Re: How to re-use default sequential filenames?

[Jens Axboe <axboe@kernel.dk>]

On Thu, Apr 04 2013, Jens Axboe wrote:
> On Thu, Apr 04 2013, Alan Hagge wrote:
> > I'm trying to put together a test of the write and read speed to some new
> > SAN storage.  Our workflow involves writing large numbers of 12 MiB files
> > (on the order of 20,000 or so) at a time.  I'd like to set up a config file
> > section that will write all 20,000 files then read all 20,000 files and
> > report on the write performance and the read performance (separately).
> > 
> > I've tried something like this:
> > 
> > [global]
> > blocksize=4m
> > filesize=12m
> > nrfiles=20000
> > openfiles=1
> > file_service_type=sequential
> > create_on_open=1
> > ioengine=posixaio
> > 
> > [write]
> > rw=write
> > 
> > [read]
> > stonewall
> > rw=read
> > 
> > But the issue is that the files get created with default filenames
> > (write.1.1, write.1.2, etc.), so that when the read job is run, it can't
> > find any files (since it expects the files to be named read.1.1, read.1.2,
> > etc.).  If I try to specify the "filename=" option in either section, fio no
> > longer appends the ".<thread>.<sequence>" to the filename, but rather tries
> > to do all I/O to a single file.
> > 
> > Is there a syntax for the "filename=" option that will allow me to specify a
> > different root filename, but still use the ".<thread>.<sequence>" naming
> > convention?  Failing that, is there any other way to accomplish my goal?
> 
> Good question, and no, you can't currently do that. But you should be
> able to do that. Fio has no current option for specifying the naming. We
> could have a fileprefix= option that allows you to set that.
> 
> So we currently have two options. The first option is that you take on
> this task. The file name (if not given with filename=) is generated in
> init.c:add_job(), here:
> 
> 	if (!td->o.filename && !td->files_index && !td->o.read_iolog_file) {
> 		file_alloced = 1;
> 
> 		if (td->o.nr_files == 1 && exists_and_not_file(jobname))
> 			add_file(td, jobname);
> 		else {
> 			for (i = 0; i < td->o.nr_files; i++) {
> 				sprintf(fname, "%s.%d.%d", jobname,
> 							td->thread_number, i);
> 				add_file(td, fname);
> 			}
> 		}
> 	}
> 
> Options are pretty easy to add, basically just an entry in the
> fio_option options[] array in options.c with pretty much
> self-explanatory fields. Add matching string type in fio.h to
> thread_options{ }.
> 
> The other option is that you claim that you are not a programmer, and
> then you are at the mercy of someone else (most likely me!) doing it for
> you. Since this is a good feature request, I can be talked into that as
> well.
> 
> Let me know.

OK, so I give it a quick shot, see below. Basically it allows you to set
fileprefix= to override the jobname.threadnumber part of the file. So
not super flexible, we'd need some reserved keywords to make it fully
flexible. Eg it would be nifty if you could do:

fileprefix=$jobnum.$threadnum.$filenum

to get the behaviour we have now, and then you could do:

fileprefix=somename.$filenum

to get the behavior you are looking for.


diff --git a/filesetup.c b/filesetup.c
index e456186..88d6565 100644
--- a/filesetup.c
+++ b/filesetup.c
@@ -719,13 +719,14 @@ uint64_t get_start_offset(struct thread_data *td)
 int setup_files(struct thread_data *td)
 {
 	unsigned long long total_size, extend_size;
+	struct thread_options *o = &td->o;
 	struct fio_file *f;
 	unsigned int i;
 	int err = 0, need_extend;
 
 	dprint(FD_FILE, "setup files\n");
 
-	if (td->o.read_iolog_file)
+	if (o->read_iolog_file)
 		goto done;
 
 	/*
@@ -753,15 +754,16 @@ int setup_files(struct thread_data *td)
 			total_size += f->real_file_size;
 	}
 
-	if (td->o.fill_device)
+	if (o->fill_device)
 		td->fill_device_size = get_fs_free_counts(td);
 
