Commit: 61c265f0660ee476985808c8aa7915617c44fd53 - qemu (git)

Commit MetaInfo

• Revisão: 61c265f0660ee476985808c8aa7915617c44fd53 (tree)
• Hora: 2020-03-13 19:33:04
• Autor: Peter Maydell <peter.maydell@lina...>
• Commiter: Peter Maydell

Mensagem de Log

Migration pull 2020-03-13

zstd build fix
A new auto-converge parameter
Some COLO improvements
-----BEGIN PGP SIGNATURE-----
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=/Uri
-----END PGP SIGNATURE-----

Merge remote-tracking branch 'remotes/dgilbert/tags/pull-migration-20200313a' into staging

Migration pull 2020-03-13

zstd build fix
A new auto-converge parameter
Some COLO improvements

# gpg: Signature made Fri 13 Mar 2020 10:29:34 GMT
# gpg: using RSA key 45F5C71B4A0CB7FB977A9FA90516331EBC5BFDE7
# gpg: Good signature from "Dr. David Alan Gilbert (RH2) <[e-mail]>" [full]
# Primary key fingerprint: 45F5 C71B 4A0C B7FB 977A 9FA9 0516 331E BC5B FDE7

* remotes/dgilbert/tags/pull-migration-20200313a:

migration: recognize COLO as part of activating process
ram/colo: only record bitmap of dirty pages in COLO stage
COLO: Optimize memory back-up process
migration/throttle: Add throttle-trig-thres migration parameter
configure: Improve zstd test

Signed-off-by: Peter Maydell <[e-mail]>

Mudança Sumário

• modified: configure
• modified: migration/colo.c
• modified: migration/migration.c
• modified: migration/ram.c
• modified: migration/ram.h
• modified: monitor/hmp-cmds.c
• modified: qapi/migration.json

Diff

--- a/configure
+++ b/configure
@@ -2475,7 +2475,8 @@ fi
 # zstd check
 
 if test "$zstd" != "no" ; then
-    if $pkg_config --exist libzstd ; then
+    libzstd_minver="1.4.0"
+    if $pkg_config --atleast-version=$libzstd_minver libzstd ; then
         zstd_cflags="$($pkg_config --cflags libzstd)"
         zstd_libs="$($pkg_config --libs libzstd)"
         LIBS="$zstd_libs $LIBS"

--- a/migration/colo.c
+++ b/migration/colo.c
@@ -26,6 +26,7 @@
 #include "qemu/main-loop.h"
 #include "qemu/rcu.h"
 #include "migration/failover.h"
+#include "migration/ram.h"
 #ifdef CONFIG_REPLICATION
 #include "replication.h"
 #endif
@@ -845,6 +846,8 @@ void *colo_process_incoming_thread(void *opaque)
      */
     qemu_file_set_blocking(mis->from_src_file, true);
 
+    colo_incoming_start_dirty_log();
+
     bioc = qio_channel_buffer_new(COLO_BUFFER_BASE_SIZE);
     fb = qemu_fopen_channel_input(QIO_CHANNEL(bioc));
     object_unref(OBJECT(bioc));

--- a/migration/migration.c
+++ b/migration/migration.c
@@ -78,6 +78,7 @@
 /*0: means nocompress, 1: best speed, ... 9: best compress ratio */
 #define DEFAULT_MIGRATE_COMPRESS_LEVEL 1
 /* Define default autoconverge cpu throttle migration parameters */
+#define DEFAULT_MIGRATE_THROTTLE_TRIGGER_THRESHOLD 50
 #define DEFAULT_MIGRATE_CPU_THROTTLE_INITIAL 20
 #define DEFAULT_MIGRATE_CPU_THROTTLE_INCREMENT 10
 #define DEFAULT_MIGRATE_MAX_CPU_THROTTLE 99
@@ -778,6 +779,8 @@ MigrationParameters *qmp_query_migrate_parameters(Error **errp)
     params->compress_wait_thread = s->parameters.compress_wait_thread;
     params->has_decompress_threads = true;
     params->decompress_threads = s->parameters.decompress_threads;
+    params->has_throttle_trigger_threshold = true;
+    params->throttle_trigger_threshold = s->parameters.throttle_trigger_threshold;
     params->has_cpu_throttle_initial = true;
     params->cpu_throttle_initial = s->parameters.cpu_throttle_initial;
     params->has_cpu_throttle_increment = true;
@@ -851,6 +854,7 @@ bool migration_is_setup_or_active(int state)
     case MIGRATION_STATUS_PRE_SWITCHOVER:
     case MIGRATION_STATUS_DEVICE:
     case MIGRATION_STATUS_WAIT_UNPLUG:
+    case MIGRATION_STATUS_COLO:
         return true;
 
     default:
@@ -1169,6 +1173,15 @@ static bool migrate_params_check(MigrationParameters *params, Error **errp)
         return false;
     }
 
