Quan Xu
2017-Nov-13 10:47 UTC
[PATCH RFC v3 4/6] Documentation: Add three sysctls for smart idle poll
From: Quan Xu <quan.xu0 at gmail.com>
To reduce the cost of poll, we introduce three sysctl to control the
poll time when running as a virtual machine with paravirt.
Signed-off-by: Yang Zhang <yang.zhang.wz at gmail.com>
Signed-off-by: Quan Xu <quan.xu0 at gmail.com>
---
Documentation/sysctl/kernel.txt | 35 +++++++++++++++++++++++++++++++++++
arch/x86/kernel/paravirt.c | 4 ++++
include/linux/kernel.h | 6 ++++++
kernel/sysctl.c | 34 ++++++++++++++++++++++++++++++++++
4 files changed, 79 insertions(+), 0 deletions(-)
diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index 694968c..30c25fb 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -714,6 +714,41 @@ kernel tries to allocate a number starting from this one.
=============================================================
+paravirt_poll_grow: (X86 only)
+
+Multiplied value to increase the poll time. This is expected to take
+effect only when running as a virtual machine with CONFIG_PARAVIRT
+enabled. This can't bring any benifit on bare mental even with
+CONFIG_PARAVIRT enabled.
+
+By default this value is 2. Possible values to set are in range {2..16}.
+
+=============================================================+
+paravirt_poll_shrink: (X86 only)
+
+Divided value to reduce the poll time. This is expected to take effect
+only when running as a virtual machine with CONFIG_PARAVIRT enabled.
+This can't bring any benifit on bare mental even with CONFIG_PARAVIRT
+enabled.
+
+By default this value is 2. Possible values to set are in range {2..16}.
+
+=============================================================+
+paravirt_poll_threshold_ns: (X86 only)
+
+Controls the maximum poll time before entering real idle path. This is
+expected to take effect only when running as a virtual machine with
+CONFIG_PARAVIRT enabled. This can't bring any benifit on bare mental
+even with CONFIG_PARAVIRT enabled.
+
+By default, this value is 0 means not to poll. Possible values to set
+are in range {0..500000}. Change the value to non-zero if running
+latency-bound workloads in a virtual machine.
+
+=============================================================+
powersave-nap: (PPC only)
If set, Linux-PPC will use the 'nap' mode of powersaving,
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 67cab22..28c74ca 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -317,6 +317,10 @@ struct pv_idle_ops pv_idle_ops = {
.poll = paravirt_nop,
};
+unsigned long paravirt_poll_threshold_ns;
+unsigned int paravirt_poll_shrink = 2;
+unsigned int paravirt_poll_grow = 2;
+
__visible struct pv_irq_ops pv_irq_ops = {
.save_fl = __PV_IS_CALLEE_SAVE(native_save_fl),
.restore_fl = __PV_IS_CALLEE_SAVE(native_restore_fl),
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 4b484ab..0f46846 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -491,6 +491,12 @@ extern __scanf(2, 0)
extern bool crash_kexec_post_notifiers;
+#ifdef CONFIG_PARAVIRT
+extern unsigned long paravirt_poll_threshold_ns;
+extern unsigned int paravirt_poll_shrink;
+extern unsigned int paravirt_poll_grow;
+#endif
+
/*
* panic_cpu is used for synchronizing panic() and crash_kexec() execution. It
* holds a CPU number which is executing panic() currently. A value of
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index d9c31bc..9f194dc 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -135,6 +135,11 @@
static int six_hundred_forty_kb = 640 * 1024;
#endif
+#ifdef CONFIG_PARAVIRT
+static int sixteen = 16;
+static int five_hundred_thousand = 500000;
+#endif
+
/* this is needed for the proc_doulongvec_minmax of vm_dirty_bytes */
static unsigned long dirty_bytes_min = 2 * PAGE_SIZE;
@@ -1226,6 +1231,35 @@ static int sysrq_sysctl_handler(struct ctl_table *table,
int write,
.extra2 = &one,
},
#endif
+#ifdef CONFIG_PARAVIRT
+ {
+ .procname = "paravirt_halt_poll_threshold",
+ .data = ¶virt_poll_threshold_ns,
+ .maxlen = sizeof(unsigned long),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
+ .extra2 = &five_hundred_thousand,
+ },
+ {
+ .procname = "paravirt_halt_poll_grow",
+ .data = ¶virt_poll_grow,
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &two,
+ .extra2 = &sixteen,
+ },
+ {
+ .procname = "paravirt_halt_poll_shrink",
+ .data = ¶virt_poll_shrink,
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &two,
+ .extra2 = &sixteen,
+ },
+#endif
{ }
};
--
1.7.1
Ingo Molnar
2017-Nov-13 15:08 UTC
[PATCH RFC v3 4/6] Documentation: Add three sysctls for smart idle poll
