From: Peter Xu <peterx@redhat.com>
To: huangy81@chinatelecom.cn
Cc: Eduardo Habkost <ehabkost@redhat.com>,
Juan Quintela <quintela@redhat.com>,
qemu-devel@nongnu.org,
"Dr. David Alan Gilbert" <dgilbert@redhat.com>,
Chuan Zheng <zhengchuan@huawei.com>,
Paolo Bonzini <pbonzini@redhat.com>
Subject: Re: [PATCH v7 6/7] migration/dirtyrate: move init step of calculation to main thread
Date: Thu, 17 Jun 2021 11:34:56 -0400 [thread overview]
Message-ID: <YMtroF40NYypccdg@t490s> (raw)
In-Reply-To: <deba8e91c23a20254f86e7cc1c0f24d19d64f98c.1623938622.git.huangy81@chinatelecom.cn>
On Thu, Jun 17, 2021 at 10:12:07PM +0800, huangy81@chinatelecom.cn wrote:
> From: Hyman Huang(黄勇) <huangy81@chinatelecom.cn>
>
> since main thread may "query dirty rate" at any time, it's better
> to move init step into main thead so that synchronization overhead
> between "main" and "get_dirtyrate" can be reduced.
>
> Signed-off-by: Hyman Huang(黄勇) <huangy81@chinatelecom.cn>
> ---
> migration/dirtyrate.c | 23 +++++++++++++++++++----
> 1 file changed, 19 insertions(+), 4 deletions(-)
>
> diff --git a/migration/dirtyrate.c b/migration/dirtyrate.c
> index a9bdd60..8a9dcf7 100644
> --- a/migration/dirtyrate.c
> +++ b/migration/dirtyrate.c
> @@ -26,6 +26,7 @@
>
> static int CalculatingState = DIRTY_RATE_STATUS_UNSTARTED;
> static struct DirtyRateStat DirtyStat;
> +static DirtyRateMeasureMode dirtyrate_mode = DIRTY_RATE_MEASURE_MODE_NONE;
>
> static int64_t set_sample_page_period(int64_t msec, int64_t initial_time)
> {
> @@ -111,6 +112,11 @@ static void init_dirtyrate_stat(int64_t start_time,
> }
> }
>
> +static void cleanup_dirtyrate_stat(struct DirtyRateConfig config)
> +{
> + /* TODO */
> +}
> +
> static void update_dirtyrate_stat(struct RamblockDirtyInfo *info)
> {
> DirtyStat.page_sampling.total_dirty_samples += info->sample_dirty_count;
> @@ -380,7 +386,6 @@ void *get_dirtyrate_thread(void *arg)
> {
> struct DirtyRateConfig config = *(struct DirtyRateConfig *)arg;
> int ret;
> - int64_t start_time;
> rcu_register_thread();
>
> ret = dirtyrate_set_state(&CalculatingState, DIRTY_RATE_STATUS_UNSTARTED,
> @@ -390,9 +395,6 @@ void *get_dirtyrate_thread(void *arg)
> return NULL;
> }
>
> - start_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME) / 1000;
> - init_dirtyrate_stat(start_time, config);
> -
> calculate_dirtyrate(config);
>
> ret = dirtyrate_set_state(&CalculatingState, DIRTY_RATE_STATUS_MEASURING,
> @@ -411,6 +413,7 @@ void qmp_calc_dirty_rate(int64_t calc_time, bool has_sample_pages,
> static struct DirtyRateConfig config;
> QemuThread thread;
> int ret;
> + int64_t start_time;
>
> /*
> * If the dirty rate is already being measured, don't attempt to start.
> @@ -451,6 +454,18 @@ void qmp_calc_dirty_rate(int64_t calc_time, bool has_sample_pages,
> config.sample_period_seconds = calc_time;
> config.sample_pages_per_gigabytes = sample_pages;
> config.mode = DIRTY_RATE_MEASURE_MODE_PAGE_SAMPLING;
> +
> + cleanup_dirtyrate_stat(config);
This line should ideally be moved into the next patch, as sampling itself
doesn't need it.
> +
> + /*
> + * update dirty rate mode so that we can figure out what mode has
> + * been used in last calculation
> + **/
> + dirtyrate_mode = DIRTY_RATE_MEASURE_MODE_PAGE_SAMPLING;
This line is odd. Would page sampling broken if without this line? We need to
make sure each commit keeps the old way working..
Thanks,
> +
> + start_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME) / 1000;
> + init_dirtyrate_stat(start_time, config);
> +
> qemu_thread_create(&thread, "get_dirtyrate", get_dirtyrate_thread,
> (void *)&config, QEMU_THREAD_DETACHED);
> }
> --
> 1.8.3.1
>
--
Peter Xu
next prev parent reply other threads:[~2021-06-17 15:36 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-06-17 14:12 [PATCH v7 0/7] support dirtyrate at the granualrity of vcpu huangy81
2021-06-17 14:12 ` [PATCH v7 1/7] KVM: introduce dirty_pages and kvm_dirty_ring_enabled huangy81
2021-06-17 14:12 ` [PATCH v7 2/7] memory: rename global_dirty_log to global_dirty_tracking huangy81
2021-06-17 14:12 ` [PATCH v7 3/7] memory: make global_dirty_tracking a bitmask huangy81
2021-06-17 15:29 ` Peter Xu
2021-06-18 0:36 ` Hyman Huang
2021-06-18 0:50 ` Hyman Huang
2021-06-17 14:12 ` [PATCH v7 4/7] migration/dirtyrate: introduce struct and adjust DirtyRateStat huangy81
2021-06-17 15:27 ` Peter Xu
2021-06-18 0:35 ` Hyman Huang
2021-06-17 14:12 ` [PATCH v7 5/7] migration/dirtyrate: adjust order of registering thread huangy81
2021-06-17 14:12 ` [PATCH v7 6/7] migration/dirtyrate: move init step of calculation to main thread huangy81
2021-06-17 15:34 ` Peter Xu [this message]
2021-06-18 1:16 ` Hyman Huang
2021-06-17 14:12 ` [PATCH v7 7/7] migration/dirtyrate: implement dirty-ring dirtyrate calculation huangy81
2021-06-17 15:41 ` 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=YMtroF40NYypccdg@t490s \
--to=peterx@redhat.com \
--cc=dgilbert@redhat.com \
--cc=ehabkost@redhat.com \
--cc=huangy81@chinatelecom.cn \
--cc=pbonzini@redhat.com \
--cc=qemu-devel@nongnu.org \
--cc=quintela@redhat.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;
as well as URLs for NNTP newsgroup(s).