev_size * 5) / 4, 0, 0, 0, 0, 1);
error = spa_vdev_add(spa, nvroot);
if (error != 0)
fatal(0, "spa_vdev_add(%p) = %d", nvroot, error);
nvlist_free(nvroot);
} else {
/*
* Remove an existing device. Sometimes, dirty its
* vdev state first to make sure we handle removal
* of devices that have pending state changes.
*/
if (ztest_random(2) == 0)
2009-07-02 22:44:48 +00:00
(void) vdev_online(spa, guid, 0, NULL);
error = spa_vdev_remove(spa, guid, B_FALSE);
if (error != 0 && error != EBUSY)
fatal(0, "spa_vdev_remove(%llu) = %d", guid, error);
}
mutex_exit(&ztest_shared->zs_vdev_lock);
2008-11-20 20:01:55 +00:00
}
/*
* Verify that we can attach and detach devices.
*/
void
ztest_vdev_attach_detach(ztest_args_t *za)
{
spa_t *spa = za->za_spa;
spa_aux_vdev_t *sav = &spa->spa_spares;
2008-11-20 20:01:55 +00:00
vdev_t *rvd = spa->spa_root_vdev;
vdev_t *oldvd, *newvd, *pvd;
nvlist_t *root;
2008-11-20 20:01:55 +00:00
uint64_t leaves = MAX(zopt_mirrors, 1) * zopt_raidz;
uint64_t leaf, top;
uint64_t ashift = ztest_get_ashift();
2009-01-15 21:59:39 +00:00
uint64_t oldguid, pguid;
2008-11-20 20:01:55 +00:00
size_t oldsize, newsize;
char oldpath[MAXPATHLEN], newpath[MAXPATHLEN];
int replacing;
int oldvd_has_siblings = B_FALSE;
int newvd_is_spare = B_FALSE;
int oldvd_is_log;
2008-11-20 20:01:55 +00:00
int error, expected_error;
mutex_enter(&ztest_shared->zs_vdev_lock);
2008-11-20 20:01:55 +00:00
spa_config_enter(spa, SCL_VDEV, FTAG, RW_READER);
2008-11-20 20:01:55 +00:00
/*
* Decide whether to do an attach or a replace.
*/
replacing = ztest_random(2);
/*
* Pick a random top-level vdev.
*/
top = ztest_random(rvd->vdev_children);
/*
* Pick a random leaf within it.
*/
leaf = ztest_random(leaves);
/*
* Locate this vdev.
2008-11-20 20:01:55 +00:00
*/
oldvd = rvd->vdev_child[top];
2009-01-15 21:59:39 +00:00
if (zopt_mirrors >= 1) {
ASSERT(oldvd->vdev_ops == &vdev_mirror_ops);
ASSERT(oldvd->vdev_children >= zopt_mirrors);
oldvd = oldvd->vdev_child[leaf / zopt_raidz];
2009-01-15 21:59:39 +00:00
}
if (zopt_raidz > 1) {
ASSERT(oldvd->vdev_ops == &vdev_raidz_ops);
ASSERT(oldvd->vdev_children == zopt_raidz);
oldvd = oldvd->vdev_child[leaf % zopt_raidz];
2009-01-15 21:59:39 +00:00
}
2008-11-20 20:01:55 +00:00
/*
* If we're already doing an attach or replace, oldvd may be a
* mirror vdev -- in which case, pick a random child.
2008-11-20 20:01:55 +00:00
*/
while (oldvd->vdev_children != 0) {
oldvd_has_siblings = B_TRUE;
2009-01-15 21:59:39 +00:00
ASSERT(oldvd->vdev_children >= 2);
oldvd = oldvd->vdev_child[ztest_random(oldvd->vdev_children)];
}
oldguid = oldvd->vdev_guid;
2009-07-02 22:44:48 +00:00
oldsize = vdev_get_min_asize(oldvd);
oldvd_is_log = oldvd->vdev_top->vdev_islog;
(void) strcpy(oldpath, oldvd->vdev_path);
pvd = oldvd->vdev_parent;
2009-01-15 21:59:39 +00:00
pguid = pvd->vdev_guid;
2008-11-20 20:01:55 +00:00
/*
* If oldvd has siblings, then half of the time, detach it.
2008-11-20 20:01:55 +00:00
*/
if (oldvd_has_siblings && ztest_random(2) == 0) {
spa_config_exit(spa, SCL_VDEV, FTAG);
2009-01-15 21:59:39 +00:00
error = spa_vdev_detach(spa, oldguid, pguid, B_FALSE);
if (error != 0 && error != ENODEV && error != EBUSY &&
error != ENOTSUP)
fatal(0, "detach (%s) returned %d", oldpath, error);
mutex_exit(&ztest_shared->zs_vdev_lock);
return;
}
2008-11-20 20:01:55 +00:00
/*
* For the new vdev, choose with equal probability between the two
* standard paths (ending in either 'a' or 'b') or a random hot spare.
2008-11-20 20:01:55 +00:00
*/
if (sav->sav_count != 0 && ztest_random(3) == 0) {
newvd = sav->sav_vdevs[ztest_random(sav->sav_count)];
newvd_is_spare = B_TRUE;
(void) strcpy(newpath, newvd->vdev_path);
} else {
(void) snprintf(newpath, sizeof (newpath), ztest_dev_template,
zopt_dir, zopt_pool, top * leaves + leaf);
if (ztest_random(2) == 0)
newpath[strlen(newpath) - 1] = 'b';
newvd = vdev_lookup_by_path(rvd, newpath);
}
if (newvd) {
2009-07-02 22:44:48 +00:00
newsize = vdev_get_min_asize(newvd);
} else {
/*
* Make newsize a little bigger or smaller than oldsize.
* If it's smaller, the attach should fail.
* If it's larger, and we're doing a replace,
* we should get dynamic LUN growth when we're done.
*/
newsize = 10 * oldsize / (9 + ztest_random(3));
}
2008-11-20 20:01:55 +00:00
/*
* If pvd is not a mirror or root, the attach should fail with ENOTSUP,
* unless it's a replace; in that case any non-replacing parent is OK.
*
* If newvd is already part of the pool, it should fail with EBUSY.
*
* If newvd is too small, it should fail with EOVERFLOW.
*/
if (pvd->vdev_ops != &vdev_mirror_ops &&
pvd->vdev_ops != &vdev_root_ops && (!replacing ||
pvd->vdev_ops == &vdev_replacing_ops ||
pvd->vdev_ops == &vdev_spare_ops))
2008-11-20 20:01:55 +00:00
expected_error = ENOTSUP;
else if (newvd_is_spare && (!replacing || oldvd_is_log))
expected_error = ENOTSUP;
else if (newvd == oldvd)
expected_error = replacing ? 0 : EBUSY;
else if (vdev_lookup_by_path(rvd, newpath) != NULL)
expected_error = EBUSY;
2008-11-20 20:01:55 +00:00
else if (newsize < oldsize)
expected_error = EOVERFLOW;
else if (ashift > oldvd->vdev_top->vdev_ashift)
expected_error = EDOM;
else
expected_error = 0;
spa_config_exit(spa, SCL_VDEV, FTAG);
2008-11-20 20:01:55 +00:00
/*
* Build the nvlist describing newpath.
*/
root = make_vdev_root(newpath, NULL, newvd == NULL ? newsize : 0,
ashift, 0, 0, 0, 1);
2008-11-20 20:01:55 +00:00
error = spa_vdev_attach(spa, oldguid, root, replacing);
2008-11-20 20:01:55 +00:00
nvlist_free(root);
/*
* If our parent was the replacing vdev, but the replace completed,
* then instead of failing with ENOTSUP we may either succeed,
* fail with ENODEV, or fail with EOVERFLOW.
*/
if (expected_error == ENOTSUP &&
(error == 0 || error == ENODEV || error == EOVERFLOW))
expected_error = error;
/*
* If someone grew the LUN, the replacement may be too small.
*/
if (error == EOVERFLOW || error == EBUSY)
2008-11-20 20:01:55 +00:00
expected_error = error;
/* XXX workaround 6690467 */
if (error != expected_error && expected_error != EBUSY) {
fatal(0, "attach (%s %llu, %s %llu, %d) "
"returned %d, expected %d",
oldpath, (longlong_t)oldsize, newpath,
(longlong_t)newsize, replacing, error, expected_error);
2008-11-20 20:01:55 +00:00
}
mutex_exit(&ztest_shared->zs_vdev_lock);
2008-11-20 20:01:55 +00:00
}
2009-07-02 22:44:48 +00:00
/*
* Callback function which expands the physical size of the vdev.
*/
vdev_t *
grow_vdev(vdev_t *vd, void *arg)
{
ASSERTV(spa_t *spa = vd->vdev_spa);
2009-07-02 22:44:48 +00:00
size_t *newsize = arg;
size_t fsize;
int fd;
ASSERT(spa_config_held(spa, SCL_STATE, RW_READER) == SCL_STATE);
ASSERT(vd->vdev_ops->vdev_op_leaf);
if ((fd = open(vd->vdev_path, O_RDWR)) == -1)
return (vd);
fsize = lseek(fd, 0, SEEK_END);
(void) ftruncate(fd, *newsize);
if (zopt_verbose >= 6) {
(void) printf("%s grew from %lu to %lu bytes\n",
vd->vdev_path, (ulong_t)fsize, (ulong_t)*newsize);
}
(void) close(fd);
return (NULL);
}
/*
* Callback function which expands a given vdev by calling vdev_online().
*/
/* ARGSUSED */
vdev_t *
online_vdev(vdev_t *vd, void *arg)
{
spa_t *spa = vd->vdev_spa;
vdev_t *tvd = vd->vdev_top;
vdev_t *pvd = vd->vdev_parent;
uint64_t guid = vd->vdev_guid;
ASSERT(spa_config_held(spa, SCL_STATE, RW_READER) == SCL_STATE);
ASSERT(vd->vdev_ops->vdev_op_leaf);
/* Calling vdev_online will initialize the new metaslabs */
spa_config_exit(spa, SCL_STATE, spa);
(void) vdev_online(spa, guid, ZFS_ONLINE_EXPAND, NULL);
spa_config_enter(spa, SCL_STATE, spa, RW_READER);
/*
* Since we dropped the lock we need to ensure that we're
* still talking to the original vdev. It's possible this
* vdev may have been detached/replaced while we were
* trying to online it.
*/
if (vd != vdev_lookup_by_guid(tvd, guid) || vd->vdev_parent != pvd) {
if (zopt_verbose >= 6) {
(void) printf("vdev %p has disappeared, was "
"guid %llu\n", (void *)vd, (u_longlong_t)guid);
}
return (vd);
}
return (NULL);
}
/*
* Traverse the vdev tree calling the supplied function.
* We continue to walk the tree until we either have walked all
* children or we receive a non-NULL return from the callback.
* If a NULL callback is passed, then we just return back the first
* leaf vdev we encounter.
*/
vdev_t *
vdev_walk_tree(vdev_t *vd, vdev_t *(*func)(vdev_t *, void *), void *arg)
{
uint_t c;
2009-07-02 22:44:48 +00:00
if (vd->vdev_ops->vdev_op_leaf) {
if (func == NULL)
return (vd);
else
return (func(vd, arg));
}
for (c = 0; c < vd->vdev_children; c++) {
2009-07-02 22:44:48 +00:00
vdev_t *cvd = vd->vdev_child[c];
if ((cvd = vdev_walk_tree(cvd, func, arg)) != NULL)
return (cvd);
}
return (NULL);
}
2008-11-20 20:01:55 +00:00
/*
* Verify that dynamic LUN growth works as expected.
*/
void
ztest_vdev_LUN_growth(ztest_args_t *za)
{
spa_t *spa = za->za_spa;
2009-07-02 22:44:48 +00:00
vdev_t *vd, *tvd = NULL;
size_t psize, newsize;
uint64_t spa_newsize, spa_cursize, ms_count;
2008-11-20 20:01:55 +00:00
mutex_enter(&ztest_shared->zs_vdev_lock);
2009-07-02 22:44:48 +00:00
mutex_enter(&spa_namespace_lock);
spa_config_enter(spa, SCL_STATE, spa, RW_READER);
while (tvd == NULL || tvd->vdev_islog) {
uint64_t vdev;
vdev = ztest_random(spa->spa_root_vdev->vdev_children);
tvd = spa->spa_root_vdev->vdev_child[vdev];
}
2008-11-20 20:01:55 +00:00
/*
2009-07-02 22:44:48 +00:00
* Determine the size of the first leaf vdev associated with
* our top-level device.
2008-11-20 20:01:55 +00:00
*/
2009-07-02 22:44:48 +00:00
vd = vdev_walk_tree(tvd, NULL, NULL);
ASSERT3P(vd, !=, NULL);
ASSERT(vd->vdev_ops->vdev_op_leaf);
2008-11-20 20:01:55 +00:00
2009-07-02 22:44:48 +00:00
psize = vd->vdev_psize;
2008-11-20 20:01:55 +00:00
2009-07-02 22:44:48 +00:00
/*
* We only try to expand the vdev if it's less than 4x its
* original size and it has a valid psize.
*/
if (psize == 0 || psize >= 4 * zopt_vdev_size) {
spa_config_exit(spa, SCL_STATE, spa);
mutex_exit(&spa_namespace_lock);
mutex_exit(&ztest_shared->zs_vdev_lock);
2009-07-02 22:44:48 +00:00
return;
}
ASSERT(psize > 0);
newsize = psize + psize / 8;
ASSERT3U(newsize, >, psize);
2008-11-20 20:01:55 +00:00
2009-07-02 22:44:48 +00:00
if (zopt_verbose >= 6) {
(void) printf("Expanding vdev %s from %lu to %lu\n",
vd->vdev_path, (ulong_t)psize, (ulong_t)newsize);
}
spa_cursize = spa_get_space(spa);
ms_count = tvd->vdev_ms_count;
/*
* Growing the vdev is a two step process:
* 1). expand the physical size (i.e. relabel)
* 2). online the vdev to create the new metaslabs
*/
if (vdev_walk_tree(tvd, grow_vdev, &newsize) != NULL ||
vdev_walk_tree(tvd, online_vdev, NULL) != NULL ||
tvd->vdev_state != VDEV_STATE_HEALTHY) {
if (zopt_verbose >= 5) {
(void) printf("Could not expand LUN because "
"some vdevs were not healthy\n");
2008-11-20 20:01:55 +00:00
}
2009-07-02 22:44:48 +00:00
(void) spa_config_exit(spa, SCL_STATE, spa);
mutex_exit(&spa_namespace_lock);
mutex_exit(&ztest_shared->zs_vdev_lock);
2009-07-02 22:44:48 +00:00
return;
2008-11-20 20:01:55 +00:00
}
2009-07-02 22:44:48 +00:00
(void) spa_config_exit(spa, SCL_STATE, spa);
mutex_exit(&spa_namespace_lock);
2009-07-02 22:44:48 +00:00
/*
* Expanding the LUN will update the config asynchronously,
* thus we must wait for the async thread to complete any
* pending tasks before proceeding.
