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 78811612D3 for ; Fri, 18 Feb 2022 12:38:34 +0100 (CET) Received: from firstgate.proxmox.com (localhost [127.0.0.1]) by firstgate.proxmox.com (Proxmox) with ESMTP id 9FD7A2942D for ; Fri, 18 Feb 2022 12:38:33 +0100 (CET) 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)) (No client certificate requested) by firstgate.proxmox.com (Proxmox) with ESMTPS id 47C562939B for ; Fri, 18 Feb 2022 12:38:30 +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 165D54628B for ; Fri, 18 Feb 2022 12:38:30 +0100 (CET) From: Aaron Lauterer To: pve-devel@lists.proxmox.com Date: Fri, 18 Feb 2022 12:38:26 +0100 Message-Id: <20220218113827.1415641-6-a.lauterer@proxmox.com> X-Mailer: git-send-email 2.30.2 In-Reply-To: <20220218113827.1415641-1-a.lauterer@proxmox.com> References: <20220218113827.1415641-1-a.lauterer@proxmox.com> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-SPAM-LEVEL: Spam detection results: 0 AWL 0.012 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 SPF_HELO_NONE 0.001 SPF: HELO does not publish an SPF Record SPF_PASS -0.001 SPF: sender matches SPF record T_SCC_BODY_TEXT_LINE -0.01 - Subject: [pve-devel] [PATCH manager 5/6] ui: osd: warn if removal could be problematic X-BeenThere: pve-devel@lists.proxmox.com X-Mailman-Version: 2.1.29 Precedence: list List-Id: Proxmox VE development discussion List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 18 Feb 2022 11:38:34 -0000 If an OSD is removed during the wrong conditions, it could lead to blocked IO or worst case data loss. Check against global flags that limit the capabilities of Ceph to heal itself (norebalance, norecover, noout) and if there are degraded objects. Unfortunately, the 'safe-to-destroy' API endpoint will not help here as it only works as long as the OSD is still running. By the time the destroy button is enabled, the OSD needs to be stopped. Signed-off-by: Aaron Lauterer --- After the short discussion on the previous version [0] and the hints to ok-to-stop & safe-to-destroy I kept the original approach with the reason given in the commit message. But now the checks are run before opening the window and showing a loading screen. [0] https://lists.proxmox.com/pipermail/pve-devel/2022-February/051597.html www/manager6/ceph/OSD.js | 66 +++++++++++++++++++++++++++++++++++++++- 1 file changed, 65 insertions(+), 1 deletion(-) diff --git a/www/manager6/ceph/OSD.js b/www/manager6/ceph/OSD.js index e126f8d0..27f56760 100644 --- a/www/manager6/ceph/OSD.js +++ b/www/manager6/ceph/OSD.js @@ -178,6 +178,20 @@ Ext.define('PVE.CephRemoveOsd', { labelWidth: 130, fieldLabel: gettext('Cleanup Disks'), }, + { + xtype: 'displayfield', + name: 'osd-flag-hint', + userCls: 'pmx-hint', + value: gettext('Global flags limiting the self healing of Ceph are enabled.'), + hidden: true, + }, + { + xtype: 'displayfield', + name: 'degraded-objects-hint', + userCls: 'pmx-hint', + value: gettext('Objects are degraded. Consider waiting until the cluster is healthy.'), + hidden: true, + }, ], initComponent: function() { let me = this; @@ -198,6 +212,13 @@ Ext.define('PVE.CephRemoveOsd', { }); me.callParent(); + + if (me.warnings.flags) { + me.down('field[name=osd-flag-hint]').setHidden(false); + } + if (me.warnings.degraded) { + me.down('field[name=degraded-objects-hint]').setHidden(false); + } }, }); @@ -434,12 +455,55 @@ Ext.define('PVE.node.CephOsdTree', { }).show(); }, - destroy_osd: function() { + destroy_osd: async function() { let me = this; let vm = this.getViewModel(); + + let warnings = { + flags: false, + degraded: false, + }; + + let flagsPromise = Proxmox.Async.api2({ + url: `/cluster/ceph/flags`, + method: 'GET', + }); + + let statusPromise = Proxmox.Async.api2({ + url: `/cluster/ceph/status`, + method: 'GET', + }); + + me.getView().mask(gettext('Please wait...')); + + try { + let result = await Promise.all([flagsPromise, statusPromise]); + + let flagsData = result[0].result.data; + let statusData = result[1].result.data; + + let flags = Array.from( + flagsData.filter(v => v.value), + v => v.name, + ).filter(v => ['norebalance', 'norecover', 'noout'].includes(v)); + + if (flags.length) { + warnings.flags = true; + } + if (Object.keys(statusData.pgmap).includes('degraded_objects')) { + warnings.degraded = true; + } + } catch (error) { + Ext.Msg.alert(gettext('Error'), error.htmlStatus); + me.getView().unmask(); + return; + } + + me.getView().unmask(); Ext.create('PVE.CephRemoveOsd', { nodename: vm.get('osdhost'), osdid: vm.get('osdid'), + warnings: warnings, taskDone: () => { me.reload(); }, }).show(); }, -- 2.30.2