2009-06-22 13:12:28 +04:00
|
|
|
/*
|
|
|
|
* Copyright (C) 2007-2009 NEC Corporation. All Rights Reserved.
|
|
|
|
*
|
|
|
|
* Module Author: Kiyoshi Ueda
|
|
|
|
*
|
|
|
|
* This file is released under the GPL.
|
|
|
|
*
|
|
|
|
* Throughput oriented path selector.
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include "dm.h"
|
|
|
|
#include "dm-path-selector.h"
|
|
|
|
|
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h
percpu.h is included by sched.h and module.h and thus ends up being
included when building most .c files. percpu.h includes slab.h which
in turn includes gfp.h making everything defined by the two files
universally available and complicating inclusion dependencies.
percpu.h -> slab.h dependency is about to be removed. Prepare for
this change by updating users of gfp and slab facilities include those
headers directly instead of assuming availability. As this conversion
needs to touch large number of source files, the following script is
used as the basis of conversion.
http://userweb.kernel.org/~tj/misc/slabh-sweep.py
The script does the followings.
* Scan files for gfp and slab usages and update includes such that
only the necessary includes are there. ie. if only gfp is used,
gfp.h, if slab is used, slab.h.
* When the script inserts a new include, it looks at the include
blocks and try to put the new include such that its order conforms
to its surrounding. It's put in the include block which contains
core kernel includes, in the same order that the rest are ordered -
alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
doesn't seem to be any matching order.
* If the script can't find a place to put a new include (mostly
because the file doesn't have fitting include block), it prints out
an error message indicating which .h file needs to be added to the
file.
The conversion was done in the following steps.
1. The initial automatic conversion of all .c files updated slightly
over 4000 files, deleting around 700 includes and adding ~480 gfp.h
and ~3000 slab.h inclusions. The script emitted errors for ~400
files.
2. Each error was manually checked. Some didn't need the inclusion,
some needed manual addition while adding it to implementation .h or
embedding .c file was more appropriate for others. This step added
inclusions to around 150 files.
3. The script was run again and the output was compared to the edits
from #2 to make sure no file was left behind.
4. Several build tests were done and a couple of problems were fixed.
e.g. lib/decompress_*.c used malloc/free() wrappers around slab
APIs requiring slab.h to be added manually.
5. The script was run on all .h files but without automatically
editing them as sprinkling gfp.h and slab.h inclusions around .h
files could easily lead to inclusion dependency hell. Most gfp.h
inclusion directives were ignored as stuff from gfp.h was usually
wildly available and often used in preprocessor macros. Each
slab.h inclusion directive was examined and added manually as
necessary.
6. percpu.h was updated not to include slab.h.
7. Build test were done on the following configurations and failures
were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my
distributed build env didn't work with gcov compiles) and a few
more options had to be turned off depending on archs to make things
build (like ipr on powerpc/64 which failed due to missing writeq).
* x86 and x86_64 UP and SMP allmodconfig and a custom test config.
* powerpc and powerpc64 SMP allmodconfig
* sparc and sparc64 SMP allmodconfig
* ia64 SMP allmodconfig
* s390 SMP allmodconfig
* alpha SMP allmodconfig
* um on x86_64 SMP allmodconfig
8. percpu.h modifications were reverted so that it could be applied as
a separate patch and serve as bisection point.
Given the fact that I had only a couple of failures from tests on step
6, I'm fairly confident about the coverage of this conversion patch.
If there is a breakage, it's likely to be something in one of the arch
headers which should be easily discoverable easily on most builds of
the specific arch.
Signed-off-by: Tejun Heo <tj@kernel.org>
Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 11:04:11 +03:00
|
|
|
#include <linux/slab.h>
|
2011-07-03 21:58:33 +04:00
|
|
|
#include <linux/module.h>
|
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h
percpu.h is included by sched.h and module.h and thus ends up being
included when building most .c files. percpu.h includes slab.h which
in turn includes gfp.h making everything defined by the two files
universally available and complicating inclusion dependencies.
percpu.h -> slab.h dependency is about to be removed. Prepare for
this change by updating users of gfp and slab facilities include those
headers directly instead of assuming availability. As this conversion
needs to touch large number of source files, the following script is
used as the basis of conversion.
http://userweb.kernel.org/~tj/misc/slabh-sweep.py
The script does the followings.
