Currently, in kfree_rcu_shrink_scan(), the drain_page_cache() is
executed before kfree_rcu_monitor() to drain page cache, if the bnode
structure's->gp_snap has done, the kvfree_rcu_bulk() will fill the
page cache again in kfree_rcu_monitor(), this commit add a check
for krcp structure's->backoff_page_cache_fill in put_cached_bnode(),
if the krcp structure's->backoff_page_cache_fill is set, prevent page
cache growing and disable allocated page in fill_page_cache_func().
Signed-off-by: Zqiang <[email protected]>
---
kernel/rcu/tree.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index cc34d13be181..9d9d3772cc45 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -2908,6 +2908,8 @@ static inline bool
put_cached_bnode(struct kfree_rcu_cpu *krcp,
struct kvfree_rcu_bulk_data *bnode)
{
+ if (atomic_read(&krcp->backoff_page_cache_fill))
+ return false;
// Check the limit.
if (krcp->nr_bkv_objs >= rcu_min_cached_objs)
return false;
@@ -3221,7 +3223,7 @@ static void fill_page_cache_func(struct work_struct *work)
int i;
nr_pages = atomic_read(&krcp->backoff_page_cache_fill) ?
- 1 : rcu_min_cached_objs;
+ 0 : rcu_min_cached_objs;
for (i = 0; i < nr_pages; i++) {
bnode = (struct kvfree_rcu_bulk_data *)
--
2.32.0
On Sat, Apr 08, 2023 at 10:25:17PM +0800, Zqiang wrote:
> Currently, in kfree_rcu_shrink_scan(), the drain_page_cache() is
> executed before kfree_rcu_monitor() to drain page cache, if the bnode
> structure's->gp_snap has done, the kvfree_rcu_bulk() will fill the
> page cache again in kfree_rcu_monitor(), this commit add a check
> for krcp structure's->backoff_page_cache_fill in put_cached_bnode(),
> if the krcp structure's->backoff_page_cache_fill is set, prevent page
> cache growing and disable allocated page in fill_page_cache_func().
>
> Signed-off-by: Zqiang <[email protected]>
Much improved! But still some questions below...
Thanx, Paul
> ---
> kernel/rcu/tree.c | 4 +++-
> 1 file changed, 3 insertions(+), 1 deletion(-)
>
> diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
> index cc34d13be181..9d9d3772cc45 100644
> --- a/kernel/rcu/tree.c
> +++ b/kernel/rcu/tree.c
> @@ -2908,6 +2908,8 @@ static inline bool
> put_cached_bnode(struct kfree_rcu_cpu *krcp,
> struct kvfree_rcu_bulk_data *bnode)
> {
> + if (atomic_read(&krcp->backoff_page_cache_fill))
> + return false;
This will mean that under low-memory conditions, we will keep zero
pages in ->bkvcache. All attempts to put something there will fail.
This is probably not an issue for structures containing an rcu_head
that are passed to kfree_rcu(p, field), but doesn't this mean that
kfree_rcu_mightsleep() unconditionally invokes synchronize_rcu()?
This could seriously slow up freeing under low-memory conditions,
which might exacerbate the low-memory conditions.
Is this really what we want? Zero cached rather than just fewer cached?
> // Check the limit.
> if (krcp->nr_bkv_objs >= rcu_min_cached_objs)
> return false;
> @@ -3221,7 +3223,7 @@ static void fill_page_cache_func(struct work_struct *work)
> int i;
>
> nr_pages = atomic_read(&krcp->backoff_page_cache_fill) ?
> - 1 : rcu_min_cached_objs;
> + 0 : rcu_min_cached_objs;
>
> for (i = 0; i < nr_pages; i++) {
I am still confused as to why we start "i" at zero rather than at
->nr_bkv_objs. What am I missing here?
> bnode = (struct kvfree_rcu_bulk_data *)
> --
> 2.32.0
>
> Currently, in kfree_rcu_shrink_scan(), the drain_page_cache() is
> executed before kfree_rcu_monitor() to drain page cache, if the bnode
> structure's->gp_snap has done, the kvfree_rcu_bulk() will fill the
> page cache again in kfree_rcu_monitor(), this commit add a check
> for krcp structure's->backoff_page_cache_fill in put_cached_bnode(),
> if the krcp structure's->backoff_page_cache_fill is set, prevent page
> cache growing and disable allocated page in fill_page_cache_func().
>
> Signed-off-by: Zqiang <[email protected]>
>
>Much improved! But still some questions below...
>
> Thanx, Paul
>
> ---
> kernel/rcu/tree.c | 4 +++-
> 1 file changed, 3 insertions(+), 1 deletion(-)
>
> diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
> index cc34d13be181..9d9d3772cc45 100644
> --- a/kernel/rcu/tree.c
> +++ b/kernel/rcu/tree.c
> @@ -2908,6 +2908,8 @@ static inline bool
> put_cached_bnode(struct kfree_rcu_cpu *krcp,
> struct kvfree_rcu_bulk_data *bnode)
> {
> + if (atomic_read(&krcp->backoff_page_cache_fill))
> + return false;
>
>This will mean that under low-memory conditions, we will keep zero
>pages in ->bkvcache. All attempts to put something there will fail.
>
>This is probably not an issue for structures containing an rcu_head
>that are passed to kfree_rcu(p, field), but doesn't this mean that
>kfree_rcu_mightsleep() unconditionally invokes synchronize_rcu()?
>This could seriously slow up freeing under low-memory conditions,
>which might exacerbate the low-memory conditions.
Thanks for mentioning this, I didn't think of this before????.
>
>Is this really what we want? Zero cached rather than just fewer cached?
>
>
>
> // Check the limit.
> if (krcp->nr_bkv_objs >= rcu_min_cached_objs)
> return false;
> @@ -3221,7 +3223,7 @@ static void fill_page_cache_func(struct work_struct *work)
> int i;
>
> nr_pages = atomic_read(&krcp->backoff_page_cache_fill) ?
> - 1 : rcu_min_cached_objs;
> + 0 : rcu_min_cached_objs;
>
> for (i = 0; i < nr_pages; i++) {
>
>I am still confused as to why we start "i" at zero rather than at
>->nr_bkv_objs. What am I missing here?
No, you are right, I missed this place.
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -2908,6 +2908,8 @@ static inline bool
put_cached_bnode(struct kfree_rcu_cpu *krcp,
struct kvfree_rcu_bulk_data *bnode)
{
+ if (atomic_read(&krcp->backoff_page_cache_fill))
+ return false;
// Check the limit.
if (krcp->nr_bkv_objs >= rcu_min_cached_objs)
return false;
@@ -3223,7 +3225,7 @@ static void fill_page_cache_func(struct work_struct *work)
nr_pages = atomic_read(&krcp->backoff_page_cache_fill) ?
1 : rcu_min_cached_objs;
- for (i = 0; i < nr_pages; i++) {
+ for (i = krcp->nr_bkv_objs; i < nr_pages; i++) {
bnode = (struct kvfree_rcu_bulk_data *)
__get_free_page(GFP_KERNEL | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN);
thoughts?
