Merge pull request '## Summary' (#60) from issue-48-49-hosts-page-controls into master

Reviewed-on: #60

README.md

@@ -154,6 +154,19 @@ The UI includes:
 - `/self-check/` for runtime checks
 - `/logs/` for filtered pobsync service logs
 
+## Bandwidth Limits
+
+Global config can set an rsync bandwidth limit in KB/s. The default `0` means unlimited. Each host can inherit the
+global value, set `0` to explicitly run unlimited, or set its own limit for slower remote links.
+
+For VPN-backed or remote backups, start conservatively and adjust after watching normal traffic:
+
+- `2500` KB/s is roughly 20 Mbit/s
+- `5000` KB/s is roughly 40 Mbit/s
+- `10000` KB/s is roughly 80 Mbit/s
+
+pobsync passes the effective value to rsync as `--bwlimit=<KB/s>` and shows it on the host detail and run detail pages.
+
 ## Restoring Data
 
 pobsync treats restores as an explicit manual operation. The control panel shows restore guidance on each snapshot

src/pobsync/commands/run_scheduled.py

@@ -23,6 +23,7 @@ from ..util import ensure_dir, realpath_startswith, sanitize_host, write_yaml_at
 
 
 DEFAULT_DRY_RUN_TIMEOUT_SECONDS = 900
+RSYNC_PARTIAL_VANISHED_EXIT_CODE = 24
 
 
 def dry_run_log_path(host: str, run_id: int | None = None) -> Path:
@@ -72,6 +73,24 @@ def classify_rsync_failure(exit_code: int | None, log_tail: list[str]) -> dict[s
     }
 
 
+def classify_rsync_warning(exit_code: int | None, log_tail: list[str]) -> dict[str, str] | None:
+    joined_tail = "\n".join(log_tail).lower()
+    if exit_code == RSYNC_PARTIAL_VANISHED_EXIT_CODE:
+        return {
+            "category": "vanished",
+            "message": "Some source files vanished during rsync.",
+            "hint": "This is common on live systems. The snapshot was kept, but review the rsync log if this happens often.",
+        }
+    if exit_code in (None, RSYNC_PARTIAL_VANISHED_EXIT_CODE) and (
+        "file has vanished" in joined_tail or "vanished before it could be transferred" in joined_tail
+    ):
+        return {
+            "category": "vanished",
+            "message": "Some source files vanished during rsync.",
+            "hint": "This is common on live systems. The snapshot was kept, but review the rsync log if this happens often.",
+        }
+    return None
+
 def _collect_run_stats(
     *,
     log_path: Path,
@@ -158,6 +177,7 @@ def run_scheduled(
     run_id: int | None = None,
     cancel_check: Callable[[], bool] | None = None,
     verbose_output: bool = False,
+    state_callback: Callable[[dict[str, Any]], None] | None = None,
 ) -> dict[str, Any]:
 
     host = sanitize_host(host)
@@ -258,6 +278,7 @@ def run_scheduled(
                 "exit_code": result.exit_code,
                 "command": result.command,
                 "log_tail": log_tail,
+                "bwlimit_kbps": bwlimit_kbps,
             },
         }
         if result.exit_code != 0:
@@ -316,20 +337,65 @@ def run_scheduled(
             "ended_at": None,
             "duration_seconds": None,
             "base": _base_meta_from_path(base_dir, link_dest),
-            "rsync": {"exit_code": None, "command": cmd, "stats": {}},
+            "rsync": {"exit_code": None, "command": cmd, "stats": {}, "bwlimit_kbps": bwlimit_kbps},
             "overrides": {"includes": [], "excludes": [], "base": None},
         }
 
         log_path.touch(exist_ok=True)
         write_yaml_atomic(meta_path, meta)
+        if state_callback is not None:
+            state_callback(
+                {
+                    "status": "running",
+                    "phase": "preparing",
+                    "snapshot": str(incomplete_dir),
+                    "log": str(log_path),
+                    "rsync": {"command": cmd, "exit_code": None, "bwlimit_kbps": bwlimit_kbps},
+                }
+            )
 
-        result = run_rsync(cmd, log_path=log_path, timeout_seconds=timeout_seconds, cancel_check=cancel_check)
+        def process_started(pid: int, pgid: int) -> None:
+            if state_callback is None:
+                return
+            state_callback(
+                {
+                    "status": "running",
+                    "phase": "rsync",
+                    "snapshot": str(incomplete_dir),
+                    "log": str(log_path),
+                    "rsync": {"command": cmd, "exit_code": None, "pid": pid, "pgid": pgid, "bwlimit_kbps": bwlimit_kbps},
+                }
+            )
+
+        run_rsync_kwargs: dict[str, Any] = {
+            "log_path": log_path,
+            "timeout_seconds": timeout_seconds,
+            "cancel_check": cancel_check,
+        }
+        if state_callback is not None:
+            run_rsync_kwargs["process_started"] = process_started
+        result = run_rsync(cmd, **run_rsync_kwargs)
+        log_tail = _read_log_tail(log_path)
+        warning = classify_rsync_warning(result.exit_code, log_tail)
+        successful_or_warning = result.exit_code == 0 or warning is not None
+        if state_callback is not None:
+            state_callback(
+                {
+                    "status": "running",
+                    "phase": "finalizing",
+                    "snapshot": str(incomplete_dir),
+                    "log": str(log_path),
+                    "rsync": {"command": cmd, "exit_code": result.exit_code, "log_tail": log_tail, "bwlimit_kbps": bwlimit_kbps},
+                }
+            )
 
         end_ts = utc_now()
         meta["ended_at"] = format_iso_z(end_ts)
         meta["duration_seconds"] = int((end_ts - ts).total_seconds())
         meta["rsync"]["exit_code"] = result.exit_code
-        meta["status"] = "cancelled" if result.cancelled else ("success" if result.exit_code == 0 else "failed")
+        meta["status"] = "cancelled" if result.cancelled else ("warning" if warning else ("success" if result.exit_code == 0 else "failed"))
+        if warning is not None:
+            meta["warning"] = warning
         meta["stats"] = _collect_run_stats(
             log_path=log_path,
             backup_root=Path(backup_root),
@@ -349,8 +415,7 @@ def run_scheduled(
                 "error": "rsync.log missing after execution",
             }
 
-        if result.exit_code != 0:
+        if not successful_or_warning:
-            log_tail = _read_log_tail(log_path)
             return {
                 "ok": False,
                 "dry_run": False,
@@ -366,6 +431,7 @@ def run_scheduled(
                     "exit_code": result.exit_code,
                     "command": result.command,
                     "log_tail": log_tail,
+                    "bwlimit_kbps": bwlimit_kbps,
                 },
                 "failure": classify_rsync_failure(result.exit_code, log_tail),
             }
@@ -404,7 +470,9 @@ def run_scheduled(
             "snapshot": str(final_dir),
             "base": str(base_dir) if base_dir else None,
             "log": str(final_log_path),
-            "rsync": {"exit_code": result.exit_code},
+            "status": meta["status"],
+            "warning": warning,
+            "rsync": {"exit_code": result.exit_code, "command": result.command, "log_tail": log_tail, "bwlimit_kbps": bwlimit_kbps},
             "verbose_output": bool(verbose_output),
             "duration_seconds": meta["duration_seconds"],
             "stats": meta["stats"],

src/pobsync/config/schemas.py

@@ -110,6 +110,7 @@ GLOBAL_SCHEMA = Schema(
 
 HOST_RSYNC_SCHEMA = Schema(
     fields={
+        "bwlimit_kbps": FieldSpec(int, required=False, min_value=0),
         "extra_args": FieldSpec(list, required=False, default=[], item=FieldSpec(str)),
     },
     allow_unknown=False,

src/pobsync/rsync.py

@@ -82,6 +82,7 @@ def run_rsync(
     log_path: Path,
     timeout_seconds: int,
     cancel_check: Callable[[], bool] | None = None,
+    process_started: Callable[[int, int], None] | None = None,
 ) -> RsyncResult:
     """
     Run rsync and always write stdout/stderr to log_path.
@@ -95,6 +96,8 @@ def run_rsync(
 
     with log_path.open("ab") as f:
         process = subprocess.Popen(command, stdout=f, stderr=subprocess.STDOUT, start_new_session=True)
+        if process_started is not None:
+            process_started(process.pid, os.getpgid(process.pid))
         started = time.monotonic()
         while True:
             exit_code = process.poll()

src/pobsync_backend/admin.py

@@ -73,7 +73,7 @@ class HostConfigAdmin(admin.ModelAdmin):
         (None, {"fields": ("host", "address", "enabled")}),
         ("SSH override", {"fields": ("ssh_credential", "ssh_user", "ssh_port")}),
         ("Source", {"fields": ("source_root", "includes", "excludes_add", "excludes_replace")}),
-        ("Rsync override", {"fields": ("rsync_extra_args",)}),
+        ("Rsync override", {"fields": ("rsync_extra_args", "rsync_bwlimit_kbps")}),
         ("Retention", {"fields": ("retention_daily", "retention_weekly", "retention_monthly", "retention_yearly")}),
         ("Runtime state", {"fields": ("config",), "classes": ("collapse",)}),
         ("Timestamps", {"fields": ("created_at", "updated_at"), "classes": ("collapse",)}),

src/pobsync_backend/backup_runner.py

@@ -8,7 +8,13 @@ from pathlib import Path
 from django.db import transaction
 from django.utils import timezone
 
-from pobsync.commands.run_scheduled import DEFAULT_DRY_RUN_TIMEOUT_SECONDS, classify_rsync_failure, dry_run_log_path, run_scheduled
+from pobsync.commands.run_scheduled import (
+    DEFAULT_DRY_RUN_TIMEOUT_SECONDS,
+    classify_rsync_failure,
+    classify_rsync_warning,
+    dry_run_log_path,
+    run_scheduled,
+)
 from pobsync_backend.config_source import DjangoConfigSource
 from pobsync_backend.models import BackupRun, HostConfig
 from pobsync_backend.retention import run_sql_retention_apply
@@ -66,6 +72,7 @@ def execute_backup_run(
             run_id=run.id,
             cancel_check=lambda: _run_cancel_requested(run.id),
             verbose_output=bool(dry_run or verbose_output),
+            state_callback=lambda state: _record_running_state(run.id, state),
         )
     except Exception as exc:
         run.refresh_from_db()
@@ -83,6 +90,8 @@ def execute_backup_run(
     run.refresh_from_db()
     if result.get("cancelled") or run.status == BackupRun.Status.CANCELLED:
         run.status = BackupRun.Status.CANCELLED
+    elif result.get("status") == BackupRun.Status.WARNING:
+        run.status = BackupRun.Status.WARNING
     else:
         run.status = BackupRun.Status.SUCCESS if result.get("ok") else BackupRun.Status.FAILED
     run.ended_at = timezone.now()
@@ -201,11 +210,98 @@ def _run_cancel_requested(run_id: int) -> bool:
     return False
 
