From: Markus Armbruster <armbru@redhat.com>
To: Gonglei <arei.gonglei@huawei.com>
Cc: <qemu-devel@nongnu.org>, <peterx@redhat.com>,
<yu.zhang@ionos.com>, <mgalaxy@akamai.com>,
<elmar.gerdes@ionos.com>, <zhengchuan@huawei.com>,
<berrange@redhat.com>, <armbru@redhat.com>,
<lizhijian@fujitsu.com>, <pbonzini@redhat.com>,
<mst@redhat.com>, <xiexiangyou@huawei.com>,
<linux-rdma@vger.kernel.org>, <lixiao91@huawei.com>,
<jinpu.wang@ionos.com>, Jialin Wang <wangjialin23@huawei.com>
Subject: Re: [PATCH 1/6] migration: remove RDMA live migration temporarily
Date: Mon, 10 Jun 2024 13:45:35 +0200 [thread overview]
Message-ID: <878qzdqaw0.fsf@pond.sub.org> (raw)
In-Reply-To: <1717503252-51884-2-git-send-email-arei.gonglei@huawei.com> (Gonglei's message of "Tue, 4 Jun 2024 20:14:07 +0800")
Gonglei <arei.gonglei@huawei.com> writes:
> From: Jialin Wang <wangjialin23@huawei.com>
>
> The new RDMA live migration will be introduced in the upcoming
> few commits.
>
> Signed-off-by: Jialin Wang <wangjialin23@huawei.com>
> Signed-off-by: Gonglei <arei.gonglei@huawei.com>
[...]
> diff --git a/qapi/migration.json b/qapi/migration.json
> index a351fd3714..4d7d49bfec 100644
> --- a/qapi/migration.json
> +++ b/qapi/migration.json
> @@ -210,9 +210,9 @@
> #
> # @setup-time: amount of setup time in milliseconds *before* the
> # iterations begin but *after* the QMP command is issued. This is
> -# designed to provide an accounting of any activities (such as
> -# RDMA pinning) which may be expensive, but do not actually occur
> -# during the iterative migration rounds themselves. (since 1.6)
> +# designed to provide an accounting of any activities which may be
> +# expensive, but do not actually occur during the iterative migration
> +# rounds themselves. (since 1.6)
I guess the new RDMA migration code will not do RDMA pinning. Correct?
> #
> # @cpu-throttle-percentage: percentage of time guest cpus are being
> # throttled during auto-converge. This is only present when
> @@ -378,10 +378,6 @@
> # for certain work loads, by sending compressed difference of the
> # pages
> #
> -# @rdma-pin-all: Controls whether or not the entire VM memory
> -# footprint is mlock()'d on demand or all at once. Refer to
> -# docs/rdma.txt for usage. Disabled by default. (since 2.0)
> -#
> # @zero-blocks: During storage migration encode blocks of zeroes
> # efficiently. This essentially saves 1MB of zeroes per block on
> # the wire. Enabling requires source and target VM to support
> @@ -476,7 +472,7 @@
> # Since: 1.2
> ##
> { 'enum': 'MigrationCapability',
> - 'data': ['xbzrle', 'rdma-pin-all', 'auto-converge', 'zero-blocks',
> + 'data': ['xbzrle', 'auto-converge', 'zero-blocks',
> 'events', 'postcopy-ram',
> { 'name': 'x-colo', 'features': [ 'unstable' ] },
> 'release-ram',
I guess you remove @rdma-pin-all, because it makes no sense with the new
migration code. However, this is an incompatible change.
Here's the orderly way to remove it:
1. Document it doesn't do anything anymore, and deprecate it.
2. Remove after the deprecation grace period (two releases, see
docs/about/deprecated.rst.
