[PATCH 21/30] migration: Use atomic ops properly for page accountings

From: Juan Quintela <quintela@redhat.com>
To: qemu-devel@nongnu.org
Cc: "Paolo Bonzini" <pbonzini@redhat.com>,
	"David Hildenbrand" <david@redhat.com>,
	"Laurent Vivier" <laurent@vivier.eu>,
	"Stefan Hajnoczi" <stefanha@redhat.com>,
	"Fam Zheng" <fam@euphon.net>,
	qemu-block@nongnu.org,
	"Dr. David Alan Gilbert" <dgilbert@redhat.com>,
	"Thomas Huth" <thuth@redhat.com>,
	"Philippe Mathieu-Daudé" <philmd@linaro.org>,
	qemu-trivial@nongnu.org, "Michael Tokarev" <mjt@tls.msk.ru>,
	"Daniel P. Berrangé" <berrange@redhat.com>,
	"Marc-André Lureau" <marcandre.lureau@redhat.com>,
	"Peter Xu" <peterx@redhat.com>,
	"Juan Quintela" <quintela@redhat.com>
Subject: [PATCH 21/30] migration: Use atomic ops properly for page accountings
Date: Tue, 15 Nov 2022 13:12:17 +0100	[thread overview]
Message-ID: <20221115121226.26609-22-quintela@redhat.com> (raw)
In-Reply-To: <20221115121226.26609-1-quintela@redhat.com>

From: Peter Xu <peterx@redhat.com>

To prepare for thread-safety on page accountings, at least below counters
need to be accessed only atomically, they are:

        ram_counters.transferred
        ram_counters.duplicate
        ram_counters.normal
        ram_counters.postcopy_bytes

There are a lot of other counters but they won't be accessed outside
migration thread, then they're still safe to be accessed without atomic
ops.

Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
---
 migration/ram.h       | 20 ++++++++++++++++++++
 migration/migration.c | 10 +++++-----
 migration/multifd.c   |  4 ++--
 migration/ram.c       | 40 ++++++++++++++++++++++++----------------
 4 files changed, 51 insertions(+), 23 deletions(-)

diff --git a/migration/ram.h b/migration/ram.h
index 038d52f49f..81cbb0947c 100644
--- a/migration/ram.h
+++ b/migration/ram.h
@@ -32,7 +32,27 @@
 #include "qapi/qapi-types-migration.h"
 #include "exec/cpu-common.h"
 #include "io/channel.h"
+#include "qemu/stats64.h"
 
+/*
+ * These are the migration statistic counters that need to be updated using
+ * atomic ops (can be accessed by more than one thread).  Here since we
+ * cannot modify MigrationStats directly to use Stat64 as it was defined in
+ * the QAPI scheme, we define an internal structure to hold them, and we
+ * propagate the real values when QMP queries happen.
+ *
+ * IOW, the corresponding fields within ram_counters on these specific
+ * fields will be always zero and not being used at all; they're just
+ * placeholders to make it QAPI-compatible.
+ */
+typedef struct {
+    Stat64 transferred;
+    Stat64 duplicate;
+    Stat64 normal;
+    Stat64 postcopy_bytes;
+} MigrationAtomicStats;
+
+extern MigrationAtomicStats ram_atomic_counters;
 extern MigrationStats ram_counters;
 extern XBZRLECacheStats xbzrle_counters;
 extern CompressionStats compression_counters;
diff --git a/migration/migration.c b/migration/migration.c
index 9fbed8819a..1f95877fb4 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -1069,13 +1069,13 @@ static void populate_ram_info(MigrationInfo *info, MigrationState *s)
 
     info->has_ram = true;
     info->ram = g_malloc0(sizeof(*info->ram));
-    info->ram->transferred = ram_counters.transferred;
+    info->ram->transferred = stat64_get(&ram_atomic_counters.transferred);
     info->ram->total = ram_bytes_total();
-    info->ram->duplicate = ram_counters.duplicate;
+    info->ram->duplicate = stat64_get(&ram_atomic_counters.duplicate);
     /* legacy value.  It is not used anymore */
     info->ram->skipped = 0;
-    info->ram->normal = ram_counters.normal;
-    info->ram->normal_bytes = ram_counters.normal * page_size;
+    info->ram->normal = stat64_get(&ram_atomic_counters.normal);
+    info->ram->normal_bytes = info->ram->normal * page_size;
     info->ram->mbps = s->mbps;
     info->ram->dirty_sync_count = ram_counters.dirty_sync_count;
     info->ram->dirty_sync_missed_zero_copy =
@@ -1086,7 +1086,7 @@ static void populate_ram_info(MigrationInfo *info, MigrationState *s)
     info->ram->pages_per_second = s->pages_per_second;
     info->ram->precopy_bytes = ram_counters.precopy_bytes;
     info->ram->downtime_bytes = ram_counters.downtime_bytes;
-    info->ram->postcopy_bytes = ram_counters.postcopy_bytes;
+    info->ram->postcopy_bytes = stat64_get(&ram_atomic_counters.postcopy_bytes);
 
     if (migrate_use_xbzrle()) {
         info->has_xbzrle_cache = true;
diff --git a/migration/multifd.c b/migration/multifd.c
index c40d98ad5c..7d3aec9a52 100644
--- a/migration/multifd.c
+++ b/migration/multifd.c
@@ -432,7 +432,7 @@ static int multifd_send_pages(QEMUFile *f)
     transferred = ((uint64_t) pages->num) * p->page_size + p->packet_len;
     qemu_file_acct_rate_limit(f, transferred);
     ram_counters.multifd_bytes += transferred;
-    ram_counters.transferred += transferred;
+    stat64_add(&ram_atomic_counters.transferred, transferred);
     qemu_mutex_unlock(&p->mutex);
     qemu_sem_post(&p->sem);
 