+    if (params->has_throttle_trigger_threshold &&
+        (params->throttle_trigger_threshold < 1 ||
+         params->throttle_trigger_threshold > 100)) {
+        error_setg(errp, QERR_INVALID_PARAMETER_VALUE,
+                   "throttle_trigger_threshold",
+                   "an integer in the range of 1 to 100");
+        return false;
+    }
+
     if (params->has_cpu_throttle_initial &&
         (params->cpu_throttle_initial < 1 ||
          params->cpu_throttle_initial > 99)) {
@@ -1298,6 +1311,10 @@ static void migrate_params_test_apply(MigrateSetParameters *params,
         dest->decompress_threads = params->decompress_threads;
     }
 
+    if (params->has_throttle_trigger_threshold) {
+        dest->throttle_trigger_threshold = params->throttle_trigger_threshold;
+    }
+
     if (params->has_cpu_throttle_initial) {
         dest->cpu_throttle_initial = params->cpu_throttle_initial;
     }
@@ -1382,6 +1399,10 @@ static void migrate_params_apply(MigrateSetParameters *params, Error **errp)
         s->parameters.decompress_threads = params->decompress_threads;
     }
 
+    if (params->has_throttle_trigger_threshold) {
+        s->parameters.throttle_trigger_threshold = params->throttle_trigger_threshold;
+    }
+
     if (params->has_cpu_throttle_initial) {
         s->parameters.cpu_throttle_initial = params->cpu_throttle_initial;
     }
@@ -3558,6 +3579,9 @@ static Property migration_properties[] = {
     DEFINE_PROP_UINT8("x-decompress-threads", MigrationState,
                       parameters.decompress_threads,
                       DEFAULT_MIGRATE_DECOMPRESS_THREAD_COUNT),
+    DEFINE_PROP_UINT8("x-throttle-trigger-threshold", MigrationState,
+                      parameters.throttle_trigger_threshold,
+                      DEFAULT_MIGRATE_THROTTLE_TRIGGER_THRESHOLD),
     DEFINE_PROP_UINT8("x-cpu-throttle-initial", MigrationState,
                       parameters.cpu_throttle_initial,
                       DEFAULT_MIGRATE_CPU_THROTTLE_INITIAL),
@@ -3667,6 +3691,7 @@ static void migration_instance_init(Object *obj)
     params->has_compress_level = true;
     params->has_compress_threads = true;
     params->has_decompress_threads = true;
+    params->has_throttle_trigger_threshold = true;
     params->has_cpu_throttle_initial = true;
     params->has_cpu_throttle_increment = true;
     params->has_max_bandwidth = true;

--- a/migration/ram.c
+++ b/migration/ram.c
@@ -896,11 +896,38 @@ static void migration_update_rates(RAMState *rs, int64_t end_time)
     }
 }
 
+static void migration_trigger_throttle(RAMState *rs)
+{
+    MigrationState *s = migrate_get_current();
+    uint64_t threshold = s->parameters.throttle_trigger_threshold;
+
+    uint64_t bytes_xfer_period = ram_counters.transferred - rs->bytes_xfer_prev;
+    uint64_t bytes_dirty_period = rs->num_dirty_pages_period * TARGET_PAGE_SIZE;
+    uint64_t bytes_dirty_threshold = bytes_xfer_period * threshold / 100;
+
+    /* During block migration the auto-converge logic incorrectly detects
+     * that ram migration makes no progress. Avoid this by disabling the
+     * throttling logic during the bulk phase of block migration. */
+    if (migrate_auto_converge() && !blk_mig_bulk_active()) {
+        /* The following detection logic can be refined later. For now:
+           Check to see if the ratio between dirtied bytes and the approx.
+           amount of bytes that just got transferred since the last time
+           we were in this routine reaches the threshold. If that happens
+           twice, start or increase throttling. */
+
+        if ((bytes_dirty_period > bytes_dirty_threshold) &&
+            (++rs->dirty_rate_high_cnt >= 2)) {
+            trace_migration_throttle();
+            rs->dirty_rate_high_cnt = 0;
+            mig_throttle_guest_down();
+        }
+    }
+}
+
 static void migration_bitmap_sync(RAMState *rs)
 {
     RAMBlock *block;
     int64_t end_time;
-    uint64_t bytes_xfer_now;
 
