Migration pull 2018-02-06

This is based off Juan's last pull with a few extras, but
 also removing:
    Add migration xbzrle test
    Add migration precopy test
 
 As well as my normal test boxes, I also gave it a test
 on a 32 bit ARM box and it seems happy (a Calxeda highbank)
 and a big-endian power box.
 
 Dave
 -----BEGIN PGP SIGNATURE-----
 
 iQIcBAABAgAGBQJaecrLAAoJEAUWMx68W/3nXMcQAKc/XyllcmwVGQ5NiEKQRcar
 7bJLgu7t4EaJkOhMN2/jeyEjX9p1GjZw6x2PCp7ipZyhLmu5mUWxKC/l+dD7XFLW
 aTRZmP7gnIUFnTc1sWYdGy59HRjQ8KeVuZILPbgWaJIkC5Pc5I0Wxvhqm0GBCKpI
 T2tCEV/PHJWyHovs1ZITKgD8NWPZpgc9ZRefomvyb4eJeplf7Eq/hZzgzIP7aoTU
 fsF/wCTg2lhILl8BvWIxp+Tlhz/hOBay5+5FEEy6x7/tfgJk76Dh/Ri2uPcGPcgG
 ReUaM9JCn+Toe75z96V43WHuPj0Ea4+7al85H6gXsQeeDBtiewBjUUwQ1mv/zZCn
 wQyWdX4OoU7gvQEF/3m/8Pb3QuXLxzs6febqcWGj8mFg+IVOEhxHYJ/UdMeq2ASI
 KG6iHGzUw33R7AE8HoQBV9C/uJ7BzzZEjuJbtzFWXK5QWC2zWOpaFu9R4VGEsAzL
 ktS96pGtUxHJXZJq8I+rmHr/4KHO6UK4B+/VGKEKzooedkHgYjdTeWyvMDzrJTaq
 pLpXJxaljuDCNZClX2F5A5GjcrFmDXyz1GGoTAqacqD0OENbqS7CcZVHaEf58/lR
 fWld/Ya1KjyEjGEsdTD2XAzEO4wMj6GYrk9lcmzIFKwtyIgDJDAWDPXzR/bx1MY8
 h0YzqwP6L8HI9nGzzEyz
 =ntXb
 -----END PGP SIGNATURE-----

Merge remote-tracking branch 'remotes/dgilbert/tags/pull-migration-20180206a' into staging

Migration pull 2018-02-06

This is based off Juan's last pull with a few extras, but
also removing:
   Add migration xbzrle test
   Add migration precopy test

As well as my normal test boxes, I also gave it a test
on a 32 bit ARM box and it seems happy (a Calxeda highbank)
and a big-endian power box.

Dave

# gpg: Signature made Tue 06 Feb 2018 15:33:31 GMT
# gpg:                using RSA key 0516331EBC5BFDE7
# gpg: Good signature from "Dr. David Alan Gilbert (RH2) <dgilbert@redhat.com>"
# Primary key fingerprint: 45F5 C71B 4A0C B7FB 977A  9FA9 0516 331E BC5B FDE7

* remotes/dgilbert/tags/pull-migration-20180206a:
  migration: incoming postcopy advise sanity checks
  migration: Don't leak IO channels
  migration: Recover block devices if failure in device state
  tests: Adjust sleeps for migration test
  tests: Create migrate-start-postcopy command
  tests: Add deprecated commands migration test
  tests: Use consistent names for migration
  tests: Consolidate accelerators declaration
  tests: Remove deprecated migration tests commands
  migration: Drop current address parameter from save_zero_page()
  migration: use s->threshold_size inside migration_update_counters
  migration/savevm.c: set MAX_VM_CMD_PACKAGED_SIZE to 1ul << 32
  migration: Route errors down through migration_channel_connect
  migration: Allow migrate_fd_connect to take an Error *

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
This commit is contained in:
Peter Maydell 2018-02-07 12:07:23 +00:00
commit 0833df03f4
13 changed files with 152 additions and 97 deletions

