All of lore.kernel.org
 help / color / mirror / Atom feed
* [RFC PATCH v5 0/4] Separate thread for VM migration
@ 2011-08-24  3:12 ` Umesh Deshpande
  0 siblings, 0 replies; 20+ messages in thread
From: Umesh Deshpande @ 2011-08-24  3:12 UTC (permalink / raw)
  To: kvm, qemu-devel; +Cc: pbonzini, quintela, mtosatti, Umesh Deshpande

Following patch series deals with VCPU and iothread starvation during the
migration of a guest. Currently the iothread is responsible for performing the
guest migration. It holds qemu_mutex during the migration and doesn't allow VCPU
to enter the qemu mode and delays its return to the guest. The guest migration,
executed as an iohandler also delays the execution of other iohandlers.
In the following patch series,

The migration has been moved to a separate thread to
reduce the qemu_mutex contention and iohandler starvation.

Umesh Deshpande (4):
  MRU ram block list
  migration thread mutex
  separate migration bitmap
  separate migration thread

 arch_init.c         |   38 ++++++++++++----
 buffered_file.c     |   75 +++++++++++++++++--------------
 cpu-all.h           |   42 +++++++++++++++++
 exec.c              |   97 ++++++++++++++++++++++++++++++++++++++--
 migration.c         |  122 +++++++++++++++++++++++++++++---------------------
 migration.h         |    9 ++++
 qemu-common.h       |    2 +
 qemu-thread-posix.c |   10 ++++
 qemu-thread.h       |    1 +
 savevm.c            |    5 --
 10 files changed, 297 insertions(+), 104 deletions(-)

-- 
1.7.4.1


^ permalink raw reply	[flat|nested] 20+ messages in thread

* [Qemu-devel] [RFC PATCH v5 0/4] Separate thread for VM migration
@ 2011-08-24  3:12 ` Umesh Deshpande
  0 siblings, 0 replies; 20+ messages in thread
From: Umesh Deshpande @ 2011-08-24  3:12 UTC (permalink / raw)
  To: kvm, qemu-devel; +Cc: pbonzini, mtosatti, Umesh Deshpande, quintela

Following patch series deals with VCPU and iothread starvation during the
migration of a guest. Currently the iothread is responsible for performing the
guest migration. It holds qemu_mutex during the migration and doesn't allow VCPU
to enter the qemu mode and delays its return to the guest. The guest migration,
executed as an iohandler also delays the execution of other iohandlers.
In the following patch series,

The migration has been moved to a separate thread to
reduce the qemu_mutex contention and iohandler starvation.

Umesh Deshpande (4):
  MRU ram block list
  migration thread mutex
  separate migration bitmap
  separate migration thread

 arch_init.c         |   38 ++++++++++++----
 buffered_file.c     |   75 +++++++++++++++++--------------
 cpu-all.h           |   42 +++++++++++++++++
 exec.c              |   97 ++++++++++++++++++++++++++++++++++++++--
 migration.c         |  122 +++++++++++++++++++++++++++++---------------------
 migration.h         |    9 ++++
 qemu-common.h       |    2 +
 qemu-thread-posix.c |   10 ++++
 qemu-thread.h       |    1 +
 savevm.c            |    5 --
 10 files changed, 297 insertions(+), 104 deletions(-)

-- 
1.7.4.1

^ permalink raw reply	[flat|nested] 20+ messages in thread

* [RFC PATCH v5 1/4] MRU ram list
  2011-08-24  3:12 ` [Qemu-devel] " Umesh Deshpande
@ 2011-08-24  3:12   ` Umesh Deshpande
  -1 siblings, 0 replies; 20+ messages in thread
From: Umesh Deshpande @ 2011-08-24  3:12 UTC (permalink / raw)
  To: kvm, qemu-devel; +Cc: pbonzini, quintela, mtosatti, Umesh Deshpande

This patch creates a new list of RAM blocks in MRU order. So that separate
locking rules can be applied to the regular RAM block list and the MRU list.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 cpu-all.h |    2 ++
 exec.c    |   17 ++++++++++++-----
 2 files changed, 14 insertions(+), 5 deletions(-)

diff --git a/cpu-all.h b/cpu-all.h
index e839100..6b217a2 100644
--- a/cpu-all.h
+++ b/cpu-all.h
@@ -925,6 +925,7 @@ typedef struct RAMBlock {
     uint32_t flags;
     char idstr[256];
     QLIST_ENTRY(RAMBlock) next;
+    QLIST_ENTRY(RAMBlock) next_mru;
 #if defined(__linux__) && !defined(TARGET_S390X)
     int fd;
 #endif
@@ -933,6 +934,7 @@ typedef struct RAMBlock {
 typedef struct RAMList {
     uint8_t *phys_dirty;
     QLIST_HEAD(ram, RAMBlock) blocks;
+    QLIST_HEAD(, RAMBlock) blocks_mru;
 } RAMList;
 extern RAMList ram_list;
 
diff --git a/exec.c b/exec.c
index 0e2ce57..c5c247c 100644
--- a/exec.c
+++ b/exec.c
@@ -113,7 +113,11 @@ static uint8_t *code_gen_ptr;
 int phys_ram_fd;
 static int in_migration;
 
-RAMList ram_list = { .blocks = QLIST_HEAD_INITIALIZER(ram_list) };
+RAMList ram_list = {
+    .blocks = QLIST_HEAD_INITIALIZER(ram_list),
+    .blocks_mru = QLIST_HEAD_INITIALIZER(ram_list.blocks_mru)
+};
+
 #endif
 
 CPUState *first_cpu;
@@ -2973,6 +2977,7 @@ ram_addr_t qemu_ram_alloc_from_ptr(DeviceState *dev, const char *name,
     new_block->length = size;
 
     QLIST_INSERT_HEAD(&ram_list.blocks, new_block, next);
+    QLIST_INSERT_HEAD(&ram_list.blocks_mru, new_block, next_mru);
 
     ram_list.phys_dirty = qemu_realloc(ram_list.phys_dirty,
                                        last_ram_offset() >> TARGET_PAGE_BITS);
@@ -2997,6 +3002,7 @@ void qemu_ram_free_from_ptr(ram_addr_t addr)
     QLIST_FOREACH(block, &ram_list.blocks, next) {
         if (addr == block->offset) {
             QLIST_REMOVE(block, next);
+            QLIST_REMOVE(block, next_mru);
             qemu_free(block);
             return;
         }
@@ -3010,6 +3016,7 @@ void qemu_ram_free(ram_addr_t addr)
     QLIST_FOREACH(block, &ram_list.blocks, next) {
         if (addr == block->offset) {
             QLIST_REMOVE(block, next);
+            QLIST_REMOVE(block, next_mru);
             if (block->flags & RAM_PREALLOC_MASK) {
                 ;
             } else if (mem_path) {
@@ -3113,12 +3120,12 @@ void *qemu_get_ram_ptr(ram_addr_t addr)
 {
     RAMBlock *block;
 
-    QLIST_FOREACH(block, &ram_list.blocks, next) {
+    QLIST_FOREACH(block, &ram_list.blocks_mru, next_mru) {
         if (addr - block->offset < block->length) {
             /* Move this entry to to start of the list.  */
             if (block != QLIST_FIRST(&ram_list.blocks)) {
-                QLIST_REMOVE(block, next);
-                QLIST_INSERT_HEAD(&ram_list.blocks, block, next);
+                QLIST_REMOVE(block, next_mru);
+                QLIST_INSERT_HEAD(&ram_list.blocks_mru, block, next_mru);
             }
             if (xen_mapcache_enabled()) {
                 /* We need to check if the requested address is in the RAM
@@ -3211,7 +3218,7 @@ int qemu_ram_addr_from_host(void *ptr, ram_addr_t *ram_addr)
         return 0;
     }
 
-    QLIST_FOREACH(block, &ram_list.blocks, next) {
+    QLIST_FOREACH(block, &ram_list.blocks_mru, next_mru) {
         /* This case append when the block is not mapped. */
         if (block->host == NULL) {
             continue;
-- 
1.7.4.1


^ permalink raw reply related	[flat|nested] 20+ messages in thread

* [Qemu-devel] [RFC PATCH v5 1/4] MRU ram list
@ 2011-08-24  3:12   ` Umesh Deshpande
  0 siblings, 0 replies; 20+ messages in thread
From: Umesh Deshpande @ 2011-08-24  3:12 UTC (permalink / raw)
  To: kvm, qemu-devel; +Cc: pbonzini, mtosatti, Umesh Deshpande, quintela

This patch creates a new list of RAM blocks in MRU order. So that separate
locking rules can be applied to the regular RAM block list and the MRU list.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 cpu-all.h |    2 ++
 exec.c    |   17 ++++++++++++-----
 2 files changed, 14 insertions(+), 5 deletions(-)

diff --git a/cpu-all.h b/cpu-all.h
index e839100..6b217a2 100644
--- a/cpu-all.h
+++ b/cpu-all.h
@@ -925,6 +925,7 @@ typedef struct RAMBlock {
     uint32_t flags;
     char idstr[256];
     QLIST_ENTRY(RAMBlock) next;
+    QLIST_ENTRY(RAMBlock) next_mru;
 #if defined(__linux__) && !defined(TARGET_S390X)
     int fd;
 #endif
@@ -933,6 +934,7 @@ typedef struct RAMBlock {
 typedef struct RAMList {
     uint8_t *phys_dirty;
     QLIST_HEAD(ram, RAMBlock) blocks;
+    QLIST_HEAD(, RAMBlock) blocks_mru;
 } RAMList;
 extern RAMList ram_list;
 
diff --git a/exec.c b/exec.c
index 0e2ce57..c5c247c 100644
--- a/exec.c
+++ b/exec.c
@@ -113,7 +113,11 @@ static uint8_t *code_gen_ptr;
 int phys_ram_fd;
 static int in_migration;
 
-RAMList ram_list = { .blocks = QLIST_HEAD_INITIALIZER(ram_list) };
+RAMList ram_list = {
+    .blocks = QLIST_HEAD_INITIALIZER(ram_list),
+    .blocks_mru = QLIST_HEAD_INITIALIZER(ram_list.blocks_mru)
+};
+
 #endif
 
 CPUState *first_cpu;
@@ -2973,6 +2977,7 @@ ram_addr_t qemu_ram_alloc_from_ptr(DeviceState *dev, const char *name,
     new_block->length = size;
 
     QLIST_INSERT_HEAD(&ram_list.blocks, new_block, next);
+    QLIST_INSERT_HEAD(&ram_list.blocks_mru, new_block, next_mru);
 
     ram_list.phys_dirty = qemu_realloc(ram_list.phys_dirty,
                                        last_ram_offset() >> TARGET_PAGE_BITS);
@@ -2997,6 +3002,7 @@ void qemu_ram_free_from_ptr(ram_addr_t addr)
     QLIST_FOREACH(block, &ram_list.blocks, next) {
         if (addr == block->offset) {
             QLIST_REMOVE(block, next);
+            QLIST_REMOVE(block, next_mru);
             qemu_free(block);
             return;
         }
@@ -3010,6 +3016,7 @@ void qemu_ram_free(ram_addr_t addr)
     QLIST_FOREACH(block, &ram_list.blocks, next) {
         if (addr == block->offset) {
             QLIST_REMOVE(block, next);
+            QLIST_REMOVE(block, next_mru);
             if (block->flags & RAM_PREALLOC_MASK) {
                 ;
             } else if (mem_path) {
@@ -3113,12 +3120,12 @@ void *qemu_get_ram_ptr(ram_addr_t addr)
 {
     RAMBlock *block;
 
-    QLIST_FOREACH(block, &ram_list.blocks, next) {
+    QLIST_FOREACH(block, &ram_list.blocks_mru, next_mru) {
         if (addr - block->offset < block->length) {
             /* Move this entry to to start of the list.  */
             if (block != QLIST_FIRST(&ram_list.blocks)) {
-                QLIST_REMOVE(block, next);
-                QLIST_INSERT_HEAD(&ram_list.blocks, block, next);
+                QLIST_REMOVE(block, next_mru);
+                QLIST_INSERT_HEAD(&ram_list.blocks_mru, block, next_mru);
             }
             if (xen_mapcache_enabled()) {
                 /* We need to check if the requested address is in the RAM
@@ -3211,7 +3218,7 @@ int qemu_ram_addr_from_host(void *ptr, ram_addr_t *ram_addr)
         return 0;
     }
 
-    QLIST_FOREACH(block, &ram_list.blocks, next) {
+    QLIST_FOREACH(block, &ram_list.blocks_mru, next_mru) {
         /* This case append when the block is not mapped. */
         if (block->host == NULL) {
             continue;
-- 
1.7.4.1

^ permalink raw reply related	[flat|nested] 20+ messages in thread

* [RFC PATCH v5 2/4] Migration thread mutex
  2011-08-24  3:12 ` [Qemu-devel] " Umesh Deshpande
@ 2011-08-24  3:12   ` Umesh Deshpande
  -1 siblings, 0 replies; 20+ messages in thread
From: Umesh Deshpande @ 2011-08-24  3:12 UTC (permalink / raw)
  To: kvm, qemu-devel; +Cc: pbonzini, quintela, mtosatti, Umesh Deshpande

ramlist mutex is implemented to protect the RAMBlock list traversal in the
migration thread from their addition/removal from the iothread.

Note: Combination of iothread mutex and migration thread mutex works as a
rw-lock. Both mutexes are acquired while modifying the ram_list members or RAM
block list.

