diff mbox

[33/47] mirror: add support for on-source-error/on-target-error

Message ID 1343127865-16608-34-git-send-email-pbonzini@redhat.com
State New
Headers show

Commit Message

Paolo Bonzini July 24, 2012, 11:04 a.m. UTC
Error management is important for mirroring; otherwise, an error on the
target (even something as "innocent" as ENOSPC) requires to start again
with a full copy.  Similar to on_read_error/on_write_error, two separate
knobs are provided for on_source_error (reads) and on_target_error (writes).
The default is 'report' for both.

The 'ignore' policy will leave the sector dirty, so that it will be
retried later.  Thus, it will not cause corruption.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 block/mirror.c   |   50 +++++++++++++++++++++++++++++++++++++++++++++-----
 block_int.h      |    4 ++++
 blockdev.c       |   14 ++++++++++++--
 hmp.c            |    3 ++-
 qapi-schema.json |   12 +++++++++++-
 qmp-commands.hx  |    8 +++++++-
 6 files changed, 81 insertions(+), 10 deletions(-)

Comments

Eric Blake July 27, 2012, 3:26 p.m. UTC | #1
On 07/24/2012 05:04 AM, Paolo Bonzini wrote:
> Error management is important for mirroring; otherwise, an error on the
> target (even something as "innocent" as ENOSPC) requires to start again
> with a full copy.  Similar to on_read_error/on_write_error, two separate
> knobs are provided for on_source_error (reads) and on_target_error (writes).
> The default is 'report' for both.
> 
> The 'ignore' policy will leave the sector dirty, so that it will be
> retried later.  Thus, it will not cause corruption.

How frequently will the dirty sector be retried when the policy is
'ignore'?  Are we going to be causing a denial-of-service by repeatedly
retrying the sector until the user does something about the error event?

> +++ b/qapi-schema.json
> @@ -1389,17 +1389,27 @@
>  #        (all the disk, only the sectors allocated in the topmost image, or
>  #        only new I/O).
>  #
> +# @on-source-error: #optional the action to take on an error on the source,
> +#                   default 'report'.  'stop' and 'enospc' can only be used
> +#                   if the block device supports io-status (see BlockInfo).
> +#
> +# @on-target-error: #optional the action to take on an error on the target,
> +#                   default 'report' (no limitations, since this applies to
> +#                   a different block device than @device).
> +#
>  # Returns: nothing on success
>  #          If @device is not a valid block device, DeviceNotFound
>  #          If @target can't be opened, OpenFileFailed
>  #          If @format is invalid, InvalidBlockFormat
> +#          If @on_source_error is not supported, InvalidParameter

s/_/-/g
Paolo Bonzini July 30, 2012, 1:29 p.m. UTC | #2
Il 27/07/2012 17:26, Eric Blake ha scritto:
> On 07/24/2012 05:04 AM, Paolo Bonzini wrote:
>> Error management is important for mirroring; otherwise, an error on the
>> target (even something as "innocent" as ENOSPC) requires to start again
>> with a full copy.  Similar to on_read_error/on_write_error, two separate
>> knobs are provided for on_source_error (reads) and on_target_error (writes).
>> The default is 'report' for both.
>>
>> The 'ignore' policy will leave the sector dirty, so that it will be
>> retried later.  Thus, it will not cause corruption.
> 
> How frequently will the dirty sector be retried when the policy is
> 'ignore'?  Are we going to be causing a denial-of-service by repeatedly
> retrying the sector until the user does something about the error event?

A lot.  It is definitely the "I know what I'm doing" kind of option.
The usecase I had in mind was a network backend that had some kind of
timeout-and-reconnect option, so that you know all failing operations
will take at least a few seconds.