 
+def _record_running_state(run_id: int, state: dict[str, object]) -> None:
+    try:
+        run = BackupRun.objects.only("id", "status", "result", "snapshot_path", "rsync_exit_code").get(id=run_id)
+    except BackupRun.DoesNotExist:
+        return
+    if run.status != BackupRun.Status.RUNNING:
+        return
+
+    result = run.result if isinstance(run.result, dict) else {}
+    execution = result.get("execution") if isinstance(result.get("execution"), dict) else {}
+    rsync = result.get("rsync") if isinstance(result.get("rsync"), dict) else {}
+    incoming_rsync = state.get("rsync") if isinstance(state.get("rsync"), dict) else {}
+
+    log_path = state.get("log")
+    snapshot_path = state.get("snapshot")
+    phase = state.get("phase")
+    if isinstance(phase, str) and phase:
+        execution["phase"] = phase
+    if isinstance(log_path, str) and log_path:
+        execution["log"] = log_path
+    if isinstance(snapshot_path, str) and snapshot_path:
+        execution["snapshot"] = snapshot_path
+        run.snapshot_path = snapshot_path
+    if incoming_rsync:
+        result["rsync"] = {**rsync, **incoming_rsync}
+        exit_code = incoming_rsync.get("exit_code")
+        if isinstance(exit_code, int):
+            run.rsync_exit_code = exit_code
+    result["execution"] = {
+        **execution,
+        "worker_pid": os.getpid(),
+        "worker_host": socket.gethostname(),
+        "heartbeat_at": timezone.now().isoformat(),
+    }
+    run.result = result
+    run.save(update_fields=["snapshot_path", "rsync_exit_code", "result"])
+
+
 def _reconcile_running_run(*, run: BackupRun, grace_seconds: int, stale_worker_seconds: int) -> bool:
     result = run.result if isinstance(run.result, dict) else {}
     requested = result.get("requested") if isinstance(result.get("requested"), dict) else {}
+    log_path = _execution_log_path(result)
+    log_tail = _read_log_tail(log_path) if log_path is not None else []
+    terminal_log = _terminal_rsync_log(log_tail)
+    exit_code = _exit_code_from_log(log_tail)
     stale_worker = _running_worker_timed_out(run=run, stale_worker_seconds=stale_worker_seconds)
     if not requested.get("dry_run"):
+        if terminal_log:
+            failure = classify_rsync_failure(exit_code or 255, log_tail)
+            result.update(
+                {
+                    "ok": False,
+                    "host": run.host.host,
+                    "log": str(log_path) if log_path else "",
+                    "failure": failure,
+                    "rsync": {
+                        **(result.get("rsync") if isinstance(result.get("rsync"), dict) else {}),
+                        "exit_code": exit_code or 255,
+                        "log_tail": log_tail,
+                    },
+                }
+            )
+            run.status = BackupRun.Status.FAILED
+            run.ended_at = timezone.now()
+            run.rsync_exit_code = exit_code or 255
+            run.result = result
+            run.save(update_fields=["status", "ended_at", "rsync_exit_code", "result"])
+            return True
+        if _running_rsync_process_missing(run=run, grace_seconds=grace_seconds):
+            result.update(
+                {
+                    "ok": False,
+                    "host": run.host.host,
+                    "log": str(log_path) if log_path else "",
+                    "failure": {
+                        "category": "rsync_process",
+                        "message": "The rsync process is no longer running while the backup is still marked running.",
+                        "hint": "Check the rsync log and pobsync-worker.service logs before retrying the backup.",
+                    },
+                    "rsync": {
+                        **(result.get("rsync") if isinstance(result.get("rsync"), dict) else {}),
+                        "exit_code": exit_code or 255,
+                        "log_tail": log_tail,
+                    },
+                }
+            )
+            run.status = BackupRun.Status.FAILED
+            run.ended_at = timezone.now()
+            run.rsync_exit_code = exit_code or 255
+            run.result = result
+            run.save(update_fields=["status", "ended_at", "rsync_exit_code", "result"])
+            return True
         if stale_worker:
             result.update(
                 {
@@ -225,14 +321,11 @@ def _reconcile_running_run(*, run: BackupRun, grace_seconds: int, stale_worker_s
             return True
         return False
 
-    log_path = _execution_log_path(result)
-    log_tail = _read_log_tail(log_path) if log_path is not None else []
-    terminal_log = _terminal_rsync_log(log_tail)
     timed_out = _running_dry_run_timed_out(run=run, grace_seconds=grace_seconds)
     if not terminal_log and not timed_out and not stale_worker:
         return False
 
-    exit_code = _exit_code_from_log(log_tail) or (124 if timed_out or stale_worker else 255)
+    exit_code = exit_code or (124 if timed_out or stale_worker else 255)
     failure = classify_rsync_failure(exit_code, log_tail)
     if stale_worker and not terminal_log:
         failure = {
@@ -305,6 +398,9 @@ def _read_log_tail(log_path: Path | None, *, max_lines: int = 40) -> list[str]:
 
 
 def _terminal_rsync_log(log_tail: list[str]) -> bool:
+    warning = classify_rsync_warning(_exit_code_from_log(log_tail), log_tail)
+    if warning is not None:
+        return False
     return any(line.startswith("rsync error:") for line in log_tail)
 
 
@@ -312,6 +408,8 @@ def _exit_code_from_log(log_tail: list[str]) -> int | None:
     for line in reversed(log_tail):
         if "code 255" in line:
             return 255
+        if "code 24" in line:
+            return 24
         if "code 124" in line:
             return 124
         if "code 12" in line:
@@ -342,6 +440,33 @@ def _running_worker_timed_out(*, run: BackupRun, stale_worker_seconds: int) -> b
     return timezone.now() >= heartbeat_at + timedelta(seconds=stale_worker_seconds)
 
 
+def _running_rsync_process_missing(*, run: BackupRun, grace_seconds: int) -> bool:
+    if grace_seconds <= 0:
+        return False
+    result = run.result if isinstance(run.result, dict) else {}
+    execution = result.get("execution") if isinstance(result.get("execution"), dict) else {}
+    if execution.get("phase") != "rsync":
+        return False
+    rsync = result.get("rsync") if isinstance(result.get("rsync"), dict) else {}
+    pid = rsync.get("pid")
+    if not isinstance(pid, int) or pid <= 0:
+        return False
+    heartbeat_at = _parse_iso_datetime(execution.get("heartbeat_at")) or run.started_at
+    if heartbeat_at is None or timezone.now() < heartbeat_at + timedelta(seconds=grace_seconds):
+        return False
+    return not _process_exists(pid)
+
+
+def _process_exists(pid: int) -> bool:
+    try:
+        os.kill(pid, 0)
+    except ProcessLookupError:
+        return False
+    except PermissionError:
+        return True
+    return True
+
+
 def _parse_iso_datetime(value: object):
     if not isinstance(value, str) or not value:
         return None

src/pobsync_backend/config_repository.py

@@ -68,8 +68,12 @@ def _host_runtime_data(host_config: HostConfig) -> dict[str, Any]:
         data["excludes_replace"] = list(host_config.excludes_replace or [])
     else:
         data["excludes_add"] = list(host_config.excludes_add or [])
+    if host_config.rsync_extra_args or host_config.rsync_bwlimit_kbps is not None:
+        data["rsync"] = {}
         if host_config.rsync_extra_args:
-        data["rsync"] = {"extra_args": list(host_config.rsync_extra_args or [])}
+            data["rsync"]["extra_args"] = list(host_config.rsync_extra_args or [])
+        if host_config.rsync_bwlimit_kbps is not None:
+            data["rsync"]["bwlimit_kbps"] = host_config.rsync_bwlimit_kbps
     return validate_dict(data, HOST_SCHEMA, path="host")
 
 

src/pobsync_backend/forms.py

@@ -60,6 +60,7 @@ class HostConfigForm(forms.ModelForm):
             "excludes_add",
             "excludes_replace",
             "rsync_extra_args",
+            "rsync_bwlimit_kbps",
             "retention_daily",
             "retention_weekly",
             "retention_monthly",
@@ -70,6 +71,7 @@ class HostConfigForm(forms.ModelForm):
             "ssh_user": "Leave empty to use the global SSH user.",
             "ssh_port": "Leave empty to use the global SSH port.",
             "source_root": "Leave empty to use the global default source root.",
+            "rsync_bwlimit_kbps": "Leave empty to inherit the global limit. Use 0 for unlimited on this host.",
         }
 
 
@@ -112,6 +114,7 @@ class GlobalConfigForm(forms.ModelForm):
         help_texts = {
             "name": "Usually 'default'. The backup engine currently reads the default config.",
             "default_ssh_credential": "Optional. Used by hosts without their own SSH credential.",
+            "rsync_bwlimit_kbps": "Rsync bandwidth limit in KB/s. Use 0 for unlimited.",
             "default_source_root": "Used by hosts without a custom source root.",
             "default_destination_subdir": "Optional subdirectory below each snapshot.",
         }

src/pobsync_backend/management/commands/configure_pobsync_host.py

@@ -22,6 +22,12 @@ class Command(BaseCommand):
         parser.add_argument("--exclude-add", action="append", default=[])
         parser.add_argument("--exclude-replace", action="append", default=None)
         parser.add_argument("--rsync-extra-arg", action="append", default=[])
+        parser.add_argument(
+            "--rsync-bwlimit-kbps",
+            type=int,
+            default=None,
+            help="Host rsync bandwidth limit in KB/s. Omit to inherit global; set 0 for unlimited.",
+        )
         parser.add_argument("--retention", default=None)
         parser.add_argument("--disabled", action="store_true")
         parser.add_argument("--force", action="store_true", help="Update existing host")
@@ -42,6 +48,7 @@ class Command(BaseCommand):
             "excludes_add": [] if options["exclude_replace"] is not None else list(options["exclude_add"]),
             "excludes_replace": options["exclude_replace"],
             "rsync_extra_args": list(options["rsync_extra_arg"]),
+            "rsync_bwlimit_kbps": options["rsync_bwlimit_kbps"],
             "retention_daily": retention["daily"],
             "retention_weekly": retention["weekly"],
             "retention_monthly": retention["monthly"],

