diff --git a/docs/cluster-watcher.md b/docs/cluster-watcher.md index 79058c5..20358c8 100644 --- a/docs/cluster-watcher.md +++ b/docs/cluster-watcher.md @@ -327,12 +327,13 @@ hide a real outage. Built on the paged, server-side lists from #69. No page ever lists everything at once. -- **Dashboard:** one line per cluster: its version, state and a summary +- **Clusters page:** one line per cluster: its version, state and a summary in its kind's terms: "31/32 nodes ready · 3,300 workloads" for Kubernetes, "2/2 controllers ready · 600 volumes · 71% used" for an array, "CPU 41% · system ASP 85% · 4 of 5 subsystems active" for an IBM i partition. The network map's cluster boxes use the same line. - The "needs attention" list takes workloads too, capped as for hosts. + The dashboard counts the clusters with a problem, and its "needs you" + and "can wait" lists take workloads too, capped as for hosts. - **Clusters:** in sections by kind (Kubernetes, Virtualization, Storage, IBM i, Secrets), the ones that need a look first in each, with a jump list counting each kind and its problems. Filters for kind, "need a diff --git a/docs/formats.md b/docs/formats.md index c70d2de..daf8275 100644 --- a/docs/formats.md +++ b/docs/formats.md @@ -728,8 +728,29 @@ restarts; admins can preview it and send it by hand on the Reports page. ### The dashboard's briefing -The same history feeds the dashboard. `GET /api/v1/overview` carries, -besides the readings: +The dashboard (Today) is written to be read, not scanned for numbers. It +opens with a sentence on whether anything needs you and whether +customers are affected (the services with `tier: public`), then: + +- **Needs you:** critical and serious problems nobody has picked up, each + with when it started, whether people were told and what it takes down. + **I'm on it** is the acknowledgement: the repeats stop, and the problem + moves to **Being handled** with who has it. +- **Can wait:** warnings, one line each with why. +- **Your services:** each service's state and its last 24 hours, one bar + per half hour. The **Services** page lists them all by tier (what + customers use, what runs it, where the data lives, the edge); picking one + shows its parts in trouble, what it needs and what needs it. +- **Since you last looked:** what opened and closed since your last visit. +- **The fleet:** hosts reporting, containers, clusters and the busiest + host, and what's worth watching: disks filling up, hosts busier than + usual for the hour, hosts restarted in the last day. The **Hosts** page + shows the same list over one square per host, grouped by the network + map's sites and by role, the host name's first word after its site + (phx1-app05 is an app server); the table is a click away. + +The same history feeds it. `GET /api/v1/overview` carries, besides the +readings: - `today`: what happened since this person last looked. A visit ends after 30 minutes without the dashboard open, and the end of the last one is @@ -754,7 +775,8 @@ besides the readings: The strips and uptimes are read from history once a minute (30 days every ten), the watch list every ten minutes, whatever the number of dashboards -open. +open. `GET /api/v1/fleet` is the Hosts page's squares: every host's state +by site and role, the hosts that need a look per site, and the watch list. ## checks.yaml: active checks diff --git a/internal/server/fleetgrid.go b/internal/server/fleetgrid.go new file mode 100644 index 0000000..bf7da5b --- /dev/null +++ b/internal/server/fleetgrid.go @@ -0,0 +1,148 @@ +package server + +import ( + "net/http" + "sort" + "strings" + "time" +) + +// The Hosts page's grid (#72): one square per host, grouped by site (the +// network map's) and role, so at thousands of hosts the odd one out still +// stands out. GET /api/v1/fleet; not under /hosts/, where a host named +// "grid" would lose its page. + +// GridSite is a site's hosts by role. +type GridSite struct { + ID string `json:"id"` + Name string `json:"name"` + Roles []GridRole `json:"roles"` + Hosts int `json:"hosts"` + // Trouble is its hosts that need a look, worst first. + Trouble []GridHost `json:"trouble"` +} + +// GridRole is one role's hosts in a site. +type GridRole struct { + Role string `json:"role"` + Hosts []GridHost `json:"hosts"` +} + +// GridHost is one square. +type GridHost struct { + Name string `json:"name"` + Status string `json:"status"` + Word string `json:"word"` +} + +// hostRole is what a host is from its name: the first word after its +// site, without its number. phx1-app05 in phx1 is "app", web-02 is "web", +// win-dc01 is "win", host3 is "host". +func hostRole(name, site string) string { + r := name + if site != "" && strings.HasPrefix(r, site) { + r = r[len(site):] + } + r = strings.Trim(r, "-_.") + if i := strings.IndexAny(r, "-_."); i >= 0 { + r = r[:i] + } + r = strings.TrimRight(r, "0123456789") + if r == "" { + return "other" + } + return r +} + +// fleetGrid groups hosts by site and role. siteOf names each host's site +// (id → name in names); hosts in none go under "Elsewhere". +func fleetGrid(hosts []HostView, siteOf map[string]string, names map[string]string) []GridSite { + by := map[string]*GridSite{} + roles := map[string]map[string]*GridRole{} + // A host the map didn't place (a collector, one without map samples) + // goes with the site its name starts with, when one does: phx1-stor01 + // with phx1. + prefixes := map[string]string{} + for id, n := range names { + if n != "" { + prefixes[n] = id + } + } + for _, h := range hosts { + id := siteOf[h.Name] + if id == "" { + if p, _, ok := strings.Cut(h.Name, "-"); ok && prefixes[p] != "" { + id = prefixes[p] + } + } + s := by[id] + if s == nil { + name := names[id] + if id == "" { + name = "Elsewhere" + } + s = &GridSite{ID: id, Name: name, Trouble: []GridHost{}} + by[id] = s + roles[id] = map[string]*GridRole{} + } + prefix := names[id] + role := hostRole(h.Name, prefix) + r := roles[id][role] + if r == nil { + r = &GridRole{Role: role} + roles[id][role] = r + } + st := h.Status + if h.Silent { + st = "critical" + } + g := GridHost{Name: h.Name, Status: st, Word: h.Word} + r.Hosts = append(r.Hosts, g) + s.Hosts++ + if st == "warning" || st == "serious" || st == "critical" { + s.Trouble = append(s.Trouble, g) + } + } + out := []GridSite{} + for id, s := range by { + for _, r := range roles[id] { + sort.Slice(r.Hosts, func(i, j int) bool { return r.Hosts[i].Name < r.Hosts[j].Name }) + s.Roles = append(s.Roles, *r) + } + // The biggest role first (the app servers), then by name. + sort.Slice(s.Roles, func(i, j int) bool { + if len(s.Roles[i].Hosts) != len(s.Roles[j].Hosts) { + return len(s.Roles[i].Hosts) > len(s.Roles[j].Hosts) + } + return s.Roles[i].Role < s.Roles[j].Role + }) + sort.SliceStable(s.Trouble, func(i, j int) bool { return statusRank[s.Trouble[i].Status] > statusRank[s.Trouble[j].Status] }) + out = append(out, *s) + } + // Sites by size, Elsewhere last. + sort.Slice(out, func(i, j int) bool { + if (out[i].ID == "") != (out[j].ID == "") { + return out[j].ID == "" + } + if out[i].Hosts != out[j].Hosts { + return out[i].Hosts > out[j].Hosts + } + return out[i].Name < out[j].Name + }) + return out +} + +func (srv *Server) handleFleet(w http.ResponseWriter, r *http.Request) { + now := time.Now() + hosts, _ := srv.view(now) + siteOf, names := map[string]string{}, map[string]string{} + if g := srv.mapGraph(now); g != nil { + for _, s := range g.Sites { + names[s.ID] = s.Name + for _, h := range s.Hosts { + siteOf[h] = s.ID + } + } + } + writeJSON(w, http.StatusOK, map[string]any{"sites": fleetGrid(hosts, siteOf, names), "watch": srv.watch(hosts, now)}) +} diff --git a/internal/server/server.go b/internal/server/server.go index d6b31c4..7670912 100644 --- a/internal/server/server.go +++ b/internal/server/server.go @@ -428,6 +428,7 @@ func (srv *Server) Handler() http.Handler { mux.HandleFunc("GET /api/v1/map/network", srv.needSession(srv.handleMapNetwork)) mux.HandleFunc("GET /api/v1/map/services", srv.needSession(srv.handleMapServices)) mux.HandleFunc("GET /api/v1/services", srv.needSession(srv.handleServices)) + mux.HandleFunc("GET /api/v1/fleet", srv.needSession(srv.handleFleet)) mux.HandleFunc("GET /api/v1/map/find", srv.needSession(srv.handleMapFind)) mux.HandleFunc("GET /api/v1/map/found", srv.needSession(srv.handleMapFound)) mux.HandleFunc("GET /api/v1/map/corrections", srv.needSession(srv.handleMapCorrections)) diff --git a/internal/server/today_test.go b/internal/server/today_test.go index 62b35e0..c9b4c21 100644 --- a/internal/server/today_test.go +++ b/internal/server/today_test.go @@ -151,3 +151,34 @@ func TestWithIncidents(t *testing.T) { t.Errorf("others: %+v %+v", got[1].Incident, got[2].Incident) } } + +func TestFleetGrid(t *testing.T) { + for _, c := range [][3]string{{"phx1-app05", "phx1", "app"}, {"web-02", "", "web"}, {"host3", "", "host"}, {"db1.example.com", "", "db"}, {"phx1-07", "phx1", "other"}, {"win-dc01", "", "win"}, {"lb-edge-01", "", "lb"}} { + if got := hostRole(c[0], c[1]); got != c[2] { + t.Errorf("hostRole(%s, %s) = %s, want %s", c[0], c[1], got, c[2]) + } + } + hosts := []HostView{ + {Name: "phx1-app02", Status: "good"}, {Name: "phx1-app01", Status: "warning", Word: "disk 91%"}, + {Name: "phx1-db01", Status: "good"}, {Name: "lon1-app01", Status: "good"}, + {Name: "bench", Status: "good", Silent: true}, {Name: "phx1-stor01", Status: "good"}, + } + siteOf := map[string]string{"phx1-app01": "s1", "phx1-app02": "s1", "phx1-db01": "s1", "lon1-app01": "s2"} + names := map[string]string{"s1": "phx1", "s2": "lon1"} + got := fleetGrid(hosts, siteOf, names) + if len(got) != 3 || got[0].Name != "phx1" || got[1].Name != "lon1" || got[2].Name != "Elsewhere" { + t.Fatalf("sites = %+v", got) + } + if got[0].Hosts != 4 { + t.Errorf("phx1-stor01 should join phx1 by its name: %+v", got[0]) + } + if r := got[0].Roles; len(r) != 3 || r[0].Role != "app" || r[0].Hosts[0].Name != "phx1-app01" || r[1].Role != "db" || r[2].Role != "stor" { + t.Errorf("phx1 roles = %+v", r) + } + if tr := got[0].Trouble; len(tr) != 1 || tr[0].Name != "phx1-app01" { + t.Errorf("phx1 trouble = %+v", tr) + } + if tr := got[2].Trouble; len(tr) != 1 || tr[0].Status != "critical" { + t.Errorf("a silent host is trouble: %+v", tr) + } +} diff --git a/web/src/lib/FleetGrid.svelte b/web/src/lib/FleetGrid.svelte new file mode 100644 index 0000000..f8d526d --- /dev/null +++ b/web/src/lib/FleetGrid.svelte @@ -0,0 +1,144 @@ + + +{#if error}