*/
mutex_enter(&spa->spa_async_lock);
2009-07-02 22:44:48 +00:00
while (spa->spa_async_thread != NULL || spa->spa_async_tasks)
cv_wait(&spa->spa_async_cv, &spa->spa_async_lock);
mutex_exit(&spa->spa_async_lock);
2009-07-02 22:44:48 +00:00
spa_config_enter(spa, SCL_STATE, spa, RW_READER);
spa_newsize = spa_get_space(spa);
/*
* Make sure we were able to grow the pool.
*/
if (ms_count >= tvd->vdev_ms_count ||
spa_cursize >= spa_newsize) {
(void) printf("Top-level vdev metaslab count: "
"before %llu, after %llu\n",
(u_longlong_t)ms_count,
(u_longlong_t)tvd->vdev_ms_count);
fatal(0, "LUN expansion failed: before %llu, "
"after %llu\n", spa_cursize, spa_newsize);
} else if (zopt_verbose >= 5) {
char oldnumbuf[6], newnumbuf[6];
nicenum(spa_cursize, oldnumbuf);
nicenum(spa_newsize, newnumbuf);
(void) printf("%s grew from %s to %s\n",
spa->spa_name, oldnumbuf, newnumbuf);
}
spa_config_exit(spa, SCL_STATE, spa);
mutex_exit(&ztest_shared->zs_vdev_lock);
2008-11-20 20:01:55 +00:00
}
/* ARGSUSED */
static void
ztest_create_cb(objset_t *os, void *arg, cred_t *cr, dmu_tx_t *tx)
{
/*
* Create the directory object.
*/
VERIFY(dmu_object_claim(os, ZTEST_DIROBJ,
DMU_OT_UINT64_OTHER, ZTEST_DIROBJ_BLOCKSIZE,
DMU_OT_UINT64_OTHER, 5 * sizeof (ztest_block_tag_t), tx) == 0);
VERIFY(zap_create_claim(os, ZTEST_MICROZAP_OBJ,
DMU_OT_ZAP_OTHER, DMU_OT_NONE, 0, tx) == 0);
VERIFY(zap_create_claim(os, ZTEST_FATZAP_OBJ,
DMU_OT_ZAP_OTHER, DMU_OT_NONE, 0, tx) == 0);
}
static int
ztest_destroy_cb(char *name, void *arg)
{
ztest_args_t *za = arg;
objset_t *os;
dmu_object_info_t *doi = &za->za_doi;
int error;
/*
* Verify that the dataset contains a directory object.
*/
error = dmu_objset_open(name, DMU_OST_OTHER,
DS_MODE_USER | DS_MODE_READONLY, &os);
2008-11-20 20:01:55 +00:00
ASSERT3U(error, ==, 0);
error = dmu_object_info(os, ZTEST_DIROBJ, doi);
if (error != ENOENT) {
/* We could have crashed in the middle of destroying it */
ASSERT3U(error, ==, 0);
ASSERT3U(doi->doi_type, ==, DMU_OT_UINT64_OTHER);
ASSERT3S(doi->doi_physical_blks, >=, 0);
}
dmu_objset_close(os);
/*
* Destroy the dataset.
*/
error = dmu_objset_destroy(name);
if (error) {
(void) dmu_objset_open(name, DMU_OST_OTHER,
DS_MODE_USER | DS_MODE_READONLY, &os);
fatal(0, "dmu_objset_destroy(os=%p) = %d\n", &os, error);
}
2008-11-20 20:01:55 +00:00
return (0);
}
/*
* Verify that dmu_objset_{create,destroy,open,close} work as expected.
*/
static uint64_t
ztest_log_create(zilog_t *zilog, dmu_tx_t *tx, uint64_t object, int mode)
{
itx_t *itx;
lr_create_t *lr;
size_t namesize;
char name[24];
(void) sprintf(name, "ZOBJ_%llu", (u_longlong_t)object);
namesize = strlen(name) + 1;
itx = zil_itx_create(TX_CREATE, sizeof (*lr) + namesize +
ztest_random(ZIL_MAX_BLKSZ));
lr = (lr_create_t *)&itx->itx_lr;
bzero(lr + 1, lr->lr_common.lrc_reclen - sizeof (*lr));
lr->lr_doid = object;
lr->lr_foid = 0;
lr->lr_mode = mode;
lr->lr_uid = 0;
lr->lr_gid = 0;
lr->lr_gen = dmu_tx_get_txg(tx);
lr->lr_crtime[0] = time(NULL);
lr->lr_crtime[1] = 0;
lr->lr_rdev = 0;
bcopy(name, (char *)(lr + 1), namesize);
return (zil_itx_assign(zilog, itx, tx));
}
void
ztest_dmu_objset_create_destroy(ztest_args_t *za)
{
int error;
objset_t *os, *os2;
2008-11-20 20:01:55 +00:00
char name[100];
int basemode, expected_error;
2008-11-20 20:01:55 +00:00
zilog_t *zilog;
uint64_t seq;
uint64_t objects;
rw_enter(&ztest_shared->zs_name_lock, RW_READER);
2008-11-20 20:01:55 +00:00
(void) snprintf(name, 100, "%s/%s_temp_%llu", za->za_pool, za->za_pool,
(u_longlong_t)za->za_instance);
basemode = DS_MODE_TYPE(za->za_instance);
if (basemode != DS_MODE_USER && basemode != DS_MODE_OWNER)
basemode = DS_MODE_USER;
2008-11-20 20:01:55 +00:00
/*
* If this dataset exists from a previous run, process its replay log
* half of the time. If we don't replay it, then dmu_objset_destroy()
* (invoked from ztest_destroy_cb() below) should just throw it away.
*/
if (ztest_random(2) == 0 &&
dmu_objset_open(name, DMU_OST_OTHER, DS_MODE_OWNER, &os) == 0) {
2009-01-15 21:59:39 +00:00
zil_replay(os, os, ztest_replay_vector);
2008-11-20 20:01:55 +00:00
dmu_objset_close(os);
}
/*
* There may be an old instance of the dataset we're about to
* create lying around from a previous run. If so, destroy it
* and all of its snapshots.
*/
(void) dmu_objset_find(name, ztest_destroy_cb, za,
DS_FIND_CHILDREN | DS_FIND_SNAPSHOTS);
/*
* Verify that the destroyed dataset is no longer in the namespace.
*/
error = dmu_objset_open(name, DMU_OST_OTHER, basemode, &os);
if (error != ENOENT)
fatal(1, "dmu_objset_open(%s) found destroyed dataset %p",
name, os);
/*
* Verify that we can create a new dataset.
*/
error = dmu_objset_create(name, DMU_OST_OTHER, NULL, 0,
ztest_create_cb, NULL);
if (error) {
if (error == ENOSPC) {
ztest_record_enospc("dmu_objset_create");
rw_exit(&ztest_shared->zs_name_lock);
2008-11-20 20:01:55 +00:00
return;
}
fatal(0, "dmu_objset_create(%s) = %d", name, error);
}
error = dmu_objset_open(name, DMU_OST_OTHER, basemode, &os);
if (error) {
fatal(0, "dmu_objset_open(%s) = %d", name, error);
}
/*
* Open the intent log for it.
*/
zilog = zil_open(os, NULL);
/*
* Put a random number of objects in there.
*/
objects = ztest_random(20);
seq = 0;
while (objects-- != 0) {
uint64_t object = 0;
2008-11-20 20:01:55 +00:00
dmu_tx_t *tx = dmu_tx_create(os);
dmu_tx_hold_write(tx, DMU_NEW_OBJECT, 0, sizeof (name));
error = dmu_tx_assign(tx, TXG_WAIT);
if (error) {
dmu_tx_abort(tx);
} else {
object = dmu_object_alloc(os, DMU_OT_UINT64_OTHER, 0,
DMU_OT_NONE, 0, tx);
ztest_set_random_blocksize(os, object, tx);
seq = ztest_log_create(zilog, tx, object,
DMU_OT_UINT64_OTHER);
dmu_write(os, object, 0, sizeof (name), name, tx);
dmu_tx_commit(tx);
}
if (ztest_random(5) == 0) {
zil_commit(zilog, seq, object);
}
if (ztest_random(100) == 0) {
error = zil_suspend(zilog);
if (error == 0) {
zil_resume(zilog);
}
}
}
/*
* Verify that we cannot create an existing dataset.
*/
error = dmu_objset_create(name, DMU_OST_OTHER, NULL, 0, NULL, NULL);
if (error != EEXIST)
fatal(0, "created existing dataset, error = %d", error);
/*
* Verify that multiple dataset holds are allowed, but only when
2008-11-20 20:01:55 +00:00
* the new access mode is compatible with the base mode.
*/
if (basemode == DS_MODE_OWNER) {
error = dmu_objset_open(name, DMU_OST_OTHER, DS_MODE_USER,
&os2);
if (error)
fatal(0, "dmu_objset_open('%s') = %d", name, error);
else
2008-11-20 20:01:55 +00:00
dmu_objset_close(os2);
}
error = dmu_objset_open(name, DMU_OST_OTHER, DS_MODE_OWNER, &os2);
expected_error = (basemode == DS_MODE_OWNER) ? EBUSY : 0;
if (error != expected_error)
fatal(0, "dmu_objset_open('%s') = %d, expected %d",
name, error, expected_error);
if (error == 0)
dmu_objset_close(os2);
2008-11-20 20:01:55 +00:00
zil_close(zilog);
dmu_objset_close(os);
error = dmu_objset_destroy(name);
if (error)
fatal(0, "dmu_objset_destroy(%s) = %d", name, error);
rw_exit(&ztest_shared->zs_name_lock);
2008-11-20 20:01:55 +00:00
}
/*
* Verify that dmu_snapshot_{create,destroy,open,close} work as expected.
*/
void
ztest_dmu_snapshot_create_destroy(ztest_args_t *za)
{
int error;
objset_t *os = za->za_os;
char snapname[100];
char osname[MAXNAMELEN];
rw_enter(&ztest_shared->zs_name_lock, RW_READER);
2008-11-20 20:01:55 +00:00
dmu_objset_name(os, osname);
(void) snprintf(snapname, 100, "%s@%llu", osname,
(u_longlong_t)za->za_instance);
error = dmu_objset_destroy(snapname);
if (error != 0 && error != ENOENT)
fatal(0, "dmu_objset_destroy() = %d", error);
2009-07-02 22:44:48 +00:00
error = dmu_objset_snapshot(osname, strchr(snapname, '@')+1,
NULL, FALSE);
2008-11-20 20:01:55 +00:00
if (error == ENOSPC)
ztest_record_enospc("dmu_take_snapshot");
else if (error != 0 && error != EEXIST)
fatal(0, "dmu_take_snapshot() = %d", error);
rw_exit(&ztest_shared->zs_name_lock);
2008-11-20 20:01:55 +00:00
}
2009-07-02 22:44:48 +00:00
/*
* Cleanup non-standard snapshots and clones.
*/
void
ztest_dsl_dataset_cleanup(char *osname, uint64_t curval)
{
char snap1name[100];
char clone1name[100];
char snap2name[100];
char clone2name[100];
char snap3name[100];
int error;
(void) snprintf(snap1name, 100, "%s@s1_%llu",
osname, (u_longlong_t)curval);
(void) snprintf(clone1name, 100, "%s/c1_%llu",
osname, (u_longlong_t)curval);
(void) snprintf(snap2name, 100, "%s@s2_%llu",
clone1name, (u_longlong_t)curval);
(void) snprintf(clone2name, 100, "%s/c2_%llu",
osname, (u_longlong_t)curval);
(void) snprintf(snap3name, 100, "%s@s3_%llu",
clone1name, (u_longlong_t)curval);
2009-07-02 22:44:48 +00:00
error = dmu_objset_destroy(clone2name);
if (error && error != ENOENT)
fatal(0, "dmu_objset_destroy(%s) = %d", clone2name, error);
error = dmu_objset_destroy(snap3name);
if (error && error != ENOENT)
fatal(0, "dmu_objset_destroy(%s) = %d", snap3name, error);
error = dmu_objset_destroy(snap2name);
if (error && error != ENOENT)
fatal(0, "dmu_objset_destroy(%s) = %d", snap2name, error);
error = dmu_objset_destroy(clone1name);
if (error && error != ENOENT)
fatal(0, "dmu_objset_destroy(%s) = %d", clone1name, error);
error = dmu_objset_destroy(snap1name);
if (error && error != ENOENT)
fatal(0, "dmu_objset_destroy(%s) = %d", snap1name, error);
}
/*
* Verify dsl_dataset_promote handles EBUSY
*/
void
ztest_dsl_dataset_promote_busy(ztest_args_t *za)
{
int error;
objset_t *os = za->za_os;
objset_t *clone;
dsl_dataset_t *ds;
char snap1name[100];
char clone1name[100];
char snap2name[100];
char clone2name[100];
char snap3name[100];
char osname[MAXNAMELEN];
uint64_t curval = za->za_instance;
rw_enter(&ztest_shared->zs_name_lock, RW_READER);
2009-07-02 22:44:48 +00:00
dmu_objset_name(os, osname);
ztest_dsl_dataset_cleanup(osname, curval);
(void) snprintf(snap1name, 100, "%s@s1_%llu",
osname, (u_longlong_t)curval);
(void) snprintf(clone1name, 100, "%s/c1_%llu",
osname, (u_longlong_t)curval);
(void) snprintf(snap2name, 100, "%s@s2_%llu",
clone1name, (u_longlong_t)curval);
(void) snprintf(clone2name, 100, "%s/c2_%llu",
osname, (u_longlong_t)curval);
(void) snprintf(snap3name, 100, "%s@s3_%llu",
clone1name, (u_longlong_t)curval);
2009-07-02 22:44:48 +00:00
error = dmu_objset_snapshot(osname, strchr(snap1name, '@')+1,
NULL, FALSE);
if (error && error != EEXIST) {
if (error == ENOSPC) {
ztest_record_enospc("dmu_take_snapshot");
goto out;
}
fatal(0, "dmu_take_snapshot(%s) = %d", snap1name, error);
}
error = dmu_objset_open(snap1name, DMU_OST_OTHER,
DS_MODE_USER | DS_MODE_READONLY, &clone);
if (error)
fatal(0, "dmu_open_snapshot(%s) = %d", snap1name, error);
error = dmu_objset_create(clone1name, DMU_OST_OTHER, clone, 0,
NULL, NULL);
dmu_objset_close(clone);
if (error) {
if (error == ENOSPC) {
ztest_record_enospc("dmu_objset_create");
goto out;
}
fatal(0, "dmu_objset_create(%s) = %d", clone1name, error);
}
error = dmu_objset_snapshot(clone1name, strchr(snap2name, '@')+1,
NULL, FALSE);
if (error && error != EEXIST) {
if (error == ENOSPC) {
ztest_record_enospc("dmu_take_snapshot");
goto out;
}
fatal(0, "dmu_open_snapshot(%s) = %d", snap2name, error);
}
error = dmu_objset_snapshot(clone1name, strchr(snap3name, '@')+1,
NULL, FALSE);
if (error && error != EEXIST) {
if (error == ENOSPC) {
ztest_record_enospc("dmu_take_snapshot");
goto out;
}
fatal(0, "dmu_open_snapshot(%s) = %d", snap3name, error);
}
error = dmu_objset_open(snap3name, DMU_OST_OTHER,
DS_MODE_USER | DS_MODE_READONLY, &clone);
if (error)
fatal(0, "dmu_open_snapshot(%s) = %d", snap3name, error);
error = dmu_objset_create(clone2name, DMU_OST_OTHER, clone, 0,
NULL, NULL);
dmu_objset_close(clone);
if (error) {
if (error == ENOSPC) {
ztest_record_enospc("dmu_objset_create");
goto out;
}
fatal(0, "dmu_objset_create(%s) = %d", clone2name, error);
}
error = dsl_dataset_own(snap1name, DS_MODE_READONLY, FTAG, &ds);
if (error)
fatal(0, "dsl_dataset_own(%s) = %d", snap1name, error);
error = dsl_dataset_promote(clone2name);
if (error != EBUSY)
fatal(0, "dsl_dataset_promote(%s), %d, not EBUSY", clone2name,
error);
dsl_dataset_disown(ds, FTAG);
out:
ztest_dsl_dataset_cleanup(osname, curval);
rw_exit(&ztest_shared->zs_name_lock);
2009-07-02 22:44:48 +00:00
}
2008-11-20 20:01:55 +00:00
/*
* Verify that dmu_object_{alloc,free} work as expected.
