From bd9da52cc4ed75b267eb72c62b2538242a3c761e Mon Sep 17 00:00:00 2001 From: Forza Date: Mon, 21 Apr 2025 06:30:04 +0200 Subject: [PATCH] Btrfs: Allocator Hints: updates to read_stats --- .../btrfs_allocator_hints-6.12_v4.patch | 356 ++++++++++++++++-- 1 file changed, 329 insertions(+), 27 deletions(-) diff --git a/Btrfs/Allocator Hints/btrfs_allocator_hints-6.12_v4.patch b/Btrfs/Allocator Hints/btrfs_allocator_hints-6.12_v4.patch index 19968ca..5bf8d21 100644 --- a/Btrfs/Allocator Hints/btrfs_allocator_hints-6.12_v4.patch +++ b/Btrfs/Allocator Hints/btrfs_allocator_hints-6.12_v4.patch @@ -1,7 +1,7 @@ From 5e49c78f38cc7f5b7ec012021c8422c1db98ef7e Mon Sep 17 00:00:00 2001 From: Goffredo Baroncelli Date: Sun, 24 Oct 2021 17:31:04 +0200 -Subject: [PATCH 01/27] btrfs: add flags to give an hint to the chunk allocator +Subject: [PATCH 01/31] btrfs: add flags to give an hint to the chunk allocator Add the following flags to give an hint about which chunk should be allocated in which a disk. @@ -50,7 +50,7 @@ index fc29d273845d84..71c6135dc7cfb2 100644 From 160344ae9ae37b32593adc43716172c37b0a734c Mon Sep 17 00:00:00 2001 From: Goffredo Baroncelli Date: Sun, 24 Oct 2021 17:31:05 +0200 -Subject: [PATCH 02/27] btrfs: export dev_item.type in +Subject: [PATCH 02/31] btrfs: export dev_item.type in /sys/fs/btrfs//devinfo//type Signed-off-by: Goffredo Baroncelli @@ -91,7 +91,7 @@ index 03926ad467c919..fe07a7cbcf74c4 100644 From 29637f2e3a69fe77a8097bd772a8a7803b9ec576 Mon Sep 17 00:00:00 2001 From: Goffredo Baroncelli Date: Sun, 24 Oct 2021 17:31:06 +0200 -Subject: [PATCH 03/27] btrfs: change the DEV_ITEM 'type' field via sysfs +Subject: [PATCH 03/31] btrfs: change the DEV_ITEM 'type' field via sysfs Signed-off-by: Kai Krakow --- @@ -197,7 +197,7 @@ index 4481575dd70f35..7bb14d51bffc58 100644 From 970b99e160487e9765b6e7db9f8a89a96ce79811 Mon Sep 17 00:00:00 2001 From: Goffredo Baroncelli Date: Sun, 24 Oct 2021 17:31:07 +0200 -Subject: [PATCH 04/27] btrfs: add allocator_hint mode +Subject: [PATCH 04/31] btrfs: add allocator_hint mode When this mode is enabled, the chunk allocation policy is modified as follow. @@ -388,7 +388,7 @@ index 7bb14d51bffc58..f3c5437e270a22 100644 From 1c1f2e27d3055b7721468c6980479a043f48e2b3 Mon Sep 17 00:00:00 2001 From: Kai Krakow Date: Thu, 27 Jun 2024 20:05:58 +0200 -Subject: [PATCH 05/27] btrfs: add allocator_hint for no allocation preferred +Subject: [PATCH 05/31] btrfs: add allocator_hint for no allocation preferred This is useful where you want to prevent new allocations of chunks on a disk which is going to removed from the pool anyways, e.g. due to bad @@ -441,7 +441,7 @@ index 71c6135dc7cfb2..92bcc59b129a97 100644 From 82553effe6b655f97478b6d13df7ab0ecc192e58 Mon Sep 17 00:00:00 2001 From: Kai Krakow Date: Fri, 6 Dec 2024 00:55:31 +0100 -Subject: [PATCH 06/27] btrfs: add allocator_hint to disable allocation +Subject: [PATCH 06/31] btrfs: add allocator_hint to disable allocation completely This is useful where you want to prevent new allocations of chunks to @@ -516,7 +516,7 @@ index 92bcc59b129a97..3db20734aacfc6 100644 From 