From: Peter Xu <peterx@redhat.com>
To: Fabiano Rosas <farosas@suse.de>
Cc: qemu-devel@nongnu.org, berrange@redhat.com, armbru@redhat.com,
Claudio Fontana <cfontana@suse.de>
Subject: Re: [PATCH v4 00/34] migration: File based migration with multifd and fixed-ram
Date: Fri, 23 Feb 2024 10:59:50 +0800 [thread overview]
Message-ID: <ZdgKJgxUqb1DrzRt@x1n> (raw)
In-Reply-To: <20240220224138.24759-1-farosas@suse.de>
On Tue, Feb 20, 2024 at 07:41:04PM -0300, Fabiano Rosas wrote:
> Latest numbers
> ==============
>
> => guest: 128 GB RAM - 120 GB dirty - 1 vcpu in tight loop dirtying memory
> => host: 128 CPU AMD EPYC 7543 - 2 NVMe disks in RAID0 (8586 MiB/s) - xfs
> => pinned vcpus w/ NUMA shortest distances - average of 3 runs - results
> from query-migrate
>
> non-live | time (ms) pages/s mb/s MB/s
> -------------------+-----------------------------------
> file | 110512 256258 9549 1193
> + bg-snapshot | 245660 119581 4303 537
Is this the one using userfault? I'm surprised it's much slower when
enabled; logically for a non-live snapshot it should take similar loops
like a normal migration as it should have zero faults, then it should be
similar performance.
> -------------------+-----------------------------------
> fixed-ram | 157975 216877 6672 834
> + multifd 8 ch. | 95922 292178 10982 1372
> + direct-io | 23268 1936897 45330 5666
> -------------------------------------------------------
>
> live | time (ms) pages/s mb/s MB/s
> -------------------+-----------------------------------
> file | - - - - (file grew 4x the VM size)
> + bg-snapshot | 357635 141747 2974 371
> -------------------+-----------------------------------
> fixed-ram | - - - - (no convergence in 5 min)
> + multifd 8 ch. | 230812 497551 14900 1862
> + direct-io | 27475 1788025 46736 5842
> -------------------------------------------------------
Also surprised on direct-io too.. that is definitely something tremendous.
--
Peter Xu
next prev parent reply other threads:[~2024-02-23 3:00 UTC|newest]
Thread overview: 79+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-02-20 22:41 [PATCH v4 00/34] migration: File based migration with multifd and fixed-ram Fabiano Rosas
2024-02-20 22:41 ` [PATCH v4 01/34] docs/devel/migration.rst: Document the file transport Fabiano Rosas
2024-02-23 3:01 ` Peter Xu
2024-02-20 22:41 ` [PATCH v4 02/34] tests/qtest/migration: Rename fd_proto test Fabiano Rosas
2024-02-23 3:03 ` Peter Xu
2024-02-20 22:41 ` [PATCH v4 03/34] tests/qtest/migration: Add a fd + file test Fabiano Rosas
2024-02-23 3:08 ` Peter Xu
2024-02-20 22:41 ` [PATCH v4 04/34] migration/multifd: Remove p->quit from recv side Fabiano Rosas
2024-02-23 3:13 ` Peter Xu
2024-02-20 22:41 ` [PATCH v4 05/34] migration/multifd: Release recv sem_sync earlier Fabiano Rosas
2024-02-23 3:16 ` Peter Xu
2024-02-20 22:41 ` [PATCH v4 06/34] io: add and implement QIO_CHANNEL_FEATURE_SEEKABLE for channel file Fabiano Rosas
2024-02-20 22:41 ` [PATCH v4 07/34] io: Add generic pwritev/preadv interface Fabiano Rosas
2024-02-20 22:41 ` [PATCH v4 08/34] io: implement io_pwritev/preadv for QIOChannelFile Fabiano Rosas
2024-02-20 22:41 ` [PATCH v4 09/34] io: fsync before closing a file channel Fabiano Rosas
2024-02-20 22:41 ` [PATCH v4 10/34] migration/qemu-file: add utility methods for working with seekable channels Fabiano Rosas
2024-02-20 22:41 ` [PATCH v4 11/34] migration/ram: Introduce 'fixed-ram' migration capability Fabiano Rosas
2024-02-21 8:41 ` Markus Armbruster
2024-02-21 13:24 ` Fabiano Rosas
2024-02-21 13:50 ` Daniel P. Berrangé
2024-02-21 15:05 ` Fabiano Rosas
2024-02-26 3:07 ` Peter Xu
2024-02-26 3:22 ` Peter Xu
2024-02-20 22:41 ` [PATCH v4 12/34] migration: Add fixed-ram URI compatibility check Fabiano Rosas