*/
void
ztest_dmu_object_alloc_free(ztest_args_t *za)
{
objset_t *os = za->za_os;
dmu_buf_t *db;
dmu_tx_t *tx;
uint64_t batchobj, object, batchsize, endoff, temp;
int b, c, error, bonuslen;
dmu_object_info_t *doi = &za->za_doi;
char osname[MAXNAMELEN];
dmu_objset_name(os, osname);
endoff = -8ULL;
batchsize = 2;
/*
* Create a batch object if necessary, and record it in the directory.
*/
VERIFY3U(0, ==, dmu_read(os, ZTEST_DIROBJ, za->za_diroff,
2009-07-02 22:44:48 +00:00
sizeof (uint64_t), &batchobj, DMU_READ_PREFETCH));
2008-11-20 20:01:55 +00:00
if (batchobj == 0) {
tx = dmu_tx_create(os);
dmu_tx_hold_write(tx, ZTEST_DIROBJ, za->za_diroff,
sizeof (uint64_t));
dmu_tx_hold_bonus(tx, DMU_NEW_OBJECT);
error = dmu_tx_assign(tx, TXG_WAIT);
if (error) {
ztest_record_enospc("create a batch object");
dmu_tx_abort(tx);
return;
}
batchobj = dmu_object_alloc(os, DMU_OT_UINT64_OTHER, 0,
DMU_OT_NONE, 0, tx);
ztest_set_random_blocksize(os, batchobj, tx);
dmu_write(os, ZTEST_DIROBJ, za->za_diroff,
sizeof (uint64_t), &batchobj, tx);
dmu_tx_commit(tx);
}
/*
* Destroy the previous batch of objects.
*/
for (b = 0; b < batchsize; b++) {
VERIFY3U(0, ==, dmu_read(os, batchobj, b * sizeof (uint64_t),
2009-07-02 22:44:48 +00:00
sizeof (uint64_t), &object, DMU_READ_PREFETCH));
2008-11-20 20:01:55 +00:00
if (object == 0)
continue;
/*
* Read and validate contents.
* We expect the nth byte of the bonus buffer to be n.
*/
VERIFY(0 == dmu_bonus_hold(os, object, FTAG, &db));
za->za_dbuf = db;
dmu_object_info_from_db(db, doi);
ASSERT(doi->doi_type == DMU_OT_UINT64_OTHER);
ASSERT(doi->doi_bonus_type == DMU_OT_PLAIN_OTHER);
ASSERT3S(doi->doi_physical_blks, >=, 0);
bonuslen = doi->doi_bonus_size;
for (c = 0; c < bonuslen; c++) {
if (((uint8_t *)db->db_data)[c] !=
(uint8_t)(c + bonuslen)) {
fatal(0,
"bad bonus: %s, obj %llu, off %d: %u != %u",
osname, object, c,
((uint8_t *)db->db_data)[c],
(uint8_t)(c + bonuslen));
}
}
dmu_buf_rele(db, FTAG);
za->za_dbuf = NULL;
/*
* We expect the word at endoff to be our object number.
*/
VERIFY(0 == dmu_read(os, object, endoff,
2009-07-02 22:44:48 +00:00
sizeof (uint64_t), &temp, DMU_READ_PREFETCH));
2008-11-20 20:01:55 +00:00
if (temp != object) {
fatal(0, "bad data in %s, got %llu, expected %llu",
osname, temp, object);
}
/*
* Destroy old object and clear batch entry.
*/
tx = dmu_tx_create(os);
dmu_tx_hold_write(tx, batchobj,
b * sizeof (uint64_t), sizeof (uint64_t));
dmu_tx_hold_free(tx, object, 0, DMU_OBJECT_END);
error = dmu_tx_assign(tx, TXG_WAIT);
if (error) {
ztest_record_enospc("free object");
dmu_tx_abort(tx);
return;
}
error = dmu_object_free(os, object, tx);
if (error) {
fatal(0, "dmu_object_free('%s', %llu) = %d",
osname, object, error);
}
object = 0;
dmu_object_set_checksum(os, batchobj,
ztest_random_checksum(), tx);
dmu_object_set_compress(os, batchobj,
ztest_random_compress(), tx);
dmu_write(os, batchobj, b * sizeof (uint64_t),
sizeof (uint64_t), &object, tx);
dmu_tx_commit(tx);
}
/*
* Before creating the new batch of objects, generate a bunch of churn.
*/
for (b = ztest_random(100); b > 0; b--) {
tx = dmu_tx_create(os);
dmu_tx_hold_bonus(tx, DMU_NEW_OBJECT);
error = dmu_tx_assign(tx, TXG_WAIT);
if (error) {
ztest_record_enospc("churn objects");
dmu_tx_abort(tx);
return;
}
object = dmu_object_alloc(os, DMU_OT_UINT64_OTHER, 0,
DMU_OT_NONE, 0, tx);
ztest_set_random_blocksize(os, object, tx);
error = dmu_object_free(os, object, tx);
if (error) {
fatal(0, "dmu_object_free('%s', %llu) = %d",
osname, object, error);
}
dmu_tx_commit(tx);
}
/*
* Create a new batch of objects with randomly chosen
* blocksizes and record them in the batch directory.
*/
for (b = 0; b < batchsize; b++) {
uint32_t va_blksize;
u_longlong_t va_nblocks;
tx = dmu_tx_create(os);
dmu_tx_hold_write(tx, batchobj, b * sizeof (uint64_t),
sizeof (uint64_t));
dmu_tx_hold_bonus(tx, DMU_NEW_OBJECT);
dmu_tx_hold_write(tx, DMU_NEW_OBJECT, endoff,
sizeof (uint64_t));
error = dmu_tx_assign(tx, TXG_WAIT);
if (error) {
ztest_record_enospc("create batchobj");
dmu_tx_abort(tx);
return;
}
bonuslen = (int)ztest_random(dmu_bonus_max()) + 1;
object = dmu_object_alloc(os, DMU_OT_UINT64_OTHER, 0,
DMU_OT_PLAIN_OTHER, bonuslen, tx);
ztest_set_random_blocksize(os, object, tx);
dmu_object_set_checksum(os, object,
ztest_random_checksum(), tx);
dmu_object_set_compress(os, object,
ztest_random_compress(), tx);
dmu_write(os, batchobj, b * sizeof (uint64_t),
sizeof (uint64_t), &object, tx);
/*
* Write to both the bonus buffer and the regular data.
*/
VERIFY(dmu_bonus_hold(os, object, FTAG, &db) == 0);
za->za_dbuf = db;
ASSERT3U(bonuslen, <=, db->db_size);
dmu_object_size_from_db(db, &va_blksize, &va_nblocks);
ASSERT3S(va_nblocks, >=, 0);
dmu_buf_will_dirty(db, tx);
/*
* See comments above regarding the contents of
* the bonus buffer and the word at endoff.
*/
for (c = 0; c < bonuslen; c++)
((uint8_t *)db->db_data)[c] = (uint8_t)(c + bonuslen);
dmu_buf_rele(db, FTAG);
za->za_dbuf = NULL;
/*
* Write to a large offset to increase indirection.
*/
dmu_write(os, object, endoff, sizeof (uint64_t), &object, tx);
dmu_tx_commit(tx);
}
}
/*
* Verify that dmu_{read,write} work as expected.
*/
typedef struct bufwad {
uint64_t bw_index;
uint64_t bw_txg;
uint64_t bw_data;
} bufwad_t;
typedef struct dmu_read_write_dir {
uint64_t dd_packobj;
uint64_t dd_bigobj;
uint64_t dd_chunk;
} dmu_read_write_dir_t;
void
ztest_dmu_read_write(ztest_args_t *za)
{
objset_t *os = za->za_os;
dmu_read_write_dir_t dd;
dmu_tx_t *tx;
int i, freeit, error;
uint64_t n, s, txg;
bufwad_t *packbuf, *bigbuf, *pack, *bigH, *bigT;
uint64_t packoff, packsize, bigoff, bigsize;
uint64_t regions = 997;
uint64_t stride = 123456789ULL;
uint64_t width = 40;
int free_percent = 5;
/*
* This test uses two objects, packobj and bigobj, that are always
* updated together (i.e. in the same tx) so that their contents are
* in sync and can be compared. Their contents relate to each other
* in a simple way: packobj is a dense array of 'bufwad' structures,
* while bigobj is a sparse array of the same bufwads. Specifically,
* for any index n, there are three bufwads that should be identical:
*
* packobj, at offset n * sizeof (bufwad_t)
* bigobj, at the head of the nth chunk
* bigobj, at the tail of the nth chunk
*
* The chunk size is arbitrary. It doesn't have to be a power of two,
* and it doesn't have any relation to the object blocksize.
* The only requirement is that it can hold at least two bufwads.
*
* Normally, we write the bufwad to each of these locations.
* However, free_percent of the time we instead write zeroes to
* packobj and perform a dmu_free_range() on bigobj. By comparing
* bigobj to packobj, we can verify that the DMU is correctly
* tracking which parts of an object are allocated and free,
* and that the contents of the allocated blocks are correct.
*/
/*
* Read the directory info. If it's the first time, set things up.
*/
VERIFY(0 == dmu_read(os, ZTEST_DIROBJ, za->za_diroff,
2009-07-02 22:44:48 +00:00
sizeof (dd), &dd, DMU_READ_PREFETCH));
2008-11-20 20:01:55 +00:00
if (dd.dd_chunk == 0) {
ASSERT(dd.dd_packobj == 0);
ASSERT(dd.dd_bigobj == 0);
tx = dmu_tx_create(os);
dmu_tx_hold_write(tx, ZTEST_DIROBJ, za->za_diroff, sizeof (dd));
dmu_tx_hold_bonus(tx, DMU_NEW_OBJECT);
error = dmu_tx_assign(tx, TXG_WAIT);
if (error) {
ztest_record_enospc("create r/w directory");
dmu_tx_abort(tx);
return;
}
dd.dd_packobj = dmu_object_alloc(os, DMU_OT_UINT64_OTHER, 0,
DMU_OT_NONE, 0, tx);
dd.dd_bigobj = dmu_object_alloc(os, DMU_OT_UINT64_OTHER, 0,
DMU_OT_NONE, 0, tx);
dd.dd_chunk = (1000 + ztest_random(1000)) * sizeof (uint64_t);
ztest_set_random_blocksize(os, dd.dd_packobj, tx);
ztest_set_random_blocksize(os, dd.dd_bigobj, tx);
dmu_write(os, ZTEST_DIROBJ, za->za_diroff, sizeof (dd), &dd,
tx);
dmu_tx_commit(tx);
}
/*
* Prefetch a random chunk of the big object.
* Our aim here is to get some async reads in flight
* for blocks that we may free below; the DMU should
* handle this race correctly.
*/
n = ztest_random(regions) * stride + ztest_random(width);
s = 1 + ztest_random(2 * width - 1);
dmu_prefetch(os, dd.dd_bigobj, n * dd.dd_chunk, s * dd.dd_chunk);
/*
* Pick a random index and compute the offsets into packobj and bigobj.
*/
n = ztest_random(regions) * stride + ztest_random(width);
s = 1 + ztest_random(width - 1);
packoff = n * sizeof (bufwad_t);
packsize = s * sizeof (bufwad_t);
bigoff = n * dd.dd_chunk;
bigsize = s * dd.dd_chunk;
packbuf = umem_alloc(packsize, UMEM_NOFAIL);
bigbuf = umem_alloc(bigsize, UMEM_NOFAIL);
/*
* free_percent of the time, free a range of bigobj rather than
* overwriting it.
*/
freeit = (ztest_random(100) < free_percent);
/*
* Read the current contents of our objects.
*/
2009-07-02 22:44:48 +00:00
error = dmu_read(os, dd.dd_packobj, packoff, packsize, packbuf,
DMU_READ_PREFETCH);
2008-11-20 20:01:55 +00:00
ASSERT3U(error, ==, 0);
2009-07-02 22:44:48 +00:00
error = dmu_read(os, dd.dd_bigobj, bigoff, bigsize, bigbuf,
DMU_READ_PREFETCH);
2008-11-20 20:01:55 +00:00
ASSERT3U(error, ==, 0);
/*
* Get a tx for the mods to both packobj and bigobj.
*/
tx = dmu_tx_create(os);
dmu_tx_hold_write(tx, dd.dd_packobj, packoff, packsize);
if (freeit)
dmu_tx_hold_free(tx, dd.dd_bigobj, bigoff, bigsize);
else
dmu_tx_hold_write(tx, dd.dd_bigobj, bigoff, bigsize);
error = dmu_tx_assign(tx, TXG_WAIT);
if (error) {
ztest_record_enospc("dmu r/w range");
dmu_tx_abort(tx);
umem_free(packbuf, packsize);
umem_free(bigbuf, bigsize);
return;
}
txg = dmu_tx_get_txg(tx);
/*
* For each index from n to n + s, verify that the existing bufwad
* in packobj matches the bufwads at the head and tail of the
* corresponding chunk in bigobj. Then update all three bufwads
* with the new values we want to write out.
*/
for (i = 0; i < s; i++) {
/* LINTED */
pack = (bufwad_t *)((char *)packbuf + i * sizeof (bufwad_t));
/* LINTED */
bigH = (bufwad_t *)((char *)bigbuf + i * dd.dd_chunk);
/* LINTED */
bigT = (bufwad_t *)((char *)bigH + dd.dd_chunk) - 1;
ASSERT((uintptr_t)bigH - (uintptr_t)bigbuf < bigsize);
ASSERT((uintptr_t)bigT - (uintptr_t)bigbuf < bigsize);
if (pack->bw_txg > txg)
fatal(0, "future leak: got %llx, open txg is %llx",
pack->bw_txg, txg);
if (pack->bw_data != 0 && pack->bw_index != n + i)
fatal(0, "wrong index: got %llx, wanted %llx+%llx",
pack->bw_index, n, i);
if (bcmp(pack, bigH, sizeof (bufwad_t)) != 0)
fatal(0, "pack/bigH mismatch in %p/%p", pack, bigH);
if (bcmp(pack, bigT, sizeof (bufwad_t)) != 0)
fatal(0, "pack/bigT mismatch in %p/%p", pack, bigT);
if (freeit) {
bzero(pack, sizeof (bufwad_t));
} else {
pack->bw_index = n + i;
pack->bw_txg = txg;
pack->bw_data = 1 + ztest_random(-2ULL);
}
*bigH = *pack;
*bigT = *pack;
}
/*
* We've verified all the old bufwads, and made new ones.