Thanks
Zqiang
>
> bnode = (struct kvfree_rcu_bulk_data *)
> --
> 2.32.0
>
On Tue, Apr 11, 2023 at 04:04:45AM +0000, Zhang, Qiang1 wrote:
> > Currently, in kfree_rcu_shrink_scan(), the drain_page_cache() is
> > executed before kfree_rcu_monitor() to drain page cache, if the bnode
> > structure's->gp_snap has done, the kvfree_rcu_bulk() will fill the
> > page cache again in kfree_rcu_monitor(), this commit add a check
> > for krcp structure's->backoff_page_cache_fill in put_cached_bnode(),
> > if the krcp structure's->backoff_page_cache_fill is set, prevent page
> > cache growing and disable allocated page in fill_page_cache_func().
> >
> > Signed-off-by: Zqiang <[email protected]>
> >
> >Much improved! But still some questions below...
> >
> > Thanx, Paul
> >
> > ---
> > kernel/rcu/tree.c | 4 +++-
> > 1 file changed, 3 insertions(+), 1 deletion(-)
> >
> > diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
> > index cc34d13be181..9d9d3772cc45 100644
> > --- a/kernel/rcu/tree.c
> > +++ b/kernel/rcu/tree.c
> > @@ -2908,6 +2908,8 @@ static inline bool
> > put_cached_bnode(struct kfree_rcu_cpu *krcp,
> > struct kvfree_rcu_bulk_data *bnode)
> > {
> > + if (atomic_read(&krcp->backoff_page_cache_fill))
> > + return false;
> >
> >This will mean that under low-memory conditions, we will keep zero
> >pages in ->bkvcache. All attempts to put something there will fail.
> >
> >This is probably not an issue for structures containing an rcu_head
> >that are passed to kfree_rcu(p, field), but doesn't this mean that
> >kfree_rcu_mightsleep() unconditionally invokes synchronize_rcu()?
> >This could seriously slow up freeing under low-memory conditions,
> >which might exacerbate the low-memory conditions.
>
> Thanks for mentioning this, I didn't think of this before????.
>
> >
> >Is this really what we want? Zero cached rather than just fewer cached?
> >
> >
> >
> > // Check the limit.
> > if (krcp->nr_bkv_objs >= rcu_min_cached_objs)
> > return false;
> > @@ -3221,7 +3223,7 @@ static void fill_page_cache_func(struct work_struct *work)
> > int i;
> >
> > nr_pages = atomic_read(&krcp->backoff_page_cache_fill) ?
> > - 1 : rcu_min_cached_objs;
> > + 0 : rcu_min_cached_objs;
> >
> > for (i = 0; i < nr_pages; i++) {
> >
> >I am still confused as to why we start "i" at zero rather than at
> >->nr_bkv_objs. What am I missing here?
>
>
> No, you are right, I missed this place.
>
> --- a/kernel/rcu/tree.c
> +++ b/kernel/rcu/tree.c
> @@ -2908,6 +2908,8 @@ static inline bool
> put_cached_bnode(struct kfree_rcu_cpu *krcp,
> struct kvfree_rcu_bulk_data *bnode)
> {
> + if (atomic_read(&krcp->backoff_page_cache_fill))
> + return false;
>
This is broken, unfortunately. If a low memory condition we fill
fill a cache with at least one page anyway because of we do not want
to hit a slow path.
> // Check the limit.
> if (krcp->nr_bkv_objs >= rcu_min_cached_objs)
> return false;
> @@ -3223,7 +3225,7 @@ static void fill_page_cache_func(struct work_struct *work)
> nr_pages = atomic_read(&krcp->backoff_page_cache_fill) ?
> 1 : rcu_min_cached_objs;
>
> - for (i = 0; i < nr_pages; i++) {
> + for (i = krcp->nr_bkv_objs; i < nr_pages; i++) {
> bnode = (struct kvfree_rcu_bulk_data *)
> __get_free_page(GFP_KERNEL | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN);
>
>
IMHO, it should be send as a separate patch explaining why it
it is needed.
--
Uladzislau Rezki
> > Currently, in kfree_rcu_shrink_scan(), the drain_page_cache() is
> > executed before kfree_rcu_monitor() to drain page cache, if the bnode
> > structure's->gp_snap has done, the kvfree_rcu_bulk() will fill the
> > page cache again in kfree_rcu_monitor(), this commit add a check
> > for krcp structure's->backoff_page_cache_fill in put_cached_bnode(),
> > if the krcp structure's->backoff_page_cache_fill is set, prevent page
> > cache growing and disable allocated page in fill_page_cache_func().
> >
> > Signed-off-by: Zqiang <[email protected]>
> >
> >Much improved! But still some questions below...
> >
> > Thanx, Paul
> >
> > ---
> > kernel/rcu/tree.c | 4 +++-
> > 1 file changed, 3 insertions(+), 1 deletion(-)
> >
> > diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
> > index cc34d13be181..9d9d3772cc45 100644
> > --- a/kernel/rcu/tree.c
> > +++ b/kernel/rcu/tree.c
> > @@ -2908,6 +2908,8 @@ static inline bool
> > put_cached_bnode(struct kfree_rcu_cpu *krcp,
> > struct kvfree_rcu_bulk_data *bnode)
> > {
> > + if (atomic_read(&krcp->backoff_page_cache_fill))
> > + return false;
> >
> >This will mean that under low-memory conditions, we will keep zero
> >pages in ->bkvcache. All attempts to put something there will fail.
> >
> >This is probably not an issue for structures containing an rcu_head
> >that are passed to kfree_rcu(p, field), but doesn't this mean that
> >kfree_rcu_mightsleep() unconditionally invokes synchronize_rcu()?
> >This could seriously slow up freeing under low-memory conditions,
> >which might exacerbate the low-memory conditions.
>
> Thanks for mentioning this, I didn't think of this before????.
>
> >
> >Is this really what we want? Zero cached rather than just fewer cached?
> >
> >
> >
> > // Check the limit.
> > if (krcp->nr_bkv_objs >= rcu_min_cached_objs)
> > return false;
> > @@ -3221,7 +3223,7 @@ static void fill_page_cache_func(struct work_struct *work)
> > int i;
> >
> > nr_pages = atomic_read(&krcp->backoff_page_cache_fill) ?
> > - 1 : rcu_min_cached_objs;
> > + 0 : rcu_min_cached_objs;
> >
> > for (i = 0; i < nr_pages; i++) {
> >
> >I am still confused as to why we start "i" at zero rather than at
> >->nr_bkv_objs. What am I missing here?
>
>
> No, you are right, I missed this place.
>
> --- a/kernel/rcu/tree.c
> +++ b/kernel/rcu/tree.c
> @@ -2908,6 +2908,8 @@ static inline bool
> put_cached_bnode(struct kfree_rcu_cpu *krcp,
> struct kvfree_rcu_bulk_data *bnode)
> {
> + if (atomic_read(&krcp->backoff_page_cache_fill))
> + return false;
>
>This is broken, unfortunately. If a low memory condition we fill
>fill a cache with at least one page anyway because of we do not want
>to hit a slow path.
Thanks remind, please ignore my v4 patch, how about the following?
