Signed-off-by: Kirill Smelkov <[email protected]>
---
man2/mmap.2 | 1 +
1 file changed, 1 insertion(+)
diff --git a/man2/mmap.2 b/man2/mmap.2
index 96875e486..f6fd56523 100644
--- a/man2/mmap.2
+++ b/man2/mmap.2
@@ -300,6 +300,7 @@ Don't perform read-ahead:
create page tables entries only for pages
that are already present in RAM.
Since Linux 2.6.23, this flag causes
+.\" commit 54cb8821de07f2ffcd28c380ce9b93d5784b40d7
.BR MAP_POPULATE
to do nothing.
One day, the combination of
--
2.11.0
On Sat, Mar 18, 2017 at 10:40:10PM +0300, Kirill Smelkov wrote:
> Signed-off-by: Kirill Smelkov <[email protected]>
> ---
> man2/mmap.2 | 1 +
> 1 file changed, 1 insertion(+)
>
> diff --git a/man2/mmap.2 b/man2/mmap.2
> index 96875e486..f6fd56523 100644
> --- a/man2/mmap.2
> +++ b/man2/mmap.2
> @@ -300,6 +300,7 @@ Don't perform read-ahead:
> create page tables entries only for pages
> that are already present in RAM.
> Since Linux 2.6.23, this flag causes
> +.\" commit 54cb8821de07f2ffcd28c380ce9b93d5784b40d7
> .BR MAP_POPULATE
> to do nothing.
> One day, the combination of
Please also find below benchmark which explains why
mmap(MAP_POPULATE | MAP_NONBLOCK)
is actually needed.
Thanks,
Kirill
---- 8< ---- (https://lab.nexedi.com/kirr/misc/blob/5a25f4ae/t_sysmmap_c.c)
/* This program benchmarks pagefault time.
*
* Unfortunately as of 2017-Mar-20 for data in pagecache the situation is as
* follows (i7-6600U, Linux 4.9.13):
*
* 1. minor pagefault: ~ 1200ns
* (this program)
*
* 2. read syscall + whole page copy: ~ 215ns
* (https://github.com/golang/go/issues/19563#issuecomment-287423654)
*
* 3. it is not possible to mmap(MAP_POPULATE | MAP_NONBLOCK) (i.e. prefault
* those PTE that are already in pagecache).
* ( http://www.spinics.net/lists/linux-man/msg11420.html,
* https://git.kernel.org/linus/54cb8821de07f2ffcd28c380ce9b93d5784b40d7 )
*
* 4. (Q) I'm not sure a mechanism exists in the kernel to automatically
* subscribe a VMA so that when a page becomes pagecached, associated PTE is
* adjusted so that programs won't need to pay minor pagefault time on
* access.
*
* unless 3 and 4 are solved mmap unfortunately seems to be slower choice
* compared to just pread.
*/
#define _GNU_SOURCE
#include <sys/types.h>
#include <sys/stat.h>
#include <fcntl.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <sys/time.h>
#include <sys/user.h>
#include <sys/mman.h>
// 12345678
#define NITER 500000
// microtime returns current time as double
double microtime() {
int err;
struct timeval tv;
err = gettimeofday(&tv, NULL);
if (err == -1) {
perror("gettimeofday");
abort();
}
return tv.tv_sec + 1E-6 * tv.tv_usec;
}
int main() {
unsigned char *addr, sum = 0;
int fd, err, i;
size_t size;
double Tstart, Tend;
fd = open("/dev/shm/y.dat", O_RDWR | O_CREAT | O_TRUNC, 0666);
if (fd == -1) {
perror("open");
abort();
}
size = NITER * PAGE_SIZE;
err = ftruncate(fd, size);
if (err == -1) {
perror("ftruncate");
abort();
}
#if 1
// make sure RAM is actually allocated
Tstart = microtime();
err = fallocate(fd, /*mode*/0, 0, size);
Tend = microtime();
if (err == -1) {
perror("fallocate");
abort();
}
printf("T(fallocate):\t%.1f\t%6.1f ns / page\n", Tend - Tstart, (Tend - Tstart) * 1E9 / NITER);
#endif
Tstart = microtime();
addr = mmap(NULL, size, PROT_READ, MAP_SHARED, fd, 0);
//addr = mmap(NULL, size, PROT_READ, MAP_SHARED | MAP_POPULATE, fd, 0);
//addr = mmap(NULL, size, PROT_READ, MAP_SHARED | MAP_POPULATE | MAP_NONBLOCK, fd, 0);
if (addr == MAP_FAILED) {
perror("mmap");
abort();
}
Tend = microtime();
printf("T(mmap):\t%.1f\t%6.1f ns / page\n", Tend - Tstart, (Tend - Tstart) * 1E9 / NITER);
Tstart = microtime();
//for (int j=0; j < 100; j++)
for (i=0; i<NITER; i++) {
sum += addr[i*PAGE_SIZE];
}
Tend = microtime();
printf("T(pagefault):\t%.1f\t%6.1f ns / page\t(%i)\n", Tend - Tstart, (Tend - Tstart) * 1E9 / NITER, sum);
return 0;
}
---- 8< ----
[CC += Michel Lespinasse <[email protected]>]
Kirill,
I need some help here.
