summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorYang Shi <shy828301@gmail.com>2022-02-10 14:52:22 -0800
committerJens Axboe <axboe@kernel.dk>2022-02-11 10:00:16 -0700
commitd5869fdc189f0f12a954a48d58a48104a2f5d044 (patch)
tree1a48848543d78cdc1a512d340a52ac7a172cbaef
parent3f607293b74d6acb06571a774a500143c1f0ed2c (diff)
block: introduce block_rq_error tracepoint
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. With this patch, rasdaemon could switch to block_rq_error. Since the new tracepoint has the similar implementation with block_rq_complete, so move the existing code from TRACE_EVENT block_rq_complete() into new event class block_rq_completion(). Then add event for block_rq_complete and block_rq_err respectively from the newly created event class per the suggestion from Chaitanya Kulkarni. Cc: Jens Axboe <axboe@kernel.dk> Cc: Christoph Hellwig <hch@infradead.org> Reviewed-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: Chaitanya Kulkarni <kch@nvidia.com> Signed-off-by: Yang Shi <shy828301@gmail.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Link: https://lore.kernel.org/r/20220210225222.260069-1-shy828301@gmail.com Signed-off-by: Jens Axboe <axboe@kernel.dk>
-rw-r--r--block/blk-mq.c4
-rw-r--r--include/trace/events/block.h49
2 files changed, 39 insertions, 14 deletions
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 4b868e792ba4..6c59ffe765fd 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -789,8 +789,10 @@ 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))) {
blk_print_req_error(req, error);
+ trace_block_rq_error(req, error, nr_bytes);
+ }
blk_account_io_completion(req, nr_bytes);
diff --git a/include/trace/events/block.h b/include/trace/events/block.h
index 27170e40e8c9..7f4dfbdf12a6 100644
--- a/include/trace/events/block.h
+++ b/include/trace/events/block.h
@@ -100,19 +100,7 @@ TRACE_EVENT(block_rq_requeue,
__entry->nr_sector, 0)
);
-/**
- * block_rq_complete - block IO operation completed by device driver
- * @rq: block operations request
- * @error: status code
- * @nr_bytes: number of completed bytes
- *
- * The block_rq_complete tracepoint event indicates that some portion
- * of operation request has been completed by the device driver. If
- * the @rq->bio is %NULL, then there is absolutely no additional work to
- * do for the request. If @rq->bio is non-NULL then there is
- * additional work required to complete the request.
- */
-TRACE_EVENT(block_rq_complete,
+DECLARE_EVENT_CLASS(block_rq_completion,
TP_PROTO(struct request *rq, blk_status_t error, unsigned int nr_bytes),
@@ -144,6 +132,41 @@ TRACE_EVENT(block_rq_complete,
__entry->nr_sector, __entry->error)
);
+/**
+ * block_rq_complete - block IO operation completed by device driver
+ * @rq: block operations request
+ * @error: status code
+ * @nr_bytes: number of completed bytes
+ *
+ * The block_rq_complete tracepoint event indicates that some portion
+ * of operation request has been completed by the device driver. If
+ * the @rq->bio is %NULL, then there is absolutely no additional work to
+ * do for the request. If @rq->bio is non-NULL then there is
+ * additional work required to complete the request.
+ */
+DEFINE_EVENT(block_rq_completion, block_rq_complete,
+
+ TP_PROTO(struct request *rq, blk_status_t error, unsigned int nr_bytes),
+
+ TP_ARGS(rq, error, nr_bytes)
+);
+
+/**
+ * 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.
+ */
+DEFINE_EVENT(block_rq_completion, block_rq_error,
+
+ TP_PROTO(struct request *rq, blk_status_t error, unsigned int nr_bytes),
+
+ TP_ARGS(rq, error, nr_bytes)
+);
+
DECLARE_EVENT_CLASS(block_rq,
TP_PROTO(struct request *rq),