static void handle_trace_discard(struct thread_data *td,
struct blk_io_trace *t,
unsigned long long ttime,
unsigned long *ios, unsigned int *bs)
{
struct io_piece *ipo = malloc(sizeof(*ipo));
int fileno;
init_ipo(ipo);
fileno = trace_add_file(td, t->device);
ios[DDIR_TRIM]++;
if (t->bytes > bs[DDIR_TRIM])
bs[DDIR_TRIM] = t->bytes;
td->o.size += t->bytes;
memset(ipo, 0, sizeof(*ipo));
INIT_FLIST_HEAD(&ipo->list);
/*
* the 512 is wrong here, it should be the hardware sector size...
*/
ipo->offset = t->sector * 512;
ipo->len = t->bytes;
ipo->delay = ttime / 1000;
ipo->ddir = DDIR_TRIM;
ipo->fileno = fileno;
dprint(FD_BLKTRACE, "store discard, off=%llu, len=%lu, delay=%lu\n",
ipo->offset, ipo->len,
ipo->delay);
queue_io_piece(td, ipo);
}
/*
* Store blk_io_trace data in an ipo for later retrieval.
*/
static void store_ipo(struct thread_data *td, unsigned long long offset,
unsigned int bytes, int rw, unsigned long long ttime,
int fileno)
{
struct io_piece *ipo = malloc(sizeof(*ipo));
init_ipo(ipo);
/*
* the 512 is wrong here, it should be the hardware sector size...
*/
ipo->offset = offset * 512;
ipo->len = bytes;
ipo->delay = ttime / 1000;
if (rw)
ipo->ddir = DDIR_WRITE;
else
ipo->ddir = DDIR_READ;
ipo->fileno = fileno;
dprint(FD_BLKTRACE, "store ddir=%d, off=%llu, len=%lu, delay=%lu\n",
ipo->ddir, ipo->offset,
ipo->len, ipo->delay);
queue_io_piece(td, ipo);
}
static void handle_trace_discard(struct thread_data *td,
struct blk_io_trace *t,
unsigned long long ttime,
unsigned long *ios, unsigned int *rw_bs)
{
struct io_piece *ipo = malloc(sizeof(*ipo));
unsigned int bs;
int fileno;
init_ipo(ipo);
fileno = trace_add_file(td, t->device, &bs);
ios[DDIR_TRIM]++;
if (t->bytes > rw_bs[DDIR_TRIM])
rw_bs[DDIR_TRIM] = t->bytes;
td->o.size += t->bytes;
memset(ipo, 0, sizeof(*ipo));
INIT_FLIST_HEAD(&ipo->list);
ipo->offset = t->sector * bs;
if (td->o.replay_scale)
ipo->offset = ipo->offset / td->o.replay_scale;
ipo_bytes_align(&td->o, ipo);
ipo->len = t->bytes;
ipo->delay = ttime / 1000;
ipo->ddir = DDIR_TRIM;
ipo->fileno = fileno;
dprint(FD_BLKTRACE, "store discard, off=%llu, len=%lu, delay=%lu\n",
ipo->offset, ipo->len,
ipo->delay);
queue_io_piece(td, ipo);
}
/*
* Store blk_io_trace data in an ipo for later retrieval.
*/
static void store_ipo(struct thread_data *td, unsigned long long offset,
unsigned int bytes, int rw, unsigned long long ttime,
int fileno, unsigned int bs)
{
struct io_piece *ipo = malloc(sizeof(*ipo));
init_ipo(ipo);
ipo->offset = offset * bs;
if (td->o.replay_scale)
ipo->offset = ipo->offset / td->o.replay_scale;
ipo_bytes_align(&td->o, ipo);
ipo->len = bytes;
ipo->delay = ttime / 1000;
if (rw)
ipo->ddir = DDIR_WRITE;
else
ipo->ddir = DDIR_READ;
ipo->fileno = fileno;
dprint(FD_BLKTRACE, "store ddir=%d, off=%llu, len=%lu, delay=%lu\n",
ipo->ddir, ipo->offset,
ipo->len, ipo->delay);
queue_io_piece(td, ipo);
}
static void trace_add_open_close_event(struct thread_data *td, int fileno, enum file_log_act action)
{
struct io_piece *ipo;
ipo = calloc(1, sizeof(*ipo));
init_ipo(ipo);
ipo->ddir = DDIR_INVAL;
ipo->fileno = fileno;
ipo->file_action = action;
flist_add_tail(&ipo->list, &td->io_log_list);
}
static void trace_add_open_event(struct thread_data *td, int fileno)
{
struct io_piece *ipo;
ipo = calloc(1, sizeof(*ipo));
init_ipo(ipo);
ipo->ddir = DDIR_INVAL;
ipo->fileno = fileno;
ipo->file_action = FIO_LOG_OPEN_FILE;
flist_add_tail(&ipo->list, &td->io_log_list);
}
/*
* Read version 2 iolog data. It is enhanced to include per-file logging,
* syncs, etc.
*/
static int read_iolog2(struct thread_data *td, FILE *f)
{
unsigned long long offset;
unsigned int bytes;
int reads, writes, waits, fileno = 0, file_action = 0; /* stupid gcc */
char *fname, *act;
char *str, *p;
enum fio_ddir rw;
free_release_files(td);
/*
* Read in the read iolog and store it, reuse the infrastructure
* for doing verifications.
*/
str = malloc(4096);
fname = malloc(256+16);
act = malloc(256+16);
reads = writes = waits = 0;
while ((p = fgets(str, 4096, f)) != NULL) {
struct io_piece *ipo;
int r;
r = sscanf(p, "%256s %256s %llu %u", fname, act, &offset,
&bytes);
if (r == 4) {
/*
* Check action first
*/
if (!strcmp(act, "wait"))
rw = DDIR_WAIT;
else if (!strcmp(act, "read"))
rw = DDIR_READ;
else if (!strcmp(act, "write"))
rw = DDIR_WRITE;
else if (!strcmp(act, "sync"))
rw = DDIR_SYNC;
else if (!strcmp(act, "datasync"))
rw = DDIR_DATASYNC;
else if (!strcmp(act, "trim"))
rw = DDIR_TRIM;
else {
log_err("fio: bad iolog file action: %s\n",
act);
continue;
}
fileno = get_fileno(td, fname);
} else if (r == 2) {
rw = DDIR_INVAL;
if (!strcmp(act, "add")) {
fileno = add_file(td, fname, 0, 1);
file_action = FIO_LOG_ADD_FILE;
continue;
} else if (!strcmp(act, "open")) {
fileno = get_fileno(td, fname);
file_action = FIO_LOG_OPEN_FILE;
} else if (!strcmp(act, "close")) {
fileno = get_fileno(td, fname);
file_action = FIO_LOG_CLOSE_FILE;
} else {
log_err("fio: bad iolog file action: %s\n",
act);
continue;
}
} else {
log_err("bad iolog2: %s", p);
continue;
}
if (rw == DDIR_READ)
reads++;
else if (rw == DDIR_WRITE) {
/*
* Don't add a write for ro mode
*/
if (read_only)
continue;
writes++;
} else if (rw == DDIR_WAIT) {
waits++;
} else if (rw == DDIR_INVAL) {
} else if (!ddir_sync(rw)) {
log_err("bad ddir: %d\n", rw);
continue;
}
/*
* Make note of file
*/
ipo = malloc(sizeof(*ipo));
init_ipo(ipo);
ipo->ddir = rw;
if (rw == DDIR_WAIT) {
ipo->delay = offset;
} else {
ipo->offset = offset;
ipo->len = bytes;
if (rw != DDIR_INVAL && bytes > td->o.max_bs[rw])
td->o.max_bs[rw] = bytes;
ipo->fileno = fileno;
ipo->file_action = file_action;
td->o.size += bytes;
}
queue_io_piece(td, ipo);
}
free(str);
free(act);
free(fname);
if (writes && read_only) {
log_err("fio: <%s> skips replay of %d writes due to"
" read-only\n", td->o.name, writes);
writes = 0;
}
if (!reads && !writes && !waits)
return 1;
else if (reads && !writes)
td->o.td_ddir = TD_DDIR_READ;
else if (!reads && writes)
td->o.td_ddir = TD_DDIR_WRITE;
else
td->o.td_ddir = TD_DDIR_RW;
return 0;
}
/*
* log a successful write, so we can unwind the log for verify
*/
void log_io_piece(struct thread_data *td, struct io_u *io_u)
{
struct rb_node **p, *parent;
struct io_piece *ipo, *__ipo;
ipo = malloc(sizeof(struct io_piece));
init_ipo(ipo);
ipo->file = io_u->file;
ipo->offset = io_u->offset;
ipo->len = io_u->buflen;
ipo->numberio = io_u->numberio;
ipo->flags = IP_F_IN_FLIGHT;
io_u->ipo = ipo;
if (io_u_should_trim(td, io_u)) {
flist_add_tail(&ipo->trim_list, &td->trim_list);
td->trim_entries++;
}
/*
* We don't need to sort the entries, if:
*
* Sequential writes, or
* Random writes that lay out the file as it goes along
*
* For both these cases, just reading back data in the order we
* wrote it out is the fastest.
*
* One exception is if we don't have a random map AND we are doing
* verifies, in that case we need to check for duplicate blocks and
* drop the old one, which we rely on the rb insert/lookup for
* handling.
*/
if (((!td->o.verifysort) || !td_random(td) || !td->o.overwrite) &&
(file_randommap(td, ipo->file) || td->o.verify == VERIFY_NONE)) {
INIT_FLIST_HEAD(&ipo->list);
flist_add_tail(&ipo->list, &td->io_hist_list);
ipo->flags |= IP_F_ONLIST;
td->io_hist_len++;
return;
}
RB_CLEAR_NODE(&ipo->rb_node);
/*
* Sort the entry into the verification list
*/
restart:
p = &td->io_hist_tree.rb_node;
parent = NULL;
while (*p) {
parent = *p;
__ipo = rb_entry(parent, struct io_piece, rb_node);
if (ipo->file < __ipo->file)
p = &(*p)->rb_left;
else if (ipo->file > __ipo->file)
p = &(*p)->rb_right;
else if (ipo->offset < __ipo->offset)
p = &(*p)->rb_left;
else if (ipo->offset > __ipo->offset)
p = &(*p)->rb_right;
else {
dprint(FD_IO, "iolog: overlap %llu/%lu, %llu/%lu",
__ipo->offset, __ipo->len,
ipo->offset, ipo->len);
td->io_hist_len--;
rb_erase(parent, &td->io_hist_tree);
remove_trim_entry(td, __ipo);
free(__ipo);
goto restart;
}
}
rb_link_node(&ipo->rb_node, parent, p);
rb_insert_color(&ipo->rb_node, &td->io_hist_tree);
ipo->flags |= IP_F_ONRB;
td->io_hist_len++;
}