View file

@ -55,29 +55,29 @@ void migration_channel_process_incoming(QIOChannel *ioc)
* @s: Current migration state
* @ioc: Channel to which we are connecting
* @hostname: Where we want to connect
* @error: Error indicating failure to connect, free'd here
*/
void migration_channel_connect(MigrationState *s,
QIOChannel *ioc,
const char *hostname)
const char *hostname,
Error *error)
{
trace_migration_set_outgoing_channel(
ioc, object_get_typename(OBJECT(ioc)), hostname);
ioc, object_get_typename(OBJECT(ioc)), hostname, error);
if (!error) {
if (s->parameters.tls_creds &&
*s->parameters.tls_creds &&
!object_dynamic_cast(OBJECT(ioc),
TYPE_QIO_CHANNEL_TLS)) {
migration_tls_channel_connect(s, ioc, hostname, &error);
} else {
QEMUFile *f = qemu_fopen_channel_output(ioc);
s->to_dst_file = f;
if (s->parameters.tls_creds &&
*s->parameters.tls_creds &&
!object_dynamic_cast(OBJECT(ioc),
TYPE_QIO_CHANNEL_TLS)) {
Error *local_err = NULL;
migration_tls_channel_connect(s, ioc, hostname, &local_err);
if (local_err) {
migrate_fd_error(s, local_err);
error_free(local_err);
}
} else {
QEMUFile *f = qemu_fopen_channel_output(ioc);
s->to_dst_file = f;
migrate_fd_connect(s);
}
migrate_fd_connect(s, error);
error_free(error);
}

View file

@ -22,5 +22,6 @@ void migration_channel_process_incoming(QIOChannel *ioc);
void migration_channel_connect(MigrationState *s,
QIOChannel *ioc,
const char *hostname);
const char *hostname,
Error *error_in);
#endif

View file

@ -39,7 +39,7 @@ void exec_start_outgoing_migration(MigrationState *s, const char *command, Error
}
qio_channel_set_name(ioc, "migration-exec-outgoing");
migration_channel_connect(s, ioc, NULL);
migration_channel_connect(s, ioc, NULL, NULL);
object_unref(OBJECT(ioc));
}

View file

@ -39,7 +39,7 @@ void fd_start_outgoing_migration(MigrationState *s, const char *fdname, Error **
}
qio_channel_set_name(QIO_CHANNEL(ioc), "migration-fd-outgoing");
migration_channel_connect(s, ioc, NULL);
migration_channel_connect(s, ioc, NULL, NULL);
object_unref(OBJECT(ioc));
}

View file

@ -2122,7 +2122,8 @@ fail_invalidate:
/* If not doing postcopy, vm_start() will be called: let's regain
* control on images.
*/
if (s->state == MIGRATION_STATUS_ACTIVE) {
if (s->state == MIGRATION_STATUS_ACTIVE ||
s->state == MIGRATION_STATUS_DEVICE) {
Error *local_err = NULL;
qemu_mutex_lock_iothread();
@ -2169,7 +2170,6 @@ static void migration_update_counters(MigrationState *s,
int64_t current_time)
{
uint64_t transferred, time_spent;
int64_t threshold_size;
double bandwidth;
if (current_time < s->iteration_start_time + BUFFER_DELAY) {
@ -2179,7 +2179,7 @@ static void migration_update_counters(MigrationState *s,
transferred = qemu_ftell(s->to_dst_file) - s->iteration_initial_bytes;
time_spent = current_time - s->iteration_start_time;
bandwidth = (double)transferred / time_spent;
threshold_size = bandwidth * s->parameters.downtime_limit;
s->threshold_size = bandwidth * s->parameters.downtime_limit;
s->mbps = (((double) transferred * 8.0) /
((double) time_spent / 1000.0)) / 1000.0 / 1000.0;
@ -2199,7 +2199,7 @@ static void migration_update_counters(MigrationState *s,
s->iteration_initial_bytes = qemu_ftell(s->to_dst_file);
trace_migrate_transferred(transferred, time_spent,
bandwidth, threshold_size);
bandwidth, s->threshold_size);
}
/* Migration thread iteration status */
@ -2378,10 +2378,15 @@ static void *migration_thread(void *opaque)
return NULL;
}
void migrate_fd_connect(MigrationState *s)
void migrate_fd_connect(MigrationState *s, Error *error_in)
{
s->expected_downtime = s->parameters.downtime_limit;
s->cleanup_bh = qemu_bh_new(migrate_fd_cleanup, s);
if (error_in) {
migrate_fd_error(s, error_in);
migrate_fd_cleanup(s);
return;
}
qemu_file_set_blocking(s->to_dst_file, true);
qemu_file_set_rate_limit(s->to_dst_file,