Signed-off-by: Umesh Deshpande <udeshpan@redhat.com>
---
 arch_init.c   |   21 +++++++++++++++++++++
 cpu-all.h     |    3 +++
 exec.c        |   23 +++++++++++++++++++++++
 qemu-common.h |    2 ++
 4 files changed, 49 insertions(+), 0 deletions(-)

diff --git a/arch_init.c b/arch_init.c
index 484b39d..9d02270 100644
--- a/arch_init.c
+++ b/arch_init.c
@@ -109,6 +109,7 @@ static int is_dup_page(uint8_t *page, uint8_t ch)
 
 static RAMBlock *last_block;
 static ram_addr_t last_offset;
+static uint64_t last_version;
 
 static int ram_save_block(QEMUFile *f)
 {
@@ -170,6 +171,7 @@ static int ram_save_block(QEMUFile *f)
 
     last_block = block;
     last_offset = offset;
+    last_version = ram_list.version;
 
     return bytes_sent;
 }
@@ -270,6 +272,7 @@ int ram_save_live(Monitor *mon, QEMUFile *f, int stage, void *opaque)
         bytes_transferred = 0;
         last_block = NULL;
         last_offset = 0;
+        last_version = ram_list.version = 0;
         sort_ram_list();
 
         /* Make sure all dirty bits are set */
@@ -298,6 +301,17 @@ int ram_save_live(Monitor *mon, QEMUFile *f, int stage, void *opaque)
     bytes_transferred_last = bytes_transferred;
     bwidth = qemu_get_clock_ns(rt_clock);
 
+    if (stage != 3) {
+        qemu_mutex_lock_migthread();
+        qemu_mutex_unlock_iothread();
+    }
+
+    if (ram_list.version != last_version) {
+        /* RAM block added or removed */
+        last_block = NULL;
+        last_offset = 0;
+    }
+
     while (!qemu_file_rate_limit(f)) {
         int bytes_sent;
 
@@ -308,6 +322,13 @@ int ram_save_live(Monitor *mon, QEMUFile *f, int stage, void *opaque)
         }
     }
 
+    if (stage != 3) {
+        qemu_mutex_unlock_migthread();
+        qemu_mutex_lock_iothread();
+        /* Lock ordering : iothread mutex is always acquired outside migthread
+         * mutex critical section to avoid deadlock */
+    }
+
     bwidth = qemu_get_clock_ns(rt_clock) - bwidth;
     bwidth = (bytes_transferred - bytes_transferred_last) / bwidth;
 
diff --git a/cpu-all.h b/cpu-all.h
index 6b217a2..b85483f 100644
--- a/cpu-all.h
+++ b/cpu-all.h
@@ -21,6 +21,7 @@
 
 #include "qemu-common.h"
 #include "cpu-common.h"
+#include "qemu-thread.h"
 
 /* some important defines:
  *
@@ -932,7 +933,9 @@ typedef struct RAMBlock {
 } RAMBlock;
 
 typedef struct RAMList {
+    QemuMutex mutex;    /* Protects RAM block list */
     uint8_t *phys_dirty;
+    uint32_t version;   /* To detect ram block addition/removal */
     QLIST_HEAD(ram, RAMBlock) blocks;
     QLIST_HEAD(, RAMBlock) blocks_mru;
 } RAMList;
diff --git a/exec.c b/exec.c
index c5c247c..7627483 100644
--- a/exec.c
+++ b/exec.c
@@ -582,6 +582,7 @@ void cpu_exec_init_all(unsigned long tb_size)
     code_gen_alloc(tb_size);
     code_gen_ptr = code_gen_buffer;
     page_init();
+    qemu_mutex_init(&ram_list.mutex);
 #if !defined(CONFIG_USER_ONLY)
     io_mem_init();
 #endif
@@ -2802,6 +2803,16 @@ static long gethugepagesize(const char *path)
     return fs.f_bsize;
 }
 
+void qemu_mutex_lock_migthread(void)
+{
+    qemu_mutex_lock(&ram_list.mutex);
+}
+
+void qemu_mutex_unlock_migthread(void)
+{
+    qemu_mutex_unlock(&ram_list.mutex);
+}
+
 static void *file_ram_alloc(RAMBlock *block,
                             ram_addr_t memory,
                             const char *path)
@@ -2976,14 +2987,20 @@ ram_addr_t qemu_ram_alloc_from_ptr(DeviceState *dev, const char *name,
     }
     new_block->length = size;
 
+    qemu_mutex_lock_migthread();
+
     QLIST_INSERT_HEAD(&ram_list.blocks, new_block, next);
     QLIST_INSERT_HEAD(&ram_list.blocks_mru, new_block, next_mru);
 
+    ram_list.version++;
+
     ram_list.phys_dirty = qemu_realloc(ram_list.phys_dirty,
                                        last_ram_offset() >> TARGET_PAGE_BITS);
     memset(ram_list.phys_dirty + (new_block->offset >> TARGET_PAGE_BITS),
            0xff, size >> TARGET_PAGE_BITS);
 
+    qemu_mutex_unlock_migthread();
+
     if (kvm_enabled())
         kvm_setup_guest_memory(new_block->host, size);
 
@@ -3001,8 +3018,11 @@ void qemu_ram_free_from_ptr(ram_addr_t addr)
 
     QLIST_FOREACH(block, &ram_list.blocks, next) {
         if (addr == block->offset) {
+            qemu_mutex_lock_migthread();
             QLIST_REMOVE(block, next);
             QLIST_REMOVE(block, next_mru);
+            ram_list.version++;
+            qemu_mutex_unlock_migthread();
             qemu_free(block);
             return;
         }
@@ -3015,8 +3035,11 @@ void qemu_ram_free(ram_addr_t addr)
 
     QLIST_FOREACH(block, &ram_list.blocks, next) {
         if (addr == block->offset) {
+            qemu_mutex_lock_migthread();
             QLIST_REMOVE(block, next);
             QLIST_REMOVE(block, next_mru);
+            ram_list.version++;
+            qemu_mutex_unlock_migthread();
             if (block->flags & RAM_PREALLOC_MASK) {
                 ;
             } else if (mem_path) {
diff --git a/qemu-common.h b/qemu-common.h
index abd7a75..7dabfe9 100644
--- a/qemu-common.h
+++ b/qemu-common.h
@@ -212,6 +212,8 @@ char *qemu_strndup(const char *str, size_t size);
 
 void qemu_mutex_lock_iothread(void);
 void qemu_mutex_unlock_iothread(void);
+void qemu_mutex_lock_migthread(void);
+void qemu_mutex_unlock_migthread(void);
 
 int qemu_open(const char *name, int flags, ...);
 ssize_t qemu_write_full(int fd, const void *buf, size_t count)
-- 
1.7.4.1


^ permalink raw reply related	[flat|nested] 20+ messages in thread

* [Qemu-devel] [RFC PATCH v5 2/4] Migration thread mutex
@ 2011-08-24  3:12   ` Umesh Deshpande
  0 siblings, 0 replies; 20+ messages in thread
From: Umesh Deshpande @ 2011-08-24  3:12 UTC (permalink / raw)
  To: kvm, qemu-devel; +Cc: pbonzini, mtosatti, Umesh Deshpande, quintela

ramlist mutex is implemented to protect the RAMBlock list traversal in the
migration thread from their addition/removal from the iothread.

Note: Combination of iothread mutex and migration thread mutex works as a
rw-lock. Both mutexes are acquired while modifying the ram_list members or RAM
block list.

Signed-off-by: Umesh Deshpande <udeshpan@redhat.com>
---
 arch_init.c   |   21 +++++++++++++++++++++
 cpu-all.h     |    3 +++
 exec.c        |   23 +++++++++++++++++++++++
 qemu-common.h |    2 ++
 4 files changed, 49 insertions(+), 0 deletions(-)

diff --git a/arch_init.c b/arch_init.c
index 484b39d..9d02270 100644
--- a/arch_init.c
+++ b/arch_init.c
@@ -109,6 +109,7 @@ static int is_dup_page(uint8_t *page, uint8_t ch)
 
 static RAMBlock *last_block;
 static ram_addr_t last_offset;
+static uint64_t last_version;
 
 static int ram_save_block(QEMUFile *f)
 {
@@ -170,6 +171,7 @@ static int ram_save_block(QEMUFile *f)
 
     last_block = block;
     last_offset = offset;
+    last_version = ram_list.version;
 
     return bytes_sent;
 }
@@ -270,6 +272,7 @@ int ram_save_live(Monitor *mon, QEMUFile *f, int stage, void *opaque)
         bytes_transferred = 0;
         last_block = NULL;
         last_offset = 0;
+        last_version = ram_list.version = 0;
         sort_ram_list();
 
         /* Make sure all dirty bits are set */
@@ -298,6 +301,17 @@ int ram_save_live(Monitor *mon, QEMUFile *f, int stage, void *opaque)
     bytes_transferred_last = bytes_transferred;
     bwidth = qemu_get_clock_ns(rt_clock);
 
+    if (stage != 3) {
+        qemu_mutex_lock_migthread();
+        qemu_mutex_unlock_iothread();
+    }
+
+    if (ram_list.version != last_version) {
+        /* RAM block added or removed */
+        last_block = NULL;
+        last_offset = 0;
+    }
+
     while (!qemu_file_rate_limit(f)) {
         int bytes_sent;
 
@@ -308,6 +322,13 @@ int ram_save_live(Monitor *mon, QEMUFile *f, int stage, void *opaque)
         }
     }
 
+    if (stage != 3) {
+        qemu_mutex_unlock_migthread();
+        qemu_mutex_lock_iothread();
+        /* Lock ordering : iothread mutex is always acquired outside migthread
+         * mutex critical section to avoid deadlock */
+    }
+
     bwidth = qemu_get_clock_ns(rt_clock) - bwidth;
     bwidth = (bytes_transferred - bytes_transferred_last) / bwidth;
 
diff --git a/cpu-all.h b/cpu-all.h
index 6b217a2..b85483f 100644
--- a/cpu-all.h
+++ b/cpu-all.h
@@ -21,6 +21,7 @@
 
 #include "qemu-common.h"
 #include "cpu-common.h"
+#include "qemu-thread.h"
 
 /* some important defines:
  *
@@ -932,7 +933,9 @@ typedef struct RAMBlock {
 } RAMBlock;
 
 typedef struct RAMList {
+    QemuMutex mutex;    /* Protects RAM block list */
     uint8_t *phys_dirty;
+    uint32_t version;   /* To detect ram block addition/removal */
     QLIST_HEAD(ram, RAMBlock) blocks;
     QLIST_HEAD(, RAMBlock) blocks_mru;
 } RAMList;
diff --git a/exec.c b/exec.c
index c5c247c..7627483 100644
--- a/exec.c
+++ b/exec.c
@@ -582,6 +582,7 @@ void cpu_exec_init_all(unsigned long tb_size)
     code_gen_alloc(tb_size);
     code_gen_ptr = code_gen_buffer;
     page_init();
+    qemu_mutex_init(&ram_list.mutex);
 #if !defined(CONFIG_USER_ONLY)
     io_mem_init();
 #endif
@@ -2802,6 +2803,16 @@ static long gethugepagesize(const char *path)
     return fs.f_bsize;
 }
 
+void qemu_mutex_lock_migthread(void)
+{
+    qemu_mutex_lock(&ram_list.mutex);
+}
+
+void qemu_mutex_unlock_migthread(void)
+{
+    qemu_mutex_unlock(&ram_list.mutex);
+}
+
 static void *file_ram_alloc(RAMBlock *block,
                             ram_addr_t memory,
                             const char *path)
@@ -2976,14 +2987,20 @@ ram_addr_t qemu_ram_alloc_from_ptr(DeviceState *dev, const char *name,
     }
     new_block->length = size;
 
+    qemu_mutex_lock_migthread();
+
     QLIST_INSERT_HEAD(&ram_list.blocks, new_block, next);
     QLIST_INSERT_HEAD(&ram_list.blocks_mru, new_block, next_mru);
 
+    ram_list.version++;
+
     ram_list.phys_dirty = qemu_realloc(ram_list.phys_dirty,
                                        last_ram_offset() >> TARGET_PAGE_BITS);
     memset(ram_list.phys_dirty + (new_block->offset >> TARGET_PAGE_BITS),
            0xff, size >> TARGET_PAGE_BITS);
 
+    qemu_mutex_unlock_migthread();
+
     if (kvm_enabled())
         kvm_setup_guest_memory(new_block->host, size);
 
@@ -3001,8 +3018,11 @@ void qemu_ram_free_from_ptr(ram_addr_t addr)
 
     QLIST_FOREACH(block, &ram_list.blocks, next) {
         if (addr == block->offset) {
+            qemu_mutex_lock_migthread();
             QLIST_REMOVE(block, next);
             QLIST_REMOVE(block, next_mru);
+            ram_list.version++;
+            qemu_mutex_unlock_migthread();
             qemu_free(block);
             return;
         }
@@ -3015,8 +3035,11 @@ void qemu_ram_free(ram_addr_t addr)
 
     QLIST_FOREACH(block, &ram_list.blocks, next) {
         if (addr == block->offset) {
+            qemu_mutex_lock_migthread();
             QLIST_REMOVE(block, next);
             QLIST_REMOVE(block, next_mru);
+            ram_list.version++;
+            qemu_mutex_unlock_migthread();
             if (block->flags & RAM_PREALLOC_MASK) {
                 ;
             } else if (mem_path) {
diff --git a/qemu-common.h b/qemu-common.h
index abd7a75..7dabfe9 100644
--- a/qemu-common.h
+++ b/qemu-common.h
@@ -212,6 +212,8 @@ char *qemu_strndup(const char *str, size_t size);
 
 void qemu_mutex_lock_iothread(void);
 void qemu_mutex_unlock_iothread(void);
+void qemu_mutex_lock_migthread(void);
+void qemu_mutex_unlock_migthread(void);
 
 int qemu_open(const char *name, int flags, ...);
 ssize_t qemu_write_full(int fd, const void *buf, size_t count)
-- 
1.7.4.1

^ permalink raw reply related	[flat|nested] 20+ messages in thread

* [RFC PATCH v5 3/4] Separate migration bitmap
  2011-08-24  3:12 ` [Qemu-devel] " Umesh Deshpande
@ 2011-08-24  3:12   ` Umesh Deshpande
  -1 siblings, 0 replies; 20+ messages in thread
From: Umesh Deshpande @ 2011-08-24  3:12 UTC (permalink / raw)
  To: kvm, qemu-devel; +Cc: pbonzini, quintela, mtosatti, Umesh Deshpande

This patch creates a migration bitmap, which is periodically kept in sync with
the qemu bitmap. A separate copy of the dirty bitmap for the migration avoids
concurrent access to the qemu bitmap from iothread and migration thread.

