Skip io_uring feature test when building with fbcode (#12525)

Summary:
Previously when building with fbcode and having a system install of liburing, it would link liburing from fbcode statically as well as the system library dynamically. That led to the following error:

```
./db_stress: error while loading shared libraries: liburing.so.1: cannot open shared object file: No such file or directory
```

The fix is to skip the feature test for system liburing when `FBCODE_BUILD=true`.

Pull Request resolved: https://github.com/facebook/rocksdb/pull/12525

Test Plan:
- `make clean && make ROCKSDB_NO_FBCODE=1 V=1 -j56 db_stress && ./db_stress`
- `make clean && make V=1 -j56 db_stress && ./db_stress`

Reviewed By: anand1976

Differential Revision: D55997335

Pulled By: ajkr

fbshipit-source-id: 17d8561100f41c6c9ae382a80c6cddc14f050bdc

HISTORY.md

@@ -1,6 +1,51 @@
 # Rocksdb Change Log
 > NOTE: Entries for next release do not go here. Follow instructions in `unreleased_history/README.txt`
 
+## 9.1.0 (03/22/2024)
+### New Features
+* Added an option, `GetMergeOperandsOptions::continue_cb`, to give users the ability to end `GetMergeOperands()`'s lookup process before all merge operands were found.
+* *Add sanity checks for ingesting external files that currently checks if the user key comparator used to create the file is compatible with the column family's user key comparator.
+*Support ingesting external files for column family that has user-defined timestamps in memtable only enabled.
+* On file systems that support storage level data checksum and reconstruction, retry SST block reads for point lookups, scans, and flush and compaction if there's a checksum mismatch on the initial read.
+* Some enhancements and fixes to experimental Temperature handling features, including new `default_write_temperature` CF option and opening an `SstFileWriter` with a temperature.
+* `WriteBatchWithIndex` now supports wide-column point lookups via the `GetEntityFromBatch` API. See the API comments for more details.
+* *Implement experimental features: API `Iterator::GetProperty("rocksdb.iterator.write-time")` to allow users to get data's approximate write unix time and write data with a specific write time via `WriteBatch::TimedPut` API.
+
+### Public API Changes
+* Best-effort recovery (`best_efforts_recovery == true`) may now be used together with atomic flush (`atomic_flush == true`). The all-or-nothing recovery guarantee for atomically flushed data will be upheld.
+* Remove deprecated option `bottommost_temperature`, already replaced by `last_level_temperature`
+* Added new PerfContext counters for block cache bytes read - block_cache_index_read_byte, block_cache_filter_read_byte, block_cache_compression_dict_read_byte, and block_cache_read_byte.
+* Deprecate experimental Remote Compaction APIs - StartV2() and WaitForCompleteV2() and introduce Schedule() and Wait(). The new APIs essentially does the same thing as the old APIs. They allow taking externally generated unique id to wait for remote compaction to complete.
+* *For API `WriteCommittedTransaction::GetForUpdate`, if the column family enables user-defined timestamp, it was mandated that argument `do_validate` cannot be false, and UDT based validation has to be done with a user set read timestamp. It's updated to make the UDT based validation optional if user sets `do_validate` to false and does not set a read timestamp. With this, `GetForUpdate` skips UDT based validation and it's users' responsibility to enforce the UDT invariant. SO DO NOT skip this UDT-based validation if users do not have ways to enforce the UDT invariant. Ways to enforce the invariant on the users side include manage a monotonically increasing timestamp, commit transactions in a single thread etc.
+* Defined a new PerfLevel `kEnableWait` to measure time spent by user threads blocked in RocksDB other than mutex, such as a write thread waiting to be added to a write group, a write thread delayed or stalled etc.
+* `RateLimiter`'s API no longer requires the burst size to be the refill size. Users of `NewGenericRateLimiter()` can now provide burst size in `single_burst_bytes`. Implementors of `RateLimiter::SetSingleBurstBytes()` need to adapt their implementations to match the changed API doc.
+* Add `write_memtable_time` to the newly introduced PerfLevel `kEnableWait`.
+
+### Behavior Changes
+* `RateLimiter`s created by `NewGenericRateLimiter()` no longer modify the refill period when `SetSingleBurstBytes()` is called.
+* Merge writes will only keep merge operand count within `ColumnFamilyOptions::max_successive_merges` when the key's merge operands are all found in memory, unless `strict_max_successive_merges` is explicitly set.
+
+### Bug Fixes
+* Fixed `kBlockCacheTier` reads to return `Status::Incomplete` when I/O is needed to fetch a merge chain's base value from a blob file.
+* Fixed `kBlockCacheTier` reads to return `Status::Incomplete` on table cache miss rather than incorrectly returning an empty value.
+* Fixed a data race in WalManager that may affect how frequent PurgeObsoleteWALFiles() runs.
+* Re-enable the recycle_log_file_num option in DBOptions for kPointInTimeRecovery WAL recovery mode, which was previously disabled due to a bug in the recovery logic. This option is incompatible with WriteOptions::disableWAL. A Status::InvalidArgument() will be returned if disableWAL is specified.
+
+### Performance Improvements
+* Java API `multiGet()` variants now take advantage of the underlying batched `multiGet()` performance improvements.
+Before
+```
+Benchmark (columnFamilyTestType) (keyCount) (keySize) (multiGetSize) (valueSize) Mode Cnt Score Error Units
+MultiGetBenchmarks.multiGetList10 no_column_family 10000 16 100 64 thrpt 25 6315.541 ± 8.106 ops/s
+MultiGetBenchmarks.multiGetList10 no_column_family 10000 16 100 1024 thrpt 25 6975.468 ± 68.964 ops/s
+```
+After
+```
+Benchmark (columnFamilyTestType) (keyCount) (keySize) (multiGetSize) (valueSize) Mode Cnt Score Error Units
+MultiGetBenchmarks.multiGetList10 no_column_family 10000 16 100 64 thrpt 25 7046.739 ± 13.299 ops/s
+MultiGetBenchmarks.multiGetList10 no_column_family 10000 16 100 1024 thrpt 25 7654.521 ± 60.121 ops/s
+```
+
 ## 9.0.0 (02/16/2024)
 ### New Features
 * Provide support for FSBuffer for point lookups. Also added support for scans and compactions that don't go through prefetching.