src/pobsync_backend/migrations/0014_host_bwlimit_override.py

@@ -0,0 +1,18 @@
+# Generated by Django 5.2.14 on 2026-05-22 22:52
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ('pobsync_backend', '0013_purgedsnapshot'),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name='hostconfig',
+            name='rsync_bwlimit_kbps',
+            field=models.PositiveIntegerField(blank=True, null=True),
+        ),
+    ]

src/pobsync_backend/models.py

@@ -63,6 +63,7 @@ class HostConfig(TimestampedModel):
     excludes_add = models.JSONField(default=list, blank=True)
     excludes_replace = models.JSONField(null=True, blank=True)
     rsync_extra_args = models.JSONField(default=list, blank=True)
+    rsync_bwlimit_kbps = models.PositiveIntegerField(null=True, blank=True)
     retention_daily = models.PositiveIntegerField(default=14)
     retention_weekly = models.PositiveIntegerField(default=8)
     retention_monthly = models.PositiveIntegerField(default=12)

src/pobsync_backend/preflight.py

@@ -97,9 +97,7 @@ def run_remote_preflight(host: HostConfig, *, timeout_seconds: int = 20) -> dict
                 *ssh_cmd,
                 "-oBatchMode=yes",
                 target,
-                "sh",
+                _remote_shell_command(f"command -v {shlex.quote(rsync_binary)} >/dev/null"),
-                "-lc",
-                f"command -v {shlex.quote(rsync_binary)} >/dev/null",
             ],
             timeout_seconds=timeout_seconds,
         ),
@@ -109,9 +107,7 @@ def run_remote_preflight(host: HostConfig, *, timeout_seconds: int = 20) -> dict
                 *ssh_cmd,
                 "-oBatchMode=yes",
                 target,
-                "sh",
+                _remote_shell_command(f"test -e {shlex.quote(source_root)} && test -r {shlex.quote(source_root)}"),
-                "-lc",
-                f"test -e {shlex.quote(source_root)} && test -r {shlex.quote(source_root)}",
             ],
             timeout_seconds=timeout_seconds,
         ),
@@ -129,6 +125,10 @@ def run_remote_preflight(host: HostConfig, *, timeout_seconds: int = 20) -> dict
     return result
 
 
+def _remote_shell_command(script: str) -> str:
+    return f"sh -lc {shlex.quote(script)}"
+
+
 def effective_host_config_preview(host: HostConfig, global_config: GlobalConfig) -> dict[str, Any]:
     config = build_effective_config(global_config_object_data(global_config), host_config_object_data(host))
     credential = host.ssh_credential or global_config.default_ssh_credential

src/pobsync_backend/templates/pobsync_backend/base.html

@@ -559,6 +559,15 @@
 	      gap: 8px;
       margin-bottom: 14px;
     }
+    .refresh-controls {
+      align-items: center;
+      display: flex;
+      gap: 14px;
+      justify-content: space-between;
+    }
+    .refresh-controls h2 {
+      margin-bottom: 4px;
+    }
     .trend-bars {
       display: grid;
       gap: 5px;
@@ -743,6 +752,15 @@
     .host-card-warning > * {
       min-width: 0;
     }
+    .host-card-actions {
+      align-items: center;
+      border-top: 1px solid var(--border);
+      display: flex;
+      flex-wrap: wrap;
+      gap: 8px;
+      margin-top: 14px;
+      padding-top: 12px;
+    }
     .messages { display: grid; gap: 8px; margin-bottom: 18px; }
 	    .message {
 	      background: var(--panel);
@@ -837,6 +855,10 @@
 	      .page-header .actions { justify-content: flex-start; }
 	      .two-col,
 	      .panel-grid { grid-template-columns: 1fr; }
+      .refresh-controls {
+        align-items: stretch;
+        display: grid;
+      }
       .dashboard-priority-grid { grid-template-columns: 1fr; }
       .host-control-grid { grid-template-columns: 1fr; }
       .schedule-row { grid-template-columns: 1fr; }
@@ -896,6 +918,7 @@
       <strong><a href="{% url 'dashboard' %}">pobsync</a></strong>
       <span class="nav-primary" aria-label="Primary navigation">
         <a href="{% url 'dashboard' %}" {% if request.resolver_match.url_name == "dashboard" %}aria-current="page"{% endif %}>Dashboard</a>
+        <a href="{% url 'hosts_list' %}" {% if request.resolver_match.url_name == "hosts_list" or request.resolver_match.url_name == "host_detail" or request.resolver_match.url_name == "create_host_config" or request.resolver_match.url_name == "edit_host_config" or request.resolver_match.url_name == "edit_host_schedule" %}aria-current="page"{% endif %}>Hosts</a>
         <a href="{% url 'ssh_credentials' %}" {% if request.resolver_match.url_name == "ssh_credentials" or request.resolver_match.url_name == "create_ssh_credential" or request.resolver_match.url_name == "generate_ssh_credential" or request.resolver_match.url_name == "edit_ssh_credential" %}aria-current="page"{% endif %}>SSH Keys</a>
         <a href="{% url 'logs' %}" {% if request.resolver_match.url_name == "logs" %}aria-current="page"{% endif %}>Logs</a>
         <a href="{% url 'purged_snapshots' %}" {% if request.resolver_match.url_name == "purged_snapshots" %}aria-current="page"{% endif %}>Purged</a>
@@ -922,8 +945,20 @@
   </main>
   <script>
     (() => {
+      const updateRefreshControls = (region) => {
+        const toggle = document.querySelector(`[data-refresh-toggle][data-refresh-target="${region.id}"]`);
+        const state = document.querySelector(`[data-refresh-state="${region.id}"]`);
+        const paused = region.dataset.refreshPaused === "true";
+        const active = region.dataset.refreshActive === "true";
+        if (state) state.textContent = paused ? "paused" : (active ? "on" : "off");
+        if (toggle) {
+          toggle.textContent = paused ? "Resume refresh" : "Pause refresh";
+          toggle.disabled = !active && !paused;
+        }
+      };
+
       const refreshRegion = async (region) => {
-        if (region.dataset.refreshActive !== "true" || document.hidden) return;
+        if (region.dataset.refreshActive !== "true" || region.dataset.refreshPaused === "true" || document.hidden) return;
         try {
           const response = await fetch(region.dataset.refreshUrl, {
             credentials: "same-origin",
@@ -933,13 +968,26 @@
           region.innerHTML = await response.text();
           const refreshActive = response.headers.get("X-Pobsync-Refresh-Active");
           if (refreshActive) region.dataset.refreshActive = refreshActive;
+          updateRefreshControls(region);
         } catch (error) {
           // Keep the current server-rendered content visible if a refresh fails.
         }
       };
 
+      document.addEventListener("click", (event) => {
+        const toggle = event.target.closest("[data-refresh-toggle]");
+        if (!toggle) return;
+        const region = document.getElementById(toggle.dataset.refreshTarget);
+        if (!region) return;
+        const paused = region.dataset.refreshPaused === "true";
+        region.dataset.refreshPaused = paused ? "false" : "true";
+        if (paused && region.dataset.refreshActive === "true") refreshRegion(region);
+        updateRefreshControls(region);
+      });
+
       document.querySelectorAll("[data-refresh-url]").forEach((region) => {
         const interval = Number.parseInt(region.dataset.refreshInterval || "5000", 10);
+        updateRefreshControls(region);
         window.setInterval(() => refreshRegion(region), Number.isFinite(interval) ? interval : 5000);
       });
     })();

src/pobsync_backend/templates/pobsync_backend/dashboard.html

@@ -42,7 +42,7 @@
   </div>
 
   <section class="grid dashboard-summary-grid" aria-label="Summary">
-    <a class="metric metric-link" href="#hosts"><div class="label">Hosts</div><div class="value">{{ counts.enabled_hosts }}/{{ counts.hosts }}</div></a>
+    <a class="metric metric-link" href="{% url 'hosts_list' %}"><div class="label">Hosts</div><div class="value">{{ counts.enabled_hosts }}/{{ counts.hosts }}</div></a>
     <a class="metric metric-link" href="{% url 'schedules_list' %}"><div class="label">Schedules</div><div class="value">{{ counts.enabled_schedules }}/{{ counts.schedules }}</div></a>
     <a class="metric metric-link" href="{% url 'snapshots_list' %}"><div class="label">Snapshots</div><div class="value">{{ counts.snapshots }}</div></a>
     <a class="metric metric-link" href="{% url 'runs_list' %}"><div class="label">Runs</div><div class="value">{{ counts.runs }}</div></a>

src/pobsync_backend/templates/pobsync_backend/host_detail.html

@@ -373,7 +373,10 @@
             <div class="record-fact"><span class="label">Rsync binary:</span><strong>{{ effective_config.rsync.binary }}</strong></div>
             <div class="record-fact"><span class="label">Rsync args:</span><span>{{ effective_config.rsync.args|join:" " }}</span></div>
             <div class="record-fact"><span class="label">Timeout:</span><strong>{{ effective_config.rsync.timeout_seconds }}s</strong></div>
-            <div class="record-fact"><span class="label">Bandwidth limit:</span><strong>{{ effective_config.rsync.bwlimit_kbps }} KB/s</strong></div>
+            <div class="record-fact">
+              <span class="label">Bandwidth limit:</span>
+              <strong>{% if effective_config.rsync.bwlimit_kbps %}{{ effective_config.rsync.bwlimit_kbps }} KB/s{% else %}unlimited{% endif %}</strong>
+            </div>
           </div>
         </article>
         <article class="record-card">