Signed-off-by: Umesh Deshpande <udeshpan@redhat.com>
---
 arch_init.c |   17 ++++++++---------
 cpu-all.h   |   37 +++++++++++++++++++++++++++++++++++++
 exec.c      |   57 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 102 insertions(+), 9 deletions(-)

diff --git a/arch_init.c b/arch_init.c
index 9d02270..b5b852b 100644
--- a/arch_init.c
+++ b/arch_init.c
@@ -124,13 +124,13 @@ static int ram_save_block(QEMUFile *f)
     current_addr = block->offset + offset;
 
     do {
-        if (cpu_physical_memory_get_dirty(current_addr, MIGRATION_DIRTY_FLAG)) {
+        if (migration_bitmap_get_dirty(current_addr, MIGRATION_DIRTY_FLAG)) {
             uint8_t *p;
             int cont = (block == last_block) ? RAM_SAVE_FLAG_CONTINUE : 0;
 
-            cpu_physical_memory_reset_dirty(current_addr,
-                                            current_addr + TARGET_PAGE_SIZE,
-                                            MIGRATION_DIRTY_FLAG);
+            migration_bitmap_reset_dirty(current_addr,
+                                         current_addr + TARGET_PAGE_SIZE,
+                                         MIGRATION_DIRTY_FLAG);
 
             p = block->host + offset;
 
@@ -187,7 +187,7 @@ static ram_addr_t ram_save_remaining(void)
         ram_addr_t addr;
         for (addr = block->offset; addr < block->offset + block->length;
              addr += TARGET_PAGE_SIZE) {
-            if (cpu_physical_memory_get_dirty(addr, MIGRATION_DIRTY_FLAG)) {
+            if (migration_bitmap_get_dirty(addr, MIGRATION_DIRTY_FLAG)) {
                 count++;
             }
         }
@@ -267,6 +267,8 @@ int ram_save_live(Monitor *mon, QEMUFile *f, int stage, void *opaque)
         return 0;
     }
 
+    sync_migration_bitmap(0, TARGET_PHYS_ADDR_MAX);
+
     if (stage == 1) {
         RAMBlock *block;
         bytes_transferred = 0;
@@ -279,10 +281,7 @@ int ram_save_live(Monitor *mon, QEMUFile *f, int stage, void *opaque)
         QLIST_FOREACH(block, &ram_list.blocks, next) {
             for (addr = block->offset; addr < block->offset + block->length;
                  addr += TARGET_PAGE_SIZE) {
-                if (!cpu_physical_memory_get_dirty(addr,
-                                                   MIGRATION_DIRTY_FLAG)) {
-                    cpu_physical_memory_set_dirty(addr);
-                }
+                migration_bitmap_set_dirty(addr);
             }
         }
 
diff --git a/cpu-all.h b/cpu-all.h
index b85483f..8181f8b 100644
--- a/cpu-all.h
+++ b/cpu-all.h
@@ -935,6 +935,7 @@ typedef struct RAMBlock {
 typedef struct RAMList {
     QemuMutex mutex;    /* Protects RAM block list */
     uint8_t *phys_dirty;
+    uint8_t *migration_bitmap; /* Dedicated bitmap for migration thread */
     uint32_t version;   /* To detect ram block addition/removal */
     QLIST_HEAD(ram, RAMBlock) blocks;
     QLIST_HEAD(, RAMBlock) blocks_mru;
@@ -1009,8 +1010,44 @@ static inline void cpu_physical_memory_mask_dirty_range(ram_addr_t start,
     }
 }
 
+
+
 void cpu_physical_memory_reset_dirty(ram_addr_t start, ram_addr_t end,
                                      int dirty_flags);
+
+static inline int migration_bitmap_get_dirty(ram_addr_t addr,
+                                             int dirty_flags)
+{
+    return ram_list.migration_bitmap[addr >> TARGET_PAGE_BITS] & dirty_flags;
+}
+
+static inline void migration_bitmap_set_dirty(ram_addr_t addr)
+{
+    ram_list.migration_bitmap[addr >> TARGET_PAGE_BITS] = 0xff;
+}
+
+static inline void migration_bitmap_mask_dirty_range(ram_addr_t start,
+                                                     int length,
+                                                     int dirty_flags)
+{
+    int i, mask, len;
+    uint8_t *p;
+
+    len = length >> TARGET_PAGE_BITS;
+    mask = ~dirty_flags;
+    p = ram_list.migration_bitmap + (start >> TARGET_PAGE_BITS);
+    for (i = 0; i < len; i++) {
+        p[i] &= mask;
+    }
+}
+
+
+void migration_bitmap_reset_dirty(ram_addr_t start,
+                                  ram_addr_t end,
+                                  int dirty_flags);
+
+void sync_migration_bitmap(ram_addr_t start, ram_addr_t end);
+
 void cpu_tlb_update_dirty(CPUState *env);
 
 int cpu_physical_memory_set_dirty_tracking(int enable);
diff --git a/exec.c b/exec.c
index 7627483..8dfbdbc 100644
--- a/exec.c
+++ b/exec.c
@@ -2111,6 +2111,10 @@ void cpu_physical_memory_reset_dirty(ram_addr_t start, ram_addr_t end,
         abort();
     }
 
+    if (kvm_enabled()) {
+        return;
+    }
+
     for(env = first_cpu; env != NULL; env = env->next_cpu) {
         int mmu_idx;
         for (mmu_idx = 0; mmu_idx < NB_MMU_MODES; mmu_idx++) {
@@ -2119,8 +2123,54 @@ void cpu_physical_memory_reset_dirty(ram_addr_t start, ram_addr_t end,
                                       start1, length);
         }
     }
+
+}
+
+void migration_bitmap_reset_dirty(ram_addr_t start, ram_addr_t end,
+                                  int dirty_flags)
+{
+    unsigned long length;
+
+    start &= TARGET_PAGE_MASK;
+    end = TARGET_PAGE_ALIGN(end);
+
+    length = end - start;
+    if (length == 0) {
+        return;
+    }
+
+    migration_bitmap_mask_dirty_range(start, length, dirty_flags);
+}
+
+/* Synchronizes migration bitmap with the qemu dirty bitmap.
+ * Called by acquiring the iothread mutex */
+
+void sync_migration_bitmap(ram_addr_t start, ram_addr_t end)
+{
+    unsigned long length, len, i;
+    ram_addr_t addr;
+    start &= TARGET_PAGE_MASK;
+    end = TARGET_PAGE_ALIGN(end);
+
+    length = end - start;
+    if (length == 0) {
+        return;
+    }
+
+    len = length >> TARGET_PAGE_BITS;
+    for (i = 0; i < len; i++) {
+        addr = i << TARGET_PAGE_BITS;
+        if (cpu_physical_memory_get_dirty(addr, MIGRATION_DIRTY_FLAG)) {
+            migration_bitmap_set_dirty(addr);
+            cpu_physical_memory_reset_dirty(addr, addr + TARGET_PAGE_SIZE,
+                                            MIGRATION_DIRTY_FLAG);
+        }
+    }
+
 }
 
+
+
 int cpu_physical_memory_set_dirty_tracking(int enable)
 {
     int ret = 0;
@@ -2999,6 +3049,13 @@ ram_addr_t qemu_ram_alloc_from_ptr(DeviceState *dev, const char *name,
     memset(ram_list.phys_dirty + (new_block->offset >> TARGET_PAGE_BITS),
            0xff, size >> TARGET_PAGE_BITS);
 
+    ram_list.migration_bitmap = qemu_realloc(ram_list.phys_dirty,
+                                             last_ram_offset() >>
+                                             TARGET_PAGE_BITS);
+
+    memset(ram_list.migration_bitmap + (new_block->offset >> TARGET_PAGE_BITS),
+           0xff, size >> TARGET_PAGE_BITS);
+
     qemu_mutex_unlock_migthread();
 
     if (kvm_enabled())
-- 
1.7.4.1


^ permalink raw reply related	[flat|nested] 20+ messages in thread

* [Qemu-devel] [RFC PATCH v5 3/4] Separate migration bitmap
@ 2011-08-24  3:12   ` Umesh Deshpande
  0 siblings, 0 replies; 20+ messages in thread
From: Umesh Deshpande @ 2011-08-24  3:12 UTC (permalink / raw)
  To: kvm, qemu-devel; +Cc: pbonzini, mtosatti, Umesh Deshpande, quintela

This patch creates a migration bitmap, which is periodically kept in sync with
the qemu bitmap. A separate copy of the dirty bitmap for the migration avoids
concurrent access to the qemu bitmap from iothread and migration thread.

Signed-off-by: Umesh Deshpande <udeshpan@redhat.com>
---
 arch_init.c |   17 ++++++++---------
 cpu-all.h   |   37 +++++++++++++++++++++++++++++++++++++
 exec.c      |   57 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 102 insertions(+), 9 deletions(-)

diff --git a/arch_init.c b/arch_init.c
index 9d02270..b5b852b 100644
--- a/arch_init.c
+++ b/arch_init.c
@@ -124,13 +124,13 @@ static int ram_save_block(QEMUFile *f)
     current_addr = block->offset + offset;
 
     do {
-        if (cpu_physical_memory_get_dirty(current_addr, MIGRATION_DIRTY_FLAG)) {
+        if (migration_bitmap_get_dirty(current_addr, MIGRATION_DIRTY_FLAG)) {
             uint8_t *p;
             int cont = (block == last_block) ? RAM_SAVE_FLAG_CONTINUE : 0;
 
-            cpu_physical_memory_reset_dirty(current_addr,
-                                            current_addr + TARGET_PAGE_SIZE,
-                                            MIGRATION_DIRTY_FLAG);
+            migration_bitmap_reset_dirty(current_addr,
+                                         current_addr + TARGET_PAGE_SIZE,
+                                         MIGRATION_DIRTY_FLAG);
 
             p = block->host + offset;
 
@@ -187,7 +187,7 @@ static ram_addr_t ram_save_remaining(void)
         ram_addr_t addr;
         for (addr = block->offset; addr < block->offset + block->length;
              addr += TARGET_PAGE_SIZE) {
-            if (cpu_physical_memory_get_dirty(addr, MIGRATION_DIRTY_FLAG)) {
+            if (migration_bitmap_get_dirty(addr, MIGRATION_DIRTY_FLAG)) {
                 count++;
             }
         }
@@ -267,6 +267,8 @@ int ram_save_live(Monitor *mon, QEMUFile *f, int stage, void *opaque)
         return 0;
     }
 
+    sync_migration_bitmap(0, TARGET_PHYS_ADDR_MAX);
+
     if (stage == 1) {
         RAMBlock *block;
         bytes_transferred = 0;
@@ -279,10 +281,7 @@ int ram_save_live(Monitor *mon, QEMUFile *f, int stage, void *opaque)
         QLIST_FOREACH(block, &ram_list.blocks, next) {
             for (addr = block->offset; addr < block->offset + block->length;
                  addr += TARGET_PAGE_SIZE) {
-                if (!cpu_physical_memory_get_dirty(addr,
-                                                   MIGRATION_DIRTY_FLAG)) {
-                    cpu_physical_memory_set_dirty(addr);
-                }
+                migration_bitmap_set_dirty(addr);
             }
         }
 
diff --git a/cpu-all.h b/cpu-all.h
index b85483f..8181f8b 100644
--- a/cpu-all.h
+++ b/cpu-all.h
@@ -935,6 +935,7 @@ typedef struct RAMBlock {
 typedef struct RAMList {
     QemuMutex mutex;    /* Protects RAM block list */
     uint8_t *phys_dirty;
+    uint8_t *migration_bitmap; /* Dedicated bitmap for migration thread */
     uint32_t version;   /* To detect ram block addition/removal */
     QLIST_HEAD(ram, RAMBlock) blocks;
     QLIST_HEAD(, RAMBlock) blocks_mru;
@@ -1009,8 +1010,44 @@ static inline void cpu_physical_memory_mask_dirty_range(ram_addr_t start,
     }
 }
 
