From: Slavomir Kaslev <kaslevs@vmware.com>
To: linux-trace-devel@vger.kernel.org
Cc: rostedt@goodmis.org, slavomir.kaslev@gmail.com,
tstoyanov@vmware.com, ykaradzhov@vmware.com
Subject: [RFC PATCH v5 06/11] trace-cmd: Use splice(2) for vsockets if available
Date: Mon, 4 Feb 2019 08:58:43 +0200 [thread overview]
Message-ID: <20190204065848.8248-7-kaslevs@vmware.com> (raw)
In-Reply-To: <20190204065848.8248-1-kaslevs@vmware.com>
Detect if splice(2) reading is supported for vsockets (Linux 4.20 and
later) and use it, or fallback to read/write-ing otherwise.
Signed-off-by: Slavomir Kaslev <kaslevs@vmware.com>
---
lib/trace-cmd/trace-recorder.c | 6 ++--
tracecmd/trace-record.c | 56 ++++++++++++++++++++++++++++++++--
2 files changed, 56 insertions(+), 6 deletions(-)
diff --git a/lib/trace-cmd/trace-recorder.c b/lib/trace-cmd/trace-recorder.c
index 83a12f4..b750935 100644
--- a/lib/trace-cmd/trace-recorder.c
+++ b/lib/trace-cmd/trace-recorder.c
@@ -380,10 +380,8 @@ static long splice_data(struct tracecmd_recorder *recorder)
ret = splice(recorder->brass[0], NULL, recorder->fd, NULL,
read, recorder->fd_flags);
if (ret < 0) {
- if (errno != EAGAIN && errno != EINTR) {
- warning("recorder error in splice output");
- return -1;
- }
+ if (errno != EAGAIN && errno != EINTR)
+ return ret;
return total_read;
} else
update_fd(recorder, ret);
diff --git a/tracecmd/trace-record.c b/tracecmd/trace-record.c
index 3c28314..71176d9 100644
--- a/tracecmd/trace-record.c
+++ b/tracecmd/trace-record.c
@@ -2656,12 +2656,61 @@ static int open_vsock(unsigned int cid, unsigned int port)
return sd;
}
+
+static int try_splice_read_vsock(void)
+{
+ int ret, sd, brass[2];
+
+ sd = socket(AF_VSOCK, SOCK_STREAM, 0);
+ if (sd < 0)
+ return sd;
+
+ ret = pipe(brass);
+ if (ret < 0)
+ goto out_close_sd;
+
+ /*
+ * On kernels that don't support splice reading from vsockets
+ * this will fail with EINVAL, or ENOTCONN otherwise.
+ * Technically, it should never succeed but if it does, claim splice
+ * reading is supported.
+ */
+ ret = splice(sd, NULL, brass[1], NULL, 10, 0);
+ if (ret < 0)
+ ret = errno != EINVAL;
+ else
+ ret = 1;
+
+ close(brass[0]);
+ close(brass[1]);
+out_close_sd:
+ close(sd);
+ return ret;
+}
+
+static bool can_splice_read_vsock(void)
+{
+ static bool initialized, res;
+
+ if (initialized)
+ return res;
+
+ res = try_splice_read_vsock() > 0;
+ initialized = true;
+ return res;
+}
+
#else
static inline int open_vsock(unsigned int cid, unsigned int port)
{
die("vsock is not supported");
return -1;
}
+
+static bool can_splice_read_vsock(void)
+{
+ return false;
+}
#endif
static int do_accept(int sd)
@@ -2866,13 +2915,16 @@ create_recorder_instance(struct buffer_instance *instance, const char *file, int
if (instance->flags & BUFFER_FL_GUEST) {
int sd;
+ unsigned int flags;
sd = open_vsock(instance->cid, instance->client_ports[cpu]);
if (sd < 0)
die("Failed to connect to agent");
- return tracecmd_create_recorder_virt(
- file, cpu, recorder_flags | TRACECMD_RECORD_NOSPLICE, sd);
+ flags = recorder_flags;
+ if (!can_splice_read_vsock())
+ flags |= TRACECMD_RECORD_NOSPLICE;
+ return tracecmd_create_recorder_virt(file, cpu, flags, sd);
}
if (brass)
--
2.19.1
next prev parent reply other threads:[~2019-02-04 6:59 UTC|newest]
Thread overview: 13+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-02-04 6:58 [RFC PATCH v5 00/11] Add VM kernel tracing over vsockets and FIFOs Slavomir Kaslev
2019-02-04 6:58 ` [RFC PATCH v5 01/11] trace-cmd: Detect if vsockets are available Slavomir Kaslev
2019-02-04 6:58 ` [RFC PATCH v5 02/11] trace-cmd: Add tracecmd_create_recorder_virt function Slavomir Kaslev
2019-02-04 6:58 ` [RFC PATCH v5 03/11] trace-cmd: Add TRACE_REQ and TRACE_RESP messages Slavomir Kaslev
2019-02-04 6:58 ` [RFC PATCH v5 04/11] trace-cmd: Add buffer instance flags for tracing in guest and agent context Slavomir Kaslev
2019-02-04 6:58 ` [RFC PATCH v5 05/11] trace-cmd: Add VM kernel tracing over vsockets transport Slavomir Kaslev
2019-02-04 6:58 ` Slavomir Kaslev [this message]
2019-02-04 6:58 ` [RFC PATCH v5 07/11] trace-cmd: Add `trace-cmd setup-guest` command Slavomir Kaslev
2019-02-04 6:58 ` [RFC PATCH v5 08/11] trace-cmd: Try to autodetect number of guest CPUs in setup-guest if not specified Slavomir Kaslev
2019-02-04 6:58 ` [RFC PATCH v5 09/11] trace-cmd: Make setup-guest auto attach FIFOs to the guest VM config Slavomir Kaslev
2019-02-04 6:58 ` [RFC PATCH v5 10/11] trace-cmd: Set both input and output to non-blocking when recording is stopped Slavomir Kaslev
2019-02-04 6:58 ` [RFC PATCH v5 11/11] trace-cmd: Add VM tracing over FIFOs transport Slavomir Kaslev
2019-02-08 21:03 ` [RFC PATCH v5 00/11] Add VM kernel tracing over vsockets and FIFOs Steven Rostedt
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20190204065848.8248-7-kaslevs@vmware.com \
--to=kaslevs@vmware.com \
--cc=linux-trace-devel@vger.kernel.org \
--cc=rostedt@goodmis.org \
--cc=slavomir.kaslev@gmail.com \
--cc=tstoyanov@vmware.com \
--cc=ykaradzhov@vmware.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).