{error}

{/if} + +{#if watch && (watch.filling.length || watch.busier.length || watch.restarted_n)} +
+

Worth watching

+
+ {#if watch.filling.length} +
+

Filling up

+
    {#each watch.filling as d (d.host + d.mount)}
  • {d.host}{Math.round(d.pct)}%{d.mount} · full {days(d.full_days)}
  • {/each}
+
+ {/if} + {#if watch.busier.length} +
+

Busier than usual

+
    {#each watch.busier as b (b.host + b.what)}
  • {b.host}{Math.round(b.now)}% {b.what === 'cpu' ? 'CPU' : 'memory'}usually {Math.round(b.usual)}% at this hour
  • {/each}
+
+ {/if} + {#if watch.restarted_n} +
+

Restarted in the last day · {watch.restarted_n}

+
    {#each watch.restarted as r (r.host)}
  • {r.host}{duration(r.up_s)} ago
  • {/each}
+ {#if watch.restarted_n > watch.restarted.length}

and {watch.restarted_n - watch.restarted.length} more

{/if} +
+ {/if} +
+
+{/if} + +{#if sites === null} +

Loading…

+{:else} + +
+ {#each sites as s (s.id)} +
+
+

{s.name}

+ {s.hosts} {s.hosts === 1 ? 'host' : 'hosts'} · {s.trouble.length ? `${s.trouble.length} need a look` : 'all fine'} +
+ {#each s.roles as r (r.role)} +
+ {roleName(r.role)} · {r.hosts.length} + + {#each r.hosts as h (h.name)}{/each} + +
+ {/each} + {#if s.trouble.length} + + {/if} +
+ {/each} +
+{/if} + + diff --git a/web/src/lib/Shell.svelte b/web/src/lib/Shell.svelte index 6cfbcbb..7891e9b 100644 --- a/web/src/lib/Shell.svelte +++ b/web/src/lib/Shell.svelte @@ -70,29 +70,36 @@ store('folded', JSON.stringify(folded)); } type Item = { href: string; icon: IconName; label: string; show?: boolean; exact?: boolean; meta?: number; sev?: string; tip?: string }; - const overview = $derived(([ - { href: '/', icon: 'dashboard', label: 'Dashboard', exact: true, show: true }, - // One entry for every host: a big fleet's partial list told you little. - { href: '/hosts', icon: 'hosts', label: 'Hosts', show: true, meta: hostLook, sev: hostCritical ? 'critical' : 'warning', tip: hostLook ? `${hostLook} need a look` : '' } + // Shaped by what people come to do (#72): today's briefing and what to + // act on first, then the fleet, the maps, and what Cairn OBS is + // connected to. + const hasServices = $derived((live.overview?.services?.length ?? 0) > 0); + const today = $derived(([ + { href: '/', icon: 'dashboard', label: 'Today', exact: true, show: true }, + { href: '/services', icon: 'services', label: 'Services', show: hasServices }, + { href: '/alerts', icon: 'bell', label: 'Alerts', show: true, meta: unacked, sev: 'critical', tip: unacked ? `${unacked} not acknowledged` : '' }, + { href: '/reports', icon: 'report', label: 'Reports', show: f?.reports } ] as Item[]).filter((i) => i.show)); - const infra = $derived(([ - { href: '/map/network', icon: 'network', label: 'Network map', show: f?.maps }, - { href: '/map/services', icon: 'services', label: 'Service map', show: f?.maps }, - { href: '/mail', icon: 'mail', label: 'Mail', show: f?.mail }, - { href: '/data', icon: 'database', label: 'Data layer', show: f?.data }, + const fleet = $derived(([ + // One entry for every host: a big fleet's partial list told you little. + { href: '/hosts', icon: 'hosts', label: 'Hosts', show: true, meta: hostLook, sev: hostCritical ? 'critical' : 'warning', tip: hostLook ? `${hostLook} need a look` : '' }, { href: '/clusters', icon: 'cluster', label: 'Clusters', show: f?.workloads, meta: clusterProblems, sev: clusterSeverity, tip: clusterProblems ? `${clusterProblems} need a look` : '' }, { href: '/workloads', icon: 'grid', label: 'Workloads', show: f?.workloads }, - { href: '/containers', icon: 'box', label: 'Containers', show: f?.containers || problems > 0, meta: problems, sev: containerSeverity, tip: problems ? `${problems} need a look` : '' }, + { href: '/containers', icon: 'box', label: 'Containers', show: f?.containers || problems > 0, meta: problems, sev: containerSeverity, tip: problems ? `${problems} need a look` : '' } + ] as Item[]).filter((i) => i.show)); + const maps = $derived(([ + { href: '/map/network', icon: 'network', label: 'Network map', show: f?.maps }, + { href: '/map/services', icon: 'services', label: 'Service map', show: f?.maps } + ] as Item[]).filter((i) => i.show)); + const connected = $derived(([ + { href: '/checks', icon: 'check', label: 'Checks', show: f?.checks || checksDown > 0, meta: checksDown, sev: live.overview?.checks?.severity ?? 'warning', tip: checksDown ? `${checksDown} down` : '' }, + { href: '/mail', icon: 'mail', label: 'Mail', show: f?.mail }, + { href: '/data', icon: 'database', label: 'Data layer', show: f?.data }, { href: '/certificates', icon: 'lock', label: 'Certificates', show: f?.certificates }, { href: '/backups', icon: 'archive', label: 'Backups', show: f?.backups }, { href: '/cloudflare', icon: 'cloud', label: 'Cloudflare', show: f?.cloudflare }, { href: '/akamai', icon: 'globe', label: 'Akamai', show: f?.akamai } ] as Item[]).filter((i) => i.show)); - const watch = $derived(([ - { href: '/checks', icon: 'check', label: 'Checks', show: f?.checks || checksDown > 0, meta: checksDown, sev: live.overview?.checks?.severity ?? 