View file

@ -190,7 +190,7 @@ uint64_t migrate_max_downtime(void);
void migrate_set_error(MigrationState *s, const Error *error);
void migrate_fd_error(MigrationState *s, const Error *error);
void migrate_fd_connect(MigrationState *s);
void migrate_fd_connect(MigrationState *s, Error *error_in);
MigrationState *migrate_init(void);
bool migration_is_blocked(Error **errp);

View file

@ -907,11 +907,10 @@ static void migration_bitmap_sync(RAMState *rs)
* @rs: current RAM state
* @block: block that contains the page we want to send
* @offset: offset inside the block for the page
* @p: pointer to the page
*/
static int save_zero_page(RAMState *rs, RAMBlock *block, ram_addr_t offset,
uint8_t *p)
static int save_zero_page(RAMState *rs, RAMBlock *block, ram_addr_t offset)
{
uint8_t *p = block->host + offset;
int pages = -1;
if (is_zero_range(p, TARGET_PAGE_SIZE)) {
@ -984,7 +983,7 @@ static int ram_save_page(RAMState *rs, PageSearchStatus *pss, bool last_stage)
}
}
} else {
pages = save_zero_page(rs, block, offset, p);
pages = save_zero_page(rs, block, offset);
if (pages > 0) {
/* Must let xbzrle know, otherwise a previous (now 0'd) cached
* page would be stale
@ -1160,7 +1159,7 @@ static int ram_save_compressed_page(RAMState *rs, PageSearchStatus *pss,
*/
if (block != rs->last_sent_block) {
flush_compressed_data(rs);
pages = save_zero_page(rs, block, offset, p);
pages = save_zero_page(rs, block, offset);
if (pages == -1) {
/* Make sure the first page is sent out before other pages */
bytes_xmit = save_page_header(rs, rs->f, block, offset |
@ -1180,7 +1179,7 @@ static int ram_save_compressed_page(RAMState *rs, PageSearchStatus *pss,
ram_release_pages(block->idstr, offset, pages);
}
} else {
pages = save_zero_page(rs, block, offset, p);
pages = save_zero_page(rs, block, offset);
if (pages == -1) {
pages = compress_page_with_multi_thread(rs, block, offset);
} else {

View file

@ -3758,7 +3758,7 @@ void rdma_start_outgoing_migration(void *opaque,
trace_rdma_start_outgoing_migration_after_rdma_connect();
s->to_dst_file = qemu_fopen_rdma(rdma, "wb");
migrate_fd_connect(s);
migrate_fd_connect(s, NULL);
return;
err:
g_free(rdma);