build_tools/build_detect_platform

@@ -163,24 +163,6 @@ case "$TARGET_OS" in
             PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -latomic"
         fi
         PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lpthread -lrt -ldl"
-        if test -z "$ROCKSDB_USE_IO_URING"; then
-            ROCKSDB_USE_IO_URING=1
-        fi
-        if test "$ROCKSDB_USE_IO_URING" -ne 0; then
-            # check for liburing
-            $CXX $PLATFORM_CXXFLAGS -x c++ - -luring -o test.o 2>/dev/null  <<EOF
-              #include <liburing.h>
-              int main() {
-                struct io_uring ring;
-                io_uring_queue_init(1, &ring, 0);
-                return 0;
-              }
-EOF
-            if [ "$?" = 0 ]; then
-                PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -luring"
-                COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_IOURING_PRESENT"
-            fi
-        fi
         # PORT_FILES=port/linux/linux_specific.cc
         ;;
     SunOS)
@@ -614,6 +596,24 @@ EOF
         fi
     fi
 
+    if test -z "$ROCKSDB_USE_IO_URING"; then
+        ROCKSDB_USE_IO_URING=1
+    fi
+    if [ "$ROCKSDB_USE_IO_URING" -ne 0 -a "$PLATFORM" = OS_LINUX ]; then
+        # check for liburing
+        $CXX $PLATFORM_CXXFLAGS -x c++ - -luring -o test.o 2>/dev/null  <<EOF
+          #include <liburing.h>
+          int main() {
+            struct io_uring ring;
+            io_uring_queue_init(1, &ring, 0);
+            return 0;
+          }
+EOF
+        if [ "$?" = 0 ]; then
+            PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -luring"
+            COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_IOURING_PRESENT"
+        fi
+    fi
 fi
 
 # TODO(tec): Fix -Wshorten-64-to-32 errors on FreeBSD and enable the warning.

table/block_based/block_based_table_reader_sync_and_async.h

@@ -729,7 +729,7 @@ DEFINE_SYNC_AND_ASYNC(void, BlockBasedTable::MultiGet)
         }
 
