From eea0b883e7a4d7a67e1dc3cdec6cc6a07f48d15d Mon Sep 17 00:00:00 2001 From: Adam Kupczyk Date: Tue, 2 Nov 2021 16:57:32 +0100 Subject: [PATCH] os/bluestore/bluefs: Fix data corruption in truncate() It is possible to create condition in which a BlueFS contains file that is corrupted. It can happen when BlueFS replay log is on device A and we just wrote to device B and truncated file. Scenario: 1) write to file h1 on SLOW device 2) flush h1 (initiate transfer, but no fdatasync yet) 3) truncate h1 4) write to file h2 on DB 5) fsync h2 (forces replay log to be written, after fdatasync to DB) 6) poweroff Fixes: https://tracker.ceph.com/issues/53129 Signed-off-by: Adam Kupczyk (cherry picked from commit 49b7b44b3b5c94ee401562e603999e2b3bd8f9a2) --- src/os/bluestore/BlueFS.cc | 1 + src/test/objectstore/test_bluefs.cc | 6 +++--- 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/src/os/bluestore/BlueFS.cc b/src/os/bluestore/BlueFS.cc index 37a000ac6ef..e9c5d7af835 100644 --- a/src/os/bluestore/BlueFS.cc +++ b/src/os/bluestore/BlueFS.cc @@ -2958,6 +2958,7 @@ int BlueFS::_truncate(FileWriter *h, uint64_t offset) ceph_abort_msg("truncate up not supported"); } ceph_assert(h->file->fnode.size >= offset); + _flush_bdev_safely(h); vselector->sub_usage(h->file->vselector_hint, h->file->fnode.size); h->file->fnode.size = offset; vselector->add_usage(h->file->vselector_hint, h->file->fnode.size); diff --git a/src/test/objectstore/test_bluefs.cc b/src/test/objectstore/test_bluefs.cc index b2367213d8d..c8144e63570 100644 --- a/src/test/objectstore/test_bluefs.cc +++ b/src/test/objectstore/test_bluefs.cc @@ -840,9 +840,9 @@ TEST(BlueFS, test_truncate_stable_53129) { TempBdev bdev_slow{size_slow}; BlueFS fs(g_ceph_context); - ASSERT_EQ(0, fs.add_block_device(BlueFS::BDEV_WAL, "wal", false, 0)); - ASSERT_EQ(0, fs.add_block_device(BlueFS::BDEV_DB, "db", false, 0)); - ASSERT_EQ(0, fs.add_block_device(BlueFS::BDEV_SLOW, "slow", false, 0)); + ASSERT_EQ(0, fs.add_block_device(BlueFS::BDEV_WAL, bdev_wal.path, false, 0)); + ASSERT_EQ(0, fs.add_block_device(BlueFS::BDEV_DB, bdev_db.path, false, 0)); + ASSERT_EQ(0, fs.add_block_device(BlueFS::BDEV_SLOW, bdev_slow.path, false, 0)); uuid_d fsid; ASSERT_EQ(0, fs.mkfs(fsid, { BlueFS::BDEV_DB, true, true })); ASSERT_EQ(0, fs.mount()); -- 2.47.3