'warning', tip: checksDown ? `${checksDown} down` : '' }, - { href: '/alerts', icon: 'bell', label: 'Alerts', show: true, meta: unacked, sev: 'critical', tip: unacked ? `${unacked} not acknowledged` : '' }, - { href: '/reports', icon: 'report', label: 'Reports', show: f?.reports } - ] as Item[]).filter((i) => i.show)); const setup: Item[] = [ { href: '/configure', icon: 'settings', label: 'Overview', exact: true }, { href: '/configure/hosts', icon: 'hosts', label: 'Hosts' }, @@ -215,9 +222,10 @@ {@render group('Configure', setup)} {@render group('Access', access)} {:else} - {@render group('Overview', overview)} - {#if infra.length}{@render group('Infrastructure', infra)}{/if} - {@render group('Watch', watch)} + {@render group('Today', today)} + {@render group('Fleet', fleet)} + {#if maps.length}{@render group('Maps', maps)}{/if} + {#if connected.length}{@render group('Connected to', connected)}{/if} {/if}
diff --git a/web/src/lib/Strip.svelte b/web/src/lib/Strip.svelte new file mode 100644 index 0000000..d8dacbf --- /dev/null +++ b/web/src/lib/Strip.svelte @@ -0,0 +1,18 @@ + + +{#each cells as c, i (i)}{/each} + + diff --git a/web/src/lib/api.ts b/web/src/lib/api.ts index b4031b0..e6d9bc7 100644 --- a/web/src/lib/api.ts +++ b/web/src/lib/api.ts @@ -40,7 +40,25 @@ export interface VMLink { source: string; namespace?: string; name: string; node /** The libvirt VMs a host runs. */ export interface HostVMCount { total: number; running: number; error?: string; href: string } export interface UnitView { name: string; load: string; active: string; sub: string; restarts: number; since?: string; host: string; severity: Severity; word: string } -export interface Attention { severity: Severity; title: string; detail: string; href: string; host: string } +export interface Attention { + severity: Severity; title: string; detail: string; href: string; host: string; + key?: string; affected?: string; + /** The open incident it is, once there is one: the dashboard's "I'm on it" acknowledges it. */ + incident?: { id: string; opened: string; fired: string | null; ack: { by: string; at: string } | null }; +} +/** What happened since this person last looked (internal/server/today.go). */ +export interface Today { since: string; last_visit: boolean; events: TodayEvent[]; opened: number; resolved: number; fixed_itself: number; told: number } +export interface TodayEvent { id: string; severity: Severity; title: string; host?: string; href?: string; at: string; opened: string; resolved?: string; ack_by?: string; told: boolean } +/** A service's last 24 hours as 48 half-hour cells (the worst status in each, '' unknown), and its uptime (-1 unknown). */ +export interface ServiceHistory { cells: string[]; pct_24h: number; pct_30d: number } +export interface ServiceBrief { id: string; name: string; tier: string; status: Severity; word: string; history: ServiceHistory } +/** The few hosts heading somewhere, in place of gauges. */ +export interface Watch { + filling: { host: string; mount: string; pct: number; full_days: number }[]; + busier: { host: string; what: 'cpu' | 'memory'; now: number; usual: number }[]; + restarted: { host: string; up_s: number }[]; + restarted_n: number; +} /** Every host in a few numbers (internal/server/lists.go). */ export interface Fleet { hosts: number; @@ -58,7 +76,7 @@ export interface HostRow { os?: string; uptime_s: number; cpu_pct: number; mem_pct: number; fullest?: Disk; containers: ContainerSummary; } /** hosts is every host in a small fleet, else the ones most in need; fleet counts them all. */ -export interface Overview { now: string; version: string; hosts: Host[]; fleet: Fleet; attention: Attention[]; containers: ContainerSummary; alerts: { firing: number; unacknowledged: number }; checks?: { down: number; severity: string }; features?: Features; clusters?: Cluster[] } +export interface Overview { now: string; version: string; hosts: Host[]; fleet: Fleet; attention: Attention[]; containers: ContainerSummary; alerts: { firing: number; unacknowledged: number }; checks?: { down: number; severity: string }; features?: Features; clusters?: Cluster[]; today?: Today; services?: ServiceBrief[]; watch?: Watch } /** A cluster agent's cluster: GET /api/v1/clusters, and the overview. */ export interface Cluster { name: string; status: Severity; word: string; heard: string | null; listed: string | null; agent?: string; version?: string; diff --git a/web/src/routes/+page.svelte b/web/src/routes/+page.svelte index bb261f9..d407ca8 100644 --- a/web/src/routes/+page.svelte +++ b/web/src/routes/+page.svelte @@ -1,13 +1,14 @@ -Cairn OBS · Dashboard +Cairn OBS · Today -
-
-
-
-
- -
-