src/pobsync_backend/templates/pobsync_backend/hosts_list.html

@@ -0,0 +1,43 @@
+{% extends "pobsync_backend/base.html" %}
+
+{% block title %}Hosts | pobsync{% endblock %}
+
+{% block content %}
+  <header class="page-header">
+    <div class="page-title">
+      <div class="page-kicker">Inventory</div>
+      <h1>Hosts</h1>
+      <div class="page-subtitle">Configured backup targets, schedules, retention state, and host-level controls.</div>
+    </div>
+    <section class="actions" aria-label="Host actions">
+      <a class="button-link" href="{% url 'create_host_config' %}">New host</a>
+    </section>
+  </header>
+
+  <section class="grid dashboard-summary-grid" aria-label="Host summary">
+    <a class="metric metric-link" href="{% url 'hosts_list' %}"><div class="label">Showing</div><div class="value">{{ counts.hosts }}</div></a>
+    <a class="metric metric-link" href="{% url 'hosts_list' %}?enabled=yes"><div class="label">Enabled</div><div class="value">{{ counts.enabled_hosts }}</div></a>
+    <a class="metric metric-link" href="{% url 'hosts_list' %}?enabled=no"><div class="label">Disabled</div><div class="value">{{ counts.disabled_hosts }}</div></a>
+    <a class="metric metric-link" href="{% url 'dashboard' %}"><div class="label">Total</div><div class="value">{{ total_count }}</div></a>
+  </section>
+
+  <section class="panel">
+    <h2>Filters</h2>
+    <form class="filter-form" method="get">
+      <div class="field">
+        <label for="enabled">Host state</label>
+        <select id="enabled" name="enabled">
+          <option value="" {% if selected_enabled == "" %}selected{% endif %}>All hosts</option>
+          <option value="yes" {% if selected_enabled == "yes" %}selected{% endif %}>Enabled only</option>
+          <option value="no" {% if selected_enabled == "no" %}selected{% endif %}>Disabled only</option>
+        </select>
+      </div>
+      <div class="form-actions">
+        <button type="submit">Apply filters</button>
+        <a class="button-link secondary" href="{% url 'hosts_list' %}">Reset</a>
+      </div>
+    </form>
+  </section>
+
+  {% include "pobsync_backend/partials/dashboard_hosts.html" %}
+{% endblock %}

src/pobsync_backend/templates/pobsync_backend/partials/dashboard_hosts.html

@@ -22,6 +22,14 @@
             {% if host.failed_run_count %}
               <span class="status failed">failed {{ host.failed_run_count }}</span>
             {% endif %}
+            {% if show_host_controls %}
+              {% if host.schedule %}
+                <span class="status {% if host.schedule.enabled %}ok{% else %}skipped{% endif %}">schedule {{ host.schedule.enabled|yesno:"on,paused" }}</span>
+                <span class="status {% if host.schedule.prune %}ok{% else %}skipped{% endif %}">retention {{ host.schedule.prune|yesno:"on,paused" }}</span>
+              {% else %}
+                <span class="status skipped">no schedule</span>
+              {% endif %}
+            {% endif %}
           </div>
         </div>
         <div class="host-card-layout">
@@ -115,6 +123,33 @@
             {% endif %}
           </div>
         {% endif %}
+        {% if show_host_controls %}
+          <div class="host-card-actions">
+            <a class="button-link compact secondary" href="{% url 'host_detail' host.host %}">Open</a>
+            <a class="button-link compact secondary" href="{% url 'edit_host_config' host.host %}">Edit config</a>
+            <a class="button-link compact secondary" href="{% url 'edit_host_schedule' host.host %}">{% if host.schedule %}Edit schedule{% else %}Create schedule{% endif %}</a>
+            <form class="inline-form" method="post" action="{% url 'update_host_state' host.host %}">
+              {% csrf_token %}
+              <input type="hidden" name="next" value="{{ request.get_full_path }}">
+              <input type="hidden" name="action" value="{% if host.enabled %}disable_host{% else %}enable_host{% endif %}">
+              <button class="compact {% if host.enabled %}secondary{% endif %}" type="submit">{{ host.enabled|yesno:"Disable host,Enable host" }}</button>
+            </form>
+            {% if host.schedule %}
+              <form class="inline-form" method="post" action="{% url 'update_host_state' host.host %}">
+                {% csrf_token %}
+                <input type="hidden" name="next" value="{{ request.get_full_path }}">
+                <input type="hidden" name="action" value="{% if host.schedule.enabled %}disable_schedule{% else %}enable_schedule{% endif %}">
+                <button class="compact secondary" type="submit">{{ host.schedule.enabled|yesno:"Pause schedule,Resume schedule" }}</button>
+              </form>
+              <form class="inline-form" method="post" action="{% url 'update_host_state' host.host %}">
+                {% csrf_token %}
+                <input type="hidden" name="next" value="{{ request.get_full_path }}">
+                <input type="hidden" name="action" value="{% if host.schedule.prune %}disable_prune{% else %}enable_prune{% endif %}">
+                <button class="compact secondary" type="submit">{{ host.schedule.prune|yesno:"Pause retention,Resume retention" }}</button>
+              </form>
+            {% endif %}
+          </div>
+        {% endif %}
       </article>
     {% empty %}
       <p class="muted">No hosts configured yet.</p>

src/pobsync_backend/templates/pobsync_backend/partials/run_detail_live.html

@@ -59,9 +59,13 @@
 
 {% if dry_run_summary %}
   <section class="panel highlight {{ dry_run_summary.highlight_class }}">
-    <h2>Dry Run Summary</h2>
+    <h2>Run Progress</h2>
-    <section class="grid" aria-label="Dry run summary">
+    <section class="grid" aria-label="Run progress">
       <div class="metric"><div class="label">Status</div><div class="value">{{ dry_run_summary.status }}</div></div>
+      <div class="metric">
+        <div class="label">Mode</div>
+        <div class="value">dry run</div>
+      </div>
       <div class="metric"><div class="label">Files Seen</div><div class="value">{{ dry_run_summary.files_seen|default:"unknown" }}</div></div>
       <div class="metric"><div class="label">Would Transfer</div><div class="value">{{ dry_run_summary.files_would_transfer|default:"unknown" }}</div></div>
       <div class="metric"><div class="label">Transfer Estimate</div><div class="value">{{ dry_run_summary.transfer_estimate_bytes|filesizeformat }}</div></div>
@@ -96,6 +100,74 @@
   </section>
 {% endif %}
 
+{% if live_progress %}
+  <section class="panel highlight running">
+    <h2>Run Progress</h2>
+    <section class="grid" aria-label="Run progress">
+      <div class="metric">
+        <div class="label">Status</div>
+        <div class="value">{{ run.status }}</div>
+      </div>
+      <div class="metric">
+        <div class="label">Mode</div>
+        <div class="value">backup</div>
+      </div>
+      <div class="metric">
+        <div class="label">Phase</div>
+        <div class="value">{{ live_progress.phase }}</div>
+      </div>
+      <div class="metric">
+        <div class="label">Rsync PID</div>
+        <div class="value">{{ live_progress.rsync_pid|default:"" }}</div>
+      </div>
+      <div class="metric">
+        <div class="label">Log Updated</div>
+        <div class="value">
+          {% if live_progress.log.exists %}
+            {{ live_progress.log.seconds_since_modified }}s ago
+          {% else %}
+            missing
+          {% endif %}
+        </div>
+      </div>
+      <div class="metric">
+        <div class="label">Log Size</div>
+        <div class="value">{{ live_progress.log.size_bytes|filesizeformat }}</div>
+      </div>
+      {% if live_progress.snapshot.exists %}
+        <div class="metric">
+          <div class="label">Data Files</div>
+          <div class="value">{% if live_progress.snapshot.scan_limited %}at least {% endif %}{{ live_progress.snapshot.files }}</div>
+        </div>
+        <div class="metric">
+          <div class="label">Data Size</div>
+          <div class="value">{% if live_progress.snapshot.scan_limited %}at least {% endif %}{{ live_progress.snapshot.apparent_size_bytes|filesizeformat }}</div>
+        </div>
+      {% endif %}
+    </section>
+    <div class="stack">
+      {% if live_progress.snapshot.path %}
+        <div><strong>Snapshot path:</strong> {{ live_progress.snapshot.path }}</div>
+      {% endif %}
+      {% if live_progress.snapshot.scan_limited %}
+        <div class="muted">Progress scan was capped to keep the UI responsive.</div>
+      {% endif %}
+      {% if live_progress.log.path %}
+        <div>
+          <strong>Log:</strong>
+          {% if live_progress.log.exists %}
+            <a href="{% url 'run_rsync_log' run.id %}">Open full rsync log</a>
+          {% else %}
+            <span class="muted">{{ live_progress.log.path }} (missing)</span>
+          {% endif %}
+        </div>
+        <div><strong>Log path:</strong> {{ live_progress.log.path }}</div>
+      {% endif %}
+      <div><strong>Warnings:</strong> none recorded</div>
+    </div>
+  </section>
+{% endif %}
+
 <div class="two-col">
   <section class="panel">
     <h2>Timing</h2>

src/pobsync_backend/templates/pobsync_backend/run_detail.html

@@ -14,10 +14,22 @@
     </section>
   </header>
 
+  {% if can_auto_refresh %}
+    <section class="panel refresh-controls" aria-label="Live refresh controls">
+      <div>
+        <h2>Live Updates</h2>
+        <p class="muted">Auto-refresh is <strong data-refresh-state="run-live-region">on</strong> while this run is active.</p>
+      </div>
+      <button type="button" class="secondary" data-refresh-toggle data-refresh-target="run-live-region">Pause refresh</button>
+    </section>
+  {% endif %}
+
   <div
+    id="run-live-region"
     data-refresh-url="{% url 'run_detail_live' run.id %}"
     data-refresh-interval="5000"
     data-refresh-active="{{ can_auto_refresh|yesno:'true,false' }}"
+    data-refresh-paused="false"
     aria-live="polite"
   >
     {% include "pobsync_backend/partials/run_detail_live.html" %}
@@ -38,6 +50,10 @@
 
   <section class="panel">
     <h2>Rsync Command</h2>
+    <p class="muted">
+      <strong>Bandwidth limit:</strong>
+      {% if rsync_bwlimit_kbps %}{{ rsync_bwlimit_kbps }} KB/s{% else %}unlimited{% endif %}
+    </p>
     {% if rsync_command %}
       <pre>{% for part in rsync_command %}{{ part }}{% if not forloop.last %}
 {% endif %}{% endfor %}</pre>

src/pobsync_backend/tests/test_backup_worker.py

@@ -85,6 +85,37 @@ class BackupWorkerTests(TestCase):
         self.assertEqual(SnapshotRecord.objects.count(), 1)
         self.assertEqual(run.snapshot, SnapshotRecord.objects.get())
 