     ram_counters.dirty_sync_count++;
 
@@ -927,26 +954,7 @@ static void migration_bitmap_sync(RAMState *rs)
 
     /* more than 1 second = 1000 millisecons */
     if (end_time > rs->time_last_bitmap_sync + 1000) {
-        bytes_xfer_now = ram_counters.transferred;
-
-        /* During block migration the auto-converge logic incorrectly detects
-         * that ram migration makes no progress. Avoid this by disabling the
-         * throttling logic during the bulk phase of block migration. */
-        if (migrate_auto_converge() && !blk_mig_bulk_active()) {
-            /* The following detection logic can be refined later. For now:
-               Check to see if the dirtied bytes is 50% more than the approx.
-               amount of bytes that just got transferred since the last time we
-               were in this routine. If that happens twice, start or increase
-               throttling */
-
-            if ((rs->num_dirty_pages_period * TARGET_PAGE_SIZE >
-                   (bytes_xfer_now - rs->bytes_xfer_prev) / 2) &&
-                (++rs->dirty_rate_high_cnt >= 2)) {
-                    trace_migration_throttle();
-                    rs->dirty_rate_high_cnt = 0;
-                    mig_throttle_guest_down();
-            }
-        }
+        migration_trigger_throttle(rs);
 
         migration_update_rates(rs, end_time);
 
@@ -955,7 +963,7 @@ static void migration_bitmap_sync(RAMState *rs)
         /* reset period counters */
         rs->time_last_bitmap_sync = end_time;
         rs->num_dirty_pages_period = 0;
-        rs->bytes_xfer_prev = bytes_xfer_now;
+        rs->bytes_xfer_prev = ram_counters.transferred;
     }
     if (migrate_use_events()) {
         qapi_event_send_migration_pass(ram_counters.dirty_sync_count);
@@ -2734,7 +2742,7 @@ static inline void *host_from_ram_block_offset(RAMBlock *block,
 }
 
 static inline void *colo_cache_from_block_offset(RAMBlock *block,
-                                                 ram_addr_t offset)
+                             ram_addr_t offset, bool record_bitmap)
 {
     if (!offset_in_ramblock(block, offset)) {
         return NULL;
@@ -2750,7 +2758,8 @@ static inline void *colo_cache_from_block_offset(RAMBlock *block,
     * It help us to decide which pages in ram cache should be flushed
     * into VM's RAM later.
     */
-    if (!test_and_set_bit(offset >> TARGET_PAGE_BITS, block->bmap)) {
+    if (record_bitmap &&
+        !test_and_set_bit(offset >> TARGET_PAGE_BITS, block->bmap)) {
         ram_state->migration_dirty_pages++;
     }
     return block->colo_cache + offset;
@@ -2986,7 +2995,6 @@ int colo_init_ram_cache(void)
                 }
                 return -errno;
             }
-            memcpy(block->colo_cache, block->host, block->used_length);
         }
     }
 
@@ -3000,19 +3008,36 @@ int colo_init_ram_cache(void)
 
         RAMBLOCK_FOREACH_NOT_IGNORED(block) {
             unsigned long pages = block->max_length >> TARGET_PAGE_BITS;
-
             block->bmap = bitmap_new(pages);
-            bitmap_set(block->bmap, 0, pages);
         }
     }
-    ram_state = g_new0(RAMState, 1);
-    ram_state->migration_dirty_pages = 0;
-    qemu_mutex_init(&ram_state->bitmap_mutex);
-    memory_global_dirty_log_start();
 
