Re: [PATCH v5 0/4] idle memory tracking

2015-06-07 Thread Raghavendra KT
On Tue, May 12, 2015 at 7:04 PM, Vladimir Davydov wrote: > Hi, > > This patch set introduces a new user API for tracking user memory pages > that have not been used for a given period of time. The purpose of this > is to provide the userspace with the means of tracking a workload's > working set,

Re: [PATCH v5 0/4] idle memory tracking

2015-06-07 Thread Raghavendra KT
On Tue, May 12, 2015 at 7:04 PM, Vladimir Davydov vdavy...@parallels.com wrote: Hi, This patch set introduces a new user API for tracking user memory pages that have not been used for a given period of time. The purpose of this is to provide the userspace with the means of tracking a

Re: [PATCH] cpusets: Make cpus_allowed and mems_allowed masks hotplug invariant

2014-10-08 Thread Raghavendra KT
On Wed, Oct 8, 2014 at 12:37 PM, Preeti U Murthy wrote: > There are two masks associated with cpusets. The cpus/mems_allowed > and effective_cpus/mems. On the legacy hierarchy both these masks > are consistent with each other. This is the intersection of their > value and the currently active

Re: [PATCH] cpusets: Make cpus_allowed and mems_allowed masks hotplug invariant

2014-10-08 Thread Raghavendra KT
On Wed, Oct 8, 2014 at 12:37 PM, Preeti U Murthy pre...@linux.vnet.ibm.com wrote: There are two masks associated with cpusets. The cpus/mems_allowed and effective_cpus/mems. On the legacy hierarchy both these masks are consistent with each other. This is the intersection of their value and the

Re: [patch] sched: signedness bug in yield_to()

2014-05-23 Thread Raghavendra KT
On Fri, May 23, 2014 at 3:50 PM, Dan Carpenter wrote: > yield_to() is supposed to return -ESRCH if there is no task to > yield to, but because the type is bool that is the same as returning > true. > > The only place I see which cares is kvm_vcpu_on_spin(). > > Signed-off-by: Dan Carpenter

Re: [patch] sched: signedness bug in yield_to()

2014-05-23 Thread Raghavendra KT
On Fri, May 23, 2014 at 3:50 PM, Dan Carpenter dan.carpen...@oracle.com wrote: yield_to() is supposed to return -ESRCH if there is no task to yield to, but because the type is bool that is the same as returning true. The only place I see which cares is kvm_vcpu_on_spin(). Signed-off-by: Dan

Re: [PATCHSET cgroup/for-3.15] cgroup: implement unified hierarchy

2014-05-05 Thread Raghavendra KT
On 5/2/14, Tejun Heo wrote: > Hello, > > On Wed, Apr 30, 2014 at 04:27:51PM +0530, Raghavendra KT wrote: [...] >> Because all the way along, though we have freedom to make the cpusets >> exclusive and move tasks (say VMs) into them, >> making sure they do not interf

Re: [PATCHSET cgroup/for-3.15] cgroup: implement unified hierarchy

2014-05-05 Thread Raghavendra KT
On 5/2/14, Tejun Heo t...@kernel.org wrote: Hello, On Wed, Apr 30, 2014 at 04:27:51PM +0530, Raghavendra KT wrote: [...] Because all the way along, though we have freedom to make the cpusets exclusive and move tasks (say VMs) into them, making sure they do not interfere with each other, we

Re: [PATCHSET cgroup/for-3.15] cgroup: implement unified hierarchy

2014-04-30 Thread Raghavendra KT
On Mon, Apr 14, 2014 at 11:22 PM, Tejun Heo wrote: >> How does this work for root's tasks now? Given that task can only be >> in leaf cgroups, that means tasks can't be in / cgroup (If one wants >> to create some cgroups). Does that mean / will be empty and init system >> need to setup things

Re: [PATCHSET cgroup/for-3.16] cgroup: implement unified hierarchy, v2

2014-04-30 Thread Raghavendra KT
On Tue, Apr 15, 2014 at 3:06 AM, Tejun Heo wrote: > Hello, > > This is v2 of the unified hierarchy patchset. Changes from v1[1] are, > > * Rebased on top of v3.15-rc1 > > * Interface file "cgroup.controllers" which was only available in the > root is now available in all cgroups. This allows,

Re: [PATCHSET cgroup/for-3.16] cgroup: implement unified hierarchy, v2

2014-04-30 Thread Raghavendra KT
On Tue, Apr 15, 2014 at 3:06 AM, Tejun Heo t...@kernel.org wrote: Hello, This is v2 of the unified hierarchy patchset. Changes from v1[1] are, * Rebased on top of v3.15-rc1 * Interface file cgroup.controllers which was only available in the root is now available in all cgroups. This

Re: [PATCHSET cgroup/for-3.15] cgroup: implement unified hierarchy

2014-04-30 Thread Raghavendra KT
On Mon, Apr 14, 2014 at 11:22 PM, Tejun Heo t...@kernel.org wrote: How does this work for root's tasks now? Given that task can only be in leaf cgroups, that means tasks can't be in / cgroup (If one wants to create some cgroups). Does that mean / will be empty and init system need to setup

