[Top][All Lists]
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [Qemu-devel] [PATCH] stop the iteration when too many pages is trans
From: |
Anthony Liguori |
Subject: |
Re: [Qemu-devel] [PATCH] stop the iteration when too many pages is transferred |
Date: |
Fri, 19 Nov 2010 20:23:55 -0600 |
User-agent: |
Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9.1.15) Gecko/20101027 Lightning/1.0b1 Thunderbird/3.0.10 |
On 11/17/2010 08:32 PM, Wen Congyang wrote:
> When the total sent page size is larger than max_factor
> times of the size of guest OS's memory, stop the
> iteration.
> The default value of max_factor is 3.
>
> This is similar to XEN.
>
>
> Signed-off-by: Wen Congyang
>
I'm strongly opposed to doing this. I think Xen gets this totally wrong.
Migration is a contract. When you set the stop time, you're saying that
you want only want the guest to experience a fixed amount of downtime.
Stopping the guest after some arbitrary number of iterations makes the
downtime non-deterministic. With a very large guest, this could wreak
havoc causing dropped networking connections, etc.
It's totally unsafe.
If a management tool wants this behavior, they can set a timeout and
explicitly stop the guest during the live migration. IMHO, such a
management tool is not doing it's job properly but it still can be
implemented.
Regards,
Anthony Liguori
> ---
> arch_init.c | 13 ++++++++++++-
> 1 files changed, 12 insertions(+), 1 deletions(-)
>
> diff --git a/arch_init.c b/arch_init.c
> index 4486925..67e90f8 100644
> --- a/arch_init.c
> +++ b/arch_init.c
> @@ -212,6 +212,14 @@ uint64_t ram_bytes_total(void)
> return total;
> }
>
> +static uint64_t ram_blocks_total(void)
> +{
> + return ram_bytes_total() / TARGET_PAGE_SIZE;
> +}
> +
> +static uint64_t blocks_transferred = 0;
> +static int max_factor = 3;
> +
> int ram_save_live(Monitor *mon, QEMUFile *f, int stage, void *opaque)
> {
> ram_addr_t addr;
> @@ -234,6 +242,7 @@ int ram_save_live(Monitor *mon, QEMUFile *f, int stage,
> void *opaque)
> bytes_transferred = 0;
> last_block = NULL;
> last_offset = 0;
> + blocks_transferred = 0;
>
> /* Make sure all dirty bits are set */
> QLIST_FOREACH(block, &ram_list.blocks, next) {
> @@ -266,6 +275,7 @@ int ram_save_live(Monitor *mon, QEMUFile *f, int stage,
> void *opaque)
>
> bytes_sent = ram_save_block(f);
> bytes_transferred += bytes_sent;
> + blocks_transferred += !!bytes_sent;
> if (bytes_sent == 0) { /* no more blocks */
> break;
> }
> @@ -295,7 +305,8 @@ int ram_save_live(Monitor *mon, QEMUFile *f, int stage,
> void *opaque)
>
> expected_time = ram_save_remaining() * TARGET_PAGE_SIZE / bwidth;
>
> - return (stage == 2) && (expected_time <= migrate_max_downtime());
> + return (stage == 2) && ((expected_time <= migrate_max_downtime())
> + || (blocks_transferred > ram_blocks_total() * max_factor));
> }
>
> static inline void *host_from_stream_offset(QEMUFile *f,
>