*/
#include <stdio.h>
#include <stdlib.h>
+#include <libgen.h>
#include <assert.h>
-#include "list.h"
+#include "flist.h"
#include "fio.h"
+#include "verify.h"
+#include "trim.h"
static const char iolog_ver2[] = "fio version 2 iolog";
+void queue_io_piece(struct thread_data *td, struct io_piece *ipo)
+{
+ flist_add_tail(&ipo->list, &td->io_log_list);
+ td->total_io_size += ipo->len;
+}
+
void log_io_u(struct thread_data *td, struct io_u *io_u)
{
- const char *act[] = { "read", "write", "sync" };
+ const char *act[] = { "read", "write", "sync", "datasync",
+ "sync_file_range", "wait", "trim" };
- assert(io_u->ddir < 3);
+ assert(io_u->ddir <= 6);
if (!td->o.write_iolog_file)
return;
- fprintf(td->iolog_f, "%s %s %llu %lu\n", io_u->file->file_name, act[io_u->ddir], io_u->offset, io_u->buflen);
+ fprintf(td->iolog_f, "%s %s %llu %lu\n", io_u->file->file_name,
+ act[io_u->ddir], io_u->offset,
+ io_u->buflen);
}
void log_file(struct thread_data *td, struct fio_file *f,
if (!td->o.write_iolog_file)
return;
+
+ /*
+ * this happens on the pre-open/close done before the job starts
+ */
+ if (!td->iolog_f)
+ return;
+
fprintf(td->iolog_f, "%s %s\n", f->file_name, act[what]);
}
usec_sleep(td, delay);
}
-int read_iolog_get(struct thread_data *td, struct io_u *io_u)
+static int ipo_special(struct thread_data *td, struct io_piece *ipo)
{
- struct io_piece *ipo;
+ struct fio_file *f;
+ int ret;
+
+ /*
+ * Not a special ipo
+ */
+ if (ipo->ddir != DDIR_INVAL)
+ return 0;
- while (!list_empty(&td->io_log_list)) {
- ipo = list_entry(td->io_log_list.next, struct io_piece, list);
- list_del(&ipo->list);
+ f = td->files[ipo->fileno];
+
+ switch (ipo->file_action) {
+ case FIO_LOG_OPEN_FILE:
+ ret = td_io_open_file(td, f);
+ if (!ret)
+ break;
+ td_verror(td, ret, "iolog open file");
+ return -1;
+ case FIO_LOG_CLOSE_FILE:
+ td_io_close_file(td, f);
+ break;
+ case FIO_LOG_UNLINK_FILE:
+ unlink(f->file_name);
+ break;
+ default:
+ log_err("fio: bad file action %d\n", ipo->file_action);
+ break;
+ }
- /*
- * invalid ddir, this is a file action
- */
- if (ipo->ddir == DDIR_INVAL) {
- struct fio_file *f = &td->files[ipo->fileno];
+ return 1;
+}
- if (ipo->file_action == FIO_LOG_OPEN_FILE) {
- assert(!td_io_open_file(td, f));
- free(ipo);
- continue;
- } else if (ipo->file_action == FIO_LOG_CLOSE_FILE) {
- td_io_close_file(td, f);
- free(ipo);
- continue;
- }
+int read_iolog_get(struct thread_data *td, struct io_u *io_u)
+{
+ struct io_piece *ipo;
+ unsigned long elapsed;
+
+ while (!flist_empty(&td->io_log_list)) {
+ int ret;
+
+ ipo = flist_entry(td->io_log_list.next, struct io_piece, list);
+ flist_del(&ipo->list);
+ remove_trim_entry(td, ipo);
+
+ ret = ipo_special(td, ipo);
+ if (ret < 0) {
+ free(ipo);
+ break;
+ } else if (ret > 0) {
+ free(ipo);
+ continue;
}
- io_u->offset = ipo->offset;
- io_u->buflen = ipo->len;
io_u->ddir = ipo->ddir;
- io_u->file = &td->files[ipo->fileno];
- get_file(io_u->file);
-
- if (ipo->delay)
- iolog_delay(td, ipo->delay);
+ if (ipo->ddir != DDIR_WAIT) {
+ io_u->offset = ipo->offset;
+ io_u->buflen = ipo->len;
+ io_u->file = td->files[ipo->fileno];
+ get_file(io_u->file);
+ dprint(FD_IO, "iolog: get %llu/%lu/%s\n", io_u->offset,
+ io_u->buflen, io_u->file->file_name);