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 41daae3239b5..e2e8412e687f 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -3238,6 +3238,9 @@ static void fill_page_cache_func(struct work_struct *work)
free_page((unsigned long) bnode);
break;
}
+
+ if (atomic_read(&krcp->backoff_page_cache_fill))
+ break;
}
atomic_set(&krcp->work_in_progress, 0);
>
> // Check the limit.
> if (krcp->nr_bkv_objs >= rcu_min_cached_objs)
> return false;
> @@ -3223,7 +3225,7 @@ static void fill_page_cache_func(struct work_struct *work)
> nr_pages = atomic_read(&krcp->backoff_page_cache_fill) ?
> 1 : rcu_min_cached_objs;
>
> - for (i = 0; i < nr_pages; i++) {
> + for (i = krcp->nr_bkv_objs; i < nr_pages; i++) {
> bnode = (struct kvfree_rcu_bulk_data *)
> __get_free_page(GFP_KERNEL | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN);
>
>
>IMHO, it should be send as a separate patch explaining why it
>it is needed.
Agree.
Thanks
Zqiang
>
>--
>Uladzislau Rezki
On Tue, Apr 11, 2023 at 02:42:27PM +0000, Zhang, Qiang1 wrote:
> > > Currently, in kfree_rcu_shrink_scan(), the drain_page_cache() is
> > > executed before kfree_rcu_monitor() to drain page cache, if the bnode
> > > structure's->gp_snap has done, the kvfree_rcu_bulk() will fill the
> > > page cache again in kfree_rcu_monitor(), this commit add a check
> > > for krcp structure's->backoff_page_cache_fill in put_cached_bnode(),
> > > if the krcp structure's->backoff_page_cache_fill is set, prevent page
> > > cache growing and disable allocated page in fill_page_cache_func().
> > >
> > > Signed-off-by: Zqiang <[email protected]>
> > >
> > >Much improved! But still some questions below...
> > >
> > > Thanx, Paul
> > >
> > > ---
> > > kernel/rcu/tree.c | 4 +++-
> > > 1 file changed, 3 insertions(+), 1 deletion(-)
> > >
> > > diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
> > > index cc34d13be181..9d9d3772cc45 100644
> > > --- a/kernel/rcu/tree.c
> > > +++ b/kernel/rcu/tree.c
> > > @@ -2908,6 +2908,8 @@ static inline bool
> > > put_cached_bnode(struct kfree_rcu_cpu *krcp,
> > > struct kvfree_rcu_bulk_data *bnode)
> > > {
> > > + if (atomic_read(&krcp->backoff_page_cache_fill))
> > > + return false;
> > >
> > >This will mean that under low-memory conditions, we will keep zero
> > >pages in ->bkvcache. All attempts to put something there will fail.
> > >
> > >This is probably not an issue for structures containing an rcu_head
> > >that are passed to kfree_rcu(p, field), but doesn't this mean that
> > >kfree_rcu_mightsleep() unconditionally invokes synchronize_rcu()?
> > >This could seriously slow up freeing under low-memory conditions,
> > >which might exacerbate the low-memory conditions.
> >
> > Thanks for mentioning this, I didn't think of this before????.
> >
> > >
> > >Is this really what we want? Zero cached rather than just fewer cached?
> > >
> > >
> > >
> > > // Check the limit.
> > > if (krcp->nr_bkv_objs >= rcu_min_cached_objs)
> > > return false;
> > > @@ -3221,7 +3223,7 @@ static void fill_page_cache_func(struct work_struct *work)
> > > int i;
> > >
> > > nr_pages = atomic_read(&krcp->backoff_page_cache_fill) ?
> > > - 1 : rcu_min_cached_objs;
> > > + 0 : rcu_min_cached_objs;
> > >
> > > for (i = 0; i < nr_pages; i++) {
> > >
> > >I am still confused as to why we start "i" at zero rather than at
> > >->nr_bkv_objs. What am I missing here?
> >
> >
> > No, you are right, I missed this place.
> >
> > --- a/kernel/rcu/tree.c
> > +++ b/kernel/rcu/tree.c
> > @@ -2908,6 +2908,8 @@ static inline bool
> > put_cached_bnode(struct kfree_rcu_cpu *krcp,
> > struct kvfree_rcu_bulk_data *bnode)
> > {
> > + if (atomic_read(&krcp->backoff_page_cache_fill))
> > + return false;
> >
> >This is broken, unfortunately. If a low memory condition we fill
> >fill a cache with at least one page anyway because of we do not want
> >to hit a slow path.
>
> Thanks remind, please ignore my v4 patch, how about the following?
>
> diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
> index 41daae3239b5..e2e8412e687f 100644
> --- a/kernel/rcu/tree.c
> +++ b/kernel/rcu/tree.c
> @@ -3238,6 +3238,9 @@ static void fill_page_cache_func(struct work_struct *work)
> free_page((unsigned long) bnode);
> break;
> }
> +
> + if (atomic_read(&krcp->backoff_page_cache_fill))
> + break;
> }
It does not fix an "issue" you are reporting. kvfree_rcu_bulk() function
can still fill it back. IMHO, the solution here is to disable cache if
a low memory condition and enable back later on.
The cache size is controlled by the rcu_min_cached_objs variable. We can
set it to 1 and restore it back to original value to make the cache operating
as before.
--
Uladzislau Rezki
> > > Currently, in kfree_rcu_shrink_scan(), the drain_page_cache() is
> > > executed before kfree_rcu_monitor() to drain page cache, if the bnode
> > > structure's->gp_snap has done, the kvfree_rcu_bulk() will fill the
> > > page cache again in kfree_rcu_monitor(), this commit add a check
> > > for krcp structure's->backoff_page_cache_fill in put_cached_bnode(),
> > > if the krcp structure's->backoff_page_cache_fill is set, prevent page
> > > cache growing and disable allocated page in fill_page_cache_func().
> > >
> > > Signed-off-by: Zqiang <[email protected]>
> > >
> > >Much improved! But still some questions below...
> > >
> > > Thanx, Paul
> > >
> > > ---
> > > kernel/rcu/tree.c | 4 +++-
> > > 1 file changed, 3 insertions(+), 1 deletion(-)
> > >
> > > diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
> > > index cc34d13be181..9d9d3772cc45 100644
> > > --- a/kernel/rcu/tree.c
> > > +++ b/kernel/rcu/tree.c
> > > @@ -2908,6 +2908,8 @@ static inline bool
> > > put_cached_bnode(struct kfree_rcu_cpu *krcp,
> > > struct kvfree_rcu_bulk_data *bnode)
> > > {
> > > + if (atomic_read(&krcp->backoff_page_cache_fill))
> > > + return false;
> > >
> > >This will mean that under low-memory conditions, we will keep zero
> > >pages in ->bkvcache. All attempts to put something there will fail.
> > >
> > >This is probably not an issue for structures containing an rcu_head
> > >that are passed to kfree_rcu(p, field), but doesn't this mean that
> > >kfree_rcu_mightsleep() unconditionally invokes synchronize_rcu()?
> > >This could seriously slow up freeing under low-memory conditions,
> > >which might exacerbate the low-memory conditions.
> >
> > Thanks for mentioning this, I didn't think of this before????.
> >
> > >
> > >Is this really what we want? Zero cached rather than just fewer cached?
> > >
> > >
> > >
> > > // Check the limit.