10248db4c682397c83b99daa2de4ee0e587c0be2 Mon Sep 17 00:00:00 2001 From: Anand Jain Date: Thu, 2 Jan 2025 02:06:31 +0800 -Subject: [PATCH 07/27] btrfs: simplify output formatting in +Subject: [PATCH 07/31] btrfs: simplify output formatting in btrfs_read_policy_show Refactor the logic in btrfs_read_policy_show() to streamline the @@ -562,7 +562,7 @@ index 3675d961b39a2a..cde47f1c11757f 100644 From 4a49a279c14d9003fd7d4865706bc78142bf1645 Mon Sep 17 00:00:00 2001 From: Anand Jain Date: Thu, 2 Jan 2025 02:06:30 +0800 -Subject: [PATCH 08/27] btrfs: initialize fs_devices->fs_info earlier +Subject: [PATCH 08/31] btrfs: initialize fs_devices->fs_info earlier Currently, fs_devices->fs_info is initialized in btrfs_init_devices_late(), but this occurs too late for find_live_mirror(), which is invoked by @@ -606,7 +606,7 @@ index 99d2c60ac2bf3e..21cc02df8edf06 100644 From ccb29226710d52abbd737fd0b2f438022c045af4 Mon Sep 17 00:00:00 2001 From: Anand Jain Date: Thu, 2 Jan 2025 02:06:32 +0800 -Subject: [PATCH 09/27] btrfs: add btrfs_read_policy_to_enum helper and +Subject: [PATCH 09/31] btrfs: add btrfs_read_policy_to_enum helper and refactor read policy store Introduce the `btrfs_read_policy_to_enum` helper function to simplify the @@ -683,7 +683,7 @@ index cde47f1c11757f..8540af0807648e 100644 From cf73e9084375ab73182d3a2d510e878a137a9664 Mon Sep 17 00:00:00 2001 From: Anand Jain Date: Thu, 2 Jan 2025 02:06:34 +0800 -Subject: [PATCH 10/27] btrfs: add tracking of read blocks for read policy +Subject: [PATCH 10/31] btrfs: add tracking of read blocks for read policy Add fs_devices::read_cnt_blocks to track read blocks, initialize it in open_fs_devices() and clean it up in close_fs_devices(). @@ -801,7 +801,7 @@ index f3c5437e270a22..91a2358b74c91f 100644 From 7070070e90e889d165590aa05f02e671d041d12c Mon Sep 17 00:00:00 2001 From: Kai Krakow Date: Mon, 16 Sep 2024 18:18:25 +0930 -Subject: [PATCH 11/27] btrfs: introduce CONFIG_BTRFS_EXPERIMENTAL from 6.13 +Subject: [PATCH 11/31] btrfs: introduce CONFIG_BTRFS_EXPERIMENTAL from 6.13 CONFIG_BTRFS_EXPERIMENTAL is needed by the RAID1 balancing patches but we don't want to use the full scope of the 6.13 patch because it also @@ -838,7 +838,7 @@ index 4fb925e8c981d8..ead317f1eeb859 100644 From 3efa6c755e4ae0dc36f606b329b10587f24dcab3 Mon Sep 17 00:00:00 2001 From: Anand Jain Date: Thu, 2 Jan 2025 02:06:33 +0800 -Subject: [PATCH 12/27] btrfs: handle value associated with read policy +Subject: [PATCH 12/31] btrfs: handle value associated with read policy parameter This change enables specifying additional configuration values alongside @@ -901,7 +901,7 @@ index 8540af0807648e..b0e624c0598f48 100644 From 687cdc03a694afb2236c7c87de458c519be771ea Mon Sep 17 00:00:00 2001 From: Anand Jain Date: Thu, 2 Jan 2025 02:06:35 +0800 -Subject: [PATCH 13/27] btrfs: introduce round-robin read policy +Subject: [PATCH 13/31] btrfs: introduce round-robin read policy This feature balances I/O across the striped devices when reading from mirrored blocks. @@ -1130,7 +1130,7 @@ index 91a2358b74c91f..65d56bffc6ef8b 100644 From 