+ if (ipo->delay)
+ iolog_delay(td, ipo->delay);
+ } else {
+ elapsed = mtime_since_genesis();
+ if (ipo->delay > elapsed)
+ usec_sleep(td, (ipo->delay - elapsed) * 1000);
+
+ }
free(ipo);
- return 0;
+
+ if (io_u->ddir != DDIR_WAIT)
+ return 0;
}
td->done = 1;
while ((n = rb_first(&td->io_hist_tree)) != NULL) {
ipo = rb_entry(n, struct io_piece, rb_node);
rb_erase(n, &td->io_hist_tree);
+ remove_trim_entry(td, ipo);
+ td->io_hist_len--;
+ free(ipo);
+ }
+
+ while (!flist_empty(&td->io_hist_list)) {
+ ipo = flist_entry(td->io_hist_list.next, struct io_piece, list);
+ flist_del(&ipo->list);
+ remove_trim_entry(td, ipo);
+ td->io_hist_len--;
free(ipo);
}
}
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;
+ 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:
*
*
* 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_random(td) || !td->o.overwrite ||
- (io_u->file->flags & FIO_FILE_NOSORT)) {
- INIT_LIST_HEAD(&ipo->list);
- list_add_tail(&ipo->list, &td->io_hist_list);
+ if ((!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);
- p = &td->io_hist_tree.rb_node;
- parent = NULL;
/*
* 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->offset <= __ipo->offset)
+ if (ipo->file < __ipo->file)
p = &(*p)->rb_left;
- else
+ 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 {
+ assert(ipo->len == __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++;
}
void write_iolog_close(struct thread_data *td)
{
unsigned long long offset;
unsigned int bytes;
- int reads, writes, fileno = 0, file_action = 0; /* stupid gcc */
+ int reads, writes, waits, fileno = 0, file_action = 0; /* stupid gcc */
char *fname, *act;
char *str, *p;
enum fio_ddir rw;
fname = malloc(256+16);
act = malloc(256+16);
- reads = writes = 0;
+ 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);
+ r = sscanf(p, "%256s %256s %llu %u", fname, act, &offset,
+ &bytes);
if (r == 4) {
/*
* Check action first
*/
- if (!strcmp(act, "read"))
+ 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);
+ log_err("fio: bad iolog file action: %s\n",
+ act);
continue;
}
} else if (r == 2) {
fileno = get_fileno(td, fname);
file_action = FIO_LOG_CLOSE_FILE;
} else {
- log_err("fio: bad iolog file action: %s\n",act);
+ 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)
+ else if (rw == DDIR_WRITE) {
+ /*
+ * Don't add a write for ro mode
+ */
+ if (read_only)
+ continue;
writes++;
- else if (rw != DDIR_SYNC && rw != DDIR_INVAL) {
+ } 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));
- memset(ipo, 0, sizeof(*ipo));
- INIT_LIST_HEAD(&ipo->list);
- ipo->offset = offset;
- ipo->len = bytes;
+ init_ipo(ipo);
ipo->ddir = rw;
- if (bytes > td->o.max_bs[rw])
- td->o.max_bs[rw] = bytes;
- if (rw == DDIR_INVAL) {
+ if (rw == DDIR_WAIT) {
+ ipo->delay = offset;
+ } else {
+ ipo->offset = offset;
+ ipo->len = bytes;
+ if (bytes > td->o.max_bs[rw])
+ td->o.max_bs[rw] = bytes;
ipo->fileno = fileno;
ipo->file_action = file_action;
}
- list_add_tail(&ipo->list, &td->io_log_list);
- td->total_io_size += bytes;
+
+ queue_io_piece(td, ipo);
}
free(str);
free(act);
free(fname);
- if (!reads && !writes)
- 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;
-}
-
-/*
- * Read version 1 iolog data.