* Now write them out.
*/
dmu_write(os, dd.dd_packobj, packoff, packsize, packbuf, tx);
if (freeit) {
if (zopt_verbose >= 6) {
(void) printf("freeing offset %llx size %llx"
" txg %llx\n",
(u_longlong_t)bigoff,
(u_longlong_t)bigsize,
(u_longlong_t)txg);
}
VERIFY(0 == dmu_free_range(os, dd.dd_bigobj, bigoff,
bigsize, tx));
} else {
if (zopt_verbose >= 6) {
(void) printf("writing offset %llx size %llx"
" txg %llx\n",
(u_longlong_t)bigoff,
(u_longlong_t)bigsize,
(u_longlong_t)txg);
}
dmu_write(os, dd.dd_bigobj, bigoff, bigsize, bigbuf, tx);
}
dmu_tx_commit(tx);
/*
* Sanity check the stuff we just wrote.
*/
{
void *packcheck = umem_alloc(packsize, UMEM_NOFAIL);
void *bigcheck = umem_alloc(bigsize, UMEM_NOFAIL);
VERIFY(0 == dmu_read(os, dd.dd_packobj, packoff,
2009-07-02 22:44:48 +00:00
packsize, packcheck, DMU_READ_PREFETCH));
2008-11-20 20:01:55 +00:00
VERIFY(0 == dmu_read(os, dd.dd_bigobj, bigoff,
2009-07-02 22:44:48 +00:00
bigsize, bigcheck, DMU_READ_PREFETCH));
2008-11-20 20:01:55 +00:00
ASSERT(bcmp(packbuf, packcheck, packsize) == 0);
ASSERT(bcmp(bigbuf, bigcheck, bigsize) == 0);
umem_free(packcheck, packsize);
umem_free(bigcheck, bigsize);
}
umem_free(packbuf, packsize);
umem_free(bigbuf, bigsize);
}
2009-07-02 22:44:48 +00:00
void
compare_and_update_pbbufs(uint64_t s, bufwad_t *packbuf, bufwad_t *bigbuf,
uint64_t bigsize, uint64_t n, dmu_read_write_dir_t dd, uint64_t txg)
{
uint64_t i;
bufwad_t *pack;
bufwad_t *bigH;
bufwad_t *bigT;
/*
* For each index from n to n + s, verify that the existing bufwad
* in packobj matches the bufwads at the head and tail of the
* corresponding chunk in bigobj. Then update all three bufwads
* with the new values we want to write out.
*/
for (i = 0; i < s; i++) {
/* LINTED */
pack = (bufwad_t *)((char *)packbuf + i * sizeof (bufwad_t));
/* LINTED */
bigH = (bufwad_t *)((char *)bigbuf + i * dd.dd_chunk);
/* LINTED */
bigT = (bufwad_t *)((char *)bigH + dd.dd_chunk) - 1;
ASSERT((uintptr_t)bigH - (uintptr_t)bigbuf < bigsize);
ASSERT((uintptr_t)bigT - (uintptr_t)bigbuf < bigsize);
if (pack->bw_txg > txg)
fatal(0, "future leak: got %llx, open txg is %llx",
pack->bw_txg, txg);
if (pack->bw_data != 0 && pack->bw_index != n + i)
fatal(0, "wrong index: got %llx, wanted %llx+%llx",
pack->bw_index, n, i);
if (bcmp(pack, bigH, sizeof (bufwad_t)) != 0)
fatal(0, "pack/bigH mismatch in %p/%p", pack, bigH);
if (bcmp(pack, bigT, sizeof (bufwad_t)) != 0)
fatal(0, "pack/bigT mismatch in %p/%p", pack, bigT);
pack->bw_index = n + i;
pack->bw_txg = txg;
pack->bw_data = 1 + ztest_random(-2ULL);
*bigH = *pack;
*bigT = *pack;
}
}
void
ztest_dmu_read_write_zcopy(ztest_args_t *za)
{
objset_t *os = za->za_os;
dmu_read_write_dir_t dd;
dmu_tx_t *tx;
uint64_t i;
int error;
uint64_t n, s, txg;
bufwad_t *packbuf, *bigbuf;
uint64_t packoff, packsize, bigoff, bigsize;
uint64_t regions = 997;
uint64_t stride = 123456789ULL;
uint64_t width = 9;
dmu_buf_t *bonus_db;
arc_buf_t **bigbuf_arcbufs;
dmu_object_info_t *doi = &za->za_doi;
/*
* This test uses two objects, packobj and bigobj, that are always
* updated together (i.e. in the same tx) so that their contents are
* in sync and can be compared. Their contents relate to each other
* in a simple way: packobj is a dense array of 'bufwad' structures,
* while bigobj is a sparse array of the same bufwads. Specifically,
* for any index n, there are three bufwads that should be identical:
*
* packobj, at offset n * sizeof (bufwad_t)
* bigobj, at the head of the nth chunk
* bigobj, at the tail of the nth chunk
*
* The chunk size is set equal to bigobj block size so that
* dmu_assign_arcbuf() can be tested for object updates.
*/
/*
* Read the directory info. If it's the first time, set things up.
*/
VERIFY(0 == dmu_read(os, ZTEST_DIROBJ, za->za_diroff,
sizeof (dd), &dd, DMU_READ_PREFETCH));
if (dd.dd_chunk == 0) {
ASSERT(dd.dd_packobj == 0);
ASSERT(dd.dd_bigobj == 0);
tx = dmu_tx_create(os);
dmu_tx_hold_write(tx, ZTEST_DIROBJ, za->za_diroff, sizeof (dd));
dmu_tx_hold_bonus(tx, DMU_NEW_OBJECT);
error = dmu_tx_assign(tx, TXG_WAIT);
if (error) {
ztest_record_enospc("create r/w directory");
dmu_tx_abort(tx);
return;
}
dd.dd_packobj = dmu_object_alloc(os, DMU_OT_UINT64_OTHER, 0,
DMU_OT_NONE, 0, tx);
dd.dd_bigobj = dmu_object_alloc(os, DMU_OT_UINT64_OTHER, 0,
DMU_OT_NONE, 0, tx);
ztest_set_random_blocksize(os, dd.dd_packobj, tx);
ztest_set_random_blocksize(os, dd.dd_bigobj, tx);
VERIFY(dmu_object_info(os, dd.dd_bigobj, doi) == 0);
ASSERT(doi->doi_data_block_size >= 2 * sizeof (bufwad_t));
ASSERT(ISP2(doi->doi_data_block_size));
dd.dd_chunk = doi->doi_data_block_size;
dmu_write(os, ZTEST_DIROBJ, za->za_diroff, sizeof (dd), &dd,
tx);
dmu_tx_commit(tx);
} else {
VERIFY(dmu_object_info(os, dd.dd_bigobj, doi) == 0);
VERIFY(ISP2(doi->doi_data_block_size));
VERIFY(dd.dd_chunk == doi->doi_data_block_size);
VERIFY(dd.dd_chunk >= 2 * sizeof (bufwad_t));
}
/*
* Pick a random index and compute the offsets into packobj and bigobj.
*/
n = ztest_random(regions) * stride + ztest_random(width);
s = 1 + ztest_random(width - 1);
packoff = n * sizeof (bufwad_t);
packsize = s * sizeof (bufwad_t);
bigoff = n * dd.dd_chunk;
bigsize = s * dd.dd_chunk;
packbuf = umem_zalloc(packsize, UMEM_NOFAIL);
bigbuf = umem_zalloc(bigsize, UMEM_NOFAIL);
VERIFY(dmu_bonus_hold(os, dd.dd_bigobj, FTAG, &bonus_db) == 0);
bigbuf_arcbufs = umem_zalloc(2 * s * sizeof (arc_buf_t *), UMEM_NOFAIL);
/*
* Iteration 0 test zcopy for DB_UNCACHED dbufs.
* Iteration 1 test zcopy to already referenced dbufs.
* Iteration 2 test zcopy to dirty dbuf in the same txg.
* Iteration 3 test zcopy to dbuf dirty in previous txg.
* Iteration 4 test zcopy when dbuf is no longer dirty.
* Iteration 5 test zcopy when it can't be done.
* Iteration 6 one more zcopy write.
*/
for (i = 0; i < 7; i++) {
uint64_t j;
uint64_t off;
/*
* In iteration 5 (i == 5) use arcbufs
* that don't match bigobj blksz to test
* dmu_assign_arcbuf() when it can't directly
* assign an arcbuf to a dbuf.
*/
for (j = 0; j < s; j++) {
if (i != 5) {
bigbuf_arcbufs[j] =
dmu_request_arcbuf(bonus_db,
dd.dd_chunk);
} else {
bigbuf_arcbufs[2 * j] =
dmu_request_arcbuf(bonus_db,
dd.dd_chunk / 2);
bigbuf_arcbufs[2 * j + 1] =
dmu_request_arcbuf(bonus_db,
dd.dd_chunk / 2);
}
}
/*
* Get a tx for the mods to both packobj and bigobj.
*/
tx = dmu_tx_create(os);
dmu_tx_hold_write(tx, dd.dd_packobj, packoff, packsize);
dmu_tx_hold_write(tx, dd.dd_bigobj, bigoff, bigsize);
if (ztest_random(100) == 0) {
error = -1;
} else {
error = dmu_tx_assign(tx, TXG_WAIT);
}
if (error) {
if (error != -1) {
ztest_record_enospc("dmu r/w range");
}
dmu_tx_abort(tx);
umem_free(packbuf, packsize);
umem_free(bigbuf, bigsize);
for (j = 0; j < s; j++) {
if (i != 5) {
dmu_return_arcbuf(bigbuf_arcbufs[j]);
} else {
dmu_return_arcbuf(
bigbuf_arcbufs[2 * j]);
dmu_return_arcbuf(
bigbuf_arcbufs[2 * j + 1]);
}
}
umem_free(bigbuf_arcbufs, 2 * s * sizeof (arc_buf_t *));
dmu_buf_rele(bonus_db, FTAG);
return;
}
txg = dmu_tx_get_txg(tx);
/*
* 50% of the time don't read objects in the 1st iteration to
* test dmu_assign_arcbuf() for the case when there're no
* existing dbufs for the specified offsets.
*/
if (i != 0 || ztest_random(2) != 0) {
error = dmu_read(os, dd.dd_packobj, packoff,
packsize, packbuf, DMU_READ_PREFETCH);
ASSERT3U(error, ==, 0);
error = dmu_read(os, dd.dd_bigobj, bigoff, bigsize,
bigbuf, DMU_READ_PREFETCH);
ASSERT3U(error, ==, 0);
}
compare_and_update_pbbufs(s, packbuf, bigbuf, bigsize,
n, dd, txg);
/*
* We've verified all the old bufwads, and made new ones.
* Now write them out.
*/
dmu_write(os, dd.dd_packobj, packoff, packsize, packbuf, tx);
if (zopt_verbose >= 6) {
(void) printf("writing offset %llx size %llx"
" txg %llx\n",
(u_longlong_t)bigoff,
(u_longlong_t)bigsize,
(u_longlong_t)txg);
}
for (off = bigoff, j = 0; j < s; j++, off += dd.dd_chunk) {
dmu_buf_t *dbt;
if (i != 5) {
bcopy((caddr_t)bigbuf + (off - bigoff),
bigbuf_arcbufs[j]->b_data, dd.dd_chunk);
} else {
bcopy((caddr_t)bigbuf + (off - bigoff),
bigbuf_arcbufs[2 * j]->b_data,
dd.dd_chunk / 2);
bcopy((caddr_t)bigbuf + (off - bigoff) +
dd.dd_chunk / 2,
bigbuf_arcbufs[2 * j + 1]->b_data,
dd.dd_chunk / 2);
}
if (i == 1) {
VERIFY(dmu_buf_hold(os, dd.dd_bigobj, off,
FTAG, &dbt) == 0);
}
if (i != 5) {
dmu_assign_arcbuf(bonus_db, off,
bigbuf_arcbufs[j], tx);
} else {
dmu_assign_arcbuf(bonus_db, off,
bigbuf_arcbufs[2 * j], tx);
dmu_assign_arcbuf(bonus_db,
off + dd.dd_chunk / 2,
bigbuf_arcbufs[2 * j + 1], tx);
}
if (i == 1) {
dmu_buf_rele(dbt, FTAG);
}
}
dmu_tx_commit(tx);
/*
* Sanity check the stuff we just wrote.
*/
{
void *packcheck = umem_alloc(packsize, UMEM_NOFAIL);
void *bigcheck = umem_alloc(bigsize, UMEM_NOFAIL);
VERIFY(0 == dmu_read(os, dd.dd_packobj, packoff,
packsize, packcheck, DMU_READ_PREFETCH));
VERIFY(0 == dmu_read(os, dd.dd_bigobj, bigoff,
bigsize, bigcheck, DMU_READ_PREFETCH));
ASSERT(bcmp(packbuf, packcheck, packsize) == 0);
ASSERT(bcmp(bigbuf, bigcheck, bigsize) == 0);
umem_free(packcheck, packsize);
umem_free(bigcheck, bigsize);
}
if (i == 2) {
txg_wait_open(dmu_objset_pool(os), 0);
} else if (i == 3) {
txg_wait_synced(dmu_objset_pool(os), 0);
}
}
dmu_buf_rele(bonus_db, FTAG);
umem_free(packbuf, packsize);
umem_free(bigbuf, bigsize);
umem_free(bigbuf_arcbufs, 2 * s * sizeof (arc_buf_t *));
}
2008-11-20 20:01:55 +00:00
void
ztest_dmu_check_future_leak(ztest_args_t *za)
{
objset_t *os = za->za_os;
dmu_buf_t *db;
ztest_block_tag_t *bt;
dmu_object_info_t *doi = &za->za_doi;
/*
* Make sure that, if there is a write record in the bonus buffer
* of the ZTEST_DIROBJ, that the txg for this record is <= the
* last synced txg of the pool.