         // Call the *saver function on each entry/block until it returns false
-        for (; biter->Valid(); biter->Next()) {
+        for (; biter->status().ok() && biter->Valid(); biter->Next()) {
           ParsedInternalKey parsed_key;
           Status pik_status = ParseInternalKey(
               biter->key(), &parsed_key, false /* log_err_key */);  // TODO
@@ -754,9 +754,6 @@ DEFINE_SYNC_AND_ASYNC(void, BlockBasedTable::MultiGet)
             done = true;
             break;
           }
-          if (s.ok()) {
-            s = biter->status();
-          }
         }
         // Write the block cache access.
         // XXX: There appear to be 'break' statements above that bypass this
@@ -779,8 +776,10 @@ DEFINE_SYNC_AND_ASYNC(void, BlockBasedTable::MultiGet)
               *lookup_data_block_context, lookup_data_block_context->block_key,
               referenced_key, does_referenced_key_exist, referenced_data_size);
         }
-        s = biter->status();
-        if (done) {
+        if (s.ok()) {
+          s = biter->status();
+        }
+        if (done || !s.ok()) {
           // Avoid the extra Next which is expensive in two-level indexes
           break;
         }

unreleased_history/behavior_changes/generic_rate_limiter_burst.md

@@ -1 +0,0 @@
-* `RateLimiter`s created by `NewGenericRateLimiter()` no longer modify the refill period when `SetSingleBurstBytes()` is called.

unreleased_history/behavior_changes/max_successive_merges_io.md

@@ -1 +0,0 @@
-* Merge writes will only keep merge operand count within `ColumnFamilyOptions::max_successive_merges` when the key's merge operands are all found in memory, unless `strict_max_successive_merges` is explicitly set.

unreleased_history/bug_fixes/blockcachetier_blob_as_mergebase.md

@@ -1 +0,0 @@
-* Fixed `kBlockCacheTier` reads to return `Status::Incomplete` when I/O is needed to fetch a merge chain's base value from a blob file.

unreleased_history/bug_fixes/blockcachetier_tablecachemiss.md

@@ -1 +0,0 @@
-* Fixed `kBlockCacheTier` reads to return `Status::Incomplete` on table cache miss rather than incorrectly returning an empty value.

unreleased_history/bug_fixes/data_race_in_wal_manager.md

@@ -1 +0,0 @@
-* Fixed a data race in WalManager that may affect how frequent PurgeObsoleteWALFiles() runs.

unreleased_history/bug_fixes/recycle_logs_point_in_time_recovery.md

@@ -1 +0,0 @@
-Re-enable the recycle_log_file_num option in DBOptions for kPointInTimeRecovery WAL recovery mode, which was previously disabled due to a bug in the recovery logic. This option is incompatible with WriteOptions::disableWAL. A Status::InvalidArgument() will be returned if disableWAL is specified.

unreleased_history/new_features/get_merge_operands_continue_callback.md

@@ -1 +0,0 @@
-* Added an option, `GetMergeOperandsOptions::continue_cb`, to give users the ability to end `GetMergeOperands()`'s lookup process before all merge operands were found.

unreleased_history/new_features/new_ingest_files_behavior.md

@@ -1,2 +0,0 @@
-*Add sanity checks for ingesting external files that currently checks if the user key comparator used to create the file is compatible with the column family's user key comparator.
-*Support ingesting external files for column family that has user-defined timestamps in memtable only enabled.

unreleased_history/new_features/retry_on_corruption.md

@@ -1 +0,0 @@
-On file systems that support storage level data checksum and reconstruction, retry SST block reads for point lookups, scans, and flush and compaction if there's a checksum mismatch on the initial read.

unreleased_history/new_features/temperature_handling.md

@@ -1 +0,0 @@
-* Some enhancements and fixes to experimental Temperature handling features, including new `default_write_temperature` CF option and opening an `SstFileWriter` with a temperature.

unreleased_history/new_features/wbwi_get_entity_from_batch.md

@@ -1 +0,0 @@
-* `WriteBatchWithIndex` now supports wide-column point lookups via the `GetEntityFromBatch` API. See the API comments for more details.