+
+
 void cpu_physical_memory_reset_dirty(ram_addr_t start, ram_addr_t end,
                                      int dirty_flags);
+
+static inline int migration_bitmap_get_dirty(ram_addr_t addr,
+                                             int dirty_flags)
+{
+    return ram_list.migration_bitmap[addr >> TARGET_PAGE_BITS] & dirty_flags;
+}
+
+static inline void migration_bitmap_set_dirty(ram_addr_t addr)
+{
+    ram_list.migration_bitmap[addr >> TARGET_PAGE_BITS] = 0xff;
+}
+
+static inline void migration_bitmap_mask_dirty_range(ram_addr_t start,
+                                                     int length,
+                                                     int dirty_flags)
+{
+    int i, mask, len;
+    uint8_t *p;
+
+    len = length >> TARGET_PAGE_BITS;
+    mask = ~dirty_flags;
+    p = ram_list.migration_bitmap + (start >> TARGET_PAGE_BITS);
+    for (i = 0; i < len; i++) {
+        p[i] &= mask;
+    }
+}
+
+
+void migration_bitmap_reset_dirty(ram_addr_t start,
+                                  ram_addr_t end,
+                                  int dirty_flags);
+
+void sync_migration_bitmap(ram_addr_t start, ram_addr_t end);
+
 void cpu_tlb_update_dirty(CPUState *env);
 
 int cpu_physical_memory_set_dirty_tracking(int enable);
diff --git a/exec.c b/exec.c
index 7627483..8dfbdbc 100644
--- a/exec.c
+++ b/exec.c
@@ -2111,6 +2111,10 @@ void cpu_physical_memory_reset_dirty(ram_addr_t start, ram_addr_t end,
         abort();
     }
 
+    if (kvm_enabled()) {
+        return;
+    }
+
     for(env = first_cpu; env != NULL; env = env->next_cpu) {
         int mmu_idx;
         for (mmu_idx = 0; mmu_idx < NB_MMU_MODES; mmu_idx++) {
@@ -2119,8 +2123,54 @@ void cpu_physical_memory_reset_dirty(ram_addr_t start, ram_addr_t end,
                                       start1, length);
         }
     }
+
+}
+
+void migration_bitmap_reset_dirty(ram_addr_t start, ram_addr_t end,
+                                  int dirty_flags)
+{
+    unsigned long length;
+
+    start &= TARGET_PAGE_MASK;
+    end = TARGET_PAGE_ALIGN(end);
+
+    length = end - start;
+    if (length == 0) {
+        return;
+    }
+
+    migration_bitmap_mask_dirty_range(start, length, dirty_flags);
+}
+
+/* Synchronizes migration bitmap with the qemu dirty bitmap.
+ * Called by acquiring the iothread mutex */
+
+void sync_migration_bitmap(ram_addr_t start, ram_addr_t end)
+{
+    unsigned long length, len, i;
+    ram_addr_t addr;
+    start &= TARGET_PAGE_MASK;
+    end = TARGET_PAGE_ALIGN(end);
+
+    length = end - start;
+    if (length == 0) {
+        return;
+    }
+
+    len = length >> TARGET_PAGE_BITS;
+    for (i = 0; i < len; i++) {
+        addr = i << TARGET_PAGE_BITS;
+        if (cpu_physical_memory_get_dirty(addr, MIGRATION_DIRTY_FLAG)) {
+            migration_bitmap_set_dirty(addr);
+            cpu_physical_memory_reset_dirty(addr, addr + TARGET_PAGE_SIZE,
+                                            MIGRATION_DIRTY_FLAG);
+        }
+    }
+
 }
 
+
+
 int cpu_physical_memory_set_dirty_tracking(int enable)
 {
     int ret = 0;
@@ -2999,6 +3049,13 @@ ram_addr_t qemu_ram_alloc_from_ptr(DeviceState *dev, const char *name,
     memset(ram_list.phys_dirty + (new_block->offset >> TARGET_PAGE_BITS),
            0xff, size >> TARGET_PAGE_BITS);
 
+    ram_list.migration_bitmap = qemu_realloc(ram_list.phys_dirty,
+                                             last_ram_offset() >>
+                                             TARGET_PAGE_BITS);
+
+    memset(ram_list.migration_bitmap + (new_block->offset >> TARGET_PAGE_BITS),
+           0xff, size >> TARGET_PAGE_BITS);
+
     qemu_mutex_unlock_migthread();
 
     if (kvm_enabled())
-- 
1.7.4.1

^ permalink raw reply related	[flat|nested] 20+ messages in thread

* [RFC PATCH v5 4/4] Separate thread for VM migration
  2011-08-24  3:12 ` [Qemu-devel] " Umesh Deshpande
@ 2011-08-24  3:12   ` Umesh Deshpande
  -1 siblings, 0 replies; 20+ messages in thread
From: Umesh Deshpande @ 2011-08-24  3:12 UTC (permalink / raw)
  To: kvm, qemu-devel; +Cc: pbonzini, quintela, mtosatti, Umesh Deshpande

This patch creates a separate thread for the guest migration on the source side.
All exits (on completion/error) from the migration thread are handled by a bottom
handler, which is called from the iothread.

Signed-off-by: Umesh Deshpande <udeshpan@redhat.com>
---
 buffered_file.c     |   75 +++++++++++++++++--------------
 migration.c         |  122 +++++++++++++++++++++++++++++---------------------
 migration.h         |    9 ++++
 qemu-thread-posix.c |   10 ++++
 qemu-thread.h       |    1 +
 savevm.c            |    5 --
 6 files changed, 132 insertions(+), 90 deletions(-)

diff --git a/buffered_file.c b/buffered_file.c
index 41b42c3..0d94baa 100644
--- a/buffered_file.c
+++ b/buffered_file.c
@@ -16,6 +16,8 @@
 #include "qemu-timer.h"
 #include "qemu-char.h"
 #include "buffered_file.h"
+#include "migration.h"
+#include "qemu-thread.h"
 
 //#define DEBUG_BUFFERED_FILE
 
@@ -28,13 +30,14 @@ typedef struct QEMUFileBuffered
     void *opaque;
     QEMUFile *file;
     int has_error;
+    int closed;
     int freeze_output;
     size_t bytes_xfer;
     size_t xfer_limit;
     uint8_t *buffer;
     size_t buffer_size;
     size_t buffer_capacity;
-    QEMUTimer *timer;
+    QemuThread thread;
 } QEMUFileBuffered;
 
 #ifdef DEBUG_BUFFERED_FILE
@@ -155,14 +158,6 @@ static int buffered_put_buffer(void *opaque, const uint8_t *buf, int64_t pos, in
         offset = size;
     }
 
-    if (pos == 0 && size == 0) {
-        DPRINTF("file is ready\n");
-        if (s->bytes_xfer <= s->xfer_limit) {
-            DPRINTF("notifying client\n");
-            s->put_ready(s->opaque);
-        }
-    }
-
     return offset;
 }
 
@@ -173,22 +168,25 @@ static int buffered_close(void *opaque)
 
     DPRINTF("closing\n");
 
-    while (!s->has_error && s->buffer_size) {
-        buffered_flush(s);
-        if (s->freeze_output)
-            s->wait_for_unfreeze(s);
-    }
+    s->closed = 1;
 
-    ret = s->close(s->opaque);
+    qemu_mutex_unlock_migthread();
+    qemu_mutex_unlock_iothread();
+
+    qemu_thread_join(&s->thread);
+    /* Waits for the completion of the migration thread */
 
-    qemu_del_timer(s->timer);
-    qemu_free_timer(s->timer);
+    qemu_mutex_lock_iothread();
+    qemu_mutex_lock_migthread();
+
+    ret = s->close(s->opaque);
     qemu_free(s->buffer);
     qemu_free(s);
 
     return ret;
 }
 
+
 static int buffered_rate_limit(void *opaque)
 {
     QEMUFileBuffered *s = opaque;
@@ -228,26 +226,36 @@ static int64_t buffered_get_rate_limit(void *opaque)
     return s->xfer_limit;
 }
 
-static void buffered_rate_tick(void *opaque)
+static void *migrate_vm(void *opaque)
 {
     QEMUFileBuffered *s = opaque;
+    int64_t current_time, expire_time = qemu_get_clock_ms(rt_clock) + 100;
+    struct timeval tv = { .tv_sec = 0, .tv_usec = 100000};
 
-    if (s->has_error) {
-        buffered_close(s);
-        return;
-    }
-
-    qemu_mod_timer(s->timer, qemu_get_clock_ms(rt_clock) + 100);
+    while (!s->has_error && (!s->closed || s->buffer_size)) {
+        if (s->freeze_output) {
+            s->wait_for_unfreeze(s);
+            s->freeze_output = 0;
+            continue;
+        }
 
-    if (s->freeze_output)
-        return;
+        current_time = qemu_get_clock_ms(rt_clock);
+        if (!s->closed && (expire_time > current_time)) {
+            tv.tv_usec = 1000 * (expire_time - current_time);
+            select(0, NULL, NULL, NULL, &tv);
+            continue;
+        }
 
-    s->bytes_xfer = 0;
+        s->bytes_xfer = 0;
+        buffered_flush(s);
 
-    buffered_flush(s);
+        expire_time = qemu_get_clock_ms(rt_clock) + 100;
+        if (!s->closed) {
+            s->put_ready(s->opaque);
+        }
+    }
 
-    /* Add some checks around this */
-    s->put_ready(s->opaque);
+    return NULL;
 }
 
 QEMUFile *qemu_fopen_ops_buffered(void *opaque,
@@ -267,15 +275,14 @@ QEMUFile *qemu_fopen_ops_buffered(void *opaque,
     s->put_ready = put_ready;
     s->wait_for_unfreeze = wait_for_unfreeze;
     s->close = close;
+    s->closed = 0;
 
     s->file = qemu_fopen_ops(s, buffered_put_buffer, NULL,
                              buffered_close, buffered_rate_limit,
                              buffered_set_rate_limit,
-			     buffered_get_rate_limit);
-
-    s->timer = qemu_new_timer_ms(rt_clock, buffered_rate_tick, s);
+                             buffered_get_rate_limit);
 
-    qemu_mod_timer(s->timer, qemu_get_clock_ms(rt_clock) + 100);
+    qemu_thread_create(&s->thread, migrate_vm, s);
 
     return s->file;
 }
diff --git a/migration.c b/migration.c
index af3a1f2..17d866a 100644
--- a/migration.c
+++ b/migration.c
@@ -149,10 +149,12 @@ int do_migrate_set_speed(Monitor *mon, const QDict *qdict, QObject **ret_data)
     }
     max_throttle = d;
 
+    qemu_mutex_lock_migthread();
     s = migrate_to_fms(current_migration);
     if (s && s->file) {
         qemu_file_set_rate_limit(s->file, max_throttle);
     }
+    qemu_mutex_unlock_migthread();
 
     return 0;
 }
@@ -284,8 +286,6 @@ int migrate_fd_cleanup(FdMigrationState *s)
 {
     int ret = 0;
 
-    qemu_set_fd_handler2(s->fd, NULL, NULL, NULL, NULL);
-
     if (s->file) {
         DPRINTF("closing file\n");
         if (qemu_fclose(s->file) != 0) {
@@ -307,14 +307,6 @@ int migrate_fd_cleanup(FdMigrationState *s)
     return ret;
 }
 
-void migrate_fd_put_notify(void *opaque)
-{
-    FdMigrationState *s = opaque;
-
-    qemu_set_fd_handler2(s->fd, NULL, NULL, NULL, NULL);
-    qemu_file_put_notify(s->file);
-}
-
 ssize_t migrate_fd_put_buffer(void *opaque, const void *data, size_t size)
 {
     FdMigrationState *s = opaque;
@@ -327,76 +319,91 @@ ssize_t migrate_fd_put_buffer(void *opaque, const void *data, size_t size)
     if (ret == -1)
         ret = -(s->get_error(s));
 
-    if (ret == -EAGAIN) {
-        qemu_set_fd_handler2(s->fd, NULL, NULL, migrate_fd_put_notify, s);
-    } else if (ret < 0) {
-        if (s->mon) {
-            monitor_resume(s->mon);
+    return ret;
+}
+
+static void migrate_fd_terminate(void *opaque)
+{
+    FdMigrationState *s = opaque;
+
+    qemu_mutex_lock_migthread();
+
+    if (s->code == COMPLETE) {
+        if (migrate_fd_cleanup(s) < 0) {
+            if (s->old_vm_running) {
+                vm_start();
+            }
+            s->state = MIG_STATE_ERROR;
+        } else {
+            s->state = MIG_STATE_COMPLETED;
         }
-        s->state = MIG_STATE_ERROR;
         notifier_list_notify(&migration_state_notifiers);
+    } else if (s->code == RESUME) {
+        if (s->old_vm_running) {
+            vm_start();
+        }
+        migrate_fd_error(s);
+    } else if (s->code == ERROR) {
+        migrate_fd_error(s);
     }
 
-    return ret;
+    qemu_mutex_unlock_migthread();
 }
 
 void migrate_fd_connect(FdMigrationState *s)
 {
-    int ret;
-
+    s->code = START;
+    s->bh = qemu_bh_new(migrate_fd_terminate, s);
     s->file = qemu_fopen_ops_buffered(s,
                                       s->bandwidth_limit,
                                       migrate_fd_put_buffer,
                                       migrate_fd_put_ready,
                                       migrate_fd_wait_for_unfreeze,
                                       migrate_fd_close);
-
-    DPRINTF("beginning savevm\n");
-    ret = qemu_savevm_state_begin(s->mon, s->file, s->mig_state.blk,
-                                  s->mig_state.shared);
-    if (ret < 0) {
-        DPRINTF("failed, %d\n", ret);
-        migrate_fd_error(s);
-        return;
-    }
-    
-    migrate_fd_put_ready(s);
 }
 
 void migrate_fd_put_ready(void *opaque)
 {
     FdMigrationState *s = opaque;
+    int ret;
 