Re: [PATCH 12/12] cgroup: implement dynamic subtree controller enable/disable on the default hierarchy

2014-04-17 Thread Raghavendra KT
On Tue, Apr 15, 2014 at 3:07 AM, Tejun Heo wrote: [...] > * White-space separated list of controller names prefixed with either > '+' or '-' can be written to "cgroup.subtree_control". The ones > prefixed with '+' are enabled on the controller and '-' disabled. > [...] > + > +/* change the

Re: [PATCH 12/12] cgroup: implement dynamic subtree controller enable/disable on the default hierarchy

2014-04-17 Thread Raghavendra KT
On Tue, Apr 15, 2014 at 3:07 AM, Tejun Heo t...@kernel.org wrote: [...] * White-space separated list of controller names prefixed with either '+' or '-' can be written to cgroup.subtree_control. The ones prefixed with '+' are enabled on the controller and '-' disabled. [...] + +/*

Re: Enhancement for PLE handler in KVM

2014-03-24 Thread Raghavendra KT
On Mon, Mar 3, 2014 at 11:54 PM, Li, Bin (Bin) wrote: > Hello, all. > > The PLE handler attempts to determine an alternate vCPU to schedule. In > some cases the wrong vCPU is scheduled and performance suffers. > > This patch allows for the guest OS to signal, using a hypercall, that it's >

Re: Enhancement for PLE handler in KVM

2014-03-24 Thread Raghavendra KT
On Mon, Mar 3, 2014 at 11:54 PM, Li, Bin (Bin) bin.bl...@alcatel-lucent.com wrote: Hello, all. The PLE handler attempts to determine an alternate vCPU to schedule. In some cases the wrong vCPU is scheduled and performance suffers. This patch allows for the guest OS to signal, using a

Re: [PATCH v2] powerpc ticket locks

2014-02-11 Thread Raghavendra KT
On Mon, Feb 10, 2014 at 8:40 AM, Benjamin Herrenschmidt wrote: > On Fri, 2014-02-07 at 17:58 +0100, Torsten Duwe wrote: >> typedef struct { >> - volatile unsigned int slock; >> -} arch_spinlock_t; >> + union { >> + __ticketpair_t head_tail; >> + struct

Re: [PATCH v2] powerpc ticket locks

2014-02-11 Thread Raghavendra KT
On Fri, Feb 7, 2014 at 10:28 PM, Torsten Duwe wrote: > Ticket locks for ppc, version 2. Changes since v1: > * The atomically exchanged entity is always 32 bits. > * asm inline string variations thus removed. > * Carry the additional holder hint only #if defined(CONFIG_PPC_SPLPAR) > >

Re: [PATCH v2] powerpc ticket locks

2014-02-11 Thread Raghavendra KT
On Fri, Feb 7, 2014 at 10:28 PM, Torsten Duwe d...@lst.de wrote: Ticket locks for ppc, version 2. Changes since v1: * The atomically exchanged entity is always 32 bits. * asm inline string variations thus removed. * Carry the additional holder hint only #if defined(CONFIG_PPC_SPLPAR)

Re: [PATCH v2] powerpc ticket locks

2014-02-11 Thread Raghavendra KT
On Mon, Feb 10, 2014 at 8:40 AM, Benjamin Herrenschmidt b...@kernel.crashing.org wrote: On Fri, 2014-02-07 at 17:58 +0100, Torsten Duwe wrote: typedef struct { - volatile unsigned int slock; -} arch_spinlock_t; + union { + __ticketpair_t head_tail; +

Re: [REGRESSION] jump label safety checks break automatic numa balancing

2013-10-08 Thread Raghavendra KT
On Fri, Oct 4, 2013 at 8:33 PM, Steven Rostedt wrote: CCing my IBM id > > > > Bisection identified this as the problem commit. > > > > 9c85f3bdf400665eecf62658a9106501f6a77a13 is the first bad commit > > commit 9c85f3bdf400665eecf62658a9106501f6a77a13 > > Author: Steven Rostedt > > Date: Thu

Re: [REGRESSION] jump label safety checks break automatic numa balancing

2013-10-08 Thread Raghavendra KT
On Fri, Oct 4, 2013 at 8:33 PM, Steven Rostedt rost...@goodmis.org wrote: CCing my IBM id Bisection identified this as the problem commit. 9c85f3bdf400665eecf62658a9106501f6a77a13 is the first bad commit commit 9c85f3bdf400665eecf62658a9106501f6a77a13 Author: Steven Rostedt

Re: [RESEND][PATCH] mm: vmstats: tlb flush counters

2013-07-19 Thread Raghavendra KT
On Wed, Jul 17, 2013 at 5:14 AM, Dave Hansen wrote: > > I was investigating some TLB flush scaling issues and realized > that we do not have any good methods for figuring out how many > TLB flushes we are doing. > > It would be nice to be able to do these in generic code, but the >