> > > if (krcp->nr_bkv_objs >= rcu_min_cached_objs)
> > > return false;
> > > @@ -3221,7 +3223,7 @@ static void fill_page_cache_func(struct work_struct *work)
> > > int i;
> > >
> > > nr_pages = atomic_read(&krcp->backoff_page_cache_fill) ?
> > > - 1 : rcu_min_cached_objs;
> > > + 0 : rcu_min_cached_objs;
> > >
> > > for (i = 0; i < nr_pages; i++) {
> > >
> > >I am still confused as to why we start "i" at zero rather than at
> > >->nr_bkv_objs. What am I missing here?
> >
> >
> > No, you are right, I missed this place.
> >
> > --- a/kernel/rcu/tree.c
> > +++ b/kernel/rcu/tree.c
> > @@ -2908,6 +2908,8 @@ static inline bool
> > put_cached_bnode(struct kfree_rcu_cpu *krcp,
> > struct kvfree_rcu_bulk_data *bnode)
> > {
> > + if (atomic_read(&krcp->backoff_page_cache_fill))
> > + return false;
> >
> >This is broken, unfortunately. If a low memory condition we fill
> >fill a cache with at least one page anyway because of we do not want
> >to hit a slow path.
>
> Thanks remind, please ignore my v4 patch, how about the following?
>
> diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
> index 41daae3239b5..e2e8412e687f 100644
> --- a/kernel/rcu/tree.c
> +++ b/kernel/rcu/tree.c
> @@ -3238,6 +3238,9 @@ static void fill_page_cache_func(struct work_struct *work)
> free_page((unsigned long) bnode);
> break;
> }
> +
> + if (atomic_read(&krcp->backoff_page_cache_fill))
> + break;
> }
>It does not fix an "issue" you are reporting. kvfree_rcu_bulk() function
>can still fill it back. IMHO, the solution here is to disable cache if
>a low memory condition and enable back later on.
>
>
>The cache size is controlled by the rcu_min_cached_objs variable. We can
>set it to 1 and restore it back to original value to make the cache operating
>as before.
A good suggestion. a question, when need to restore rcu_min_cached_objs?
after the execution of kfree_rcu_shrink_scan() ends?
Thanks
Zqiang
>
>--
>Uladzislau Rezki
On Tue, Apr 11, 2023 at 03:09:13PM +0000, Zhang, Qiang1 wrote:
> > > > Currently, in kfree_rcu_shrink_scan(), the drain_page_cache() is
> > > > executed before kfree_rcu_monitor() to drain page cache, if the bnode
> > > > structure's->gp_snap has done, the kvfree_rcu_bulk() will fill the
> > > > page cache again in kfree_rcu_monitor(), this commit add a check
> > > > for krcp structure's->backoff_page_cache_fill in put_cached_bnode(),
> > > > if the krcp structure's->backoff_page_cache_fill is set, prevent page
> > > > cache growing and disable allocated page in fill_page_cache_func().
> > > >
> > > > Signed-off-by: Zqiang <[email protected]>
> > > >
> > > >Much improved! But still some questions below...
> > > >
> > > > Thanx, Paul
> > > >
> > > > ---
> > > > kernel/rcu/tree.c | 4 +++-
> > > > 1 file changed, 3 insertions(+), 1 deletion(-)
> > > >
> > > > diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
> > > > index cc34d13be181..9d9d3772cc45 100644
> > > > --- a/kernel/rcu/tree.c
> > > > +++ b/kernel/rcu/tree.c
> > > > @@ -2908,6 +2908,8 @@ static inline bool
> > > > put_cached_bnode(struct kfree_rcu_cpu *krcp,
> > > > struct kvfree_rcu_bulk_data *bnode)
> > > > {
> > > > + if (atomic_read(&krcp->backoff_page_cache_fill))
> > > > + return false;
> > > >
> > > >This will mean that under low-memory conditions, we will keep zero
> > > >pages in ->bkvcache. All attempts to put something there will fail.
> > > >
> > > >This is probably not an issue for structures containing an rcu_head
> > > >that are passed to kfree_rcu(p, field), but doesn't this mean that
> > > >kfree_rcu_mightsleep() unconditionally invokes synchronize_rcu()?
> > > >This could seriously slow up freeing under low-memory conditions,
> > > >which might exacerbate the low-memory conditions.
> > >
> > > Thanks for mentioning this, I didn't think of this before????.
> > >
> > > >
> > > >Is this really what we want? Zero cached rather than just fewer cached?
> > > >
> > > >
> > > >
> > > > // Check the limit.
> > > > if (krcp->nr_bkv_objs >= rcu_min_cached_objs)
> > > > return false;
> > > > @@ -3221,7 +3223,7 @@ static void fill_page_cache_func(struct work_struct *work)
> > > > int i;
> > > >
> > > > nr_pages = atomic_read(&krcp->backoff_page_cache_fill) ?
> > > > - 1 : rcu_min_cached_objs;
> > > > + 0 : rcu_min_cached_objs;
> > > >
> > > > for (i = 0; i < nr_pages; i++) {
> > > >
> > > >I am still confused as to why we start "i" at zero rather than at
> > > >->nr_bkv_objs. What am I missing here?
> > >
> > >
> > > No, you are right, I missed this place.
> > >
> > > --- a/kernel/rcu/tree.c
> > > +++ b/kernel/rcu/tree.c
> > > @@ -2908,6 +2908,8 @@ static inline bool
> > > put_cached_bnode(struct kfree_rcu_cpu *krcp,
> > > struct kvfree_rcu_bulk_data *bnode)
> > > {
> > > + if (atomic_read(&krcp->backoff_page_cache_fill))
> > > + return false;
> > >
> > >This is broken, unfortunately. If a low memory condition we fill
> > >fill a cache with at least one page anyway because of we do not want
> > >to hit a slow path.
> >
> > Thanks remind, please ignore my v4 patch, how about the following?
> >
> > diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
> > index 41daae3239b5..e2e8412e687f 100644
> > --- a/kernel/rcu/tree.c
> > +++ b/kernel/rcu/tree.c
> > @@ -3238,6 +3238,9 @@ static void fill_page_cache_func(struct work_struct *work)
> > free_page((unsigned long) bnode);
> > break;
> > }
> > +
> > + if (atomic_read(&krcp->backoff_page_cache_fill))
> > + break;
> > }
> >It does not fix an "issue" you are reporting. kvfree_rcu_bulk() function
> >can still fill it back. IMHO, the solution here is to disable cache if
> >a low memory condition and enable back later on.
> >
> >
> >The cache size is controlled by the rcu_min_cached_objs variable. We can
> >set it to 1 and restore it back to original value to make the cache operating
> >as before.
>
> A good suggestion. a question, when need to restore rcu_min_cached_objs?
> after the execution of kfree_rcu_shrink_scan() ends?
>
We do not know when a low memory condition ends :) Therefore we defer a
refill work for a certain time. In the fill_page_cache_func() we allow the
cache operate as normal again:
...
atomic_set(&krcp->backoff_page_cache_fill, 0);
...