*/
VERIFY(dmu_bonus_hold(os, ZTEST_DIROBJ, FTAG, &db) == 0);
za->za_dbuf = db;
VERIFY(dmu_object_info(os, ZTEST_DIROBJ, doi) == 0);
ASSERT3U(doi->doi_bonus_size, >=, sizeof (*bt));
ASSERT3U(doi->doi_bonus_size, <=, db->db_size);
ASSERT3U(doi->doi_bonus_size % sizeof (*bt), ==, 0);
bt = (void *)((char *)db->db_data + doi->doi_bonus_size - sizeof (*bt));
if (bt->bt_objset != 0) {
ASSERT3U(bt->bt_objset, ==, dmu_objset_id(os));
ASSERT3U(bt->bt_object, ==, ZTEST_DIROBJ);
ASSERT3U(bt->bt_offset, ==, -1ULL);
ASSERT3U(bt->bt_txg, <, spa_first_txg(za->za_spa));
}
dmu_buf_rele(db, FTAG);
za->za_dbuf = NULL;
}
void
ztest_dmu_write_parallel(ztest_args_t *za)
{
objset_t *os = za->za_os;
ztest_block_tag_t *rbt = &za->za_rbt;
ztest_block_tag_t *wbt = &za->za_wbt;
const size_t btsize = sizeof (ztest_block_tag_t);
dmu_buf_t *db;
int b, error;
int bs = ZTEST_DIROBJ_BLOCKSIZE;
int do_free = 0;
uint64_t off, txg, txg_how;
kmutex_t *lp;
2008-11-20 20:01:55 +00:00
char osname[MAXNAMELEN];
char iobuf[SPA_MAXBLOCKSIZE];
blkptr_t blk;
2008-11-20 20:01:55 +00:00
uint64_t blkoff;
zbookmark_t zb;
dmu_tx_t *tx = dmu_tx_create(os);
2009-07-02 22:44:48 +00:00
dmu_buf_t *bonus_db;
arc_buf_t *abuf = NULL;
2008-11-20 20:01:55 +00:00
bzero(&blk, sizeof(blkptr_t));
2008-11-20 20:01:55 +00:00
dmu_objset_name(os, osname);
/*
* Have multiple threads write to large offsets in ZTEST_DIROBJ
* to verify that having multiple threads writing to the same object
* in parallel doesn't cause any trouble.
*/
if (ztest_random(4) == 0) {
/*
* Do the bonus buffer instead of a regular block.
* We need a lock to serialize resize vs. others,
* so we hash on the objset ID.
*/
b = dmu_objset_id(os) % ZTEST_SYNC_LOCKS;
off = -1ULL;
dmu_tx_hold_bonus(tx, ZTEST_DIROBJ);
} else {
b = ztest_random(ZTEST_SYNC_LOCKS);
off = za->za_diroff_shared + (b << SPA_MAXBLOCKSHIFT);
if (ztest_random(4) == 0) {
do_free = 1;
dmu_tx_hold_free(tx, ZTEST_DIROBJ, off, bs);
} else {
dmu_tx_hold_write(tx, ZTEST_DIROBJ, off, bs);
}
}
2009-07-02 22:44:48 +00:00
if (off != -1ULL && P2PHASE(off, bs) == 0 && !do_free &&
ztest_random(8) == 0) {
VERIFY(dmu_bonus_hold(os, ZTEST_DIROBJ, FTAG, &bonus_db) == 0);
abuf = dmu_request_arcbuf(bonus_db, bs);
}
2008-11-20 20:01:55 +00:00
txg_how = ztest_random(2) == 0 ? TXG_WAIT : TXG_NOWAIT;
error = dmu_tx_assign(tx, txg_how);
if (error) {
if (error == ERESTART) {
ASSERT(txg_how == TXG_NOWAIT);
dmu_tx_wait(tx);
} else {
ztest_record_enospc("dmu write parallel");
}
dmu_tx_abort(tx);
2009-07-02 22:44:48 +00:00
if (abuf != NULL) {
dmu_return_arcbuf(abuf);
dmu_buf_rele(bonus_db, FTAG);
}
2008-11-20 20:01:55 +00:00
return;
}
txg = dmu_tx_get_txg(tx);
2008-11-20 20:01:55 +00:00
lp = &ztest_shared->zs_sync_lock[b];
mutex_enter(lp);
2008-11-20 20:01:55 +00:00
wbt->bt_objset = dmu_objset_id(os);
wbt->bt_object = ZTEST_DIROBJ;
wbt->bt_offset = off;
wbt->bt_txg = txg;
2008-11-20 20:01:55 +00:00
wbt->bt_thread = za->za_instance;
wbt->bt_seq = ztest_shared->zs_seq[b]++; /* protected by lp */
/*
* Occasionally, write an all-zero block to test the behavior
* of blocks that compress into holes.
*/
if (off != -1ULL && ztest_random(8) == 0)
bzero(wbt, btsize);
2008-11-20 20:01:55 +00:00
if (off == -1ULL) {
dmu_object_info_t *doi = &za->za_doi;
char *dboff;
VERIFY(dmu_bonus_hold(os, ZTEST_DIROBJ, FTAG, &db) == 0);
za->za_dbuf = db;
dmu_object_info_from_db(db, doi);
ASSERT3U(doi->doi_bonus_size, <=, db->db_size);
ASSERT3U(doi->doi_bonus_size, >=, btsize);
ASSERT3U(doi->doi_bonus_size % btsize, ==, 0);
dboff = (char *)db->db_data + doi->doi_bonus_size - btsize;
bcopy(dboff, rbt, btsize);
if (rbt->bt_objset != 0) {
ASSERT3U(rbt->bt_objset, ==, wbt->bt_objset);
ASSERT3U(rbt->bt_object, ==, wbt->bt_object);
ASSERT3U(rbt->bt_offset, ==, wbt->bt_offset);
ASSERT3U(rbt->bt_txg, <=, wbt->bt_txg);
}
if (ztest_random(10) == 0) {
int newsize = (ztest_random(db->db_size /
btsize) + 1) * btsize;
ASSERT3U(newsize, >=, btsize);
ASSERT3U(newsize, <=, db->db_size);
VERIFY3U(dmu_set_bonus(db, newsize, tx), ==, 0);
dboff = (char *)db->db_data + newsize - btsize;
}
dmu_buf_will_dirty(db, tx);
bcopy(wbt, dboff, btsize);
dmu_buf_rele(db, FTAG);
za->za_dbuf = NULL;
} else if (do_free) {
VERIFY(dmu_free_range(os, ZTEST_DIROBJ, off, bs, tx) == 0);
2009-07-02 22:44:48 +00:00
} else if (abuf == NULL) {
2008-11-20 20:01:55 +00:00
dmu_write(os, ZTEST_DIROBJ, off, btsize, wbt, tx);
2009-07-02 22:44:48 +00:00
} else {
bcopy(wbt, abuf->b_data, btsize);
dmu_assign_arcbuf(bonus_db, off, abuf, tx);
dmu_buf_rele(bonus_db, FTAG);
2008-11-20 20:01:55 +00:00
}
mutex_exit(lp);
2008-11-20 20:01:55 +00:00
if (ztest_random(1000) == 0)
(void) poll(NULL, 0, 1); /* open dn_notxholds window */
dmu_tx_commit(tx);
if (ztest_random(10000) == 0)
txg_wait_synced(dmu_objset_pool(os), txg);
2008-11-20 20:01:55 +00:00
if (off == -1ULL || do_free)
2008-11-20 20:01:55 +00:00
return;
if (ztest_random(2) != 0)
return;
/*
* dmu_sync() the block we just wrote.
*/
mutex_enter(lp);
2008-11-20 20:01:55 +00:00
blkoff = P2ALIGN_TYPED(off, bs, uint64_t);
error = dmu_buf_hold(os, ZTEST_DIROBJ, blkoff, FTAG, &db);
za->za_dbuf = db;
if (error) {
mutex_exit(lp);
2008-11-20 20:01:55 +00:00
return;
}
blkoff = off - blkoff;
error = dmu_sync(NULL, db, &blk, txg, NULL, NULL);
2008-11-20 20:01:55 +00:00
dmu_buf_rele(db, FTAG);
za->za_dbuf = NULL;
2009-07-02 22:44:48 +00:00
if (error) {
mutex_exit(lp);
2008-11-20 20:01:55 +00:00
return;
2009-07-02 22:44:48 +00:00
}
2008-11-20 20:01:55 +00:00
2009-07-02 22:44:48 +00:00
if (blk.blk_birth == 0) { /* concurrent free */
mutex_exit(lp);
2008-11-20 20:01:55 +00:00
return;
2009-07-02 22:44:48 +00:00
}
2008-11-20 20:01:55 +00:00
txg_suspend(dmu_objset_pool(os));
mutex_exit(lp);
2009-07-02 22:44:48 +00:00
2008-11-20 20:01:55 +00:00
ASSERT(blk.blk_fill == 1);
ASSERT3U(BP_GET_TYPE(&blk), ==, DMU_OT_UINT64_OTHER);
ASSERT3U(BP_GET_LEVEL(&blk), ==, 0);
ASSERT3U(BP_GET_LSIZE(&blk), ==, bs);
/*
* Read the block that dmu_sync() returned to make sure its contents
* match what we wrote. We do this while still txg_suspend()ed
* to ensure that the block can't be reused before we read it.
*/
zb.zb_objset = dmu_objset_id(os);
zb.zb_object = ZTEST_DIROBJ;
zb.zb_level = 0;
zb.zb_blkid = off / bs;
error = zio_wait(zio_read(NULL, za->za_spa, &blk, iobuf, bs,
NULL, NULL, ZIO_PRIORITY_SYNC_READ, ZIO_FLAG_MUSTSUCCEED, &zb));
ASSERT3U(error, ==, 0);
txg_resume(dmu_objset_pool(os));
bcopy(&iobuf[blkoff], rbt, btsize);
if (rbt->bt_objset == 0) /* concurrent free */
return;
if (wbt->bt_objset == 0) /* all-zero overwrite */
return;
2008-11-20 20:01:55 +00:00
ASSERT3U(rbt->bt_objset, ==, wbt->bt_objset);
ASSERT3U(rbt->bt_object, ==, wbt->bt_object);
ASSERT3U(rbt->bt_offset, ==, wbt->bt_offset);
/*
* The semantic of dmu_sync() is that we always push the most recent
* version of the data, so in the face of concurrent updates we may
* see a newer version of the block. That's OK.
*/
ASSERT3U(rbt->bt_txg, >=, wbt->bt_txg);
if (rbt->bt_thread == wbt->bt_thread)
ASSERT3U(rbt->bt_seq, ==, wbt->bt_seq);
else
ASSERT3U(rbt->bt_seq, >, wbt->bt_seq);
}
/*
* Verify that zap_{create,destroy,add,remove,update} work as expected.
*/
#define ZTEST_ZAP_MIN_INTS 1
#define ZTEST_ZAP_MAX_INTS 4
#define ZTEST_ZAP_MAX_PROPS 1000
void
ztest_zap(ztest_args_t *za)
{
objset_t *os = za->za_os;
uint64_t object;
uint64_t txg, last_txg;
uint64_t value[ZTEST_ZAP_MAX_INTS];
uint64_t zl_ints, zl_intsize, prop;
int i, ints;
dmu_tx_t *tx;
char propname[100], txgname[100];
int error;
char osname[MAXNAMELEN];
char *hc[2] = { "s.acl.h", ".s.open.h.hyLZlg" };
dmu_objset_name(os, osname);
/*
* Create a new object if necessary, and record it in the directory.
*/
VERIFY(0 == dmu_read(os, ZTEST_DIROBJ, za->za_diroff,
2009-07-02 22:44:48 +00:00
sizeof (uint64_t), &object, DMU_READ_PREFETCH));
2008-11-20 20:01:55 +00:00
if (object == 0) {
tx = dmu_tx_create(os);
dmu_tx_hold_write(tx, ZTEST_DIROBJ, za->za_diroff,
sizeof (uint64_t));
dmu_tx_hold_zap(tx, DMU_NEW_OBJECT, TRUE, NULL);
error = dmu_tx_assign(tx, TXG_WAIT);
if (error) {
ztest_record_enospc("create zap test obj");
dmu_tx_abort(tx);
return;
}
object = zap_create(os, DMU_OT_ZAP_OTHER, DMU_OT_NONE, 0, tx);
if (error) {
fatal(0, "zap_create('%s', %llu) = %d",
osname, object, error);
}
ASSERT(object != 0);
dmu_write(os, ZTEST_DIROBJ, za->za_diroff,
sizeof (uint64_t), &object, tx);
/*
* Generate a known hash collision, and verify that
* we can lookup and remove both entries.
*/
for (i = 0; i < 2; i++) {
value[i] = i;
error = zap_add(os, object, hc[i], sizeof (uint64_t),
1, &value[i], tx);
ASSERT3U(error, ==, 0);
}
for (i = 0; i < 2; i++) {
error = zap_add(os, object, hc[i], sizeof (uint64_t),
1, &value[i], tx);
ASSERT3U(error, ==, EEXIST);
error = zap_length(os, object, hc[i],
&zl_intsize, &zl_ints);
ASSERT3U(error, ==, 0);
ASSERT3U(zl_intsize, ==, sizeof (uint64_t));
ASSERT3U(zl_ints, ==, 1);
}
for (i = 0; i < 2; i++) {
error = zap_remove(os, object, hc[i], tx);
ASSERT3U(error, ==, 0);
}
dmu_tx_commit(tx);
}
ints = MAX(ZTEST_ZAP_MIN_INTS, object % ZTEST_ZAP_MAX_INTS);
prop = ztest_random(ZTEST_ZAP_MAX_PROPS);
(void) sprintf(propname, "prop_%llu", (u_longlong_t)prop);
(void) sprintf(txgname, "txg_%llu", (u_longlong_t)prop);
bzero(value, sizeof (value));
last_txg = 0;
/*
* If these zap entries already exist, validate their contents.
*/
error = zap_length(os, object, txgname, &zl_intsize, &zl_ints);
if (error == 0) {
ASSERT3U(zl_intsize, ==, sizeof (uint64_t));
ASSERT3U(zl_ints, ==, 1);
VERIFY(zap_lookup(os, object, txgname, zl_intsize,
zl_ints, &last_txg) == 0);
VERIFY(zap_length(os, object, propname, &zl_intsize,
&zl_ints) == 0);
ASSERT3U(zl_intsize, ==, sizeof (uint64_t));
ASSERT3U(zl_ints, ==, ints);
VERIFY(zap_lookup(os, object, propname, zl_intsize,
zl_ints, value) == 0);
for (i = 0; i < ints; i++) {
ASSERT3U(value[i], ==, last_txg + object + i);
}
} else {
ASSERT3U(error, ==, ENOENT);
}
/*
* Atomically update two entries in our zap object.
* The first is named txg_%llu, and contains the txg
* in which the property was last updated. The second
* is named prop_%llu, and the nth element of its value
* should be txg + object + n.
*/
tx = dmu_tx_create(os);
dmu_tx_hold_zap(tx, object, TRUE, NULL);
error = dmu_tx_assign(tx, TXG_WAIT);
if (error) {
ztest_record_enospc("create zap entry");
dmu_tx_abort(tx);
return;
}
txg = dmu_tx_get_txg(tx);
if (last_txg > txg)
fatal(0, "zap future leak: old %llu new %llu", last_txg, txg);
for (i = 0; i < ints; i++)
value[i] = txg + object + i;
error = zap_update(os, object, txgname, sizeof (uint64_t), 1, &txg, tx);
if (error)
fatal(0, "zap_update('%s', %llu, '%s') = %d",
osname, object, txgname, error);
error = zap_update(os, object, propname, sizeof (uint64_t),
ints, value, tx);
if (error)
fatal(0, "zap_update('%s', %llu, '%s') = %d",
osname, object, propname, error);
dmu_tx_commit(tx);
/*
* Remove a random pair of entries.
