[Qemu-devel] [PATCH v16 10/14] migration: Create ram_save_multifd_page

[Juan Quintela <quintela@redhat.com>]

The function still don't use multifd, but we have simplified
ram_save_page, xbzrle and RDMA stuff is gone.  We have added a new
counter.

Signed-off-by: Juan Quintela <quintela@redhat.com>
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>

--
Add last_page parameter
Add commets for done and address
Remove multifd field, it is the same than normal pages
Merge next patch, now we send multiple pages at a time
Remove counter for multifd pages, it is identical to normal pages
Use iovec's instead of creating the equivalent.
Clear memory used by pages (dave)
Use g_new0(danp)
define MULTIFD_CONTINUE
now pages member is a pointer
Fix off-by-one in number of pages in one packet
Remove RAM_SAVE_FLAG_MULTIFD_PAGE
s/multifd_pages_t/MultiFDPages_t/
add comment explaining what it means
---
 migration/migration.c |   2 +-
 migration/ram.c       | 107 ++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 108 insertions(+), 1 deletion(-)

diff --git a/migration/migration.c b/migration/migration.c
index 2680ba2d47..d075c27886 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -2708,7 +2708,7 @@ static MigThrError migration_detect_error(MigrationState *s)
 /* How many bytes have we transferred since the beggining of the migration */
 static uint64_t migration_total_bytes(MigrationState *s)
 {
-    return qemu_ftell(s->to_dst_file);
+    return qemu_ftell(s->to_dst_file) + ram_counters.multifd_bytes;
 }
 
 static void migration_calculate_complete(MigrationState *s)
diff --git a/migration/ram.c b/migration/ram.c
index 77c66a4391..050e2f2000 100644
--- a/migration/ram.c
+++ b/migration/ram.c
@@ -55,6 +55,7 @@
 #include "sysemu/sysemu.h"
 #include "qemu/uuid.h"
 #include "savevm.h"
+#include "qemu/iov.h"
 
 /***********************************************************/
 /* ram save/restore */
@@ -811,8 +812,87 @@ struct {
     QemuSemaphore sem_sync;
     /* global number of generated multifd packets */
     uint64_t packet_num;
+    /* send channels ready */
+    QemuSemaphore channels_ready;
 } *multifd_send_state;
 
+/*
+ * How we use multifd_send_state->pages and channel->pages?
+ *
+ * We create a pages for each channel, and a main one.  Each time that
+ * we need to send a batch of pages we interchange the ones between
+ * multifd_send_state and the channel that is sending it.  There are
+ * two reasons for that:
+ *    - to not have to do so many mallocs during migration
+ *    - to make easier to know what to free at the end of migration
+ *
+ * This way we always know who is the owner of each "pages" struct,
+ * and we don't need any loocking.  It belongs to the migration thread
+ * or to the channel thread.  Switching is safe because the migration
+ * thread is using the channel mutex when changing it, and the channel
+ * have to had finish with its own, otherwise pending_job can't be
+ * false.
+ */
+
+static void multifd_send_pages(void)
+{
+    int i;
+    static int next_channel;
+    MultiFDSendParams *p = NULL; /* make happy gcc */
+    MultiFDPages_t *pages = multifd_send_state->pages;
+    uint64_t transferred;
+
+    qemu_sem_wait(&multifd_send_state->channels_ready);
+    for (i = next_channel;; i = (i + 1) % migrate_multifd_channels()) {
+        p = &multifd_send_state->params[i];
+
+        qemu_mutex_lock(&p->mutex);
+        if (!p->pending_job) {
+            p->pending_job++;
+            next_channel = (i + 1) % migrate_multifd_channels();
+            break;
+        }
+        qemu_mutex_unlock(&p->mutex);
+    }
+    p->pages->used = 0;
+
+    p->packet_num = multifd_send_state->packet_num++;
+    p->pages->block = NULL;
+    multifd_send_state->pages = p->pages;
+    p->pages = pages;
+    transferred = pages->used * TARGET_PAGE_SIZE + p->packet_len;
+    ram_counters.multifd_bytes += transferred;
+    ram_counters.transferred += transferred;;
+    qemu_mutex_unlock(&p->mutex);
+    qemu_sem_post(&p->sem);
+}
+
+static void multifd_queue_page(RAMBlock *block, ram_addr_t offset)
+{
+    MultiFDPages_t *pages = multifd_send_state->pages;
+
+    if (!pages->block) {
+        pages->block = block;
+    }
+
+    if (pages->block == block) {
+        pages->offset[pages->used] = offset;
+        pages->iov[pages->used].iov_base = block->host + offset;
+        pages->iov[pages->used].iov_len = TARGET_PAGE_SIZE;
+        pages->used++;
+
+        if (pages->used < pages->allocated) {
+            return;
+        }
+    }
+
+    multifd_send_pages();
+
+    if (pages->block != block) {
+        multifd_queue_page(block, offset);
+    }
+}
+
 static void multifd_send_terminate_threads(Error *err)
 {
     int i;
@@ -867,6 +947,7 @@ int multifd_save_cleanup(Error **errp)
         g_free(p->packet);
         p->packet = NULL;
     }
+    qemu_sem_destroy(&multifd_send_state->channels_ready);
     qemu_sem_destroy(&multifd_send_state->sem_sync);
     g_free(multifd_send_state->params);
     multifd_send_state->params = NULL;
@@ -884,12 +965,17 @@ static void multifd_send_sync_main(void)
     if (!migrate_use_multifd()) {
         return;
     }
+    if (multifd_send_state->pages->used) {
+        multifd_send_pages();
+    }
     for (i = 0; i < migrate_multifd_channels(); i++) {
         MultiFDSendParams *p = &multifd_send_state->params[i];
 