--
Uladzislau Rezki
On Tue, Apr 11, 2023 at 04:58:22PM +0200, Uladzislau Rezki wrote:
> On Tue, Apr 11, 2023 at 02:42:27PM +0000, Zhang, Qiang1 wrote:
> > > > Currently, in kfree_rcu_shrink_scan(), the drain_page_cache() is
> > > > executed before kfree_rcu_monitor() to drain page cache, if the bnode
> > > > structure's->gp_snap has done, the kvfree_rcu_bulk() will fill the
> > > > page cache again in kfree_rcu_monitor(), this commit add a check
> > > > for krcp structure's->backoff_page_cache_fill in put_cached_bnode(),
> > > > if the krcp structure's->backoff_page_cache_fill is set, prevent page
> > > > cache growing and disable allocated page in fill_page_cache_func().
> > > >
> > > > Signed-off-by: Zqiang <[email protected]>
> > > >
> > > >Much improved! But still some questions below...
> > > >
> > > > Thanx, Paul
> > > >
> > > > ---
> > > > kernel/rcu/tree.c | 4 +++-
> > > > 1 file changed, 3 insertions(+), 1 deletion(-)
> > > >
> > > > diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
> > > > index cc34d13be181..9d9d3772cc45 100644
> > > > --- a/kernel/rcu/tree.c
> > > > +++ b/kernel/rcu/tree.c
> > > > @@ -2908,6 +2908,8 @@ static inline bool
> > > > put_cached_bnode(struct kfree_rcu_cpu *krcp,
> > > > struct kvfree_rcu_bulk_data *bnode)
> > > > {
> > > > + if (atomic_read(&krcp->backoff_page_cache_fill))
> > > > + return false;
> > > >
> > > >This will mean that under low-memory conditions, we will keep zero
> > > >pages in ->bkvcache. All attempts to put something there will fail.
> > > >
> > > >This is probably not an issue for structures containing an rcu_head
> > > >that are passed to kfree_rcu(p, field), but doesn't this mean that
> > > >kfree_rcu_mightsleep() unconditionally invokes synchronize_rcu()?
> > > >This could seriously slow up freeing under low-memory conditions,
> > > >which might exacerbate the low-memory conditions.
> > >
> > > Thanks for mentioning this, I didn't think of this before????.
> > >
> > > >
> > > >Is this really what we want? Zero cached rather than just fewer cached?
> > > >
> > > >
> > > >
> > > > // Check the limit.
> > > > if (krcp->nr_bkv_objs >= rcu_min_cached_objs)
> > > > return false;
> > > > @@ -3221,7 +3223,7 @@ static void fill_page_cache_func(struct work_struct *work)
> > > > int i;
> > > >
> > > > nr_pages = atomic_read(&krcp->backoff_page_cache_fill) ?
> > > > - 1 : rcu_min_cached_objs;
> > > > + 0 : rcu_min_cached_objs;
> > > >
> > > > for (i = 0; i < nr_pages; i++) {
> > > >
> > > >I am still confused as to why we start "i" at zero rather than at
> > > >->nr_bkv_objs. What am I missing here?
> > >
> > >
> > > No, you are right, I missed this place.
> > >
> > > --- a/kernel/rcu/tree.c
> > > +++ b/kernel/rcu/tree.c
> > > @@ -2908,6 +2908,8 @@ static inline bool
> > > put_cached_bnode(struct kfree_rcu_cpu *krcp,
> > > struct kvfree_rcu_bulk_data *bnode)
> > > {
> > > + if (atomic_read(&krcp->backoff_page_cache_fill))
> > > + return false;
> > >
> > >This is broken, unfortunately. If a low memory condition we fill
> > >fill a cache with at least one page anyway because of we do not want
> > >to hit a slow path.
> >
> > Thanks remind, please ignore my v4 patch, how about the following?
> >
> > diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
> > index 41daae3239b5..e2e8412e687f 100644
> > --- a/kernel/rcu/tree.c
> > +++ b/kernel/rcu/tree.c
> > @@ -3238,6 +3238,9 @@ static void fill_page_cache_func(struct work_struct *work)
> > free_page((unsigned long) bnode);
> > break;
> > }
> > +
> > + if (atomic_read(&krcp->backoff_page_cache_fill))
> > + break;
> > }
> It does not fix an "issue" you are reporting. kvfree_rcu_bulk() function
> can still fill it back. IMHO, the solution here is to disable cache if
> a low memory condition and enable back later on.
>
> The cache size is controlled by the rcu_min_cached_objs variable. We can
> set it to 1 and restore it back to original value to make the cache operating
> as before.
It would be best to use a second variable for this. Users might get
annoyed if their changes to rcu_min_cached_objs got overwritten once
things got set back to normal operation.
Thanx, Paul
On Tue, Apr 11, 2023 at 09:42:37AM -0700, Paul E. McKenney wrote:
> On Tue, Apr 11, 2023 at 04:58:22PM +0200, Uladzislau Rezki wrote:
> > On Tue, Apr 11, 2023 at 02:42:27PM +0000, Zhang, Qiang1 wrote:
> > > > > Currently, in kfree_rcu_shrink_scan(), the drain_page_cache() is
> > > > > executed before kfree_rcu_monitor() to drain page cache, if the bnode
> > > > > structure's->gp_snap has done, the kvfree_rcu_bulk() will fill the
> > > > > page cache again in kfree_rcu_monitor(), this commit add a check
> > > > > for krcp structure's->backoff_page_cache_fill in put_cached_bnode(),
> > > > > if the krcp structure's->backoff_page_cache_fill is set, prevent page
> > > > > cache growing and disable allocated page in fill_page_cache_func().
> > > > >
> > > > > Signed-off-by: Zqiang <[email protected]>
> > > > >
> > > > >Much improved! But still some questions below...
> > > > >
> > > > > Thanx, Paul
> > > > >
> > > > > ---
> > > > > kernel/rcu/tree.c | 4 +++-
> > > > > 1 file changed, 3 insertions(+), 1 deletion(-)
> > > > >
> > > > > diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
> > > > > index cc34d13be181..9d9d3772cc45 100644
> > > > > --- a/kernel/rcu/tree.c
> > > > > +++ b/kernel/rcu/tree.c
> > > > > @@ -2908,6 +2908,8 @@ static inline bool
> > > > > put_cached_bnode(struct kfree_rcu_cpu *krcp,
> > > > > struct kvfree_rcu_bulk_data *bnode)
> > > > > {
> > > > > + if (atomic_read(&krcp->backoff_page_cache_fill))
> > > > > + return false;
> > > > >
> > > > >This will mean that under low-memory conditions, we will keep zero
> > > > >pages in ->bkvcache. All attempts to put something there will fail.
> > > > >
> > > > >This is probably not an issue for structures containing an rcu_head
> > > > >that are passed to kfree_rcu(p, field), but doesn't this mean that
> > > > >kfree_rcu_mightsleep() unconditionally invokes synchronize_rcu()?
> > > > >This could seriously slow up freeing under low-memory conditions,
> > > > >which might exacerbate the low-memory conditions.
> > > >
> > > > Thanks for mentioning this, I didn't think of this before????.
> > > >
> > > > >
> > > > >Is this really what we want? Zero cached rather than just fewer cached?
> > > > >
> > > > >
> > > > >
> > > > > // Check the limit.
