krbd: retry on an empty list from udev_enumerate_scan_devices()

systemd 219 doesn't have the issue that is worked around in the
previous commit, but has a different one: udev_enumerate_scan_devices()
always succeeds, but sometimes returns an empty list when the device is
actually there.  This happens rarely and at random so I haven't been
able to get to the bottom of it yet, but it looks like another similar
race condition in libudev.

Since an empty list is expected if the device isn't there, retry just
twice with a small sleep in-between.  This appears to be enough: I got
7 occurrences per 600000 "rbd unmap" invocations, all of which needed
a single retry:

  rbd: udev enumerate missed a device, tries = 1

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>

diff --git a/src/krbd.cc b/src/krbd.cc
index 3a548233b0fedb7d52b1de452a0255002b361a67..43f08070cb45c4a291ee9bbf1a159466af8301ab 100644 (file)
--- a/src/krbd.cc
+++ b/src/krbd.cc
@@ -814,13 +814,25 @@ static int unmap_image(struct krbd_ctx *ctx, const char *devnode,
     wholedevno = sb.st_rdev;
   }
 
-  r = devno_to_krbd_id(ctx->udev, wholedevno, &id);
-  if (r < 0) {
-    if (r == -ENOENT) {
-      cerr << "rbd: '" << devnode << "' is not an rbd device" << std::endl;
-      r = -EINVAL;
+  for (int tries = 0; ; tries++) {
+    r = devno_to_krbd_id(ctx->udev, wholedevno, &id);
+    if (r == -ENOENT && tries < 2) {
+      usleep(250 * 1000);
+    } else {
+      if (r < 0) {
+        if (r == -ENOENT) {
+          std::cerr << "rbd: '" << devnode << "' is not an rbd device"
+                    << std::endl;
+          r = -EINVAL;
+        }
+        return r;
+      }
+      if (tries) {
+        std::cerr << "rbd: udev enumerate missed a device, tries = " << tries
+                  << std::endl;
+      }
+      break;
     }
-    return r;
   }
 
   return do_unmap(ctx->udev, wholedevno, build_unmap_buf(id, options));
@@ -833,14 +845,25 @@ static int unmap_image(struct krbd_ctx *ctx, const krbd_spec& spec,
   string id;
   int r;
 
-  r = spec_to_devno_and_krbd_id(ctx->udev, spec, &devno, &id);
-  if (r < 0) {
-    if (r == -ENOENT) {
-      cerr << "rbd: " << spec << ": not a mapped image or snapshot"
-           << std::endl;
-      r = -EINVAL;
+  for (int tries = 0; ; tries++) {
+    r = spec_to_devno_and_krbd_id(ctx->udev, spec, &devno, &id);
+    if (r == -ENOENT && tries < 2) {
+      usleep(250 * 1000);
+    } else {
+      if (r < 0) {
+        if (r == -ENOENT) {
+          std::cerr << "rbd: " << spec << ": not a mapped image or snapshot"
+                    << std::endl;
+          r = -EINVAL;
+        }
+        return r;
+      }
+      if (tries) {
+        std::cerr << "rbd: udev enumerate missed a device, tries = " << tries
+                  << std::endl;
+      }
+      break;
     }
-    return r;
   }
 
   return do_unmap(ctx->udev, devno, build_unmap_buf(id, options));