From mboxrd@z Thu Jan 1 00:00:00 1970
Return-Path: <pbs-devel-bounces@lists.proxmox.com>
Received: from firstgate.proxmox.com (firstgate.proxmox.com [212.224.123.68])
by lore.proxmox.com (Postfix) with ESMTPS id 73C111FF170
for <inbox@lore.proxmox.com>; Tue, 3 Dec 2024 12:24:16 +0100 (CET)
Received: from firstgate.proxmox.com (localhost [127.0.0.1])
by firstgate.proxmox.com (Proxmox) with ESMTP id 4994F1BDF;
Tue, 3 Dec 2024 12:24:22 +0100 (CET)
From: Dominik Csapak <d.csapak@proxmox.com>
To: pbs-devel@lists.proxmox.com
Date: Tue, 3 Dec 2024 12:23:49 +0100
Message-Id: <20241203112349.2446383-1-d.csapak@proxmox.com>
X-Mailer: git-send-email 2.39.5
MIME-Version: 1.0
X-SPAM-LEVEL: Spam detection results: 0
AWL 0.016 Adjusted score from AWL reputation of From: address
BAYES_00 -1.9 Bayes spam probability is 0 to 1%
DMARC_MISSING 0.1 Missing DMARC policy
KAM_DMARC_STATUS 0.01 Test Rule for DKIM or SPF Failure with Strict Alignment
RCVD_IN_VALIDITY_CERTIFIED_BLOCKED 0.001 ADMINISTRATOR NOTICE: The query to
Validity was blocked. See
https://knowledge.validity.com/hc/en-us/articles/20961730681243 for more
information.
RCVD_IN_VALIDITY_RPBL_BLOCKED 0.001 ADMINISTRATOR NOTICE: The query to
Validity was blocked. See
https://knowledge.validity.com/hc/en-us/articles/20961730681243 for more
information.
RCVD_IN_VALIDITY_SAFE_BLOCKED 0.001 ADMINISTRATOR NOTICE: The query to
Validity was blocked. See
https://knowledge.validity.com/hc/en-us/articles/20961730681243 for more
information.
SPF_HELO_NONE 0.001 SPF: HELO does not publish an SPF Record
SPF_PASS -0.001 SPF: sender matches SPF record
URIBL_BLOCKED 0.001 ADMINISTRATOR NOTICE: The query to URIBL was blocked. See
http://wiki.apache.org/spamassassin/DnsBlocklists#dnsbl-block for more
information. [server.rs]
Subject: [pbs-devel] [PATCH proxmox v2] daemon: clean up middle process of
double fork
X-BeenThere: pbs-devel@lists.proxmox.com
X-Mailman-Version: 2.1.29
Precedence: list
List-Id: Proxmox Backup Server development discussion
<pbs-devel.lists.proxmox.com>
List-Unsubscribe: <https://lists.proxmox.com/cgi-bin/mailman/options/pbs-devel>,
<mailto:pbs-devel-request@lists.proxmox.com?subject=unsubscribe>
List-Archive: <http://lists.proxmox.com/pipermail/pbs-devel/>
List-Post: <mailto:pbs-devel@lists.proxmox.com>
List-Help: <mailto:pbs-devel-request@lists.proxmox.com?subject=help>
List-Subscribe: <https://lists.proxmox.com/cgi-bin/mailman/listinfo/pbs-devel>,
<mailto:pbs-devel-request@lists.proxmox.com?subject=subscribe>
Reply-To: Proxmox Backup Server development discussion
<pbs-devel@lists.proxmox.com>
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: 7bit
Errors-To: pbs-devel-bounces@lists.proxmox.com
Sender: "pbs-devel" <pbs-devel-bounces@lists.proxmox.com>
so we don't leave around a zombie process when the old daemon still
needs to run, because of e.g. a running task.
Since this is mostly a cosmetic issue though, only try a clean up with a
10 second timeout, so we don't block forever. (It could happen that it
didn't exit at that point, but it's very unlikely.)
In case we do run into the timeout here, the process will not be
collected until the parent process exits and the middle process is
collected by pid 1.
Signed-off-by: Dominik Csapak <d.csapak@proxmox.com>
---
changes from v1:
* use a timeout
* log the error
proxmox-daemon/src/server.rs | 33 +++++++++++++++++++++++++++++++--
1 file changed, 31 insertions(+), 2 deletions(-)
diff --git a/proxmox-daemon/src/server.rs b/proxmox-daemon/src/server.rs
index efea9078..27153fc2 100644
--- a/proxmox-daemon/src/server.rs
+++ b/proxmox-daemon/src/server.rs
@@ -8,6 +8,7 @@ use std::os::unix::io::{AsRawFd, FromRawFd, IntoRawFd, OwnedFd, RawFd};
use std::panic::UnwindSafe;
use std::path::PathBuf;
use std::pin::{pin, Pin};
+use std::time::Duration;
use anyhow::{bail, format_err, Error};
use futures::future::{self, Either};
@@ -15,6 +16,7 @@ use nix::unistd::{fork, ForkResult};
use proxmox_sys::fd::fd_change_cloexec;
use proxmox_sys::fs::CreateOptions;
+use proxmox_sys::linux::timer;
type BoxedStoreFunc = Box<dyn FnOnce() -> Result<String, Error> + UnwindSafe + Send>;
@@ -165,10 +167,12 @@ impl Reloader {
// No matter how we managed to get here, this is the time where we bail out quickly:
unsafe { libc::_exit(-1) }
}
- Ok(ForkResult::Parent { child }) => {
+ Ok(ForkResult::Parent {
+ child: middle_child,
+ }) => {
log::debug!(
"forked off a new server (first pid: {}), waiting for 2nd pid",
- child
+ middle_child
);
std::mem::drop(pnew);
let mut pold = std::fs::File::from(pold);
@@ -211,6 +215,10 @@ impl Reloader {
log::error!("child vanished during reload: {}", e);
}
+ if let Err(e) = waitpid_with_timeout(middle_child, Duration::from_secs(10)) {
+ log::error!("waitpid for middle process failed: {e}");
+ }
+
Ok(())
}
Err(e) => {
@@ -230,6 +238,27 @@ impl Reloader {
}
}
+fn waitpid_with_timeout(pid: nix::unistd::Pid, timeout: std::time::Duration) -> Result<(), Error> {
+ // unblock the timeout signal temporarily
+ let _sigblock_guard = timer::unblock_timeout_signal();
+
+ // setup a timeout timer
+ let mut timer = timer::Timer::create(
+ timer::Clock::Realtime,
+ timer::TimerEvent::ThisThreadSignal(timer::SIGTIMEOUT),
+ )?;
+
+ timer.arm(
+ timer::TimerSpec::new()
+ .value(Some(timeout))
+ .interval(Some(Duration::from_millis(10))),
+ )?;
+
+ nix::sys::wait::waitpid(pid, None)?;
+
+ Ok(())
+}
+
fn fd_store_func(fd: RawFd) -> Result<BoxedStoreFunc, Error> {
let fd = unsafe {
OwnedFd::from_raw_fd(nix::fcntl::fcntl(
--
2.39.5
_______________________________________________
pbs-devel mailing list
pbs-devel@lists.proxmox.com
https://lists.proxmox.com/cgi-bin/mailman/listinfo/pbs-devel