View file

@ -81,7 +81,7 @@ enum qemu_vm_cmd {
MIG_CMD_MAX
};
#define MAX_VM_CMD_PACKAGED_SIZE (1ul << 24)
#define MAX_VM_CMD_PACKAGED_SIZE UINT32_MAX
static struct mig_cmd_args {
ssize_t len; /* -1 = variable */
const char *name;
@ -1376,7 +1376,8 @@ static int qemu_loadvm_state_main(QEMUFile *f, MigrationIncomingState *mis);
* *might* happen - it might be skipped if precopy transferred everything
* quickly.
*/
static int loadvm_postcopy_handle_advise(MigrationIncomingState *mis)
static int loadvm_postcopy_handle_advise(MigrationIncomingState *mis,
uint16_t len)
{
PostcopyState ps = postcopy_state_set(POSTCOPY_INCOMING_ADVISE);
uint64_t remote_pagesize_summary, local_pagesize_summary, remote_tps;
@ -1387,8 +1388,22 @@ static int loadvm_postcopy_handle_advise(MigrationIncomingState *mis)
return -1;
}
if (!migrate_postcopy_ram()) {
switch (len) {
case 0:
if (migrate_postcopy_ram()) {
error_report("RAM postcopy is enabled but have 0 byte advise");
return -EINVAL;
}
return 0;
case 8 + 8:
if (!migrate_postcopy_ram()) {
error_report("RAM postcopy is disabled but have 16 byte advise");
return -EINVAL;
}
break;
default:
error_report("CMD_POSTCOPY_ADVISE invalid length (%d)", len);
return -EINVAL;
}
if (!postcopy_ram_supported_by_host(mis)) {
@ -1807,7 +1822,7 @@ static int loadvm_process_command(QEMUFile *f)
return loadvm_handle_cmd_packaged(mis);
case MIG_CMD_POSTCOPY_ADVISE:
return loadvm_postcopy_handle_advise(mis);
return loadvm_postcopy_handle_advise(mis, len);
case MIG_CMD_POSTCOPY_LISTEN:
return loadvm_postcopy_handle_listen(mis);
@ -2266,6 +2281,7 @@ void qmp_xen_save_devices_state(const char *filename, bool has_live, bool live,
}
qio_channel_set_name(QIO_CHANNEL(ioc), "migration-xen-save-state");
f = qemu_fopen_channel_output(QIO_CHANNEL(ioc));
object_unref(OBJECT(ioc));
ret = qemu_save_device_state(f);
qemu_fclose(f);
if (ret < 0) {
@ -2313,6 +2329,7 @@ void qmp_xen_load_devices_state(const char *filename, Error **errp)
}
qio_channel_set_name(QIO_CHANNEL(ioc), "migration-xen-load-state");
f = qemu_fopen_channel_input(QIO_CHANNEL(ioc));
object_unref(OBJECT(ioc));
ret = qemu_loadvm_state(f);
qemu_fclose(f);

View file

@ -79,12 +79,10 @@ static void socket_outgoing_migration(QIOTask *task,
if (qio_task_propagate_error(task, &err)) {
trace_migration_socket_outgoing_error(error_get_pretty(err));
migrate_fd_error(data->s, err);
error_free(err);
} else {
trace_migration_socket_outgoing_connected(data->hostname);
migration_channel_connect(data->s, sioc, data->hostname);
}
migration_channel_connect(data->s, sioc, data->hostname, err);
object_unref(OBJECT(sioc));
}

View file

@ -118,11 +118,10 @@ static void migration_tls_outgoing_handshake(QIOTask *task,
if (qio_task_propagate_error(task, &err)) {
trace_migration_tls_outgoing_handshake_error(error_get_pretty(err));
migrate_fd_error(s, err);
} else {
trace_migration_tls_outgoing_handshake_complete();
migration_channel_connect(s, ioc, NULL);
}
migration_channel_connect(s, ioc, NULL, err);
object_unref(OBJECT(ioc));
}

View file

@ -114,7 +114,7 @@ migrate_transferred(uint64_t tranferred, uint64_t time_spent, double bandwidth,
process_incoming_migration_co_end(int ret, int ps) "ret=%d postcopy-state=%d"
process_incoming_migration_co_postcopy_end_main(void) ""
migration_set_incoming_channel(void *ioc, const char *ioctype) "ioc=%p ioctype=%s"
migration_set_outgoing_channel(void *ioc, const char *ioctype, const char *hostname) "ioc=%p ioctype=%s hostname=%s"
migration_set_outgoing_channel(void *ioc, const char *ioctype, const char *hostname, void *err) "ioc=%p ioctype=%s hostname=%s err=%p"
# migration/rdma.c
qemu_rdma_accept_incoming_migration(void) ""

