Merge remote-tracking branch 'remotes/dgilbert/tags/pull-migration-20…

…180926a' into staging

Migration pull 2018-09-26

This supercedes Juan's pull from the 13th

# gpg: Signature made Wed 26 Sep 2018 18:07:30 BST
# 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-20180926a:
  migration/ram.c: Avoid taking address of fields in packed MultiFDInit_t struct
  migration: fix the compression code
  migration: fix QEMUFile leak
  tests/migration: Speed up the test on ppc64
  migration: cleanup in error paths in loadvm
  migration/postcopy: Clear have_listen_thread
  tests/migration: Add migration-test header file
  tests/migration: Support cross compilation in generating boot header file
  tests/migration: Convert x86 boot block compilation script into Makefile
  migration: use save_page_use_compression in flush_compressed_data
  migration: show the statistics of compression
  migration: do not flush_compressed_data at the end of iteration
  Add a hint message to loadvm and exits on failure
  migration: handle the error condition properly
  migration: fix calculating xbzrle_counters.cache_miss_rate
  migration/rdma: Fix uninitialised rdma_return_path

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

hmp.c

@@ -271,6 +271,19 @@ void hmp_info_migrate(Monitor *mon, const QDict *qdict)
                        info->xbzrle_cache->overflow);
     }
 
+    if (info->has_compression) {
+        monitor_printf(mon, "compression pages: %" PRIu64 " pages\n",
+                       info->compression->pages);
+        monitor_printf(mon, "compression busy: %" PRIu64 "\n",
+                       info->compression->busy);
+        monitor_printf(mon, "compression busy rate: %0.2f\n",
+                       info->compression->busy_rate);
+        monitor_printf(mon, "compressed size: %" PRIu64 "\n",
+                       info->compression->compressed_size);
+        monitor_printf(mon, "compression rate: %0.2f\n",
+                       info->compression->compression_rate);
+    }
+
     if (info->has_cpu_throttle_percentage) {
         monitor_printf(mon, "cpu throttle percentage: %" PRIu64 "\n",
                        info->cpu_throttle_percentage);

migration/migration.c

@@ -758,6 +758,18 @@ static void populate_ram_info(MigrationInfo *info, MigrationState *s)
         info->xbzrle_cache->overflow = xbzrle_counters.overflow;
     }
 
+    if (migrate_use_compression()) {
+        info->has_compression = true;
+        info->compression = g_malloc0(sizeof(*info->compression));
+        info->compression->pages = compression_counters.pages;
+        info->compression->busy = compression_counters.busy;
+        info->compression->busy_rate = compression_counters.busy_rate;
+        info->compression->compressed_size =
+                                    compression_counters.compressed_size;
+        info->compression->compression_rate =
+                                    compression_counters.compression_rate;
+    }
+
     if (cpu_throttle_active()) {
         info->has_cpu_throttle_percentage = true;
         info->cpu_throttle_percentage = cpu_throttle_get_percentage();
@@ -2268,7 +2280,10 @@ static void *source_return_path_thread(void *opaque)
              */
             if (postcopy_pause_return_path_thread(ms)) {
                 /* Reload rp, reset the rest */
-                rp = ms->rp_state.from_dst_file;
+                if (rp != ms->rp_state.from_dst_file) {
+                    qemu_fclose(rp);
+                    rp = ms->rp_state.from_dst_file;
+                }
                 ms->rp_state.error = false;
                 goto retry;
             }

migration/ram.c

@@ -301,10 +301,19 @@ struct RAMState {
     uint64_t num_dirty_pages_period;
     /* xbzrle misses since the beginning of the period */
     uint64_t xbzrle_cache_miss_prev;
-    /* number of iterations at the beginning of period */
-    uint64_t iterations_prev;
-    /* Iterations since start */
-    uint64_t iterations;
+
+    /* compression statistics since the beginning of the period */
+    /* amount of count that no free thread to compress data */
+    uint64_t compress_thread_busy_prev;
+    /* amount bytes after compression */
+    uint64_t compressed_size_prev;
+    /* amount of compressed pages */
+    uint64_t compress_pages_prev;
+
+    /* total handled target pages at the beginning of period */
+    uint64_t target_page_count_prev;
+    /* total handled target pages since start */
+    uint64_t target_page_count;
     /* number of dirty bits in the bitmap */
     uint64_t migration_dirty_pages;
     /* protects modification of the bitmap */
@@ -338,6 +347,8 @@ struct PageSearchStatus {
 };
 typedef struct PageSearchStatus PageSearchStatus;
 
+CompressionStats compression_counters;
+
 struct CompressParam {
     bool done;
     bool quit;
@@ -420,28 +431,14 @@ static void *do_data_compress(void *opaque)
     return NULL;
 }
 
-static inline void terminate_compression_threads(void)
-{
-    int idx, thread_count;
-
-    thread_count = migrate_compress_threads();
-
-    for (idx = 0; idx < thread_count; idx++) {
-        qemu_mutex_lock(&comp_param[idx].mutex);
-        comp_param[idx].quit = true;
-        qemu_cond_signal(&comp_param[idx].cond);
-        qemu_mutex_unlock(&comp_param[idx].mutex);
-    }
-}
-
 static void compress_threads_save_cleanup(void)
 {
     int i, thread_count;
 
-    if (!migrate_use_compression()) {
+    if (!migrate_use_compression() || !comp_param) {
         return;
     }
-    terminate_compression_threads();
+
     thread_count = migrate_compress_threads();
     for (i = 0; i < thread_count; i++) {
         /*
@@ -451,6 +448,12 @@ static void compress_threads_save_cleanup(void)
         if (!comp_param[i].file) {
             break;
         }
+
+        qemu_mutex_lock(&comp_param[i].mutex);
+        comp_param[i].quit = true;
+        qemu_cond_signal(&comp_param[i].cond);
+        qemu_mutex_unlock(&comp_param[i].mutex);
+
         qemu_thread_join(compress_threads + i);
         qemu_mutex_destroy(&comp_param[i].mutex);
         qemu_cond_destroy(&comp_param[i].cond);
@@ -648,8 +651,8 @@ static int multifd_recv_initial_packet(QIOChannel *c, Error **errp)
         return -1;
     }
 
-    be32_to_cpus(&msg.magic);
-    be32_to_cpus(&msg.version);
+    msg.magic = be32_to_cpu(msg.magic);
+    msg.version = be32_to_cpu(msg.version);
 
     if (msg.magic != MULTIFD_MAGIC) {
         error_setg(errp, "multifd: received packet magic %x "
@@ -734,15 +737,15 @@ static int multifd_recv_unfill_packet(MultiFDRecvParams *p, Error **errp)
     RAMBlock *block;
     int i;
 
-    be32_to_cpus(&packet->magic);
+    packet->magic = be32_to_cpu(packet->magic);
     if (packet->magic != MULTIFD_MAGIC) {
         error_setg(errp, "multifd: received packet "
                    "magic %x and expected magic %x",
                    packet->magic, MULTIFD_MAGIC);
         return -1;
     }
 
-    be32_to_cpus(&packet->version);
+    packet->version = be32_to_cpu(packet->version);
     if (packet->version != MULTIFD_VERSION) {
         error_setg(errp, "multifd: received packet "
                    "version %d and expected version %d",
@@ -752,7 +755,7 @@ static int multifd_recv_unfill_packet(MultiFDRecvParams *p, Error **errp)
 
     p->flags = be32_to_cpu(packet->flags);
 
-    be32_to_cpus(&packet->size);
+    packet->size = be32_to_cpu(packet->size);
     if (packet->size > migrate_multifd_page_count()) {
         error_setg(errp, "multifd: received packet "
                    "with size %d and expected maximum size %d",
@@ -1592,21 +1595,42 @@ uint64_t ram_pagesize_summary(void)
 
 static void migration_update_rates(RAMState *rs, int64_t end_time)
 {
-    uint64_t iter_count = rs->iterations - rs->iterations_prev;
+    uint64_t page_count = rs->target_page_count - rs->target_page_count_prev;
+    double compressed_size;
 
     /* calculate period counters */
     ram_counters.dirty_pages_rate = rs->num_dirty_pages_period * 1000
                 / (end_time - rs->time_last_bitmap_sync);
 
-    if (!iter_count) {
+    if (!page_count) {
         return;
     }
 
     if (migrate_use_xbzrle()) {
         xbzrle_counters.cache_miss_rate = (double)(xbzrle_counters.cache_miss -
-            rs->xbzrle_cache_miss_prev) / iter_count;
+            rs->xbzrle_cache_miss_prev) / page_count;
         rs->xbzrle_cache_miss_prev = xbzrle_counters.cache_miss;
     }
+
+    if (migrate_use_compression()) {
+        compression_counters.busy_rate = (double)(compression_counters.busy -
+            rs->compress_thread_busy_prev) / page_count;
+        rs->compress_thread_busy_prev = compression_counters.busy;
+
+        compressed_size = compression_counters.compressed_size -
+                          rs->compressed_size_prev;
+        if (compressed_size) {
+            double uncompressed_size = (compression_counters.pages -
+                                    rs->compress_pages_prev) * TARGET_PAGE_SIZE;
+
+            /* Compression-Ratio = Uncompressed-size / Compressed-size */
+            compression_counters.compression_rate =
+                                        uncompressed_size / compressed_size;
+
+            rs->compress_pages_prev = compression_counters.pages;
+            rs->compressed_size_prev = compression_counters.compressed_size;
+        }
+    }
 }
 
 static void migration_bitmap_sync(RAMState *rs)
@@ -1662,7 +1686,7 @@ static void migration_bitmap_sync(RAMState *rs)
 
         migration_update_rates(rs, end_time);
 
-        rs->iterations_prev = rs->iterations;
+        rs->target_page_count_prev = rs->target_page_count;
 
