Re: [Qemu-devel] [PATCH 1/6] tests: Add basic migration precopy test

["Daniel P. Berrange" <berrange@redhat.com>]

On Wed, Oct 04, 2017 at 12:39:28PM +0200, Juan Quintela wrote:
> Signed-off-by: Juan Quintela <quintela@redhat.com>
> ---
>  tests/Makefile.include |   3 +
>  tests/migration-test.c | 497 +++++++++++++++++++++++++++++++++++++++++++++++++
>  2 files changed, 500 insertions(+)
>  create mode 100644 tests/migration-test.c
> 


> +
> +/* A simple PC boot sector that modifies memory (1-100MB) quickly
> + * outputing a 'B' every so often if it's still running.
> + */


Can you add a comment about what it is actually doing to dirty the memory.

eg is it writing a different random value at each byte of RAM, or picking
a random value at the stasrt of each iteration and writing it to all RAM,
or it is just xoring current memory contents, or something else ?

Understanding this would be helpful in understanding how well the tests
for xbzrle / compression are working, because the pattern of dirtying
memory will affect whether the compression does anything useful or not.

> +unsigned char bootsect[] = {
> +  0xfa, 0x0f, 0x01, 0x16, 0x74, 0x7c, 0x66, 0xb8, 0x01, 0x00, 0x00, 0x00,
> +  0x0f, 0x22, 0xc0, 0x66, 0xea, 0x20, 0x7c, 0x00, 0x00, 0x08, 0x00, 0x00,
> +  0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xe4, 0x92, 0x0c, 0x02,
> +  0xe6, 0x92, 0xb8, 0x10, 0x00, 0x00, 0x00, 0x8e, 0xd8, 0x66, 0xb8, 0x41,
> +  0x00, 0x66, 0xba, 0xf8, 0x03, 0xee, 0xb3, 0x00, 0xb8, 0x00, 0x00, 0x10,
> +  0x00, 0xfe, 0x00, 0x05, 0x00, 0x10, 0x00, 0x00, 0x3d, 0x00, 0x00, 0x40,
> +  0x06, 0x7c, 0xf2, 0xfe, 0xc3, 0x75, 0xe9, 0x66, 0xb8, 0x42, 0x00, 0x66,
> +  0xba, 0xf8, 0x03, 0xee, 0xeb, 0xde, 0x66, 0x90, 0x00, 0x00, 0x00, 0x00,
> +  0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0x00, 0x00, 0x00, 0x9a, 0xcf, 0x00,
> +  0xff, 0xff, 0x00, 0x00, 0x00, 0x92, 0xcf, 0x00, 0x27, 0x00, 0x5c, 0x7c,
> +  0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
> +  0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
> +  0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
> +  0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
> +  0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
> +  0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
> +  0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
> +  0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
> +  0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
> +  0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
> +  0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
> +  0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
> +  0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
> +  0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
> +  0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
> +  0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
> +  0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
> +  0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
> +  0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
> +  0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
> +  0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
> +  0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
> +  0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
> +  0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
> +  0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
> +  0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
> +  0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
> +  0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
> +  0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
> +  0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
> +  0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
> +  0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
> +  0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x55, 0xaa
> +};
> +
> +static void init_bootfile_x86(const char *bootpath)
> +{