Paolo

>> +++ b/qapi-schema.json
>> @@ -1389,17 +1389,27 @@
>>  #        (all the disk, only the sectors allocated in the topmost image, or
>>  #        only new I/O).
>>  #
>> +# @on-source-error: #optional the action to take on an error on the source,
>> +#                   default 'report'.  'stop' and 'enospc' can only be used
>> +#                   if the block device supports io-status (see BlockInfo).
>> +#
>> +# @on-target-error: #optional the action to take on an error on the target,
>> +#                   default 'report' (no limitations, since this applies to
>> +#                   a different block device than @device).
>> +#
>>  # Returns: nothing on success
>>  #          If @device is not a valid block device, DeviceNotFound
>>  #          If @target can't be opened, OpenFileFailed
>>  #          If @format is invalid, InvalidBlockFormat
>> +#          If @on_source_error is not supported, InvalidParameter
> 
> s/_/-/g
>
diff mbox

Patch

diff --git a/block/mirror.c b/block/mirror.c
index 4454ef3..fb54d27 100644
--- a/block/mirror.c
+++ b/block/mirror.c
@@ -32,13 +32,15 @@  typedef struct MirrorBlockJob {
     RateLimit limit;
     BlockDriverState *target;
     MirrorSyncMode mode;
+    BlockdevOnError on_source_error, on_target_error;
     bool synced;
     bool complete;
     int64_t sector_num;
     uint8_t *buf;
 } MirrorBlockJob;
 
-static int coroutine_fn mirror_iteration(MirrorBlockJob *s)
+static int coroutine_fn mirror_iteration(MirrorBlockJob *s,
+                                         BlockErrorAction *p_action)
 {
     BlockDriverState *source = s->common.bs;
     BlockDriverState *target = s->target;
@@ -60,9 +62,24 @@  static int coroutine_fn mirror_iteration(MirrorBlockJob *s)
     trace_mirror_one_iteration(s, s->sector_num, nb_sectors);
     ret = bdrv_co_readv(source, s->sector_num, nb_sectors, &qiov);
     if (ret < 0) {
-        return ret;
+        *p_action = block_job_error_action(&s->common, source,
+                                           s->on_source_error, true, -ret);
+        s->synced = false;
+        goto fail;
     }
-    return bdrv_co_writev(target, s->sector_num, nb_sectors, &qiov);
+    ret = bdrv_co_writev(target, s->sector_num, nb_sectors, &qiov);
+    if (ret < 0) {
+        *p_action = block_job_error_action(&s->common, target,
+                                           s->on_target_error, false, -ret);
+        s->synced = false;
+        goto fail;
+    }
+    return 0;
+
+fail:
+    /* Try again later.  */
+    bdrv_set_dirty(source, s->sector_num, nb_sectors);
+    return ret;
 }
 
 static void coroutine_fn mirror_run(void *opaque)
@@ -118,8 +135,9 @@  static void coroutine_fn mirror_run(void *opaque)
 
         cnt = bdrv_get_dirty_count(bs);
         if (cnt != 0) {
-            ret = mirror_iteration(s);
-            if (ret < 0) {
+            BlockErrorAction action = BDRV_ACTION_REPORT;
+            ret = mirror_iteration(s, &action);
+            if (ret < 0 && action == BDRV_ACTION_REPORT) {
                 break;
             }
             cnt = bdrv_get_dirty_count(bs);
@@ -193,6 +211,7 @@  static void coroutine_fn mirror_run(void *opaque)
 immediate_exit:
     g_free(s->buf);
     bdrv_set_dirty_tracking(bs, false);
+    bdrv_iostatus_disable(s->target);
     if (s->complete && ret == 0) {
         bdrv_swap(s->target, s->common.bs);
     } else {
@@ -213,6 +232,13 @@  static void mirror_set_speed(BlockJob *job, int64_t speed, Error **errp)
     ratelimit_set_speed(&s->limit, speed / BDRV_SECTOR_SIZE, SLICE_TIME);
 }
 