-    if (s->state != MIG_STATE_ACTIVE) {
+    qemu_mutex_lock_iothread();
+    if (s->code != ACTIVE && s->code != START) {
         DPRINTF("put_ready returning because of non-active state\n");
+        qemu_mutex_unlock_iothread();
         return;
     }
 
+    if (!s->code) {
+        DPRINTF("beginning savevm\n");
+        ret = qemu_savevm_state_begin(s->mon, s->file, s->mig_state.blk,
+                s->mig_state.shared);
+        if (ret < 0) {
+            DPRINTF("failed, %d\n", ret);
+            s->code = ERROR;
+            qemu_bh_schedule(s->bh);
+            qemu_mutex_unlock_iothread();
+            return;
+        }
+        s->code = ACTIVE;
+    }
+
     DPRINTF("iterate\n");
     if (qemu_savevm_state_iterate(s->mon, s->file) == 1) {
-        int state;
-        int old_vm_running = vm_running;
+        s->old_vm_running = vm_running;
 
         DPRINTF("done iterating\n");
         vm_stop(VMSTOP_MIGRATE);
 
         if ((qemu_savevm_state_complete(s->mon, s->file)) < 0) {
-            if (old_vm_running) {
-                vm_start();
-            }
-            state = MIG_STATE_ERROR;
+            s->code = RESUME;
         } else {
-            state = MIG_STATE_COMPLETED;
-        }
-        if (migrate_fd_cleanup(s) < 0) {
-            if (old_vm_running) {
-                vm_start();
-            }
-            state = MIG_STATE_ERROR;
+            s->code = COMPLETE;
         }
-        s->state = state;
-        notifier_list_notify(&migration_state_notifiers);
+
+        qemu_bh_schedule(s->bh);
     }
+    qemu_mutex_unlock_iothread();
 }
 
 int migrate_fd_get_status(MigrationState *mig_state)
@@ -416,9 +423,11 @@ void migrate_fd_cancel(MigrationState *mig_state)
 
     s->state = MIG_STATE_CANCELLED;
     notifier_list_notify(&migration_state_notifiers);
-    qemu_savevm_state_cancel(s->mon, s->file);
 
+    qemu_mutex_lock_migthread();
+    qemu_savevm_state_cancel(s->mon, s->file);
     migrate_fd_cleanup(s);
+    qemu_mutex_unlock_migthread();
 }
 
 void migrate_fd_release(MigrationState *mig_state)
@@ -426,22 +435,34 @@ void migrate_fd_release(MigrationState *mig_state)
     FdMigrationState *s = migrate_to_fms(mig_state);
 
     DPRINTF("releasing state\n");
-   
+
     if (s->state == MIG_STATE_ACTIVE) {
         s->state = MIG_STATE_CANCELLED;
         notifier_list_notify(&migration_state_notifiers);
+        qemu_mutex_lock_migthread();
         migrate_fd_cleanup(s);
+        qemu_mutex_unlock_migthread();
+    }
+
+    if (s->bh) {
+        qemu_bh_delete(s->bh);
     }
+
     qemu_free(s);
 }
 
 void migrate_fd_wait_for_unfreeze(void *opaque)
 {
     FdMigrationState *s = opaque;
-    int ret;
+    int ret, state;
 
     DPRINTF("wait for unfreeze\n");
-    if (s->state != MIG_STATE_ACTIVE)
+
+    qemu_mutex_lock_iothread();
+    state = s->state;
+    qemu_mutex_unlock_iothread();
+
+    if (state != MIG_STATE_ACTIVE)
         return;
 
     do {
@@ -458,7 +479,6 @@ int migrate_fd_close(void *opaque)
 {
     FdMigrationState *s = opaque;
 
-    qemu_set_fd_handler2(s->fd, NULL, NULL, NULL, NULL);
     return s->close(s);
 }
 
diff --git a/migration.h b/migration.h
index 050c56c..abbf9e4 100644
--- a/migration.h
+++ b/migration.h
@@ -23,6 +23,12 @@
 #define MIG_STATE_CANCELLED	1
 #define MIG_STATE_ACTIVE	2
 
+#define START       0
+#define ACTIVE      1
+#define COMPLETE    2
+#define ERROR       3
+#define RESUME      4
+
 typedef struct MigrationState MigrationState;
 
 struct MigrationState
@@ -45,10 +51,13 @@ struct FdMigrationState
     int fd;
     Monitor *mon;
     int state;
+    int code;
+    int old_vm_running;
     int (*get_error)(struct FdMigrationState*);
     int (*close)(struct FdMigrationState*);
     int (*write)(struct FdMigrationState*, const void *, size_t);
     void *opaque;
+    QEMUBH *bh;
 };
 
 void process_incoming_migration(QEMUFile *f);
diff --git a/qemu-thread-posix.c b/qemu-thread-posix.c
index 2bd02ef..6a275be 100644
--- a/qemu-thread-posix.c
+++ b/qemu-thread-posix.c
@@ -115,6 +115,16 @@ void qemu_cond_wait(QemuCond *cond, QemuMutex *mutex)
         error_exit(err, __func__);
 }
 
+void qemu_thread_join(QemuThread *thread)
+{
+    int err;
+
+    err = pthread_join(thread->thread, NULL);
+    if (err) {
+        error_exit(err, __func__);
+    }
+}
+
 void qemu_thread_create(QemuThread *thread,
                        void *(*start_routine)(void*),
                        void *arg)
diff --git a/qemu-thread.h b/qemu-thread.h
index 0a73d50..d5b99d5 100644
--- a/qemu-thread.h
+++ b/qemu-thread.h
@@ -30,6 +30,7 @@ void qemu_cond_destroy(QemuCond *cond);
 void qemu_cond_signal(QemuCond *cond);
 void qemu_cond_broadcast(QemuCond *cond);
 void qemu_cond_wait(QemuCond *cond, QemuMutex *mutex);
+void qemu_thread_join(QemuThread *thread);
 
 void qemu_thread_create(QemuThread *thread,
                        void *(*start_routine)(void*),
diff --git a/savevm.c b/savevm.c
index 8139bc7..f54f555 100644
--- a/savevm.c
+++ b/savevm.c
@@ -481,11 +481,6 @@ int qemu_fclose(QEMUFile *f)
     return ret;
 }
 
-void qemu_file_put_notify(QEMUFile *f)
-{
-    f->put_buffer(f->opaque, NULL, 0, 0);
-}
-
 void qemu_put_buffer(QEMUFile *f, const uint8_t *buf, int size)
 {
     int l;
-- 
1.7.4.1


^ permalink raw reply related	[flat|nested] 20+ messages in thread

* [Qemu-devel] [RFC PATCH v5 4/4] Separate thread for VM migration
@ 2011-08-24  3:12   ` Umesh Deshpande
  0 siblings, 0 replies; 20+ messages in thread
From: Umesh Deshpande @ 2011-08-24  3:12 UTC (permalink / raw)
  To: kvm, qemu-devel; +Cc: pbonzini, mtosatti, Umesh Deshpande, quintela

This patch creates a separate thread for the guest migration on the source side.
All exits (on completion/error) from the migration thread are handled by a bottom
handler, which is called from the iothread.

Signed-off-by: Umesh Deshpande <udeshpan@redhat.com>
---
 buffered_file.c     |   75 +++++++++++++++++--------------
 migration.c         |  122 +++++++++++++++++++++++++++++---------------------
 migration.h         |    9 ++++
 qemu-thread-posix.c |   10 ++++
 qemu-thread.h       |    1 +
 savevm.c            |    5 --
 6 files changed, 132 insertions(+), 90 deletions(-)

diff --git a/buffered_file.c b/buffered_file.c
index 41b42c3..0d94baa 100644
--- a/buffered_file.c
+++ b/buffered_file.c
@@ -16,6 +16,8 @@
 #include "qemu-timer.h"
 #include "qemu-char.h"
 #include "buffered_file.h"
+#include "migration.h"
+#include "qemu-thread.h"
 
 //#define DEBUG_BUFFERED_FILE
 
@@ -28,13 +30,14 @@ typedef struct QEMUFileBuffered
     void *opaque;
     QEMUFile *file;
     int has_error;
+    int closed;
     int freeze_output;
     size_t bytes_xfer;
     size_t xfer_limit;
     uint8_t *buffer;
     size_t buffer_size;
     size_t buffer_capacity;
-    QEMUTimer *timer;
+    QemuThread thread;
 } QEMUFileBuffered;
 
 #ifdef DEBUG_BUFFERED_FILE
@@ -155,14 +158,6 @@ static int buffered_put_buffer(void *opaque, const uint8_t *buf, int64_t pos, in
         offset = size;
     }
 
-    if (pos == 0 && size == 0) {
-        DPRINTF("file is ready\n");
-        if (s->bytes_xfer <= s->xfer_limit) {
-            DPRINTF("notifying client\n");
-            s->put_ready(s->opaque);
-        }
-    }
-
     return offset;
 }
 
@@ -173,22 +168,25 @@ static int buffered_close(void *opaque)
 
     DPRINTF("closing\n");
 
-    while (!s->has_error && s->buffer_size) {
-        buffered_flush(s);
-        if (s->freeze_output)
-            s->wait_for_unfreeze(s);
-    }
+    s->closed = 1;
 
-    ret = s->close(s->opaque);
+    qemu_mutex_unlock_migthread();
+    qemu_mutex_unlock_iothread();
+
+    qemu_thread_join(&s->thread);
+    /* Waits for the completion of the migration thread */
 
-    qemu_del_timer(s->timer);
-    qemu_free_timer(s->timer);
+    qemu_mutex_lock_iothread();
+    qemu_mutex_lock_migthread();
+
+    ret = s->close(s->opaque);
     qemu_free(s->buffer);
     qemu_free(s);
 
     return ret;
 }
 
+
 static int buffered_rate_limit(void *opaque)
 {
     QEMUFileBuffered *s = opaque;
@@ -228,26 +226,36 @@ static int64_t buffered_get_rate_limit(void *opaque)
     return s->xfer_limit;
 }
 
-static void buffered_rate_tick(void *opaque)
+static void *migrate_vm(void *opaque)
 {
     QEMUFileBuffered *s = opaque;
+    int64_t current_time, expire_time = qemu_get_clock_ms(rt_clock) + 100;
+    struct timeval tv = { .tv_sec = 0, .tv_usec = 100000};
 
-    if (s->has_error) {
-        buffered_close(s);
-        return;
-    }
-
-    qemu_mod_timer(s->timer, qemu_get_clock_ms(rt_clock) + 100);
+    while (!s->has_error && (!s->closed || s->buffer_size)) {
+        if (s->freeze_output) {
+            s->wait_for_unfreeze(s);
+            s->freeze_output = 0;
+            continue;
+        }
 
-    if (s->freeze_output)
-        return;
+        current_time = qemu_get_clock_ms(rt_clock);
+        if (!s->closed && (expire_time > current_time)) {
+            tv.tv_usec = 1000 * (expire_time - current_time);
+            select(0, NULL, NULL, NULL, &tv);
+            continue;
+        }
 
-    s->bytes_xfer = 0;
+        s->bytes_xfer = 0;
+        buffered_flush(s);
 
-    buffered_flush(s);
+        expire_time = qemu_get_clock_ms(rt_clock) + 100;
+        if (!s->closed) {
+            s->put_ready(s->opaque);
+        }
+    }
 
-    /* Add some checks around this */
-    s->put_ready(s->opaque);
+    return NULL;
 }
 
 QEMUFile *qemu_fopen_ops_buffered(void *opaque,
@@ -267,15 +275,14 @@ QEMUFile *qemu_fopen_ops_buffered(void *opaque,
     s->put_ready = put_ready;
     s->wait_for_unfreeze = wait_for_unfreeze;
     s->close = close;
+    s->closed = 0;
 
     s->file = qemu_fopen_ops(s, buffered_put_buffer, NULL,
                              buffered_close, buffered_rate_limit,
                              buffered_set_rate_limit,
-			     buffered_get_rate_limit);
-
-    s->timer = qemu_new_timer_ms(rt_clock, buffered_rate_tick, s);
+                             buffered_get_rate_limit);
 
-    qemu_mod_timer(s->timer, qemu_get_clock_ms(rt_clock) + 100);
+    qemu_thread_create(&s->thread, migrate_vm, s);
 
     return s->file;
 }
diff --git a/migration.c b/migration.c
index af3a1f2..17d866a 100644
--- a/migration.c
+++ b/migration.c
@@ -149,10 +149,12 @@ int do_migrate_set_speed(Monitor *mon, const QDict *qdict, QObject **ret_data)
     }
     max_throttle = d;
 
+    qemu_mutex_lock_migthread();
     s = migrate_to_fms(current_migration);
     if (s && s->file) {
         qemu_file_set_rate_limit(s->file, max_throttle);
     }
+    qemu_mutex_unlock_migthread();
 
     return 0;
 }
@@ -284,8 +286,6 @@ int migrate_fd_cleanup(FdMigrationState *s)
 {
     int ret = 0;
 
-    qemu_set_fd_handler2(s->fd, NULL, NULL, NULL, NULL);
-
     if (s->file) {
         DPRINTF("closing file\n");
         if (qemu_fclose(s->file) != 0) {
@@ -307,14 +307,6 @@ int migrate_fd_cleanup(FdMigrationState *s)
     return ret;
 }
 