> > > > > if (krcp->nr_bkv_objs >= rcu_min_cached_objs)
> > > > > return false;
> > > > > @@ -3221,7 +3223,7 @@ static void fill_page_cache_func(struct work_struct *work)
> > > > > int i;
> > > > >
> > > > > nr_pages = atomic_read(&krcp->backoff_page_cache_fill) ?
> > > > > - 1 : rcu_min_cached_objs;
> > > > > + 0 : rcu_min_cached_objs;
> > > > >
> > > > > for (i = 0; i < nr_pages; i++) {
> > > > >
> > > > >I am still confused as to why we start "i" at zero rather than at
> > > > >->nr_bkv_objs. What am I missing here?
> > > >
> > > >
> > > > No, you are right, I missed this place.
> > > >
> > > > --- a/kernel/rcu/tree.c
> > > > +++ b/kernel/rcu/tree.c
> > > > @@ -2908,6 +2908,8 @@ static inline bool
> > > > put_cached_bnode(struct kfree_rcu_cpu *krcp,
> > > > struct kvfree_rcu_bulk_data *bnode)
> > > > {
> > > > + if (atomic_read(&krcp->backoff_page_cache_fill))
> > > > + return false;
> > > >
> > > >This is broken, unfortunately. If a low memory condition we fill
> > > >fill a cache with at least one page anyway because of we do not want
> > > >to hit a slow path.
> > >
> > > Thanks remind, please ignore my v4 patch, how about the following?
> > >
> > > diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
> > > index 41daae3239b5..e2e8412e687f 100644
> > > --- a/kernel/rcu/tree.c
> > > +++ b/kernel/rcu/tree.c
> > > @@ -3238,6 +3238,9 @@ static void fill_page_cache_func(struct work_struct *work)
> > > free_page((unsigned long) bnode);
> > > break;
> > > }
> > > +
> > > + if (atomic_read(&krcp->backoff_page_cache_fill))
> > > + break;
> > > }
> > It does not fix an "issue" you are reporting. kvfree_rcu_bulk() function
> > can still fill it back. IMHO, the solution here is to disable cache if
> > a low memory condition and enable back later on.
> >
> > The cache size is controlled by the rcu_min_cached_objs variable. We can
> > set it to 1 and restore it back to original value to make the cache operating
> > as before.
>
> It would be best to use a second variable for this. Users might get
> annoyed if their changes to rcu_min_cached_objs got overwritten once
> things got set back to normal operation.
>
Agree. So we do not make it visible over sysfs interface for user that
we manipulate it.
--
Uladzislau Rezki
> On Tue, Apr 11, 2023 at 04:58:22PM +0200, Uladzislau Rezki wrote:
> > On Tue, Apr 11, 2023 at 02:42:27PM +0000, Zhang, Qiang1 wrote:
> > > > > Currently, in kfree_rcu_shrink_scan(), the drain_page_cache()
> > > > > is executed before kfree_rcu_monitor() to drain page cache, if
> > > > > the bnode structure's->gp_snap has done, the kvfree_rcu_bulk()
> > > > > will fill the page cache again in kfree_rcu_monitor(), this
> > > > > commit add a check for krcp
> > > > > structure's->backoff_page_cache_fill in put_cached_bnode(), if
> > > > > the krcp structure's->backoff_page_cache_fill is set, prevent page cache growing and disable allocated page in fill_page_cache_func().
> > > > >
> > > > > Signed-off-by: Zqiang <[email protected]>
> > > > >
> > > > >Much improved! But still some questions below...
> > > > >
> > > > > Thanx, Paul
> > > > >
> > > > > ---
> > > > > kernel/rcu/tree.c | 4 +++-
> > > > > 1 file changed, 3 insertions(+), 1 deletion(-)
> > > > >
> > > > > diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index
> > > > > cc34d13be181..9d9d3772cc45 100644
> > > > > --- a/kernel/rcu/tree.c
> > > > > +++ b/kernel/rcu/tree.c
> > > > > @@ -2908,6 +2908,8 @@ static inline bool
> > > > > put_cached_bnode(struct kfree_rcu_cpu *krcp,
> > > > > struct kvfree_rcu_bulk_data *bnode) {
> > > > > + if (atomic_read(&krcp->backoff_page_cache_fill))
> > > > > + return false;
> > > > >
> > > > >This will mean that under low-memory conditions, we will keep
> > > > >zero pages in ->bkvcache. All attempts to put something there will fail.
> > > > >
> > > > >This is probably not an issue for structures containing an
> > > > >rcu_head that are passed to kfree_rcu(p, field), but doesn't
> > > > >this mean that
> > > > >kfree_rcu_mightsleep() unconditionally invokes synchronize_rcu()?
> > > > >This could seriously slow up freeing under low-memory
> > > > >conditions, which might exacerbate the low-memory conditions.
> > > >
> > > > Thanks for mentioning this, I didn't think of this before????.
> > > >
> > > > >
> > > > >Is this really what we want? Zero cached rather than just fewer cached?
> > > > >
> > > > >
> > > > >
> > > > > // Check the limit.
> > > > > if (krcp->nr_bkv_objs >= rcu_min_cached_objs)
> > > > > return false;
> > > > > @@ -3221,7 +3223,7 @@ static void fill_page_cache_func(struct work_struct *work)
> > > > > int i;
> > > > >
> > > > > nr_pages = atomic_read(&krcp->backoff_page_cache_fill) ?
> > > > > - 1 : rcu_min_cached_objs;
> > > > > + 0 : rcu_min_cached_objs;
> > > > >
> > > > > for (i = 0; i < nr_pages; i++) {
> > > > >
> > > > >I am still confused as to why we start "i" at zero rather than
> > > > >at
> > > > >->nr_bkv_objs. What am I missing here?
> > > >
> > > >
> > > > No, you are right, I missed this place.
> > > >
> > > > --- a/kernel/rcu/tree.c
> > > > +++ b/kernel/rcu/tree.c
> > > > @@ -2908,6 +2908,8 @@ static inline bool
> > > > put_cached_bnode(struct kfree_rcu_cpu *krcp,
> > > > struct kvfree_rcu_bulk_data *bnode) {
> > > > + if (atomic_read(&krcp->backoff_page_cache_fill))
> > > > + return false;
> > > >
> > > >This is broken, unfortunately. If a low memory condition we fill
> > > >fill a cache with at least one page anyway because of we do not
> > > >want to hit a slow path.
> > >
> > > Thanks remind, please ignore my v4 patch, how about the following?
> > >
> > > diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index
> > > 41daae3239b5..e2e8412e687f 100644
> > > --- a/kernel/rcu/tree.c
> > > +++ b/kernel/rcu/tree.c
> > > @@ -3238,6 +3238,9 @@ static void fill_page_cache_func(struct work_struct *work)
> > > free_page((unsigned long) bnode);
> > > break;
> > > }
> > > +
> > > + if (atomic_read(&krcp->backoff_page_cache_fill))
> > > + break;
> > > }
> > It does not fix an "issue" you are reporting. kvfree_rcu_bulk()
> > function can still fill it back. IMHO, the solution here is to
> > disable cache if a low memory condition and enable back later on.