 	/*
 	 * device/file sizes are zero and no size given, punt
 	 */
-	if ((!total_size || total_size == -1ULL) && !td->o.size &&
-	    !(td->io_ops->flags & FIO_NOIO) && !td->o.fill_device) {
-		log_err("%s: you need to specify size=\n", td->o.name);
+	if ((!total_size || total_size == -1ULL) && !o->size &&
+	    !(td->io_ops->flags & FIO_NOIO) && !o->fill_device &&
+	    !(o->nr_files && (o->file_size_low || o->file_size_high))) {
+		log_err("%s: you need to specify size=\n", o->name);
 		td_verror(td, EINVAL, "total_file_size");
 		return 1;
 	}
@@ -776,27 +778,26 @@ int setup_files(struct thread_data *td)
 	for_each_file(td, f, i) {
 		f->file_offset = get_start_offset(td);
 
-		if (!td->o.file_size_low) {
+		if (!o->file_size_low) {
 			/*
 			 * no file size range given, file size is equal to
 			 * total size divided by number of files. if that is
 			 * zero, set it to the real file size.
 			 */
-			f->io_size = td->o.size / td->o.nr_files;
+			f->io_size = o->size / o->nr_files;
 			if (!f->io_size)
 				f->io_size = f->real_file_size - f->file_offset;
-		} else if (f->real_file_size < td->o.file_size_low ||
-			   f->real_file_size > td->o.file_size_high) {
-			if (f->file_offset > td->o.file_size_low)
+		} else if (f->real_file_size < o->file_size_low ||
+			   f->real_file_size > o->file_size_high) {
+			if (f->file_offset > o->file_size_low)
 				goto err_offset;
 			/*
 			 * file size given. if it's fixed, use that. if it's a
 			 * range, generate a random size in-between.
 			 */
-			if (td->o.file_size_low == td->o.file_size_high) {
-				f->io_size = td->o.file_size_low
-						- f->file_offset;
-			} else {
+			if (o->file_size_low == o->file_size_high)
+				f->io_size = o->file_size_low - f->file_offset;
+			else {
 				f->io_size = get_rand_file_size(td)
 						- f->file_offset;
 			}
@@ -806,15 +807,15 @@ int setup_files(struct thread_data *td)
 		if (f->io_size == -1ULL)
 			total_size = -1ULL;
 		else {
-                        if (td->o.size_percent)
-                                f->io_size = (f->io_size * td->o.size_percent) / 100;
+                        if (o->size_percent)
+                                f->io_size = (f->io_size * o->size_percent) / 100;
 			total_size += f->io_size;
 		}
 
 		if (f->filetype == FIO_TYPE_FILE &&
 		    (f->io_size + f->file_offset) > f->real_file_size &&
 		    !(td->io_ops->flags & FIO_DISKLESSIO)) {
-			if (!td->o.create_on_open) {
+			if (!o->create_on_open) {
 				need_extend++;
 				extend_size += (f->io_size + f->file_offset);
 			} else
@@ -823,8 +824,8 @@ int setup_files(struct thread_data *td)
 		}
 	}
 
-	if (!td->o.size || td->o.size > total_size)
-		td->o.size = total_size;
+	if (!o->size || o->size > total_size)
+		o->size = total_size;
 
 	/*
 	 * See if we need to extend some files
@@ -833,7 +834,7 @@ int setup_files(struct thread_data *td)
 		temp_stall_ts = 1;
 		if (output_format == FIO_OUTPUT_NORMAL)
 			log_info("%s: Laying out IO file(s) (%u file(s) /"
-				 " %lluMB)\n", td->o.name, need_extend,
+				 " %lluMB)\n", o->name, need_extend,
 					extend_size >> 20);
 
 		for_each_file(td, f, i) {
@@ -844,7 +845,7 @@ int setup_files(struct thread_data *td)
 
 			assert(f->filetype == FIO_TYPE_FILE);
 			fio_file_clear_extend(f);
-			if (!td->o.fill_device) {
+			if (!o->fill_device) {
 				old_len = f->real_file_size;
 				extend_len = f->io_size + f->file_offset -
 						old_len;
@@ -867,23 +868,23 @@ int setup_files(struct thread_data *td)
 	if (err)
 		return err;
 
-	if (!td->o.zone_size)
-		td->o.zone_size = td->o.size;
+	if (!o->zone_size)
+		o->zone_size = o->size;
 