+    def test_worker_records_warning_status_from_completed_run(self) -> None:
+        with TemporaryDirectory() as tmp:
+            backup_root = Path(tmp) / "backups"
+            GlobalConfig.objects.create(name="default", backup_root=str(backup_root))
+            host = HostConfig.objects.create(host="web-01", address="web-01.example.test")
+            snapshot_dir = backup_root / host.host / "scheduled" / "20260519-021500Z__ABCDEFGH"
+            meta_dir = snapshot_dir / "meta"
+            meta_dir.mkdir(parents=True)
+            write_yaml_atomic(meta_dir / "meta.yaml", {"status": "warning", "started_at": "2026-05-19T02:15:00Z"})
+            run = queue_backup_run(host=host)
+
+            with patch("pobsync_backend.backup_runner.run_scheduled") as run_scheduled:
+                run_scheduled.return_value = {
+                    "ok": True,
+                    "status": "warning",
+                    "dry_run": False,
+                    "host": host.host,
+                    "snapshot": str(snapshot_dir),
+                    "base": None,
+                    "warning": {"category": "vanished"},
+                    "rsync": {"exit_code": 24},
+                }
+
+                count = Command()._run_once(prefix=Path(tmp) / "home")
+
+        self.assertEqual(count, 1)
+        run.refresh_from_db()
+        self.assertEqual(run.status, BackupRun.Status.WARNING)
+        self.assertEqual(run.rsync_exit_code, 24)
+        self.assertEqual(run.result["warning"]["category"], "vanished")
+
     def test_worker_refreshes_heartbeat_while_run_is_active(self) -> None:
         with TemporaryDirectory() as tmp:
             GlobalConfig.objects.create(name="default", backup_root=str(Path(tmp) / "backups"))
@@ -116,6 +147,44 @@ class BackupWorkerTests(TestCase):
                 run_scheduled.side_effect = fake_run_scheduled
                 Command()._run_once(prefix=Path(tmp) / "home")
 
+    def test_worker_records_real_run_log_path_while_running(self) -> None:
+        with TemporaryDirectory() as tmp:
+            GlobalConfig.objects.create(name="default", backup_root=str(Path(tmp) / "backups"))
+            host = HostConfig.objects.create(host="web-01", address="web-01.example.test")
+            run = queue_backup_run(host=host)
+            snapshot_dir = Path(tmp) / "backups" / host.host / ".incomplete" / "20260519-021500Z__ABCDEFGH"
+            log_path = snapshot_dir / "meta" / "rsync.log"
+
+            with patch("pobsync_backend.backup_runner.run_scheduled") as run_scheduled:
+                def fake_run_scheduled(**kwargs):
+                    kwargs["state_callback"](
+                        {
+                            "status": "running",
+                            "phase": "rsync",
+                            "snapshot": str(snapshot_dir),
+                            "log": str(log_path),
+                            "rsync": {"command": ["rsync"], "exit_code": None, "pid": 1234, "pgid": 1234},
+                        }
+                    )
+                    run.refresh_from_db()
+                    self.assertEqual(run.snapshot_path, str(snapshot_dir))
+                    self.assertEqual(run.result["execution"]["phase"], "rsync")
+                    self.assertEqual(run.result["execution"]["log"], str(log_path))
+                    self.assertEqual(run.result["execution"]["snapshot"], str(snapshot_dir))
+                    self.assertEqual(run.result["rsync"]["command"], ["rsync"])
+                    self.assertEqual(run.result["rsync"]["pid"], 1234)
+                    return {
+                        "ok": True,
+                        "dry_run": False,
+                        "host": host.host,
+                        "snapshot": "",
+                        "base": None,
+                        "rsync": {"exit_code": 0},
+                    }
+
+                run_scheduled.side_effect = fake_run_scheduled
+                Command()._run_once(prefix=Path(tmp) / "home")
+
     def test_worker_reconciles_stale_real_run_after_heartbeat_timeout(self) -> None:
         host = HostConfig.objects.create(host="web-01", address="web-01.example.test")
         run = queue_backup_run(host=host)
@@ -136,6 +205,97 @@ class BackupWorkerTests(TestCase):
         self.assertEqual(run.result["failure"]["category"], "worker")
         self.assertIn("heartbeat stopped", run.result["failure"]["message"])
 
+    def test_worker_reconciles_real_run_with_terminal_broken_pipe_log(self) -> None:
+        with TemporaryDirectory() as tmp:
+            host = HostConfig.objects.create(host="web-01", address="web-01.example.test")
+            run = queue_backup_run(host=host)
+            log_path = Path(tmp) / "backups" / host.host / ".incomplete" / "20260519-021500Z__ABCDEFGH" / "meta" / "rsync.log"
+            log_path.parent.mkdir(parents=True, exist_ok=True)
+            log_path.write_text(
+                "rsync error: unexplained error (code 255) at rsync.c(716) [generator=3.4.1]\n"
+                "rsync error: received SIGUSR1 (code 19) at main.c(1600) [receiver=3.4.1]\n"
+                "rsync: [generator] write error: Broken pipe (32)\n",
+                encoding="utf-8",
+            )
+            run.status = BackupRun.Status.RUNNING
+            run.started_at = timezone.now()
+            run.result["execution"] = {"log": str(log_path)}
+            run.save(update_fields=["status", "started_at", "result"])
+
+            reconciled = reconcile_running_runs()
+
+        self.assertEqual(reconciled, 1)
+        run.refresh_from_db()
+        self.assertEqual(run.status, BackupRun.Status.FAILED)
+        self.assertEqual(run.rsync_exit_code, 255)
+        self.assertEqual(run.result["failure"]["category"], "transport")
+        self.assertIn("Broken pipe", "\n".join(run.result["rsync"]["log_tail"]))
+
+    def test_worker_reconciles_real_run_when_rsync_process_disappears(self) -> None:
+        with TemporaryDirectory() as tmp:
+            host = HostConfig.objects.create(host="web-01", address="web-01.example.test")
+            run = queue_backup_run(host=host)
+            log_path = Path(tmp) / "backups" / host.host / ".incomplete" / "20260519-021500Z__ABCDEFGH" / "meta" / "rsync.log"
+            log_path.parent.mkdir(parents=True, exist_ok=True)
+            log_path.write_text("sending incremental file list\n", encoding="utf-8")
+            run.status = BackupRun.Status.RUNNING
+            run.started_at = timezone.now() - timedelta(minutes=10)
+            run.result["execution"] = {
+                "phase": "rsync",
+                "log": str(log_path),
+                "heartbeat_at": (timezone.now() - timedelta(minutes=10)).isoformat(),
+            }
+            run.result["rsync"] = {"pid": 999999, "pgid": 999999, "command": ["rsync"]}
+            run.save(update_fields=["status", "started_at", "result"])
+
+            reconciled = reconcile_running_runs(grace_seconds=300, stale_worker_seconds=24 * 60 * 60)
+
+        self.assertEqual(reconciled, 1)
+        run.refresh_from_db()
+        self.assertEqual(run.status, BackupRun.Status.FAILED)
+        self.assertEqual(run.result["failure"]["category"], "rsync_process")
+        self.assertEqual(run.rsync_exit_code, 255)
+
+    def test_worker_does_not_reconcile_missing_rsync_process_during_finalizing_phase(self) -> None:
+        host = HostConfig.objects.create(host="web-01", address="web-01.example.test")
+        run = queue_backup_run(host=host)
+        run.status = BackupRun.Status.RUNNING
+        run.started_at = timezone.now() - timedelta(minutes=10)
+        run.result["execution"] = {
+            "phase": "finalizing",
+            "heartbeat_at": (timezone.now() - timedelta(minutes=10)).isoformat(),
+        }
+        run.result["rsync"] = {"pid": 999999, "pgid": 999999, "command": ["rsync"], "exit_code": 0}
+        run.save(update_fields=["status", "started_at", "result"])
+
+        reconciled = reconcile_running_runs(grace_seconds=300, stale_worker_seconds=24 * 60 * 60)
+
+        self.assertEqual(reconciled, 0)
+        run.refresh_from_db()
+        self.assertEqual(run.status, BackupRun.Status.RUNNING)
+
+    def test_worker_does_not_fail_real_run_for_vanished_file_warning_log(self) -> None:
+        with TemporaryDirectory() as tmp:
+            host = HostConfig.objects.create(host="web-01", address="web-01.example.test")
+            run = queue_backup_run(host=host)
+            log_path = Path(tmp) / "backups" / host.host / ".incomplete" / "20260519-021500Z__ABCDEFGH" / "meta" / "rsync.log"
+            log_path.parent.mkdir(parents=True, exist_ok=True)
+            log_path.write_text(
+                "file has vanished: \"/var/lib/app/session\"\n"
+                "rsync warning: some files vanished before they could be transferred (code 24) at main.c(1338) [sender=3.4.1]\n",
+                encoding="utf-8",
+            )
+            run.status = BackupRun.Status.RUNNING
+            run.started_at = timezone.now()
+            run.result["execution"] = {"log": str(log_path)}
+            run.save(update_fields=["status", "started_at", "result"])
+
+            reconciled = reconcile_running_runs()
+
+        self.assertEqual(reconciled, 0)
+        run.refresh_from_db()
+        self.assertEqual(run.status, BackupRun.Status.RUNNING)
+
     def test_worker_records_dry_run_log_path_while_running(self) -> None:
         with TemporaryDirectory() as tmp:
             GlobalConfig.objects.create(name="default", backup_root=str(Path(tmp) / "backups"))

src/pobsync_backend/tests/test_configure_commands.py

@@ -42,6 +42,7 @@ class ConfigureCommandsTests(TestCase):
             address="web-01.example.test",
             exclude_add=["/tmp/***"],
             rsync_extra_arg=["--delete"],
+            rsync_bwlimit_kbps=4096,
             stdout=out,
         )
 
@@ -49,10 +50,12 @@ class ConfigureCommandsTests(TestCase):
         self.assertEqual(host.retention_daily, 5)
         self.assertEqual(host.excludes_add, ["/tmp/***"])
         self.assertEqual(host.rsync_extra_args, ["--delete"])
+        self.assertEqual(host.rsync_bwlimit_kbps, 4096)
 
         effective = DjangoConfigSource().effective_config_for_host("web-01")
         self.assertEqual(effective["retention"]["yearly"], 2)
         self.assertEqual(effective["excludes_effective"], ["/tmp/***"])
+        self.assertEqual(effective["rsync"]["bwlimit_kbps"], 4096)
 
     def test_configure_schedule_creates_sql_schedule(self) -> None:
         host = HostConfig.objects.create(host="web-01", address="web-01.example.test")

src/pobsync_backend/tests/test_django_config_source.py

@@ -17,6 +17,7 @@ class DjangoConfigSourceTests(TestCase):
             backup_root="/backups",
             rsync_args=["--archive"],
             rsync_extra_args=["--numeric-ids"],
+            rsync_bwlimit_kbps=10000,
             excludes_default=["/proc/***"],
             retention_daily=7,
             retention_weekly=4,
@@ -28,6 +29,7 @@ class DjangoConfigSourceTests(TestCase):
             address="web-01.example.test",
             excludes_add=["/tmp/***"],
             rsync_extra_args=["--delete"],
+            rsync_bwlimit_kbps=2500,
             retention_daily=7,
             retention_weekly=4,
             retention_monthly=3,
@@ -46,6 +48,24 @@ class DjangoConfigSourceTests(TestCase):
         self.assertEqual(cfg["address"], "web-01.example.test")
         self.assertEqual(cfg["excludes_effective"], ["/proc/***", "/tmp/***"])
         self.assertEqual(cfg["rsync"]["args_effective"], ["--archive", "--numeric-ids", "--delete"])
+        self.assertEqual(cfg["rsync"]["bwlimit_kbps"], 2500)
+
+    def test_host_can_disable_global_rsync_bandwidth_limit(self) -> None:
+        GlobalConfig.objects.create(
+            name="default",
+            backup_root="/backups",
+            rsync_args=["--archive"],
+            rsync_bwlimit_kbps=5000,
+        )
+        HostConfig.objects.create(
+            host="web-01",
+            address="web-01.example.test",
+            rsync_bwlimit_kbps=0,
+        )
+
+        cfg = DjangoConfigSource().effective_config_for_host("web-01")
+
+        self.assertEqual(cfg["rsync"]["bwlimit_kbps"], 0)
 
     def test_materializes_global_ssh_credential_for_runtime_config(self) -> None:
         credential = SshCredential.objects.create(
@@ -113,6 +133,7 @@ class DjangoConfigSourceTests(TestCase):
             )
             HostConfig.objects.create(host="web-01", address="web-01.example.test")
 
