From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from firstgate.proxmox.com (firstgate.proxmox.com [212.224.123.68]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (2048 bits) server-digest SHA256) (No client certificate requested) by lists.proxmox.com (Postfix) with ESMTPS id 6BD3170A3B for ; Thu, 30 Sep 2021 10:21:10 +0200 (CEST) Received: from firstgate.proxmox.com (localhost [127.0.0.1]) by firstgate.proxmox.com (Proxmox) with ESMTP id 5E6DF1C24C for ; Thu, 30 Sep 2021 10:21:10 +0200 (CEST) Received: from proxmox-new.maurer-it.com (proxmox-new.maurer-it.com [94.136.29.106]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (2048 bits) server-digest SHA256) (No client certificate requested) by firstgate.proxmox.com (Proxmox) with ESMTPS id 446581C23E for ; Thu, 30 Sep 2021 10:21:09 +0200 (CEST) Received: from proxmox-new.maurer-it.com (localhost.localdomain [127.0.0.1]) by proxmox-new.maurer-it.com (Proxmox) with ESMTP id 1722544871 for ; Thu, 30 Sep 2021 10:21:03 +0200 (CEST) Message-ID: <963c1d55-6358-b3f9-5a82-9e1a8bdeda83@proxmox.com> Date: Thu, 30 Sep 2021 10:19:59 +0200 MIME-Version: 1.0 User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:93.0) Gecko/20100101 Thunderbird/93.0 Content-Language: en-US To: Proxmox Backup Server development discussion , Dominik Csapak References: <20210930071858.1116527-1-d.csapak@proxmox.com> From: Thomas Lamprecht In-Reply-To: <20210930071858.1116527-1-d.csapak@proxmox.com> Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 7bit X-SPAM-LEVEL: Spam detection results: 0 AWL 1.756 Adjusted score from AWL reputation of From: address BAYES_00 -1.9 Bayes spam probability is 0 to 1% KAM_DMARC_STATUS 0.01 Test Rule for DKIM or SPF Failure with Strict Alignment NICE_REPLY_A -3.03 Looks like a legit reply (A) 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. [minimal-rest-server.rs, proxmox-backup-proxy.rs, daemon.rs, proxmox-backup-api.rs] Subject: Re: [pbs-devel] [PATCH proxmox-backup] rest-server/daemon: use sd_notify_barrier for service reloading X-BeenThere: pbs-devel@lists.proxmox.com X-Mailman-Version: 2.1.29 Precedence: list List-Id: Proxmox Backup Server development discussion List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 30 Sep 2021 08:21:10 -0000 On 30.09.21 09:18, Dominik Csapak wrote: > until now, we manually polled the systemd service state during a reload > so that the sd_notify messages get processed in the correct order > (RELOAD(old) -> MAINPID(old) -> READY(new)) > > with systemd >= 246 there is now 'sd_notify_barrier' which > blocks until systemd processed all prior messages > > with that change, the daemon does not need to know the service name anymore > looks OK, much nicer, two nits inline (that can be followed up too) > Signed-off-by: Dominik Csapak > --- > debian/control | 2 +- > .../examples/minimal-rest-server.rs | 1 - > proxmox-rest-server/src/daemon.rs | 61 +++++++------------ > src/bin/proxmox-backup-api.rs | 1 - > src/bin/proxmox-backup-proxy.rs | 1 - > 5 files changed, 22 insertions(+), 44 deletions(-) > > diff --git a/debian/control b/debian/control > index 02b094bd..8aec88cf 100644 > --- a/debian/control > +++ b/debian/control > @@ -89,7 +89,7 @@ Build-Depends: debhelper (>= 12), > librust-zstd-0.6+default-dev, > libacl1-dev, > libfuse3-dev, > - libsystemd-dev, > + libsystemd-dev (>= 246-~~), > uuid-dev, > libsgutils2-dev, > bash-completion, > diff --git a/proxmox-rest-server/examples/minimal-rest-server.rs b/proxmox-rest-server/examples/minimal-rest-server.rs > index 22477039..2b6a40a1 100644 > --- a/proxmox-rest-server/examples/minimal-rest-server.rs > +++ b/proxmox-rest-server/examples/minimal-rest-server.rs > @@ -207,7 +207,6 @@ async fn run() -> Result<(), Error> { > Ok(()) > }) > }, > - "example_server", > ).await?; > > Ok(()) > diff --git a/proxmox-rest-server/src/daemon.rs b/proxmox-rest-server/src/daemon.rs > index 9d48ecd2..5d59fce2 100644 > --- a/proxmox-rest-server/src/daemon.rs > +++ b/proxmox-rest-server/src/daemon.rs > @@ -186,6 +186,9 @@ impl Reloader { > if let Err(e) = systemd_notify(SystemdNotify::MainPid(child)) { > log::error!