On Sun, Dec 27, 2015 at 01:26:15PM +0800, Mia Lueng wrote:
> How does epoch works? I have examined the source code. when primary
> recieves a bio with bi_size=0 or bio num > MAX_EPOCH_SIZE or idle
> time exceeds limit , there will be a P_BARRIER packet triggered?
Yes, that too.
But the important
How does epoch works? I have examined the source code. when primary
recieves a bio with bi_size=0 or bio num > MAX_EPOCH_SIZE or idle
time exceeds limit , there will be a P_BARRIER packet triggered?
2015-12-24 23:49 GMT+08:00 Lars Ellenberg :
> On Wed, Dec 23, 2015 at 12:11:51AM +0800, Mia Lueng
On Wed, Dec 23, 2015 at 12:11:51AM +0800, Mia Lueng wrote:
> Hi:
> I'm just wondering how secondary handle the write ordering when a same
> block is written twice on primary.
>
> Application submits these updates: X, Y, Z.
> They may or may not be to the same block.
> If they are to the same block
but in protocol a, the change is saved in network buffer and send to
peer. peer may receive x,y,z at the same time and write to local
backend device . Because the generic_make_request is async . We
should need some mechenism to make sure y is written to backend device
just after x is written compl
On 22/12/15 11:11 AM, Mia Lueng wrote:
> Hi:
> I'm just wondering how secondary handle the write ordering when a same
> block is written twice on primary.
>
> Application submits these updates: X, Y, Z.
> They may or may not be to the same block.
> If they are to the same block, then the applicati
Hi:
I'm just wondering how secondary handle the write ordering when a same
block is written twice on primary.
Application submits these updates: X, Y, Z.
They may or may not be to the same block.
If they are to the same block, then the application, file system
or other layer already makes sure (or