+    ram_state_init(&ram_state);
     return 0;
 }
 
+/* TODO: duplicated with ram_init_bitmaps */
+void colo_incoming_start_dirty_log(void)
+{
+    RAMBlock *block = NULL;
+    /* For memory_global_dirty_log_start below. */
+    qemu_mutex_lock_iothread();
+    qemu_mutex_lock_ramlist();
+
+    memory_global_dirty_log_sync();
+    WITH_RCU_READ_LOCK_GUARD() {
+        RAMBLOCK_FOREACH_NOT_IGNORED(block) {
+            ramblock_sync_dirty_bitmap(ram_state, block);
+            /* Discard this dirty bitmap record */
+            bitmap_zero(block->bmap, block->max_length >> TARGET_PAGE_BITS);
+        }
+        memory_global_dirty_log_start();
+    }
+    ram_state->migration_dirty_pages = 0;
+    qemu_mutex_unlock_ramlist();
+    qemu_mutex_unlock_iothread();
+}
+
 /* It is need to hold the global lock to call this helper */
 void colo_release_ram_cache(void)
 {
@@ -3032,9 +3057,7 @@ void colo_release_ram_cache(void)
             }
         }
     }
-    qemu_mutex_destroy(&ram_state->bitmap_mutex);
-    g_free(ram_state);
-    ram_state = NULL;
+    ram_state_cleanup(&ram_state);
 }
 
 /**
@@ -3348,7 +3371,7 @@ static int ram_load_precopy(QEMUFile *f)
 
     while (!ret && !(flags & RAM_SAVE_FLAG_EOS)) {
         ram_addr_t addr, total_ram_bytes;
-        void *host = NULL;
+        void *host = NULL, *host_bak = NULL;
         uint8_t ch;
 
         /*
@@ -3379,20 +3402,35 @@ static int ram_load_precopy(QEMUFile *f)
                      RAM_SAVE_FLAG_COMPRESS_PAGE | RAM_SAVE_FLAG_XBZRLE)) {
             RAMBlock *block = ram_block_from_stream(f, flags);
 
+            host = host_from_ram_block_offset(block, addr);
             /*
-             * After going into COLO, we should load the Page into colo_cache.
+             * After going into COLO stage, we should not load the page
+             * into SVM's memory directly, we put them into colo_cache firstly.
+             * NOTE: We need to keep a copy of SVM's ram in colo_cache.
+             * Previously, we copied all these memory in preparing stage of COLO
+             * while we need to stop VM, which is a time-consuming process.
+             * Here we optimize it by a trick, back-up every page while in
+             * migration process while COLO is enabled, though it affects the
+             * speed of the migration, but it obviously reduce the downtime of
+             * back-up all SVM'S memory in COLO preparing stage.
              */
-            if (migration_incoming_in_colo_state()) {
-                host = colo_cache_from_block_offset(block, addr);
-            } else {
-                host = host_from_ram_block_offset(block, addr);
+            if (migration_incoming_colo_enabled()) {
+                if (migration_incoming_in_colo_state()) {
+                    /* In COLO stage, put all pages into cache temporarily */
+                    host = colo_cache_from_block_offset(block, addr, true);
+                } else {
+                   /*
+                    * In migration stage but before COLO stage,
+                    * Put all pages into both cache and SVM's memory.
+                    */
+                    host_bak = colo_cache_from_block_offset(block, addr, false);
+                }
             }
             if (!host) {
                 error_report("Illegal RAM offset " RAM_ADDR_FMT, addr);
                 ret = -EINVAL;
                 break;
             }
-
             if (!migration_incoming_in_colo_state()) {
                 ramblock_recv_bitmap_set(block, host);
             }
@@ -3506,6 +3544,9 @@ static int ram_load_precopy(QEMUFile *f)
         if (!ret) {
             ret = qemu_file_get_error(f);
         }
+        if (!ret && host_bak) {
+            memcpy(host_bak, host, TARGET_PAGE_SIZE);
+        }
     }
 
     ret |= wait_for_decompress_done();

--- a/migration/ram.h
+++ b/migration/ram.h
@@ -66,5 +66,6 @@ int ram_dirty_bitmap_reload(MigrationState *s, RAMBlock *rb);
 /* ram cache */
 int colo_init_ram_cache(void);
 void colo_release_ram_cache(void);
+void colo_incoming_start_dirty_log(void);
 
