mbox series

[v2,00/48] xen: add core scheduling support

Message ID 20190809145833.1020-1-jgross@suse.com (mailing list archive)
Headers show
Series xen: add core scheduling support | expand

Message

Jürgen Groß Aug. 9, 2019, 2:57 p.m. UTC
Add support for core- and socket-scheduling in the Xen hypervisor.

Via boot parameter sched-gran=core (or sched-gran=socket)
it is possible to change the scheduling granularity from cpu (the
default) to either whole cores or even sockets.

All logical cpus (threads) of the core or socket are always scheduled
together. This means that on a core always vcpus of the same domain
will be active, and those vcpus will always be scheduled at the same
time.

This is achieved by switching the scheduler to no longer see vcpus as
the primary object to schedule, but "schedule units". Each schedule
unit consists of as many vcpus as each core has threads on the current
system. The vcpu->unit relation is fixed.

I have done some very basic performance testing: on a 4 cpu system
(2 cores with 2 threads each) I did a "make -j 4" for building the Xen
hypervisor. With This test has been run on dom0, once with no other
guest active and once with another guest with 4 vcpus running the same
test. The results are (always elapsed time, system time, user time):

sched-gran=cpu,    no other guest: 116.10 177.65 207.84
sched-gran=core,   no other guest: 114.04 175.47 207.45
sched-gran=cpu,    other guest:    202.30 334.21 384.63
sched-gran=core,   other guest:    207.24 293.04 371.37

The performance tests have been performed with credit2, the other
schedulers are tested only briefly to be able to create a domain in a
cpupool.

Cpupools have been moderately tested (cpu add/remove, create, destroy,
move domain).

Cpu on-/offlining has been moderately tested, too.

The series is based on the series:
"xen/sched: use new idle scheduler for free cpus"
which has been split off from V1.

The complete patch series is available under:

  git://github.com/jgross1/xen/ sched-v2

Changes in V2:
- comments addressed
- some patches merged into one
- idle scheduler related patches split off to own series
- some patches are already applied
- some bugs fixed (e.g. crashes when powering off)

Changes in V1:
- cpupools are working now
- cpu on-/offlining working now
- all schedulers working now
- renamed "items" to "units"
- introduction of "idle scheduler"
- several new patches (see individual patches, mostly splits of
  former patches or cpupool and cpu on-/offlining support)
- all review comments addressed
- some minor changes (see individual patches)

Changes in RFC V2:
- ARM is building now
- HVM domains are working now
- idling will always be done with idle_vcpu active
- other small changes see individual patches

Juergen Gross (48):
  xen/sched: use new sched_unit instead of vcpu in scheduler interfaces
  xen/sched: move per-vcpu scheduler private data pointer to sched_unit
  xen/sched: build a linked list of struct sched_unit
  xen/sched: introduce struct sched_resource
  xen/sched: let pick_cpu return a scheduler resource
  xen/sched: switch schedule_data.curr to point at sched_unit
  xen/sched: move per cpu scheduler private data into struct
    sched_resource
  xen/sched: switch vcpu_schedule_lock to unit_schedule_lock
  xen/sched: move some per-vcpu items to struct sched_unit
  xen/sched: add scheduler helpers hiding vcpu
  xen/sched: rename scheduler related perf counters
  xen/sched: switch struct task_slice from vcpu to sched_unit
  xen/sched: add is_running indicator to struct sched_unit
  xen/sched: make null scheduler vcpu agnostic.
  xen/sched: make rt scheduler vcpu agnostic.
  xen/sched: make credit scheduler vcpu agnostic.
  xen/sched: make credit2 scheduler vcpu agnostic.
  xen/sched: make arinc653 scheduler vcpu agnostic.
  xen: add sched_unit_pause_nosync() and sched_unit_unpause()
  xen: let vcpu_create() select processor
  xen/sched: use sched_resource cpu instead smp_processor_id in
    schedulers
  xen/sched: switch schedule() from vcpus to sched_units
  xen/sched: switch sched_move_irqs() to take sched_unit as parameter
  xen: switch from for_each_vcpu() to for_each_sched_unit()
  xen/sched: add runstate counters to struct sched_unit
  xen/sched: rework and rename vcpu_force_reschedule()
  xen/sched: Change vcpu_migrate_*() to operate on schedule unit
  xen/sched: move struct task_slice into struct sched_unit
  xen/sched: add code to sync scheduling of all vcpus of a sched unit
  xen/sched: introduce unit_runnable_state()
  xen/sched: add support for multiple vcpus per sched unit where missing
  xen/sched: modify cpupool_domain_cpumask() to be an unit mask
  xen/sched: support allocating multiple vcpus into one sched unit
  xen/sched: add a percpu resource index
  xen/sched: add fall back to idle vcpu when scheduling unit
  xen/sched: make vcpu_wake() and vcpu_sleep() core scheduling aware
  xen/sched: carve out freeing sched_unit memory into dedicated function
  xen/sched: move per-cpu variable scheduler to struct sched_resource
  xen/sched: move per-cpu variable cpupool to struct sched_resource
  xen/sched: reject switching smt on/off with core scheduling active
  xen/sched: prepare per-cpupool scheduling granularity
  xen/sched: split schedule_cpu_switch()
  xen/sched: protect scheduling resource via rcu
  xen/sched: support multiple cpus per scheduling resource
  xen/sched: support differing granularity in schedule_cpu_[add/rm]()
  xen/sched: support core scheduling for moving cpus to/from cpupools
  xen/sched: disable scheduling when entering ACPI deep sleep states
  xen/sched: add scheduling granularity enum