> +    FILE *bootfile = fopen(bootpath, "wb");
> +
> +    g_assert_cmpint(fwrite(bootsect, 512, 1, bootfile), ==, 1);
> +    fclose(bootfile);
> +}
> +
> +static void init_bootfile_ppc(const char *bootpath)
> +{
> +    FILE *bootfile;
> +    char buf[MIN_NVRAM_SIZE];
> +    ChrpNvramPartHdr *header = (ChrpNvramPartHdr *)buf;
> +
> +    memset(buf, 0, MIN_NVRAM_SIZE);
> +
> +    /* Create a "common" partition in nvram to store boot-command property */
> +
> +    header->signature = CHRP_NVPART_SYSTEM;
> +    memcpy(header->name, "common", 6);
> +    chrp_nvram_finish_partition(header, MIN_NVRAM_SIZE);
> +
> +    /* FW_MAX_SIZE is 4MB, but slof.bin is only 900KB,
> +     * so let's modify memory between 1MB and 100MB
> +     * to do like PC bootsector
> +     */
> +
> +    sprintf(buf + 16,
> +            "boot-command=hex .\" _\" begin %x %x do i c@ 1 + i c! 1000 +loop "
> +            ".\" B\" 0 until", end_address, start_address);
> +
> +    /* Write partition to the NVRAM file */
> +
> +    bootfile = fopen(bootpath, "wb");
> +    g_assert_cmpint(fwrite(buf, MIN_NVRAM_SIZE, 1, bootfile), ==, 1);
> +    fclose(bootfile);
> +}
> +
> +/*
> + * Wait for some output in the serial output file,
> + * we get an 'A' followed by an endless string of 'B's
> + * but on the destination we won't have the A.
> + */
> +static void wait_for_serial(const char *side)
> +{
> +    char *serialpath = g_strdup_printf("%s/%s", tmpfs, side);
> +    FILE *serialfile = fopen(serialpath, "r");
> +    const char *arch = qtest_get_arch();
> +    int started = (strcmp(side, "src_serial") == 0 &&
> +                   strcmp(arch, "ppc64") == 0) ? 0 : 1;
> +
> +    g_free(serialpath);
> +    do {
> +        int readvalue = fgetc(serialfile);
> +
> +        if (!started) {
> +            /* SLOF prints its banner before starting test,
> +             * to ignore it, mark the start of the test with '_',
> +             * ignore all characters until this marker
> +             */
> +            switch (readvalue) {
> +            case '_':
> +                started = 1;
> +                break;
> +            case EOF:
> +                fseek(serialfile, 0, SEEK_SET);
> +                usleep(1000);
> +                break;
> +            }
> +            continue;
> +        }
> +        switch (readvalue) {
> +        case 'A':
> +            /* Fine */
> +            break;
> +
> +        case 'B':
> +            /* It's alive! */
> +            fclose(serialfile);
> +            return;
> +
> +        case EOF:
> +            started = (strcmp(side, "src_serial") == 0 &&
> +                       strcmp(arch, "ppc64") == 0) ? 0 : 1;
> +            fseek(serialfile, 0, SEEK_SET);
> +            usleep(1000);
> +            break;
> +
> +        default:
> +            fprintf(stderr, "Unexpected %d on %s serial\n", readvalue, side);
> +            g_assert_not_reached();
> +        }
> +    } while (true);
> +}
> +
> +/*
> + * Events can get in the way of responses we are actually waiting for.
> + */
> +static QDict *return_or_event(QDict *response, QTestState *who)
> +{
> +    const char *event_string;
> +    if (!qdict_haskey(response, "event")) {
> +        return response;
> +    }
> +
> +    /* OK, it was an event */
> +    event_string = qdict_get_str(response, "event");
> +    if (!strcmp(event_string, "STOP")) {
> +        got_stop = true;
> +    }
> +    QDECREF(response);
> +    return return_or_event(qtest_qmp_receive(who), who);
> +}
> +
> +
> +/*
> + * It's tricky to use qemu's migration event capability with qtest,
> + * events suddenly appearing confuse the qmp()/hmp() responses.
> + * so wait for a couple of passes to have happened before
> + * going postcopy.
> + */
> +
> +static uint64_t get_migration_pass(QTestState *who)
> +{
> +    QDict *rsp, *rsp_return, *rsp_ram;
> +    uint64_t result;
> +
> +    rsp = return_or_event(qmp("{ 'execute': 'query-migrate' }"), who);
> +    rsp_return = qdict_get_qdict(rsp, "return");