-void migrate_fd_put_notify(void *opaque)
-{
-    FdMigrationState *s = opaque;
-
-    qemu_set_fd_handler2(s->fd, NULL, NULL, NULL, NULL);
-    qemu_file_put_notify(s->file);
-}
-
 ssize_t migrate_fd_put_buffer(void *opaque, const void *data, size_t size)
 {
     FdMigrationState *s = opaque;
@@ -327,76 +319,91 @@ ssize_t migrate_fd_put_buffer(void *opaque, const void *data, size_t size)
     if (ret == -1)
         ret = -(s->get_error(s));
 
-    if (ret == -EAGAIN) {
-        qemu_set_fd_handler2(s->fd, NULL, NULL, migrate_fd_put_notify, s);
-    } else if (ret < 0) {
-        if (s->mon) {
-            monitor_resume(s->mon);
+    return ret;
+}
+
+static void migrate_fd_terminate(void *opaque)
+{
+    FdMigrationState *s = opaque;
+
+    qemu_mutex_lock_migthread();
+
+    if (s->code == COMPLETE) {
+        if (migrate_fd_cleanup(s) < 0) {
+            if (s->old_vm_running) {
+                vm_start();
+            }
+            s->state = MIG_STATE_ERROR;
+        } else {
+            s->state = MIG_STATE_COMPLETED;
         }
-        s->state = MIG_STATE_ERROR;
         notifier_list_notify(&migration_state_notifiers);
+    } else if (s->code == RESUME) {
+        if (s->old_vm_running) {
+            vm_start();
+        }
+        migrate_fd_error(s);
+    } else if (s->code == ERROR) {
+        migrate_fd_error(s);
     }
 
-    return ret;
+    qemu_mutex_unlock_migthread();
 }
 
 void migrate_fd_connect(FdMigrationState *s)
 {
-    int ret;
-
+    s->code = START;
+    s->bh = qemu_bh_new(migrate_fd_terminate, s);
     s->file = qemu_fopen_ops_buffered(s,
                                       s->bandwidth_limit,
                                       migrate_fd_put_buffer,
                                       migrate_fd_put_ready,
                                       migrate_fd_wait_for_unfreeze,
                                       migrate_fd_close);
-
-    DPRINTF("beginning savevm\n");
-    ret = qemu_savevm_state_begin(s->mon, s->file, s->mig_state.blk,
-                                  s->mig_state.shared);
-    if (ret < 0) {
-        DPRINTF("failed, %d\n", ret);
-        migrate_fd_error(s);
-        return;
-    }
-    
-    migrate_fd_put_ready(s);
 }
 
 void migrate_fd_put_ready(void *opaque)
 {
     FdMigrationState *s = opaque;
+    int ret;
 
-    if (s->state != MIG_STATE_ACTIVE) {
+    qemu_mutex_lock_iothread();
+    if (s->code != ACTIVE && s->code != START) {
         DPRINTF("put_ready returning because of non-active state\n");
+        qemu_mutex_unlock_iothread();
         return;
     }
 
+    if (!s->code) {
+        DPRINTF("beginning savevm\n");
+        ret = qemu_savevm_state_begin(s->mon, s->file, s->mig_state.blk,
+                s->mig_state.shared);
+        if (ret < 0) {
+            DPRINTF("failed, %d\n", ret);
+            s->code = ERROR;
+            qemu_bh_schedule(s->bh);
+            qemu_mutex_unlock_iothread();
+            return;
+        }
+        s->code = ACTIVE;
+    }
+
     DPRINTF("iterate\n");
     if (qemu_savevm_state_iterate(s->mon, s->file) == 1) {
-        int state;
-        int old_vm_running = vm_running;
+        s->old_vm_running = vm_running;
 
         DPRINTF("done iterating\n");
         vm_stop(VMSTOP_MIGRATE);
 
         if ((qemu_savevm_state_complete(s->mon, s->file)) < 0) {
-            if (old_vm_running) {
-                vm_start();
-            }
-            state = MIG_STATE_ERROR;
+            s->code = RESUME;
         } else {
-            state = MIG_STATE_COMPLETED;
-        }
-        if (migrate_fd_cleanup(s) < 0) {
-            if (old_vm_running) {
-                vm_start();
-            }
-            state = MIG_STATE_ERROR;
+            s->code = COMPLETE;
         }
-        s->state = state;
-        notifier_list_notify(&migration_state_notifiers);
+
+        qemu_bh_schedule(s->bh);
     }
+    qemu_mutex_unlock_iothread();
 }
 
 int migrate_fd_get_status(MigrationState *mig_state)
@@ -416,9 +423,11 @@ void migrate_fd_cancel(MigrationState *mig_state)
 
     s->state = MIG_STATE_CANCELLED;
     notifier_list_notify(&migration_state_notifiers);
-    qemu_savevm_state_cancel(s->mon, s->file);
 
+    qemu_mutex_lock_migthread();
+    qemu_savevm_state_cancel(s->mon, s->file);
     migrate_fd_cleanup(s);
+    qemu_mutex_unlock_migthread();
 }
 
 void migrate_fd_release(MigrationState *mig_state)
@@ -426,22 +435,34 @@ void migrate_fd_release(MigrationState *mig_state)
     FdMigrationState *s = migrate_to_fms(mig_state);
 
     DPRINTF("releasing state\n");
-   
+
     if (s->state == MIG_STATE_ACTIVE) {
         s->state = MIG_STATE_CANCELLED;
         notifier_list_notify(&migration_state_notifiers);
+        qemu_mutex_lock_migthread();
         migrate_fd_cleanup(s);
+        qemu_mutex_unlock_migthread();
+    }
+
+    if (s->bh) {
+        qemu_bh_delete(s->bh);
     }
+
     qemu_free(s);
 }
 
 void migrate_fd_wait_for_unfreeze(void *opaque)
 {
     FdMigrationState *s = opaque;
-    int ret;
+    int ret, state;
 
     DPRINTF("wait for unfreeze\n");
-    if (s->state != MIG_STATE_ACTIVE)
+
+    qemu_mutex_lock_iothread();
+    state = s->state;
+    qemu_mutex_unlock_iothread();
+
+    if (state != MIG_STATE_ACTIVE)
         return;
 
     do {
@@ -458,7 +479,6 @@ int migrate_fd_close(void *opaque)
 {
     FdMigrationState *s = opaque;
 
-    qemu_set_fd_handler2(s->fd, NULL, NULL, NULL, NULL);
     return s->close(s);
 }
 
diff --git a/migration.h b/migration.h
index 050c56c..abbf9e4 100644
--- a/migration.h
+++ b/migration.h
@@ -23,6 +23,12 @@
 #define MIG_STATE_CANCELLED	1
 #define MIG_STATE_ACTIVE	2
 
+#define START       0
+#define ACTIVE      1
+#define COMPLETE    2
+#define ERROR       3
+#define RESUME      4
+
 typedef struct MigrationState MigrationState;
 
 struct MigrationState
@@ -45,10 +51,13 @@ struct FdMigrationState
     int fd;
     Monitor *mon;
     int state;
+    int code;
+    int old_vm_running;
     int (*get_error)(struct FdMigrationState*);
     int (*close)(struct FdMigrationState*);
     int (*write)(struct FdMigrationState*, const void *, size_t);
     void *opaque;
+    QEMUBH *bh;
 };
 
 void process_incoming_migration(QEMUFile *f);
diff --git a/qemu-thread-posix.c b/qemu-thread-posix.c
index 2bd02ef..6a275be 100644
--- a/qemu-thread-posix.c
+++ b/qemu-thread-posix.c
@@ -115,6 +115,16 @@ void qemu_cond_wait(QemuCond *cond, QemuMutex *mutex)
         error_exit(err, __func__);
 }
 
+void qemu_thread_join(QemuThread *thread)
+{
+    int err;
+
+    err = pthread_join(thread->thread, NULL);
+    if (err) {
+        error_exit(err, __func__);
+    }
+}
+
 void qemu_thread_create(QemuThread *thread,
                        void *(*start_routine)(void*),
                        void *arg)
diff --git a/qemu-thread.h b/qemu-thread.h
index 0a73d50..d5b99d5 100644
--- a/qemu-thread.h
+++ b/qemu-thread.h
@@ -30,6 +30,7 @@ void qemu_cond_destroy(QemuCond *cond);
 void qemu_cond_signal(QemuCond *cond);
 void qemu_cond_broadcast(QemuCond *cond);
 void qemu_cond_wait(QemuCond *cond, QemuMutex *mutex);
+void qemu_thread_join(QemuThread *thread);
 
 void qemu_thread_create(QemuThread *thread,
                        void *(*start_routine)(void*),
diff --git a/savevm.c b/savevm.c
index 8139bc7..f54f555 100644
--- a/savevm.c
+++ b/savevm.c
@@ -481,11 +481,6 @@ int qemu_fclose(QEMUFile *f)
     return ret;
 }
 
-void qemu_file_put_notify(QEMUFile *f)
-{
-    f->put_buffer(f->opaque, NULL, 0, 0);
-}
-
 void qemu_put_buffer(QEMUFile *f, const uint8_t *buf, int size)
 {
     int l;
-- 
1.7.4.1

^ permalink raw reply related	[flat|nested] 20+ messages in thread

* Re: [Qemu-devel] [RFC PATCH v5 0/4] Separate thread for VM migration
  2011-08-24  3:12 ` [Qemu-devel] " Umesh Deshpande
@ 2011-08-24 17:19   ` Anthony Liguori
  -1 siblings, 0 replies; 20+ messages in thread
From: Anthony Liguori @ 2011-08-24 17:19 UTC (permalink / raw)
  To: Umesh Deshpande; +Cc: kvm, qemu-devel, pbonzini, mtosatti, quintela

On 08/23/2011 10:12 PM, Umesh Deshpande wrote:
> Following patch series deals with VCPU and iothread starvation during the
> migration of a guest. Currently the iothread is responsible for performing the
> guest migration. It holds qemu_mutex during the migration and doesn't allow VCPU
> to enter the qemu mode and delays its return to the guest. The guest migration,
> executed as an iohandler also delays the execution of other iohandlers.
> In the following patch series,

Can you please include detailed performance data with and without this 
series?

Perhaps runs of migration with jitterd running in the guest.

Regards,

Anthony Liguori

>
> The migration has been moved to a separate thread to
> reduce the qemu_mutex contention and iohandler starvation.
>
> Umesh Deshpande (4):
>    MRU ram block list
>    migration thread mutex
>    separate migration bitmap
>    separate migration thread
>
>   arch_init.c         |   38 ++++++++++++----
>   buffered_file.c     |   75 +++++++++++++++++--------------
>   cpu-all.h           |   42 +++++++++++++++++
>   exec.c              |   97 ++++++++++++++++++++++++++++++++++++++--
>   migration.c         |  122 +++++++++++++++++++++++++++++---------------------
>   migration.h         |    9 ++++
>   qemu-common.h       |    2 +
>   qemu-thread-posix.c |   10 ++++
>   qemu-thread.h       |    1 +
>   savevm.c            |    5 --
>   10 files changed, 297 insertions(+), 104 deletions(-)
>


^ permalink raw reply	[flat|nested] 20+ messages in thread

* Re: [Qemu-devel] [RFC PATCH v5 0/4] Separate thread for VM migration
@ 2011-08-24 17:19   ` Anthony Liguori
  0 siblings, 0 replies; 20+ messages in thread
From: Anthony Liguori @ 2011-08-24 17:19 UTC (permalink / raw)
  To: Umesh Deshpande; +Cc: pbonzini, mtosatti, qemu-devel, kvm, quintela

On 08/23/2011 10:12 PM, Umesh Deshpande wrote:
> Following patch series deals with VCPU and iothread starvation during the
> migration of a guest. Currently the iothread is responsible for performing the
> guest migration. It holds qemu_mutex during the migration and doesn't allow VCPU
> to enter the qemu mode and delays its return to the guest. The guest migration,
> executed as an iohandler also delays the execution of other iohandlers.
> In the following patch series,

Can you please include detailed performance data with and without this 
series?

Perhaps runs of migration with jitterd running in the guest.

Regards,

Anthony Liguori

>
> The migration has been moved to a separate thread to
> reduce the qemu_mutex contention and iohandler starvation.
>
> Umesh Deshpande (4):
>    MRU ram block list
>    migration thread mutex
>    separate migration bitmap
>    separate migration thread
>
>   arch_init.c         |   38 ++++++++++++----
>   buffered_file.c     |   75 +++++++++++++++++--------------
>   cpu-all.h           |   42 +++++++++++++++++
>   exec.c              |   97 ++++++++++++++++++++++++++++++++++++++--
>   migration.c         |  122 +++++++++++++++++++++++++++++---------------------
>   migration.h         |    9 ++++
>   qemu-common.h       |    2 +
>   qemu-thread-posix.c |   10 ++++
>   qemu-thread.h       |    1 +
>   savevm.c            |    5 --
>   10 files changed, 297 insertions(+), 104 deletions(-)
>

^ permalink raw reply	[flat|nested] 20+ messages in thread

* Re: [RFC PATCH v5 0/4] Separate thread for VM migration
  2011-08-24 17:19   ` Anthony Liguori
@ 2011-08-25  6:25     ` Umesh Deshpande
  -1 siblings, 0 replies; 20+ messages in thread
From: Umesh Deshpande @ 2011-08-25  6:25 UTC (permalink / raw)
  To: Anthony Liguori; +Cc: pbonzini, mtosatti, qemu-devel, kvm, quintela

[-- Attachment #1: Type: text/plain, Size: 2361 bytes --]

*Jitterd Test*
I ran jitterd in a migrating VM of size 8GB with and w/o the patch series.
./jitterd -f -m 1 -p 100 -r 40
That is to report the jitter of greater than 400ms during the interval 
of 40 seconds.