@@ -624,7 +624,7 @@ int multifd_send_sync_main(QEMUFile *f)
         p->pending_job++;
         qemu_file_acct_rate_limit(f, p->packet_len);
         ram_counters.multifd_bytes += p->packet_len;
-        ram_counters.transferred += p->packet_len;
+        stat64_add(&ram_atomic_counters.transferred, p->packet_len);
         qemu_mutex_unlock(&p->mutex);
         qemu_sem_post(&p->sem);
 
diff --git a/migration/ram.c b/migration/ram.c
index 6428138194..25fd3cf7dc 100644
--- a/migration/ram.c
+++ b/migration/ram.c
@@ -453,18 +453,25 @@ uint64_t ram_bytes_remaining(void)
                        0;
 }
 
+/*
+ * NOTE: not all stats in ram_counters are used in reality.  See comments
+ * for struct MigrationAtomicStats.  The ultimate result of ram migration
+ * counters will be a merged version with both ram_counters and the atomic
+ * fields in ram_atomic_counters.
+ */
 MigrationStats ram_counters;
+MigrationAtomicStats ram_atomic_counters;
 
 void ram_transferred_add(uint64_t bytes)
 {
     if (runstate_is_running()) {
         ram_counters.precopy_bytes += bytes;
     } else if (migration_in_postcopy()) {
-        ram_counters.postcopy_bytes += bytes;
+        stat64_add(&ram_atomic_counters.postcopy_bytes, bytes);
     } else {
         ram_counters.downtime_bytes += bytes;
     }
-    ram_counters.transferred += bytes;
+    stat64_add(&ram_atomic_counters.transferred, bytes);
 }
 
 void dirty_sync_missed_zero_copy(void)
@@ -753,7 +760,7 @@ void mig_throttle_counter_reset(void)
 
     rs->time_last_bitmap_sync = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
     rs->num_dirty_pages_period = 0;
-    rs->bytes_xfer_prev = ram_counters.transferred;
+    rs->bytes_xfer_prev = stat64_get(&ram_atomic_counters.transferred);
 }
 
 /**
@@ -1113,8 +1120,9 @@ uint64_t ram_pagesize_summary(void)
 
 uint64_t ram_get_total_transferred_pages(void)
 {
-    return  ram_counters.normal + ram_counters.duplicate +
-                compression_counters.pages + xbzrle_counters.pages;
+    return  stat64_get(&ram_atomic_counters.normal) +
+        stat64_get(&ram_atomic_counters.duplicate) +
+        compression_counters.pages + xbzrle_counters.pages;
 }
 
 static void migration_update_rates(RAMState *rs, int64_t end_time)
@@ -1173,8 +1181,8 @@ 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_xfer_period =
+        stat64_get(&ram_atomic_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;
 
@@ -1237,7 +1245,7 @@ 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 = ram_counters.transferred;
+        rs->bytes_xfer_prev = stat64_get(&ram_atomic_counters.transferred);
     }
     if (migrate_use_events()) {
         qapi_event_send_migration_pass(ram_counters.dirty_sync_count);
@@ -1313,7 +1321,7 @@ static int save_zero_page(RAMState *rs, RAMBlock *block, ram_addr_t offset)
     int len = save_zero_page_to_file(rs, rs->f, block, offset);
 
     if (len) {
-        ram_counters.duplicate++;
+        stat64_add(&ram_atomic_counters.duplicate, 1);
         ram_transferred_add(len);
         return 1;
     }
@@ -1350,9 +1358,9 @@ static bool control_save_page(RAMState *rs, RAMBlock *block, ram_addr_t offset,
     }
 
     if (bytes_xmit > 0) {
-        ram_counters.normal++;
+        stat64_add(&ram_atomic_counters.normal, 1);
     } else if (bytes_xmit == 0) {
-        ram_counters.duplicate++;
+        stat64_add(&ram_atomic_counters.duplicate, 1);
     }
 
     return true;
@@ -1382,7 +1390,7 @@ static int save_normal_page(RAMState *rs, RAMBlock *block, ram_addr_t offset,
         qemu_put_buffer(rs->f, buf, TARGET_PAGE_SIZE);
     }
     ram_transferred_add(TARGET_PAGE_SIZE);
-    ram_counters.normal++;
+    stat64_add(&ram_atomic_counters.normal, 1);
     return 1;
 }
 
@@ -1438,7 +1446,7 @@ static int ram_save_multifd_page(RAMState *rs, RAMBlock *block,
     if (multifd_queue_page(rs->f, block, offset) < 0) {
         return -1;
     }
-    ram_counters.normal++;
+    stat64_add(&ram_atomic_counters.normal, 1);
 
     return 1;
 }
@@ -1476,7 +1484,7 @@ update_compress_thread_counts(const CompressParam *param, int bytes_xmit)
     ram_transferred_add(bytes_xmit);
 
     if (param->zero_page) {
-        ram_counters.duplicate++;
+        stat64_add(&ram_atomic_counters.duplicate, 1);
         return;
     }
 
@@ -2651,9 +2659,9 @@ void acct_update_position(QEMUFile *f, size_t size, bool zero)
     uint64_t pages = size / TARGET_PAGE_SIZE;
 
     if (zero) {
-        ram_counters.duplicate += pages;
+        stat64_add(&ram_atomic_counters.duplicate, pages);
     } else {
-        ram_counters.normal += pages;
+        stat64_add(&ram_atomic_counters.normal, pages);
         ram_transferred_add(size);
         qemu_file_credit_transfer(f, size);
     }
-- 
2.38.1


