[Qemu-devel] [RFC][PATCH 09/14 v4] run dump at the background

[Wen Congyang <wency@cn.fujitsu.com>]

The new monitor command dump may take long time to finish. So we need run it
at the background.

Signed-off-by: Wen Congyang <wency@cn.fujitsu.com>
---
 dump.c |  158 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++--------
 1 files changed, 139 insertions(+), 19 deletions(-)

diff --git a/dump.c b/dump.c
index ab29a4c..09ed96a 100644
--- a/dump.c
+++ b/dump.c
@@ -75,12 +75,20 @@ typedef struct DumpState {
     Monitor *mon;
     int fd;
     target_phys_addr_t memory_offset;
+    int64_t bandwidth;
+    RAMBlock *block;
+    ram_addr_t start;
+    target_phys_addr_t offset;
+    QEMUTimer *timer;
 } DumpState;
 
+#define DEFAULT_THROTTLE  (32 << 20)      /* Default dump speed throttling */
+
 static DumpState *dump_get_current(void)
 {
     static DumpState current_dump = {
         .state = DUMP_STATE_SETUP,
+        .bandwidth = DEFAULT_THROTTLE,
     };
 
     return &current_dump;
@@ -91,11 +99,21 @@ static int dump_cleanup(DumpState *s)
     int ret = 0;
 
     free_memory_mapping_list(&s->list);
+
     if (s->fd != -1) {
         close(s->fd);
         s->fd = -1;
     }
 
+    if (s->timer) {
+        qemu_del_timer(s->timer);
+        qemu_free_timer(s->timer);
+    }
+
+    if (s->mon) {
+        monitor_resume(s->mon);
+    }
+
     return ret;
 }
 
@@ -330,25 +348,40 @@ static int write_data(DumpState *s, void *buf, int length,
 }
 
 /* write the memroy to vmcore. 1 page per I/O. */
-static int write_memory(DumpState *s, RAMBlock *block,
-                        target_phys_addr_t *offset)
+static int write_memory(DumpState *s, RAMBlock *block, ram_addr_t start,
+                        target_phys_addr_t *offset, int64_t *size,
+                        int64_t deadline)
 {
     int i, ret;
+    int64_t writen_size = 0;
+    int64_t time;
 
-    for (i = 0; i < block->length / TARGET_PAGE_SIZE; i++) {
-        ret = write_data(s, block->host + i * TARGET_PAGE_SIZE,
+    for (i = 0; i < *size / TARGET_PAGE_SIZE; i++) {
+        ret = write_data(s, block->host + start + i * TARGET_PAGE_SIZE,
                          TARGET_PAGE_SIZE, offset);
         if (ret < 0) {
             return -1;
         }
+        writen_size += TARGET_PAGE_SIZE;
+        time = qemu_get_clock_ms(rt_clock);
+        if (time >= deadline) {
+            /* time out */
+            *size = writen_size;
+            return 1;
+        }
     }
 
-    if ((block->length % TARGET_PAGE_SIZE) != 0) {
-        ret = write_data(s, block->host + i * TARGET_PAGE_SIZE,
-                         block->length % TARGET_PAGE_SIZE, offset);
+    if ((*size % TARGET_PAGE_SIZE) != 0) {
+        ret = write_data(s, block->host + start + i * TARGET_PAGE_SIZE,
+                         *size % TARGET_PAGE_SIZE, offset);
         if (ret < 0) {
             return -1;
         }
+        time = qemu_get_clock_ms(rt_clock);
+        if (time >= deadline) {
+            /* time out */
+            return 1;
+        }
     }
 
     return 0;
@@ -383,6 +416,9 @@ static DumpState *dump_init(Monitor *mon, int fd)
     s->error = NULL;
     s->mon = mon;
     s->fd = fd;
+    s->block = QLIST_FIRST(&ram_list.blocks);
+    s->start = 0;
+    s->timer = NULL;
 
     /*
      * get dump info: endian, class and architecture.
@@ -425,6 +461,11 @@ static DumpState *dump_init(Monitor *mon, int fd)
         s->phdr_num += s->list.num;
     }
 