On 20 March 2017 at 16:59, Kirill Smelkov <[email protected]> wrote:
> On Sat, Mar 18, 2017 at 10:40:10PM +0300, Kirill Smelkov wrote:
>> Signed-off-by: Kirill Smelkov <[email protected]>
>> ---
>> man2/mmap.2 | 1 +
>> 1 file changed, 1 insertion(+)
>>
>> diff --git a/man2/mmap.2 b/man2/mmap.2
>> index 96875e486..f6fd56523 100644
>> --- a/man2/mmap.2
>> +++ b/man2/mmap.2
>> @@ -300,6 +300,7 @@ Don't perform read-ahead:
>> create page tables entries only for pages
>> that are already present in RAM.
>> Since Linux 2.6.23, this flag causes
>> +.\" commit 54cb8821de07f2ffcd28c380ce9b93d5784b40d7
>> .BR MAP_POPULATE
>> to do nothing.
>> One day, the combination of
>
> Please also find below benchmark which explains why
>
> mmap(MAP_POPULATE | MAP_NONBLOCK)
>
> is actually needed.
Okay -- clearly things have changed (but I received no man-pages
patch). What do you believe the man page should now say.
Or, perhaps we can ask Michel:
commit bebeb3d68b24bb4132d452c5707fe321208bcbcd
Author: Michel Lespinasse <[email protected]>
Date: Fri Feb 22 16:32:37 2013 -0800
The above commit (which went into Linux 3.9) seems to be the source of
the change.
Michael, can you suggest to us what the mmap() man page should now say
about MAP_POPULATE?
Thanks,
Michael
>
> Thanks,
> Kirill
>
> ---- 8< ---- (https://lab.nexedi.com/kirr/misc/blob/5a25f4ae/t_sysmmap_c.c)
> /* This program benchmarks pagefault time.
> *
> * Unfortunately as of 2017-Mar-20 for data in pagecache the situation is as
> * follows (i7-6600U, Linux 4.9.13):
> *
> * 1. minor pagefault: ~ 1200ns
> * (this program)
> *
> * 2. read syscall + whole page copy: ~ 215ns
> * (https://github.com/golang/go/issues/19563#issuecomment-287423654)
> *
> * 3. it is not possible to mmap(MAP_POPULATE | MAP_NONBLOCK) (i.e. prefault
> * those PTE that are already in pagecache).
> * ( http://www.spinics.net/lists/linux-man/msg11420.html,
> * https://git.kernel.org/linus/54cb8821de07f2ffcd28c380ce9b93d5784b40d7 )
> *
> * 4. (Q) I'm not sure a mechanism exists in the kernel to automatically
> * subscribe a VMA so that when a page becomes pagecached, associated PTE is
> * adjusted so that programs won't need to pay minor pagefault time on
> * access.
> *
> * unless 3 and 4 are solved mmap unfortunately seems to be slower choice
> * compared to just pread.
