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)) (No client certificate requested) by lists.proxmox.com (Postfix) with ESMTPS id 0F527617A9 for ; Thu, 17 Dec 2020 15:50:20 +0100 (CET) Received: from firstgate.proxmox.com (localhost [127.0.0.1]) by firstgate.proxmox.com (Proxmox) with ESMTP id 073D2284AA for ; Thu, 17 Dec 2020 15:50:20 +0100 (CET) Received: from proxmox-new.maurer-it.com (proxmox-new.maurer-it.com [212.186.127.180]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (2048 bits)) (No client certificate requested) by firstgate.proxmox.com (Proxmox) with ESMTPS id 6CD70284A2 for ; Thu, 17 Dec 2020 15:50:19 +0100 (CET) Received: from proxmox-new.maurer-it.com (localhost.localdomain [127.0.0.1]) by proxmox-new.maurer-it.com (Proxmox) with ESMTP id 31BAC45250 for ; Thu, 17 Dec 2020 15:50:19 +0100 (CET) From: Dominik Csapak To: pbs-devel@lists.proxmox.com Date: Thu, 17 Dec 2020 15:50:18 +0100 Message-Id: <20201217145018.2902-1-d.csapak@proxmox.com> X-Mailer: git-send-email 2.20.1 MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-SPAM-LEVEL: Spam detection results: 0 AWL 0.281 Adjusted score from AWL reputation of From: address KAM_DMARC_STATUS 0.01 Test Rule for DKIM or SPF Failure with Strict Alignment RCVD_IN_DNSWL_MED -2.3 Sender listed at https://www.dnswl.org/, medium trust 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. [daemon.rs] Subject: [pbs-devel] [PATCH proxmox-backup v2] tools/daemon: improve reload behaviour 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, 17 Dec 2020 14:50:20 -0000 it seems that sometimes, the child process signal gets handled before the parent process signal. Systemd then ignores the childs signal (finished reloading) and only after going into reloading state because of the parent. this will never finish. Instead, wait for the state to change to 'reloading' after sending that signal in the parent, an only fork afterwards. This way we ensure that systemd knows about the reloading before actually trying to do it. Signed-off-by: Dominik Csapak --- changes from v1: * introduce wait_service_is_(not_)state it is a bit more generic has a better name * factor the common code out into get_service_state src/tools/daemon.rs | 45 ++++++++++++++++++++++++++++----------------- 1 file changed, 28 insertions(+), 17 deletions(-) diff --git a/src/tools/daemon.rs b/src/tools/daemon.rs index 6bb4a41b..0e3a174a 100644 --- a/src/tools/daemon.rs +++ b/src/tools/daemon.rs @@ -291,6 +291,7 @@ 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) = reloader.take().unwrap().fork_restart() { log::error!("error during reload: {}", e); let _ = systemd_notify(SystemdNotify::Status("error during reload".to_string())); @@ -305,7 +306,7 @@ where // FIXME: this is a hack, replace with sd_notify_barrier when available if server::is_reload_request() { - wait_service_is_active(service_name).await?; + wait_service_is_not_state(service_name, "reloading").await?; } log::info!("daemon shut down..."); @@ -313,26 +314,36 @@ where } // hack, do not use if unsure! -async fn wait_service_is_active(service: &str) -> Result<(), Error> { +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::delay_for(std::time::Duration::new(1, 0)).await; - loop { - 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), - }; + while get_service_state(service).await? != state { + tokio::time::delay_for(std::time::Duration::new(5, 0)).await; + } + Ok(()) +} - if text.trim().trim_start() != "reloading" { - return Ok(()); - } +async fn wait_service_is_not_state(service: &str, state: &str) -> Result<(), Error> { + tokio::time::delay_for(std::time::Duration::new(1, 0)).await; + while get_service_state(service).await? == state { tokio::time::delay_for(std::time::Duration::new(5, 0)).await; } + Ok(()) } #[link(name = "systemd")] -- 2.20.1