 xen/arch/arm/domain.c             |    2 +-
 xen/arch/arm/domain_build.c       |   13 +-
 xen/arch/x86/Kconfig              |    1 +
 xen/arch/x86/acpi/cpu_idle.c      |    1 -
 xen/arch/x86/acpi/power.c         |    4 +
 xen/arch/x86/cpu/mcheck/mce.c     |    1 -
 xen/arch/x86/cpu/mcheck/mctelem.c |    1 -
 xen/arch/x86/dom0_build.c         |   10 +-
 xen/arch/x86/domain.c             |   26 +-
 xen/arch/x86/hvm/dom0_build.c     |    9 +-
 xen/arch/x86/pv/dom0_build.c      |   10 +-
 xen/arch/x86/pv/shim.c            |    4 +-
 xen/arch/x86/setup.c              |    1 -
 xen/arch/x86/smpboot.c            |    1 -
 xen/arch/x86/sysctl.c             |    5 +
 xen/common/Kconfig                |    3 +
 xen/common/cpupool.c              |  157 +++-
 xen/common/domain.c               |   35 +-
 xen/common/domctl.c               |   23 +-
 xen/common/keyhandler.c           |   58 +-
 xen/common/sched_arinc653.c       |  256 +++--
 xen/common/sched_credit.c         |  760 +++++++--------
 xen/common/sched_credit2.c        | 1119 +++++++++++-----------
 xen/common/sched_null.c           |  466 +++++-----
 xen/common/sched_rt.c             |  543 +++++------
 xen/common/schedule.c             | 1851 +++++++++++++++++++++++++++++--------
 xen/common/softirq.c              |    6 +-
 xen/include/asm-arm/current.h     |    1 +
 xen/include/asm-x86/cpuidle.h     |   11 -
 xen/include/asm-x86/current.h     |   19 +-
 xen/include/asm-x86/dom0_build.h  |    3 +-
 xen/include/asm-x86/smp.h         |    3 +
 xen/include/xen/domain.h          |    3 +-
 xen/include/xen/perfc_defn.h      |   32 +-
 xen/include/xen/sched-if.h        |  340 +++++--
 xen/include/xen/sched.h           |   93 +-
 xen/include/xen/softirq.h         |    1 +
 37 files changed, 3675 insertions(+), 2197 deletions(-)

Comments

Sergey Dyasli Aug. 15, 2019, 10:17 a.m. UTC | #1
Hi Juergen,

The latest round of testing revealed the following 3 Xen crashes:

1. vcpu_sleep_sync() <-- vlapic_init_sipi_action()
This was seen multiple times. It tends to happen on large Windows Server
VMs (>= 12 vCPUs).
https://paste.debian.net/1095844/

2. vcpu_sleep_sync() <-- vcpu_set_periodic_timer() <-- pv_hypercall()
This was seen on Sles 11.4 PV VM with 32 vCPUs and 6GB RAM
https://paste.debian.net/1095843/

3. ACPI S5: schedule.c#sched_slave()
This one was during shutdown again.
https://paste.debian.net/1095845/

There also were a number of Dom0 soft-lockups (together with RCU stalls)
but unfortunately our crashdump tool was a bit broken so full Dom0 kernel
logs were not captured this time.

And CentOS 5.11 suspend regression (as reported previously) is still
present.

Thanks,
Sergey
Jürgen Groß Sept. 5, 2019, 6:22 a.m. UTC | #2
Hi Sergey,

On 15.08.19 12:17, Sergey Dyasli wrote:
> Hi Juergen,
> 
> The latest round of testing revealed the following 3 Xen crashes:
> 
> 1. vcpu_sleep_sync() <-- vlapic_init_sipi_action()
> This was seen multiple times. It tends to happen on large Windows Server
> VMs (>= 12 vCPUs).
> https://paste.debian.net/1095844/
> 
> 2. vcpu_sleep_sync() <-- vcpu_set_periodic_timer() <-- pv_hypercall()
> This was seen on Sles 11.4 PV VM with 32 vCPUs and 6GB RAM
> https://paste.debian.net/1095843/
> 
> 3. ACPI S5: schedule.c#sched_slave()
> This one was during shutdown again.
> https://paste.debian.net/1095845/
> 
> There also were a number of Dom0 soft-lockups (together with RCU stalls)
> but unfortunately our crashdump tool was a bit broken so full Dom0 kernel
> logs were not captured this time.
> 
> And CentOS 5.11 suspend regression (as reported previously) is still
> present.

I have found one bug in the v->is_running setting, which might be
related to your observed hangs, but I couldn't verify that.

I have rebased my series with the is_running fix to current staging. You
can find that under

git://github.com/jgross1/xen/ sched-v2b-2019-09-05

This branch includes the needed prerequisite series ("xen/sched: use new 
idle scheduler for free cpus"), and some additional debug enhancements
I'd like you to use:

- my series for debugtrace enhancements
- my series for lock-profiling enhancements
- and as the last patch some debugtrace hooks in the scheduler

Please make sure to have CONFIG_DEBUG_TRACE and
CONFIG_DEBUG_LOCK_PROFILE set when building the hypervisor.

When testing please add:

async-show-all=on watchdog=on debugtrace=cpu:16

to the hypervisor boot parameters. This should add a lot of additional
output in case of a crash, which will (hopefully) help to find the
reason(s) for hangs and crashes.


Juergen