 	/*
 	 * iolog already set the total io size, if we read back
 	 * stored entries.
 	 */
-	if (!td->o.read_iolog_file)
-		td->total_io_size = td->o.size * td->o.loops;
+	if (!o->read_iolog_file)
+		td->total_io_size = o->size * o->loops;
 
 done:
-	if (td->o.create_only)
+	if (o->create_only)
 		td->done = 1;
 
 	return 0;
 err_offset:
-	log_err("%s: you need to specify valid offset=\n", td->o.name);
+	log_err("%s: you need to specify valid offset=\n", o->name);
 	return 1;
 }
 
diff --git a/fio.h b/fio.h
index a1b2a93..16e05c4 100644
--- a/fio.h
+++ b/fio.h
@@ -102,6 +102,7 @@ struct thread_options {
 	char *name;
 	char *directory;
 	char *filename;
+	char *fileprefix;
 	char *opendir;
 	char *ioengine;
 	enum td_ddir td_ddir;
diff --git a/init.c b/init.c
index 9d15318..00701cf 100644
--- a/init.c
+++ b/init.c
@@ -812,6 +812,7 @@ static int add_job(struct thread_data *td, const char *jobname, int job_add_num)
 	unsigned int i;
 	char fname[PATH_MAX];
 	int numjobs, file_alloced;
+	struct thread_options *o = &td->o;
 
 	/*
 	 * the def_thread is just for options, it's not a real job
@@ -835,24 +836,32 @@ static int add_job(struct thread_data *td, const char *jobname, int job_add_num)
 	if (ioengine_load(td))
 		goto err;
 
-	if (td->o.use_thread)
+	if (o->use_thread)
 		nr_thread++;
 	else
 		nr_process++;
 
-	if (td->o.odirect)
+	if (o->odirect)
 		td->io_ops->flags |= FIO_RAWIO;
 
 	file_alloced = 0;
-	if (!td->o.filename && !td->files_index && !td->o.read_iolog_file) {
+	if (!o->filename && !td->files_index && !o->read_iolog_file) {
 		file_alloced = 1;
 
-		if (td->o.nr_files == 1 && exists_and_not_file(jobname))
-			add_file(td, jobname);
-		else {
-			for (i = 0; i < td->o.nr_files; i++) {
-				sprintf(fname, "%s.%d.%d", jobname,
+		if (o->nr_files == 1 && exists_and_not_file(jobname)) {
+			if (o->fileprefix)
+				add_file(td, o->fileprefix);
+			else
+				add_file(td, jobname);
+		} else {
+			for (i = 0; i < o->nr_files; i++) {
+				if (o->fileprefix) {
+					sprintf(fname, "%s.%d", o->fileprefix,
+							i);
+				} else {
+					sprintf(fname, "%s.%d.%d", jobname,
 							td->thread_number, i);
+				}
 				add_file(td, fname);
 			}
 		}
@@ -879,9 +888,9 @@ static int add_job(struct thread_data *td, const char *jobname, int job_add_num)
 
 	td->mutex = fio_mutex_init(FIO_MUTEX_LOCKED);
 
-	td->ts.clat_percentiles = td->o.clat_percentiles;
-	td->ts.percentile_precision = td->o.percentile_precision;
-	memcpy(td->ts.percentile_list, td->o.percentile_list, sizeof(td->o.percentile_list));
+	td->ts.clat_percentiles = o->clat_percentiles;
+	td->ts.percentile_precision = o->percentile_precision;
+	memcpy(td->ts.percentile_list, o->percentile_list, sizeof(o->percentile_list));
 
 	for (i = 0; i < DDIR_RWDIR_CNT; i++) {
 		td->ts.clat_stat[i].min_val = ULONG_MAX;
@@ -889,9 +898,9 @@ static int add_job(struct thread_data *td, const char *jobname, int job_add_num)
 		td->ts.lat_stat[i].min_val = ULONG_MAX;
 		td->ts.bw_stat[i].min_val = ULONG_MAX;
 	}
-	td->ddir_seq_nr = td->o.ddir_seq_nr;
+	td->ddir_seq_nr = o->ddir_seq_nr;
 
-	if ((td->o.stonewall || td->o.new_group) && prev_group_jobs) {
+	if ((o->stonewall || o->new_group) && prev_group_jobs) {
 		prev_group_jobs = 0;
 		groupid++;
 	}
@@ -907,43 +916,41 @@ static int add_job(struct thread_data *td, const char *jobname, int job_add_num)
 	if (setup_rate(td))
 		goto err;
 
