LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
* Simple utility to measure disk random access time
@ 2007-01-16 14:49 Linux Portal
2007-01-16 19:01 ` Bill Davidsen
0 siblings, 1 reply; 2+ messages in thread
From: Linux Portal @ 2007-01-16 14:49 UTC (permalink / raw)
To: linux-kernel
And a few graphs here: http://linux.inet.hr/how_fast_is_your_disk.html
Comments welcome!
#define _LARGEFILE64_SOURCE
#include <stdio.h>
#include <stdlib.h>
#include <unistd.h>
#include <errno.h>
#include <time.h>
#include <signal.h>
#include <sys/fcntl.h>
#include <sys/ioctl.h>
#include <linux/fs.h>
#define BLOCKSIZE 512
#define TIMEOUT 30
int count;
time_t start;
void done()
{
time_t end;
time(&end);
if (end < start + TIMEOUT) {
printf(".");
alarm(1);
return;
}
if (count) {
printf(".\nResults: %d seeks/second, %.2f ms random access time\n",
count / TIMEOUT, 1000.0 * TIMEOUT / count);
}
exit(EXIT_SUCCESS);
}
void handle(const char *string, int error)
{
if (error) {
perror(string);
exit(EXIT_FAILURE);
}
}
int main(int argc, char **argv)
{
char buffer[BLOCKSIZE];
int fd, retval;
unsigned long numblocks;
off64_t offset;
setvbuf(stdout, NULL, _IONBF, 0);
printf("Seeker v2.0, 2007-01-15, "
"http://linux.inet.hr/how_fast_is_your_disk.html\n");
if (argc != 2) {
printf("Usage: seeker <raw disk device>\n");
exit(EXIT_SUCCESS);
}
fd = open(argv[1], O_RDONLY);
handle("open", fd < 0);
retval = ioctl(fd, BLKGETSIZE, &numblocks);
handle("ioctl", retval == -1);
printf("Benchmarking %s [%luMB], wait %d seconds",
argv[1], numblocks / 2048, TIMEOUT);
time(&start);
srand(start);
signal(SIGALRM, &done);
alarm(1);
for (;;) {
offset = (off64_t) numblocks * random() / RAND_MAX;
retval = lseek64(fd, BLOCKSIZE * offset, SEEK_SET);
handle("lseek64", retval == (off64_t) -1);
retval = read(fd, buffer, BLOCKSIZE);
handle("read", retval < 0);
count++;
}
/* notreached */
}
^ permalink raw reply [flat|nested] 2+ messages in thread
* Re: Simple utility to measure disk random access time
2007-01-16 14:49 Simple utility to measure disk random access time Linux Portal
@ 2007-01-16 19:01 ` Bill Davidsen
0 siblings, 0 replies; 2+ messages in thread
From: Bill Davidsen @ 2007-01-16 19:01 UTC (permalink / raw)
To: Linux Portal, Linux Kernel mailing List
Linux Portal wrote:
> And a few graphs here: http://linux.inet.hr/how_fast_is_your_disk.html
>
> Comments welcome!
These results:
gaimboi:davidsen> ./da /dev/hdb
Seeker v2.0, 2007-01-15, http://linux.inet.hr/how_fast_is_your_disk.html
Benchmarking /dev/hdb [0MB], wait 30 seconds..............................
Results: 565841 seeks/second, 0.00 ms random access time
gaimboi:davidsen> ./da /dev/hda
Seeker v2.0, 2007-01-15, http://linux.inet.hr/how_fast_is_your_disk.html
Benchmarking /dev/hda [19092MB], wait 30
seconds..............................
Results: 49 seeks/second, 20.20 ms random access time
gaimboi:davidsen> ./da /dev/hdc
Seeker v2.0, 2007-01-15, http://linux.inet.hr/how_fast_is_your_disk.html
Benchmarking /dev/hdc [57241MB], wait 30
seconds..............................
Results: 64 seeks/second, 15.56 ms random access time
led to this patch:
RCS file: RCS/disk_access.c,v
retrieving revision 1.1
diff -r1.1 disk_access.c
67a68,72
> if (numblocks <= 0) {
> /* pretty small disk found here */
> printf("Disk too small, size: %d blocks\n", numblocks);
> exit(EXIT_FAILURE);
> }
69a75
>
and this warning:
gaimboi:davidsen> ./da /dev/hdb
Seeker v2.0, 2007-01-15, http://linux.inet.hr/how_fast_is_your_disk.html
Disk too small, size: 0 blocks
--
bill davidsen <davidsen@tmr.com>
CTO TMR Associates, Inc
Doing interesting things with small computers since 1979
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2007-01-16 18:59 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2007-01-16 14:49 Simple utility to measure disk random access time Linux Portal
2007-01-16 19:01 ` Bill Davidsen
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).