From f56112abb7efc825a2ce4febe592447bf04c04b6 Mon Sep 17 00:00:00 2001
From: Anusha Mukka <anushamukka@meta.com>
Date: Thu, 23 Jul 2026 18:43:39 -0700
Subject: [PATCH] Plumb Env::IOActivity into DBImpl::ResumeImpl (#14952)

Summary:
Pull Request resolved: https://github.com/facebook/rocksdb/pull/14952

`DBImpl::ResumeImpl()` constructed its local `ReadOptions`/`WriteOptions`
with defaults and carried a `// TODO: plumb Env::IOActivity, Env::IOPriority`
comment. Those options flow into `VersionSet::LogAndApply()` (the MANIFEST
write during error recovery), so the rate limiter could not attribute or
prioritize that I/O correctly.

This resolves the TODO for `ResumeImpl` (1 of 91 identical TODOs across the
codebase) by accepting an `Env::IOActivity` parameter and constructing the
options with it, following the pattern already established in `Get()`,
`MultiGet()`, and `NewIterator()`, and in the `kDBOpen` paths in
`db_impl_open.cc`.

Error recovery is driven by flush operations (as the existing comment in
`ErrorHandler::RecoverFromRetryableBGIOError` notes), so both production
callers and the `TEST_ResumeImpl` hook pass `Env::IOActivity::kFlush`. Setting
`io_activity` on these options is safe: `LogAndApply` does not assert
`io_activity == kUnknown`.

Reviewed By: pdillinger

Differential Revision: D112537885

fbshipit-source-id: 59045fd2f0a6e5bbacef6e0381e03ff95cd28c51
---
 db/db_impl/db_impl.cc       | 8 ++++----
 db/db_impl/db_impl.h        | 5 ++++-
 db/db_impl/db_impl_debug.cc | 2 +-
 db/error_handler.cc         | 4 ++--
 4 files changed, 11 insertions(+), 8 deletions(-)

diff --git a/db/db_impl/db_impl.cc b/db/db_impl/db_impl.cc
index f221e58945..9a9b82fbab 100644
--- a/db/db_impl/db_impl.cc
+++ b/db/db_impl/db_impl.cc
@@ -323,12 +323,12 @@ Status DBImpl::Resume() {
 // 4. Schedule compactions if needed for all the CFs. This is needed as the
 //    flush in the prior step might have been a no-op for some CFs, which
 //    means a new super version wouldn't have been installed
-Status DBImpl::ResumeImpl(DBRecoverContext context) {
+Status DBImpl::ResumeImpl(DBRecoverContext context,
+                          Env::IOActivity io_activity) {
   mutex_.AssertHeld();
 
-  // TODO: plumb Env::IOActivity, Env::IOPriority
-  const ReadOptions read_options;
-  const WriteOptions write_options;
+  const ReadOptions read_options(io_activity);
+  const WriteOptions write_options(io_activity);
 
   WaitForBackgroundWork();
 
diff --git a/db/db_impl/db_impl.h b/db/db_impl/db_impl.h
index ae316cc3e4..a9d8435aac 100644
--- a/db/db_impl/db_impl.h
+++ b/db/db_impl/db_impl.h
@@ -2233,7 +2233,10 @@ class DBImpl : public DB {
   // Required: DB mutex held
   Status PersistentStatsProcessFormatVersion();
 
-  Status ResumeImpl(DBRecoverContext context);
+  // `io_activity` is used to construct the ReadOptions/WriteOptions for the
+  // internal recovery work (e.g. the MANIFEST write in LogAndApply). Recovery
+  // is driven by flush operations, so callers pass Env::IOActivity::kFlush.
+  Status ResumeImpl(DBRecoverContext context, Env::IOActivity io_activity);
 
   void MaybeIgnoreError(Status* s) const;
 
diff --git a/db/db_impl/db_impl_debug.cc b/db/db_impl/db_impl_debug.cc
index b13d3251af..2ab541063e 100644
--- a/db/db_impl/db_impl_debug.cc
+++ b/db/db_impl/db_impl_debug.cc
@@ -37,7 +37,7 @@ Status DBImpl::TEST_SwitchWAL() {
 
 Status DBImpl::TEST_ResumeImpl(DBRecoverContext context) {
   InstrumentedMutexLock l(&mutex_);
-  return ResumeImpl(context);
+  return ResumeImpl(context, Env::IOActivity::kFlush);
 }
 
 uint64_t DBImpl::TEST_MaxNextLevelOverlappingBytes(
diff --git a/db/error_handler.cc b/db/error_handler.cc
index e15de116cb..9138bdb7be 100644
--- a/db/error_handler.cc
+++ b/db/error_handler.cc
@@ -668,7 +668,7 @@ Status ErrorHandler::RecoverFromBGError(bool is_manual) {
   // can generate background errors should be the flush operations
   recovery_error_ = IOStatus::OK();
   recovery_error_.PermitUncheckedError();
-  Status s = db_->ResumeImpl(recover_context_);
+  Status s = db_->ResumeImpl(recover_context_, Env::IOActivity::kFlush);
   if (s.ok()) {
     soft_error_no_bg_work_ = false;
   } else {
@@ -764,7 +764,7 @@ void ErrorHandler::RecoverFromRetryableBGIOError() {
     TEST_SYNC_POINT("RecoverFromRetryableBGIOError:BeforeResume1");
     recovery_error_ = IOStatus::OK();
     retry_count++;
-    Status s = db_->ResumeImpl(context);
+    Status s = db_->ResumeImpl(context, Env::IOActivity::kFlush);
     RecordStats({ERROR_HANDLER_AUTORESUME_RETRY_TOTAL_COUNT},
                 {} /* int_histograms */);
     if (s.IsShutdownInProgress() ||