* Scan files for gfp and slab usages and update includes such that
only the necessary includes are there. ie. if only gfp is used,
gfp.h, if slab is used, slab.h.
* When the script inserts a new include, it looks at the include
blocks and try to put the new include such that its order conforms
to its surrounding. It's put in the include block which contains
core kernel includes, in the same order that the rest are ordered -
alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
doesn't seem to be any matching order.
* If the script can't find a place to put a new include (mostly
because the file doesn't have fitting include block), it prints out
an error message indicating which .h file needs to be added to the
file.
The conversion was done in the following steps.
1. The initial automatic conversion of all .c files updated slightly
over 4000 files, deleting around 700 includes and adding ~480 gfp.h
and ~3000 slab.h inclusions. The script emitted errors for ~400
files.
2. Each error was manually checked. Some didn't need the inclusion,
some needed manual addition while adding it to implementation .h or
embedding .c file was more appropriate for others. This step added
inclusions to around 150 files.
3. The script was run again and the output was compared to the edits
from #2 to make sure no file was left behind.
4. Several build tests were done and a couple of problems were fixed.
e.g. lib/decompress_*.c used malloc/free() wrappers around slab
APIs requiring slab.h to be added manually.
5. The script was run on all .h files but without automatically
editing them as sprinkling gfp.h and slab.h inclusions around .h
files could easily lead to inclusion dependency hell. Most gfp.h
inclusion directives were ignored as stuff from gfp.h was usually
wildly available and often used in preprocessor macros. Each
slab.h inclusion directive was examined and added manually as
necessary.
6. percpu.h was updated not to include slab.h.
7. Build test were done on the following configurations and failures
were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my
distributed build env didn't work with gcov compiles) and a few
more options had to be turned off depending on archs to make things
build (like ipr on powerpc/64 which failed due to missing writeq).
* x86 and x86_64 UP and SMP allmodconfig and a custom test config.
* powerpc and powerpc64 SMP allmodconfig
* sparc and sparc64 SMP allmodconfig
* ia64 SMP allmodconfig
* s390 SMP allmodconfig
* alpha SMP allmodconfig
* um on x86_64 SMP allmodconfig
8. percpu.h modifications were reverted so that it could be applied as
a separate patch and serve as bisection point.
Given the fact that I had only a couple of failures from tests on step
6, I'm fairly confident about the coverage of this conversion patch.
If there is a breakage, it's likely to be something in one of the arch
headers which should be easily discoverable easily on most builds of
the specific arch.
Signed-off-by: Tejun Heo <tj@kernel.org>
Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 11:04:11 +03:00
|
|
|
|
2009-06-22 13:12:28 +04:00
|
|
|
#define DM_MSG_PREFIX "multipath service-time"
|
|
|
|
#define ST_MIN_IO 1
|
|
|
|
#define ST_MAX_RELATIVE_THROUGHPUT 100
|
|
|
|
#define ST_MAX_RELATIVE_THROUGHPUT_SHIFT 7
|
|
|
|
#define ST_MAX_INFLIGHT_SIZE ((size_t)-1 >> ST_MAX_RELATIVE_THROUGHPUT_SHIFT)
|
2016-02-10 19:58:45 +03:00
|
|
|
#define ST_VERSION "0.3.0"
|
2009-06-22 13:12:28 +04:00
|
|
|
|
|
|
|
struct selector {
|
|
|
|
struct list_head valid_paths;
