[Ocfs2-devel] [PATCH] ocfs2: submit disk heartbeat bio using WRITE_SYNC

[Ocfs2-devel] [PATCH] ocfs2: submit disk heartbeat bio using WRITE_SYNC

[Noboru Iwamatsu]

Under heavy I/O load, writing the disk heartbeat can be forced
to wait for minutes, and this causes the node to be fenced.

This patch tries to use WRITE_SYNC in submitting the heartbeat
bio, so that writing the heartbeat will have a priority over
other requests.

Signed-off-by: Noboru Iwamatsu <n_iwamatsu@jp.fujitsu.com>
---
 fs/ocfs2/cluster/heartbeat.c |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index 9a3e6bb..6b0c1e4 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -491,7 +491,7 @@ static int o2hb_issue_node_write(struct o2hb_region *reg,
 	}
 
 	atomic_inc(&write_wc->wc_num_reqs);
-	submit_bio(WRITE, bio);
+	submit_bio(WRITE_SYNC, bio);
 
 	status = 0;
 bail:
-- 
1.7.6.4

[Ocfs2-devel] [PATCH] ocfs2: submit disk heartbeat bio using WRITE_SYNC

[Tao Ma]

On 12/06/2011 12:57 PM, Noboru Iwamatsu wrote:
> Under heavy I/O load, writing the disk heartbeat can be forced
> to wait for minutes, and this causes the node to be fenced.
> 
> This patch tries to use WRITE_SYNC in submitting the heartbeat
> bio, so that writing the heartbeat will have a priority over
> other requests.
> 
> Signed-off-by: Noboru Iwamatsu <n_iwamatsu@jp.fujitsu.com>
looks good to me.
Acked-by: Tao Ma <boyu.mt@taobao.com>
> ---
>  fs/ocfs2/cluster/heartbeat.c |    2 +-
>  1 files changed, 1 insertions(+), 1 deletions(-)
> 
> diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
> index 9a3e6bb..6b0c1e4 100644
> --- a/fs/ocfs2/cluster/heartbeat.c
> +++ b/fs/ocfs2/cluster/heartbeat.c
> @@ -491,7 +491,7 @@ static int o2hb_issue_node_write(struct o2hb_region *reg,
>  	}
>  
>  	atomic_inc(&write_wc->wc_num_reqs);
> -	submit_bio(WRITE, bio);
> +	submit_bio(WRITE_SYNC, bio);
>  
>  	status = 0;
>  bail:

[Ocfs2-devel] [PATCH] ocfs2: submit disk heartbeat bio using WRITE_SYNC

[Sunil Mushran]

Acked-by: Sunil Mushran <sunil.mushran@oracle.com>

On 12/05/2011 09:18 PM, Tao Ma wrote:
> On 12/06/2011 12:57 PM, Noboru Iwamatsu wrote:
>> Under heavy I/O load, writing the disk heartbeat can be forced
>> to wait for minutes, and this causes the node to be fenced.
>>
>> This patch tries to use WRITE_SYNC in submitting the heartbeat
>> bio, so that writing the heartbeat will have a priority over
>> other requests.
>>
>> Signed-off-by: Noboru Iwamatsu<n_iwamatsu@jp.fujitsu.com>
> looks good to me.
> Acked-by: Tao Ma<boyu.mt@taobao.com>
>> ---
>>   fs/ocfs2/cluster/heartbeat.c |    2 +-
>>   1 files changed, 1 insertions(+), 1 deletions(-)
>>
>> diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
>> index 9a3e6bb..6b0c1e4 100644
>> --- a/fs/ocfs2/cluster/heartbeat.c
>> +++ b/fs/ocfs2/cluster/heartbeat.c
>> @@ -491,7 +491,7 @@ static int o2hb_issue_node_write(struct o2hb_region *reg,
>>   	}
>>
>>   	atomic_inc(&write_wc->wc_num_reqs);
>> -	submit_bio(WRITE, bio);
>> +	submit_bio(WRITE_SYNC, bio);
>>
>>   	status = 0;
>>   bail:
>
> _______________________________________________
> Ocfs2-devel mailing list
> Ocfs2-devel at oss.oracle.com
> http://oss.oracle.com/mailman/listinfo/ocfs2-devel