* Quan Xu <quan.xu04 at gmail.com> wrote:> From: Quan Xu <quan.xu0 at gmail.com> > > To reduce the cost of poll, we introduce three sysctl to control the > poll time when running as a virtual machine with paravirt. > > Signed-off-by: Yang Zhang <yang.zhang.wz at gmail.com> > Signed-off-by: Quan Xu <quan.xu0 at gmail.com> > --- > Documentation/sysctl/kernel.txt | 35 +++++++++++++++++++++++++++++++++++ > arch/x86/kernel/paravirt.c | 4 ++++ > include/linux/kernel.h | 6 ++++++ > kernel/sysctl.c | 34 ++++++++++++++++++++++++++++++++++ > 4 files changed, 79 insertions(+), 0 deletions(-) > > diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt > index 694968c..30c25fb 100644 > --- a/Documentation/sysctl/kernel.txt > +++ b/Documentation/sysctl/kernel.txt > @@ -714,6 +714,41 @@ kernel tries to allocate a number starting from this one. > > =============================================================> > +paravirt_poll_grow: (X86 only) > + > +Multiplied value to increase the poll time. This is expected to take > +effect only when running as a virtual machine with CONFIG_PARAVIRT > +enabled. This can't bring any benifit on bare mental even with > +CONFIG_PARAVIRT enabled. > + > +By default this value is 2. Possible values to set are in range {2..16}. > + > +=============================================================> + > +paravirt_poll_shrink: (X86 only) > + > +Divided value to reduce the poll time. This is expected to take effect > +only when running as a virtual machine with CONFIG_PARAVIRT enabled. > +This can't bring any benifit on bare mental even with CONFIG_PARAVIRT > +enabled. > + > +By default this value is 2. Possible values to set are in range {2..16}. > + > +=============================================================> + > +paravirt_poll_threshold_ns: (X86 only) > + > +Controls the maximum poll time before entering real idle path. This is > +expected to take effect only when running as a virtual machine with > +CONFIG_PARAVIRT enabled. This can't bring any benifit on bare mental > +even with CONFIG_PARAVIRT enabled. > + > +By default, this value is 0 means not to poll. Possible values to set > +are in range {0..500000}. Change the value to non-zero if running > +latency-bound workloads in a virtual machine.I absolutely hate it how this hybrid idle loop polling mechanism is not self-tuning! Please make it all work fine by default, and automatically so, instead of adding three random parameters... And if it cannot be done automatically then we should rather not do it at all. Maybe the next submitter of a similar feature can think of a better approach. Thanks, Ingo
Wanpeng Li
2017-Nov-13 21:44 UTC
[PATCH RFC v3 4/6] Documentation: Add three sysctls for smart idle poll
Hi Ingo,
On 11/13/17 11:08 PM, Ingo Molnar wrote:
* Quan Xu <quan.xu04 at gmail.com><mailto:quan.xu04 at gmail.com>
wrote:
From: Quan Xu <quan.xu0 at gmail.com><mailto:quan.xu0 at gmail.com>
To reduce the cost of poll, we introduce three sysctl to control the
poll time when running as a virtual machine with paravirt.
Signed-off-by: Yang Zhang <yang.zhang.wz at
gmail.com><mailto:yang.zhang.wz at gmail.com>
Signed-off-by: Quan Xu <quan.xu0 at gmail.com><mailto:quan.xu0 at
gmail.com>
---
Documentation/sysctl/kernel.txt | 35 +++++++++++++++++++++++++++++++++++
arch/x86/kernel/paravirt.c | 4 ++++
include/linux/kernel.h | 6 ++++++
kernel/sysctl.c | 34 ++++++++++++++++++++++++++++++++++
4 files changed, 79 insertions(+), 0 deletions(-)
diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index 694968c..30c25fb 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -714,6 +714,41 @@ kernel tries to allocate a number starting from this one.
=============================================================
+paravirt_poll_grow: (X86 only)
+
+Multiplied value to increase the poll time. This is expected to take
+effect only when running as a virtual machine with CONFIG_PARAVIRT
+enabled. This can't bring any benifit on bare mental even with
+CONFIG_PARAVIRT enabled.
+
+By default this value is 2. Possible values to set are in range {2..16}.
+
+=============================================================+
+paravirt_poll_shrink: (X86 only)
+
+Divided value to reduce the poll time. This is expected to take effect
+only when running as a virtual machine with CONFIG_PARAVIRT enabled.
+This can't bring any benifit on bare mental even with CONFIG_PARAVIRT
+enabled.
+
+By default this value is 2. Possible values to set are in range {2..16}.
+
+=============================================================+
+paravirt_poll_threshold_ns: (X86 only)
+
+Controls the maximum poll time before entering real idle path. This is
+expected to take effect only when running as a virtual machine with
+CONFIG_PARAVIRT enabled. This can't bring any benifit on bare mental
+even with CONFIG_PARAVIRT enabled.
+
+By default, this value is 0 means not to poll. Possible values to set
+are in range {0..500000}. Change the value to non-zero if running
+latency-bound workloads in a virtual machine.
I absolutely hate it how this hybrid idle loop polling mechanism is not
self-tuning!
Please make it all work fine by default, and automatically so, instead of adding
three random parameters...
And if it cannot be done automatically then we should rather not do it at all.
One of the main benefit of this patchset is the customers who use the VM can
tune the mechanism by themself. I remember Andi also has the concern about two
much random parameters. In addition, there is a "Adaptive
halt-polling" which are merged to upstream more than two years ago in kvm
which is self-tuning, https://lkml.org/lkml/2015/9/3/615
Regards,
Wanpeng Li
-------------- next part --------------
An HTML attachment was scrubbed...
URL:
<http://lists.linuxfoundation.org/pipermail/virtualization/attachments/20171113/10fd7006/attachment-0001.html>
Quan Xu
2017-Nov-14 04:05 UTC
[PATCH RFC v3 4/6] Documentation: Add three sysctls for smart idle poll
On 2017/11/13 23:08, Ingo Molnar wrote:> * Quan Xu <quan.xu04 at gmail.com> wrote: > >> From: Quan Xu <quan.xu0 at gmail.com> >> >> To reduce the cost of poll, we introduce three sysctl to control the >> poll time when running as a virtual machine with paravirt. >> >> Signed-off-by: Yang Zhang <yang.zhang.wz at gmail.com> >> Signed-off-by: Quan Xu <quan.xu0 at gmail.com> >> --- >> Documentation/sysctl/kernel.txt | 35 +++++++++++++++++++++++++++++++++++ >> arch/x86/kernel/paravirt.c | 4 ++++ >> include/linux/kernel.h | 6 ++++++ >> kernel/sysctl.c | 34 ++++++++++++++++++++++++++++++++++ >> 4 files changed, 79 insertions(+), 0 deletions(-) >> >> diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt >> index 694968c..30c25fb 100644 >> --- a/Documentation/sysctl/kernel.txt >> +++ b/Documentation/sysctl/kernel.txt >> @@ -714,6 +714,41 @@ kernel tries to allocate a number starting from this one. >> >> =============================================================>> >> +paravirt_poll_grow: (X86 only) >> + >> +Multiplied value to increase the poll time. This is expected to take >> +effect only when running as a virtual machine with CONFIG_PARAVIRT >> +enabled. This can't bring any benifit on bare mental even with >> +CONFIG_PARAVIRT enabled. >> + >> +By default this value is 2. Possible values to set are in range {2..16}. >> + >> +=============================================================>> + >> +paravirt_poll_shrink: (X86 only) >> + >> +Divided value to reduce the poll time. This is expected to take effect >> +only when running as a virtual machine with CONFIG_PARAVIRT enabled. >> +This can't bring any benifit on bare mental even with CONFIG_PARAVIRT >> +enabled. >> + >> +By default this value is 2. Possible values to set are in range {2..16}. >> + >> +=============================================================>> + >> +paravirt_poll_threshold_ns: (X86 only) >> + >> +Controls the maximum poll time before entering real idle path. This is >> +expected to take effect only when running as a virtual machine with >> +CONFIG_PARAVIRT enabled. This can't bring any benifit on bare mental >> +even with CONFIG_PARAVIRT enabled. >> + >> +By default, this value is 0 means not to poll. Possible values to set >> +are in range {0..500000}. Change the value to non-zero if running >> +latency-bound workloads in a virtual machine. > I absolutely hate it how this hybrid idle loop polling mechanism is not > self-tuning!Ingo, actually it is self-tuning..> Please make it all work fine by default, and automatically so, instead of adding > three random parameters..... I will make it all fine by default. howerver cloud environment is of diversity, could I only leave paravirt_poll_threshold_ns parameter (the maximum poll time), which is as similar as "adaptive halt-polling" Wanpeng mentioned.. then user can turn it off, or find an appropriate threshold for some odd scenario.. thanks for your comments!! Quan Alibaba Cloud> And if it cannot be done automatically then we should rather not do it at all. > Maybe the next submitter of a similar feature can think of a better approach. > > Thanks, > > Ingo >
Possibly Parallel Threads
- [PATCH RFC v3 4/6] Documentation: Add three sysctls for smart idle poll
- [PATCH RFC v3 4/6] Documentation: Add three sysctls for smart idle poll
- [PATCH RFC v3 4/6] Documentation: Add three sysctls for smart idle poll
- [PATCH RFC v3 4/6] Documentation: Add three sysctls for smart idle poll
- [PATCH RFC v3 4/6] Documentation: Add three sysctls for smart idle poll