*/
prop = ztest_random(ZTEST_ZAP_MAX_PROPS);
(void) sprintf(propname, "prop_%llu", (u_longlong_t)prop);
(void) sprintf(txgname, "txg_%llu", (u_longlong_t)prop);
error = zap_length(os, object, txgname, &zl_intsize, &zl_ints);
if (error == ENOENT)
return;
ASSERT3U(error, ==, 0);
tx = dmu_tx_create(os);
dmu_tx_hold_zap(tx, object, TRUE, NULL);
error = dmu_tx_assign(tx, TXG_WAIT);
if (error) {
ztest_record_enospc("remove zap entry");
dmu_tx_abort(tx);
return;
}
error = zap_remove(os, object, txgname, tx);
if (error)
fatal(0, "zap_remove('%s', %llu, '%s') = %d",
osname, object, txgname, error);
error = zap_remove(os, object, propname, tx);
if (error)
fatal(0, "zap_remove('%s', %llu, '%s') = %d",
osname, object, propname, error);
dmu_tx_commit(tx);
/*
* Once in a while, destroy the object.
*/
if (ztest_random(1000) != 0)
return;
tx = dmu_tx_create(os);
dmu_tx_hold_write(tx, ZTEST_DIROBJ, za->za_diroff, sizeof (uint64_t));
dmu_tx_hold_free(tx, object, 0, DMU_OBJECT_END);
error = dmu_tx_assign(tx, TXG_WAIT);
if (error) {
ztest_record_enospc("destroy zap object");
dmu_tx_abort(tx);
return;
}
error = zap_destroy(os, object, tx);
if (error)
fatal(0, "zap_destroy('%s', %llu) = %d",
osname, object, error);
object = 0;
dmu_write(os, ZTEST_DIROBJ, za->za_diroff, sizeof (uint64_t),
&object, tx);
dmu_tx_commit(tx);
}
void
ztest_zap_parallel(ztest_args_t *za)
{
objset_t *os = za->za_os;
uint64_t txg, object, count, wsize, wc, zl_wsize, zl_wc;
dmu_tx_t *tx;
int i, namelen, error;
char name[20], string_value[20];
void *data;
/*
* Generate a random name of the form 'xxx.....' where each
* x is a random printable character and the dots are dots.
* There are 94 such characters, and the name length goes from
* 6 to 20, so there are 94^3 * 15 = 12,458,760 possible names.
*/
namelen = ztest_random(sizeof (name) - 5) + 5 + 1;
for (i = 0; i < 3; i++)
name[i] = '!' + ztest_random('~' - '!' + 1);
for (; i < namelen - 1; i++)
name[i] = '.';
name[i] = '\0';
if (ztest_random(2) == 0)
object = ZTEST_MICROZAP_OBJ;
else
object = ZTEST_FATZAP_OBJ;
if ((namelen & 1) || object == ZTEST_MICROZAP_OBJ) {
wsize = sizeof (txg);
wc = 1;
data = &txg;
} else {
wsize = 1;
wc = namelen;
data = string_value;
}
count = -1ULL;
VERIFY(zap_count(os, object, &count) == 0);
ASSERT(count != -1ULL);
/*
* Select an operation: length, lookup, add, update, remove.
*/
i = ztest_random(5);
if (i >= 2) {
tx = dmu_tx_create(os);
dmu_tx_hold_zap(tx, object, TRUE, NULL);
error = dmu_tx_assign(tx, TXG_WAIT);
if (error) {
ztest_record_enospc("zap parallel");
dmu_tx_abort(tx);
return;
}
txg = dmu_tx_get_txg(tx);
bcopy(name, string_value, namelen);
} else {
tx = NULL;
txg = 0;
bzero(string_value, namelen);
}
switch (i) {
case 0:
error = zap_length(os, object, name, &zl_wsize, &zl_wc);
if (error == 0) {
ASSERT3U(wsize, ==, zl_wsize);
ASSERT3U(wc, ==, zl_wc);
} else {
ASSERT3U(error, ==, ENOENT);
}
break;
case 1:
error = zap_lookup(os, object, name, wsize, wc, data);
if (error == 0) {
if (data == string_value &&
bcmp(name, data, namelen) != 0)
fatal(0, "name '%s' != val '%s' len %d",
name, data, namelen);
} else {
ASSERT3U(error, ==, ENOENT);
}
break;
case 2:
error = zap_add(os, object, name, wsize, wc, data, tx);
ASSERT(error == 0 || error == EEXIST);
break;
case 3:
VERIFY(zap_update(os, object, name, wsize, wc, data, tx) == 0);
break;
case 4:
error = zap_remove(os, object, name, tx);
ASSERT(error == 0 || error == ENOENT);
break;
}
if (tx != NULL)
dmu_tx_commit(tx);
}
/*
* Commit callback data.
*/
typedef struct ztest_cb_data {
list_node_t zcd_node;
ztest_cb_list_t *zcd_zcl;
uint64_t zcd_txg;
int zcd_expected_err;
boolean_t zcd_added;
boolean_t zcd_called;
spa_t *zcd_spa;
} ztest_cb_data_t;
static void
ztest_commit_callback(void *arg, int error)
{
ztest_cb_data_t *data = arg;
ztest_cb_list_t *zcl;
uint64_t synced_txg;
VERIFY(data != NULL);
VERIFY3S(data->zcd_expected_err, ==, error);
VERIFY(!data->zcd_called);
synced_txg = spa_last_synced_txg(data->zcd_spa);
if (data->zcd_txg > synced_txg)
fatal(0, "commit callback of txg %llu prematurely called, last"
" synced txg = %llu\n", data->zcd_txg, synced_txg);
zcl = data->zcd_zcl;
data->zcd_called = B_TRUE;
if (error == ECANCELED) {
ASSERT3U(data->zcd_txg, ==, 0);
ASSERT(!data->zcd_added);
/*
* The private callback data should be destroyed here, but
* since we are going to check the zcd_called field after
* dmu_tx_abort(), we will destroy it there.
*/
return;
}
if (!data->zcd_added)
goto out;
ASSERT3U(data->zcd_txg, !=, 0);
/* Remove our callback from the list */
mutex_enter(&zcl->zcl_callbacks_lock);
list_remove(&zcl->zcl_callbacks, data);
mutex_exit(&zcl->zcl_callbacks_lock);
out:
umem_free(data, sizeof (ztest_cb_data_t));
}
static ztest_cb_data_t *
ztest_create_cb_data(objset_t *os, ztest_cb_list_t *zcl, uint64_t txg)
{
ztest_cb_data_t *cb_data;
cb_data = umem_zalloc(sizeof (ztest_cb_data_t), UMEM_NOFAIL);
cb_data->zcd_zcl = zcl;
cb_data->zcd_txg = txg;
cb_data->zcd_spa = os->os->os_spa;
return (cb_data);
}
/*
* If a number of txgs equal to this threshold have been created after a commit
* callback has been registered but not called, then we assume there is an
* implementation bug.
*/
#define ZTEST_COMMIT_CALLBACK_THRESH 3
/*
* Commit callback test.
*/
void
ztest_dmu_commit_callbacks(ztest_args_t *za)
{
objset_t *os = za->za_os;
dmu_tx_t *tx;
ztest_cb_list_t *zcl = &ztest_shared->zs_cb_list;
ztest_cb_data_t *cb_data[3], *tmp_cb;
uint64_t old_txg, txg;
int i, error = 0;
tx = dmu_tx_create(os);
cb_data[0] = ztest_create_cb_data(os, zcl, 0);
dmu_tx_callback_register(tx, ztest_commit_callback, cb_data[0]);
dmu_tx_hold_write(tx, ZTEST_DIROBJ, za->za_diroff, sizeof (uint64_t));
/* Every once in a while, abort the transaction on purpose */
if (ztest_random(100) == 0)
error = -1;
if (!error)
error = dmu_tx_assign(tx, TXG_NOWAIT);
txg = error ? 0 : dmu_tx_get_txg(tx);
cb_data[1] = ztest_create_cb_data(os, zcl, txg);
dmu_tx_callback_register(tx, ztest_commit_callback, cb_data[1]);
if (error) {
/*
* It's not a strict requirement to call the registered
* callbacks from inside dmu_tx_abort(), but that's what
* happens in the current implementation so we will check for
* that.
*/
for (i = 0; i < 2; i++) {
cb_data[i]->zcd_expected_err = ECANCELED;
VERIFY(!cb_data[i]->zcd_called);
}
dmu_tx_abort(tx);
for (i = 0; i < 2; i++) {
VERIFY(cb_data[i]->zcd_called);
umem_free(cb_data[i], sizeof (ztest_cb_data_t));
}
return;
}
cb_data[0]->zcd_txg = txg;
cb_data[2] = ztest_create_cb_data(os, zcl, txg);
dmu_tx_callback_register(tx, ztest_commit_callback, cb_data[2]);
/*
* Read existing data to make sure there isn't a future leak.
*/
VERIFY(0 == dmu_read(os, ZTEST_DIROBJ, za->za_diroff,
sizeof (uint64_t), &old_txg, DMU_READ_PREFETCH));
if (old_txg > txg)
fatal(0, "future leak: got %llx, open txg is %llx", old_txg,
txg);
dmu_write(os, ZTEST_DIROBJ, za->za_diroff, sizeof (uint64_t), &txg, tx);
mutex_enter(&zcl->zcl_callbacks_lock);
/*
* Since commit callbacks don't have any ordering requirement and since
* it is theoretically possible for a commit callback to be called
* after an arbitrary amount of time has elapsed since its txg has been
* synced, it is difficult to reliably determine whether a commit
* callback hasn't been called due to high load or due to a flawed
* implementation.
*
* In practice, we will assume that if after a certain number of txgs a
* commit callback hasn't been called, then most likely there's an
* implementation bug..
*/
tmp_cb = list_head(&zcl->zcl_callbacks);
if (tmp_cb != NULL)
VERIFY3U(tmp_cb->zcd_txg, >,
txg - ZTEST_COMMIT_CALLBACK_THRESH);
/*
* Let's find the place to insert our callbacks.
*
* Even though the list is ordered by txg, it is possible for the
* insertion point to not be the end because our txg may already be
* quiescing at this point and other callbacks in the open txg may
* have sneaked in.
*/
tmp_cb = list_tail(&zcl->zcl_callbacks);
while (tmp_cb != NULL && tmp_cb->zcd_txg > txg)
tmp_cb = list_prev(&zcl->zcl_callbacks, tmp_cb);
/* Add the 3 callbacks to the list */
for (i = 0; i < 3; i++) {
if (tmp_cb == NULL)
list_insert_head(&zcl->zcl_callbacks, cb_data[i]);
else
list_insert_after(&zcl->zcl_callbacks, tmp_cb,
cb_data[i]);
cb_data[i]->zcd_added = B_TRUE;
VERIFY(!cb_data[i]->zcd_called);
tmp_cb = cb_data[i];
}
mutex_exit(&zcl->zcl_callbacks_lock);
dmu_tx_commit(tx);
}
2008-11-20 20:01:55 +00:00
void
ztest_dsl_prop_get_set(ztest_args_t *za)
{
objset_t *os = za->za_os;
int i, inherit;
uint64_t value;
const char *prop, *valname;
char setpoint[MAXPATHLEN];
char osname[MAXNAMELEN];
int error;
rw_enter(&ztest_shared->zs_name_lock, RW_READER);
2008-11-20 20:01:55 +00:00
dmu_objset_name(os, osname);
for (i = 0; i < 2; i++) {
if (i == 0) {
prop = "checksum";
value = ztest_random_checksum();
inherit = (value == ZIO_CHECKSUM_INHERIT);
} else {
prop = "compression";
value = ztest_random_compress();
inherit = (value == ZIO_COMPRESS_INHERIT);
}
error = dsl_prop_set(osname, prop, sizeof (value),
!inherit, &value);
if (error == ENOSPC) {
ztest_record_enospc("dsl_prop_set");
break;
}
ASSERT3U(error, ==, 0);
VERIFY3U(dsl_prop_get(osname, prop, sizeof (value),
1, &value, setpoint), ==, 0);
if (i == 0)
valname = zio_checksum_table[value].ci_name;
else
valname = zio_compress_table[value].ci_name;
if (zopt_verbose >= 6) {
(void) printf("%s %s = %s for '%s'\n",
osname, prop, valname, setpoint);
}
}
rw_exit(&ztest_shared->zs_name_lock);
2008-11-20 20:01:55 +00:00
}
/*
* Inject random faults into the on-disk data.
*/
void
ztest_fault_inject(ztest_args_t *za)
{
int fd;
uint64_t offset;
uint64_t leaves = MAX(zopt_mirrors, 1) * zopt_raidz;
2009-02-22 02:07:33 +00:00
uint64_t bad = 0x1990c0ffeedecadeull;
2008-11-20 20:01:55 +00:00
uint64_t top, leaf;
char path0[MAXPATHLEN];
char pathrand[MAXPATHLEN];
size_t fsize;
spa_t *spa = za->za_spa;
int bshift = SPA_MAXBLOCKSHIFT + 2; /* don't scrog all labels */
int iters = 1000;
int maxfaults = zopt_maxfaults;
vdev_t *vd0 = NULL;
2008-11-20 20:01:55 +00:00
uint64_t guid0 = 0;
ASSERT(leaves >= 1);
2008-11-20 20:01:55 +00:00
/*
* We need SCL_STATE here because we're going to look at vd0->vdev_tsd.
2008-11-20 20:01:55 +00:00
*/
spa_config_enter(spa, SCL_STATE, FTAG, RW_READER);
2008-11-20 20:01:55 +00:00
if (ztest_random(2) == 0) {
/*
* Inject errors on a normal data device.
*/
top = ztest_random(spa->spa_root_vdev->vdev_children);
leaf = ztest_random(leaves);
2008-11-20 20:01:55 +00:00
/*
* Generate paths to the first leaf in this top-level vdev,
* and to the random leaf we selected. We'll induce transient
* write failures and random online/offline activity on leaf 0,
* and we'll write random garbage to the randomly chosen leaf.
*/
(void) snprintf(path0, sizeof (path0), ztest_dev_template,
zopt_dir, zopt_pool, top * leaves + 0);
(void) snprintf(pathrand, sizeof (pathrand), ztest_dev_template,
zopt_dir, zopt_pool, top * leaves + leaf);
2008-11-20 20:01:55 +00:00
vd0 = vdev_lookup_by_path(spa->spa_root_vdev, path0);
if (vd0 != NULL && maxfaults != 1) {
/*
* Make vd0 explicitly claim to be unreadable,
* or unwriteable, or reach behind its back
* and close the underlying fd. We can do this if
* maxfaults == 0 because we'll fail and reexecute,
* and we can do it if maxfaults >= 2 because we'll
* have enough redundancy. If maxfaults == 1, the
* combination of this with injection of random data
* corruption below exceeds the pool's fault tolerance.
*/
vdev_file_t *vf = vd0->vdev_tsd;
if (vf != NULL && ztest_random(3) == 0) {
(void) close(vf->vf_vnode->v_fd);
vf->vf_vnode->v_fd = -1;
} else if (ztest_random(2) == 0) {
vd0->vdev_cant_read = B_TRUE;
} else {
vd0->vdev_cant_write = B_TRUE;
}
guid0 = vd0->vdev_guid;
}
} else {
/*
* Inject errors on an l2cache device.