> */
> #define _GNU_SOURCE
> #include <sys/types.h>
> #include <sys/stat.h>
> #include <fcntl.h>
> #include <unistd.h>
> #include <stdio.h>
> #include <stdlib.h>
> #include <sys/time.h>
> #include <sys/user.h>
> #include <sys/mman.h>
>
> // 12345678
> #define NITER 500000
>
> // microtime returns current time as double
> double microtime() {
> int err;
> struct timeval tv;
>
> err = gettimeofday(&tv, NULL);
> if (err == -1) {
> perror("gettimeofday");
> abort();
> }
>
> return tv.tv_sec + 1E-6 * tv.tv_usec;
> }
>
>
> int main() {
> unsigned char *addr, sum = 0;
> int fd, err, i;
> size_t size;
> double Tstart, Tend;
>
> fd = open("/dev/shm/y.dat", O_RDWR | O_CREAT | O_TRUNC, 0666);
> if (fd == -1) {
> perror("open");
> abort();
> }
>
> size = NITER * PAGE_SIZE;
>
> err = ftruncate(fd, size);
> if (err == -1) {
> perror("ftruncate");
> abort();
> }
>
> #if 1
> // make sure RAM is actually allocated
> Tstart = microtime();
> err = fallocate(fd, /*mode*/0, 0, size);
> Tend = microtime();
> if (err == -1) {
> perror("fallocate");
> abort();
> }
> printf("T(fallocate):\t%.1f\t%6.1f ns / page\n", Tend - Tstart, (Tend - Tstart) * 1E9 / NITER);
> #endif
>
> Tstart = microtime();
> addr = mmap(NULL, size, PROT_READ, MAP_SHARED, fd, 0);
> //addr = mmap(NULL, size, PROT_READ, MAP_SHARED | MAP_POPULATE, fd, 0);
> //addr = mmap(NULL, size, PROT_READ, MAP_SHARED | MAP_POPULATE | MAP_NONBLOCK, fd, 0);
> if (addr == MAP_FAILED) {
> perror("mmap");
> abort();
> }
> Tend = microtime();
> printf("T(mmap):\t%.1f\t%6.1f ns / page\n", Tend - Tstart, (Tend - Tstart) * 1E9 / NITER);
>
> Tstart = microtime();
> //for (int j=0; j < 100; j++)
> for (i=0; i<NITER; i++) {
> sum += addr[i*PAGE_SIZE];
> }
> Tend = microtime();
>
> printf("T(pagefault):\t%.1f\t%6.1f ns / page\t(%i)\n", Tend - Tstart, (Tend - Tstart) * 1E9 / NITER, sum);
>
> return 0;
> }
> ---- 8< ----
--
Michael Kerrisk
Linux man-pages maintainer; http://www.kernel.org/doc/man-pages/
Linux/UNIX System Programming Training: http://man7.org/training/
Michael, first of all thanks for feedback.
On Mon, Mar 20, 2017 at 08:38:50PM +0100, Michael Kerrisk (man-pages) wrote:
> [CC += Michel Lespinasse <[email protected]>]
>
> Kirill,
>
> I need some help here.
>
> On 20 March 2017 at 16:59, Kirill Smelkov <[email protected]> wrote:
> > On Sat, Mar 18, 2017 at 10:40:10PM +0300, Kirill Smelkov wrote:
> >> Signed-off-by: Kirill Smelkov <[email protected]>
> >> ---
> >> man2/mmap.2 | 1 +
> >> 1 file changed, 1 insertion(+)
> >>
> >> diff --git a/man2/mmap.2 b/man2/mmap.2
> >> index 96875e486..f6fd56523 100644
> >> --- a/man2/mmap.2
> >> +++ b/man2/mmap.2
> >> @@ -300,6 +300,7 @@ Don't perform read-ahead:
> >> create page tables entries only for pages
> >> that are already present in RAM.
> >> Since Linux 2.6.23, this flag causes
> >> +.\" commit 54cb8821de07f2ffcd28c380ce9b93d5784b40d7
> >> .BR MAP_POPULATE
> >> to do nothing.
> >> One day, the combination of
> >
> > Please also find below benchmark which explains why
> >
> > mmap(MAP_POPULATE | MAP_NONBLOCK)
> >
> > is actually needed.
>
> Okay -- clearly things have changed (but I received no man-pages
> patch).
Strange it was sent. Let me show it once again here (git am -s):
---- 8< ----
From: Kirill Smelkov <[email protected]>
Subject: [patch] mmap.2: Add link to commit which broke MAP_POPULATE | MAP_NONBLOCK to be noop
Signed-off-by: Kirill Smelkov <[email protected]>
---
man2/mmap.2 | 1 +
1 file changed, 1 insertion(+)
diff --git a/man2/mmap.2 b/man2/mmap.2
index 96875e486..f6fd56523 100644
--- a/man2/mmap.2
+++ b/man2/mmap.2
@@ -300,6 +300,7 @@ Don't perform read-ahead:
create page tables entries only for pages
that are already present in RAM.
