Re: [Qemu-devel] Question about drive mirror

[address@hidden]



Thank you for your detailed reply.

Now, I am modifying the code to change the reading and writing processes,

My purpose is that after it send the writing requestion and the writing requestion

is not come back, then it send the reading requestion.

I think this way will be more reading and writing pressure than before. 

 

I don't know why in mirror_iteration, each iteration send the number of data is

continuous dirty data, the maximum is the size of free_buffer(default is 10M),

I think the way will reduce the performance of IO,because the mirror will wait long

time to send next reading requestion. I think each iteration send the number of data

should base on the granularity ,we can set the granularity  is 1M. This way may be

let the reading  and writing is parallel. 

 

---

zhang min

 

From: Stefan Hajnoczi

Date: 2014-01-14 13:57

To: Fam Zheng

CC: address@hidden; rudy.zhangmin; qemu-devel

Subject: Re: [Qemu-devel] Question about drive mirror

On Tue, Jan 14, 2014 at 09:41:41AM +0800, Fam Zheng wrote:

> On Mon, 01/13 23:44, address@hidden wrote:

> > I tested the capability of drive mirror, I found the IO is low. Then I read the code,

> > The code mirror_run() will call mirror_iteration() to read the size of buffer data 

> > from source storage, when the read callback ,and then in mirror_read_complete ()

> > write the data to the target storage, It is serial.

 

And it also uses throttling to avoid impacting the guest too much.  It's

considered a background job, i.e. not trying to saturate storage

bandwidth.

 

That said, improving performance while keeping I/O isolated from higher

priority guest I/O can be good.

 

> > Now, I hope when it is writing the data to target storage ,we can send the request

> > of reading data from source storage. Because of  using  coroutine to do it ,there is

> > some troubles to achieve it. why not use Multi-thread?

> > Some one can give me some idea?

 

It can be parallelized by splitting the code into two separate loops:

 

A reader coroutine that reads data from the source device and places

buffers in a queue.

 

A writer coroutine that takes buffers from the queue and writes data to

the target device.

 

(In fact there could be multiple readers and writers.)

 

Stefan