*/
spa_aux_vdev_t *sav = &spa->spa_l2cache;
2008-11-20 20:01:55 +00:00
if (sav->sav_count == 0) {
spa_config_exit(spa, SCL_STATE, FTAG);
return;
}
vd0 = sav->sav_vdevs[ztest_random(sav->sav_count)];
2008-11-20 20:01:55 +00:00
guid0 = vd0->vdev_guid;
(void) strcpy(path0, vd0->vdev_path);
(void) strcpy(pathrand, vd0->vdev_path);
leaf = 0;
leaves = 1;
maxfaults = INT_MAX; /* no limit on cache devices */
2008-11-20 20:01:55 +00:00
}
spa_config_exit(spa, SCL_STATE, FTAG);
if (maxfaults == 0)
return;
2008-11-20 20:01:55 +00:00
/*
* If we can tolerate two or more faults, randomly online/offline vd0.
*/
if (maxfaults >= 2 && guid0 != 0) {
2009-01-15 21:59:39 +00:00
if (ztest_random(10) < 6) {
int flags = (ztest_random(2) == 0 ?
ZFS_OFFLINE_TEMPORARY : 0);
VERIFY(vdev_offline(spa, guid0, flags) != EBUSY);
} else {
(void) vdev_online(spa, guid0, 0, NULL);
}
2008-11-20 20:01:55 +00:00
}
/*
* We have at least single-fault tolerance, so inject data corruption.
*/
fd = open(pathrand, O_RDWR);
if (fd == -1) /* we hit a gap in the device namespace */
return;
fsize = lseek(fd, 0, SEEK_END);
while (--iters != 0) {
offset = ztest_random(fsize / (leaves << bshift)) *
(leaves << bshift) + (leaf << bshift) +
(ztest_random(1ULL << (bshift - 1)) & -8ULL);
if (offset >= fsize)
continue;
if (zopt_verbose >= 6)
(void) printf("injecting bad word into %s,"
" offset 0x%llx\n", pathrand, (u_longlong_t)offset);
if (pwrite(fd, &bad, sizeof (bad), offset) != sizeof (bad))
fatal(1, "can't inject bad word at 0x%llx in %s",
offset, pathrand);
}
(void) close(fd);
}
/*
* Scrub the pool.
*/
void
ztest_scrub(ztest_args_t *za)
{
spa_t *spa = za->za_spa;
(void) spa_scrub(spa, POOL_SCRUB_EVERYTHING);
2008-11-20 20:01:55 +00:00
(void) poll(NULL, 0, 1000); /* wait a second, then force a restart */
(void) spa_scrub(spa, POOL_SCRUB_EVERYTHING);
2008-11-20 20:01:55 +00:00
}
/*
* Rename the pool to a different name and then rename it back.
*/
void
ztest_spa_rename(ztest_args_t *za)
{
char *oldname, *newname;
int error;
spa_t *spa;
rw_enter(&ztest_shared->zs_name_lock, RW_WRITER);
2008-11-20 20:01:55 +00:00
oldname = za->za_pool;
newname = umem_alloc(strlen(oldname) + 5, UMEM_NOFAIL);
(void) strcpy(newname, oldname);
(void) strcat(newname, "_tmp");
/*
* Do the rename
*/
error = spa_rename(oldname, newname);
if (error)
fatal(0, "spa_rename('%s', '%s') = %d", oldname,
newname, error);
/*
* Try to open it under the old name, which shouldn't exist
*/
error = spa_open(oldname, &spa, FTAG);
if (error != ENOENT)
fatal(0, "spa_open('%s') = %d", oldname, error);
/*
* Open it under the new name and make sure it's still the same spa_t.
*/
error = spa_open(newname, &spa, FTAG);
if (error != 0)
fatal(0, "spa_open('%s') = %d", newname, error);
ASSERT(spa == za->za_spa);
spa_close(spa, FTAG);
/*
* Rename it back to the original
*/
error = spa_rename(newname, oldname);
if (error)
fatal(0, "spa_rename('%s', '%s') = %d", newname,
oldname, error);
/*
* Make sure it can still be opened
*/
error = spa_open(oldname, &spa, FTAG);
if (error != 0)
fatal(0, "spa_open('%s') = %d", oldname, error);
ASSERT(spa == za->za_spa);
spa_close(spa, FTAG);
umem_free(newname, strlen(newname) + 1);
rw_exit(&ztest_shared->zs_name_lock);
2008-11-20 20:01:55 +00:00
}
/*
* Completely obliterate one disk.
*/
static void
ztest_obliterate_one_disk(uint64_t vdev)
{
int fd;
char dev_name[MAXPATHLEN], copy_name[MAXPATHLEN];
size_t fsize;
if (zopt_maxfaults < 2)
return;
(void) sprintf(dev_name, ztest_dev_template, zopt_dir, zopt_pool, vdev);
(void) snprintf(copy_name, MAXPATHLEN, "%s.old", dev_name);
fd = open(dev_name, O_RDWR);
if (fd == -1)
fatal(1, "can't open %s", dev_name);
/*
* Determine the size.
*/
fsize = lseek(fd, 0, SEEK_END);
(void) close(fd);
/*
* Rename the old device to dev_name.old (useful for debugging).
*/
VERIFY(rename(dev_name, copy_name) == 0);
/*
* Create a new one.
*/
VERIFY((fd = open(dev_name, O_RDWR | O_CREAT | O_TRUNC, 0666)) >= 0);
VERIFY(ftruncate(fd, fsize) == 0);
(void) close(fd);
}
static void
ztest_replace_one_disk(spa_t *spa, uint64_t vdev)
{
char dev_name[MAXPATHLEN];
nvlist_t *root;
2008-11-20 20:01:55 +00:00
int error;
uint64_t guid;
vdev_t *vd;
(void) sprintf(dev_name, ztest_dev_template, zopt_dir, zopt_pool, vdev);
/*
* Build the nvlist describing dev_name.
*/
root = make_vdev_root(dev_name, NULL, 0, 0, 0, 0, 0, 1);
2008-11-20 20:01:55 +00:00
spa_config_enter(spa, SCL_VDEV, FTAG, RW_READER);
2008-11-20 20:01:55 +00:00
if ((vd = vdev_lookup_by_path(spa->spa_root_vdev, dev_name)) == NULL)
guid = 0;
else
guid = vd->vdev_guid;
spa_config_exit(spa, SCL_VDEV, FTAG);
2008-11-20 20:01:55 +00:00
error = spa_vdev_attach(spa, guid, root, B_TRUE);
if (error != 0 &&
error != EBUSY &&
error != ENOTSUP &&
error != ENODEV &&
error != EDOM)
fatal(0, "spa_vdev_attach(in-place) = %d", error);
nvlist_free(root);
}
static void
ztest_verify_blocks(char *pool)
{
int status;
2009-01-14 21:38:07 +00:00
char bin[MAXPATHLEN + MAXNAMELEN + 20];
2008-11-20 20:01:55 +00:00
char zdb[MAXPATHLEN + MAXNAMELEN + 20];
char zbuf[1024];
FILE *fp;
2009-01-14 21:38:07 +00:00
/* Designed to be run exclusively in the development tree */
2009-03-12 22:49:23 +00:00
VERIFY(realpath(getexecname(), bin) != NULL);
2009-01-14 21:38:07 +00:00
strstr(bin, "/ztest/")[0] = '\0';
2008-11-20 20:01:55 +00:00
2009-01-14 21:38:07 +00:00
(void) sprintf(zdb,
"%s/zdb/zdb -bcc%s%s -U /tmp/zpool.cache %s",
2009-01-14 21:38:07 +00:00
bin,
2008-11-20 20:01:55 +00:00
zopt_verbose >= 3 ? "s" : "",
zopt_verbose >= 4 ? "v" : "",
pool);
2008-11-20 20:01:55 +00:00
if (zopt_verbose >= 5)
(void) printf("Executing %s\n", strstr(zdb, "zdb "));
fp = popen(zdb, "r");
while (fgets(zbuf, sizeof (zbuf), fp) != NULL)
if (zopt_verbose >= 3)
(void) printf("%s", zbuf);
status = pclose(fp);
if (status == 0)
return;
ztest_dump_core = 0;
if (WIFEXITED(status))
fatal(0, "'%s' exit code %d", zdb, WEXITSTATUS(status));
else
fatal(0, "'%s' died with signal %d", zdb, WTERMSIG(status));
}
static void
ztest_walk_pool_directory(char *header)
{
spa_t *spa = NULL;
if (zopt_verbose >= 6)
(void) printf("%s\n", header);
mutex_enter(&spa_namespace_lock);
while ((spa = spa_next(spa)) != NULL)
if (zopt_verbose >= 6)
(void) printf("\t%s\n", spa_name(spa));
mutex_exit(&spa_namespace_lock);
}
static void
ztest_spa_import_export(char *oldname, char *newname)
{
2009-01-15 21:59:39 +00:00
nvlist_t *config, *newconfig;
2008-11-20 20:01:55 +00:00
uint64_t pool_guid;
spa_t *spa;
int error;
if (zopt_verbose >= 4) {
(void) printf("import/export: old = %s, new = %s\n",
oldname, newname);
}
/*
* Clean up from previous runs.
*/
(void) spa_destroy(newname);
/*
* Get the pool's configuration and guid.
*/
error = spa_open(oldname, &spa, FTAG);
if (error)
fatal(0, "spa_open('%s') = %d", oldname, error);
2009-01-15 21:59:39 +00:00
/*
* Kick off a scrub to tickle scrub/export races.
*/
if (ztest_random(2) == 0)
(void) spa_scrub(spa, POOL_SCRUB_EVERYTHING);
2008-11-20 20:01:55 +00:00
pool_guid = spa_guid(spa);
spa_close(spa, FTAG);
ztest_walk_pool_directory("pools before export");
/*
* Export it.
*/
2009-01-15 21:59:39 +00:00
error = spa_export(oldname, &config, B_FALSE, B_FALSE);
2008-11-20 20:01:55 +00:00
if (error)
fatal(0, "spa_export('%s') = %d", oldname, error);
ztest_walk_pool_directory("pools after export");
2009-01-15 21:59:39 +00:00
/*
* Try to import it.
*/
newconfig = spa_tryimport(config);
ASSERT(newconfig != NULL);
nvlist_free(newconfig);
2008-11-20 20:01:55 +00:00
/*
* Import it under the new name.
*/
error = spa_import(newname, config, NULL);
if (error)
fatal(0, "spa_import('%s') = %d", newname, error);
ztest_walk_pool_directory("pools after import");
/*
* Try to import it again -- should fail with EEXIST.
*/
error = spa_import(newname, config, NULL);
if (error != EEXIST)
fatal(0, "spa_import('%s') twice", newname);
/*
* Try to import it under a different name -- should fail with EEXIST.
*/
error = spa_import(oldname, config, NULL);
if (error != EEXIST)
fatal(0, "spa_import('%s') under multiple names", newname);
/*
* Verify that the pool is no longer visible under the old name.
*/
error = spa_open(oldname, &spa, FTAG);
if (error != ENOENT)
fatal(0, "spa_open('%s') = %d", newname, error);
/*
* Verify that we can open and close the pool using the new name.
*/
error = spa_open(newname, &spa, FTAG);
if (error)
fatal(0, "spa_open('%s') = %d", newname, error);
ASSERT(pool_guid == spa_guid(spa));
spa_close(spa, FTAG);
nvlist_free(config);
}
static void
ztest_resume(spa_t *spa)
2009-01-15 21:59:39 +00:00
{
if (spa_suspended(spa)) {
spa_vdev_state_enter(spa);
vdev_clear(spa, NULL);
(void) spa_vdev_state_exit(spa, NULL, 0);
2009-07-02 22:44:48 +00:00
(void) zio_resume(spa);
2009-01-15 21:59:39 +00:00
}
}
2008-11-20 20:01:55 +00:00
static void *
2009-01-15 21:59:39 +00:00
ztest_resume_thread(void *arg)
2008-11-20 20:01:55 +00:00
{
spa_t *spa = arg;
2008-11-20 20:01:55 +00:00
while (!ztest_exiting) {
(void) poll(NULL, 0, 1000);
2009-01-15 21:59:39 +00:00
ztest_resume(spa);
2008-11-20 20:01:55 +00:00
}
thread_exit();
2008-11-20 20:01:55 +00:00
return (NULL);
}
static void *
ztest_thread(void *arg)
{
ztest_args_t *za = arg;
ztest_shared_t *zs = ztest_shared;
hrtime_t now, functime;
ztest_info_t *zi;
int f, i;
while ((now = gethrtime()) < za->za_stop) {
/*
* See if it's time to force a crash.
*/
if (now > za->za_kill) {
zs->zs_alloc = spa_get_alloc(za->za_spa);
zs->zs_space = spa_get_space(za->za_spa);
(void) kill(getpid(), SIGKILL);
}
/*
* Pick a random function.
*/
f = ztest_random(ZTEST_FUNCS);
zi = &zs->zs_info[f];
/*
* Decide whether to call it, based on the requested frequency.
*/
if (zi->zi_call_target == 0 ||
(double)zi->zi_call_total / zi->zi_call_target >
(double)(now - zs->zs_start_time) / (zopt_time * NANOSEC))
continue;
atomic_add_64(&zi->zi_calls, 1);
atomic_add_64(&zi->zi_call_total, 1);
za->za_diroff = (za->za_instance * ZTEST_FUNCS + f) *
ZTEST_DIRSIZE;
za->za_diroff_shared = (1ULL << 63);
for (i = 0; i < zi->zi_iters; i++)
zi->zi_func(za);
functime = gethrtime() - now;
atomic_add_64(&zi->zi_call_time, functime);
if (zopt_verbose >= 4) {
Dl_info dli;
(void) dladdr((void *)zi->zi_func, &dli);
(void) printf("%6.2f sec in %s\n",
(double)functime / NANOSEC, dli.dli_sname);
}
/*
* If we're getting ENOSPC with some regularity, stop.
*/
if (zs->zs_enospc_count > 10)
break;
}
thread_exit();
2008-11-20 20:01:55 +00:00
return (NULL);
}
/*
* Kick off threads to run tests on all datasets in parallel.
*/
static void
ztest_run(char *pool)
{
int t, d, error;
ztest_shared_t *zs = ztest_shared;
ztest_args_t *za;
spa_t *spa;
char name[100];
kthread_t *resume_thread;
kt_did_t resume_id;
ztest_exiting = B_FALSE;
2008-11-20 20:01:55 +00:00
mutex_init(&zs->zs_vdev_lock, NULL, MUTEX_DEFAULT, NULL);
rw_init(&zs->zs_name_lock, NULL, RW_DEFAULT, NULL);
mutex_init(&zs->zs_cb_list.zcl_callbacks_lock,NULL,MUTEX_DEFAULT,NULL);
list_create(&zs->zs_cb_list.zcl_callbacks, sizeof (ztest_cb_data_t),
offsetof(ztest_cb_data_t, zcd_node));
2008-11-20 20:01:55 +00:00
for (t = 0; t < ZTEST_SYNC_LOCKS; t++)
mutex_init(&zs->zs_sync_lock[t], NULL, MUTEX_DEFAULT, NULL);
2008-11-20 20:01:55 +00:00
/*
* Destroy one disk before we even start.
* It's mirrored, so everything should work just fine.
* This makes us exercise fault handling very early in spa_load().
