[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [Qemu-devel] [Qemu-block] [PATCH 1/3] blockjob: Introduce block_job_
Re: [Qemu-devel] [Qemu-block] [PATCH 1/3] blockjob: Introduce block_job_relax_cpu
Fri, 10 Jul 2015 05:42:48 +0200 (CEST)
>>By the way, why did you choose 10 milliseconds? That is quite long.
>>If this function is called once per 10 ms disk I/O operations then we
>>lose 50% utilization. 1 ms or less would be reasonable.
>From my tests, 1ms is not enough, It still hanging in guest or qmp queries.
10ms give me optimal balance between bitmap scan speed and guest responsiveness.
I don't known if this can be compute automaticaly ? (maybe it's depend of disk
lseek speed and cpu speed).
----- Mail original -----
De: "Stefan Hajnoczi" <address@hidden>
À: "Fam Zheng" <address@hidden>
Cc: "Kevin Wolf" <address@hidden>, "qemu-devel" <address@hidden>, address@hidden
Envoyé: Jeudi 9 Juillet 2015 14:54:55
Objet: Re: [Qemu-devel] [Qemu-block] [PATCH 1/3] blockjob: Introduce
On Thu, Jul 09, 2015 at 11:47:56AM +0800, Fam Zheng wrote:
> block_job_sleep_ns is called by block job coroutines to yield the
> execution to VCPU threads and monitor etc. It is pointless to sleep for
> 0 or a few nanoseconds, because that equals to a "yield + enter" with no
> intermission in between (the timer fires immediately in the same
> iteration of event loop), which means other code still doesn't get a
> fair share of main loop / BQL.
> Introduce block_job_relax_cpu which will at least for
> BLOCK_JOB_RELAX_CPU_NS. Existing block_job_sleep_ns(job, 0) callers can
> be replaced by this later.
> Reported-by: Alexandre DERUMIER <address@hidden>
> Signed-off-by: Fam Zheng <address@hidden>
> include/block/blockjob.h | 16 ++++++++++++++++
> 1 file changed, 16 insertions(+)
> diff --git a/include/block/blockjob.h b/include/block/blockjob.h
> index 57d8ef1..53ac4f4 100644
> --- a/include/block/blockjob.h
> +++ b/include/block/blockjob.h
> @@ -157,6 +157,22 @@ void *block_job_create(const BlockJobDriver *driver,
> BlockDriverState *bs,
> void block_job_sleep_ns(BlockJob *job, QEMUClockType type, int64_t ns);
> +#define BLOCK_JOB_RELAX_CPU_NS 10000000L
By the way, why did you choose 10 milliseconds? That is quite long.
If this function is called once per 10 ms disk I/O operations then we
lose 50% utilization. 1 ms or less would be reasonable.
> + * block_job_relax_cpu:
> + * @job: The job that calls the function.
> + *
> + * Sleep a little to avoid intensive cpu time occupation. Block jobs should
> + * call this or block_job_sleep_ns (for more precision, but note that 0 ns
> + * usually not enought) periodically, otherwise the QMP and VCPU could
> + * on CPU and/or BQL.
> + */
> +static inline void block_job_relax_cpu(BlockJob *job)
coroutine_fn is missing.
[Qemu-devel] [PATCH 2/3] mirror: Use block_job_relax_cpu during bitmap scanning, Fam Zheng, 2015/07/08
[Qemu-devel] [PATCH 3/3] mirror: Speed up bitmap initial scanning, Fam Zheng, 2015/07/08
Re: [Qemu-devel] [PATCH 0/3] mirror: Fix guest responsiveness during bitmap scan, Alexandre DERUMIER, 2015/07/09
Re: [Qemu-devel] [Qemu-block] [PATCH 0/3] mirror: Fix guest responsiveness during bitmap scan, Stefan Hajnoczi, 2015/07/09