("failed to notify systemd about the new main pid: {}", e); > } > + if let Err(e) = systemd_notify_barrier() { maybe add a comment regarding ordering here, e.g., something like // ensure systemd got the message about the new main PID before continuing, else it gets confused > + log::error!("failed to wait on systemd-processing: {}", e); > + } > > // notify child that it is now the new main process: > if let Err(e) = pold.write_all(&[1u8]) { > @@ -248,7 +251,6 @@ impl Reloadable for tokio::net::TcpListener { > pub async fn create_daemon( > address: std::net::SocketAddr, > create_service: F, > - service_name: &str, > ) -> Result<(), Error> > where > F: FnOnce(tokio::net::TcpListener) -> Result, > @@ -289,7 +291,10 @@ where > if let Err(e) = systemd_notify(SystemdNotify::Reloading) { > log::error!("failed to notify systemd about the state change: {}", e); > } > - wait_service_is_state(service_name, "reloading").await?; > + if let Err(e) = systemd_notify_barrier() { > + log::error!("failed to wait on systemd-processing: {}", e); > + } > + > if let Err(e) = reloader.take().unwrap().fork_restart() { > log::error!("error during reload: {}", e); > let _ = systemd_notify(SystemdNotify::Status("error during reload".to_string())); > @@ -302,51 +307,14 @@ where > future.await; > } > > - // FIXME: this is a hack, replace with sd_notify_barrier when available > - if crate::is_reload_request() { > - wait_service_is_not_state(service_name, "reloading").await?; > - } > - > log::info!("daemon shut down."); > Ok(()) > } > > -// hack, do not use if unsure! > -async fn get_service_state(service: &str) -> Result { > - let text = match tokio::process::Command::new("systemctl") > - .args(&["is-active", service]) > - .output() > - .await > - { > - Ok(output) => match String::from_utf8(output.stdout) { > - Ok(text) => text, > - Err(err) => bail!("output of 'systemctl is-active' not valid UTF-8 - {}", err), > - }, > - Err(err) => bail!("executing 'systemctl is-active' failed - {}", err), > - }; > - > - Ok(text.trim().trim_start().to_string()) > -} > - > -async fn wait_service_is_state(service: &str, state: &str) -> Result<(), Error> { > - tokio::time::sleep(std::time::Duration::new(1, 0)).await; > - while get_service_state(service).await? != state { > - tokio::time::sleep(std::time::Duration::new(5, 0)).await; > - } > - Ok(()) > -} > - > -async fn wait_service_is_not_state(service: &str, state: &str) -> Result<(), Error> { > - tokio::time::sleep(std::time::Duration::new(1, 0)).await; > - while get_service_state(service).await? == state { > - tokio::time::sleep(std::time::Duration::new(5, 0)).await; > - } > - Ok(()) > -} > - > #[link(name = "systemd")] > extern "C" { > fn sd_notify(unset_environment: c_int, state: *const c_char) -> c_int; > + fn sd_notify_barrier(unset_environment: c_int, timeout: u64) -> c_int; > } > > /// Systemd sercice startup states (see: ``man sd_notify``) > @@ -358,6 +326,19 @@ pub enum SystemdNotify { > MainPid(nix::unistd::Pid), > } > > +/// Waits until all previously sent messages with sd_notify are processed > +pub fn systemd_notify_barrier() -> Result<(), Error> { > + let rc = unsafe { sd_notify_barrier(0, u64::MAX) }; // infinite timeout > + if rc < 0 { > + bail!( > + "systemd_notify_barrier failed: {}", > + std::io::Error::from_raw_os_error(-rc), > + ); single line for above would works out nicely for our <= 100 cc in rust here :) > + } > + > + Ok(()) > +} > + > /// Tells systemd the startup state of the service (see: ``man sd_notify``) > pub fn systemd_notify(state: SystemdNotify) -> Result<(), Error> { > > diff --git a/src/bin/proxmox-backup-api.rs b/src/bin/proxmox-backup-api.rs > index 35cfc5f0..97b7a5e8 100644 > --- a/src/bin/proxmox-backup-api.rs > +++ b/src/bin/proxmox-backup-api.rs > @@ -119,7 +119,6 @@ async fn run() -> Result<(), Error> { > .await > }) > }, > - "proxmox-backup.service", > ); > > proxmox_rest_server::write_pid(pbs_buildcfg::PROXMOX_BACKUP_API_PID_FN)?; > diff --git a/src/bin/proxmox-backup-proxy.rs b/src/bin/proxmox-backup-proxy.rs > index a98d4c1f..a548b535 100644 > --- a/src/bin/proxmox-backup-proxy.rs > +++ b/src/bin/proxmox-backup-proxy.rs > @@ -262,7 +262,6 @@ async fn run() -> Result<(), Error> { > .await > }) > }, > - "proxmox-backup-proxy.service", > ); > > proxmox_rest_server::write_pid(pbs_buildcfg::PROXMOX_BACKUP_PROXY_PID_FN)?; >