|
|
|
|
struct list_head failed_paths;
|
2016-02-15 22:25:00 +03:00
|
|
|
spinlock_t lock;
|
2009-06-22 13:12:28 +04:00
|
|
|
};
|
|
|
|
|
|
|
|
struct path_info {
|
|
|
|
struct list_head list;
|
|
|
|
struct dm_path *path;
|
|
|
|
unsigned repeat_count;
|
|
|
|
unsigned relative_throughput;
|
|
|
|
atomic_t in_flight_size; /* Total size of in-flight I/Os */
|
|
|
|
};
|
|
|
|
|
|
|
|
static struct selector *alloc_selector(void)
|
|
|
|
{
|
|
|
|
struct selector *s = kmalloc(sizeof(*s), GFP_KERNEL);
|
|
|
|
|
|
|
|
if (s) {
|
|
|
|
INIT_LIST_HEAD(&s->valid_paths);
|
|
|
|
INIT_LIST_HEAD(&s->failed_paths);
|
2016-02-15 22:25:00 +03:00
|
|
|
spin_lock_init(&s->lock);
|
2009-06-22 13:12:28 +04:00
|
|
|
}
|
|
|
|
|
|
|
|
return s;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int st_create(struct path_selector *ps, unsigned argc, char **argv)
|
|
|
|
{
|
|
|
|
struct selector *s = alloc_selector();
|
|
|
|
|
|
|
|
if (!s)
|
|
|
|
return -ENOMEM;
|
|
|
|
|
|
|
|
ps->context = s;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void free_paths(struct list_head *paths)
|
|
|
|
{
|
|
|
|
struct path_info *pi, *next;
|
|
|
|
|
|
|
|
list_for_each_entry_safe(pi, next, paths, list) {
|
|
|
|
list_del(&pi->list);
|
|
|
|
kfree(pi);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
static void st_destroy(struct path_selector *ps)
|
|
|
|
{
|
|
|
|
struct selector *s = ps->context;
|
|
|
|
|
|
|
|
free_paths(&s->valid_paths);
|
|
|
|
free_paths(&s->failed_paths);
|
|
|
|
kfree(s);
|
|
|
|
ps->context = NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int st_status(struct path_selector *ps, struct dm_path *path,
|
|
|
|
status_type_t type, char *result, unsigned maxlen)
|
|
|
|
{
|
|
|
|
unsigned sz = 0;
|
|
|
|
struct path_info *pi;
|
|
|
|
|
|
|
|
if (!path)
|
|
|
|
DMEMIT("0 ");
|
|
|
|
else {
|
|
|
|
pi = path->pscontext;
|
|
|
|
|
|
|
|
switch (type) {
|
|
|
|
case STATUSTYPE_INFO:
|
|
|
|
DMEMIT("%d %u ", atomic_read(&pi->in_flight_size),
|
|
|
|
pi->relative_throughput);
|
|
|
|
break;
|
|
|
|
case STATUSTYPE_TABLE:
|
|
|
|
DMEMIT("%u %u ", pi->repeat_count,
|
|
|
|
pi->relative_throughput);
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
return sz;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int st_add_path(struct path_selector *ps, struct dm_path *path,
|
|
|
|
int argc, char **argv, char **error)
|
|
|
|
{
|
|
|
|
struct selector *s = ps->context;
|
|
|
|
struct path_info *pi;
|
|
|
|
unsigned repeat_count = ST_MIN_IO;
|
|
|
|
unsigned relative_throughput = 1;
|
dm: reject trailing characters in sccanf input
Device mapper uses sscanf to convert arguments to numbers. The problem is that
the way we use it ignores additional unmatched characters in the scanned string.
For example, this `if (sscanf(string, "%d", &number) == 1)' will match a number,
but also it will match number with some garbage appended, like "123abc".
As a result, device mapper accepts garbage after some numbers. For example
the command `dmsetup create vg1-new --table "0 16384 linear 254:1bla 34816bla"'
will pass without an error.
This patch fixes all sscanf uses in device mapper. It appends "%c" with
a pointer to a dummy character variable to every sscanf statement.
The construct `if (sscanf(string, "%d%c", &number, &dummy) == 1)' succeeds
only if string is a null-terminated number (optionally preceded by some
whitespace characters). If there is some character appended after the number,
sscanf matches "%c", writes the character to the dummy variable and returns 2.
