MDEV-14244 MariaDB fails to run with O_DIRECT

os_file_set_size(): If posix_fallocate() returns EINVAL, fall back
to writing zero bytes to the file. Also, remove some error log output,
and make it possible for a server shutdown to interrupt the fall-back
code.

MariaDB used to ignore any possible return value from posix_fallocate()
ever since innodb_use_fallocate was introduced in MDEV-4338. If EINVAL
was returned, the file would not be extended.

Starting with MDEV-11520, MariaDB would treat EINVAL as a hard error.

Why is the EINVAL returned? The GNU posix_fallocate() function
would first try the fallocate() system call, which would return
-EOPNOTSUPP for many file systems (notably, not ext4). Then, it
would fall back to extending the file one block at a time by invoking
pwrite(fd, "", 1, offset) where offset is 1 less than a multiple of
the file block size. This would fail with EINVAL if the file is in
O_DIRECT mode, because O_DIRECT requires aligned operation.

2 files changed, 28 insertions, 12 deletions

diff --git a/storage/innobase/os/os0file.cc b/storage/innobase/os/os0file.cc
index 2a13746516f..7edf69a4571 100644
--- a/storage/innobase/os/os0file.cc
+++ b/storage/innobase/os/os0file.cc
@@ -2394,15 +2394,22 @@ os_file_set_size(
 		} while (err == EINTR
 			 && srv_shutdown_state == SRV_SHUTDOWN_NONE);
 
-		if (err) {
+		switch (err) {
+		case 0:
+			return true;
+		default:
 			ib_logf(IB_LOG_LEVEL_ERROR,
 				"preallocating " INT64PF " bytes for"
 				"file %s failed with error %d",
 				size, name, err);
+			/* fall through */
+		case EINTR:
+			errno = err;
+			return false;
+		case EINVAL:
+			/* fall back to the code below */
+			break;
 		}
-		/* Set errno because posix_fallocate() does not do it.*/
-		errno = err;
-		return(!err);
 	}
 # endif
 
@@ -2444,11 +2451,12 @@ os_file_set_size(
 		}
 
 		current_size += n_bytes;
-	} while (current_size < size);
+	} while (current_size < size
+		 && srv_shutdown_state == SRV_SHUTDOWN_NONE);
 
 	free(buf2);
 
-	return(ret && os_file_flush(file));
+	return(ret && current_size >= size && os_file_flush(file));
 #endif
 }
 
diff --git a/storage/xtradb/os/os0file.cc b/storage/xtradb/os/os0file.cc
index 183f65bcbd8..69b8a9da671 100644
--- a/storage/xtradb/os/os0file.cc
+++ b/storage/xtradb/os/os0file.cc
@@ -2629,15 +2629,22 @@ os_file_set_size(
 		} while (err == EINTR
 			 && srv_shutdown_state == SRV_SHUTDOWN_NONE);
 
-		if (err) {
+		switch (err) {
+		case 0:
+			return true;
+		default:
 			ib_logf(IB_LOG_LEVEL_ERROR,
 				"preallocating " INT64PF " bytes for"
 				"file %s failed with error %d",
 				size, name, err);
+			/* fall through */
+		case EINTR:
+			errno = err;
+			return false;
+		case EINVAL:
+			/* fall back to the code below */
+			break;
 		}
-		/* Set errno because posix_fallocate() does not do it.*/
-		errno = err;
-		return(!err);
 	}
 # endif
 
@@ -2679,11 +2686,12 @@ os_file_set_size(
 		}
 
 		current_size += n_bytes;
-	} while (current_size < size);
+	} while (current_size < size
+		 && srv_shutdown_state == SRV_SHUTDOWN_NONE);
 
 	free(buf2);
 
-	return(ret && os_file_flush(file));
+	return(ret && current_size >= size && os_file_flush(file));
 #endif
 }