t/io_uring: link with libaio when necessary

[fio.git] / io_u.c

diff --git a/io_u.c b/io_u.c
index b421a579bd0a1aaa594692a21731a2774de77cea..3c72d63d0d5368db1ecae9158371f99efb9a27e0 100644 (file)
--- a/io_u.c
+++ b/io_u.c
@@ -1595,7 +1595,7 @@ again:
                assert(io_u->flags & IO_U_F_FREE);
                io_u_clear(td, io_u, IO_U_F_FREE | IO_U_F_NO_FILE_PUT |
                                 IO_U_F_TRIMMED | IO_U_F_BARRIER |
-                                IO_U_F_VER_LIST | IO_U_F_PRIORITY);
+                                IO_U_F_VER_LIST | IO_U_F_HIGH_PRIO);
 
                io_u->error = 0;
                io_u->acct_ddir = -1;
@@ -1799,6 +1799,10 @@ struct io_u *get_io_u(struct thread_data *td)
        io_u->xfer_buf = io_u->buf;
        io_u->xfer_buflen = io_u->buflen;
 
+       /*
+        * Remember the issuing context priority. The IO engine may change this.
+        */
+       io_u->ioprio = td->ioprio;
 out:
        assert(io_u->file);
        if (!td_io_prep(td, io_u)) {
@@ -1884,7 +1888,8 @@ static void account_io_completion(struct thread_data *td, struct io_u *io_u,
                unsigned long long tnsec;
 
                tnsec = ntime_since(&io_u->start_time, &icd->time);
-               add_lat_sample(td, idx, tnsec, bytes, io_u->offset, io_u_is_prio(io_u));
+               add_lat_sample(td, idx, tnsec, bytes, io_u->offset,
+                              io_u->ioprio, io_u_is_high_prio(io_u));
 
                if (td->flags & TD_F_PROFILE_OPS) {
                        struct prof_io_ops *ops = &td->prof_io_ops;
@@ -1905,7 +1910,8 @@ static void account_io_completion(struct thread_data *td, struct io_u *io_u,
 
        if (ddir_rw(idx)) {
                if (!td->o.disable_clat) {
-                       add_clat_sample(td, idx, llnsec, bytes, io_u->offset, io_u_is_prio(io_u));
+                       add_clat_sample(td, idx, llnsec, bytes, io_u->offset,
+                                       io_u->ioprio, io_u_is_high_prio(io_u));
                        io_u_mark_latency(td, llnsec);
                }
 
@@ -1998,7 +2004,7 @@ static void io_completed(struct thread_data *td, struct io_u **io_u_ptr,
                 * Make sure we notice short IO from here, and requeue them
                 * appropriately!
                 */
-               if (io_u->resid) {
+               if (bytes && io_u->resid) {
                        io_u->xfer_buflen = io_u->resid;
                        io_u->xfer_buf += bytes;
                        io_u->offset += bytes;
@@ -2162,7 +2168,7 @@ void io_u_queued(struct thread_data *td, struct io_u *io_u)
                        td = td->parent;
 
                add_slat_sample(td, io_u->ddir, slat_time, io_u->xfer_buflen,
-                               io_u->offset, io_u_is_prio(io_u));
+                               io_u->offset, io_u->ioprio);
        }
 }
 
@@ -2172,6 +2178,7 @@ void io_u_queued(struct thread_data *td, struct io_u *io_u)
 static struct frand_state *get_buf_state(struct thread_data *td)
 {
        unsigned int v;
+       unsigned long long i;
 
        if (!td->o.dedupe_percentage)
                return &td->buf_state;
@@ -2183,7 +2190,24 @@ static struct frand_state *get_buf_state(struct thread_data *td)
        v = rand_between(&td->dedupe_state, 1, 100);
 
        if (v <= td->o.dedupe_percentage)
-               return &td->buf_state_prev;
+               switch (td->o.dedupe_mode) {
+               case DEDUPE_MODE_REPEAT:
+                       /*
+                       * The caller advances the returned frand_state.
+                       * A copy of prev should be returned instead since
+                       * a subsequent intention to generate a deduped buffer
+                       * might result in generating a unique one
+                       */
+                       frand_copy(&td->buf_state_ret, &td->buf_state_prev);
+                       return &td->buf_state_ret;
+               case DEDUPE_MODE_WORKING_SET:
+                       i = rand_between(&td->dedupe_working_set_index_state, 0, td->num_unique_pages - 1);
+                       frand_copy(&td->buf_state_ret, &td->dedupe_working_set_states[i]);
+                       return &td->buf_state_ret;
+               default:
+                       log_err("unexpected dedupe mode %u\n", td->o.dedupe_mode);
+                       assert(0);
+               }
 
        return &td->buf_state;
 }
@@ -2206,27 +2230,30 @@ void fill_io_buffer(struct thread_data *td, void *buf, unsigned long long min_wr
 
        if (o->compress_percentage || o->dedupe_percentage) {
                unsigned int perc = td->o.compress_percentage;
-               struct frand_state *rs;
+               struct frand_state *rs = NULL;
                unsigned long long left = max_bs;
                unsigned long long this_write;
 
                do {
-                       rs = get_buf_state(td);
+                       /*
+                        * Buffers are either entirely dedupe-able or not.
+                        * If we choose to dedup, the buffer should undergo
+                        * the same manipulation as the original write. Which
+                        * means we should retrack the steps we took for compression
+                        * as well.
+                        */
+                       if (!rs)
+                               rs = get_buf_state(td);
 
                        min_write = min(min_write, left);
 
-                       if (perc) {
-                               this_write = min_not_zero(min_write,
-                                                       (unsigned long long) td->o.compress_chunk);
+                       this_write = min_not_zero(min_write,
+                                               (unsigned long long) td->o.compress_chunk);
 
-                               fill_random_buf_percentage(rs, buf, perc,
-                                       this_write, this_write,
-                                       o->buffer_pattern,
-                                       o->buffer_pattern_bytes);
-                       } else {
-                               fill_random_buf(rs, buf, min_write);
-                               this_write = min_write;
-                       }
+                       fill_random_buf_percentage(rs, buf, perc,
+                               this_write, this_write,
+                               o->buffer_pattern,
+                               o->buffer_pattern_bytes);
 
                        buf += this_write;
                        left -= this_write;
@@ -2299,10 +2326,19 @@ int do_io_u_trim(const struct thread_data *td, struct io_u *io_u)
        struct fio_file *f = io_u->file;
        int ret;
 
+       if (td->o.zone_mode == ZONE_MODE_ZBD) {
+               ret = zbd_do_io_u_trim(td, io_u);
+               if (ret == io_u_completed)
+                       return io_u->xfer_buflen;
+               if (ret)
+                       goto err;
+       }
+
        ret = os_trim(f, io_u->offset, io_u->xfer_buflen);
        if (!ret)
                return io_u->xfer_buflen;
 
+err:
        io_u->error = ret;
        return 0;
 #endif