Hi Dario,
On Tue, Feb 9, 2021 at 7:32 AM Dario Faggioli <dfaggioli@xxxxxxxx> wrote:
>
> Hello,
>
> On Mon, 2021-02-08 at 08:17 +0200, Tzvetomir Stoyanov (VMware) wrote:
> > Basic infrastructure for host - guest timestamp synchronization and a
> > PoC implementation of PTP-like and KVM algorithms.
> >
> I'm trying to play with trace-cmd agent & clock syncronization, so I
> applied this series.
>
> However, when I try to connect to a VM where I have the agent running,
> I'm seeing this (on the host):
>
> # ./tracecmd/trace-cmd record --debug -p nop -e sched:* -e kvm:* -e timer:hrtimer* -A tumbleweed-jeos:8888 -e all sleep 1
> trace-cmd: No such file or directory
> Failed to receive trace response -107
>
> I tried to do a strace, still on the host, and this is what I see (the
> last part of the output):
>
> rt_sigaction(SIGINT, {sa_handler=0x4116a5, sa_mask=[INT], sa_flags=SA_RESTORER|SA_RESTART, sa_restorer=0x7f29f1b55b70}, {sa_handler=SIG_DFL, sa_mask=[], sa_flags=0}, 8) = 0
> openat(AT_FDCWD, "/var/lib/trace-cmd/virt/(null)/trace-pipe-cpu0.out", O_RDONLY|O_NONBLOCK) = -1 ENOENT (No such file or directory)
> socket(AF_VSOCK, SOCK_STREAM, 0) = 4
> connect(4, {sa_family=AF_VSOCK, sa_data="\0\0\270\"\0\0\3\0\0\0\0\0\0\0"}, 16) = 0
> openat(AT_FDCWD, "/sys/kernel/debug/tracing/trace_clock", O_RDONLY) = 6
> read(6, "local global counter uptime perf"..., 8192) = 62
> read(6, "", 8192) = 0
> close(6) = 0
> write(4, "\0\0\0<\0\0\0\6\0\0\0\20\0\0\0\0\0\0\0\0\347\366+n\204\271\35\334", 28) = 28
> write(4, "\0\0\0\0\0\0\0\v\0\0\0\2-e\0all\0\0\0\0\1\0\0\0\5ptp\0\0", 32) = 32
> read(4, "", 12) = 0
> dup(2) = 6
> fcntl(6, F_GETFL) = 0x402 (flags O_RDWR|O_APPEND)
> fstat(6, {st_mode=S_IFCHR|0620, st_rdev=makedev(0x88, 0x9), ...}) = 0
> write(6, "trace-cmd: No such file or direc"..., 37trace-cmd: No such file or directory
> ) = 37
> close(6) = 0
> write(2, " ", 2 ) = 2
> write(2, "Failed to receive trace response"..., 37Failed to receive trace response -107) = 37
> write(2, "\n", 1
> ) = 1
> exit_group(2) = ?
> +++ exited with 2 +++
>
> Finally, if I use `--debug` both on the host and in the VM, here's what
> I get.
>
> Guest:
> # ./tracecmd/trace-cmd agent -p 8888 --debug
> listening on @3:8888
> msg received: 6 (TRACE_REQ) [60]
> Segmentation fault
>
> Host:
> # ./tracecmd/trace-cmd record --debug -p nop -e sched:* -e kvm:* -e timer:hrtimer* -A tumbleweed-jeos:8888 -e all sleep 1
> msg send: 6 (TRACE_REQ) [60]
> trace-cmd: No such file or directory
> Failed to receive trace response -107
>
> Am I doing something wrong? :-)
>
> If necessary, I can provide more info about my setup, or do more tests.
There are a few limitations that we are working to address:
1. Ensure that vhost_vsock module is loaded on the host.
2. You should add a vsock device manually to your VM config, I use
"virsh edit <vm name>" to add:
<vsock model='virtio'>
<cid auto='yes'/>
<address type='pci' domain='0x0000' bus='0x00' slot='0x09'
function='0x0'/>
</vsock>
somewhere in the <devices> </devices> section.
>
> Thanks and Regards
> --
> Dario Faggioli, Ph.D
> http://about.me/dario.faggioli
> Virtualization Software Engineer
> SUSE Labs, SUSE https://www.suse.com/
> -------------------------------------------------------------------
> <<This happens because _I_ choose it to happen!>> (Raistlin Majere)
--
Tzvetomir (Ceco) Stoyanov
VMware Open Source Technology Center
|