Jitter in ms. with the migration thread.
Run    Total (Peak)
1        No chatter
2        No chatter
3        No chatter
4        409 (360)

Jitter in ms. without migration thread.
Run    Total (Peak)
1        4663 (2413)
2        643 (423)
3        1973 (1817)
4        3908 (3772)

*Flood ping test* : ping to the migrating VM from a third machine (data 
over 3 runs)
Latency (ms) ping to a non-migrating VM    : Avg 0.156, Max: 0.96
Latency (ms) with migration thread             : Avg 0.215, Max: 280
Latency (ms) without migration thread        : Avg 6.47,   Max: 4562

- Umesh


On 08/24/2011 01:19 PM, Anthony Liguori wrote:
> On 08/23/2011 10:12 PM, Umesh Deshpande wrote:
>> Following patch series deals with VCPU and iothread starvation during 
>> the
>> migration of a guest. Currently the iothread is responsible for 
>> performing the
>> guest migration. It holds qemu_mutex during the migration and doesn't 
>> allow VCPU
>> to enter the qemu mode and delays its return to the guest. The guest 
>> migration,
>> executed as an iohandler also delays the execution of other iohandlers.
>> In the following patch series,
>
> Can you please include detailed performance data with and without this 
> series?
>
> Perhaps runs of migration with jitterd running in the guest.
>
> Regards,
>
> Anthony Liguori
>
>>
>> The migration has been moved to a separate thread to
>> reduce the qemu_mutex contention and iohandler starvation.
>>
>> Umesh Deshpande (4):
>>    MRU ram block list
>>    migration thread mutex
>>    separate migration bitmap
>>    separate migration thread
>>
>>   arch_init.c         |   38 ++++++++++++----
>>   buffered_file.c     |   75 +++++++++++++++++--------------
>>   cpu-all.h           |   42 +++++++++++++++++
>>   exec.c              |   97 ++++++++++++++++++++++++++++++++++++++--
>>   migration.c         |  122 
>> +++++++++++++++++++++++++++++---------------------
>>   migration.h         |    9 ++++
>>   qemu-common.h       |    2 +
>>   qemu-thread-posix.c |   10 ++++
>>   qemu-thread.h       |    1 +
>>   savevm.c            |    5 --
>>   10 files changed, 297 insertions(+), 104 deletions(-)
>>
>


[-- Attachment #2: Type: text/html, Size: 4588 bytes --]

^ permalink raw reply	[flat|nested] 20+ messages in thread

* Re: [Qemu-devel] [RFC PATCH v5 0/4] Separate thread for VM migration
@ 2011-08-25  6:25     ` Umesh Deshpande
  0 siblings, 0 replies; 20+ messages in thread
From: Umesh Deshpande @ 2011-08-25  6:25 UTC (permalink / raw)
  To: Anthony Liguori; +Cc: pbonzini, mtosatti, qemu-devel, kvm, quintela

[-- Attachment #1: Type: text/plain, Size: 2361 bytes --]

*Jitterd Test*
I ran jitterd in a migrating VM of size 8GB with and w/o the patch series.
./jitterd -f -m 1 -p 100 -r 40
That is to report the jitter of greater than 400ms during the interval 
of 40 seconds.

Jitter in ms. with the migration thread.
Run    Total (Peak)
1        No chatter
2        No chatter
3        No chatter
4        409 (360)

Jitter in ms. without migration thread.
Run    Total (Peak)
1        4663 (2413)
2        643 (423)
3        1973 (1817)
4        3908 (3772)

*Flood ping test* : ping to the migrating VM from a third machine (data 
over 3 runs)
Latency (ms) ping to a non-migrating VM    : Avg 0.156, Max: 0.96
Latency (ms) with migration thread             : Avg 0.215, Max: 280
Latency (ms) without migration thread        : Avg 6.47,   Max: 4562

- Umesh


On 08/24/2011 01:19 PM, Anthony Liguori wrote:
> On 08/23/2011 10:12 PM, Umesh Deshpande wrote:
>> Following patch series deals with VCPU and iothread starvation during 
>> the
>> migration of a guest. Currently the iothread is responsible for 
>> performing the
>> guest migration. It holds qemu_mutex during the migration and doesn't 
>> allow VCPU
>> to enter the qemu mode and delays its return to the guest. The guest 
>> migration,
>> executed as an iohandler also delays the execution of other iohandlers.
>> In the following patch series,
>
> Can you please include detailed performance data with and without this 
> series?
>
> Perhaps runs of migration with jitterd running in the guest.
>
> Regards,
>
> Anthony Liguori
>
>>
>> The migration has been moved to a separate thread to
>> reduce the qemu_mutex contention and iohandler starvation.
>>
>> Umesh Deshpande (4):
>>    MRU ram block list
>>    migration thread mutex
>>    separate migration bitmap
>>    separate migration thread
>>
>>   arch_init.c         |   38 ++++++++++++----
>>   buffered_file.c     |   75 +++++++++++++++++--------------
>>   cpu-all.h           |   42 +++++++++++++++++
>>   exec.c              |   97 ++++++++++++++++++++++++++++++++++++++--
>>   migration.c         |  122 
>> +++++++++++++++++++++++++++++---------------------
>>   migration.h         |    9 ++++
>>   qemu-common.h       |    2 +
>>   qemu-thread-posix.c |   10 ++++
>>   qemu-thread.h       |    1 +
>>   savevm.c            |    5 --
>>   10 files changed, 297 insertions(+), 104 deletions(-)
>>
>


[-- Attachment #2: Type: text/html, Size: 4588 bytes --]

^ permalink raw reply	[flat|nested] 20+ messages in thread

* Re: [RFC PATCH v5 0/4] Separate thread for VM migration
  2011-08-24 17:19   ` Anthony Liguori
@ 2011-08-25  6:29     ` Umesh Deshpande
  -1 siblings, 0 replies; 20+ messages in thread
From: Umesh Deshpande @ 2011-08-25  6:29 UTC (permalink / raw)
  To: Anthony Liguori; +Cc: pbonzini, mtosatti, qemu-devel, kvm, quintela

Jitterd Test
I ran jitterd in a migrating VM of size 8GB with and w/o the patch series.
./jitterd -f -m 1 -p 100 -r 40
That is to report the jitter of greater than 400ms during the interval 
of 40 seconds.

Jitter in ms. with the migration thread.
Run    Total (Peak)
1        No chatter
2        No chatter
3        No chatter
4        409 (360)

Jitter in ms. without migration thread.
Run    Total (Peak)
1        4663 (2413)
2        643 (423)
3        1973 (1817)
4        3908 (3772)

--------------------------------------------------------------
Flood ping test : ping to the migrating VM from a third machine (data 
over 3 runs)
Latency (ms) ping to a non-migrating VM    : Avg 0.156, Max: 0.96
Latency (ms) with migration thread             : Avg 0.215, Max: 280
Latency (ms) without migration thread        : Avg 6.47,   Max: 4562

- Umesh


On 08/24/2011 01:19 PM, Anthony Liguori wrote:
> On 08/23/2011 10:12 PM, Umesh Deshpande wrote:
>> Following patch series deals with VCPU and iothread starvation during 
>> the
>> migration of a guest. Currently the iothread is responsible for 
>> performing the
>> guest migration. It holds qemu_mutex during the migration and doesn't 
>> allow VCPU
>> to enter the qemu mode and delays its return to the guest. The guest 
>> migration,
>> executed as an iohandler also delays the execution of other iohandlers.
>> In the following patch series,
>
> Can you please include detailed performance data with and without this 
> series?
>
> Perhaps runs of migration with jitterd running in the guest.
>
> Regards,
>
> Anthony Liguori
>
>>
>> The migration has been moved to a separate thread to
>> reduce the qemu_mutex contention and iohandler starvation.
>>
>> Umesh Deshpande (4):
>>    MRU ram block list
>>    migration thread mutex
>>    separate migration bitmap
>>    separate migration thread
>>
>>   arch_init.c         |   38 ++++++++++++----
>>   buffered_file.c     |   75 +++++++++++++++++--------------
>>   cpu-all.h           |   42 +++++++++++++++++
>>   exec.c              |   97 ++++++++++++++++++++++++++++++++++++++--
>>   migration.c         |  122 
>> +++++++++++++++++++++++++++++---------------------
>>   migration.h         |    9 ++++
>>   qemu-common.h       |    2 +
>>   qemu-thread-posix.c |   10 ++++
>>   qemu-thread.h       |    1 +
>>   savevm.c            |    5 --
>>   10 files changed, 297 insertions(+), 104 deletions(-)
>>
>

^ permalink raw reply	[flat|nested] 20+ messages in thread

* Re: [Qemu-devel] [RFC PATCH v5 0/4] Separate thread for VM migration
@ 2011-08-25  6:29     ` Umesh Deshpande
  0 siblings, 0 replies; 20+ messages in thread
From: Umesh Deshpande @ 2011-08-25  6:29 UTC (permalink / raw)
  To: Anthony Liguori; +Cc: pbonzini, mtosatti, qemu-devel, kvm, quintela

Jitterd Test
I ran jitterd in a migrating VM of size 8GB with and w/o the patch series.
./jitterd -f -m 1 -p 100 -r 40
That is to report the jitter of greater than 400ms during the interval 
of 40 seconds.

Jitter in ms. with the migration thread.
Run    Total (Peak)
1        No chatter
2        No chatter
3        No chatter
4        409 (360)

Jitter in ms. without migration thread.
Run    Total (Peak)
1        4663 (2413)
2        643 (423)
3        1973 (1817)
4        3908 (3772)

--------------------------------------------------------------
Flood ping test : ping to the migrating VM from a third machine (data 
over 3 runs)
Latency (ms) ping to a non-migrating VM    : Avg 0.156, Max: 0.96
Latency (ms) with migration thread             : Avg 0.215, Max: 280
Latency (ms) without migration thread        : Avg 6.47,   Max: 4562

- Umesh


On 08/24/2011 01:19 PM, Anthony Liguori wrote:
> On 08/23/2011 10:12 PM, Umesh Deshpande wrote:
>> Following patch series deals with VCPU and iothread starvation during 
>> the
>> migration of a guest. Currently the iothread is responsible for 
>> performing the
>> guest migration. It holds qemu_mutex during the migration and doesn't 
>> allow VCPU
>> to enter the qemu mode and delays its return to the guest. The guest 
>> migration,
>> executed as an iohandler also delays the execution of other iohandlers.
>> In the following patch series,
>
> Can you please include detailed performance data with and without this 
> series?
>
> Perhaps runs of migration with jitterd running in the guest.
>
> Regards,
>
> Anthony Liguori
>
>>
>> The migration has been moved to a separate thread to
>> reduce the qemu_mutex contention and iohandler starvation.
>>
>> Umesh Deshpande (4):
>>    MRU ram block list
>>    migration thread mutex
>>    separate migration bitmap
>>    separate migration thread
>>
>>   arch_init.c         |   38 ++++++++++++----
>>   buffered_file.c     |   75 +++++++++++++++++--------------
>>   cpu-all.h           |   42 +++++++++++++++++
>>   exec.c              |   97 ++++++++++++++++++++++++++++++++++++++--
>>   migration.c         |  122 
>> +++++++++++++++++++++++++++++---------------------
>>   migration.h         |    9 ++++
>>   qemu-common.h       |    2 +
>>   qemu-thread-posix.c |   10 ++++
>>   qemu-thread.h       |    1 +
>>   savevm.c            |    5 --
>>   10 files changed, 297 insertions(+), 104 deletions(-)
>>
>

^ permalink raw reply	[flat|nested] 20+ messages in thread

* Re: [Qemu-devel] [RFC PATCH v5 0/4] Separate thread for VM migration
  2011-08-25  6:29     ` [Qemu-devel] " Umesh Deshpande
@ 2011-08-25  6:35       ` Avi Kivity
  -1 siblings, 0 replies; 20+ messages in thread
From: Avi Kivity @ 2011-08-25  6:35 UTC (permalink / raw)
  To: Umesh Deshpande
  Cc: Anthony Liguori, pbonzini, mtosatti, qemu-devel, kvm, quintela

On 08/25/2011 09:29 AM, Umesh Deshpande wrote:
> Jitterd Test
> I ran jitterd in a migrating VM of size 8GB with and w/o the patch 
> series.
> ./jitterd -f -m 1 -p 100 -r 40
> That is to report the jitter of greater than 400ms during the interval 
> of 40 seconds.
>
> Jitter in ms. with the migration thread.
> Run    Total (Peak)
> 1        No chatter
> 2        No chatter
> 3        No chatter
> 4        409 (360)
>
> Jitter in ms. without migration thread.
> Run    Total (Peak)
> 1        4663 (2413)
> 2        643 (423)
> 3        1973 (1817)
> 4        3908 (3772)
>
> --------------------------------------------------------------
> Flood ping test : ping to the migrating VM from a third machine (data 
> over 3 runs)
> Latency (ms) ping to a non-migrating VM    : Avg 0.156, Max: 0.96
> Latency (ms) with migration thread             : Avg 0.215, Max: 280
> Latency (ms) without migration thread        : Avg 6.47,   Max: 4562
>

Very impressive numbers.

-- 
I have a truly marvellous patch that fixes the bug which this
signature is too narrow to contain.