> >
> > The cache size is controlled by the rcu_min_cached_objs variable. We
> > can set it to 1 and restore it back to original value to make the
> > cache operating as before.
>
> It would be best to use a second variable for this. Users might get
> annoyed if their changes to rcu_min_cached_objs got overwritten once
> things got set back to normal operation.
>
>Agree. So we do not make it visible over sysfs interface for user that we manipulate it.
>
>
The rcu_min_cached_objs is read-only, Users cannot be set rcu_min_cached_objs dynamically.
-r--r--r-- 1 root root 4.0K Apr 12 01:08 rcu_min_cached_objs
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 41daae3239b5..0e9f83562823 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -2909,7 +2909,8 @@ put_cached_bnode(struct kfree_rcu_cpu *krcp,
struct kvfree_rcu_bulk_data *bnode)
{
// Check the limit.
- if (krcp->nr_bkv_objs >= rcu_min_cached_objs)
+ if ((atomic_read(&krcp->backoff_page_cache_fill) && krcp->nr_bkv_objs) ||
+ krcp->nr_bkv_objs >= rcu_min_cached_objs)
return false;
llist_add((struct llist_node *) bnode, &krcp->bkvcache);
thoughts?
Thanks
Zqiang
>
>--
>Uladzislau Rezki
On Wed, Apr 12, 2023 at 09:14:15AM +0000, Zhang, Qiang1 wrote:
>
> > On Tue, Apr 11, 2023 at 04:58:22PM +0200, Uladzislau Rezki wrote:
> > > On Tue, Apr 11, 2023 at 02:42:27PM +0000, Zhang, Qiang1 wrote:
> > > > > > Currently, in kfree_rcu_shrink_scan(), the drain_page_cache()
> > > > > > is executed before kfree_rcu_monitor() to drain page cache, if
> > > > > > the bnode structure's->gp_snap has done, the kvfree_rcu_bulk()
> > > > > > will fill the page cache again in kfree_rcu_monitor(), this
> > > > > > commit add a check for krcp
> > > > > > structure's->backoff_page_cache_fill in put_cached_bnode(), if
> > > > > > the krcp structure's->backoff_page_cache_fill is set, prevent page cache growing and disable allocated page in fill_page_cache_func().
> > > > > >
> > > > > > Signed-off-by: Zqiang <[email protected]>
> > > > > >
> > > > > >Much improved! But still some questions below...
> > > > > >
> > > > > > Thanx, Paul
> > > > > >
> > > > > > ---
> > > > > > kernel/rcu/tree.c | 4 +++-
> > > > > > 1 file changed, 3 insertions(+), 1 deletion(-)
> > > > > >
> > > > > > diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index
> > > > > > cc34d13be181..9d9d3772cc45 100644
> > > > > > --- a/kernel/rcu/tree.c
> > > > > > +++ b/kernel/rcu/tree.c
> > > > > > @@ -2908,6 +2908,8 @@ static inline bool
> > > > > > put_cached_bnode(struct kfree_rcu_cpu *krcp,
> > > > > > struct kvfree_rcu_bulk_data *bnode) {
> > > > > > + if (atomic_read(&krcp->backoff_page_cache_fill))
> > > > > > + return false;
> > > > > >
> > > > > >This will mean that under low-memory conditions, we will keep
> > > > > >zero pages in ->bkvcache. All attempts to put something there will fail.
> > > > > >
> > > > > >This is probably not an issue for structures containing an
> > > > > >rcu_head that are passed to kfree_rcu(p, field), but doesn't
> > > > > >this mean that
> > > > > >kfree_rcu_mightsleep() unconditionally invokes synchronize_rcu()?
> > > > > >This could seriously slow up freeing under low-memory
> > > > > >conditions, which might exacerbate the low-memory conditions.
> > > > >
> > > > > Thanks for mentioning this, I didn't think of this before????.
> > > > >
> > > > > >
> > > > > >Is this really what we want? Zero cached rather than just fewer cached?
> > > > > >
> > > > > >
> > > > > >
> > > > > > // Check the limit.
> > > > > > if (krcp->nr_bkv_objs >= rcu_min_cached_objs)
> > > > > > return false;
> > > > > > @@ -3221,7 +3223,7 @@ static void fill_page_cache_func(struct work_struct *work)
> > > > > > int i;
> > > > > >
> > > > > > nr_pages = atomic_read(&krcp->backoff_page_cache_fill) ?
> > > > > > - 1 : rcu_min_cached_objs;
> > > > > > + 0 : rcu_min_cached_objs;
> > > > > >
> > > > > > for (i = 0; i < nr_pages; i++) {
> > > > > >
> > > > > >I am still confused as to why we start "i" at zero rather than
> > > > > >at
> > > > > >->nr_bkv_objs. What am I missing here?
> > > > >
> > > > >
> > > > > No, you are right, I missed this place.
> > > > >
> > > > > --- a/kernel/rcu/tree.c
> > > > > +++ b/kernel/rcu/tree.c
> > > > > @@ -2908,6 +2908,8 @@ static inline bool
> > > > > put_cached_bnode(struct kfree_rcu_cpu *krcp,
> > > > > struct kvfree_rcu_bulk_data *bnode) {
> > > > > + if (atomic_read(&krcp->backoff_page_cache_fill))
> > > > > + return false;
> > > > >
> > > > >This is broken, unfortunately. If a low memory condition we fill
> > > > >fill a cache with at least one page anyway because of we do not
> > > > >want to hit a slow path.
> > > >
> > > > Thanks remind, please ignore my v4 patch, how about the following?
> > > >
> > > > diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index
> > > > 41daae3239b5..e2e8412e687f 100644
> > > > --- a/kernel/rcu/tree.c
> > > > +++ b/kernel/rcu/tree.c
> > > > @@ -3238,6 +3238,9 @@ static void fill_page_cache_func(struct work_struct *work)
> > > > free_page((unsigned long) bnode);
> > > > break;
> > > > }
> > > > +
> > > > + if (atomic_read(&krcp->backoff_page_cache_fill))
> > > > + break;
> > > > }
> > > It does not fix an "issue" you are reporting. kvfree_rcu_bulk()
> > > function can still fill it back. IMHO, the solution here is to
> > > disable cache if a low memory condition and enable back later on.
> > >
> > > The cache size is controlled by the rcu_min_cached_objs variable. We
> > > can set it to 1 and restore it back to original value to make the
> > > cache operating as before.
> >
> > It would be best to use a second variable for this. Users might get
> > annoyed if their changes to rcu_min_cached_objs got overwritten once
> > things got set back to normal operation.
> >
> >Agree. So we do not make it visible over sysfs interface for user that we manipulate it.
> >
> >
>
>
> The rcu_min_cached_objs is read-only, Users cannot be set rcu_min_cached_objs dynamically.
>
> -r--r--r-- 1 root root 4.0K Apr 12 01:08 rcu_min_cached_objs
>
You can set it as a boot parameter: rcutree.rcu_min_cached_objs=XXX
> diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
> index 41daae3239b5..0e9f83562823 100644
> --- a/kernel/rcu/tree.c
> +++ b/kernel/rcu/tree.c
> @@ -2909,7 +2909,8 @@ put_cached_bnode(struct kfree_rcu_cpu *krcp,
> struct kvfree_rcu_bulk_data *bnode)
> {
> // Check the limit.