{hello}{firstName ? ', ' + firstName : ''}

-

Here's how your systems are doing.

-
+
+
+
+

{hello}{firstName ? ', ' + firstName : ''} · {dayFmt.format(now)}

+ {#if o} +

{headline} {#if needs.length}{customers}{/if}

+ {#if subline || (!needs.length && customers)}

{!needs.length && customers ? customers + ' ' : ''}{subline}

{/if} + {:else} +

Looking…

+ {/if}
-
- {reporting}/{total} hosts reporting -
{hms(now)}{zone(now)} · {utc(now)}
-
-
-
+

+ {live.error ? live.error : checked < 0 ? 'Connecting' : checked < 3 ? 'Live · checked just now' : `Live · checked ${checked} s ago`} +

+ -{#if o} -
-
- -

{o.attention.length ? `Needs attention · ${o.attention.length}` : 'All clear'}

- -
- {#if o.attention.length} -
- {#each o.attention.slice(0, 6) as a} - -
{a.title}
{#if a.detail}

{a.detail}

{/if}
- -
+ {#if o} + {#if error}{/if} + + {#if needs.length || taken.length} +
+
+

Needs you{#if needs.length} · {needs.length}{/if}

+

Worst first. {needs.length ? 'Nobody has picked these up yet.' : 'Everything urgent has someone on it.'}