> @@ -533,7 +529,6 @@
> # -> { "execute": "query-migrate-capabilities" }
> # <- { "return": [
> # {"state": false, "capability": "xbzrle"},
> -# {"state": false, "capability": "rdma-pin-all"},
> # {"state": false, "capability": "auto-converge"},
> # {"state": false, "capability": "zero-blocks"},
> # {"state": true, "capability": "events"},
[...]
next prev parent reply other threads:[~2024-06-10 11:45 UTC|newest]
Thread overview: 55+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-06-04 12:14 [PATCH 0/6] refactor RDMA live migration based on rsocket API Gonglei
2024-06-04 12:14 ` [PATCH 1/6] migration: remove RDMA live migration temporarily Gonglei
2024-06-04 14:01 ` David Hildenbrand
2024-06-05 10:02 ` Gonglei (Arei)
2024-06-10 11:45 ` Markus Armbruster [this message]
2024-06-04 12:14 ` [PATCH 2/6] io: add QIOChannelRDMA class Gonglei
2024-06-10 6:54 ` Jinpu Wang
2024-06-04 12:14 ` [PATCH 3/6] io/channel-rdma: support working in coroutine Gonglei
2024-06-06 13:34 ` Haris Iqbal
2024-06-07 8:45 ` Gonglei (Arei)
2024-06-07 10:01 ` Haris Iqbal
2024-06-07 9:04 ` Daniel P. Berrangé
2024-06-07 9:28 ` Gonglei (Arei)
2024-06-04 12:14 ` [PATCH 4/6] tests/unit: add test-io-channel-rdma.c Gonglei
2024-06-04 12:14 ` [PATCH 5/6] migration: introduce new RDMA live migration Gonglei
2024-06-04 12:14 ` [PATCH 6/6] migration/rdma: support multifd for RDMA migration Gonglei
2024-06-04 19:32 ` [PATCH 0/6] refactor RDMA live migration based on rsocket API Peter Xu
2024-06-05 10:09 ` Gonglei (Arei)
2024-06-05 14:18 ` Peter Xu
2024-06-07 8:49 ` Gonglei (Arei)
2024-06-10 16:35 ` Peter Xu
2024-06-07 10:06 ` Daniel P. Berrangé
2024-06-05 7:57 ` Michael S. Tsirkin
2024-06-05 10:00 ` Gonglei (Arei)
2024-06-05 10:23 ` Michael S. Tsirkin
2024-06-06 11:31 ` Leon Romanovsky
2024-06-07 1:04 ` Zhijian Li (Fujitsu)
2024-06-07 16:24 ` Yu Zhang
2024-06-07 5:53 ` Jinpu Wang
2024-06-07 8:28 ` Gonglei (Arei)
2024-06-10 16:31 ` Peter Xu
2024-08-27 20:15 ` Peter Xu
2024-08-27 20:57 ` Michael S. Tsirkin
2024-09-22 19:29 ` Michael Galaxy
2024-09-23 1:04 ` Gonglei (Arei)
2024-09-25 15:08 ` Peter Xu
2024-09-27 21:45 ` Sean Hefty
2024-09-28 17:52 ` Michael Galaxy
2024-09-29 18:14 ` Michael S. Tsirkin
2024-09-29 20:26 ` Michael Galaxy
2024-09-29 22:26 ` Michael S. Tsirkin
2024-09-30 15:00 ` Michael Galaxy
2024-09-30 15:31 ` Yu Zhang
2024-09-30 18:16 ` Peter Xu
2024-09-30 19:20 ` Sean Hefty
2024-09-30 19:47 ` Peter Xu
2024-10-03 21:26 ` Michael Galaxy
2024-10-03 21:43 ` Peter Xu
2024-10-04 14:04 ` Michael Galaxy
2024-10-07 8:47 ` Yu Zhang
2024-10-07 13:45 ` Michael Galaxy
2024-10-07 18:15 ` Leon Romanovsky
2024-10-08 9:31 ` Zhu Yanjun
2024-10-23 13:42 ` Michael Galaxy
2024-09-27 20:34 ` Michael Galaxy
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=878qzdqaw0.fsf@pond.sub.org \
--to=armbru@redhat.com \
--cc=arei.gonglei@huawei.com \
--cc=berrange@redhat.com \
--cc=elmar.gerdes@ionos.com \
--cc=jinpu.wang@ionos.com \
--cc=linux-rdma@vger.kernel.org \
--cc=lixiao91@huawei.com \
--cc=lizhijian@fujitsu.com \
--cc=mgalaxy@akamai.com \
--cc=mst@redhat.com \
--cc=pbonzini@redhat.com \
--cc=peterx@redhat.com \
--cc=qemu-devel@nongnu.org \
--cc=wangjialin23@huawei.com \
--cc=xiexiangyou@huawei.com \
--cc=yu.zhang@ionos.com \
--cc=zhengchuan@huawei.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox