On 01/16/2014 02:53 AM, Andrew Morton wrote:
> On Wed, 15 Jan 2014 19:55:11 +0400 Vladimir Davydov
> wrote:
>
>>> We could avoid the "scan 32 then scan just 1" issue with something like
>>>
>>> if (total_scan > batch_size)
>>> total_scan %= batch_size;
>>>
>>> before the loop.
On 01/16/2014 02:53 AM, Andrew Morton wrote:
On Wed, 15 Jan 2014 19:55:11 +0400 Vladimir Davydov vdavy...@parallels.com
wrote:
We could avoid the scan 32 then scan just 1 issue with something like
if (total_scan batch_size)
total_scan %= batch_size;
before the loop. But
On Wed, 15 Jan 2014 19:55:11 +0400 Vladimir Davydov
wrote:
> >
> > We could avoid the "scan 32 then scan just 1" issue with something like
> >
> > if (total_scan > batch_size)
> > total_scan %= batch_size;
> >
> > before the loop. But I expect the effects of that will be
On 01/15/2014 01:25 PM, Andrew Morton wrote:
> On Wed, 15 Jan 2014 12:47:35 +0400 Vladimir Davydov
> wrote:
>
>> On 01/15/2014 02:14 AM, Andrew Morton wrote:
>>> On Tue, 14 Jan 2014 11:23:30 +0400 Vladimir Davydov
>>> wrote:
>>>
On 01/14/2014 03:05 AM, Andrew Morton wrote:
> That
On Wed, 15 Jan 2014 12:47:35 +0400 Vladimir Davydov
wrote:
> On 01/15/2014 02:14 AM, Andrew Morton wrote:
> > On Tue, 14 Jan 2014 11:23:30 +0400 Vladimir Davydov
> > wrote:
> >
> >> On 01/14/2014 03:05 AM, Andrew Morton wrote:
> >>> That being said, I think I'll schedule this patch as-is for
On 01/15/2014 02:14 AM, Andrew Morton wrote:
> On Tue, 14 Jan 2014 11:23:30 +0400 Vladimir Davydov
> wrote:
>
>> On 01/14/2014 03:05 AM, Andrew Morton wrote:
>>> That being said, I think I'll schedule this patch as-is for 3.14. Can
>>> you please take a look at implementing the simpler
On 01/15/2014 02:14 AM, Andrew Morton wrote:
On Tue, 14 Jan 2014 11:23:30 +0400 Vladimir Davydov vdavy...@parallels.com
wrote:
On 01/14/2014 03:05 AM, Andrew Morton wrote:
That being said, I think I'll schedule this patch as-is for 3.14. Can
you please take a look at implementing the
On Wed, 15 Jan 2014 12:47:35 +0400 Vladimir Davydov vdavy...@parallels.com
wrote:
On 01/15/2014 02:14 AM, Andrew Morton wrote:
On Tue, 14 Jan 2014 11:23:30 +0400 Vladimir Davydov
vdavy...@parallels.com wrote:
On 01/14/2014 03:05 AM, Andrew Morton wrote:
That being said, I think I'll
On 01/15/2014 01:25 PM, Andrew Morton wrote:
On Wed, 15 Jan 2014 12:47:35 +0400 Vladimir Davydov vdavy...@parallels.com
wrote:
On 01/15/2014 02:14 AM, Andrew Morton wrote:
On Tue, 14 Jan 2014 11:23:30 +0400 Vladimir Davydov
vdavy...@parallels.com wrote:
On 01/14/2014 03:05 AM, Andrew
On Wed, 15 Jan 2014 19:55:11 +0400 Vladimir Davydov vdavy...@parallels.com
wrote:
We could avoid the scan 32 then scan just 1 issue with something like
if (total_scan batch_size)
total_scan %= batch_size;
before the loop. But I expect the effects of that will be
On Tue, 14 Jan 2014 11:23:30 +0400 Vladimir Davydov
wrote:
> On 01/14/2014 03:05 AM, Andrew Morton wrote:
> > On Sat, 11 Jan 2014 16:36:31 +0400 Vladimir Davydov
> > wrote:
> >
> >> When reclaiming kmem, we currently don't scan slabs that have less than
> >> batch_size objects (see
On Tue, 14 Jan 2014 11:23:30 +0400 Vladimir Davydov vdavy...@parallels.com
wrote:
On 01/14/2014 03:05 AM, Andrew Morton wrote:
On Sat, 11 Jan 2014 16:36:31 +0400 Vladimir Davydov
vdavy...@parallels.com wrote:
When reclaiming kmem, we currently don't scan slabs that have less than
On 01/14/2014 03:05 AM, Andrew Morton wrote:
> On Sat, 11 Jan 2014 16:36:31 +0400 Vladimir Davydov
> wrote:
>
>> When reclaiming kmem, we currently don't scan slabs that have less than
>> batch_size objects (see shrink_slab_node()):
>>
>> while (total_scan >= batch_size) {
>>
On Sat, 11 Jan 2014 16:36:31 +0400 Vladimir Davydov
wrote:
> When reclaiming kmem, we currently don't scan slabs that have less than
> batch_size objects (see shrink_slab_node()):
>
> while (total_scan >= batch_size) {
> shrinkctl->nr_to_scan = batch_size;
>
On Sat, 11 Jan 2014 16:36:31 +0400 Vladimir Davydov vdavy...@parallels.com
wrote:
When reclaiming kmem, we currently don't scan slabs that have less than
batch_size objects (see shrink_slab_node()):
while (total_scan = batch_size) {
shrinkctl-nr_to_scan =
On 01/14/2014 03:05 AM, Andrew Morton wrote:
On Sat, 11 Jan 2014 16:36:31 +0400 Vladimir Davydov vdavy...@parallels.com
wrote:
When reclaiming kmem, we currently don't scan slabs that have less than
batch_size objects (see shrink_slab_node()):
while (total_scan = batch_size) {
When reclaiming kmem, we currently don't scan slabs that have less than
batch_size objects (see shrink_slab_node()):
while (total_scan >= batch_size) {
shrinkctl->nr_to_scan = batch_size;
shrinker->scan_objects(shrinker, shrinkctl);
When reclaiming kmem, we currently don't scan slabs that have less than
batch_size objects (see shrink_slab_node()):
while (total_scan = batch_size) {
shrinkctl-nr_to_scan = batch_size;
shrinker-scan_objects(shrinker, shrinkctl);
total_scan
18 matches
Mail list logo