+
+ {#each needs as a (a.key || a.title)} +
+
+ + + {a.host ? a.host + ' · ' : ''}{a.incident ? 'started ' + ago(a.incident.opened, now) : 'just now'}{a.incident?.fired ? ' · people were told' : ''} + +
+

{a.title}

+ {#if a.detail}

{a.detail}

{/if} + {#if a.affected}

What it touches {a.affected}

{/if} +
+ {#if a.incident && canAck} + + {:else if a.incident && live.session?.demo} + + {/if} + Open + {#if a.incident}{a.incident.id}{/if} +
+
{/each} -
- {:else} -

Every host is reporting, no disk is past 80%, and every container is where it should be.

+ {#if taken.length} +
+

Being handled · {taken.length}

+
    + {#each taken as a (a.key || a.title)} +
  • + + {a.title} + {a.incident?.ack?.by} is on it · {ago(a.incident?.ack?.at ?? now, now)} +
  • + {/each} +
+
+ {/if} +
{/if} - - -
- - - = 90 ? 'critical' : (fullest?.pct ?? 0) >= 80 ? 'warning' : 'data'} bands={[{ from: 0.8, to: 0.9, tone: 'warning' }, { from: 0.9, to: 1, tone: 'critical' }]} /> - -
-
+ {#if later.length} +
+
+

Can wait · {later.length}

+

Worth a look today. None of these is hurting anything yet.

+
+
    + {#each later.slice(0, 6) as a (a.key || a.title)} +
  • + + {a.title}{#if a.detail}{a.detail}{/if} + {#if a.incident}{duration((now - new Date(a.incident.opened).getTime()) / 1000)}{/if} + Open +
  • + {/each} +
+ {#if later.length > 6}And {later.length - 6} more on the Alerts page{/if} +
+ {/if} -
- hosts.length ? `the ${hosts.length} most in need, of ${total}` : 'cpu · last hour'} href={total > hosts.length ? '/hosts' : undefined} hrefLabel="All hosts"> - - -
+ {#if !needs.length && !later.length && !taken.length} +
+ +
+

Nothing needs you right now

+

Cairn OBS tells the alert channels if that changes.{watch?.filling.length ? ` Next to look at: ${watch.filling[0].host}'s ${watch.filling[0].mount}, which fills ${days(watch.filling[0].full_days)}.` : ''}

+
+ This week’s report +
+ {/if} - {#if o.clusters?.length} -
- - - {/if} + + {/if} - {#if c} -
- -
-
{c.running}running fine
-
0}>{c.problems}need a look
-
{c.stopped}stopped on purpose
-
{c.ci}CI jobs now
+ {#if today} +
+
+

Since you last looked

+

{today.last_visit ? `You were last here ${ago(today.since, now)}, at ${hm(today.since)}` : 'The last 12 hours'}

- -
+ {#if today.events.length} +
    + {#each today.events as e (e.id)} + {@const [word, tone] = outcome(e)} +
  1. + + + {#if e.href}{e.title}{:else}{e.title}{/if} + {word} +
  2. + {/each} +
+

+ {today.opened} opened, {today.resolved} closed{today.fixed_itself ? ` (${today.fixed_itself} on their own)` : ''}. {today.told ? `${today.told} ${today.told === 1 ? 'alert' : 'alerts'} went out to people.` : 'Nobody was alerted.'} + {#if today.opened + today.resolved > today.events.length}Everything on the Alerts page{/if} +

+ {:else} +

Nothing opened or closed since then.