We check the return value for 1 and consequently reject numbers with some
garbage appended.
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Acked-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
2012-03-28 21:41:26 +04:00
|
|
|
char dummy;
|
2016-02-15 22:25:00 +03:00
|
|
|
unsigned long flags;
|
2009-06-22 13:12:28 +04:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Arguments: [<repeat_count> [<relative_throughput>]]
|
|
|
|
* <repeat_count>: The number of I/Os before switching path.
|
|
|
|
* If not given, default (ST_MIN_IO) is used.
|
|
|
|
* <relative_throughput>: The relative throughput value of
|
|
|
|
* the path among all paths in the path-group.
|
|
|
|
* The valid range: 0-<ST_MAX_RELATIVE_THROUGHPUT>
|
|
|
|
* If not given, minimum value '1' is used.
|
|
|
|
* If '0' is given, the path isn't selected while
|
|
|
|
* other paths having a positive value are
|
|
|
|
* available.
|
|
|
|
*/
|
|
|
|
if (argc > 2) {
|
|
|
|
*error = "service-time ps: incorrect number of arguments";
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
|
dm: reject trailing characters in sccanf input
Device mapper uses sscanf to convert arguments to numbers. The problem is that
the way we use it ignores additional unmatched characters in the scanned string.
For example, this `if (sscanf(string, "%d", &number) == 1)' will match a number,
but also it will match number with some garbage appended, like "123abc".
As a result, device mapper accepts garbage after some numbers. For example
the command `dmsetup create vg1-new --table "0 16384 linear 254:1bla 34816bla"'
will pass without an error.
This patch fixes all sscanf uses in device mapper. It appends "%c" with
a pointer to a dummy character variable to every sscanf statement.
The construct `if (sscanf(string, "%d%c", &number, &dummy) == 1)' succeeds
only if string is a null-terminated number (optionally preceded by some
whitespace characters). If there is some character appended after the number,
sscanf matches "%c", writes the character to the dummy variable and returns 2.
We check the return value for 1 and consequently reject numbers with some
garbage appended.
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Acked-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
2012-03-28 21:41:26 +04:00
|
|
|
if (argc && (sscanf(argv[0], "%u%c", &repeat_count, &dummy) != 1)) {
|
2009-06-22 13:12:28 +04:00
|
|
|
*error = "service-time ps: invalid repeat count";
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
|
2016-02-10 19:58:45 +03:00
|
|
|
if (repeat_count > 1) {
|
|
|
|
DMWARN_LIMIT("repeat_count > 1 is deprecated, using 1 instead");
|
|
|
|
repeat_count = 1;
|
|
|
|
}
|
|
|
|
|
2009-06-22 13:12:28 +04:00
|
|
|
if ((argc == 2) &&
|
dm: reject trailing characters in sccanf input
Device mapper uses sscanf to convert arguments to numbers. The problem is that
the way we use it ignores additional unmatched characters in the scanned string.
For example, this `if (sscanf(string, "%d", &number) == 1)' will match a number,
but also it will match number with some garbage appended, like "123abc".
As a result, device mapper accepts garbage after some numbers. For example
the command `dmsetup create vg1-new --table "0 16384 linear 254:1bla 34816bla"'
will pass without an error.
This patch fixes all sscanf uses in device mapper. It appends "%c" with
a pointer to a dummy character variable to every sscanf statement.
The construct `if (sscanf(string, "%d%c", &number, &dummy) == 1)' succeeds
only if string is a null-terminated number (optionally preceded by some
whitespace characters). If there is some character appended after the number,
sscanf matches "%c", writes the character to the dummy variable and returns 2.
We check the return value for 1 and consequently reject numbers with some
garbage appended.
