Hi Steven,
JSON output is a feature I have waited for a long time. Thank you! Just
my two cents: why not create your own struct btrfs_send_ops object and
your own set of print_* functions? I think that may be more OOP design.
Regards,
Sheng
On Sat, Jan 16, 2021 at 03:56:06PM +, Steven Davi
Alignment to cache line is a great idea. I guess compiler can issue
faster memcpy version.
Thank you!
On Wed, Jan 06, 2021 at 01:16:35PM +0100, David Sterba wrote:
>
> On Sat, Dec 26, 2020 at 02:46:06PM -0700, shng...@gmail.com wrote:
> > From: Sheng Mao
> >
> &
n Sun, Jan 03, 2021 at 11:25:36PM -0700, Sheng Mao wrote:
> Hi Yugui,
>
> I can reproduce the issue with your pstack trick. Many thanks! I am
> trying to use a larger SEND_BUFFER_SIZE. The strange thing is socket
> should never send wrong data. Thanks for the insight, my guess is
>
; > >
> > > > > --dump only writes to stdout thus we can see network-only performance.
> > > > >
> > > > > Thank you!
> > > > >
> > > > > On Sat, Jan 02, 2021 at 06:45:32PM +0800, Wang Yugui wrote:
> > > > > > To: Sheng
&g
btrfs-5.9 receive --listen-addr ::
> > > > --tcp-port 8080 /btrfs &
> > > > sleep 2
> > > > /usr/bin/time btrfs-5.9 send --conn-addr ${server} --tcp-port 8080
> > > > /archive/movie2 2>time.send
> > > > sleep 1
> > > &g
p result:
> > > PID USER PR NIVIRTRESSHR S %CPU %MEM TIME+
> > > COMMAND
> > >7479 root 20 0 45568 5200 4540 R 100.0 0.0 8:16.05
> > > btrfs-5.9 receive --listen-addr
> > >
> > > #pstack 7479
> > >
.c:330
>
> That is to say, for high speed network/disk config, the current bottleneck
> of btrfs send/receive is the CRC process in btrfs receive side.
>
> Best Regards
> Wang Yugui (wangyu...@e16-tech.com)
> 2021/01/02
>
> > From: Sheng Mao
> >
> >
.
>
> Best Regards
> Wang Yugui (wangyu...@e16-tech.com)
> 2021/01/01
>
>
> > Thank you! Happy new year!
> >
> > Regards,
> > Sheng
> >
> > > On Dec 31, 2020, at 04:16, Wang Yugui wrote:
> > >
> > > Hi, Sheng Mao
> > &g
ote:
>
> Hi, Sheng Mao
>
> some feedback.
>
> 1, can we use 'listen-addr' for sever side, and 'conn-addr' for client
> side?
>
> 2, can we support '--tls-mode none' for tcp without TLS,
> and then change 'tls-port' to
