X-Git-Url: https://git.kernel.dk/?p=fio.git;a=blobdiff_plain;f=io_u.c;h=7ccbd312d8d0018f57159baa05b1cf31b0583639;hp=6b950014aa7cb6382d5ce2be00e18b30c745ba7f;hb=1a9bf8146d9842d268bcb01f4286325a8cfccc21;hpb=e3c8c1081fb361803f7414fcc593b0dedc3c3bed

diff --git a/io_u.c b/io_u.c
index 6b950014..7ccbd312 100644
--- a/io_u.c
+++ b/io_u.c
@@ -775,8 +775,7 @@ static enum fio_ddir rate_ddir(struct thread_data *td, enum fio_ddir ddir)
 	if (td->o.io_submit_mode == IO_MODE_INLINE)
 		io_u_quiesce(td);
 
-	usec = usec_sleep(td, usec);
-
+	usec_sleep(td, usec);
 	return ddir;
 }
 
@@ -1409,10 +1408,10 @@ static long set_io_u_file(struct thread_data *td, struct io_u *io_u)
 }
 
 static void lat_fatal(struct thread_data *td, struct io_completion_data *icd,
-		      unsigned long tusec, unsigned long max_usec)
+		      unsigned long long tnsec, unsigned long long max_nsec)
 {
 	if (!td->error)
-		log_err("fio: latency of %lu usec exceeds specified max (%lu usec)\n", tusec, max_usec);
+		log_err("fio: latency of %llu nsec exceeds specified max (%llu nsec)\n", tnsec, max_nsec);
 	td_verror(td, ETIMEDOUT, "max latency exceeded");
 	icd->error = ETIMEDOUT;
 }
@@ -1615,22 +1614,19 @@ static bool check_get_trim(struct thread_data *td, struct io_u *io_u)
 {
 	if (!(td->flags & TD_F_TRIM_BACKLOG))
 		return false;
+	if (!td->trim_entries)
+		return false;
 
-	if (td->trim_entries) {
-		int get_trim = 0;
-
-		if (td->trim_batch) {
-			td->trim_batch--;
-			get_trim = 1;
-		} else if (!(td->io_hist_len % td->o.trim_backlog) &&
-			 td->last_ddir != DDIR_READ) {
-			td->trim_batch = td->o.trim_batch;
-			if (!td->trim_batch)
-				td->trim_batch = td->o.trim_backlog;
-			get_trim = 1;
-		}
-
-		if (get_trim && get_next_trim(td, io_u))
+	if (td->trim_batch) {
+		td->trim_batch--;
+		if (get_next_trim(td, io_u))
+			return true;
+	} else if (!(td->io_hist_len % td->o.trim_backlog) &&
+		     td->last_ddir != DDIR_READ) {
+		td->trim_batch = td->o.trim_batch;
+		if (!td->trim_batch)
+			td->trim_batch = td->o.trim_backlog;
+		if (get_next_trim(td, io_u))
 			return true;
 	}
 
@@ -1672,32 +1668,40 @@ static bool check_get_verify(struct thread_data *td, struct io_u *io_u)
  */
 static void small_content_scramble(struct io_u *io_u)
 {
-	unsigned int i, nr_blocks = io_u->buflen / 512;
-	uint64_t boffset;
+	unsigned int i, nr_blocks = io_u->buflen >> 9;
 	unsigned int offset;
-	char *p, *end;
+	uint64_t boffset, *iptr;
+	char *p;
 
 	if (!nr_blocks)
 		return;
 
 	p = io_u->xfer_buf;
 	boffset = io_u->offset;
-	io_u->buf_filled_len = 0;
+
+	if (io_u->buf_filled_len)
+		io_u->buf_filled_len = 0;
+
+	/*
+	 * Generate random index between 0..7. We do chunks of 512b, if
+	 * we assume a cacheline is 64 bytes, then we have 8 of those.
+	 * Scramble content within the blocks in the same cacheline to
+	 * speed things up.
+	 */
+	offset = (io_u->start_time.tv_nsec ^ boffset) & 7;
 
 	for (i = 0; i < nr_blocks; i++) {
 		/*
-		 * Fill the byte offset into a "random" start offset of
-		 * the buffer, given by the product of the usec time
-		 * and the actual offset.
+		 * Fill offset into start of cacheline, time into end
+		 * of cacheline
 		 */
-		offset = ((io_u->start_time.tv_nsec/1000) ^ boffset) & 511;
-		offset &= ~(sizeof(uint64_t) - 1);
-		if (offset >= 512 - sizeof(uint64_t))
-			offset -= sizeof(uint64_t);
-		memcpy(p + offset, &boffset, sizeof(boffset));
-
-		end = p + 512 - sizeof(io_u->start_time);
-		memcpy(end, &io_u->start_time, sizeof(io_u->start_time));
+		iptr = (void *) p + (offset << 6);
+		*iptr = boffset;
+
+		iptr = (void *) p + 64 - 2 * sizeof(uint64_t);
+		iptr[0] = io_u->start_time.tv_sec;
+		iptr[1] = io_u->start_time.tv_nsec;
+
 		p += 512;
 		boffset += 512;
 	}
@@ -1868,14 +1872,14 @@ static void account_io_completion(struct thread_data *td, struct io_u *io_u,
 			struct prof_io_ops *ops = &td->prof_io_ops;
 
 			if (ops->io_u_lat)
-				icd->error = ops->io_u_lat(td, tnsec/1000);
+				icd->error = ops->io_u_lat(td, tnsec);
 		}
 
-		if (td->o.max_latency && tnsec/1000 > td->o.max_latency)
-			lat_fatal(td, icd, tnsec/1000, td->o.max_latency);
-		if (td->o.latency_target && tnsec/1000 > td->o.latency_target) {
+		if (td->o.max_latency && tnsec > td->o.max_latency)
+			lat_fatal(td, icd, tnsec, td->o.max_latency);
+		if (td->o.latency_target && tnsec > td->o.latency_target) {
 			if (lat_target_failed(td))
-				lat_fatal(td, icd, tnsec/1000, td->o.latency_target);
+				lat_fatal(td, icd, tnsec, td->o.latency_target);
 		}
 	}
 
@@ -1972,11 +1976,12 @@ static void io_completed(struct thread_data *td, struct io_u **io_u_ptr,
 		int ret;
 
 		td->io_blocks[ddir]++;
-		td->this_io_blocks[ddir]++;
 		td->io_bytes[ddir] += bytes;
 
-		if (!(io_u->flags & IO_U_F_VER_LIST))
+		if (!(io_u->flags & IO_U_F_VER_LIST)) {
+			td->this_io_blocks[ddir]++;
 			td->this_io_bytes[ddir] += bytes;
+		}
 
 		if (ddir == DDIR_WRITE)
 			file_log_write_comp(td, f, io_u->offset, bytes);