Since Linux 2.6.23, this flag causes
+.\" commit 54cb8821de07f2ffcd28c380ce9b93d5784b40d7
.BR MAP_POPULATE
to do nothing.
One day, the combination of
--
2.11.0
---- 8< ----
> What do you believe the man page should now say.
What man page says today correctly describes current behaviour:
---- 8< ----
MAP_NONBLOCK (since Linux 2.5.46)
This flag is meaningful only in conjunction with MAP_POPULATE. Don't perform read-
ahead: create page tables entries only for pages that are already present in RAM. Since
Linux 2.6.23, this flag causes MAP_POPULATE to do nothing. One day, the combination of
MAP_POPULATE and MAP_NONBLOCK may be reimplemented.
---- 8< ----
For now I've just added reference to commit corresponding to "Since Linux
2.6.23, this flag causes MAP_POPULATE to do nothing."
> Or, perhaps we can ask Michel:
>
> commit bebeb3d68b24bb4132d452c5707fe321208bcbcd
> Author: Michel Lespinasse <[email protected]>
> Date: Fri Feb 22 16:32:37 2013 -0800
>
> The above commit (which went into Linux 3.9) seems to be the source of
> the change.
>
> Michael, can you suggest to us what the mmap() man page should now say
> about MAP_POPULATE?
It is good to have feedback from relevant people, but as my patch to
man-pages says, if I understand it correctly, the original patch which
changed behaviour is this:
---- 8< ----
commit 54cb8821de07f2ffcd28c380ce9b93d5784b40d7
Author: Nick Piggin <[email protected]>
Date: Thu Jul 19 01:46:59 2007 -0700
mm: merge populate and nopage into fault (fixes nonlinear)
...
After this patch, MAP_NONBLOCK no longer sets up ptes for pages present in <-- NOTE here
pagecache. Seems like a fringe functionality anyway.
...
[[email protected]: cleanup]
[[email protected]: doc. fixes for readahead]
[[email protected]: build fix]
Signed-off-by: Nick Piggin <[email protected]>
Signed-off-by: Randy Dunlap <[email protected]>
Cc: Mark Fasheh <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
---- 8< ----
Adding all people involved to Cc - please have a look at quoted benchmark below
which justifies usage of mmap(MAP_POPULATE | MAP_NONBLOCK).
Thanks,
Kirill
> > ---- 8< ---- (https://lab.nexedi.com/kirr/misc/blob/5a25f4ae/t_sysmmap_c.c)
> > /* This program benchmarks pagefault time.
> > *
> > * Unfortunately as of 2017-Mar-20 for data in pagecache the situation is as
> > * follows (i7-6600U, Linux 4.9.13):
> > *
> > * 1. minor pagefault: ~ 1200ns
> > * (this program)
> > *
> > * 2. read syscall + whole page copy: ~ 215ns
> > * (https://github.com/golang/go/issues/19563#issuecomment-287423654)
> > *
> > * 3. it is not possible to mmap(MAP_POPULATE | MAP_NONBLOCK) (i.e. prefault
> > * those PTE that are already in pagecache).
> > * ( http://www.spinics.net/lists/linux-man/msg11420.html,
> > * https://git.kernel.org/linus/54cb8821de07f2ffcd28c380ce9b93d5784b40d7 )
> > *
> > * 4. (Q) I'm not sure a mechanism exists in the kernel to automatically
> > * subscribe a VMA so that when a page becomes pagecached, associated PTE is
> > * adjusted so that programs won't need to pay minor pagefault time on
> > * access.
> > *
> > * unless 3 and 4 are solved mmap unfortunately seems to be slower choice
> > * compared to just pread.
