Currently, rasdaemon uses the existing tracepoint block_rq_complete
and filters out non-error cases in order to capture block disk errors.
But there are a few problems with this approach:
1. Even kernel trace filter could do the filtering work, there is
still some overhead after we enable this tracepoint.
2. The filter is merely based on errno, which does not align with kernel
logic to check the errors for print_req_error().
3. block_rq_complete only provides dev major and minor to identify
the block device, it is not convenient to use in user-space.
So introduce a new tracepoint block_rq_error just for the error case
and provides the device name for convenience too. With this patch,
rasdaemon could switch to block_rq_error.
Cc: Jens Axboe <axboe@xxxxxxxxx>
Cc: Steven Rostedt <rostedt@xxxxxxxxxxx>
Signed-off-by: Cong Wang <xiyou.wangcong@xxxxxxxxx>
---
block/blk-core.c | 4 +++-
include/trace/events/block.h | 43 ++++++++++++++++++++++++++++++++++++
2 files changed, 46 insertions(+), 1 deletion(-)
diff --git a/block/blk-core.c b/block/blk-core.c
index 089e890ab208..0c7ad70d06be 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1450,8 +1450,10 @@ bool blk_update_request(struct request *req, blk_status_t error,
#endif
if (unlikely(error && !blk_rq_is_passthrough(req) &&
- !(req->rq_flags & RQF_QUIET)))
+ !(req->rq_flags & RQF_QUIET))) {
+ trace_block_rq_error(req, blk_status_to_errno(error), nr_bytes);
print_req_error(req, error, __func__);
+ }
blk_account_io_completion(req, nr_bytes);
diff --git a/include/trace/events/block.h b/include/trace/events/block.h
index 81b43f5bdf23..a0f63f4d50c4 100644
--- a/include/trace/events/block.h
+++ b/include/trace/events/block.h
@@ -145,6 +145,49 @@ TRACE_EVENT(block_rq_complete,
__entry->nr_sector, __entry->error)
);
+/**
+ * block_rq_error - block IO operation error reported by device driver
+ * @rq: block operations request
+ * @error: status code
+ * @nr_bytes: number of completed bytes
+ *
+ * The block_rq_error tracepoint event indicates that some portion
+ * of operation request has failed as reported by the device driver.
+ */
+TRACE_EVENT(block_rq_error,
+
+ TP_PROTO(struct request *rq, int error, unsigned int nr_bytes),
+
+ TP_ARGS(rq, error, nr_bytes),
+
+ TP_STRUCT__entry(
+ __field( dev_t, dev )
+ __field( char *, name )
+ __field( sector_t, sector )
+ __field( unsigned int, nr_sector )
+ __field( int, error )
+ __array( char, rwbs, RWBS_LEN )
+ __dynamic_array( char, cmd, 1 )
+ ),
+
+ TP_fast_assign(
+ __entry->dev = rq->rq_disk ? disk_devt(rq->rq_disk) : 0;
+ __entry->name = rq->rq_disk ? rq->rq_disk->disk_name : "?";
+ __entry->sector = blk_rq_pos(rq);
+ __entry->nr_sector = nr_bytes >> 9;
+ __entry->error = error;
+
+ blk_fill_rwbs(__entry->rwbs, rq->cmd_flags, nr_bytes);
+ __get_str(cmd)[0] = '\0';
+ ),
+
+ TP_printk("%d,%d %s %s (%s) %llu + %u [%d]",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->name, __entry->rwbs, __get_str(cmd),
+ (unsigned long long)__entry->sector,
+ __entry->nr_sector, __entry->error)
+);
+
DECLARE_EVENT_CLASS(block_rq,
TP_PROTO(struct request_queue *q, struct request *rq),
--
2.21.1
