summaryrefslogtreecommitdiff
path: root/kernel/trace/blktrace.c
diff options
context:
space:
mode:
authorLi Zefan <lizf@cn.fujitsu.com>2009-06-09 05:43:05 (GMT)
committerSteven Rostedt <rostedt@goodmis.org>2009-06-09 16:34:23 (GMT)
commit55782138e47d9baf2f7d3a7af9e7cf42adf72c56 (patch)
treec7ccabae20e27bbeb08b69a358e8b86c98d1d9f3 /kernel/trace/blktrace.c
parentf57a8a1911342265e7acdc190333c4e9235a6632 (diff)
downloadlinux-55782138e47d9baf2f7d3a7af9e7cf42adf72c56.tar.xz
tracing/events: convert block trace points to TRACE_EVENT()
TRACE_EVENT is a more generic way to define tracepoints. Doing so adds these new capabilities to this tracepoint: - zero-copy and per-cpu splice() tracing - binary tracing without printf overhead - structured logging records exposed under /debug/tracing/events - trace events embedded in function tracer output and other plugins - user-defined, per tracepoint filter expressions ... Cons: - no dev_t info for the output of plug, unplug_timer and unplug_io events. no dev_t info for getrq and sleeprq events if bio == NULL. no dev_t info for rq_abort,...,rq_requeue events if rq->rq_disk == NULL. This is mainly because we can't get the deivce from a request queue. But this may change in the future. - A packet command is converted to a string in TP_assign, not TP_print. While blktrace do the convertion just before output. Since pc requests should be rather rare, this is not a big issue. - In blktrace, an event can have 2 different print formats, but a TRACE_EVENT has a unique format, which means we have some unused data in a trace entry. The overhead is minimized by using __dynamic_array() instead of __array(). I've benchmarked the ioctl blktrace vs the splice based TRACE_EVENT tracing: dd dd + ioctl blktrace dd + TRACE_EVENT (splice) 1 7.36s, 42.7 MB/s 7.50s, 42.0 MB/s 7.41s, 42.5 MB/s 2 7.43s, 42.3 MB/s 7.48s, 42.1 MB/s 7.43s, 42.4 MB/s 3 7.38s, 42.6 MB/s 7.45s, 42.2 MB/s 7.41s, 42.5 MB/s So the overhead of tracing is very small, and no regression when using those trace events vs blktrace. And the binary output of TRACE_EVENT is much smaller than blktrace: # ls -l -h -rw-r--r-- 1 root root 8.8M 06-09 13:24 sda.blktrace.0 -rw-r--r-- 1 root root 195K 06-09 13:24 sda.blktrace.1 -rw-r--r-- 1 root root 2.7M 06-09 13:25 trace_splice.out Following are some comparisons between TRACE_EVENT and blktrace: plug: kjournald-480 [000] 303.084981: block_plug: [kjournald] kjournald-480 [000] 303.084981: 8,0 P N [kjournald] unplug_io: kblockd/0-118 [000] 300.052973: block_unplug_io: [kblockd/0] 1 kblockd/0-118 [000] 300.052974: 8,0 U N [kblockd/0] 1 remap: kjournald-480 [000] 303.085042: block_remap: 8,0 W 102736992 + 8 <- (8,8) 33384 kjournald-480 [000] 303.085043: 8,0 A W 102736992 + 8 <- (8,8) 33384 bio_backmerge: kjournald-480 [000] 303.085086: block_bio_backmerge: 8,0 W 102737032 + 8 [kjournald] kjournald-480 [000] 303.085086: 8,0 M W 102737032 + 8 [kjournald] getrq: kjournald-480 [000] 303.084974: block_getrq: 8,0 W 102736984 + 8 [kjournald] kjournald-480 [000] 303.084975: 8,0 G W 102736984 + 8 [kjournald] bash-2066 [001] 1072.953770: 8,0 G N [bash] bash-2066 [001] 1072.953773: block_getrq: 0,0 N 0 + 0 [bash] rq_complete: konsole-2065 [001] 300.053184: block_rq_complete: 8,0 W () 103669040 + 16 [0] konsole-2065 [001] 300.053191: 8,0 C W 103669040 + 16 [0] ksoftirqd/1-7 [001] 1072.953811: 8,0 C N (5a 00 08 00 00 00 00 00 24 00) [0] ksoftirqd/1-7 [001] 1072.953813: block_rq_complete: 0,0 N (5a 00 08 00 00 00 00 00 24 00) 0 + 0 [0] rq_insert: kjournald-480 [000] 303.084985: block_rq_insert: 8,0 W 0 () 102736984 + 8 [kjournald] kjournald-480 [000] 303.084986: 8,0 I W 102736984 + 8 [kjournald] Changelog from v2 -> v3: - use the newly introduced __dynamic_array(). Changelog from v1 -> v2: - use __string() instead of __array() to minimize the memory required to store hex dump of rq->cmd(). - support large pc requests. - add missing blk_fill_rwbs_rq() in block_rq_requeue TRACE_EVENT. - some cleanups. Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> LKML-Reference: <4A2DF669.5070905@cn.fujitsu.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Diffstat (limited to 'kernel/trace/blktrace.c')
-rw-r--r--kernel/trace/blktrace.c78
1 files changed, 77 insertions, 1 deletions
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index e3abf55..7bd6a98 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -23,10 +23,14 @@
#include <linux/mutex.h>
#include <linux/debugfs.h>
#include <linux/time.h>
-#include <trace/block.h>
#include <linux/uaccess.h>
+
+#include <trace/events/block.h>
+
#include "trace_output.h"
+#ifdef CONFIG_BLK_DEV_IO_TRACE
+
static unsigned int blktrace_seq __read_mostly = 1;
static struct trace_array *blk_tr;
@@ -1658,3 +1662,75 @@ int blk_trace_init_sysfs(struct device *dev)
return sysfs_create_group(&dev->kobj, &blk_trace_attr_group);
}
+#endif /* CONFIG_BLK_DEV_IO_TRACE */
+
+#ifdef CONFIG_EVENT_TRACING
+
+void blk_dump_cmd(char *buf, struct request *rq)
+{
+ int i, end;
+ int len = rq->cmd_len;
+ unsigned char *cmd = rq->cmd;
+
+ if (!blk_pc_request(rq)) {
+ buf[0] = '\0';
+ return;
+ }
+
+ for (end = len - 1; end >= 0; end--)
+ if (cmd[end])
+ break;
+ end++;
+
+ for (i = 0; i < len; i++) {
+ buf += sprintf(buf, "%s%02x", i == 0 ? "" : " ", cmd[i]);
+ if (i == end && end != len - 1) {
+ sprintf(buf, " ..");
+ break;
+ }
+ }
+}
+
+void blk_fill_rwbs(char *rwbs, u32 rw, int bytes)
+{
+ int i = 0;
+
+ if (rw & WRITE)
+ rwbs[i++] = 'W';
+ else if (rw & 1 << BIO_RW_DISCARD)
+ rwbs[i++] = 'D';
+ else if (bytes)
+ rwbs[i++] = 'R';
+ else
+ rwbs[i++] = 'N';
+
+ if (rw & 1 << BIO_RW_AHEAD)
+ rwbs[i++] = 'A';
+ if (rw & 1 << BIO_RW_BARRIER)
+ rwbs[i++] = 'B';
+ if (rw & 1 << BIO_RW_SYNCIO)
+ rwbs[i++] = 'S';
+ if (rw & 1 << BIO_RW_META)
+ rwbs[i++] = 'M';
+
+ rwbs[i] = '\0';
+}
+
+void blk_fill_rwbs_rq(char *rwbs, struct request *rq)
+{
+ int rw = rq->cmd_flags & 0x03;
+ int bytes;
+
+ if (blk_discard_rq(rq))
+ rw |= (1 << BIO_RW_DISCARD);
+
+ if (blk_pc_request(rq))
+ bytes = rq->data_len;
+ else
+ bytes = rq->hard_nr_sectors << 9;
+
+ blk_fill_rwbs(rwbs, rw, bytes);
+}
+
+#endif /* CONFIG_EVENT_TRACING */
+