^ permalink raw reply	[flat|nested] 20+ messages in thread

* Re: [Qemu-devel] [RFC PATCH v5 0/4] Separate thread for VM migration
@ 2011-08-25  6:35       ` Avi Kivity
  0 siblings, 0 replies; 20+ messages in thread
From: Avi Kivity @ 2011-08-25  6:35 UTC (permalink / raw)
  To: Umesh Deshpande; +Cc: kvm, quintela, mtosatti, qemu-devel, pbonzini

On 08/25/2011 09:29 AM, Umesh Deshpande wrote:
> Jitterd Test
> I ran jitterd in a migrating VM of size 8GB with and w/o the patch 
> series.
> ./jitterd -f -m 1 -p 100 -r 40
> That is to report the jitter of greater than 400ms during the interval 
> of 40 seconds.
>
> Jitter in ms. with the migration thread.
> Run    Total (Peak)
> 1        No chatter
> 2        No chatter
> 3        No chatter
> 4        409 (360)
>
> Jitter in ms. without migration thread.
> Run    Total (Peak)
> 1        4663 (2413)
> 2        643 (423)
> 3        1973 (1817)
> 4        3908 (3772)
>
> --------------------------------------------------------------
> Flood ping test : ping to the migrating VM from a third machine (data 
> over 3 runs)
> Latency (ms) ping to a non-migrating VM    : Avg 0.156, Max: 0.96
> Latency (ms) with migration thread             : Avg 0.215, Max: 280
> Latency (ms) without migration thread        : Avg 6.47,   Max: 4562
>

Very impressive numbers.

-- 
I have a truly marvellous patch that fixes the bug which this
signature is too narrow to contain.

^ permalink raw reply	[flat|nested] 20+ messages in thread

* Re: [RFC PATCH v5 2/4] Migration thread mutex
  2011-08-24  3:12   ` [Qemu-devel] " Umesh Deshpande
@ 2011-08-26 17:00     ` Marcelo Tosatti
  -1 siblings, 0 replies; 20+ messages in thread
From: Marcelo Tosatti @ 2011-08-26 17:00 UTC (permalink / raw)
  To: Umesh Deshpande; +Cc: kvm, qemu-devel, pbonzini, quintela

On Tue, Aug 23, 2011 at 11:12:48PM -0400, Umesh Deshpande wrote:
> ramlist mutex is implemented to protect the RAMBlock list traversal in the
> migration thread from their addition/removal from the iothread.
> 
> Note: Combination of iothread mutex and migration thread mutex works as a
> rw-lock. Both mutexes are acquired while modifying the ram_list members or RAM
> block list.
> 
> Signed-off-by: Umesh Deshpande <udeshpan@redhat.com>
> ---
>  arch_init.c   |   21 +++++++++++++++++++++
>  cpu-all.h     |    3 +++
>  exec.c        |   23 +++++++++++++++++++++++
>  qemu-common.h |    2 ++
>  4 files changed, 49 insertions(+), 0 deletions(-)
> 
> diff --git a/arch_init.c b/arch_init.c
> index 484b39d..9d02270 100644
> --- a/arch_init.c
> +++ b/arch_init.c
> @@ -109,6 +109,7 @@ static int is_dup_page(uint8_t *page, uint8_t ch)
>  
>  static RAMBlock *last_block;
>  static ram_addr_t last_offset;
> +static uint64_t last_version;
>  
>  static int ram_save_block(QEMUFile *f)
>  {
> @@ -170,6 +171,7 @@ static int ram_save_block(QEMUFile *f)
>  
>      last_block = block;
>      last_offset = offset;
> +    last_version = ram_list.version;
>  
>      return bytes_sent;
>  }
> @@ -270,6 +272,7 @@ int ram_save_live(Monitor *mon, QEMUFile *f, int stage, void *opaque)
>          bytes_transferred = 0;
>          last_block = NULL;
>          last_offset = 0;
> +        last_version = ram_list.version = 0;
>          sort_ram_list();
>  
>          /* Make sure all dirty bits are set */
> @@ -298,6 +301,17 @@ int ram_save_live(Monitor *mon, QEMUFile *f, int stage, void *opaque)
>      bytes_transferred_last = bytes_transferred;
>      bwidth = qemu_get_clock_ns(rt_clock);
>  
> +    if (stage != 3) {
> +        qemu_mutex_lock_migthread();
> +        qemu_mutex_unlock_iothread();
> +    }
> +
> +    if (ram_list.version != last_version) {
> +        /* RAM block added or removed */
> +        last_block = NULL;
> +        last_offset = 0;
> +    }
> +
>      while (!qemu_file_rate_limit(f)) {
>          int bytes_sent;
>  
> @@ -308,6 +322,13 @@ int ram_save_live(Monitor *mon, QEMUFile *f, int stage, void *opaque)
>          }
>      }
>  
> +    if (stage != 3) {
> +        qemu_mutex_unlock_migthread();
> +        qemu_mutex_lock_iothread();
> +        /* Lock ordering : iothread mutex is always acquired outside migthread
> +         * mutex critical section to avoid deadlock */
> +    }
> +
>      bwidth = qemu_get_clock_ns(rt_clock) - bwidth;
>      bwidth = (bytes_transferred - bytes_transferred_last) / bwidth;
>  
> diff --git a/cpu-all.h b/cpu-all.h
> index 6b217a2..b85483f 100644
> --- a/cpu-all.h
> +++ b/cpu-all.h
> @@ -21,6 +21,7 @@
>  
>  #include "qemu-common.h"
>  #include "cpu-common.h"
> +#include "qemu-thread.h"
>  
>  /* some important defines:
>   *
> @@ -932,7 +933,9 @@ typedef struct RAMBlock {
>  } RAMBlock;
>  
>  typedef struct RAMList {
> +    QemuMutex mutex;    /* Protects RAM block list */
>      uint8_t *phys_dirty;
> +    uint32_t version;   /* To detect ram block addition/removal */
>      QLIST_HEAD(ram, RAMBlock) blocks;
>      QLIST_HEAD(, RAMBlock) blocks_mru;
>  } RAMList;
> diff --git a/exec.c b/exec.c
> index c5c247c..7627483 100644
> --- a/exec.c
> +++ b/exec.c
> @@ -582,6 +582,7 @@ void cpu_exec_init_all(unsigned long tb_size)
>      code_gen_alloc(tb_size);
>      code_gen_ptr = code_gen_buffer;
>      page_init();
> +    qemu_mutex_init(&ram_list.mutex);
>  #if !defined(CONFIG_USER_ONLY)
>      io_mem_init();
>  #endif
> @@ -2802,6 +2803,16 @@ static long gethugepagesize(const char *path)
>      return fs.f_bsize;
>  }
>  
> +void qemu_mutex_lock_migthread(void)
> +{
> +    qemu_mutex_lock(&ram_list.mutex);
> +}

qemu_mutex_lock_ramlist is a better name, _migthread is confusing.


^ permalink raw reply	[flat|nested] 20+ messages in thread

* Re: [Qemu-devel] [RFC PATCH v5 2/4] Migration thread mutex
@ 2011-08-26 17:00     ` Marcelo Tosatti
  0 siblings, 0 replies; 20+ messages in thread
From: Marcelo Tosatti @ 2011-08-26 17:00 UTC (permalink / raw)
  To: Umesh Deshpande; +Cc: pbonzini, qemu-devel, kvm, quintela

On Tue, Aug 23, 2011 at 11:12:48PM -0400, Umesh Deshpande wrote:
> ramlist mutex is implemented to protect the RAMBlock list traversal in the
> migration thread from their addition/removal from the iothread.
> 
> Note: Combination of iothread mutex and migration thread mutex works as a
> rw-lock. Both mutexes are acquired while modifying the ram_list members or RAM
> block list.
> 
> Signed-off-by: Umesh Deshpande <udeshpan@redhat.com>
> ---
>  arch_init.c   |   21 +++++++++++++++++++++
>  cpu-all.h     |    3 +++
>  exec.c        |   23 +++++++++++++++++++++++
>  qemu-common.h |    2 ++
>  4 files changed, 49 insertions(+), 0 deletions(-)
> 
> diff --git a/arch_init.c b/arch_init.c
> index 484b39d..9d02270 100644
> --- a/arch_init.c
> +++ b/arch_init.c
> @@ -109,6 +109,7 @@ static int is_dup_page(uint8_t *page, uint8_t ch)
>  
>  static RAMBlock *last_block;
>  static ram_addr_t last_offset;
> +static uint64_t last_version;
>  
>  static int ram_save_block(QEMUFile *f)
>  {
> @@ -170,6 +171,7 @@ static int ram_save_block(QEMUFile *f)
>  
>      last_block = block;
>      last_offset = offset;
> +    last_version = ram_list.version;
>  
>      return bytes_sent;
>  }
> @@ -270,6 +272,7 @@ int ram_save_live(Monitor *mon, QEMUFile *f, int stage, void *opaque)
>          bytes_transferred = 0;
>          last_block = NULL;
>          last_offset = 0;
> +        last_version = ram_list.version = 0;
>          sort_ram_list();
>  
>          /* Make sure all dirty bits are set */
> @@ -298,6 +301,17 @@ int ram_save_live(Monitor *mon, QEMUFile *f, int stage, void *opaque)
>      bytes_transferred_last = bytes_transferred;
>      bwidth = qemu_get_clock_ns(rt_clock);
>  
> +    if (stage != 3) {
> +        qemu_mutex_lock_migthread();
> +        qemu_mutex_unlock_iothread();
> +    }
> +
> +    if (ram_list.version != last_version) {
> +        /* RAM block added or removed */
> +        last_block = NULL;
> +        last_offset = 0;
> +    }
> +
>      while (!qemu_file_rate_limit(f)) {
>          int bytes_sent;
>  
> @@ -308,6 +322,13 @@ int ram_save_live(Monitor *mon, QEMUFile *f, int stage, void *opaque)
>          }
>      }
>  
> +    if (stage != 3) {
> +        qemu_mutex_unlock_migthread();
> +        qemu_mutex_lock_iothread();
> +        /* Lock ordering : iothread mutex is always acquired outside migthread
> +         * mutex critical section to avoid deadlock */
> +    }
> +
>      bwidth = qemu_get_clock_ns(rt_clock) - bwidth;
>      bwidth = (bytes_transferred - bytes_transferred_last) / bwidth;
>  
> diff --git a/cpu-all.h b/cpu-all.h
> index 6b217a2..b85483f 100644
> --- a/cpu-all.h
> +++ b/cpu-all.h
> @@ -21,6 +21,7 @@
>  
>  #include "qemu-common.h"
>  #include "cpu-common.h"
> +#include "qemu-thread.h"
>  
>  /* some important defines:
>   *
> @@ -932,7 +933,9 @@ typedef struct RAMBlock {
>  } RAMBlock;
>  
>  typedef struct RAMList {
> +    QemuMutex mutex;    /* Protects RAM block list */
>      uint8_t *phys_dirty;
> +    uint32_t version;   /* To detect ram block addition/removal */
>      QLIST_HEAD(ram, RAMBlock) blocks;
>      QLIST_HEAD(, RAMBlock) blocks_mru;
>  } RAMList;
> diff --git a/exec.c b/exec.c
> index c5c247c..7627483 100644
> --- a/exec.c
> +++ b/exec.c
> @@ -582,6 +582,7 @@ void cpu_exec_init_all(unsigned long tb_size)
>      code_gen_alloc(tb_size);
>      code_gen_ptr = code_gen_buffer;
>      page_init();
> +    qemu_mutex_init(&ram_list.mutex);
>  #if !defined(CONFIG_USER_ONLY)
>      io_mem_init();
>  #endif
> @@ -2802,6 +2803,16 @@ static long gethugepagesize(const char *path)
>      return fs.f_bsize;
>  }
>  
> +void qemu_mutex_lock_migthread(void)
> +{
> +    qemu_mutex_lock(&ram_list.mutex);
> +}

qemu_mutex_lock_ramlist is a better name, _migthread is confusing.

^ permalink raw reply	[flat|nested] 20+ messages in thread

end of thread, other threads:[~2011-08-27 14:38 UTC | newest]

Thread overview: 20+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2011-08-24  3:12 [RFC PATCH v5 0/4] Separate thread for VM migration Umesh Deshpande
2011-08-24  3:12 ` [Qemu-devel] " Umesh Deshpande
2011-08-24  3:12 ` [RFC PATCH v5 1/4] MRU ram list Umesh Deshpande
2011-08-24  3:12   ` [Qemu-devel] " Umesh Deshpande
2011-08-24  3:12 ` [RFC PATCH v5 2/4] Migration thread mutex Umesh Deshpande
2011-08-24  3:12   ` [Qemu-devel] " Umesh Deshpande
2011-08-26 17:00   ` Marcelo Tosatti
2011-08-26 17:00     ` [Qemu-devel] " Marcelo Tosatti
2011-08-24  3:12 ` [RFC PATCH v5 3/4] Separate migration bitmap Umesh Deshpande
2011-08-24  3:12   ` [Qemu-devel] " Umesh Deshpande
2011-08-24  3:12 ` [RFC PATCH v5 4/4] Separate thread for VM migration Umesh Deshpande
2011-08-24  3:12   ` [Qemu-devel] " Umesh Deshpande
2011-08-24 17:19 ` [Qemu-devel] [RFC PATCH v5 0/4] " Anthony Liguori
2011-08-24 17:19   ` Anthony Liguori
2011-08-25  6:25   ` Umesh Deshpande
2011-08-25  6:25     ` [Qemu-devel] " Umesh Deshpande
2011-08-25  6:29   ` Umesh Deshpande
2011-08-25  6:29     ` [Qemu-devel] " Umesh Deshpande
2011-08-25  6:35     ` Avi Kivity
2011-08-25  6:35       ` Avi Kivity

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.