View file

@ -268,10 +268,9 @@ static uint64_t get_migration_pass(QTestState *who)
static void wait_for_migration_complete(QTestState *who)
{
QDict *rsp, *rsp_return;
bool completed;
do {
while (true) {
QDict *rsp, *rsp_return;
bool completed;
const char *status;
rsp = wait_command(who, "{ 'execute': 'query-migrate' }");
@ -280,8 +279,11 @@ static void wait_for_migration_complete(QTestState *who)
completed = strcmp(status, "completed") == 0;
g_assert_cmpstr(status, !=, "failed");
QDECREF(rsp);
usleep(1000 * 100);
} while (!completed);
if (completed) {
return;
}
usleep(1000);
}
}
static void wait_for_migration_pass(QTestState *who)
@ -290,16 +292,13 @@ static void wait_for_migration_pass(QTestState *who)
uint64_t pass;
/* Wait for the 1st sync */
do {
while (!got_stop && !initial_pass) {
usleep(1000);
initial_pass = get_migration_pass(who);
if (got_stop || initial_pass) {
break;
}
usleep(1000 * 100);
} while (true);
}
do {
usleep(1000 * 100);
usleep(1000);
pass = get_migration_pass(who);
} while (pass == initial_pass && !got_stop);
}
@ -369,37 +368,20 @@ static void migrate_check_parameter(QTestState *who, const char *parameter,
QDECREF(rsp);
}
static void migrate_set_downtime(QTestState *who, const double value)
{
QDict *rsp;
gchar *cmd;
char *expected;
int64_t result_int;
cmd = g_strdup_printf("{ 'execute': 'migrate_set_downtime',"
"'arguments': { 'value': %g } }", value);
rsp = qtest_qmp(who, cmd);
g_free(cmd);
g_assert(qdict_haskey(rsp, "return"));
QDECREF(rsp);
result_int = value * 1000L;
expected = g_strdup_printf("%" PRId64, result_int);
migrate_check_parameter(who, "downtime-limit", expected);
g_free(expected);
}
static void migrate_set_speed(QTestState *who, const char *value)
static void migrate_set_parameter(QTestState *who, const char *parameter,
const char *value)
{
QDict *rsp;
gchar *cmd;
cmd = g_strdup_printf("{ 'execute': 'migrate_set_speed',"
"'arguments': { 'value': %s } }", value);
cmd = g_strdup_printf("{ 'execute': 'migrate-set-parameters',"
"'arguments': { '%s': %s } }",
parameter, value);
rsp = qtest_qmp(who, cmd);
g_free(cmd);
g_assert(qdict_haskey(rsp, "return"));
QDECREF(rsp);
migrate_check_parameter(who, "max-bandwidth", value);
migrate_check_parameter(who, parameter, value);
}
static void migrate_set_capability(QTestState *who, const char *capability,
@ -433,41 +415,52 @@ static void migrate(QTestState *who, const char *uri)
QDECREF(rsp);
}
static void migrate_start_postcopy(QTestState *who)
{
QDict *rsp;
rsp = wait_command(who, "{ 'execute': 'migrate-start-postcopy' }");
g_assert(qdict_haskey(rsp, "return"));
QDECREF(rsp);
}
static void test_migrate_start(QTestState **from, QTestState **to,
const char *uri)
{
gchar *cmd_src, *cmd_dst;
char *bootpath = g_strdup_printf("%s/bootsect", tmpfs);
const char *arch = qtest_get_arch();
const char *accel = "kvm:tcg";
got_stop = false;
if (strcmp(arch, "i386") == 0 || strcmp(arch, "x86_64") == 0) {
init_bootfile_x86(bootpath);
cmd_src = g_strdup_printf("-machine accel=kvm:tcg -m 150M"
" -name pcsource,debug-threads=on"
cmd_src = g_strdup_printf("-machine accel=%s -m 150M"
" -name source,debug-threads=on"
" -serial file:%s/src_serial"
" -drive file=%s,format=raw",
tmpfs, bootpath);
cmd_dst = g_strdup_printf("-machine accel=kvm:tcg -m 150M"
" -name pcdest,debug-threads=on"
accel, tmpfs, bootpath);
cmd_dst = g_strdup_printf("-machine accel=%s -m 150M"
" -name target,debug-threads=on"
" -serial file:%s/dest_serial"
" -drive file=%s,format=raw"
" -incoming %s",