unreleased_history/new_features/write_time_and_timed_put.md

@@ -1 +0,0 @@
-*Implement experimental features: API `Iterator::GetProperty("rocksdb.iterator.write-time")` to allow users to get data's approximate write unix time and write data with a specific write time via `WriteBatch::TimedPut` API.

unreleased_history/performance_improvements/java_api_multiget.md

@@ -1,14 +0,0 @@
-Java API `multiGet()` variants now take advantage of the underlying batched `multiGet()` performance improvements.
-
-Before
-```
-Benchmark (columnFamilyTestType) (keyCount) (keySize) (multiGetSize) (valueSize) Mode Cnt Score Error Units
-MultiGetBenchmarks.multiGetList10 no_column_family 10000 16 100 64 thrpt 25 6315.541 ± 8.106 ops/s
-MultiGetBenchmarks.multiGetList10 no_column_family 10000 16 100 1024 thrpt 25 6975.468 ± 68.964 ops/s
-```
-After
-```
-Benchmark (columnFamilyTestType) (keyCount) (keySize) (multiGetSize) (valueSize) Mode Cnt Score Error Units
-MultiGetBenchmarks.multiGetList10 no_column_family 10000 16 100 64 thrpt 25 7046.739 ± 13.299 ops/s
-MultiGetBenchmarks.multiGetList10 no_column_family 10000 16 100 1024 thrpt 25 7654.521 ± 60.121 ops/s
-```

unreleased_history/public_api_changes/best_effort_atomic.md

@@ -1 +0,0 @@
-* Best-effort recovery (`best_efforts_recovery == true`) may now be used together with atomic flush (`atomic_flush == true`). The all-or-nothing recovery guarantee for atomically flushed data will be upheld.

unreleased_history/public_api_changes/bottommost_temperature.md

@@ -1 +0,0 @@
-Remove deprecated option `bottommost_temperature`, already replaced by `last_level_temperature`

unreleased_history/public_api_changes/new_block_cache_perf_counters.md

@@ -1 +0,0 @@
-Added new PerfContext counters for block cache bytes read - block_cache_index_read_byte, block_cache_filter_read_byte, block_cache_compression_dict_read_byte, and block_cache_read_byte.

unreleased_history/public_api_changes/new_remote_compaction_api.md

@@ -1 +0,0 @@
-Deprecate experimental Remote Compaction APIs - StartV2() and WaitForCompleteV2() and introduce Schedule() and Wait(). The new APIs essentially does the same thing as the old APIs. They allow taking externally generated unique id to wait for remote compaction to complete.

unreleased_history/public_api_changes/optional_skip_udt_based_validation_write_committed.md

@@ -1 +0,0 @@
-*For API `WriteCommittedTransaction::GetForUpdate`, if the column family enables user-defined timestamp, it was mandated that argument `do_validate` cannot be false, and UDT based validation has to be done with a user set read timestamp. It's updated to make the UDT based validation optional if user sets `do_validate` to false and does not set a read timestamp. With this, `GetForUpdate` skips UDT based validation and it's users' responsibility to enforce the UDT invariant. SO DO NOT skip this UDT-based validation if users do not have ways to enforce the UDT invariant. Ways to enforce the invariant on the users side include manage a monotonically increasing timestamp, commit transactions in a single thread etc.

unreleased_history/public_api_changes/perf_level_for_blocking_events.md

@@ -1 +0,0 @@
-Defined a new PerfLevel `kEnableWait` to measure time spent by user threads blocked in RocksDB other than mutex, such as a write thread waiting to be added to a write group, a write thread delayed or stalled etc.

unreleased_history/public_api_changes/rate_limiter_burst.md

@@ -1 +0,0 @@
-* `RateLimiter`'s API no longer requires the burst size to be the refill size. Users of `NewGenericRateLimiter()` can now provide burst size in `single_burst_bytes`. Implementors of `RateLimiter::SetSingleBurstBytes()` need to adapt their implementations to match the changed API doc.

unreleased_history/public_api_changes/write-memtable-time-new-perf-level.md

@@ -1 +0,0 @@
-* Add `write_memtable_time` to the newly introduced PerfLevel `kEnableWait`.