> > */
> > #define _GNU_SOURCE
> > #include <sys/types.h>
> > #include <sys/stat.h>
> > #include <fcntl.h>
> > #include <unistd.h>
> > #include <stdio.h>
> > #include <stdlib.h>
> > #include <sys/time.h>
> > #include <sys/user.h>
> > #include <sys/mman.h>
> >
> > // 12345678
> > #define NITER 500000
> >
> > // microtime returns current time as double
> > double microtime() {
> > int err;
> > struct timeval tv;
> >
> > err = gettimeofday(&tv, NULL);
> > if (err == -1) {
> > perror("gettimeofday");
> > abort();
> > }
> >
> > return tv.tv_sec + 1E-6 * tv.tv_usec;
> > }
> >
> >
> > int main() {
> > unsigned char *addr, sum = 0;
> > int fd, err, i;
> > size_t size;
> > double Tstart, Tend;
> >
> > fd = open("/dev/shm/y.dat", O_RDWR | O_CREAT | O_TRUNC, 0666);
> > if (fd == -1) {
> > perror("open");
> > abort();
> > }
> >
> > size = NITER * PAGE_SIZE;
> >
> > err = ftruncate(fd, size);
> > if (err == -1) {
> > perror("ftruncate");
> > abort();
> > }
> >
> > #if 1
> > // make sure RAM is actually allocated
> > Tstart = microtime();
> > err = fallocate(fd, /*mode*/0, 0, size);
> > Tend = microtime();
> > if (err == -1) {
> > perror("fallocate");
> > abort();
> > }
> > printf("T(fallocate):\t%.1f\t%6.1f ns / page\n", Tend - Tstart, (Tend - Tstart) * 1E9 / NITER);
> > #endif
> >
> > Tstart = microtime();
> > addr = mmap(NULL, size, PROT_READ, MAP_SHARED, fd, 0);
> > //addr = mmap(NULL, size, PROT_READ, MAP_SHARED | MAP_POPULATE, fd, 0);
> > //addr = mmap(NULL, size, PROT_READ, MAP_SHARED | MAP_POPULATE | MAP_NONBLOCK, fd, 0);
> > if (addr == MAP_FAILED) {
> > perror("mmap");
> > abort();
> > }
> > Tend = microtime();
> > printf("T(mmap):\t%.1f\t%6.1f ns / page\n", Tend - Tstart, (Tend - Tstart) * 1E9 / NITER);
> >
> > Tstart = microtime();
> > //for (int j=0; j < 100; j++)
> > for (i=0; i<NITER; i++) {
> > sum += addr[i*PAGE_SIZE];
> > }
> > Tend = microtime();
> >
> > printf("T(pagefault):\t%.1f\t%6.1f ns / page\t(%i)\n", Tend - Tstart, (Tend - Tstart) * 1E9 / NITER, sum);
> >
> > return 0;
> > }
> > ---- 8< ----
Michael, there are no replies, but I still think it is better we apply
the following patch to man-pages. Thanks.
---- 8< ----
From: Kirill Smelkov <[email protected]>
Subject: [patch] mmap.2: Add link to commit which broke MAP_POPULATE | MAP_NONBLOCK to be noop
Signed-off-by: Kirill Smelkov <[email protected]>
---
man2/mmap.2 | 1 +
1 file changed, 1 insertion(+)
diff --git a/man2/mmap.2 b/man2/mmap.2
index 96875e486..f6fd56523 100644
--- a/man2/mmap.2
+++ b/man2/mmap.2
@@ -300,6 +300,7 @@ Don't perform read-ahead:
create page tables entries only for pages
that are already present in RAM.
Since Linux 2.6.23, this flag causes
+.\" commit 54cb8821de07f2ffcd28c380ce9b93d5784b40d7
.BR MAP_POPULATE
to do nothing.
One day, the combination of
--
2.11.0
---- 8< ----
On Mon, Mar 20, 2017 at 11:06:44PM +0300, Kirill Smelkov wrote:
> Michael, first of all thanks for feedback.
>
> On Mon, Mar 20, 2017 at 08:38:50PM +0100, Michael Kerrisk (man-pages) wrote:
> > [CC += Michel Lespinasse <[email protected]>]
> >
> > Kirill,
> >
> > I need some help here.
> >
> > On 20 March 2017 at 16:59, Kirill Smelkov <[email protected]> wrote:
> > > On Sat, Mar 18, 2017 at 10:40:10PM +0300, Kirill Smelkov wrote:
> > >> Signed-off-by: Kirill Smelkov <[email protected]>
> > >> ---
> > >> man2/mmap.2 | 1 +
> > >> 1 file changed, 1 insertion(+)
> > >>
> > >> diff --git a/man2/mmap.2 b/man2/mmap.2
> > >> index 96875e486..f6fd56523 100644
> > >> --- a/man2/mmap.2
> > >> +++ b/man2/mmap.2
> > >> @@ -300,6 +300,7 @@ Don't perform read-ahead:
> > >> create page tables entries only for pages
> > >> that are already present in RAM.