tmpfs, bootpath, uri);
accel, tmpfs, bootpath, uri);
} else if (strcmp(arch, "ppc64") == 0) {
const char *accel;
/* On ppc64, the test only works with kvm-hv, but not with kvm-pr */
accel = access("/sys/module/kvm_hv", F_OK) ? "tcg" : "kvm:tcg";
if (access("/sys/module/kvm_hv", F_OK)) {
accel = "tcg";
}
init_bootfile_ppc(bootpath);
cmd_src = g_strdup_printf("-machine accel=%s -m 256M"
" -name pcsource,debug-threads=on"
" -name source,debug-threads=on"
" -serial file:%s/src_serial"
" -drive file=%s,if=pflash,format=raw",
accel, tmpfs, bootpath);
cmd_dst = g_strdup_printf("-machine accel=%s -m 256M"
" -name pcdest,debug-threads=on"
" -name target,debug-threads=on"
" -serial file:%s/dest_serial"
" -incoming %s",
accel, tmpfs, uri);
@ -495,13 +488,13 @@ static void test_migrate_end(QTestState *from, QTestState *to)
/* Destination still running, wait for a byte to change */
do {
qtest_memread(to, start_address, &dest_byte_b, 1);
usleep(10 * 1000);
usleep(1000 * 10);
} while (dest_byte_a == dest_byte_b);
qtest_qmp_discard_response(to, "{ 'execute' : 'stop'}");
/* With it stopped, check nothing changes */
qtest_memread(to, start_address, &dest_byte_c, 1);
sleep(1);
usleep(1000 * 200);
qtest_memread(to, start_address, &dest_byte_d, 1);
g_assert_cmpint(dest_byte_c, ==, dest_byte_d);
@ -515,11 +508,55 @@ static void test_migrate_end(QTestState *from, QTestState *to)
cleanup("dest_serial");
}
static void deprecated_set_downtime(QTestState *who, const double value)
{
QDict *rsp;
gchar *cmd;
char *expected;
int64_t result_int;
cmd = g_strdup_printf("{ 'execute': 'migrate_set_downtime',"
"'arguments': { 'value': %g } }", value);
rsp = qtest_qmp(who, cmd);
g_free(cmd);
g_assert(qdict_haskey(rsp, "return"));
QDECREF(rsp);
result_int = value * 1000L;
expected = g_strdup_printf("%" PRId64, result_int);
migrate_check_parameter(who, "downtime-limit", expected);
g_free(expected);
}
static void deprecated_set_speed(QTestState *who, const char *value)
{
QDict *rsp;
gchar *cmd;
cmd = g_strdup_printf("{ 'execute': 'migrate_set_speed',"
"'arguments': { 'value': %s } }", value);
rsp = qtest_qmp(who, cmd);
g_free(cmd);
g_assert(qdict_haskey(rsp, "return"));
QDECREF(rsp);
migrate_check_parameter(who, "max-bandwidth", value);
}
static void test_deprecated(void)
{
QTestState *from;
from = qtest_start("");
deprecated_set_downtime(from, 0.12345);
deprecated_set_speed(from, "12345");
qtest_quit(from);
}
static void test_migrate(void)
{
char *uri = g_strdup_printf("unix:%s/migsocket", tmpfs);
QTestState *from, *to;
QDict *rsp;
test_migrate_start(&from, &to, uri);
@ -530,8 +567,8 @@ static void test_migrate(void)
* quickly, but that it doesn't complete precopy even on a slow
* machine, so also set the downtime.
*/
migrate_set_speed(from, "100000000");
migrate_set_downtime(from, 0.001);
migrate_set_parameter(from, "max-bandwidth", "100000000");
migrate_set_parameter(from, "downtime-limit", "1");
/* Wait for the first serial output from the source */
wait_for_serial("src_serial");
@ -540,9 +577,7 @@ static void test_migrate(void)
wait_for_migration_pass(from);
rsp = wait_command(from, "{ 'execute': 'migrate-start-postcopy' }");
g_assert(qdict_haskey(rsp, "return"));
QDECREF(rsp);
migrate_start_postcopy(from);
if (!got_stop) {
qtest_qmp_eventwait(from, "STOP");
@ -578,6 +613,7 @@ int main(int argc, char **argv)
module_call_init(MODULE_INIT_QOM);
qtest_add_func("/migration/postcopy/unix", test_migrate);
qtest_add_func("/migration/deprecated", test_deprecated);
ret = g_test_run();