> +    if (!qdict_haskey(rsp_return, "ram")) {
> +        /* Still in setup */
> +        result = 0;
> +    } else {
> +        rsp_ram = qdict_get_qdict(rsp_return, "ram");
> +        result = qdict_get_try_int(rsp_ram, "dirty-sync-count", 0);
> +    }
> +    QDECREF(rsp);
> +    return result;
> +}
> +
> +static void wait_for_migration_complete(QTestState *who)
> +{
> +    bool completed;
> +
> +    do {
> +        QDict *rsp, *rsp_return;
> +        const char *status;
> +
> +        rsp = return_or_event(qmp("{ 'execute': 'query-migrate' }"), who);
> +        rsp_return = qdict_get_qdict(rsp, "return");
> +        status = qdict_get_str(rsp_return, "status");
> +        completed = strcmp(status, "completed") == 0;
> +        g_assert_cmpstr(status, !=,  "failed");
> +        QDECREF(rsp);
> +        usleep(1000 * 100);
> +    } while (!completed);
> +}
> +
> +static void wait_for_migration_pass(QTestState *who)
> +{
> +    uint64_t initial_pass = get_migration_pass(who);
> +    uint64_t pass;
> +
> +    /* Wait for the 1st sync */
> +    do {
> +        initial_pass = get_migration_pass(who);
> +        if (got_stop || initial_pass) {
> +            break;
> +        }
> +        usleep(1000 * 100);
> +    } while (true);
> +
> +    do {
> +        usleep(1000 * 100);
> +        pass = get_migration_pass(who);
> +    } while (pass == initial_pass && !got_stop);
> +}
> +
> +static void check_guests_ram(QTestState *who)
> +{
> +    /* Our ASM test will have been incrementing one byte from each page from
> +     * 1MB to <100MB in order.
> +     * This gives us a constraint that any page's byte should be equal or less
> +     * than the previous pages byte (mod 256); and they should all be equal
> +     * except for one transition at the point where we meet the incrementer.
> +     * (We're running this with the guest stopped).
> +     */
> +    unsigned address;
> +    uint8_t first_byte;
> +    uint8_t last_byte;
> +    bool hit_edge = false;
> +    bool bad = false;
> +
> +    qtest_memread(who, start_address, &first_byte, 1);
> +    last_byte = first_byte;
> +
> +    for (address = start_address + 4096; address < end_address; address += 4096)
> +    {
> +        uint8_t b;
> +        qtest_memread(who, address, &b, 1);
> +        if (b != last_byte) {
> +            if (((b + 1) % 256) == last_byte && !hit_edge) {
> +                /* This is OK, the guest stopped at the point of
> +                 * incrementing the previous page but didn't get
> +                 * to us yet.
> +                 */
> +                hit_edge = true;
> +            } else {
> +                fprintf(stderr, "Memory content inconsistency at %x"
> +                                " first_byte = %x last_byte = %x current = %x"
> +                                " hit_edge = %x\n",
> +                                address, first_byte, last_byte, b, hit_edge);
> +                bad = true;
> +            }
> +        }
> +        last_byte = b;
> +    }
> +    g_assert_false(bad);
> +}
> +
> +static void cleanup(const char *filename)
> +{
> +    char *path = g_strdup_printf("%s/%s", tmpfs, filename);
> +
> +    unlink(path);
> +    g_free(path);
> +}
> +
> +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();
> +
> +    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"
> +                                  " -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"
> +                                  " -serial file:%s/dest_serial"
> +                                  " -drive file=%s,format=raw"
> +                                  " -incoming %s",
> +                                  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";
> +        init_bootfile_ppc(bootpath);
> +        cmd_src = g_strdup_printf("-machine accel=%s -m 256M"
> +                                  " -name pcsource,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"
> +                                  " -serial file:%s/dest_serial"
