andreacavalli/rocksdb
0
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Fix recovery for WALs without data for all CFs

Browse Source 
Summary:
if one or more CFs had no data in the WAL, the log number that's used
by FindObsoleteFiles() wasn't updated. We need to treat this case the same as
if the data for that WAL had been flushed.

Test Plan: new unit test

Reviewers: IslamAbdelRahman, yiwu, sdong

Reviewed By: sdong

Subscribers: andrewkr, dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D63963
This commit is contained in:
Andrew Kryczka 2016-09-15 11:40:48 -07:00
parent d7242ff4d5
commit 06b4785fec
2 changed files with 26 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
db/db_impl.cc
View File

@ -1722,7 +1722,7 @@ Status DBImpl::RecoverLogFiles(const std::vector<uint64_t>& log_numbers,
// recovered and should be ignored on next reincarnation.
// Since we already recovered max_log_number, we want all logs
// with numbers `<= max_log_number` (includes this one) to be ignored
if (flushed) {
if (flushed || cfd->mem()->GetFirstSequenceNumber() == 0) {
edit->SetLogNumber(max_log_number + 1);
}
// we must mark the next log number as used, even though it's

25
db/db_wal_test.cc
View File

@ -305,6 +305,31 @@ TEST_F(DBWALTest, GetSortedWalFiles) {
} while (ChangeOptions());
}
TEST_F(DBWALTest, RecoveryWithLogDataForSomeCFs) {
// Test for regression of WAL cleanup missing files that don't contain data
// for every column family.
do {
CreateAndReopenWithCF({"pikachu"}, CurrentOptions());
ASSERT_OK(Put(1, "foo", "v1"));
ASSERT_OK(Put(1, "foo", "v2"));
std::array<uint64_t, 2> earliest_log_nums;
for (int i = 0; i < 2; ++i) {
if (i > 0) {
ReopenWithColumnFamilies({"default", "pikachu"}, CurrentOptions());
}
VectorLogPtr log_files;
ASSERT_OK(dbfull()->GetSortedWalFiles(log_files));
if (log_files.size() > 0) {
earliest_log_nums[i] = log_files[0]->LogNumber();
} else {
earliest_log_nums[i] = port::kMaxUint64;
}
}
// Check at least the first WAL was cleaned up during the recovery.
ASSERT_LT(earliest_log_nums[0], earliest_log_nums[1]);
} while (ChangeOptions());
}
TEST_F(DBWALTest, RecoverWithLargeLog) {
do {
{