On 15 Jan 2001, Linus Torvalds wrote:
> int fd = open(..)
> fstat(fd..);
> sendfile(fd..);
> close(fd);
>
> is any slower than
>
> .. cache stat() in user space based on name ..
> sendpath(name, ..);
>
> on any real load.
just for kicks i've implemented sendpath() support. (patch against
2.4.0-test and sample code attached) It appears to work just fine here.
With a bit of reorganization in mm/filemap.c it was quite straightforward
to do.
Jonathan, is this what Zeus needs? If yes, it could be interesting to run
a simple benchmark to compare sendpath() to open()+sendfile()?
Ingo
--- linux/mm/filemap.c.orig Mon Jan 15 22:43:21 2001
+++ linux/mm/filemap.c Mon Jan 15 23:09:55 2001
@@ -39,6 +39,8 @@
* page-cache, 21.05.1999, Ingo Molnar <[EMAIL PROTECTED]>
*
* SMP-threaded pagemap-LRU 1999, Andrea Arcangeli <[EMAIL PROTECTED]>
+ *
+ * Started sendpath() support, (C) 2000 Ingo Molnar <[EMAIL PROTECTED]>
*/
atomic_t page_cache_size = ATOMIC_INIT(0);
@@ -1450,15 +1452,15 @@
return written;
}
-asmlinkage ssize_t sys_sendfile(int out_fd, int in_fd, off_t *offset, size_t count)
+/*
+ * Get input file, and verify that it is ok..
+ */
+static struct file * get_verify_in_file (int in_fd, size_t count)
{
- ssize_t retval;
- struct file * in_file, * out_file;
- struct inode * in_inode, * out_inode;
+ struct inode * in_inode;
+ struct file * in_file;
+ int retval;
- /*
- * Get input file, and verify that it is ok..
- */
retval = -EBADF;
in_file = fget(in_fd);
if (!in_file)
@@ -1474,10 +1476,21 @@
retval = locks_verify_area(FLOCK_VERIFY_READ, in_inode, in_file,
in_file->f_pos, count);
if (retval)
goto fput_in;
+ return in_file;
+fput_in:
+ fput(in_file);
+out:
+ return ERR_PTR(retval);
+}
+/*
+ * Get output file, and verify that it is ok..
+ */
+static struct file * get_verify_out_file (int out_fd, size_t count)
+{
+ struct file *out_file;
+ struct inode *out_inode;
+ int retval;
- /*
- * Get output file, and verify that it is ok..
- */
retval = -EBADF;
out_file = fget(out_fd);
if (!out_file)
@@ -1491,6 +1504,29 @@
retval = locks_verify_area(FLOCK_VERIFY_WRITE, out_inode, out_file,
out_file->f_pos, count);
if (retval)
goto fput_out;
+ return out_file;
+
+fput_out:
+ fput(out_file);
+fput_in:
+ return ERR_PTR(retval);
+}
+
+asmlinkage ssize_t sys_sendfile(int out_fd, int in_fd, off_t *offset, size_t count)
+{
+ ssize_t retval;
+ struct file * in_file, *out_file;
+
+ in_file = get_verify_in_file(in_fd, count);
+ if (IS_ERR(in_file)) {
+ retval = PTR_ERR(in_file);
+ goto out;
+ }
+ out_file = get_verify_out_file(out_fd, count);
+ if (IS_ERR(out_file)) {
+ retval = PTR_ERR(out_file);
+ goto fput_in;
+ }
retval = 0;
if (count) {
@@ -1524,6 +1560,56 @@
fput(in_file);
out:
return retval;
+}
+
+asmlinkage ssize_t sys_sendpath(int out_fd, char *path, off_t *offset, size_t count)
+{
+ struct file in_file, *out_file;
+ read_descriptor_t desc;
+ loff_t pos = 0, *ppos;
+ struct nameidata nd;
+ int ret;
+
+ out_file = get_verify_out_file(out_fd, count);
+ if (IS_ERR(out_file)) {
+ ret = PTR_ERR(out_file);
+ goto err;
+ }
+ ret = user_path_walk(path, &nd);
+ if (ret)
+ goto put_out;
+ ret = -EINVAL;
+ if (!nd.dentry || !nd.dentry->d_inode)
+ goto put_in_out;
+
+ memset(&in_file, 0, sizeof(in_file));
+ in_file.f_dentry = nd.dentry;
+ in_file.f_op = nd.dentry->d_inode->i_fop;
+
+ ppos = &in_file.f_pos;
+ if (offset) {
+ if (get_user(pos, offset))
+ goto put_in_out;
+ ppos = &pos;
+ }
+ desc.written = 0;
+ desc.count = count;
+ desc.buf = (char *) out_file;
+ desc.error = 0;
+ do_generic_file_read(&in_file, ppos, &desc, file_send_actor, 0);
+
+ ret = desc.written;
+ if (!ret)
+ ret = desc.error;
+ if (offset)
+ put_user(pos, offset);
+
+put_in_out:
+ fput(out_file);
+put_out:
+ path_release(&nd);
+err:
+ return ret;
}
/*
--- linux/arch/i386/kernel/entry.S.orig Mon Jan 15 22:42:47 2001
+++ linux/arch/i386/kernel/entry.S Mon Jan 15 22:43:12 2001
@@ -646,6 +646,7 @@
.long SYMBOL_NAME(sys_getdents64) /* 220 */
.long SYMBOL_NAME(sys_fcntl64)
.long SYMBOL_NAME(sys_ni_syscall) /* reserved for TUX */
+ .long SYMBOL_NAME(sys_sendpath)
/*
* NOTE!! This doesn't have to be exact - we just have
@@ -653,6 +654,6 @@
* entries. Don't panic if you notice that this hasn't
* been shrunk every time we add a new system call.
*/
- .rept NR_syscalls-221
+ .rept NR_syscalls-223
.long SYMBOL_NAME(sys_ni_syscall)
.endr
/*
* Sample sendpath() code. It should mainly be used for sockets.
*/
#include <linux/unistd.h>
#include <sys/sendfile.h>
#include <stdlib.h>
#include <unistd.h>
#include <stdio.h>
#include <fcntl.h>
#define __NR_sendpath 223
_syscall4 (int, sendpath, int, out_fd, char *, path, off_t *, off, size_t, size)
int main (int argc, char **argv)
{
int out_fd;
int ret;
out_fd = open("./tmpfile", O_RDWR|O_CREAT|O_TRUNC, 0700);
ret = sendpath(out_fd, "/usr/include/unistd.h", NULL, 300);
printf("sendpath wrote %d bytes into ./tmpfile.\n", ret);
return 0;
}