+ {/if} + + {/if} + +
+
+

The fleet

+

All hosts{#if clusters.length} · Clusters{/if}

+
+ + {#if watch && (watch.filling.length || watch.busier.length || watch.restarted_n)} +
+

Worth watching

+
    + {#each watch.filling as d (d.host + d.mount)} +
  • {d.host} {d.mount} is {Math.round(d.pct)}% full and fills {days(d.full_days)}
  • + {/each} + {#each watch.busier as b (b.host + b.what)} +
  • {b.host} {b.what === 'cpu' ? 'CPU' : 'memory'} at {Math.round(b.now)}%, usually {Math.round(b.usual)}% at this hour
  • + {/each} + {#if watch.restarted_n} +
  • + {watch.restarted_n === 1 ? 'Restarted' : `${watch.restarted_n} hosts restarted`} in the last day: + {#each watch.restarted as r, i (r.host)}{i ? ', ' : ' '}{r.host} {duration(r.up_s)} ago{/each}{watch.restarted_n > watch.restarted.length ? ` and ${watch.restarted_n - watch.restarted.length} more` : ''} +
  • + {/if} +
+
+ {/if} +
{/if} -{:else} -

Loading…

-{/if} +
diff --git a/web/src/routes/hosts/+page.svelte b/web/src/routes/hosts/+page.svelte index 5496d25..230a870 100644 --- a/web/src/routes/hosts/+page.svelte +++ b/web/src/routes/hosts/+page.svelte @@ -2,12 +2,22 @@ import Icon from '$lib/Icon.svelte'; import Status from '$lib/Status.svelte'; import Pager from '$lib/Pager.svelte'; + import FleetGrid from '$lib/FleetGrid.svelte'; + import { goto } from '$app/navigation'; + import { page } from '$app/state'; import { get, SignedOut, type HostRow } from '$lib/api'; import { live } from '$lib/live.svelte'; import { ago, pct } from '$lib/format'; - // The hosts list, filtered and paged by obs-beacond: a fleet can be - // thousands of hosts. + // Squares by site and role first (#72); the list, filtered and paged by + // obs-beacond, a click away: a fleet can be thousands of hosts. + const view = $derived(page.url.searchParams.get('view') === 'list' ? 'list' : 'grid'); + function setView(v: string) { + const u = new URL(page.url); + if (v === 'list') u.searchParams.set('view', 'list'); + else u.searchParams.delete('view'); + void goto(u, { replaceState: true, noScroll: true, keepFocus: true }); + } const limit = 100; let rows = $state([]); let total = $state(0); @@ -41,6 +51,7 @@ } } $effect(() => { + if (view !== 'list') return; const args = [q, status, offset] as const; void load(...args); const t = setInterval(() => void load(...args), 10_000); @@ -62,10 +73,20 @@
-

Hosts

Every host with an agent, the ones that need a look first. Adding and removing hosts is under Configure.

- {#if live.seesAll}{/if} +

Hosts

Every host with an agent, grouped by site and role so the odd one out stands out. Adding and removing hosts is under Configure.

+
+ + + + + {#if live.seesAll} Configure{/if} +
+{#if view === 'grid'} + +{:else} + {#if error}

{error}

{/if}
@@ -97,8 +118,10 @@
+{/if}

Refreshes every 10 seconds.

diff --git a/web/src/routes/services/+page.svelte b/web/src/routes/services/+page.svelte new file mode 100644 index 0000000..83dc6db --- /dev/null +++ b/web/src/routes/services/+page.svelte @@ -0,0 +1,227 @@ + + +Cairn OBS · Services + +
+
+
+
+

{heading || 'Services'}

+

Grouped by who depends on them. Pick one to see what it’s made of and what breaks if it goes.

+
+ {#if all.length} +
+ + + +
+ {/if} +
+ + {#if error}{/if} + + {#if services === null} +

Loading…

+ {:else if !topology || !all.length} +

No services yet. Services come from the service map: declare them in topology.yaml, or correct what the map found (docs/maps.md).

+ {:else} +
+
+ {#each tiers as t (t.id)} +
+

{t.name}{#if t.blurb} · {t.blurb}{/if}

+
+ {#each t.rows as s (s.id)} + + {/each} +
+
+ {/each} +
+ + {#if sel} + + {/if} +
+ {/if} +
+ +