Re: [PATCH v2 3/5] mm: use a dedicated workqueue for the free workers

2017-03-24 Thread Aaron Lu
On Thu, Mar 23, 2017 at 08:38:43AM -0700, Dave Hansen wrote: > On 03/22/2017 01:41 AM, Aaron Lu wrote: > > On Wed, Mar 22, 2017 at 03:33:35PM +0900, Minchan Kim wrote: > >> On Wed, Mar 15, 2017 at 05:00:02PM +0800, Aaron Lu wrote: > >>> Introduce a workqueue for all the free workers so that user

Re: [PATCH v2 3/5] mm: use a dedicated workqueue for the free workers

2017-03-24 Thread Aaron Lu
On Thu, Mar 23, 2017 at 08:38:43AM -0700, Dave Hansen wrote: > On 03/22/2017 01:41 AM, Aaron Lu wrote: > > On Wed, Mar 22, 2017 at 03:33:35PM +0900, Minchan Kim wrote: > >> On Wed, Mar 15, 2017 at 05:00:02PM +0800, Aaron Lu wrote: > >>> Introduce a workqueue for all the free workers so that user

Re: [PATCH v2 3/5] mm: use a dedicated workqueue for the free workers

2017-03-23 Thread Dave Hansen
On 03/22/2017 01:41 AM, Aaron Lu wrote: > On Wed, Mar 22, 2017 at 03:33:35PM +0900, Minchan Kim wrote: >> On Wed, Mar 15, 2017 at 05:00:02PM +0800, Aaron Lu wrote: >>> Introduce a workqueue for all the free workers so that user can fine >>> tune how many workers can be active through sysfs

Re: [PATCH v2 3/5] mm: use a dedicated workqueue for the free workers

2017-03-23 Thread Dave Hansen
On 03/22/2017 01:41 AM, Aaron Lu wrote: > On Wed, Mar 22, 2017 at 03:33:35PM +0900, Minchan Kim wrote: >> On Wed, Mar 15, 2017 at 05:00:02PM +0800, Aaron Lu wrote: >>> Introduce a workqueue for all the free workers so that user can fine >>> tune how many workers can be active through sysfs

Re: [PATCH v2 3/5] mm: use a dedicated workqueue for the free workers

2017-03-23 Thread Minchan Kim
On Wed, Mar 22, 2017 at 09:43:04PM +0800, Aaron Lu wrote: > On Wed, Mar 22, 2017 at 05:55:12PM +0900, Minchan Kim wrote: > > On Wed, Mar 22, 2017 at 04:41:04PM +0800, Aaron Lu wrote: > > > My understanding of the unbound workqueue is that it will create a > > > thread pool for each node, versus

Re: [PATCH v2 3/5] mm: use a dedicated workqueue for the free workers

2017-03-23 Thread Minchan Kim
On Wed, Mar 22, 2017 at 09:43:04PM +0800, Aaron Lu wrote: > On Wed, Mar 22, 2017 at 05:55:12PM +0900, Minchan Kim wrote: > > On Wed, Mar 22, 2017 at 04:41:04PM +0800, Aaron Lu wrote: > > > My understanding of the unbound workqueue is that it will create a > > > thread pool for each node, versus

Re: [PATCH v2 3/5] mm: use a dedicated workqueue for the free workers

2017-03-22 Thread Aaron Lu
On Wed, Mar 22, 2017 at 05:55:12PM +0900, Minchan Kim wrote: > On Wed, Mar 22, 2017 at 04:41:04PM +0800, Aaron Lu wrote: > > My understanding of the unbound workqueue is that it will create a > > thread pool for each node, versus each CPU as in the bound workqueue > > case, and use threads from

Re: [PATCH v2 3/5] mm: use a dedicated workqueue for the free workers

2017-03-22 Thread Aaron Lu
On Wed, Mar 22, 2017 at 05:55:12PM +0900, Minchan Kim wrote: > On Wed, Mar 22, 2017 at 04:41:04PM +0800, Aaron Lu wrote: > > My understanding of the unbound workqueue is that it will create a > > thread pool for each node, versus each CPU as in the bound workqueue > > case, and use threads from

Re: [PATCH v2 3/5] mm: use a dedicated workqueue for the free workers

2017-03-22 Thread Minchan Kim
On Wed, Mar 22, 2017 at 04:41:04PM +0800, Aaron Lu wrote: > On Wed, Mar 22, 2017 at 03:33:35PM +0900, Minchan Kim wrote: > > Hi, > > > > On Wed, Mar 15, 2017 at 05:00:02PM +0800, Aaron Lu wrote: > > > Introduce a workqueue for all the free workers so that user can fine > > > tune how many workers

Re: [PATCH v2 3/5] mm: use a dedicated workqueue for the free workers

2017-03-22 Thread Minchan Kim
On Wed, Mar 22, 2017 at 04:41:04PM +0800, Aaron Lu wrote: > On Wed, Mar 22, 2017 at 03:33:35PM +0900, Minchan Kim wrote: > > Hi, > > > > On Wed, Mar 15, 2017 at 05:00:02PM +0800, Aaron Lu wrote: > > > Introduce a workqueue for all the free workers so that user can fine > > > tune how many workers

Re: [PATCH v2 3/5] mm: use a dedicated workqueue for the free workers

2017-03-22 Thread Aaron Lu
On Wed, Mar 22, 2017 at 03:33:35PM +0900, Minchan Kim wrote: > Hi, > > On Wed, Mar 15, 2017 at 05:00:02PM +0800, Aaron Lu wrote: > > Introduce a workqueue for all the free workers so that user can fine > > tune how many workers can be active through sysfs interface: max_active. > > More workers

Re: [PATCH v2 3/5] mm: use a dedicated workqueue for the free workers

2017-03-22 Thread Aaron Lu
On Wed, Mar 22, 2017 at 03:33:35PM +0900, Minchan Kim wrote: > Hi, > > On Wed, Mar 15, 2017 at 05:00:02PM +0800, Aaron Lu wrote: > > Introduce a workqueue for all the free workers so that user can fine > > tune how many workers can be active through sysfs interface: max_active. > > More workers

Re: [PATCH v2 3/5] mm: use a dedicated workqueue for the free workers

2017-03-22 Thread Minchan Kim
Hi, On Wed, Mar 15, 2017 at 05:00:02PM +0800, Aaron Lu wrote: > Introduce a workqueue for all the free workers so that user can fine > tune how many workers can be active through sysfs interface: max_active. > More workers will normally lead to better performance, but too many can > cause severe

Re: [PATCH v2 3/5] mm: use a dedicated workqueue for the free workers

2017-03-22 Thread Minchan Kim
Hi, On Wed, Mar 15, 2017 at 05:00:02PM +0800, Aaron Lu wrote: > Introduce a workqueue for all the free workers so that user can fine > tune how many workers can be active through sysfs interface: max_active. > More workers will normally lead to better performance, but too many can > cause severe

[PATCH v2 3/5] mm: use a dedicated workqueue for the free workers

2017-03-15 Thread Aaron Lu
Introduce a workqueue for all the free workers so that user can fine tune how many workers can be active through sysfs interface: max_active. More workers will normally lead to better performance, but too many can cause severe lock contention. Note that since the zone lock is global, the

[PATCH v2 3/5] mm: use a dedicated workqueue for the free workers

2017-03-15 Thread Aaron Lu
Introduce a workqueue for all the free workers so that user can fine tune how many workers can be active through sysfs interface: max_active. More workers will normally lead to better performance, but too many can cause severe lock contention. Note that since the zone lock is global, the