The figure is based on our experience of running scope probes in
production systems. Below this we see a lot of "conntrack
stderr:WARNING: We have hit ENOBUFS! We are losing events."
Changed default for flag `-app.docker` to use the DOCKER_* env variables
instead of hardcoded /var/run/docker.sock; uses docker's default if
no DOCKER_HOST defined, for both probe and app.
Fixes#1975
Since https://github.com/weaveworks/tcptracer-bpf/pull/39, tcptracer-bpf
can generate "fd_install" events when a process installs a new file
descriptor in its fd table. Those events must be requested explicitely
on a per-pid basis with tracer.AddFdInstallWatcher(pid).
This is useful to know about "accept" events that would otherwise be
missed because kretprobes are not triggered for functions that were
called before the installation of the kretprobe.
This patch find all the processes that are currently blocked on an
accept() syscall during the EbpfTracker initialization.
feedInitialConnections() will use tracer.AddFdInstallWatcher() to
subscribe to fd_install events. When a fd_install event is received,
synthesise an accept event with the connection tuple and the network
namespace (from /proc).
Based on work from Lorenzo, updated by Iago, Alban, Alessandro and
Michael.
This PR adds connection tracking using eBPF. This feature is not enabled by default.
For now, you can enable it by launching scope with the following command:
```
sudo ./scope launch --probe.ebpf.connections=true
```
This patch allows scope to get notified of every connection event,
without relying on the parsing of /proc/$pid/net/tcp{,6} and
/proc/$pid/fd/*, and therefore improve performance.
We vendor https://github.com/iovisor/gobpf in Scope to load the
pre-compiled ebpf program and https://github.com/weaveworks/tcptracer-bpf
to guess the offsets of the structures we need in the kernel. In this
way we don't need a different pre-compiled ebpf object file per kernel.
The pre-compiled ebpf program is included in the vendoring of
tcptracer-bpf.
The ebpf program uses kprobes/kretprobes on the following kernel functions:
- tcp_v4_connect
- tcp_v6_connect
- tcp_set_state
- inet_csk_accept
- tcp_close
It generates "connect", "accept" and "close" events containing the
connection tuple but also pid and netns.
Note: the IPv6 events are not supported in Scope and thus not passed on.
probe/endpoint/ebpf.go maintains the list of connections. Similarly to
conntrack, it also keeps the dead connections for one iteration in order
to report short-lived connections.
The code for parsing /proc/$pid/net/tcp{,6} and /proc/$pid/fd/* is still
there and still used at start-up because eBPF only brings us the events
and not the initial state. However, the /proc parsing for the initial
state is now done in foreground instead of background, via
newForegroundReader().
NAT resolution on connections from eBPF works in the same way as it did
on connections from /proc: by using conntrack. One of the two conntrack
instances is only started to get the initial state and then it is
stopped since eBPF detects short-lived connections.
The Scope Docker image size comparison:
- weaveworks/scope in current master: 22 MB (compressed), 68 MB
(uncompressed)
- weaveworks/scope with this patchset: 23 MB (compressed), 69 MB
(uncompressed)
Fixes#1168 (walking /proc to obtain connections is very expensive)
Fixes#1260 (Short-lived connections not tracked for containers in
shared networking namespaces)
Fixes#1962 (Port ebpf tracker to Go)
Fixes#1961 (Remove runtime kernel header dependency from ebpf tracker)
* Add options to hide args and env vars
To allow for use of weave-scope in an unauthenticated environment,
add options to the probe to hide comand line arguments and
environment variables, which might contain secret data.
Fixes#2222
* Change docker.NewRegistry arguments to be a struct
* Remove redundant declarations of default values
* Move registry options outside to improve readability
Now you can launch the scope app with something like
./prog/scope --mode=app --weave=false --app.collector=file:///tmp/reports
and if the specified dir contains reports with filenames in the form
<timestamp>.{msgpack|json}[.gz],
e.g. "1488557088545489008.msgpack.gz", then these reports are replayed
in a loop at a sequence and speed determined by the timestamps.
User can control the webserver listen address with `-app.http.address`.
If they do, `scope --mode probe ...` should use the port part of address
in the default target and not ':4040'. Otherwise we encounter a
`dial tcp 127.0.0.1:4040: getsockopt: connection refused` error and
`scope-probe` cannot report.
Signed-off-by: Michael Schubert <michael@kinvolk.io>
