From: Juan Quintela <quintela@redhat.com>
To: qemu-devel@nongnu.org, Fiona Ebner <f.ebner@proxmox.com>
Cc: qemu-block@nongnu.org, Leonardo Bras <leobras@redhat.com>,
Hailiang Zhang <zhanghailiang@xfusion.com>,
Peter Xu <peterx@redhat.com>, Fam Zheng <fam@euphon.net>,
Stefan Hajnoczi <stefanha@redhat.com>
Subject: Re: [PATCH 00/16] Next round of migration atomic counters
Date: Tue, 30 May 2023 14:40:56 +0200 [thread overview]
Message-ID: <87fs7evvon.fsf@secure.mitica> (raw)
In-Reply-To: <20230530122813.2674-1-quintela@redhat.com> (Juan Quintela's message of "Tue, 30 May 2023 14:27:57 +0200")
Juan Quintela <quintela@redhat.com> wrote:
> Hi
Hi
Fiona, I forgot to put your on the CC'd list. This series should reget
the speed problem that you find.
Later, Juan.
> On this series:
>
> - Make sure that qemu_file_transferred() make sense and its used
> coherently
>
> - Use stat64 for qemu_file_transferred(), so we can call the function
> from any thread.
>
> - Don't account for the same transfer twice (i.e. it is multifd_bytes,
> rdma_bytes or qemu_file_bytes) qemu_file_transferred() just sums all
> of them.
>
> - Use this new counter for rate_limit()
>
> - Remove old trasferred stat64 (now we use the real thing)
>
> - Simplify qemu_file_get_error(): see where next cleanups are coming
>
> - As an example, qemu_fflush() now return errors.
>
> Please review.
>
> Later, Juan.
>
> Based-on: Message-Id: <20230530115429.1998-1-quintela@redhat.com>
> Subject: [PULL 00/21] Migration 20230530 patches
>
> Juan Quintela (16):
> qemu-file: Rename qemu_file_transferred_ fast -> noflush
> migration: Change qemu_file_transferred to noflush
> migration: Use qemu_file_transferred_noflush() for block migration.
> qemu-file: Don't call qemu_fflush() for read only files
> qemu-file: We only call qemu_file_transferred_* on the sending side
> qemu_file: Use a stat64 for qemu_file_transferred
> qemu_file: total_transferred is not used anymore
> migration: Use the number of transferred bytes directly
> qemu_file: Remove unused qemu_file_transferred()
> qemu-file: Remove _noflush from qemu_file_transferred_noflush()
> migration: migration_transferred_bytes() don't need the QEMUFile
> migration: migration_rate_limit_reset() don't need the QEMUFile
> qemu-file: Simplify qemu_file_get_error()
> migration: Use migration_transferred_bytes()
> migration: Remove transferred atomic counter
> qemu-file: Make qemu_fflush() return errors
>
> migration/migration-stats.h | 16 ++++++----------
> migration/qemu-file.h | 29 +++++------------------------
> migration/colo.c | 11 +++--------
> migration/migration-stats.c | 10 +++++-----
> migration/migration.c | 17 ++++++-----------
> migration/multifd.c | 3 ---
> migration/qemu-file.c | 35 ++++++++++++++---------------------
> migration/ram.c | 29 ++++++++++-------------------
> migration/rdma.c | 4 +---
> migration/savevm.c | 7 +++----
> migration/vmstate.c | 4 ++--
> 11 files changed, 55 insertions(+), 110 deletions(-)
prev parent reply other threads:[~2023-05-30 12:43 UTC|newest]
Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-05-30 12:27 [PATCH 00/16] Next round of migration atomic counters Juan Quintela
2023-05-30 12:27 ` [PATCH 01/16] qemu-file: Rename qemu_file_transferred_ fast -> noflush Juan Quintela
2023-05-30 12:36 ` Philippe Mathieu-Daudé
2023-05-30 12:39 ` Philippe Mathieu-Daudé
2023-05-30 12:27 ` [PATCH 02/16] migration: Change qemu_file_transferred to noflush Juan Quintela
2023-05-30 12:37 ` Philippe Mathieu-Daudé
2023-05-30 12:28 ` [PATCH 03/16] migration: Use qemu_file_transferred_noflush() for block migration Juan Quintela
2023-05-30 13:45 ` Fabiano Rosas
2023-05-30 12:28 ` [PATCH 04/16] qemu-file: Don't call qemu_fflush() for read only files Juan Quintela
2023-05-30 14:06 ` Fabiano Rosas
2023-05-30 17:01 ` Richard Henderson
2023-05-30 17:06 ` Juan Quintela
2023-05-30 17:14 ` Richard Henderson
2023-05-30 17:26 ` Juan Quintela
2023-05-30 17:36 ` Juan Quintela
2023-05-30 12:28 ` [PATCH 05/16] qemu-file: We only call qemu_file_transferred_* on the sending side Juan Quintela
2023-05-30 12:28 ` [PATCH 06/16] qemu_file: Use a stat64 for qemu_file_transferred Juan Quintela
2023-05-30 12:28 ` [PATCH 07/16] qemu_file: total_transferred is not used anymore Juan Quintela
2023-05-30 12:28 ` [PATCH 08/16] migration: Use the number of transferred bytes directly Juan Quintela
2023-05-30 12:28 ` [PATCH 09/16] qemu_file: Remove unused qemu_file_transferred() Juan Quintela
2023-05-30 12:28 ` [PATCH 10/16] qemu-file: Remove _noflush from qemu_file_transferred_noflush() Juan Quintela
2023-05-30 13:10 ` Fabiano Rosas
2023-05-30 17:57 ` Juan Quintela
2023-05-30 12:28 ` [PATCH 11/16] migration: migration_transferred_bytes() don't need the QEMUFile Juan Quintela
2023-05-30 12:34 ` Philippe Mathieu-Daudé
2023-05-30 12:28 ` [PATCH 12/16] migration: migration_rate_limit_reset() " Juan Quintela
2023-05-30 12:34 ` Philippe Mathieu-Daudé
2023-05-30 12:28 ` [PATCH 13/16] qemu-file: Simplify qemu_file_get_error() Juan Quintela
2023-05-30 13:41 ` Fabiano Rosas
2023-05-30 12:28 ` [PATCH 14/16] migration: Use migration_transferred_bytes() Juan Quintela
2023-05-30 12:28 ` [PATCH 15/16] migration: Remove transferred atomic counter Juan Quintela
2023-05-30 12:28 ` [PATCH 16/16] qemu-file: Make qemu_fflush() return errors Juan Quintela
2023-05-30 12:41 ` Philippe Mathieu-Daudé
2023-05-30 12:40 ` Juan Quintela [this message]
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=87fs7evvon.fsf@secure.mitica \
--to=quintela@redhat.com \
--cc=f.ebner@proxmox.com \
--cc=fam@euphon.net \
--cc=leobras@redhat.com \
--cc=peterx@redhat.com \
--cc=qemu-block@nongnu.org \
--cc=qemu-devel@nongnu.org \
--cc=stefanha@redhat.com \
--cc=zhanghailiang@xfusion.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;
as well as URLs for NNTP newsgroup(s).