         /* reset period counters */
         rs->time_last_bitmap_sync = end_time;
@@ -1888,17 +1912,25 @@ static bool do_compress_ram_page(QEMUFile *f, z_stream *stream, RAMBlock *block,
 static void
 update_compress_thread_counts(const CompressParam *param, int bytes_xmit)
 {
+    ram_counters.transferred += bytes_xmit;
+
     if (param->zero_page) {
         ram_counters.duplicate++;
+        return;
     }
-    ram_counters.transferred += bytes_xmit;
+
+    /* 8 means a header with RAM_SAVE_FLAG_CONTINUE. */
+    compression_counters.compressed_size += bytes_xmit - 8;
+    compression_counters.pages++;
 }
 
+static bool save_page_use_compression(RAMState *rs);
+
 static void flush_compressed_data(RAMState *rs)
 {
     int idx, len, thread_count;
 
-    if (!migrate_use_compression()) {
+    if (!save_page_use_compression(rs)) {
         return;
     }
     thread_count = migrate_compress_threads();
@@ -1996,17 +2028,22 @@ static bool find_dirty_block(RAMState *rs, PageSearchStatus *pss, bool *again)
         pss->page = 0;
         pss->block = QLIST_NEXT_RCU(pss->block, next);
         if (!pss->block) {
+            /*
+             * If memory migration starts over, we will meet a dirtied page
+             * which may still exists in compression threads's ring, so we
+             * should flush the compressed data to make sure the new page
+             * is not overwritten by the old one in the destination.
+             *
+             * Also If xbzrle is on, stop using the data compression at this
+             * point. In theory, xbzrle can do better than compression.
+             */
+            flush_compressed_data(rs);
+
             /* Hit the end of the list */
             pss->block = QLIST_FIRST_RCU(&ram_list.blocks);
             /* Flag that we've looped */
             pss->complete_round = true;
             rs->ram_bulk_stage = false;
-            if (migrate_use_xbzrle()) {
-                /* If xbzrle is on, stop using the data compression at this
-                 * point. In theory, xbzrle can do better than compression.
-                 */
-                flush_compressed_data(rs);
-            }
         }
         /* Didn't find anything this time, but try again on the new block */
         *again = true;
@@ -2259,6 +2296,7 @@ static bool save_compress_page(RAMState *rs, RAMBlock *block, ram_addr_t offset)
         return true;
     }
 
+    compression_counters.busy++;
     return false;
 }
 
@@ -2372,7 +2410,8 @@ static int ram_save_host_page(RAMState *rs, PageSearchStatus *pss,
  *
  * Called within an RCU critical section.
  *
- * Returns the number of pages written where zero means no dirty pages
+ * Returns the number of pages written where zero means no dirty pages,
+ * or negative on error
  *
  * @rs: current RAM state
  * @last_stage: if we are at the completion stage
@@ -3196,7 +3235,13 @@ static int ram_save_iterate(QEMUFile *f, void *opaque)
             done = 1;
             break;
         }
-        rs->iterations++;
+
+        if (pages < 0) {
+            qemu_file_set_error(f, pages);
+            break;
+        }
+
+        rs->target_page_count += pages;
 
         /* we want to check in the 1st loop, just in case it was the 1st time
            and we had to sync the dirty bitmap.
@@ -3212,7 +3257,6 @@ static int ram_save_iterate(QEMUFile *f, void *opaque)
         }
         i++;
     }
-    flush_compressed_data(rs);
     rcu_read_unlock();
 
     /*
@@ -3238,7 +3282,7 @@ static int ram_save_iterate(QEMUFile *f, void *opaque)
 /**
  * ram_save_complete: function called to send the remaining amount of ram
  *
- * Returns zero to indicate success
+ * Returns zero to indicate success or negative on error
  *
  * Called with iothread lock
  *
@@ -3249,6 +3293,7 @@ static int ram_save_complete(QEMUFile *f, void *opaque)
 {
     RAMState **temp = opaque;
     RAMState *rs = *temp;
+    int ret = 0;
 
     rcu_read_lock();
 
@@ -3269,6 +3314,10 @@ static int ram_save_complete(QEMUFile *f, void *opaque)
         if (pages == 0) {
             break;
         }
+        if (pages < 0) {
+            ret = pages;
+            break;
+        }
     }
 
     flush_compressed_data(rs);
@@ -3280,7 +3329,7 @@ static int ram_save_complete(QEMUFile *f, void *opaque)
     qemu_put_be64(f, RAM_SAVE_FLAG_EOS);
     qemu_fflush(f);
 
-    return 0;
+    return ret;
 }
 
 static void ram_save_pending(QEMUFile *f, void *opaque, uint64_t max_size,

migration/ram.h

@@ -36,6 +36,7 @@
 
 extern MigrationStats ram_counters;
 extern XBZRLECacheStats xbzrle_counters;
+extern CompressionStats compression_counters;
 
 int xbzrle_cache_resize(int64_t new_size, Error **errp);
 uint64_t ram_bytes_remaining(void);

migration/rdma.c

@@ -4012,7 +4012,7 @@ static void rdma_accept_incoming_migration(void *opaque)
 void rdma_start_incoming_migration(const char *host_port, Error **errp)
 {
     int ret;
-    RDMAContext *rdma, *rdma_return_path;
+    RDMAContext *rdma, *rdma_return_path = NULL;
     Error *local_err = NULL;
 
     trace_rdma_start_incoming_migration();