-	if (td->o.write_lat_log) {
-		setup_log(&td->lat_log, td->o.log_avg_msec);
-		setup_log(&td->slat_log, td->o.log_avg_msec);
-		setup_log(&td->clat_log, td->o.log_avg_msec);
+	if (o->write_lat_log) {
+		setup_log(&td->lat_log, o->log_avg_msec);
+		setup_log(&td->slat_log, o->log_avg_msec);
+		setup_log(&td->clat_log, o->log_avg_msec);
 	}
-	if (td->o.write_bw_log)
-		setup_log(&td->bw_log, td->o.log_avg_msec);
-	if (td->o.write_iops_log)
-		setup_log(&td->iops_log, td->o.log_avg_msec);
+	if (o->write_bw_log)
+		setup_log(&td->bw_log, o->log_avg_msec);
+	if (o->write_iops_log)
+		setup_log(&td->iops_log, o->log_avg_msec);
 
-	if (!td->o.name)
-		td->o.name = strdup(jobname);
+	if (!o->name)
+		o->name = strdup(jobname);
 
 	if (output_format == FIO_OUTPUT_NORMAL) {
 		if (!job_add_num) {
 			if (!strcmp(td->io_ops->name, "cpuio")) {
 				log_info("%s: ioengine=cpu, cpuload=%u,"
-					 " cpucycle=%u\n", td->o.name,
-							td->o.cpuload,
-							td->o.cpucycle);
+					 " cpucycle=%u\n", o->name,
+						o->cpuload, o->cpucycle);
 			} else {
 				char *c1, *c2, *c3, *c4, *c5, *c6;
 
-				c1 = to_kmg(td->o.min_bs[DDIR_READ]);
-				c2 = to_kmg(td->o.max_bs[DDIR_READ]);
-				c3 = to_kmg(td->o.min_bs[DDIR_WRITE]);
-				c4 = to_kmg(td->o.max_bs[DDIR_WRITE]);
-				c5 = to_kmg(td->o.min_bs[DDIR_TRIM]);
-				c6 = to_kmg(td->o.max_bs[DDIR_TRIM]);
+				c1 = to_kmg(o->min_bs[DDIR_READ]);
+				c2 = to_kmg(o->max_bs[DDIR_READ]);
+				c3 = to_kmg(o->min_bs[DDIR_WRITE]);
+				c4 = to_kmg(o->max_bs[DDIR_WRITE]);
+				c5 = to_kmg(o->min_bs[DDIR_TRIM]);
+				c6 = to_kmg(o->max_bs[DDIR_TRIM]);
 
 				log_info("%s: (g=%d): rw=%s, bs=%s-%s/%s-%s/%s-%s,"
 					 " ioengine=%s, iodepth=%u\n",
-						td->o.name, td->groupid,
-						ddir_str[td->o.td_ddir],
+						o->name, td->groupid,
+						ddir_str[o->td_ddir],
 						c1, c2, c3, c4, c5, c6,
-						td->io_ops->name,
-						td->o.iodepth);
+						td->io_ops->name, o->iodepth);
 
 				free(c1);
 				free(c2);
@@ -960,7 +967,7 @@ static int add_job(struct thread_data *td, const char *jobname, int job_add_num)
 	 * recurse add identical jobs, clear numjobs and stonewall options
 	 * as they don't apply to sub-jobs
 	 */
-	numjobs = td->o.numjobs;
+	numjobs = o->numjobs;
 	while (--numjobs) {
 		struct thread_data *td_new = get_new_job(0, td, 1);
 
diff --git a/options.c b/options.c
index 3eb5fdc..e2a0a2e 100644
--- a/options.c
+++ b/options.c
@@ -1132,6 +1132,13 @@ static struct fio_option options[FIO_MAX_OPTS] = {
 		.help	= "File(s) to use for the workload",
 	},
 	{
+		.name	= "fileprefix",
+		.type	= FIO_OPT_STR_STORE,
+		.off1	= td_var_offset(fileprefix),
+		.prio	= -1, /* must come after "directory" */
+		.help	= "Override default <job.threadnum>.filenum naming",
+	},
+	{
 		.name	= "kb_base",
 		.type	= FIO_OPT_INT,
 		.off1	= td_var_offset(kb_base),

-- 
Jens Axboe