 #endif

--- a/monitor/hmp-cmds.c
+++ b/monitor/hmp-cmds.c
@@ -407,6 +407,10 @@ void hmp_info_migrate_parameters(Monitor *mon, const QDict *qdict)
         monitor_printf(mon, "%s: %u\n",
             MigrationParameter_str(MIGRATION_PARAMETER_DECOMPRESS_THREADS),
             params->decompress_threads);
+        assert(params->has_throttle_trigger_threshold);
+        monitor_printf(mon, "%s: %u\n",
+            MigrationParameter_str(MIGRATION_PARAMETER_THROTTLE_TRIGGER_THRESHOLD),
+            params->throttle_trigger_threshold);
         assert(params->has_cpu_throttle_initial);
         monitor_printf(mon, "%s: %u\n",
             MigrationParameter_str(MIGRATION_PARAMETER_CPU_THROTTLE_INITIAL),
@@ -1254,6 +1258,9 @@ void hmp_migrate_set_parameter(Monitor *mon, const QDict *qdict)
         p->has_decompress_threads = true;
         visit_type_int(v, param, &p->decompress_threads, &err);
         break;
+    case MIGRATION_PARAMETER_THROTTLE_TRIGGER_THRESHOLD:
+        p->has_throttle_trigger_threshold = true;
+        visit_type_int(v, param, &p->throttle_trigger_threshold, &err);
     case MIGRATION_PARAMETER_CPU_THROTTLE_INITIAL:
         p->has_cpu_throttle_initial = true;
         visit_type_int(v, param, &p->cpu_throttle_initial, &err);

--- a/qapi/migration.json
+++ b/qapi/migration.json
@@ -540,6 +540,10 @@
 #                      compression, so set the decompress-threads to the number about 1/4
 #                      of compress-threads is adequate.
 #
+# @throttle-trigger-threshold: The ratio of bytes_dirty_period and bytes_xfer_period
+#                              to trigger throttling. It is expressed as percentage.
+#                              The default value is 50. (Since 5.0)
+#
 # @cpu-throttle-initial: Initial percentage of time guest cpus are throttled
 #                        when migration auto-converge is activated. The
 #                        default value is 20. (Since 2.7)
@@ -625,7 +629,7 @@
   'data': ['announce-initial', 'announce-max',
            'announce-rounds', 'announce-step',
            'compress-level', 'compress-threads', 'decompress-threads',
-           'compress-wait-thread',
+           'compress-wait-thread', 'throttle-trigger-threshold',
            'cpu-throttle-initial', 'cpu-throttle-increment',
            'tls-creds', 'tls-hostname', 'tls-authz', 'max-bandwidth',
            'downtime-limit', 'x-checkpoint-delay', 'block-incremental',
@@ -660,6 +664,10 @@
 #
 # @decompress-threads: decompression thread count
 #
+# @throttle-trigger-threshold: The ratio of bytes_dirty_period and bytes_xfer_period
+#                              to trigger throttling. It is expressed as percentage.
+#                              The default value is 50. (Since 5.0)
+#
 # @cpu-throttle-initial: Initial percentage of time guest cpus are
 #                        throttled when migration auto-converge is activated.
 #                        The default value is 20. (Since 2.7)
@@ -752,6 +760,7 @@
             '*compress-threads': 'int',
             '*compress-wait-thread': 'bool',
             '*decompress-threads': 'int',
+            '*throttle-trigger-threshold': 'int',
             '*cpu-throttle-initial': 'int',
             '*cpu-throttle-increment': 'int',
             '*tls-creds': 'StrOrNull',
@@ -813,6 +822,10 @@
 #
 # @decompress-threads: decompression thread count
 #
+# @throttle-trigger-threshold: The ratio of bytes_dirty_period and bytes_xfer_period
+#                              to trigger throttling. It is expressed as percentage.
+#                              The default value is 50. (Since 5.0)
+#
 # @cpu-throttle-initial: Initial percentage of time guest cpus are
 #                        throttled when migration auto-converge is activated.
 #                        (Since 2.7)
@@ -905,6 +918,7 @@
             '*compress-threads': 'uint8',
             '*compress-wait-thread': 'bool',
             '*decompress-threads': 'uint8',
+            '*throttle-trigger-threshold': 'uint8',
             '*cpu-throttle-initial': 'uint8',
             '*cpu-throttle-increment': 'uint8',
             '*tls-creds': 'str',