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Acked-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
2012-03-28 21:41:26 +04:00
|
|
|
(sscanf(argv[1], "%u%c", &relative_throughput, &dummy) != 1 ||
|
2009-06-22 13:12:28 +04:00
|
|
|
relative_throughput > ST_MAX_RELATIVE_THROUGHPUT)) {
|
|
|
|
*error = "service-time ps: invalid relative_throughput value";
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* allocate the path */
|
|
|
|
pi = kmalloc(sizeof(*pi), GFP_KERNEL);
|
|
|
|
if (!pi) {
|
|
|
|
*error = "service-time ps: Error allocating path context";
|
|
|
|
return -ENOMEM;
|
|
|
|
}
|
|
|
|
|
|
|
|
pi->path = path;
|
|
|
|
pi->repeat_count = repeat_count;
|
|
|
|
pi->relative_throughput = relative_throughput;
|
|
|
|
atomic_set(&pi->in_flight_size, 0);
|
|
|
|
|
|
|
|
path->pscontext = pi;
|
|
|
|
|
2016-02-15 22:25:00 +03:00
|
|
|
spin_lock_irqsave(&s->lock, flags);
|
2009-06-22 13:12:28 +04:00
|
|
|
list_add_tail(&pi->list, &s->valid_paths);
|
2016-02-15 22:25:00 +03:00
|
|
|
spin_unlock_irqrestore(&s->lock, flags);
|
2009-06-22 13:12:28 +04:00
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void st_fail_path(struct path_selector *ps, struct dm_path *path)
|
|
|
|
{
|
|
|
|
struct selector *s = ps->context;
|
|
|
|
struct path_info *pi = path->pscontext;
|
2016-02-15 22:25:00 +03:00
|
|
|
unsigned long flags;
|
2009-06-22 13:12:28 +04:00
|
|
|
|
2016-02-15 22:25:00 +03:00
|
|
|
spin_lock_irqsave(&s->lock, flags);
|
2009-06-22 13:12:28 +04:00
|
|
|
list_move(&pi->list, &s->failed_paths);
|
2016-02-15 22:25:00 +03:00
|
|
|
spin_unlock_irqrestore(&s->lock, flags);
|
2009-06-22 13:12:28 +04:00
|
|
|
}
|
|
|
|
|
|
|
|
static int st_reinstate_path(struct path_selector *ps, struct dm_path *path)
|
|
|
|
{
|
|
|
|
struct selector *s = ps->context;
|
|
|
|
struct path_info *pi = path->pscontext;
|
2016-02-15 22:25:00 +03:00
|
|
|
unsigned long flags;
|
2009-06-22 13:12:28 +04:00
|
|
|
|
2016-02-15 22:25:00 +03:00
|
|
|
spin_lock_irqsave(&s->lock, flags);
|
2009-06-22 13:12:28 +04:00
|
|
|
list_move_tail(&pi->list, &s->valid_paths);
|
2016-02-15 22:25:00 +03:00
|
|
|
spin_unlock_irqrestore(&s->lock, flags);
|
2009-06-22 13:12:28 +04:00
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Compare the estimated service time of 2 paths, pi1 and pi2,
|
|
|
|
* for the incoming I/O.
|
|
|
|
*
|
|
|
|
* Returns:
|
|
|
|
* < 0 : pi1 is better
|
|
|
|
* 0 : no difference between pi1 and pi2
|
|
|
|
* > 0 : pi2 is better
|
|
|
|
*
|
|
|
|
* Description:
|
|
|
|
* Basically, the service time is estimated by:
|
|
|
|
* ('pi->in-flight-size' + 'incoming') / 'pi->relative_throughput'
|
|
|
|
* To reduce the calculation, some optimizations are made.
|
|
|
|
* (See comments inline)
|
|
|
|
*/
|
|
|
|
static int st_compare_load(struct path_info *pi1, struct path_info *pi2,
|
|
|
|
size_t incoming)
|
|
|
|
{
|
|
|
|
size_t sz1, sz2, st1, st2;
|
|
|
|
|
|
|
|
sz1 = atomic_read(&pi1->in_flight_size);
|
|
|
|
sz2 = atomic_read(&pi2->in_flight_size);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Case 1: Both have same throughput value. Choose less loaded path.
|
|
|
|
*/
|
|
|
|
if (pi1->relative_throughput == pi2->relative_throughput)
|
|
|
|
return sz1 - sz2;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Case 2a: Both have same load. Choose higher throughput path.