*/
ztest_obliterate_one_disk(0);
/*
* Verify that the sum of the sizes of all blocks in the pool
* equals the SPA's allocated space total.
*/
ztest_verify_blocks(pool);
/*
* Kick off a replacement of the disk we just obliterated.
*/
kernel_init(FREAD | FWRITE);
VERIFY(spa_open(pool, &spa, FTAG) == 0);
2008-11-20 20:01:55 +00:00
ztest_replace_one_disk(spa, 0);
if (zopt_verbose >= 5)
show_pool_stats(spa);
spa_close(spa, FTAG);
kernel_fini();
kernel_init(FREAD | FWRITE);
/*
* Verify that we can export the pool and reimport it under a
* different name.
*/
if (ztest_random(2) == 0) {
(void) snprintf(name, 100, "%s_import", pool);
ztest_spa_import_export(pool, name);
ztest_spa_import_export(name, pool);
}
/*
* Verify that we can loop over all pools.
*/
mutex_enter(&spa_namespace_lock);
for (spa = spa_next(NULL); spa != NULL; spa = spa_next(spa)) {
if (zopt_verbose > 3) {
(void) printf("spa_next: found %s\n", spa_name(spa));
}
}
mutex_exit(&spa_namespace_lock);
/*
* Open our pool.
2008-11-20 20:01:55 +00:00
*/
VERIFY(spa_open(pool, &spa, FTAG) == 0);
2008-11-20 20:01:55 +00:00
2009-01-15 21:59:39 +00:00
/*
* We don't expect the pool to suspend unless maxfaults == 0,
* in which case ztest_fault_inject() temporarily takes away
* the only valid replica.
*/
if (zopt_maxfaults == 0)
spa->spa_failmode = ZIO_FAILURE_MODE_WAIT;
else
spa->spa_failmode = ZIO_FAILURE_MODE_PANIC;
2008-11-20 20:01:55 +00:00
/*
* Create a thread to periodically resume suspended I/O.
2008-11-20 20:01:55 +00:00
*/
VERIFY3P((resume_thread = thread_create(NULL, 0, ztest_resume_thread,
spa, THR_BOUND, NULL, 0, 0)), !=, NULL);
resume_id = resume_thread->t_tid;
2008-11-20 20:01:55 +00:00
/*
* Verify that we can safely inquire about about any object,
* whether it's allocated or not. To make it interesting,
* we probe a 5-wide window around each power of two.
* This hits all edge cases, including zero and the max.
*/
for (t = 0; t < 64; t++) {
for (d = -5; d <= 5; d++) {
error = dmu_object_info(spa->spa_meta_objset,
(1ULL << t) + d, NULL);
ASSERT(error == 0 || error == ENOENT ||
error == EINVAL);
}
}
/*
* Now kick off all the tests that run in parallel.
*/
zs->zs_enospc_count = 0;
za = umem_zalloc(zopt_threads * sizeof (ztest_args_t), UMEM_NOFAIL);
if (zopt_verbose >= 4)
(void) printf("starting main threads...\n");
za[0].za_start = gethrtime();
za[0].za_stop = za[0].za_start + zopt_passtime * NANOSEC;
za[0].za_stop = MIN(za[0].za_stop, zs->zs_stop_time);
za[0].za_kill = za[0].za_stop;
if (ztest_random(100) < zopt_killrate)
za[0].za_kill -= ztest_random(zopt_passtime * NANOSEC);
for (t = 0; t < zopt_threads; t++) {
d = t % zopt_datasets;
(void) strcpy(za[t].za_pool, pool);
za[t].za_os = za[d].za_os;
za[t].za_spa = spa;
za[t].za_zilog = za[d].za_zilog;
za[t].za_instance = t;
za[t].za_random = ztest_random(-1ULL);
za[t].za_start = za[0].za_start;
za[t].za_stop = za[0].za_stop;
za[t].za_kill = za[0].za_kill;
if (t < zopt_datasets) {
int test_future = FALSE;
rw_enter(&ztest_shared->zs_name_lock, RW_READER);
2008-11-20 20:01:55 +00:00
(void) snprintf(name, 100, "%s/%s_%d", pool, pool, d);
error = dmu_objset_create(name, DMU_OST_OTHER, NULL, 0,
ztest_create_cb, NULL);
if (error == EEXIST) {
test_future = TRUE;
} else if (error == ENOSPC) {
zs->zs_enospc_count++;
rw_exit(&ztest_shared->zs_name_lock);
2008-11-20 20:01:55 +00:00
break;
} else if (error != 0) {
fatal(0, "dmu_objset_create(%s) = %d",
name, error);
}
error = dmu_objset_open(name, DMU_OST_OTHER,
DS_MODE_USER, &za[d].za_os);
2008-11-20 20:01:55 +00:00
if (error)
fatal(0, "dmu_objset_open('%s') = %d",
name, error);
rw_exit(&ztest_shared->zs_name_lock);
2008-11-20 20:01:55 +00:00
if (test_future)
ztest_dmu_check_future_leak(&za[t]);
2009-01-15 21:59:39 +00:00
zil_replay(za[d].za_os, za[d].za_os,
ztest_replay_vector);
2008-11-20 20:01:55 +00:00
za[d].za_zilog = zil_open(za[d].za_os, NULL);
}
VERIFY3P((za[t].za_thread = thread_create(NULL, 0, ztest_thread,
&za[t], THR_BOUND, NULL, 0, 0)), !=, NULL);
za[t].za_threadid = za[t].za_thread->t_tid;
2008-11-20 20:01:55 +00:00
}
while (--t >= 0) {
VERIFY(thread_join(za[t].za_threadid, NULL, NULL) == 0);
2008-11-20 20:01:55 +00:00
if (t < zopt_datasets) {
zil_close(za[t].za_zilog);
dmu_objset_close(za[t].za_os);
}
}
if (zopt_verbose >= 3)
show_pool_stats(spa);
txg_wait_synced(spa_get_dsl(spa), 0);
zs->zs_alloc = spa_get_alloc(spa);
zs->zs_space = spa_get_space(spa);
/*
* If we had out-of-space errors, destroy a random objset.
*/
if (zs->zs_enospc_count != 0) {
rw_enter(&ztest_shared->zs_name_lock, RW_READER);
2008-11-20 20:01:55 +00:00
d = (int)ztest_random(zopt_datasets);
(void) snprintf(name, 100, "%s/%s_%d", pool, pool, d);
if (zopt_verbose >= 3)
(void) printf("Destroying %s to free up space\n", name);
2009-07-02 22:44:48 +00:00
/* Cleanup any non-standard clones and snapshots */
ztest_dsl_dataset_cleanup(name, za[d].za_instance);
2008-11-20 20:01:55 +00:00
(void) dmu_objset_find(name, ztest_destroy_cb, &za[d],
DS_FIND_SNAPSHOTS | DS_FIND_CHILDREN);
rw_exit(&ztest_shared->zs_name_lock);
2008-11-20 20:01:55 +00:00
}
txg_wait_synced(spa_get_dsl(spa), 0);
umem_free(za, zopt_threads * sizeof (ztest_args_t));
/* Kill the resume thread */
ztest_exiting = B_TRUE;
VERIFY(thread_join(resume_id, NULL, NULL) == 0);
2009-01-15 21:59:39 +00:00
ztest_resume(spa);
2008-11-20 20:01:55 +00:00
/*
* Right before closing the pool, kick off a bunch of async I/O;
* spa_close() should wait for it to complete.
*/
for (t = 1; t < 50; t++)
dmu_prefetch(spa->spa_meta_objset, t, 0, 1 << 15);
spa_close(spa, FTAG);
kernel_fini();
list_destroy(&zs->zs_cb_list.zcl_callbacks);
mutex_destroy(&zs->zs_cb_list.zcl_callbacks_lock);
rw_destroy(&zs->zs_name_lock);
mutex_destroy(&zs->zs_vdev_lock);
2008-11-20 20:01:55 +00:00
}
void
print_time(hrtime_t t, char *timebuf)
{
hrtime_t s = t / NANOSEC;
hrtime_t m = s / 60;
hrtime_t h = m / 60;
hrtime_t d = h / 24;
s -= m * 60;
m -= h * 60;
h -= d * 24;
timebuf[0] = '\0';
if (d)
(void) sprintf(timebuf,
"%llud%02lluh%02llum%02llus", d, h, m, s);
else if (h)
(void) sprintf(timebuf, "%lluh%02llum%02llus", h, m, s);
else if (m)
(void) sprintf(timebuf, "%llum%02llus", m, s);
else
(void) sprintf(timebuf, "%llus", s);
}
/*
* Create a storage pool with the given name and initial vdev size.
* Then create the specified number of datasets in the pool.
*/
static void
ztest_init(char *pool)
{
spa_t *spa;
int error;
nvlist_t *nvroot;
kernel_init(FREAD | FWRITE);
/*
* Create the storage pool.
*/
(void) spa_destroy(pool);
ztest_shared->zs_vdev_primaries = 0;
nvroot = make_vdev_root(NULL, NULL, zopt_vdev_size, 0,
0, zopt_raidz, zopt_mirrors, 1);
error = spa_create(pool, nvroot, NULL, NULL, NULL);
2008-11-20 20:01:55 +00:00
nvlist_free(nvroot);
if (error)
fatal(0, "spa_create() = %d", error);
error = spa_open(pool, &spa, FTAG);
if (error)
fatal(0, "spa_open() = %d", error);
2009-07-02 22:44:48 +00:00
metaslab_sz = 1ULL << spa->spa_root_vdev->vdev_child[0]->vdev_ms_shift;
2008-11-20 20:01:55 +00:00
if (zopt_verbose >= 3)
show_pool_stats(spa);
spa_close(spa, FTAG);
kernel_fini();
}
int
main(int argc, char **argv)
{
int kills = 0;
int iters = 0;
int i, f;
ztest_shared_t *zs;
ztest_info_t *zi;
char timebuf[100];
char numbuf[6];
(void) setvbuf(stdout, NULL, _IOLBF, 0);
/* Override location of zpool.cache */
spa_config_path = "/tmp/zpool.cache";
2008-11-20 20:01:55 +00:00
ztest_random_fd = open("/dev/urandom", O_RDONLY);
process_options(argc, argv);
/*
* Blow away any existing copy of zpool.cache
*/
if (zopt_init != 0)
(void) remove("/tmp/zpool.cache");
zs = ztest_shared = (void *)mmap(0,
P2ROUNDUP(sizeof (ztest_shared_t), getpagesize()),
PROT_READ | PROT_WRITE, MAP_SHARED | MAP_ANON, -1, 0);
if (zopt_verbose >= 1) {
(void) printf("%llu vdevs, %d datasets, %d threads,"
" %llu seconds...\n",
(u_longlong_t)zopt_vdevs, zopt_datasets, zopt_threads,
(u_longlong_t)zopt_time);
}
/*
* Create and initialize our storage pool.
*/
for (i = 1; i <= zopt_init; i++) {
bzero(zs, sizeof (ztest_shared_t));
if (zopt_verbose >= 3 && zopt_init != 1)
(void) printf("ztest_init(), pass %d\n", i);
ztest_init(zopt_pool);
}
/*
* Initialize the call targets for each function.
*/
for (f = 0; f < ZTEST_FUNCS; f++) {
zi = &zs->zs_info[f];
*zi = ztest_info[f];
if (*zi->zi_interval == 0)
zi->zi_call_target = UINT64_MAX;
else
zi->zi_call_target = zopt_time / *zi->zi_interval;
}
zs->zs_start_time = gethrtime();
zs->zs_stop_time = zs->zs_start_time + zopt_time * NANOSEC;
/*
* Run the tests in a loop. These tests include fault injection
* to verify that self-healing data works, and forced crashes
* to verify that we never lose on-disk consistency.
*/
while (gethrtime() < zs->zs_stop_time) {
int status;
pid_t pid;
char *tmp;
/*
* Initialize the workload counters for each function.
*/
for (f = 0; f < ZTEST_FUNCS; f++) {
zi = &zs->zs_info[f];
zi->zi_calls = 0;
zi->zi_call_time = 0;
}
2009-07-02 22:44:48 +00:00
/* Set the allocation switch size */
metaslab_df_alloc_threshold = ztest_random(metaslab_sz / 4) + 1;
2008-11-20 20:01:55 +00:00
pid = fork();
if (pid == -1)
fatal(1, "fork failed");
if (pid == 0) { /* child */
struct rlimit rl = { 1024, 1024 };
(void) setrlimit(RLIMIT_NOFILE, &rl);
(void) enable_extended_FILE_stdio(-1, -1);
ztest_run(zopt_pool);
exit(0);
}
while (waitpid(pid, &status, 0) != pid)
continue;
if (WIFEXITED(status)) {
if (WEXITSTATUS(status) != 0) {
(void) fprintf(stderr,
"child exited with code %d\n",
WEXITSTATUS(status));
exit(2);
}
} else if (WIFSIGNALED(status)) {
if (WTERMSIG(status) != SIGKILL) {
(void) fprintf(stderr,
"child died with signal %d\n",
WTERMSIG(status));
exit(3);
}
kills++;
} else {
(void) fprintf(stderr, "something strange happened "
"to child\n");
exit(4);
}
iters++;
if (zopt_verbose >= 1) {
hrtime_t now = gethrtime();
now = MIN(now, zs->zs_stop_time);
print_time(zs->zs_stop_time - now, timebuf);
nicenum(zs->zs_space, numbuf);
(void) printf("Pass %3d, %8s, %3llu ENOSPC, "
"%4.1f%% of %5s used, %3.0f%% done, %8s to go\n",
iters,
WIFEXITED(status) ? "Complete" : "SIGKILL",
(u_longlong_t)zs->zs_enospc_count,
100.0 * zs->zs_alloc / zs->zs_space,
numbuf,
100.0 * (now - zs->zs_start_time) /
(zopt_time * NANOSEC), timebuf);
}
if (zopt_verbose >= 2) {
(void) printf("\nWorkload summary:\n\n");
(void) printf("%7s %9s %s\n",
"Calls", "Time", "Function");
(void) printf("%7s %9s %s\n",
"-----", "----", "--------");
for (f = 0; f < ZTEST_FUNCS; f++) {
Dl_info dli;
zi = &zs->zs_info[f];
print_time(zi->zi_call_time, timebuf);
(void) dladdr((void *)zi->zi_func, &dli);
(void) printf("%7llu %9s %s\n",
(u_longlong_t)zi->zi_calls, timebuf,
dli.dli_sname);
}
(void) printf("\n");
}
/*
* It's possible that we killed a child during a rename test, in
* which case we'll have a 'ztest_tmp' pool lying around instead
* of 'ztest'. Do a blind rename in case this happened.
*/
tmp = umem_alloc(strlen(zopt_pool) + 5, UMEM_NOFAIL);
(void) strcpy(tmp, zopt_pool);
(void) strcat(tmp, "_tmp");
kernel_init(FREAD | FWRITE);
(void) spa_rename(tmp, zopt_pool);
kernel_fini();
umem_free(tmp, strlen(tmp) + 1);
}
ztest_verify_blocks(zopt_pool);
if (zopt_verbose >= 1) {
(void) printf("%d killed, %d completed, %.0f%% kill rate\n",
kills, iters - kills, (100.0 * kills) / MAX(1, iters));
}
return (0);
}