diff mbox

[V8,15/17] filter-rewriter: handle checkpoint and failover event

Message ID 20180603050546.6827-16-zhangckid@gmail.com (mailing list archive)
State New, archived
Headers show

Commit Message

Zhang Chen June 3, 2018, 5:05 a.m. UTC 
After one round of checkpoint, the states between PVM and SVM
become consistent, so it is unnecessary to adjust the sequence
of net packets for old connections, besides, while failover
happens, filter-rewriter needs to check if it still needs to
adjust sequence of net packets.

Signed-off-by: zhanghailiang <zhang.zhanghailiang@huawei.com>
Signed-off-by: Zhang Chen <zhangckid@gmail.com>
---
 migration/colo.c      | 13 +++++++++++++
 net/filter-rewriter.c | 40 ++++++++++++++++++++++++++++++++++++++++
 2 files changed, 53 insertions(+)

Comments

Jason Wang June 4, 2018, 7:42 a.m. UTC | #1 
On 2018年06月03日 13:05, Zhang Chen wrote:
> After one round of checkpoint, the states between PVM and SVM
> become consistent, so it is unnecessary to adjust the sequence
> of net packets for old connections, besides, while failover
> happens, filter-rewriter needs to check if it still needs to
> adjust sequence of net packets.
>
> Signed-off-by: zhanghailiang <zhang.zhanghailiang@huawei.com>
> Signed-off-by: Zhang Chen <zhangckid@gmail.com>
> ---
>   migration/colo.c      | 13 +++++++++++++
>   net/filter-rewriter.c | 40 ++++++++++++++++++++++++++++++++++++++++
>   2 files changed, 53 insertions(+)
>
> diff --git a/migration/colo.c b/migration/colo.c
> index 442471e088..0bff21d9e5 100644
> --- a/migration/colo.c
> +++ b/migration/colo.c
> @@ -31,6 +31,7 @@
>   #include "qapi/qapi-events-migration.h"
>   #include "qapi/qmp/qerror.h"
>   #include "sysemu/cpus.h"
> +#include "net/filter.h"
>   
>   static bool vmstate_loading;
>   static Notifier packets_compare_notifier;
> @@ -82,6 +83,11 @@ static void secondary_vm_do_failover(void)
>       if (local_err) {
>           error_report_err(local_err);
>       }
> +    /* Notify all filters of all NIC to do checkpoint */
> +    colo_notify_filters_event(COLO_EVENT_FAILOVER, &local_err);
> +    if (local_err) {
> +        error_report_err(local_err);
> +    }
>   
>       if (!autostart) {
>           error_report("\"-S\" qemu option will be ignored in secondary side");
> @@ -800,6 +806,13 @@ void *colo_process_incoming_thread(void *opaque)
>               goto out;
>           }
>   
> +        /* Notify all filters of all NIC to do checkpoint */
> +        colo_notify_filters_event(COLO_EVENT_CHECKPOINT, &local_err);
> +        if (local_err) {
> +            qemu_mutex_unlock_iothread();
> +            goto out;
> +        }
> +

I think the above should belong to another patch.

>           vmstate_loading = false;
>           vm_start();
>           trace_colo_vm_state_change("stop", "run");
> diff --git a/net/filter-rewriter.c b/net/filter-rewriter.c
> index 0909a9a8af..f3c306cc89 100644
> --- a/net/filter-rewriter.c
> +++ b/net/filter-rewriter.c
> @@ -20,6 +20,8 @@
>   #include "qemu/main-loop.h"
>   #include "qemu/iov.h"
>   #include "net/checksum.h"
> +#include "net/colo.h"
> +#include "migration/colo.h"
>   
>   #define FILTER_COLO_REWRITER(obj) \
>       OBJECT_CHECK(RewriterState, (obj), TYPE_FILTER_REWRITER)
> @@ -277,6 +279,43 @@ static ssize_t colo_rewriter_receive_iov(NetFilterState *nf,
>       return 0;
>   }
>   
> +static void reset_seq_offset(gpointer key, gpointer value, gpointer user_data)
> +{
> +    Connection *conn = (Connection *)value;
> +
> +    conn->offset = 0;
> +}
> +
> +static gboolean offset_is_nonzero(gpointer key,
> +                                  gpointer value,
> +                                  gpointer user_data)
> +{
> +    Connection *conn = (Connection *)value;
> +
> +    return conn->offset ? true : false;
> +}
> +
> +static void colo_rewriter_handle_event(NetFilterState *nf, int event,
> +                                       Error **errp)
> +{
> +    RewriterState *rs = FILTER_COLO_REWRITER(nf);
> +
> +    switch (event) {
> +    case COLO_EVENT_CHECKPOINT:
> +        g_hash_table_foreach(rs->connection_track_table,
> +                            reset_seq_offset, NULL);
> +        break;
> +    case COLO_EVENT_FAILOVER:
> +        if (!g_hash_table_find(rs->connection_track_table,
> +                              offset_is_nonzero, NULL)) {
> +            object_property_set_str(OBJECT(nf), "off", "status", errp);
> +        }

I may miss something but I think rewriter should not be turned off even 
after failover?