+            with override_settings(POBSYNC_HOME=str(Path(tmp) / "home")):
                 cfg = DjangoConfigSource().effective_config_for_host("web-01")
 
         self.assertIn(f"-oIdentityFile={identity_file}", cfg["ssh"]["options"])

src/pobsync_backend/tests/test_run_scheduled_config_source.py

@@ -12,8 +12,9 @@ from pobsync.rsync import RsyncResult
 
 
 class FakeConfigSource:
-    def __init__(self, backup_root: str = "/tmp/pobsync-test-backups") -> None:
+    def __init__(self, backup_root: str = "/tmp/pobsync-test-backups", bwlimit_kbps: int = 0) -> None:
         self.backup_root = backup_root
+        self.bwlimit_kbps = bwlimit_kbps
 
     def effective_config_for_host(self, host: str) -> dict:
         return {
@@ -25,7 +26,7 @@ class FakeConfigSource:
                 "binary": "rsync",
                 "args_effective": ["--archive"],
                 "timeout_seconds": 0,
-                "bwlimit_kbps": 0,
+                "bwlimit_kbps": self.bwlimit_kbps,
             },
             "source_root": "/",
             "includes": [],
@@ -54,6 +55,21 @@ class RunScheduledConfigSourceTests(SimpleTestCase):
         self.assertEqual(result["host"], "web-01")
         run_rsync.assert_called_once()
 
+    def test_dry_run_applies_configured_bandwidth_limit(self) -> None:
+        with patch("pobsync.commands.run_scheduled.run_rsync") as run_rsync:
+            run_rsync.return_value = RsyncResult(exit_code=0, command=["rsync", "--bwlimit=4096"])
+
+            result = run_scheduled(
+                prefix=Path("/missing-prefix"),
+                host="web-01",
+                dry_run=True,
+                config_source=FakeConfigSource(bwlimit_kbps=4096),
+            )
+
+        command = run_rsync.call_args.args[0]
+        self.assertIn("--bwlimit=4096", command)
+        self.assertEqual(result["rsync"]["bwlimit_kbps"], 4096)
+
     def test_failed_dry_run_includes_log_tail(self) -> None:
         def fake_run_rsync(command, log_path, timeout_seconds, cancel_check=None):
             log_path.parent.mkdir(parents=True, exist_ok=True)
@@ -186,11 +202,13 @@ class RunScheduledConfigSourceTests(SimpleTestCase):
                     host="web-01",
                     dry_run=False,
                     verbose_output=True,
-                    config_source=FakeConfigSource(backup_root=str(Path(tmp) / "backups")),
+                    config_source=FakeConfigSource(backup_root=str(Path(tmp) / "backups"), bwlimit_kbps=2048),
                 )
 
         command = run_rsync.call_args.args[0]
         self.assertTrue(result["ok"])
+        self.assertIn("--bwlimit=2048", command)
+        self.assertEqual(result["rsync"]["bwlimit_kbps"], 2048)
         self.assertIn("--stats", command)
         self.assertIn("--itemize-changes", command)
         self.assertIn("--info=flist2,progress2,stats2", command)
@@ -256,6 +274,71 @@ class RunScheduledConfigSourceTests(SimpleTestCase):
         self.assertIn("stats:", meta_text)
         self.assertIn("files_total: 10", meta_text)
 
+    def test_real_run_reports_running_state_callback_before_rsync_returns(self) -> None:
+        states = []
+
+        def fake_run_rsync(command, log_path, timeout_seconds, cancel_check=None, process_started=None):
+            self.assertEqual(len(states), 1)
+            self.assertEqual(states[0]["status"], "running")
+            self.assertEqual(states[0]["phase"], "preparing")
+            self.assertEqual(states[0]["log"], str(log_path))
+            self.assertEqual(states[0]["rsync"]["command"], command)
+            self.assertIsNotNone(process_started)
+            process_started(1234, 1234)
+            self.assertEqual(len(states), 2)
+            self.assertEqual(states[1]["phase"], "rsync")
+            self.assertEqual(states[1]["rsync"]["pid"], 1234)
+            self.assertEqual(states[1]["rsync"]["pgid"], 1234)
+            log_path.write_text("Number of files: 1\n", encoding="utf-8")
+            return RsyncResult(exit_code=0, command=command)
+
+        with TemporaryDirectory() as tmp:
+            with patch("pobsync.commands.run_scheduled.run_rsync", side_effect=fake_run_rsync):
+                run_scheduled(
+                    prefix=Path(tmp) / "home",
+                    host="web-01",
+                    dry_run=False,
+                    config_source=FakeConfigSource(backup_root=str(Path(tmp) / "backups")),
+                    state_callback=states.append,
+                )
+
+        self.assertEqual(len(states), 3)
+        self.assertIn("/.incomplete/", states[0]["snapshot"])
+        self.assertEqual(states[2]["phase"], "finalizing")
+        self.assertEqual(states[2]["rsync"]["exit_code"], 0)
+
+    def test_real_run_keeps_snapshot_with_warning_for_vanished_files(self) -> None:
+        def fake_run_rsync(command, log_path, timeout_seconds, cancel_check=None):
+            log_path.write_text(
+                "file has vanished: \"/var/lib/app/session\"\n"
+                "rsync warning: some files vanished before they could be transferred (code 24) at main.c(1338) [sender=3.4.1]\n",
+                encoding="utf-8",
+            )
+            data_dir = log_path.parent.parent / "data"
+            data_dir.mkdir(parents=True, exist_ok=True)
+            (data_dir / "payload.txt").write_text("payload", encoding="utf-8")
+            return RsyncResult(exit_code=24, command=command)
+
+        with TemporaryDirectory() as tmp:
+            backup_root = Path(tmp) / "backups"
+            with patch("pobsync.commands.run_scheduled.run_rsync", side_effect=fake_run_rsync):
+                result = run_scheduled(
+                    prefix=Path(tmp) / "home",
+                    host="web-01",
+                    dry_run=False,
+                    config_source=FakeConfigSource(backup_root=str(backup_root)),
+                )
+
+            snapshot = Path(result["snapshot"])
+            self.assertTrue((snapshot / "data" / "payload.txt").exists())
+
+        self.assertTrue(result["ok"])
+        self.assertEqual(result["status"], "warning")
+        self.assertEqual(result["rsync"]["exit_code"], 24)
+        self.assertEqual(result["warning"]["category"], "vanished")
+        self.assertEqual(snapshot.parent.name, "scheduled")
+        self.assertIn("file has vanished", "\n".join(result["rsync"]["log_tail"]))
+
     def test_dry_run_reports_cancelled_rsync(self) -> None:
         def fake_run_rsync(command, log_path, timeout_seconds, cancel_check=None):
             self.assertTrue(cancel_check())

src/pobsync_backend/tests/test_views.py

@@ -48,6 +48,7 @@ class ViewTests(TestCase):
         self.assertContains(response, 'aria-label="Primary navigation"', html=False)
         self.assertContains(response, 'aria-label="System navigation"', html=False)
         self.assertContains(response, reverse("dashboard"))
+        self.assertContains(response, reverse("hosts_list"))
         self.assertContains(response, reverse("ssh_credentials"))
         self.assertContains(response, reverse("logs"))
         self.assertContains(response, reverse("purged_snapshots"))
@@ -202,6 +203,72 @@ class ViewTests(TestCase):
         self.assertContains(response, "Snapshot health")
         self.assertNotContains(response, "<html", html=False)
 
+    def test_hosts_list_renders_host_cards_and_controls(self) -> None:
+        self.client.force_login(self.staff_user)
+        web = HostConfig.objects.create(host="web-01", address="web-01.example.test")
+        db = HostConfig.objects.create(host="db-01", address="db-01.example.test", enabled=False)
+        ScheduleConfig.objects.create(host=web, cron_expr="15 2 * * *", enabled=True, prune=True)
+        BackupRun.objects.create(host=web, status=BackupRun.Status.RUNNING)
+
+        response = self.client.get(reverse("hosts_list"))
+
+        self.assertEqual(response.status_code, 200)
+        self.assertContains(response, "Inventory")
+        self.assertContains(response, "Configured backup targets")
+        self.assertContains(response, "web-01")
+        self.assertContains(response, "db-01")
+        self.assertContains(response, "running 1")
+        self.assertContains(response, "schedule on")
+        self.assertContains(response, "retention on")
+        self.assertContains(response, "Disable host")
+        self.assertContains(response, "Enable host")
+        self.assertContains(response, "Pause schedule")
+        self.assertContains(response, "Pause retention")
+        self.assertContains(response, reverse("update_host_state", args=[web.host]))
+        self.assertContains(response, reverse("edit_host_config", args=[web.host]))
+        self.assertContains(response, reverse("edit_host_schedule", args=[web.host]))
+
+    def test_hosts_list_filters_by_enabled_state(self) -> None:
+        self.client.force_login(self.staff_user)
+        HostConfig.objects.create(host="web-01", address="web-01.example.test")
+        HostConfig.objects.create(host="db-01", address="db-01.example.test", enabled=False)
+
+        response = self.client.get(reverse("hosts_list"), {"enabled": "no"})
+
+        self.assertEqual(response.status_code, 200)
+        self.assertContains(response, "db-01")
+        self.assertNotContains(response, "web-01")
+
+    def test_update_host_state_toggles_host_schedule_and_retention(self) -> None:
+        self.client.force_login(self.staff_user)
+        host = HostConfig.objects.create(host="web-01", address="web-01.example.test")
+        schedule = ScheduleConfig.objects.create(host=host, cron_expr="15 2 * * *", enabled=True, prune=True)
+
+        response = self.client.post(
+            reverse("update_host_state", args=[host.host]),
+            {"action": "disable_host", "next": reverse("hosts_list")},
+            follow=True,
+        )
+        self.assertRedirects(response, reverse("hosts_list"))
+        host.refresh_from_db()
+        self.assertFalse(host.enabled)
+        self.assertContains(response, "Disabled host web-01.")
+
+        self.client.post(reverse("update_host_state", args=[host.host]), {"action": "disable_schedule"})
+        self.client.post(reverse("update_host_state", args=[host.host]), {"action": "disable_prune"})
+        schedule.refresh_from_db()
+        self.assertFalse(schedule.enabled)
+        self.assertFalse(schedule.prune)
+
+        self.client.post(reverse("update_host_state", args=[host.host]), {"action": "enable_host"})
+        self.client.post(reverse("update_host_state", args=[host.host]), {"action": "enable_schedule"})
+        self.client.post(reverse("update_host_state", args=[host.host]), {"action": "enable_prune"})
+        host.refresh_from_db()
+        schedule.refresh_from_db()
+        self.assertTrue(host.enabled)
+        self.assertTrue(schedule.enabled)
+        self.assertTrue(schedule.prune)
+
     def test_dashboard_renders_backup_trend_summary(self) -> None:
         self.client.force_login(self.staff_user)
         GlobalConfig.objects.create(name="default", backup_root="/missing-backup-root")
@@ -921,6 +988,7 @@ class ViewTests(TestCase):
                 "excludes_add": "*.tmp",
                 "excludes_replace": "",
                 "rsync_extra_args": "--numeric-ids",
+                "rsync_bwlimit_kbps": "4096",
                 "retention_daily": "7",
                 "retention_weekly": "4",
                 "retention_monthly": "2",
@@ -938,6 +1006,7 @@ class ViewTests(TestCase):
         self.assertEqual(host.includes, ["/srv/www", "/srv/db"])
         self.assertEqual(host.excludes_add, ["*.tmp"])
         self.assertEqual(host.rsync_extra_args, ["--numeric-ids"])
+        self.assertEqual(host.rsync_bwlimit_kbps, 4096)
         self.assertEqual(host.retention_weekly, 4)
 
     def test_create_host_config_uses_global_defaults_and_prepares_directories(self) -> None:
@@ -1077,6 +1146,7 @@ class ViewTests(TestCase):
         self.assertContains(response, "default-key")
         self.assertContains(response, "-oBatchMode=yes")
         self.assertContains(response, "--archive --numeric-ids --delete --one-file-system")
+        self.assertContains(response, "2048 KB/s")
         self.assertContains(response, "/srv/www/***")
         self.assertContains(response, "/srv/www/cache/***")
         self.assertContains(response, "d14")
@@ -1100,6 +1170,10 @@ class ViewTests(TestCase):
         self.assertContains(response, "Remote rsync")
         self.assertContains(response, "Remote source root")
         self.assertEqual(run.call_count, 3)
+        commands = [call.kwargs["args"] if "args" in call.kwargs else call.args[0] for call in run.call_args_list]
+        self.assertEqual(commands[1][-1], "sh -lc 'command -v rsync >/dev/null'")
+        self.assertEqual(commands[2][-1], "sh -lc 'test -e / && test -r /'")
+        self.assertNotIn("sh", commands[2][commands[2].index("root@web-01.example.test") + 1 : -1])
         host.refresh_from_db()
         self.assertTrue(host.config["last_preflight"]["ok"])
         self.assertEqual(host.config["last_preflight"]["target"], "root@web-01.example.test")
@@ -1469,9 +1543,10 @@ class ViewTests(TestCase):
                 "ok": True,
                 "snapshot": snapshot.path,
                 "rsync": {
-                    "command": ["rsync", "--archive", "root@web-01:/", snapshot.path],
+                    "command": ["rsync", "--archive", "--bwlimit=2048", "root@web-01:/", snapshot.path],
                     "exit_code": 0,
                     "log_tail": ["sending incremental file list", "sent 500 bytes"],
+                    "bwlimit_kbps": 2048,
                 },
                 "requested": {
                     "dry_run": True,
@@ -1506,10 +1581,13 @@ class ViewTests(TestCase):
         self.assertContains(response, "Dry run:</strong> yes")
         self.assertContains(response, "Verbose rsync output:</strong> yes")
         self.assertContains(response, "Rsync Command")
+        self.assertContains(response, "Bandwidth limit:</strong>")
+        self.assertContains(response, "2048 KB/s")
         self.assertContains(response, "--archive")
         self.assertContains(response, "Rsync Log")
         self.assertContains(response, "sending incremental file list")
-        self.assertContains(response, "Dry Run Summary")
+        self.assertContains(response, "Run Progress")
+        self.assertContains(response, "dry run")
         self.assertContains(response, "Files Seen")
         self.assertContains(response, "Would Transfer")
         self.assertContains(response, "Transfer Estimate")
@@ -1559,7 +1637,8 @@ class ViewTests(TestCase):
             response = self.client.get(reverse("run_detail", args=[run.id]))
 
         self.assertEqual(response.status_code, 200)
-        self.assertContains(response, "Dry Run Summary")
+        self.assertContains(response, "Run Progress")
+        self.assertContains(response, "dry run")
         self.assertContains(response, "failed")
         self.assertContains(response, "Files Seen")
         self.assertContains(response, "25")
@@ -1745,6 +1824,8 @@ class ViewTests(TestCase):
         self.assertContains(response, f'data-refresh-url="{reverse("run_detail_live", args=[run.id])}"', html=False)
         self.assertContains(response, 'data-refresh-interval="5000"', html=False)
         self.assertContains(response, 'data-refresh-active="true"', html=False)
+        self.assertContains(response, "Live Updates")
+        self.assertContains(response, "Pause refresh")
 
     def test_run_detail_live_returns_partial_for_active_run(self) -> None:
         self.client.force_login(self.staff_user)
@@ -1763,6 +1844,45 @@ class ViewTests(TestCase):
         self.assertContains(response, "sending incremental file list")
         self.assertNotContains(response, "<html", html=False)
 
+    def test_run_detail_live_shows_progress_for_running_real_run(self) -> None:
+        self.client.force_login(self.staff_user)
+        host = HostConfig.objects.create(host="web-01", address="web-01.example.test")
+        with TemporaryDirectory() as tmp:
+            snapshot_path = Path(tmp) / "backups" / host.host / ".incomplete" / "20260523-010000Z__ABCDEFGH"
+            data_path = snapshot_path / "data"
+            log_path = snapshot_path / "meta" / "rsync.log"
+            data_path.mkdir(parents=True)
+            log_path.parent.mkdir(parents=True)
+            (data_path / "payload.txt").write_text("payload", encoding="utf-8")
+            log_path.write_text("sending incremental file list\npayload.txt\n", encoding="utf-8")
+            run = BackupRun.objects.create(
+                host=host,
+                status=BackupRun.Status.RUNNING,
+                snapshot_path=str(snapshot_path),
+                result={
+                    "requested": {"dry_run": False},
+                    "execution": {
+                        "phase": "rsync",
+                        "snapshot": str(snapshot_path),
+                        "log": str(log_path),
+                        "heartbeat_at": "2026-05-23T01:00:00+02:00",
+                    },
+                    "rsync": {"pid": 1234, "pgid": 1234, "command": ["rsync"]},
+                },
+            )
+
+            response = self.client.get(reverse("run_detail_live", args=[run.id]))
+
+        self.assertEqual(response.status_code, 200)
+        self.assertContains(response, "Run Progress")
+        self.assertContains(response, "backup")
+        self.assertContains(response, "rsync")
+        self.assertContains(response, "1234")
+        self.assertContains(response, "Data Files")
+        self.assertContains(response, "Open full rsync log")
+        self.assertContains(response, "payload.txt")
+        self.assertContains(response, "sending incremental file list")
+
     def test_run_detail_live_stops_refresh_for_terminal_run(self) -> None:
         self.client.force_login(self.staff_user)
         host = HostConfig.objects.create(host="web-01", address="web-01.example.test")
@@ -2417,6 +2537,7 @@ class ViewTests(TestCase):
                 "excludes_add": "*.tmp\ncache/",
                 "excludes_replace": "",
                 "rsync_extra_args": "--numeric-ids\n--delete",
+                "rsync_bwlimit_kbps": "8192",
                 "retention_daily": "7",
                 "retention_weekly": "4",
                 "retention_monthly": "2",
@@ -2436,6 +2557,7 @@ class ViewTests(TestCase):
         self.assertEqual(host.excludes_add, ["*.tmp", "cache/"])
         self.assertIsNone(host.excludes_replace)
         self.assertEqual(host.rsync_extra_args, ["--numeric-ids", "--delete"])
+        self.assertEqual(host.rsync_bwlimit_kbps, 8192)
         self.assertEqual(host.retention_daily, 7)
         self.assertEqual(host.retention_yearly, 1)
 

src/pobsync_backend/views.py

@@ -1,5 +1,6 @@
 from __future__ import annotations
 
+import os
 import json
 import shlex
 import shutil
@@ -16,6 +17,7 @@ from django.db.models import Count, Q
 from django.shortcuts import get_object_or_404, redirect, render
 from django.urls import reverse
 from django.utils import timezone
+from django.utils.http import url_has_allowed_host_and_scheme
 from django.views.decorators.http import require_POST
 
 from pobsync import __version__
@@ -61,8 +63,7 @@ def dashboard_hosts_live(request):
     return render(request, "pobsync_backend/partials/dashboard_hosts.html", _dashboard_context())
 
