diff mbox

migration: avoid divide by zero in xbzrle cache miss rate

Message ID 1429070355-19862-1-git-send-email-mike@very.puzzling.org
State New
Headers show

Commit Message

Michael Chapman April 15, 2015, 3:59 a.m. UTC
This bug manifested itself as a VM that could not be resumed by libvirt
following a migration:

  # virsh resume example
  error: Failed to resume domain example
  error: internal error: cannot parse json {"return":
    {"xbzrle-cache":
      {..., "cache-miss-rate": -nan, ...},
      ...
    }
  }: lexical error: malformed number, a digit is required after the minus sign.

This patch also ensures xbzrle_cache_miss_prev and iterations_prev are
cleared at the start of the migration.

Signed-off-by: Michael Chapman <mike@very.puzzling.org>
---
 arch_init.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

Comments

Amit Shah April 20, 2015, 7:10 a.m. UTC | #1
On (Wed) 15 Apr 2015 [13:59:14], Michael Chapman wrote:
> This bug manifested itself as a VM that could not be resumed by libvirt
> following a migration:
> 
>   # virsh resume example
>   error: Failed to resume domain example
>   error: internal error: cannot parse json {"return":
>     {"xbzrle-cache":
>       {..., "cache-miss-rate": -nan, ...},
>       ...
>     }
>   }: lexical error: malformed number, a digit is required after the minus sign.
> 
> This patch also ensures xbzrle_cache_miss_prev and iterations_prev are
> cleared at the start of the migration.
> 
> Signed-off-by: Michael Chapman <mike@very.puzzling.org>

Reviewed-by: Amit Shah <amit.shah@redhat.com>

		Amit
Juan Quintela April 22, 2015, 11:39 a.m. UTC | #2
Michael Chapman <mike@very.puzzling.org> wrote:
> This bug manifested itself as a VM that could not be resumed by libvirt
> following a migration:
>
>   # virsh resume example
>   error: Failed to resume domain example
>   error: internal error: cannot parse json {"return":
>     {"xbzrle-cache":
>       {..., "cache-miss-rate": -nan, ...},
>       ...
>     }
>   }: lexical error: malformed number, a digit is required after the minus sign.
>
> This patch also ensures xbzrle_cache_miss_prev and iterations_prev are
> cleared at the start of the migration.
>
> Signed-off-by: Michael Chapman <mike@very.puzzling.org>

Added to queue for 2.4 & stable

Thanks

> ---
>  arch_init.c | 8 +++++---
>  1 file changed, 5 insertions(+), 3 deletions(-)
>
> diff --git a/arch_init.c b/arch_init.c
> index 4c8fcee..ca45c7a 100644
> --- a/arch_init.c
> +++ b/arch_init.c
> @@ -520,12 +520,16 @@ static void migration_bitmap_sync_range(ram_addr_t start, ram_addr_t length)
>  static int64_t start_time;
>  static int64_t bytes_xfer_prev;
>  static int64_t num_dirty_pages_period;
> +static uint64_t xbzrle_cache_miss_prev;
> +static uint64_t iterations_prev;
>  
>  static void migration_bitmap_sync_init(void)
>  {
>      start_time = 0;
>      bytes_xfer_prev = 0;
>      num_dirty_pages_period = 0;
> +    xbzrle_cache_miss_prev = 0;
> +    iterations_prev = 0;
>  }
>  
>  /* Called with iothread lock held, to protect ram_list.dirty_memory[] */
> @@ -536,8 +540,6 @@ static void migration_bitmap_sync(void)
>      MigrationState *s = migrate_get_current();
>      int64_t end_time;
>      int64_t bytes_xfer_now;
> -    static uint64_t xbzrle_cache_miss_prev;
> -    static uint64_t iterations_prev;
>  
>      bitmap_sync_count++;
>  
> @@ -585,7 +587,7 @@ static void migration_bitmap_sync(void)
>               mig_throttle_on = false;
>          }
>          if (migrate_use_xbzrle()) {
> -            if (iterations_prev != 0) {
> +            if (iterations_prev != acct_info.iterations) {
>                  acct_info.xbzrle_cache_miss_rate =
>                     (double)(acct_info.xbzrle_cache_miss -
>                              xbzrle_cache_miss_prev) /
Juan Quintela May 6, 2015, 3:35 p.m. UTC | #3
Michael Chapman <mike@very.puzzling.org> wrote:
> This bug manifested itself as a VM that could not be resumed by libvirt
> following a migration:
>
>   # virsh resume example
>   error: Failed to resume domain example
>   error: internal error: cannot parse json {"return":
>     {"xbzrle-cache":
>       {..., "cache-miss-rate": -nan, ...},
>       ...
>     }
>   }: lexical error: malformed number, a digit is required after the minus sign.
>
> This patch also ensures xbzrle_cache_miss_prev and iterations_prev are
> cleared at the start of the migration.
>
> Signed-off-by: Michael Chapman <mike@very.puzzling.org>

Applied, thanks.
diff mbox

Patch

diff --git a/arch_init.c b/arch_init.c
index 4c8fcee..ca45c7a 100644
--- a/arch_init.c
+++ b/arch_init.c
@@ -520,12 +520,16 @@  static void migration_bitmap_sync_range(ram_addr_t start, ram_addr_t length)
 static int64_t start_time;
 static int64_t bytes_xfer_prev;
 static int64_t num_dirty_pages_period;
+static uint64_t xbzrle_cache_miss_prev;
+static uint64_t iterations_prev;
 
 static void migration_bitmap_sync_init(void)
 {
     start_time = 0;
     bytes_xfer_prev = 0;
     num_dirty_pages_period = 0;
+    xbzrle_cache_miss_prev = 0;
+    iterations_prev = 0;
 }
 
 /* Called with iothread lock held, to protect ram_list.dirty_memory[] */
@@ -536,8 +540,6 @@  static void migration_bitmap_sync(void)
     MigrationState *s = migrate_get_current();
     int64_t end_time;
     int64_t bytes_xfer_now;
-    static uint64_t xbzrle_cache_miss_prev;
-    static uint64_t iterations_prev;
 
     bitmap_sync_count++;
 
@@ -585,7 +587,7 @@  static void migration_bitmap_sync(void)
              mig_throttle_on = false;
         }
         if (migrate_use_xbzrle()) {
-            if (iterations_prev != 0) {
+            if (iterations_prev != acct_info.iterations) {
                 acct_info.xbzrle_cache_miss_rate =
                    (double)(acct_info.xbzrle_cache_miss -
                             xbzrle_cache_miss_prev) /