|
|
|
|
* Case 2b: One path has no throughput value. Choose the other one.
|
|
|
|
*/
|
|
|
|
if (sz1 == sz2 ||
|
|
|
|
!pi1->relative_throughput || !pi2->relative_throughput)
|
|
|
|
return pi2->relative_throughput - pi1->relative_throughput;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Case 3: Calculate service time. Choose faster path.
|
|
|
|
* Service time using pi1:
|
|
|
|
* st1 = (sz1 + incoming) / pi1->relative_throughput
|
|
|
|
* Service time using pi2:
|
|
|
|
* st2 = (sz2 + incoming) / pi2->relative_throughput
|
|
|
|
*
|
|
|
|
* To avoid the division, transform the expression to use
|
|
|
|
* multiplication.
|
|
|
|
* Because ->relative_throughput > 0 here, if st1 < st2,
|
|
|
|
* the expressions below are the same meaning:
|
|
|
|
* (sz1 + incoming) / pi1->relative_throughput <
|
|
|
|
* (sz2 + incoming) / pi2->relative_throughput
|
|
|
|
* (sz1 + incoming) * pi2->relative_throughput <
|
|
|
|
* (sz2 + incoming) * pi1->relative_throughput
|
|
|
|
* So use the later one.
|
|
|
|
*/
|
|
|
|
sz1 += incoming;
|
|
|
|
sz2 += incoming;
|
|
|
|
if (unlikely(sz1 >= ST_MAX_INFLIGHT_SIZE ||
|
|
|
|
sz2 >= ST_MAX_INFLIGHT_SIZE)) {
|
|
|
|
/*
|
|
|
|
* Size may be too big for multiplying pi->relative_throughput
|
|
|
|
* and overflow.
|
|
|
|
* To avoid the overflow and mis-selection, shift down both.
|
|
|
|
*/
|
|
|
|
sz1 >>= ST_MAX_RELATIVE_THROUGHPUT_SHIFT;
|
|
|
|
sz2 >>= ST_MAX_RELATIVE_THROUGHPUT_SHIFT;
|
|
|
|
}
|
|
|
|
st1 = sz1 * pi2->relative_throughput;
|
|
|
|
st2 = sz2 * pi1->relative_throughput;
|
|
|
|
if (st1 != st2)
|
|
|
|
return st1 - st2;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Case 4: Service time is equal. Choose higher throughput path.
|
|
|
|
*/
|
|
|
|
return pi2->relative_throughput - pi1->relative_throughput;
|
|
|
|
}
|
|
|
|
|
2016-02-18 05:29:17 +03:00
|
|
|
static struct dm_path *st_select_path(struct path_selector *ps, size_t nr_bytes)
|
2009-06-22 13:12:28 +04:00
|
|
|
{
|
|
|
|
struct selector *s = ps->context;
|
|
|
|
struct path_info *pi = NULL, *best = NULL;
|
2016-02-15 22:25:00 +03:00
|
|
|
struct dm_path *ret = NULL;
|
|
|
|
unsigned long flags;
|
2009-06-22 13:12:28 +04:00
|
|
|
|
2016-02-15 22:25:00 +03:00
|
|
|
spin_lock_irqsave(&s->lock, flags);
|
2009-06-22 13:12:28 +04:00
|
|
|
if (list_empty(&s->valid_paths))
|
2016-02-15 22:25:00 +03:00
|
|
|
goto out;
|
2009-06-22 13:12:28 +04:00
|
|
|
|
|
|
|
list_for_each_entry(pi, &s->valid_paths, list)
|
|
|
|
if (!best || (st_compare_load(pi, best, nr_bytes) < 0))
|
|
|
|
best = pi;
|
|
|
|
|
|
|
|
if (!best)
|
2016-02-15 22:25:00 +03:00
|
|
|
goto out;
|
2009-06-22 13:12:28 +04:00
|
|
|
|
dm mpath selector: more evenly distribute ties
Move the last used path to the end of the list (least preferred) so that
ties are more evenly distributed.