> > >> Since Linux 2.6.23, this flag causes
> > >> +.\" commit 54cb8821de07f2ffcd28c380ce9b93d5784b40d7
> > >> .BR MAP_POPULATE
> > >> to do nothing.
> > >> One day, the combination of
> > >
> > > Please also find below benchmark which explains why
> > >
> > > mmap(MAP_POPULATE | MAP_NONBLOCK)
> > >
> > > is actually needed.
> >
> > Okay -- clearly things have changed (but I received no man-pages
> > patch).
>
> Strange it was sent. Let me show it once again here (git am -s):
>
> ---- 8< ----
> From: Kirill Smelkov <[email protected]>
> Subject: [patch] mmap.2: Add link to commit which broke MAP_POPULATE | MAP_NONBLOCK to be noop
>
> Signed-off-by: Kirill Smelkov <[email protected]>
> ---
> man2/mmap.2 | 1 +
> 1 file changed, 1 insertion(+)
>
> diff --git a/man2/mmap.2 b/man2/mmap.2
> index 96875e486..f6fd56523 100644
> --- a/man2/mmap.2
> +++ b/man2/mmap.2
> @@ -300,6 +300,7 @@ Don't perform read-ahead:
> create page tables entries only for pages
> that are already present in RAM.
> Since Linux 2.6.23, this flag causes
> +.\" commit 54cb8821de07f2ffcd28c380ce9b93d5784b40d7
> .BR MAP_POPULATE
> to do nothing.
> One day, the combination of
> --
> 2.11.0
> ---- 8< ----
>
>
> > What do you believe the man page should now say.
>
> What man page says today correctly describes current behaviour:
>
> ---- 8< ----
> MAP_NONBLOCK (since Linux 2.5.46)
> This flag is meaningful only in conjunction with MAP_POPULATE. Don't perform read-
> ahead: create page tables entries only for pages that are already present in RAM. Since
> Linux 2.6.23, this flag causes MAP_POPULATE to do nothing. One day, the combination of
> MAP_POPULATE and MAP_NONBLOCK may be reimplemented.
> ---- 8< ----
>
> For now I've just added reference to commit corresponding to "Since Linux
> 2.6.23, this flag causes MAP_POPULATE to do nothing."
>
>
> > Or, perhaps we can ask Michel:
> >
> > commit bebeb3d68b24bb4132d452c5707fe321208bcbcd
> > Author: Michel Lespinasse <[email protected]>
> > Date: Fri Feb 22 16:32:37 2013 -0800
> >
> > The above commit (which went into Linux 3.9) seems to be the source of
> > the change.
> >
> > Michael, can you suggest to us what the mmap() man page should now say
> > about MAP_POPULATE?
>
> It is good to have feedback from relevant people, but as my patch to
> man-pages says, if I understand it correctly, the original patch which
> changed behaviour is this:
>
> ---- 8< ----
> commit 54cb8821de07f2ffcd28c380ce9b93d5784b40d7
> Author: Nick Piggin <[email protected]>
> Date: Thu Jul 19 01:46:59 2007 -0700
>
> mm: merge populate and nopage into fault (fixes nonlinear)
>
> ...
>
> After this patch, MAP_NONBLOCK no longer sets up ptes for pages present in <-- NOTE here
> pagecache. Seems like a fringe functionality anyway.
>
> ...
>
> [[email protected]: cleanup]
> [[email protected]: doc. fixes for readahead]
> [[email protected]: build fix]
> Signed-off-by: Nick Piggin <[email protected]>
> Signed-off-by: Randy Dunlap <[email protected]>
> Cc: Mark Fasheh <[email protected]>
> Signed-off-by: Andrew Morton <[email protected]>
> Signed-off-by: Linus Torvalds <[email protected]>
> ---- 8< ----
>
> Adding all people involved to Cc - please have a look at quoted benchmark below
> which justifies usage of mmap(MAP_POPULATE | MAP_NONBLOCK).
>
> Thanks,
> Kirill
>
>
> > > ---- 8< ---- (https://lab.nexedi.com/kirr/misc/blob/5a25f4ae/t_sysmmap_c.c)
> > > /* This program benchmarks pagefault time.