2024-02-26 3:11 ` Peter Xu
2024-02-20 22:41 ` [PATCH v4 13/34] migration/ram: Add outgoing 'fixed-ram' migration Fabiano Rosas
2024-02-26 4:03 ` Peter Xu
2024-02-20 22:41 ` [PATCH v4 14/34] migration/ram: Add incoming " Fabiano Rosas
2024-02-26 5:19 ` Peter Xu
2024-02-20 22:41 ` [PATCH v4 15/34] tests/qtest/migration: Add tests for fixed-ram file-based migration Fabiano Rosas
2024-02-20 22:41 ` [PATCH v4 16/34] migration/multifd: Rename MultiFDSend|RecvParams::data to compress_data Fabiano Rosas
2024-02-20 22:41 ` [PATCH v4 17/34] migration/multifd: Decouple recv method from pages Fabiano Rosas
2024-02-20 22:41 ` [PATCH v4 18/34] migration/multifd: Allow multifd without packets Fabiano Rosas
2024-02-26 5:57 ` Peter Xu
2024-02-20 22:41 ` [PATCH v4 19/34] migration/multifd: Allow receiving pages " Fabiano Rosas
2024-02-26 6:58 ` Peter Xu
2024-02-26 19:19 ` Fabiano Rosas
2024-02-26 20:54 ` Fabiano Rosas
2024-02-20 22:41 ` [PATCH v4 20/34] migration/multifd: Add outgoing QIOChannelFile support Fabiano Rosas
2024-02-26 7:10 ` Peter Xu
2024-02-26 7:21 ` Peter Xu
2024-02-20 22:41 ` [PATCH v4 21/34] migration/multifd: Add incoming " Fabiano Rosas
2024-02-26 7:34 ` Peter Xu
2024-02-26 7:53 ` Peter Xu
2024-02-20 22:41 ` [PATCH v4 22/34] migration/multifd: Prepare multifd sync for fixed-ram migration Fabiano Rosas
2024-02-26 7:47 ` Peter Xu
2024-02-26 22:52 ` Fabiano Rosas
2024-02-27 3:52 ` Peter Xu
2024-02-27 14:00 ` Fabiano Rosas
2024-02-27 23:46 ` Peter Xu
2024-02-20 22:41 ` [PATCH v4 23/34] migration/multifd: Support outgoing fixed-ram stream format Fabiano Rosas
2024-02-26 8:08 ` Peter Xu
2024-02-20 22:41 ` [PATCH v4 24/34] migration/multifd: Support incoming " Fabiano Rosas
2024-02-26 8:30 ` Peter Xu
2024-02-20 22:41 ` [PATCH v4 25/34] migration/multifd: Add fixed-ram support to fd: URI Fabiano Rosas
2024-02-26 8:37 ` Peter Xu
2024-02-20 22:41 ` [PATCH v4 26/34] tests/qtest/migration: Add a multifd + fixed-ram migration test Fabiano Rosas
2024-02-26 8:42 ` Peter Xu
2024-02-20 22:41 ` [PATCH v4 27/34] migration: Add direct-io parameter Fabiano Rosas
2024-02-21 9:17 ` Markus Armbruster
2024-02-26 8:50 ` Peter Xu
2024-02-26 13:28 ` Fabiano Rosas
2024-02-20 22:41 ` [PATCH v4 28/34] migration/multifd: Add direct-io support Fabiano Rosas
2024-02-20 22:41 ` [PATCH v4 29/34] tests/qtest/migration: Add tests for file migration with direct-io Fabiano Rosas
2024-02-20 22:41 ` [PATCH v4 30/34] monitor: Honor QMP request for fd removal immediately Fabiano Rosas
2024-02-21 9:20 ` Markus Armbruster
2024-02-20 22:41 ` [PATCH v4 31/34] monitor: Extract fdset fd flags comparison into a function Fabiano Rosas
2024-02-20 22:41 ` [PATCH v4 32/34] monitor: fdset: Match against O_DIRECT Fabiano Rosas
2024-02-21 9:27 ` Markus Armbruster
2024-02-21 13:37 ` Fabiano Rosas
2024-02-22 6:56 ` Markus Armbruster
2024-02-22 13:26 ` Fabiano Rosas
2024-02-22 14:44 ` Markus Armbruster
2024-02-20 22:41 ` [PATCH v4 33/34] migration: Add support for fdset with multifd + file Fabiano Rosas
2024-02-20 22:41 ` [PATCH v4 34/34] tests/qtest/migration: Add a test for fixed-ram with passing of fds Fabiano Rosas
2024-02-23 2:59 ` Peter Xu [this message]
2024-02-23 13:48 ` [PATCH v4 00/34] migration: File based migration with multifd and fixed-ram Claudio Fontana
2024-02-23 14:22 ` Fabiano Rosas
2024-02-26 6:15 ` Peter Xu
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=ZdgKJgxUqb1DrzRt@x1n \
--to=peterx@redhat.com \
--cc=armbru@redhat.com \
--cc=berrange@redhat.com \
--cc=cfontana@suse.de \
--cc=farosas@suse.de \
--cc=qemu-devel@nongnu.org \
/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;
as well as URLs for NNTP newsgroup(s).