> +                                  " -incoming %s",
> +                                  accel, tmpfs, uri);
> +    } else {
> +        g_assert_not_reached();
> +    }
> +
> +    g_free(bootpath);
> +
> +    *from = qtest_start(cmd_src);
> +    g_free(cmd_src);
> +
> +    *to = qtest_init(cmd_dst);
> +    g_free(cmd_dst);
> +}
> +
> +static void test_migrate_end(QTestState *from, QTestState *to)
> +{
> +    unsigned char dest_byte_a, dest_byte_b, dest_byte_c, dest_byte_d;
> +
> +    qtest_quit(from);
> +
> +    qtest_memread(to, start_address, &dest_byte_a, 1);
> +
> +    /* Destination still running, wait for a byte to change */
> +    do {
> +        qtest_memread(to, start_address, &dest_byte_b, 1);
> +        usleep(10 * 1000);
> +    } 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);
> +    qtest_memread(to, start_address, &dest_byte_d, 1);
> +    g_assert_cmpint(dest_byte_c, ==, dest_byte_d);
> +
> +    check_guests_ram(to);
> +
> +    qtest_quit(to);
> +
> +    cleanup("bootsect");
> +    cleanup("migsocket");
> +    cleanup("src_serial");
> +    cleanup("dest_serial");
> +}
> +
> +static void migrate(QTestState *who, const char *uri)
> +{
> +    QDict *rsp;
> +    gchar *cmd;
> +
> +    cmd = g_strdup_printf("{ 'execute': 'migrate',"
> +                          "'arguments': { 'uri': '%s' } }",
> +                          uri);
> +    rsp = qtest_qmp(who, cmd);
> +    g_free(cmd);
> +    g_assert(qdict_haskey(rsp, "return"));
> +    QDECREF(rsp);
> +}
> +
> +static void migrate_set_parameter(QTestState *who, const char *parameter,
> +                                  const char *value)
> +{
> +    QDict *rsp;
> +    gchar *cmd;
> +
> +    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);
> +}
> +
> +static void test_precopy(const char *uri)
> +{
> +    QTestState *from, *to;
> +
> +    test_migrate_start(&from, &to, uri);
> +
> +    /* We want to pick a speed slow enough that the test completes
> +     * quickly, but that it doesn't complete precopy even on a slow
> +     * machine, so also set the downtime.
> +     */
> +    /* 100 ms */
> +    migrate_set_parameter(from, "downtime-limit", "100");
> +    /* 1MB/s slow*/
> +    migrate_set_parameter(from, "max-bandwidth", "100000000");
> +
> +    /* Wait for the first serial output from the source */
> +    wait_for_serial("src_serial");
> +
> +    migrate(from, uri);
> +
> +    wait_for_migration_pass(from);
> +
> +    /* 1GB/s now it should converge */
> +    migrate_set_parameter(from, "max-bandwidth", "1000000000");
> +
> +    if (!got_stop) {
> +        qtest_qmp_eventwait(from, "STOP");
> +    }
> +    qtest_qmp_eventwait(to, "RESUME");
> +
> +    wait_for_serial("dest_serial");
> +    wait_for_migration_complete(from);
> +
> +    test_migrate_end(from, to);
> +}
> +
> +static void test_precopy_unix(void)
> +{
> +    char *uri = g_strdup_printf("unix:%s/migsocket", tmpfs);
> +
> +    test_precopy(uri);
> +    g_free(uri);
> +}
> +
> +int main(int argc, char **argv)
> +{
> +    char template[] = "/tmp/migration-test-XXXXXX";
> +    int ret;
> +
> +    g_test_init(&argc, &argv, NULL);
> +
> +    tmpfs = mkdtemp(template);
> +    if (!tmpfs) {
> +        g_test_message("mkdtemp on path (%s): %s\n", template, strerror(errno));
> +    }
> +    g_assert(tmpfs);
> +
> +    module_call_init(MODULE_INIT_QOM);
> +
> +    qtest_add_func("/migration/precopy/unix", test_precopy_unix);
> +
> +    ret = g_test_run();
> +
> +    g_assert_cmpint(ret, ==, 0);
> +
> +    ret = rmdir(tmpfs);
> +    if (ret != 0) {
> +        g_test_message("unable to rmdir: path (%s): %s\n",
> +                       tmpfs, strerror(errno));
> +    }
> +
> +    return ret;
> +}
> -- 
> 2.13.5
> 
> 

Regards,
Daniel
-- 
|: https://berrange.com      -o-    https://www.flickr.com/photos/dberrange :|
|: https://libvirt.org         -o-            https://fstop138.berrange.com :|
|: https://entangle-photo.org    -o-    https://www.instagram.com/dberrange :|