+static void mirror_iostatus_reset(BlockJob *job)
+{
+    MirrorBlockJob *s = container_of(job, MirrorBlockJob, common);
+
+    bdrv_iostatus_reset(s->target);
+}
+
 static void mirror_query(BlockJob *job, BlockJobInfo *info)
 {
     MirrorBlockJob *s = container_of(job, MirrorBlockJob, common);
@@ -249,25 +275,39 @@  static BlockJobType mirror_job_type = {
     .instance_size = sizeof(MirrorBlockJob),
     .job_type      = "mirror",
     .set_speed     = mirror_set_speed,
+    .iostatus_reset= mirror_iostatus_reset,
     .query         = mirror_query,
     .complete      = mirror_complete,
 };
 
 void mirror_start(BlockDriverState *bs, BlockDriverState *target,
                   int64_t speed, MirrorSyncMode mode,
+                  BlockdevOnError on_source_error,
+                  BlockdevOnError on_target_error,
                   BlockDriverCompletionFunc *cb,
                   void *opaque, Error **errp)
 {
     MirrorBlockJob *s;
 
+    if ((on_source_error == BLOCKDEV_ON_ERROR_STOP ||
+         on_source_error == BLOCKDEV_ON_ERROR_ENOSPC) &&
+        !bdrv_iostatus_is_enabled(bs)) {
+        error_set(errp, QERR_INVALID_PARAMETER, "on-source-error");
+        return;
+    }
+
     s = block_job_create(&mirror_job_type, bs, speed, cb, opaque, errp);
     if (!s) {
         return;
     }
 
+    s->on_source_error = on_source_error;
+    s->on_target_error = on_target_error;
     s->target = target;
     s->mode = mode;
     bdrv_set_dirty_tracking(bs, true);
+    bdrv_set_on_error(s->target, on_target_error, on_target_error);
+    bdrv_iostatus_enable(s->target);
     s->common.co = qemu_coroutine_create(mirror_run);
     trace_mirror_start(bs, s, s->common.co, opaque);
     qemu_coroutine_enter(s->common.co, s);
diff --git a/block_int.h b/block_int.h
index 714f939..0de2fdc 100644
--- a/block_int.h
+++ b/block_int.h
@@ -311,6 +311,8 @@  void stream_start(BlockDriverState *bs, BlockDriverState *base,
  * @target: Block device to write to.
  * @speed: The maximum speed, in bytes per second, or 0 for unlimited.
  * @mode: Whether to collapse all images in the chain to the target.
+ * @on_source_error: The action to take upon error reading from the source.
+ * @on_target_error: The action to take upon error writing to the target.
  * @cb: Completion function for the job.
  * @opaque: Opaque pointer value passed to @cb.
  * @errp: Error object.
@@ -322,6 +324,8 @@  void stream_start(BlockDriverState *bs, BlockDriverState *base,
  */
 void mirror_start(BlockDriverState *bs, BlockDriverState *target,
                   int64_t speed, MirrorSyncMode mode,
+                  BlockdevOnError on_source_error,
+                  BlockdevOnError on_target_error,
                   BlockDriverCompletionFunc *cb,
                   void *opaque, Error **errp);
 
diff --git a/blockdev.c b/blockdev.c
index 4b4574a..eb528cd 100644
--- a/blockdev.c
+++ b/blockdev.c
@@ -831,7 +831,10 @@  void qmp_drive_mirror(const char *device, const char *target,
                       bool has_format, const char *format,
                       enum MirrorSyncMode sync,
                       bool has_mode, enum NewImageMode mode,
-                      bool has_speed, int64_t speed, Error **errp)
+                      bool has_speed, int64_t speed,
+                      bool has_on_source_error, BlockdevOnError on_source_error,
+                      bool has_on_target_error, BlockdevOnError on_target_error,
+                      Error **errp)
 {
     BlockDriverInfo bdi;
     BlockDriverState *bs;
@@ -846,6 +849,12 @@  void qmp_drive_mirror(const char *device, const char *target,
     if (!has_speed) {
         speed = 0;
     }
+    if (!has_on_source_error) {
+        on_source_error = BLOCKDEV_ON_ERROR_REPORT;
+    }
+    if (!has_on_target_error) {
+        on_target_error = BLOCKDEV_ON_ERROR_REPORT;
+    }
     if (!has_mode) {
         mode = NEW_IMAGE_MODE_ABSOLUTE_PATHS;
     }
@@ -938,7 +947,8 @@  void qmp_drive_mirror(const char *device, const char *target,
         }
     }
 