+    if (monitor_suspend(mon) != 0) {
+        monitor_printf(mon, "terminal does not allow synchronous "
+                       "dump, continuing detached\n");
+    }
+
     return s;
 }
 
@@ -482,6 +523,7 @@ static int dump_begin(DumpState *s)
     }
 
     s->memory_offset = offset;
+    s->offset = offset;
     return 0;
 }
 
@@ -509,38 +551,116 @@ static int dump_completed(DumpState *s)
     return 0;
 }
 
-/* write all memory to vmcore */
-static int dump_iterate(DumpState *s)
+/*
+ * write memory to vmcore.
+ *
+ * this function has three return values:
+ *  -1 : there was one error
+ *   0 : We haven't finished, caller have to go again
+ *   1 : We have finished, we can go to complete phase
+ */
+static int dump_iterate(DumpState *s, int64_t deadline)
 {
-    RAMBlock *block;
-    target_phys_addr_t offset = s->memory_offset;
+    RAMBlock *block = s->block;
+    target_phys_addr_t offset = s->offset;
+    int64_t size, remain, writen_size;
+    int64_t total = s->bandwidth / 10;
     int ret;
 
-    /* write all memory to vmcore */
-    QLIST_FOREACH(block, &ram_list.blocks, next) {
-        ret = write_memory(s, block, &offset);
+    if ((block->length - s->start) >= total) {
+        size = total;
+    } else {
+        size = block->length - s->start;
+    }
+
+    ret = write_memory(s, block, s->start, &offset, &size, deadline);
+    if (ret < 0) {
+        return -1;
+    }
+
+    if (size == total || ret == 1) {
+        if ((size + s->start) == block->length) {
+            s->block = QLIST_NEXT(block, next);
+            s->start = 0;
+        } else {
+            s->start += size;
+        }
+        goto end;
+    }
+
+    while (size < total) {
+        block = QLIST_NEXT(block, next);
+        if (!block) {
+            /* we have finished */
+            return 1;
+        }
+
+        remain = total - size;
+        if (remain >= block->length) {
+            writen_size = block->length;
+        } else {
+            writen_size = remain;
+        }
+        ret = write_memory(s, block, 0, &offset, &writen_size, deadline);
         if (ret < 0) {
             return -1;
+        } else if (ret == 1) {
+            break;
         }
+        size += writen_size;
+    }
+    if (writen_size == block->length) {
+        s->block = QLIST_NEXT(block, next);
+        s->start = 0;
+    } else {
+        s->block = block;
+        s->start = writen_size;
+    }
+
+end:
+    s->offset = offset;
+    if (!s->block) {
+        /* we have finished */
+        return 1;
     }
 
-    return dump_completed(s);
+    return 0;
 }
 
-static int create_vmcore(DumpState *s)
+static void dump_rate_tick(void *opaque)
 {
+    DumpState *s = opaque;
+    int64_t begin, end;
     int ret;
 
-    ret = dump_begin(s);
+    begin = qemu_get_clock_ms(rt_clock);
+    ret = dump_iterate(s, begin + 100);
     if (ret < 0) {
-        return -1;
+        return;
+    } else if (ret == 1) {
+        dump_completed(s);
+        return;
+    }
+    end = qemu_get_clock_ms(rt_clock);
+    if (end - begin >= 100) {
+        qemu_mod_timer(s->timer, end + 10);
+    } else {
+        qemu_mod_timer(s->timer, begin + 100);
     }
+}
 
-    ret = dump_iterate(s);
+static int create_vmcore(DumpState *s)
+{
+    int ret;
+
+    ret = dump_begin(s);
     if (ret < 0) {
         return -1;
     }
 
+    s->timer = qemu_new_timer_ms(rt_clock, dump_rate_tick, s);
+    qemu_mod_timer(s->timer, qemu_get_clock_ms(rt_clock) + 100);
+
     return 0;
 }
 
-- 
1.7.1