lkml.org 
[lkml]   [2019]   [Sep]   [18]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
    /
    From
    SubjectRe: [PATCH 0/2] pseries/hotplug: Change the default behaviour of cede_offline
    Date
    "Gautham R. Shenoy" <ego@linux.vnet.ibm.com> writes:
    > From: "Gautham R. Shenoy" <ego@linux.vnet.ibm.com>
    >
    > Currently on Pseries Linux Guests, the offlined CPU can be put to one
    > of the following two states:
    > - Long term processor cede (also called extended cede)
    > - Returned to the Hypervisor via RTAS "stop-self" call.
    >
    > This is controlled by the kernel boot parameter "cede_offline=on/off".
    >
    > By default the offlined CPUs enter extended cede.

    Since commit 3aa565f53c39 ("powerpc/pseries: Add hooks to put the CPU into an appropriate offline state") (Nov 2009)

    Which you wrote :)

    Why was that wrong?

    > The PHYP hypervisor considers CPUs in extended cede to be "active"
    > since the CPUs are still under the control fo the Linux Guests. Hence, when we change the
    > SMT modes by offlining the secondary CPUs, the PURR and the RWMR SPRs
    > will continue to count the values for offlined CPUs in extended cede
    > as if they are online.
    >
    > One of the expectations with PURR is that the for an interval of time,
    > the sum of the PURR increments across the online CPUs of a core should
    > equal the number of timebase ticks for that interval.
    >
    > This is currently not the case.

    But why does that matter? It's just some accounting stuff, does it
    actually break something meaningful?

    Also what does this do to the latency of CPU online/offline.
    And what does this do on KVM?


    > In the following data (Generated using
    > https://github.com/gautshen/misc/blob/master/purr_tb.py):
    >
    >
    > delta tb = tb ticks elapsed in 1 second.
    > delta purr = sum of PURR increments on online CPUs of that core in 1
    > second
    >
    > SMT=off
    > ===========================================
    > Core delta tb(apprx) delta purr
    > ===========================================
    > core00 [ 0] 512000000 69883784
    > core01 [ 8] 512000000 88782536
    > core02 [ 16] 512000000 94296824
    > core03 [ 24] 512000000 80951968

    Showing the expected value in another column would make this much
    clearer.

    cheers


    > SMT=2
    > ===========================================
    > Core delta tb(apprx) delta purr
    > ===========================================
    > core00 [ 0,1] 512000000 136147792
    > core01 [ 8,9] 512000000 128636784
    > core02 [ 16,17] 512000000 135426488
    > core03 [ 24,25] 512000000 153027520
    >
    > SMT=4
    > ===================================================
    > Core delta tb(apprx) delta purr
    > ===================================================
    > core00 [ 0,1,2,3] 512000000 258331616
    > core01 [ 8,9,10,11] 512000000 274220072
    > core02 [ 16,17,18,19] 512000000 260013736
    > core03 [ 24,25,26,27] 512000000 260079672
    >
    > SMT=on
    > ===================================================================
    > Core delta tb(apprx) delta purr
    > ===================================================================
    > core00 [ 0,1,2,3,4,5,6,7] 512000000 512941248
    > core01 [ 8,9,10,11,12,13,14,15] 512000000 512936544
    > core02 [ 16,17,18,19,20,21,22,23] 512000000 512931544
    > core03 [ 24,25,26,27,28,29,30,31] 512000000 512923800
    >
    > This patchset addresses this issue by ensuring that by default, the
    > offlined CPUs are returned to the Hypervisor via RTAS "stop-self" call
    > by changing the default value of "cede_offline_enabled" to false.
    >
    > The patchset also defines a new sysfs attribute
    > "/sys/device/system/cpu/cede_offline_enabled" on PSeries Linux guests
    > to allow userspace programs to change the state into which the
    > offlined CPU need to be put to at runtime. This is intended for
    > userspace programs that fold CPUs for the purpose of saving energy
    > when the utilization is low. Setting the value of this attribute
    > ensures that subsequent CPU offline operations will put the offlined
    > CPUs to extended cede. However, it will cause inconsistencies in the
    > PURR accounting. Clearing the attribute will make the offlined CPUs
    > call the RTAS "stop-self" call thereby returning the CPU to the
    > hypervisor.
    >
    > With the patches,
    >
    > SMT=off
    > ===========================================
    > Core delta tb(apprx) delta purr
    > ===========================================
    > core00 [ 0] 512000000 512527568
    > core01 [ 8] 512000000 512556128
    > core02 [ 16] 512000000 512590016
    > core03 [ 24] 512000000 512589440
    >
    > SMT=2
    > ===========================================
    > Core delta tb(apprx) delta purr
    > ===========================================
    > core00 [ 0,1] 512000000 512635328
    > core01 [ 8,9] 512000000 512610416
    > core02 [ 16,17] 512000000 512639360
    > core03 [ 24,25] 512000000 512638720
    >
    > SMT=4
    > ===================================================
    > Core delta tb(apprx) delta purr
    > ===================================================
    > core00 [ 0,1,2,3] 512000000 512757328
    > core01 [ 8,9,10,11] 512000000 512727920
    > core02 [ 16,17,18,19] 512000000 512754712
    > core03 [ 24,25,26,27] 512000000 512739040
    >
    > SMT=on
    > ==============================================================
    > Core delta tb(apprx) delta purr
    > ==============================================================
    > core00 [ 0,1,2,3,4,5,6,7] 512000000 512920936
    > core01 [ 8,9,10,11,12,13,14,15] 512000000 512878728
    > core02 [ 16,17,18,19,20,21,22,23] 512000000 512921192
    > core03 [ 24,25,26,27,28,29,30,31] 512000000 512924816
    >
    > Gautham R. Shenoy (2):
    > pseries/hotplug-cpu: Change default behaviour of cede_offline to "off"
    > pseries/hotplug-cpu: Add sysfs attribute for cede_offline
    >
    > Documentation/ABI/testing/sysfs-devices-system-cpu | 14 ++++
    > Documentation/core-api/cpu_hotplug.rst | 2 +-
    > arch/powerpc/platforms/pseries/hotplug-cpu.c | 80 ++++++++++++++++++++--
    > 3 files changed, 88 insertions(+), 8 deletions(-)
    >
    > --
    > 1.9.4

    \
     
     \ /
      Last update: 2019-09-18 07:14    [W:2.998 / U:0.008 seconds]
    ©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site