Re: [Xen-devel] [PATCH v16 2/7] remus: introduce remus device

[Shriram Rajagopalan <rshriram@xxxxxxxxx>]

On Fri, Jul 18, 2014 at 11:58 AM, Ian Campbell <Ian.Campbell@xxxxxxxxxx> wrote:

On Fri, 2014-07-18 at 11:54 -0400, Shriram Rajagopalan wrote:

> if (info->netbuf) {
> Â...
> } else
> Â LOG(WARN, "Network buffering disabled. Failover may not be successful")

If this is the case then why are we offering that option to the user in
the first place?

What is the use case for disabling network buffering given that it
breaks failover?

The keyword above is "may". Without network buffering, ongoing TCPÂ

connections "may" be hung, depending on whether any communicationÂ

happened during the failed checkpoint. Same applies to disk.

If one can control the network interactions or if the application is capable of recovering

from lost TCP connections (or lost UDP packets for that matter), then it stands to benefit

from no-network buffering as it eliminates the latency overhead introduced by buffering every

packet [ 0.5 x checkpoint-interval + RTT between primary-backup].Â

Â

Ian.

_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel