Re: [PATCH] blktrace: Use rq->cmd_flags directly in blk_add_trace_rq.

[Jeff Moyer <jmoyer@redhat.com>]

Tao Ma <tm@tao.ma> writes:

> From: Tao Ma <boyu.mt@taobao.com>
>
> In blk_add_trace_rq, we only chose the minor 2 bits from
> request's cmd_flags and did some check for discard.
> so most of other flags(e.g, REQ_SYNC) are missing.
>
> For example, with a sync write after blkparse we get:
>   8,16   1        1     0.001776503  7509  A  WS 1349632 + 1024 <- (8,17) 1347584
>   8,16   1        2     0.001776813  7509  Q  WS 1349632 + 1024 [dd]
>   8,16   1        3     0.001780395  7509  G  WS 1349632 + 1024 [dd]
>   8,16   1        5     0.001783186  7509  I   W 1349632 + 1024 [dd]
>   8,16   1       11     0.001816987  7509  D   W 1349632 + 1024 [dd]
>   8,16   0        2     0.006218192     0  C   W 1349632 + 1024 [0]
>
> Since now we have integrated the flags of both bio and request,
> it is safe to pass rq->cmd_flags directly to __blk_add_trace.
>
> With this patch, after a sync write we get:
>   8,16   1        1     0.001776900  5425  A  WS 1189888 + 1024 <- (8,17) 1187840
>   8,16   1        2     0.001777179  5425  Q  WS 1189888 + 1024 [dd]
>   8,16   1        3     0.001780797  5425  G  WS 1189888 + 1024 [dd]
>   8,16   1        5     0.001783402  5425  I  WS 1189888 + 1024 [dd]
>   8,16   1       11     0.001817468  5425  D  WS 1189888 + 1024 [dd]
>   8,16   0        2     0.005640709     0  C  WS 1189888 + 1024 [0]
>
> Cc: Jens Axboe <jaxboe@fusionio.com>
> Signed-off-by: Tao Ma <boyu.mt@taobao.com>
> ---
>  kernel/trace/blktrace.c |   15 ++++-----------
>  1 files changed, 4 insertions(+), 11 deletions(-)
>
> diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
> index cbafed7..7aa40f8 100644
> --- a/kernel/trace/blktrace.c
> +++ b/kernel/trace/blktrace.c
> @@ -703,28 +703,21 @@ void blk_trace_shutdown(struct request_queue *q)
>   *
>   **/
>  static void blk_add_trace_rq(struct request_queue *q, struct request *rq,
> -				    u32 what)
> +			     u32 what)
>  {
>  	struct blk_trace *bt = q->blk_trace;
> -	int rw = rq->cmd_flags & 0x03;
>  
>  	if (likely(!bt))
>  		return;
>  
> -	if (rq->cmd_flags & REQ_DISCARD)
> -		rw |= REQ_DISCARD;
> -
> -	if (rq->cmd_flags & REQ_SECURE)
> -		rw |= REQ_SECURE;
> -
>  	if (rq->cmd_type == REQ_TYPE_BLOCK_PC) {
>  		what |= BLK_TC_ACT(BLK_TC_PC);
> -		__blk_add_trace(bt, 0, blk_rq_bytes(rq), rw,
> +		__blk_add_trace(bt, 0, blk_rq_bytes(rq), rq->cmd_flags,
>  				what, rq->errors, rq->cmd_len, rq->cmd);
>  	} else  {
>  		what |= BLK_TC_ACT(BLK_TC_FS);
> -		__blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq), rw,
> -				what, rq->errors, 0, NULL);
> +		__blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq),
> +				rq->cmd_flags, what, rq->errors, 0, NULL);
>  	}
>  }

Looks like a fine cleanup to me.

Acked-by: Jeff Moyer <jmoyer@redhat.com>