Thanks

> +        break;
> +    default:
> +        break;
> +    }
> +}
> +
>   static void colo_rewriter_cleanup(NetFilterState *nf)
>   {
>       RewriterState *s = FILTER_COLO_REWRITER(nf);
> @@ -332,6 +371,7 @@ static void colo_rewriter_class_init(ObjectClass *oc, void *data)
>       nfc->setup = colo_rewriter_setup;
>       nfc->cleanup = colo_rewriter_cleanup;
>       nfc->receive_iov = colo_rewriter_receive_iov;
> +    nfc->handle_event = colo_rewriter_handle_event;
>   }
>   
>   static const TypeInfo colo_rewriter_info = {
Zhang Chen June 10, 2018, 5:20 p.m. UTC | #2 
On Mon, Jun 4, 2018 at 3:42 PM, Jason Wang <jasowang@redhat.com> wrote:

>
>
> On 2018年06月03日 13:05, Zhang Chen wrote:
>
>> After one round of checkpoint, the states between PVM and SVM
>> become consistent, so it is unnecessary to adjust the sequence
>> of net packets for old connections, besides, while failover
>> happens, filter-rewriter needs to check if it still needs to
>> adjust sequence of net packets.
>>
>> Signed-off-by: zhanghailiang <zhang.zhanghailiang@huawei.com>
>> Signed-off-by: Zhang Chen <zhangckid@gmail.com>
>> ---
>>   migration/colo.c      | 13 +++++++++++++
>>   net/filter-rewriter.c | 40 ++++++++++++++++++++++++++++++++++++++++
>>   2 files changed, 53 insertions(+)
>>
>> diff --git a/migration/colo.c b/migration/colo.c
>> index 442471e088..0bff21d9e5 100644
>> --- a/migration/colo.c
>> +++ b/migration/colo.c
>> @@ -31,6 +31,7 @@
>>   #include "qapi/qapi-events-migration.h"
>>   #include "qapi/qmp/qerror.h"
>>   #include "sysemu/cpus.h"
>> +#include "net/filter.h"
>>     static bool vmstate_loading;
>>   static Notifier packets_compare_notifier;
>> @@ -82,6 +83,11 @@ static void secondary_vm_do_failover(void)
>>       if (local_err) {
>>           error_report_err(local_err);
>>       }
>> +    /* Notify all filters of all NIC to do checkpoint */
>> +    colo_notify_filters_event(COLO_EVENT_FAILOVER, &local_err);
>> +    if (local_err) {
>> +        error_report_err(local_err);
>> +    }
>>         if (!autostart) {
>>           error_report("\"-S\" qemu option will be ignored in secondary
>> side");
>> @@ -800,6 +806,13 @@ void *colo_process_incoming_thread(void *opaque)
>>               goto out;
>>           }
>>   +        /* Notify all filters of all NIC to do checkpoint */
>> +        colo_notify_filters_event(COLO_EVENT_CHECKPOINT, &local_err);
>> +        if (local_err) {
>> +            qemu_mutex_unlock_iothread();
>> +            goto out;
>> +        }
>> +
>>
>
> I think the above should belong to another patch.
>
>
>
Yes, I will relocate above code.



>           vmstate_loading = false;
>>           vm_start();
>>           trace_colo_vm_state_change("stop", "run");
>> diff --git a/net/filter-rewriter.c b/net/filter-rewriter.c
>> index 0909a9a8af..f3c306cc89 100644
>> --- a/net/filter-rewriter.c
>> +++ b/net/filter-rewriter.c
>> @@ -20,6 +20,8 @@
>>   #include "qemu/main-loop.h"
>>   #include "qemu/iov.h"
>>   #include "net/checksum.h"
>> +#include "net/colo.h"
>> +#include "migration/colo.h"
>>     #define FILTER_COLO_REWRITER(obj) \
>>       OBJECT_CHECK(RewriterState, (obj), TYPE_FILTER_REWRITER)
>> @@ -277,6 +279,43 @@ static ssize_t colo_rewriter_receive_iov(NetFilterState
>> *nf,
>>       return 0;
>>   }
>>   +static void reset_seq_offset(gpointer key, gpointer value, gpointer
>> user_data)
>> +{
>> +    Connection *conn = (Connection *)value;
>> +
>> +    conn->offset = 0;
>> +}
>> +
>> +static gboolean offset_is_nonzero(gpointer key,
>> +                                  gpointer value,
>> +                                  gpointer user_data)
>> +{
>> +    Connection *conn = (Connection *)value;
>> +
>> +    return conn->offset ? true : false;
>> +}
>> +
>> +static void colo_rewriter_handle_event(NetFilterState *nf, int event,
>> +                                       Error **errp)
>> +{
>> +    RewriterState *rs = FILTER_COLO_REWRITER(nf);
>> +
>> +    switch (event) {
>> +    case COLO_EVENT_CHECKPOINT:
>> +        g_hash_table_foreach(rs->connection_track_table,
>> +                            reset_seq_offset, NULL);
>> +        break;
>> +    case COLO_EVENT_FAILOVER:
>> +        if (!g_hash_table_find(rs->connection_track_table,
>> +                              offset_is_nonzero, NULL)) {
>> +            object_property_set_str(OBJECT(nf), "off", "status", errp);
>> +        }
>>
>
> I may miss something but I think rewriter should not be turned off even
> after failover?
>
>
Yes, after failover, rewriter should maintain the connection that created
before failover and turned off for other connections.
I will fix it in next version.
Very thanks your comments Jason~~~