         trace_multifd_send_sync_main_signal(p->id);
 
         qemu_mutex_lock(&p->mutex);
+
+        p->packet_num = multifd_send_state->packet_num++;
         p->flags |= MULTIFD_FLAG_SYNC;
         p->pending_job++;
         qemu_mutex_unlock(&p->mutex);
@@ -944,6 +1030,7 @@ static void *multifd_send_thread(void *opaque)
             if (flags & MULTIFD_FLAG_SYNC) {
                 qemu_sem_post(&multifd_send_state->sem_sync);
             }
+            qemu_sem_post(&multifd_send_state->channels_ready);
         } else if (p->quit) {
             qemu_mutex_unlock(&p->mutex);
             break;
@@ -1003,6 +1090,7 @@ int multifd_save_setup(void)
     atomic_set(&multifd_send_state->count, 0);
     multifd_send_state->pages = multifd_pages_init(page_count);
     qemu_sem_init(&multifd_send_state->sem_sync, 0);
+    qemu_sem_init(&multifd_send_state->channels_ready, 0);
 
     for (i = 0; i < thread_count; i++) {
         MultiFDSendParams *p = &multifd_send_state->params[i];
@@ -1724,6 +1812,23 @@ static int ram_save_page(RAMState *rs, PageSearchStatus *pss, bool last_stage)
     return pages;
 }
 
+static int ram_save_multifd_page(RAMState *rs, RAMBlock *block,
+                                 ram_addr_t offset)
+{
+    uint8_t *p;
+
+    p = block->host + offset;
+
+    ram_counters.transferred += save_page_header(rs, rs->f, block,
+                                                 offset | RAM_SAVE_FLAG_PAGE);
+    multifd_queue_page(block, offset);
+    qemu_put_buffer(rs->f, p, TARGET_PAGE_SIZE);
+    ram_counters.transferred += TARGET_PAGE_SIZE;
+    ram_counters.normal++;
+
+    return 1;
+}
+
 static int do_compress_ram_page(QEMUFile *f, z_stream *stream, RAMBlock *block,
                                 ram_addr_t offset, uint8_t *source_buf)
 {
@@ -2129,6 +2234,8 @@ static int ram_save_target_page(RAMState *rs, PageSearchStatus *pss,
      */
     if (block == rs->last_sent_block && save_page_use_compression(rs)) {
         return compress_page_with_multi_thread(rs, block, offset);
+    } else if (migrate_use_multifd()) {
+        return ram_save_multifd_page(rs, block, offset);
     }
 
     return ram_save_page(rs, pss, last_stage);
-- 
2.17.1