-    mirror_start(bs, target_bs, speed, sync, block_job_cb, bs, &local_err);
+    mirror_start(bs, target_bs, speed, sync, on_source_error, on_target_error,
+                 block_job_cb, bs, &local_err);
     if (local_err != NULL) {
         bdrv_delete(target_bs);
         error_propagate(errp, local_err);
diff --git a/hmp.c b/hmp.c
index 1d6a606..b6bc263 100644
--- a/hmp.c
+++ b/hmp.c
@@ -719,7 +719,8 @@  void hmp_drive_mirror(Monitor *mon, const QDict *qdict)
 
     qmp_drive_mirror(device, filename, !!format, format,
                      full ? MIRROR_SYNC_MODE_FULL : MIRROR_SYNC_MODE_TOP,
-                     true, mode, false, 0, &errp);
+                     true, mode, false, 0,
+                     false, 0, false, 0, &errp);
     hmp_handle_error(mon, &errp);
 }
 
diff --git a/qapi-schema.json b/qapi-schema.json
index f5c20ca..7a97fad 100644
--- a/qapi-schema.json
+++ b/qapi-schema.json
@@ -1389,17 +1389,27 @@ 
 #        (all the disk, only the sectors allocated in the topmost image, or
 #        only new I/O).
 #
+# @on-source-error: #optional the action to take on an error on the source,
+#                   default 'report'.  'stop' and 'enospc' can only be used
+#                   if the block device supports io-status (see BlockInfo).
+#
+# @on-target-error: #optional the action to take on an error on the target,
+#                   default 'report' (no limitations, since this applies to
+#                   a different block device than @device).
+#
 # Returns: nothing on success
 #          If @device is not a valid block device, DeviceNotFound
 #          If @target can't be opened, OpenFileFailed
 #          If @format is invalid, InvalidBlockFormat
+#          If @on_source_error is not supported, InvalidParameter
 #
 # Since 1.2
 ##
 { 'command': 'drive-mirror',
   'data': { 'device': 'str', 'target': 'str', '*format': 'str',
             'sync': 'MirrorSyncMode', '*mode': 'NewImageMode',
-            '*speed': 'int' } }
+            '*speed': 'int', '*on-source-error': 'BlockdevOnError',
+            '*on-target-error': 'BlockdevOnError' } }
 
 ##
 # @migrate_cancel
diff --git a/qmp-commands.hx b/qmp-commands.hx
index 7a32bb6..5081b01 100644
--- a/qmp-commands.hx
+++ b/qmp-commands.hx
@@ -838,7 +838,8 @@  EQMP
 
     {
         .name       = "drive-mirror",
-        .args_type  = "sync:s,device:B,target:s,speed:i?,mode:s?,format:s?",
+        .args_type  = "sync:s,device:B,target:s,speed:i?,mode:s?,format:s?,"
+                      "on-source-error:s?,on-target-error:s?",
         .mhandler.cmd_new = qmp_marshal_input_drive_mirror,
     },
 
@@ -866,6 +867,11 @@  Arguments:
   possibilities include "full" for all the disk, "top" for only the sectors
   allocated in the topmost image, or "none" to only replicate new I/O
   (MirrorSyncMode).
+- "on-source-error": the action to take on an error on the source
+  (BlockdevOnError, default 'report')
+- "on-target-error": the action to take on an error on the target
+  (BlockdevOnError, default 'report')
+
 
 
 Example: