qemu-s390x
[Top][All Lists]
Advanced

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [PATCH v1 2/9] s390x: toplogy: adding drawers and books to smp parsi


From: Pierre Morel
Subject: Re: [PATCH v1 2/9] s390x: toplogy: adding drawers and books to smp parsing
Date: Fri, 16 Jul 2021 13:08:27 +0200
User-agent: Mozilla/5.0 (X11; Linux x86_64; rv:78.0) Gecko/20100101 Thunderbird/78.11.0



On 7/16/21 11:23 AM, Daniel P. Berrangé wrote:
On Thu, Jul 15, 2021 at 08:16:32AM +0200, Markus Armbruster wrote:
Pierre Morel <pmorel@linux.ibm.com> writes:

Drawers and Books are levels 4 and 3 of the S390 CPU
topology.
We allow the user to define these levels and we will
store the values inside the S390CcwMachineState.

Double-checking: are these members specific to S390?


Signed-off-by: Pierre Morel <pmorel@linux.ibm.com>
---

[...]

diff --git a/qapi/machine.json b/qapi/machine.json
index c3210ee1fb..98aff804c6 100644
--- a/qapi/machine.json
+++ b/qapi/machine.json
@@ -883,6 +883,8 @@
    ##
    # @CpuInstanceProperties:
    #
    # List of properties to be used for hotplugging a CPU instance,
    # it should be passed by management with device_add command when
    # a CPU is being hotplugged.
    #
    # @node-id: NUMA node ID the CPU belongs to
    # @socket-id: socket number within node/board the CPU belongs to

Missing: documentation for your new members.

It is also missing in qemu-options.hx which covers -smp

To quote the lscpu manpage, it seems drawer/book fit inbetween
NUMA node and socket level:

        CPU    The logical CPU number of a CPU as used by the Linux kernel.

        CORE   The logical core number.  A core can contain several CPUs.

        SOCKET The logical socket number.  A socket can contain several cores.

        BOOK   The logical book number.  A book can contain several sockets.

        DRAWER The logical drawer number.  A drawer can contain several books.

        NODE   The logical NUMA node number.  A node can contain several 
drawers.

Regards,
Daniel


Yes, seems I missed a fundamental change.
Will adapt this too.

--
Pierre Morel
IBM Lab Boeblingen



reply via email to

[Prev in Thread] Current Thread [Next in Thread]