Re: [RESEND][PATCH] mm: vmstats: tlb flush counters

2013-07-19 Thread Raghavendra KT
On Wed, Jul 17, 2013 at 5:14 AM, Dave Hansen d...@sr71.net wrote: I was investigating some TLB flush scaling issues and realized that we do not have any good methods for figuring out how many TLB flushes we are doing. It would be nice to be able to do these in generic code, but the

Re: [PATCH RFC ticketlock] v3 Auto-queued ticketlock

2013-07-01 Thread Raghavendra KT
On Sun, Jun 23, 2013 at 11:23 PM, Raghavendra KT wrote: > > > On Wed, Jun 12, 2013 at 9:10 PM, Paul E. McKenney > wrote: >> >> Breaking up locks is better than implementing high-contention locks, but >> if we must have high-contention locks, why not make them a

Re: [PATCH RFC ticketlock] v3 Auto-queued ticketlock

2013-07-01 Thread Raghavendra KT
On Sun, Jun 23, 2013 at 11:23 PM, Raghavendra KT raghavendra.kt.li...@gmail.com wrote: On Wed, Jun 12, 2013 at 9:10 PM, Paul E. McKenney paul...@linux.vnet.ibm.com wrote: Breaking up locks is better than implementing high-contention locks, but if we must have high-contention locks, why

Re: sched: Fix signedness bug in yield_to()

2013-02-21 Thread Raghavendra KT
On Fri, Feb 22, 2013 at 4:56 AM, Marcelo Tosatti wrote: > On Thu, Feb 21, 2013 at 09:56:54AM +0100, Ingo Molnar wrote: >> >> * Shuah Khan wrote: >> >> > On Tue, Feb 19, 2013 at 7:27 PM, Linux Kernel Mailing List >> > wrote: >> > > Gitweb: >> > >

Re: sched: Fix signedness bug in yield_to()

2013-02-21 Thread Raghavendra KT
On Thu, Feb 21, 2013 at 2:26 PM, Ingo Molnar wrote: > > * Shuah Khan wrote: > >> On Tue, Feb 19, 2013 at 7:27 PM, Linux Kernel Mailing List >> wrote: >> > Gitweb: >> > http://git.kernel.org/linus/;a=commit;h=c3c186403c6abd32e719f005f0af950155a9e54d >> > Commit:

Re: sched: Fix signedness bug in yield_to()

2013-02-21 Thread Raghavendra KT
On Thu, Feb 21, 2013 at 2:26 PM, Ingo Molnar mi...@kernel.org wrote: * Shuah Khan shuahk...@gmail.com wrote: On Tue, Feb 19, 2013 at 7:27 PM, Linux Kernel Mailing List linux-kernel@vger.kernel.org wrote: Gitweb:

Re: sched: Fix signedness bug in yield_to()

2013-02-21 Thread Raghavendra KT
On Fri, Feb 22, 2013 at 4:56 AM, Marcelo Tosatti mtosa...@redhat.com wrote: On Thu, Feb 21, 2013 at 09:56:54AM +0100, Ingo Molnar wrote: * Shuah Khan shuahk...@gmail.com wrote: On Tue, Feb 19, 2013 at 7:27 PM, Linux Kernel Mailing List linux-kernel@vger.kernel.org wrote: Gitweb:

Re: [RFC PATCH 2/5] x86,smp: proportional backoff for ticket spinlocks

2013-01-03 Thread Raghavendra KT
[Ccing IBM id] On Thu, Jan 3, 2013 at 10:52 AM, Rik van Riel wrote: > Simple fixed value proportional backoff for ticket spinlocks. > By pounding on the cacheline with the spin lock less often, > bus traffic is reduced. In cases of a data structure with > embedded spinlock, the lock holder has a

Re: [RFC PATCH 0/5] x86,smp: make ticket spinlock proportional backoff w/ auto tuning

2013-01-03 Thread Raghavendra KT
[CCing my ibm id] On Thu, Jan 3, 2013 at 10:45 AM, Rik van Riel wrote: > Many spinlocks are embedded in data structures; having many CPUs > pounce on the cache line the lock is in will slow down the lock > holder, and can cause system performance to fall off a cliff. > > The paper "Non-scalable

Re: [RFC PATCH 0/5] x86,smp: make ticket spinlock proportional backoff w/ auto tuning

2013-01-03 Thread Raghavendra KT
[CCing my ibm id] On Thu, Jan 3, 2013 at 10:45 AM, Rik van Riel r...@redhat.com wrote: Many spinlocks are embedded in data structures; having many CPUs pounce on the cache line the lock is in will slow down the lock holder, and can cause system performance to fall off a cliff. The paper

Re: [RFC PATCH 2/5] x86,smp: proportional backoff for ticket spinlocks

2013-01-03 Thread Raghavendra KT
[Ccing IBM id] On Thu, Jan 3, 2013 at 10:52 AM, Rik van Riel r...@redhat.com wrote: Simple fixed value proportional backoff for ticket spinlocks. By pounding on the cacheline with the spin lock less often, bus traffic is reduced. In cases of a data structure with embedded spinlock, the lock