On 6/10/19 9:02 AM, Eric Blake wrote:
>
> send(MSG_MORE)
> send()
>
> is ideal; under the hood, we can translate it to:
>
> send(MSG_MORE)
> gnutls_record_cork()
> gnutls_record_send()
> send()
> if (size > threshold) {
> gnutls_record_uncork()
> gnutls_record_send()
> } else {
On 6/10/19 4:08 AM, Daniel P. Berrangé wrote:
> On Fri, Jun 07, 2019 at 05:14:14PM -0500, Eric Blake wrote:
>> Our current implementation of qio_channel_set_cork() is pointless for
>> TLS sessions: we block the underlying channel, but still hand things
>> piecemeal to gnutls which then produces mul
On Fri, Jun 07, 2019 at 05:14:14PM -0500, Eric Blake wrote:
> Our current implementation of qio_channel_set_cork() is pointless for
> TLS sessions: we block the underlying channel, but still hand things
> piecemeal to gnutls which then produces multiple encryption packets.
> Better is to directly u
On 6/7/19 5:14 PM, Eric Blake wrote:
> Our current implementation of qio_channel_set_cork() is pointless for
> TLS sessions: we block the underlying channel, but still hand things
> piecemeal to gnutls which then produces multiple encryption packets.
> Better is to directly use gnutls corking, whic
Our current implementation of qio_channel_set_cork() is pointless for
TLS sessions: we block the underlying channel, but still hand things
piecemeal to gnutls which then produces multiple encryption packets.
Better is to directly use gnutls corking, which collects multiple
inputs into a single encr