Thanks
Zhang Chen




> Thanks
>
>
> +        break;
>> +    default:
>> +        break;
>> +    }
>> +}
>> +
>>   static void colo_rewriter_cleanup(NetFilterState *nf)
>>   {
>>       RewriterState *s = FILTER_COLO_REWRITER(nf);
>> @@ -332,6 +371,7 @@ static void colo_rewriter_class_init(ObjectClass
>> *oc, void *data)
>>       nfc->setup = colo_rewriter_setup;
>>       nfc->cleanup = colo_rewriter_cleanup;
>>       nfc->receive_iov = colo_rewriter_receive_iov;
>> +    nfc->handle_event = colo_rewriter_handle_event;
>>   }
>>     static const TypeInfo colo_rewriter_info = {
>>
>
>
diff mbox

Patch

diff --git a/migration/colo.c b/migration/colo.c
index 442471e088..0bff21d9e5 100644
--- a/migration/colo.c
+++ b/migration/colo.c
@@ -31,6 +31,7 @@ 
 #include "qapi/qapi-events-migration.h"
 #include "qapi/qmp/qerror.h"
 #include "sysemu/cpus.h"
+#include "net/filter.h"
 
 static bool vmstate_loading;
 static Notifier packets_compare_notifier;
@@ -82,6 +83,11 @@  static void secondary_vm_do_failover(void)
     if (local_err) {
         error_report_err(local_err);
     }
+    /* Notify all filters of all NIC to do checkpoint */
+    colo_notify_filters_event(COLO_EVENT_FAILOVER, &local_err);
+    if (local_err) {
+        error_report_err(local_err);
+    }
 
     if (!autostart) {
         error_report("\"-S\" qemu option will be ignored in secondary side");
@@ -800,6 +806,13 @@  void *colo_process_incoming_thread(void *opaque)
             goto out;
         }
 
+        /* Notify all filters of all NIC to do checkpoint */
+        colo_notify_filters_event(COLO_EVENT_CHECKPOINT, &local_err);
+        if (local_err) {
+            qemu_mutex_unlock_iothread();
+            goto out;
+        }
+
         vmstate_loading = false;
         vm_start();
         trace_colo_vm_state_change("stop", "run");
diff --git a/net/filter-rewriter.c b/net/filter-rewriter.c
index 0909a9a8af..f3c306cc89 100644
--- a/net/filter-rewriter.c
+++ b/net/filter-rewriter.c
@@ -20,6 +20,8 @@ 
 #include "qemu/main-loop.h"
 #include "qemu/iov.h"
 #include "net/checksum.h"
+#include "net/colo.h"
+#include "migration/colo.h"
 
 #define FILTER_COLO_REWRITER(obj) \
     OBJECT_CHECK(RewriterState, (obj), TYPE_FILTER_REWRITER)
@@ -277,6 +279,43 @@  static ssize_t colo_rewriter_receive_iov(NetFilterState *nf,
     return 0;
 }
 
+static void reset_seq_offset(gpointer key, gpointer value, gpointer user_data)
+{
+    Connection *conn = (Connection *)value;
+
+    conn->offset = 0;
+}
+
+static gboolean offset_is_nonzero(gpointer key,
+                                  gpointer value,
+                                  gpointer user_data)
+{
+    Connection *conn = (Connection *)value;
+
+    return conn->offset ? true : false;
+}
+
+static void colo_rewriter_handle_event(NetFilterState *nf, int event,
+                                       Error **errp)
+{
+    RewriterState *rs = FILTER_COLO_REWRITER(nf);
+
+    switch (event) {
+    case COLO_EVENT_CHECKPOINT:
+        g_hash_table_foreach(rs->connection_track_table,
+                            reset_seq_offset, NULL);
+        break;
+    case COLO_EVENT_FAILOVER:
+        if (!g_hash_table_find(rs->connection_track_table,
+                              offset_is_nonzero, NULL)) {
+            object_property_set_str(OBJECT(nf), "off", "status", errp);
+        }
+        break;
+    default:
+        break;
+    }
+}
+
 static void colo_rewriter_cleanup(NetFilterState *nf)
 {
     RewriterState *s = FILTER_COLO_REWRITER(nf);
@@ -332,6 +371,7 @@  static void colo_rewriter_class_init(ObjectClass *oc, void *data)
     nfc->setup = colo_rewriter_setup;
     nfc->cleanup = colo_rewriter_cleanup;
     nfc->receive_iov = colo_rewriter_receive_iov;
+    nfc->handle_event = colo_rewriter_handle_event;
 }
 
 static const TypeInfo colo_rewriter_info = {