Add option to ignore thinktime for rated IO

[fio.git] / io_u.c

diff --git a/io_u.c b/io_u.c
index 8087bd6a119217e9df7954bfec52a4afaea1dcd7..7ccbd312d8d0018f57159baa05b1cf31b0583639 100644 (file)
--- 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;
 }
 
@@ -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;
+       unsigned int i, nr_blocks = io_u->buflen >> 9;
        unsigned int offset;
-       uint64_t boffset;
-       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 ^ 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;
        }
@@ -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);