> > > *
> > > * Unfortunately as of 2017-Mar-20 for data in pagecache the situation is as
> > > * follows (i7-6600U, Linux 4.9.13):
> > > *
> > > * 1. minor pagefault: ~ 1200ns
> > > * (this program)
> > > *
> > > * 2. read syscall + whole page copy: ~ 215ns
> > > * (https://github.com/golang/go/issues/19563#issuecomment-287423654)
> > > *
> > > * 3. it is not possible to mmap(MAP_POPULATE | MAP_NONBLOCK) (i.e. prefault
> > > * those PTE that are already in pagecache).
> > > * ( http://www.spinics.net/lists/linux-man/msg11420.html,
> > > * https://git.kernel.org/linus/54cb8821de07f2ffcd28c380ce9b93d5784b40d7 )
> > > *
> > > * 4. (Q) I'm not sure a mechanism exists in the kernel to automatically
> > > * subscribe a VMA so that when a page becomes pagecached, associated PTE is
> > > * adjusted so that programs won't need to pay minor pagefault time on
> > > * access.
> > > *
> > > * unless 3 and 4 are solved mmap unfortunately seems to be slower choice
> > > * compared to just pread.
> > > */
> > > #define _GNU_SOURCE
> > > #include <sys/types.h>
> > > #include <sys/stat.h>
> > > #include <fcntl.h>
> > > #include <unistd.h>
> > > #include <stdio.h>
> > > #include <stdlib.h>
> > > #include <sys/time.h>
> > > #include <sys/user.h>
> > > #include <sys/mman.h>
> > >
> > > // 12345678
> > > #define NITER 500000
> > >
> > > // microtime returns current time as double
> > > double microtime() {
> > > int err;
> > > struct timeval tv;
> > >
> > > err = gettimeofday(&tv, NULL);
> > > if (err == -1) {
> > > perror("gettimeofday");
> > > abort();
> > > }
> > >
> > > return tv.tv_sec + 1E-6 * tv.tv_usec;
> > > }
> > >
> > >
> > > int main() {
> > > unsigned char *addr, sum = 0;
> > > int fd, err, i;
> > > size_t size;
> > > double Tstart, Tend;
> > >
> > > fd = open("/dev/shm/y.dat", O_RDWR | O_CREAT | O_TRUNC, 0666);
> > > if (fd == -1) {
> > > perror("open");
> > > abort();
> > > }
> > >
> > > size = NITER * PAGE_SIZE;
> > >
> > > err = ftruncate(fd, size);
> > > if (err == -1) {
> > > perror("ftruncate");
> > > abort();
> > > }
> > >
> > > #if 1
> > > // make sure RAM is actually allocated
> > > Tstart = microtime();
> > > err = fallocate(fd, /*mode*/0, 0, size);
> > > Tend = microtime();
> > > if (err == -1) {
> > > perror("fallocate");
> > > abort();
> > > }
> > > printf("T(fallocate):\t%.1f\t%6.1f ns / page\n", Tend - Tstart, (Tend - Tstart) * 1E9 / NITER);
> > > #endif
> > >
> > > Tstart = microtime();
> > > addr = mmap(NULL, size, PROT_READ, MAP_SHARED, fd, 0);
> > > //addr = mmap(NULL, size, PROT_READ, MAP_SHARED | MAP_POPULATE, fd, 0);
> > > //addr = mmap(NULL, size, PROT_READ, MAP_SHARED | MAP_POPULATE | MAP_NONBLOCK, fd, 0);
> > > if (addr == MAP_FAILED) {
> > > perror("mmap");
> > > abort();
> > > }
> > > Tend = microtime();
> > > printf("T(mmap):\t%.1f\t%6.1f ns / page\n", Tend - Tstart, (Tend - Tstart) * 1E9 / NITER);
> > >
> > > Tstart = microtime();
> > > //for (int j=0; j < 100; j++)
> > > for (i=0; i<NITER; i++) {
> > > sum += addr[i*PAGE_SIZE];
> > > }
> > > Tend = microtime();
> > >
> > > printf("T(pagefault):\t%.1f\t%6.1f ns / page\t(%i)\n", Tend - Tstart, (Tend - Tstart) * 1E9 / NITER, sum);
> > >
> > > return 0;
> > > }
> > > ---- 8< ----