- */
-static int read_iolog(struct thread_data *td, FILE *f)
-{
- unsigned long long offset;
- unsigned int bytes;
- char *str, *p;
- int reads, writes;
- enum fio_ddir rw;
-
- /*
- * Read in the read iolog and store it, reuse the infrastructure
- * for doing verifications.
- */
- str = malloc(4096);
- reads = writes = 0;
- while ((p = fgets(str, 4096, f)) != NULL) {
- struct io_piece *ipo;
-
- if (sscanf(p, "%d,%llu,%u", &rw, &offset, &bytes) != 3) {
- log_err("bad iolog: %s\n", p);
- continue;
- }
- if (rw == DDIR_READ)
- reads++;
- else if (rw == DDIR_WRITE)
- writes++;
- else if (rw != DDIR_SYNC) {
- log_err("bad ddir: %d\n", rw);
- continue;
- }
-
- ipo = malloc(sizeof(*ipo));
- memset(ipo, 0, sizeof(*ipo));
- INIT_LIST_HEAD(&ipo->list);
- ipo->offset = offset;
- ipo->len = bytes;
- ipo->ddir = rw;
- if (bytes > td->o.max_bs[rw])
- td->o.max_bs[rw] = bytes;
- list_add_tail(&ipo->list, &td->io_log_list);
- td->total_io_size += bytes;
+ if (writes && read_only) {
+ log_err("fio: <%s> skips replay of %d writes due to"
+ " read-only\n", td->o.name, writes);
+ writes = 0;
}
- free(str);
-
- if (!reads && !writes)
+ if (!reads && !writes && !waits)
return 1;
else if (reads && !writes)
td->o.td_ddir = TD_DDIR_READ;
if (!strncmp(iolog_ver2, buffer, strlen(iolog_ver2)))
ret = read_iolog2(td, f);
else {
- /*
- * seek back to the beginning
- */
- if (fseek(f, 0, SEEK_SET) < 0) {
- td_verror(td, errno, "iolog read");
- log_err("fio: unable to read iolog\n");
- return 1;
- }
-
- ret = read_iolog(td, f);
+ log_err("fio: iolog version 1 is no longer supported\n");
+ ret = 1;
}
fclose(f);
FILE *f;
unsigned int i;
- f = fopen(td->o.write_iolog_file, "w+");
+ f = fopen(td->o.write_iolog_file, "a");
if (!f) {
perror("fopen write iolog");
return 1;
{
int ret = 0;
- if (td->io_ops->flags & FIO_DISKLESSIO)
- return 0;
-
if (td->o.read_iolog_file) {
/*
* Check if it's a blktrace file and load that if possible.
unsigned int i;
FILE *f;
- f = fopen(name, "w");
+ f = fopen(name, "a");
if (!f) {
perror("fopen log");
return;
}
- for (i = 0; i < log->nr_samples; i++)
- fprintf(f, "%lu, %lu, %u\n", log->log[i].time, log->log[i].val, log->log[i].ddir);
+ for (i = 0; i < log->nr_samples; i++) {
+ fprintf(f, "%lu, %lu, %u, %u\n", log->log[i].time,
+ log->log[i].val,
+ log->log[i].ddir,
+ log->log[i].bs);
+ }
fclose(f);
free(log->log);
free(log);
}
-void finish_log(struct thread_data *td, struct io_log *log, const char *name)
+void finish_log_named(struct thread_data *td, struct io_log *log,
+ const char *prefix, const char *postfix)
{
- char file_name[256];
+ char file_name[256], *p;
+
+ snprintf(file_name, 200, "%s_%s.log", prefix, postfix);
+ p = basename(file_name);
+ __finish_log(log, p);
+}
- snprintf(file_name, 200, "client%d_%s.log", td->thread_number, name);
- __finish_log(log, file_name);
+void finish_log(struct thread_data *td, struct io_log *log, const char *name)
+{
+ finish_log_named(td, log, td->o.name, name);
}