All of lore.kernel.org
 help / color / mirror / Atom feed
From: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
To: Peter Xu <peterx@redhat.com>
Cc: Chuan Zheng <zhengchuan@huawei.com>,
	Leonardo Bras Soares Passos <lsoaresp@redhat.com>,
	huangy81@chinatelecom.cn, qemu-devel@nongnu.org,
	Juan Quintela <quintela@redhat.com>
Subject: Re: [PATCH] hmp: Add "calc_dirty_rate" and "info dirty_rate" cmds
Date: Tue, 8 Jun 2021 19:49:56 +0100	[thread overview]
Message-ID: <YL+71C9cteDVYJum@work-vm> (raw)
In-Reply-To: <20210601005708.189888-1-peterx@redhat.com>

* Peter Xu (peterx@redhat.com) wrote:
> These two commands are missing when adding the QMP sister commands.  Add them,
> so developers can play with them easier.
> 
> Cc: Dr. David Alan Gilbert <dgilbert@redhat.com>
> Cc: Juan Quintela <quintela@redhat.com>
> Cc: Leonardo Bras Soares Passos <lsoaresp@redhat.com>
> Cc: Chuan Zheng <zhengchuan@huawei.com>
> Cc: huangy81@chinatelecom.cn
> Signed-off-by: Peter Xu <peterx@redhat.com>

Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>

> ---
> PS: I really doubt whether this is working as expected... I ran one 200MB/s
> workload inside, what I measured is 20MB/s with current algorithm...  Sampling
> 512 pages out of 1G mem is not wise enough I guess, especially that assumes
> dirty workload is spread across the memories while it's normally not the case..

What size of address space did you dirty - was it 20MB?

Dave

> ---
>  hmp-commands-info.hx  | 13 +++++++++++++
>  hmp-commands.hx       | 14 ++++++++++++++
>  include/monitor/hmp.h |  2 ++
>  migration/dirtyrate.c | 43 +++++++++++++++++++++++++++++++++++++++++++
>  4 files changed, 72 insertions(+)
> 
> diff --git a/hmp-commands-info.hx b/hmp-commands-info.hx
> index ab0c7aa5eea..f8a9141dd8a 100644
> --- a/hmp-commands-info.hx
> +++ b/hmp-commands-info.hx
> @@ -880,3 +880,16 @@ SRST
>    ``info replay``
>      Display the record/replay information: mode and the current icount.
>  ERST
> +
> +    {
> +        .name       = "dirty_rate",
> +        .args_type  = "",
> +        .params     = "",
> +        .help       = "show dirty rate information",
> +        .cmd        = hmp_info_dirty_rate,
> +    },
> +
> +SRST
> +  ``info dirty_rate``
> +    Display the vcpu dirty rate information.
> +ERST
> diff --git a/hmp-commands.hx b/hmp-commands.hx
> index 2d21fe5ad42..4c27fb91f7d 100644
> --- a/hmp-commands.hx
> +++ b/hmp-commands.hx
> @@ -1727,3 +1727,17 @@ ERST
>          .flags      = "p",
>      },
>  
> +SRST
> +``calc_dirty_rate`` *second*
> +  Start a round of dirty rate measurement with the period specified in *second*.
> +  The result of the dirty rate measurement may be observed with ``info
> +  dirty_rate`` command.
> +ERST
> +
> +    {
> +        .name       = "calc_dirty_rate",
> +        .args_type  = "second:l",
> +        .params     = "second",
> +        .help       = "start a round of guest dirty rate measurement",
> +        .cmd        = hmp_calc_dirty_rate,
> +    },
> diff --git a/include/monitor/hmp.h b/include/monitor/hmp.h
> index 605d57287ae..3baa1058e2c 100644
> --- a/include/monitor/hmp.h
> +++ b/include/monitor/hmp.h
> @@ -129,5 +129,7 @@ void hmp_info_replay(Monitor *mon, const QDict *qdict);
>  void hmp_replay_break(Monitor *mon, const QDict *qdict);
>  void hmp_replay_delete_break(Monitor *mon, const QDict *qdict);
>  void hmp_replay_seek(Monitor *mon, const QDict *qdict);
> +void hmp_info_dirty_rate(Monitor *mon, const QDict *qdict);
> +void hmp_calc_dirty_rate(Monitor *mon, const QDict *qdict);
>  
>  #endif
> diff --git a/migration/dirtyrate.c b/migration/dirtyrate.c
> index ccb98147e89..382287d2912 100644
> --- a/migration/dirtyrate.c
> +++ b/migration/dirtyrate.c
> @@ -20,6 +20,9 @@
>  #include "ram.h"
>  #include "trace.h"
>  #include "dirtyrate.h"
> +#include "monitor/hmp.h"
> +#include "monitor/monitor.h"
> +#include "qapi/qmp/qdict.h"
>  
>  static int CalculatingState = DIRTY_RATE_STATUS_UNSTARTED;
>  static struct DirtyRateStat DirtyStat;
> @@ -424,3 +427,43 @@ struct DirtyRateInfo *qmp_query_dirty_rate(Error **errp)
>  {
>      return query_dirty_rate_info();
>  }
> +
> +void hmp_info_dirty_rate(Monitor *mon, const QDict *qdict)
> +{
> +    DirtyRateInfo *info = query_dirty_rate_info();
> +
> +    monitor_printf(mon, "Status: %s\n",
> +                   DirtyRateStatus_str(info->status));
> +    monitor_printf(mon, "Start Time: %"PRIi64" (ms)\n",
> +                   info->start_time);
> +    monitor_printf(mon, "Period: %"PRIi64" (sec)\n",
> +                   info->calc_time);
> +    monitor_printf(mon, "Dirty rate: ");
> +    if (info->has_dirty_rate) {
> +        monitor_printf(mon, "%"PRIi64" (MB/s)\n", info->dirty_rate);
> +    } else {
> +        monitor_printf(mon, "(not ready)\n");
> +    }
> +    g_free(info);
> +}
> +
> +void hmp_calc_dirty_rate(Monitor *mon, const QDict *qdict)
> +{
> +    int64_t sec = qdict_get_try_int(qdict, "second", 0);
> +    Error *err = NULL;
> +
> +    if (!sec) {
> +        monitor_printf(mon, "Incorrect period length specified!\n");
> +        return;
> +    }
> +
> +    qmp_calc_dirty_rate(sec, &err);
> +    if (err) {
> +        hmp_handle_error(mon, err);
> +        return;
> +    }
> +
> +    monitor_printf(mon, "Starting dirty rate measurement with period %"PRIi64
> +                   " seconds\n", sec);
> +    monitor_printf(mon, "[Please use 'info dirty_rate' to check results]\n");
> +}
> -- 
> 2.31.1
> 
-- 
Dr. David Alan Gilbert / dgilbert@redhat.com / Manchester, UK



  parent reply	other threads:[~2021-06-08 18:52 UTC|newest]

Thread overview: 7+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-06-01  0:57 [PATCH] hmp: Add "calc_dirty_rate" and "info dirty_rate" cmds Peter Xu
2021-06-01 14:08 ` Hyman
2021-06-01 14:36   ` Peter Xu
2021-06-08 18:49 ` Dr. David Alan Gilbert [this message]
2021-06-08 19:19   ` Peter Xu
2021-06-08 19:36     ` Dr. David Alan Gilbert
2021-06-09 18:57       ` 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=YL+71C9cteDVYJum@work-vm \
    --to=dgilbert@redhat.com \
    --cc=huangy81@chinatelecom.cn \
    --cc=lsoaresp@redhat.com \
    --cc=peterx@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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.