For example, in case with three paths with one that is slower than
others, the remaining two would be unevenly used if they tie. This is
due to the rotation not being a truely fair distribution.
Illustrated: paths a, b, c, 'c' has 1 outstanding IO, a and b are 'tied'
Three possible rotations:
(a, b, c) -> best path 'a'
(b, c, a) -> best path 'b'
(c, a, b) -> best path 'a'
(a, b, c) -> best path 'a'
(b, c, a) -> best path 'b'
(c, a, b) -> best path 'a'
...
So 'a' is used 2x more than 'b', although they should be used evenly.
With this change, the most recently used path is always the least
preferred, removing this bias resulting in even distribution.
(a, b, c) -> best path 'a'
(b, c, a) -> best path 'b'
(c, a, b) -> best path 'a'
(c, b, a) -> best path 'b'
...
Signed-off-by: Khazhismel Kumykov <khazhy@google.com>
Reviewed-by: Martin Wilck <mwilck@suse.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2018-01-20 02:07:37 +03:00
|
|
|
/* Move most recently used to least preferred to evenly balance. */
|
|
|
|
list_move_tail(&best->list, &s->valid_paths);
|
|
|
|
|
2016-02-15 22:25:00 +03:00
|
|
|
ret = best->path;
|
|
|
|
out:
|
|
|
|
spin_unlock_irqrestore(&s->lock, flags);
|
|
|
|
return ret;
|
2009-06-22 13:12:28 +04:00
|
|
|
}
|
|
|
|
|
|
|
|
static int st_start_io(struct path_selector *ps, struct dm_path *path,
|
|
|
|
size_t nr_bytes)
|
|
|
|
{
|
|
|
|
struct path_info *pi = path->pscontext;
|
|
|
|
|
|
|
|
atomic_add(nr_bytes, &pi->in_flight_size);
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int st_end_io(struct path_selector *ps, struct dm_path *path,
|
|
|
|
size_t nr_bytes)
|
|
|
|
{
|
|
|
|
struct path_info *pi = path->pscontext;
|
|
|
|
|
|
|
|
atomic_sub(nr_bytes, &pi->in_flight_size);
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static struct path_selector_type st_ps = {
|
|
|
|
.name = "service-time",
|
|
|
|
.module = THIS_MODULE,
|
|
|
|
.table_args = 2,
|
|
|
|
.info_args = 2,
|
|
|
|
.create = st_create,
|
|
|
|
.destroy = st_destroy,
|
|
|
|
.status = st_status,
|
|
|
|
.add_path = st_add_path,
|
|
|
|
.fail_path = st_fail_path,
|
|
|
|
.reinstate_path = st_reinstate_path,
|
|
|
|
.select_path = st_select_path,
|
|
|
|
.start_io = st_start_io,
|
|
|
|
.end_io = st_end_io,
|
|
|
|
};
|
|
|
|
|
|
|
|
static int __init dm_st_init(void)
|
|
|
|
{
|
|
|
|
int r = dm_register_path_selector(&st_ps);
|
|
|
|
|
|
|
|
if (r < 0)
|
|
|
|
DMERR("register failed %d", r);
|
|
|
|
|
|
|
|
DMINFO("version " ST_VERSION " loaded");
|
|
|
|
|
|
|
|
return r;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void __exit dm_st_exit(void)
|
|
|
|
{
|
|
|
|
int r = dm_unregister_path_selector(&st_ps);
|
|
|
|
|
|
|
|
if (r < 0)
|
|
|
|
DMERR("unregister failed %d", r);
|
|
|
|
}
|
|
|
|
|
|
|
|
module_init(dm_st_init);
|
|
|
|
module_exit(dm_st_exit);
|
|
|
|
|
|
|
|
MODULE_DESCRIPTION(DM_NAME " throughput oriented path selector");
|
|
|
|
MODULE_AUTHOR("Kiyoshi Ueda <k-ueda@ct.jp.nec.com>");
|
|
|
|
MODULE_LICENSE("GPL");
|