 
-def _dashboard_context() -> dict[str, object]:
+def _host_cards_context(*, enabled: str = "") -> dict[str, object]:
-    global_config = GlobalConfig.objects.filter(name="default").first()
     hosts = list(
         HostConfig.objects.select_related("schedule")
         .annotate(
@@ -83,6 +84,11 @@ def _dashboard_context() -> dict[str, object]:
         )
         .order_by("host")
     )
+    if enabled == "yes":
+        hosts = [host for host in hosts if host.enabled]
+    elif enabled == "no":
+        hosts = [host for host in hosts if not host.enabled]
+
     for host_config in hosts:
         host_config.latest_snapshot = (
             host_config.snapshots.select_related("base")
@@ -91,6 +97,22 @@ def _dashboard_context() -> dict[str, object]:
         )
         host_config.next_run_at = _next_run_for_host(host_config)
         host_config.retention_warning = _retention_warning_for_host(host_config, _schedule_for_host(host_config))
+    return {
+        "hosts": hosts,
+        "scheduler_timezone": timezone.get_current_timezone_name(),
+        "selected_enabled": enabled,
+        "counts": {
+            "hosts": len(hosts),
+            "enabled_hosts": sum(1 for host in hosts if host.enabled),
+            "disabled_hosts": sum(1 for host in hosts if not host.enabled),
+        },
+    }
+
+
+def _dashboard_context() -> dict[str, object]:
+    global_config = GlobalConfig.objects.filter(name="default").first()
+    host_context = _host_cards_context()
+    hosts = host_context["hosts"]
     action_items = _dashboard_action_items(hosts)
     next_schedule_rows = _dashboard_next_schedule_rows()
     recent_runs = BackupRun.objects.select_related("host", "snapshot").order_by("-created_at", "-id")[:6]
@@ -99,7 +121,7 @@ def _dashboard_context() -> dict[str, object]:
         "hosts": hosts,
         "global_config": global_config,
         "stats_summary": stats_summary,
-        "scheduler_timezone": timezone.get_current_timezone_name(),
+        "scheduler_timezone": host_context["scheduler_timezone"],
         "action_items": action_items,
         "next_schedule_rows": next_schedule_rows,
         "recent_runs": recent_runs,
@@ -126,6 +148,69 @@ def _dashboard_context() -> dict[str, object]:
     return context
 
 
+@staff_member_required
+def hosts_list(request):
+    enabled = request.GET.get("enabled", "").strip()
+    if enabled not in {"", "yes", "no"}:
+        enabled = ""
+    global_config = GlobalConfig.objects.filter(name="default").first()
+    context = _host_cards_context(enabled=enabled)
+    collect_dashboard_stats(hosts=context["hosts"], global_config=global_config)
+    return render(
+        request,
+        "pobsync_backend/hosts_list.html",
+        {
+            **context,
+            "global_config": global_config,
+            "show_host_controls": True,
+            "total_count": HostConfig.objects.count(),
+        },
+    )
+
+
+@staff_member_required
+@require_POST
+def update_host_state(request, host: str):
+    host_config = get_object_or_404(HostConfig, host=host)
+    action = request.POST.get("action", "").strip()
+    next_url = request.POST.get("next") or reverse("hosts_list")
+    if not url_has_allowed_host_and_scheme(next_url, allowed_hosts={request.get_host()}):
+        next_url = reverse("hosts_list")
+
+    if action == "enable_host":
+        host_config.enabled = True
+        host_config.save(update_fields=["enabled", "updated_at"])
+        messages.success(request, f"Enabled host {host_config.host}.")
+    elif action == "disable_host":
+        host_config.enabled = False
+        host_config.save(update_fields=["enabled", "updated_at"])
+        messages.success(request, f"Disabled host {host_config.host}.")
+    elif action in {"enable_schedule", "disable_schedule", "enable_prune", "disable_prune"}:
+        try:
+            schedule = host_config.schedule
+        except ScheduleConfig.DoesNotExist:
+            messages.warning(request, f"{host_config.host} does not have a schedule yet.")
+        else:
+            if action == "enable_schedule":
+                schedule.enabled = True
+                message = f"Enabled backup schedule for {host_config.host}."
+            elif action == "disable_schedule":
+                schedule.enabled = False
+                message = f"Paused backup schedule for {host_config.host}."
+            elif action == "enable_prune":
+                schedule.prune = True
+                message = f"Enabled scheduled retention for {host_config.host}."
+            else:
+                schedule.prune = False
+                message = f"Paused scheduled retention for {host_config.host}."
+            schedule.save(update_fields=["enabled", "prune", "updated_at"])
+            messages.success(request, message)
+    else:
+        messages.error(request, "Unknown host state action.")
+
+    return redirect(next_url)
+
+
 def _dashboard_action_items(hosts: list[HostConfig]) -> list[dict[str, object]]:
     action_items: list[dict[str, object]] = []
     for host_config in hosts:
@@ -703,6 +788,7 @@ def _run_detail_context(run: BackupRun) -> dict[str, object]:
         "stats": run_stats if isinstance(run_stats, dict) else {},
         "rsync": rsync_result,
         "rsync_command": _run_rsync_command(rsync_result),
+        "rsync_bwlimit_kbps": _run_rsync_bwlimit_kbps(rsync_result),
         "failure": failure,
         "failure_summary": failure.get("message") or failure.get("summary") or "",
         "prune_result": prune_result,
@@ -711,6 +797,7 @@ def _run_detail_context(run: BackupRun) -> dict[str, object]:
         "rsync_log_path": str(rsync_log_path) if rsync_log_path is not None else "",
         "rsync_log_exists": bool(rsync_log_path and rsync_log_path.exists()),
         "rsync_log_tail": rsync_log_tail,
+        "live_progress": _run_live_progress(run, rsync_log_path),
         "dry_run_summary": _dry_run_summary(
             result=result,
             requested=requested,
@@ -1247,6 +1334,23 @@ def _run_rsync_command(rsync_result: dict) -> list[str]:
     return [str(part) for part in command]
 
 
+def _run_rsync_bwlimit_kbps(rsync_result: dict) -> int:
+    stored_limit = rsync_result.get("bwlimit_kbps")
+    if stored_limit is not None:
+        try:
+            return max(0, int(stored_limit))
+        except (TypeError, ValueError):
+            return 0
+
+    for part in _run_rsync_command(rsync_result):
+        if part.startswith("--bwlimit="):
+            try:
+                return max(0, int(part.split("=", 1)[1]))
+            except ValueError:
+                return 0
+    return 0
+
+
 def _run_rsync_log_tail(rsync_result: dict, log_path: Path | None, *, max_lines: int = 30) -> list[str]:
     log_tail = rsync_result.get("log_tail")
     if isinstance(log_tail, list):
@@ -1260,6 +1364,97 @@ def _run_rsync_log_tail(rsync_result: dict, log_path: Path | None, *, max_lines:
         return []
 
 
+def _run_live_progress(run: BackupRun, log_path: Path | None) -> dict[str, object]:
+    if run.status not in {BackupRun.Status.QUEUED, BackupRun.Status.RUNNING}:
+        return {}
+
+    result = run.result if isinstance(run.result, dict) else {}
+    requested = result.get("requested") if isinstance(result.get("requested"), dict) else {}
+    if requested.get("dry_run") or result.get("dry_run"):
+        return {}
+
+    execution = result.get("execution") if isinstance(result.get("execution"), dict) else {}
+    rsync = result.get("rsync") if isinstance(result.get("rsync"), dict) else {}
+    progress: dict[str, object] = {
+        "phase": execution.get("phase") or ("queued" if run.status == BackupRun.Status.QUEUED else "running"),
+        "worker_pid": execution.get("worker_pid"),
+        "rsync_pid": rsync.get("pid"),
+        "rsync_pgid": rsync.get("pgid"),
+    }
+
+    log_stats = _live_log_stats(log_path)
+    if log_stats:
+        progress["log"] = log_stats
+
+    snapshot_path = _run_progress_snapshot_path(run, execution)
+    if snapshot_path is not None:
+        progress["snapshot"] = {
+            "path": str(snapshot_path),
+            **_scan_snapshot_progress(snapshot_path / "data" if (snapshot_path / "data").exists() else snapshot_path),
+        }
+    return progress
+
+
+def _run_progress_snapshot_path(run: BackupRun, execution: dict) -> Path | None:
+    snapshot = execution.get("snapshot")
+    if isinstance(snapshot, str) and snapshot:
+        return Path(snapshot)
+    if run.snapshot_path:
+        return Path(run.snapshot_path)
+    return None
+
+
+def _live_log_stats(log_path: Path | None) -> dict[str, object]:
+    if log_path is None:
+        return {}
+    try:
+        stat = log_path.stat()
+    except OSError:
+        return {"path": str(log_path), "exists": False}
+    modified_at = timezone.datetime.fromtimestamp(stat.st_mtime, tz=timezone.get_current_timezone())
+    return {
+        "path": str(log_path),
+        "exists": True,
+        "size_bytes": stat.st_size,
+        "modified_at": modified_at,
+        "seconds_since_modified": max(0, int((timezone.now() - modified_at).total_seconds())),
+    }
+
+
+def _scan_snapshot_progress(data_path: Path, *, max_entries: int = 20000) -> dict[str, object]:
+    progress: dict[str, object] = {
+        "data_path": str(data_path),
+        "exists": data_path.exists(),
+        "files": 0,
+        "directories": 0,
+        "apparent_size_bytes": 0,
+        "scan_limited": False,
+    }
+    if not data_path.exists():
+        return progress
+
+    entries_seen = 0
+    for root, dirnames, filenames in os.walk(data_path):
+        progress["directories"] = int(progress["directories"]) + len(dirnames)
+        entries_seen += len(dirnames)
+        for filename in filenames:
+            file_path = Path(root) / filename
+            try:
+                file_stat = file_path.lstat()
+            except OSError:
+                continue
+            progress["files"] = int(progress["files"]) + 1
+            progress["apparent_size_bytes"] = int(progress["apparent_size_bytes"]) + int(file_stat.st_size)
+            entries_seen += 1
+            if entries_seen >= max_entries:
+                progress["scan_limited"] = True
+                return progress
+        if entries_seen >= max_entries:
+            progress["scan_limited"] = True
+            return progress
+    return progress
+
+
 def _dry_run_summary(
     *,
     result: dict,

src/pobsync_server/urls.py

@@ -21,8 +21,10 @@ urlpatterns = [
     path("ssh-credentials/generate/", views.generate_ssh_credential, name="generate_ssh_credential"),
     path("ssh-credentials/<int:credential_id>/", views.edit_ssh_credential, name="edit_ssh_credential"),
     path("ssh-credentials/<int:credential_id>/delete/", views.delete_ssh_credential, name="delete_ssh_credential"),
+    path("hosts/", views.hosts_list, name="hosts_list"),
     path("hosts/new/", views.create_host_config, name="create_host_config"),
     path("hosts/<str:host>/", views.host_detail, name="host_detail"),
+    path("hosts/<str:host>/state/", views.update_host_state, name="update_host_state"),
     path("hosts/<str:host>/config/", views.edit_host_config, name="edit_host_config"),
     path("hosts/<str:host>/prepare-directories/", views.prepare_host_directories, name="prepare_host_directories"),
     path("hosts/<str:host>/scan-known-key/", views.scan_host_known_key, name="scan_host_known_key"),