> - if (krcp->nr_bkv_objs >= rcu_min_cached_objs)
> + if ((atomic_read(&krcp->backoff_page_cache_fill) && krcp->nr_bkv_objs) ||
> + krcp->nr_bkv_objs >= rcu_min_cached_objs)
> return false;
>
We can eliminate the backoff_page_cache_fill per-cpu atomic variable and
just change a new one, say, min_cached_objs, if a low memory condition.
Restore it to a default what is the rcu_min_cached_objs.
I can post here an example if it helps to make it more clear.
--
Uladzislau Rezki
> > On Tue, Apr 11, 2023 at 04:58:22PM +0200, Uladzislau Rezki wrote:
> > > On Tue, Apr 11, 2023 at 02:42:27PM +0000, Zhang, Qiang1 wrote:
> > > > > > Currently, in kfree_rcu_shrink_scan(), the drain_page_cache()
> > > > > > is executed before kfree_rcu_monitor() to drain page cache, if
> > > > > > the bnode structure's->gp_snap has done, the kvfree_rcu_bulk()
> > > > > > will fill the page cache again in kfree_rcu_monitor(), this
> > > > > > commit add a check for krcp
> > > > > > structure's->backoff_page_cache_fill in put_cached_bnode(), if
> > > > > > the krcp structure's->backoff_page_cache_fill is set, prevent page cache growing and disable allocated page in fill_page_cache_func().
> > > > > >
> > > > > > Signed-off-by: Zqiang <[email protected]>
> > > > > >
> > > > > >Much improved! But still some questions below...
> > > > > >
> > > > > > Thanx, Paul
> > > > > >
> > > > > > ---
> > > > > > kernel/rcu/tree.c | 4 +++-
> > > > > > 1 file changed, 3 insertions(+), 1 deletion(-)
> > > > > >
> > > > > > diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index
> > > > > > cc34d13be181..9d9d3772cc45 100644
> > > > > > --- a/kernel/rcu/tree.c
> > > > > > +++ b/kernel/rcu/tree.c
> > > > > > @@ -2908,6 +2908,8 @@ static inline bool
> > > > > > put_cached_bnode(struct kfree_rcu_cpu *krcp,
> > > > > > struct kvfree_rcu_bulk_data *bnode) {
> > > > > > + if (atomic_read(&krcp->backoff_page_cache_fill))
> > > > > > + return false;
> > > > > >
> > > > > >This will mean that under low-memory conditions, we will keep
> > > > > >zero pages in ->bkvcache. All attempts to put something there will fail.
> > > > > >
> > > > > >This is probably not an issue for structures containing an
> > > > > >rcu_head that are passed to kfree_rcu(p, field), but doesn't
> > > > > >this mean that
> > > > > >kfree_rcu_mightsleep() unconditionally invokes synchronize_rcu()?
> > > > > >This could seriously slow up freeing under low-memory
> > > > > >conditions, which might exacerbate the low-memory conditions.
> > > > >
> > > > > Thanks for mentioning this, I didn't think of this before????.
> > > > >
> > > > > >
> > > > > >Is this really what we want? Zero cached rather than just fewer cached?
> > > > > >
> > > > > >
> > > > > >
> > > > > > // Check the limit.
> > > > > > if (krcp->nr_bkv_objs >= rcu_min_cached_objs)
> > > > > > return false;
> > > > > > @@ -3221,7 +3223,7 @@ static void fill_page_cache_func(struct work_struct *work)
> > > > > > int i;
> > > > > >
> > > > > > nr_pages = atomic_read(&krcp->backoff_page_cache_fill) ?
> > > > > > - 1 : rcu_min_cached_objs;
> > > > > > + 0 : rcu_min_cached_objs;
> > > > > >
> > > > > > for (i = 0; i < nr_pages; i++) {
> > > > > >
> > > > > >I am still confused as to why we start "i" at zero rather than
> > > > > >at
> > > > > >->nr_bkv_objs. What am I missing here?
> > > > >
> > > > >
> > > > > No, you are right, I missed this place.
> > > > >
> > > > > --- a/kernel/rcu/tree.c
> > > > > +++ b/kernel/rcu/tree.c
> > > > > @@ -2908,6 +2908,8 @@ static inline bool
> > > > > put_cached_bnode(struct kfree_rcu_cpu *krcp,
> > > > > struct kvfree_rcu_bulk_data *bnode) {
> > > > > + if (atomic_read(&krcp->backoff_page_cache_fill))
> > > > > + return false;
> > > > >
> > > > >This is broken, unfortunately. If a low memory condition we fill
> > > > >fill a cache with at least one page anyway because of we do not
> > > > >want to hit a slow path.
> > > >
> > > > Thanks remind, please ignore my v4 patch, how about the following?
> > > >
> > > > diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index
> > > > 41daae3239b5..e2e8412e687f 100644
> > > > --- a/kernel/rcu/tree.c
> > > > +++ b/kernel/rcu/tree.c
> > > > @@ -3238,6 +3238,9 @@ static void fill_page_cache_func(struct work_struct *work)
> > > > free_page((unsigned long) bnode);
> > > > break;
> > > > }
> > > > +
> > > > + if (atomic_read(&krcp->backoff_page_cache_fill))
> > > > + break;
> > > > }
> > > It does not fix an "issue" you are reporting. kvfree_rcu_bulk()
> > > function can still fill it back. IMHO, the solution here is to
> > > disable cache if a low memory condition and enable back later on.
> > >
> > > The cache size is controlled by the rcu_min_cached_objs variable. We
> > > can set it to 1 and restore it back to original value to make the
> > > cache operating as before.
> >
> > It would be best to use a second variable for this. Users might get
> > annoyed if their changes to rcu_min_cached_objs got overwritten once
> > things got set back to normal operation.
> >
> >Agree. So we do not make it visible over sysfs interface for user that we manipulate it.
> >
> >
>
>
> The rcu_min_cached_objs is read-only, Users cannot be set rcu_min_cached_objs dynamically.
>
> -r--r--r-- 1 root root 4.0K Apr 12 01:08 rcu_min_cached_objs
>
You can set it as a boot parameter: rcutree.rcu_min_cached_objs=XXX
> diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
> index 41daae3239b5..0e9f83562823 100644
> --- a/kernel/rcu/tree.c
> +++ b/kernel/rcu/tree.c
> @@ -2909,7 +2909,8 @@ put_cached_bnode(struct kfree_rcu_cpu *krcp,
> struct kvfree_rcu_bulk_data *bnode)
> {
> // Check the limit.
> - if (krcp->nr_bkv_objs >= rcu_min_cached_objs)
> + if ((atomic_read(&krcp->backoff_page_cache_fill) && krcp->nr_bkv_objs) ||
> + krcp->nr_bkv_objs >= rcu_min_cached_objs)
> return false;
>
>We can eliminate the backoff_page_cache_fill per-cpu atomic variable and
>just change a new one, say, min_cached_objs, if a low memory condition.
>Restore it to a default what is the rcu_min_cached_objs.
Thanks for suggestion, will be modified in this way.
>
>I can post here an example if it helps to make it more clear.
>
>--
>Uladzislau Rezki