328002ad27e90dc8ff6b7c2022711b6f0df74a01 Mon Sep 17 00:00:00 2001 From: Anand Jain Date: Thu, 2 Jan 2025 02:06:36 +0800 -Subject: [PATCH 14/27] btrfs: add RAID1 preferred read device +Subject: [PATCH 14/31] btrfs: add RAID1 preferred read device When there's stale data on a mirrored device, this feature lets you choose which device to read from. Mainly used for testing. @@ -1276,7 +1276,7 @@ index 65d56bffc6ef8b..d8075ad17a6d3a 100644 From 5084cf69a0e706dfcae5e594d915e46a124fb25c Mon Sep 17 00:00:00 2001 From: Anand Jain Date: Thu, 2 Jan 2025 02:06:37 +0800 -Subject: [PATCH 15/27] btrfs: expose experimental mode in module information +Subject: [PATCH 15/31] btrfs: expose experimental mode in module information Commit c9c49e8f157e ("btrfs: split out CONFIG_BTRFS_EXPERIMENTAL from CONFIG_BTRFS_DEBUG") introduces a way to enable or disable experimental @@ -1307,7 +1307,7 @@ index c64d0713412231..4742bb2af601a7 100644 From fd9d23cf84c07baec0ba5d4bbd9ecd4c0e671e47 Mon Sep 17 00:00:00 2001 From: Anand Jain Date: Thu, 2 Jan 2025 02:06:38 +0800 -Subject: [PATCH 16/27] btrfs: enable read policy configuration via modprobe +Subject: [PATCH 16/31] btrfs: enable read policy configuration via modprobe parameter This update allows configuring the `read_policy` methods using a @@ -1454,7 +1454,7 @@ index a2a0af8f6a9f94..f61844fc2da9ab 100644 From 77f79e1f0d91253b9a2aa0ff975bf34ecf3d243e Mon Sep 17 00:00:00 2001 From: Anand Jain Date: Thu, 2 Jan 2025 02:06:39 +0800 -Subject: [PATCH 17/27] btrfs: modload to print read policy status +Subject: [PATCH 17/31] btrfs: modload to print read policy status Modified the Btrfs loading message to include the read policy status if the experimental feature is enabled. @@ -1490,7 +1490,7 @@ index 448db8974cda70..ea5ff01881d706 100644 From ea9e632401927e9c38ae4b3e505fff377535f58b Mon Sep 17 00:00:00 2001 From: Anand Jain Date: Fri, 11 Oct 2024 10:49:17 +0800 -Subject: [PATCH 18/27] btrfs: use the path with the lowest latency for RAID1 +Subject: [PATCH 18/31] btrfs: use the path with the lowest latency for RAID1 reads This feature aims to direct the read I/O to the device with the lowest @@ -1605,7 +1605,7 @@ index d8075ad17a6d3a..6c1f219f83b388 100644 From 680350c9732c58e321968974868836bf13ec5c96 Mon Sep 17 00:00:00 2001 From: Kai Krakow Date: Wed, 9 Apr 2025 14:07:18 +0200 -Subject: [PATCH 19/27] btrfs: move latency-based selection into helper +Subject: [PATCH 19/31] btrfs: move latency-based selection into helper Signed-off-by: Kai Krakow --- @@ -1688,7 +1688,7 @@ index a36c2bfa339785..c2f235a02a79ea 100644 From 1f255624630f889fbd9e268b8d7a77f5ed68fa8c Mon Sep 17 00:00:00 2001 From: Kai Krakow Date: Wed, 9 Apr 2025 15:21:14 +0200 -Subject: [PATCH 20/27] btrfs: fix btrfs_read_rr to use the actual number of +Subject: [PATCH 20/31] btrfs: fix btrfs_read_rr to use the actual number of stripes While num_stripes is identical to index at the end of the loop, index @@ -1722,7 +1722,7 @@ index c2f235a02a79ea..63384cd731ded2 100644 From c26c5bdfbeea36dd89fcbefe1c86561a5113869a Mon Sep 17 00:00:00 2001 From: Kai Krakow Date: Tue, 15 Apr 2025 09:04:57 +0200 -Subject: [PATCH 21/27] btrfs: create a helper instead of open coding device +Subject: [PATCH 21/31] btrfs: create a helper instead of open coding device latency calculation Signed-off-by: Kai Krakow @@ -1797,7 +1797,7 @@ index 63384cd731ded2..14baa1b391a936 100644 From e54bf3f05a0c202c8637206b9a4bb03b1e5fe42f Mon Sep 17 00:00:00 2001 From: Kai Krakow Date: Tue, 15 Apr 2025 01:28:06 +0200 -Subject: [PATCH 22/27] btrfs: add filtering by latency to btrfs_read_rr +Subject: [PATCH 22/31] btrfs: add filtering by latency to btrfs_read_rr This introduces a new parameter to btrfs_read_rr to select whether we filter for latency. In case the caller passes latency, we return -1 if @@ -1861,7 +1861,7 @@ index 14baa1b391a936..ff6fd21aaa3226 100644 From b606dcc6ff4a175a3e80a17bb9a85f85a0c9ec03 Mon Sep 17 00:00:00 2001 From: Kai Krakow Date: Fri, 18 Apr 2025 23:31:04 +0200 -Subject: [PATCH 23/27] btrfs: add hybrid latency-rr read policy +Subject: [PATCH 23/31] btrfs: add hybrid latency-rr read policy This mode combines latency and round-robin modes by considering all stripes within 125% of the minimum latency. It falls back to round-robin @@ -1994,7 +1994,7 @@ index 6c1f219f83b388..a6e8a722d9c742 100644 From 5f850824c0b496809d10b8c217c1f347f2f6377e Mon Sep 17 00:00:00 2001 From: Kai Krakow Date: Wed, 16 Apr 2025 22:06:37 +0200 -Subject: [PATCH 24/27] btrfs: add devinfo read stats to sysfs +Subject: [PATCH 24/31] btrfs: add devinfo read stats to sysfs Signed-off-by: Kai Krakow --- @@ -2053,7 +2053,7 @@ index 2014475af9716e..d629ececa0b65e 100644 From 127de63e502294bc6c27a9ae54208481a9b0cb51 Mon Sep 17 00:00:00 2001 From: Kai Krakow Date: Wed, 16 Apr 2025 22:52:14 +0200 -Subject: [PATCH 25/27] btrfs: add last IO age to sysfs read_stats +Subject: [PATCH 25/31] btrfs: add last IO age to sysfs read_stats Each time a stripe is going to be selected, increase a counter in each possible stripe. After selecting a stripe, reset the counter to zero. @@ -2147,7 +2147,7 @@ index a6e8a722d9c742..f2807a7463bf17 100644 From 911a9ed3b04a378537f16669676cfea6a557ec57 Mon Sep 17 00:00:00 2001 From: Kai Krakow Date: Thu, 17 Apr 2025 00:26:03 +0200 -Subject: [PATCH 26/27] btrfs: probe read latency if device is 1000 IOs behind +Subject: [PATCH 26/31] btrfs: probe read latency if device is 1000 IOs behind its siblings This should solve a problem where devices get "frozen" if their read @@ -2184,7 +2184,7 @@ index 59bc6fa8b68e40..124fac989a2541 100644 From 7c11b64d08d6b1a79ba2af5167330d63a392ac18 Mon Sep 17 00:00:00 2001 From: Kai Krakow Date: Thu, 17 Apr 2025 23:59:58 +0200 -Subject: [PATCH 27/27] btrfs: allow a short burst of IO for probing read +Subject: [PATCH 27/31] btrfs: allow a short burst of IO for probing read latency If we do a probe to detect the current read latency of the device, @@ -2259,3 +2259,305 @@ index 124fac989a2541..070e26fda91f8a 100644 #endif /* we couldn't find one that doesn't fail. Just return something + +From c0007becc57f2f8fd3b12be04ff3a62b142bf436 Mon Sep 17 00:00:00 2001 +From: Kai Krakow +Date: Sun, 20 Apr 2025 21:38:56 +0200 +Subject: [PATCH 28/31] btrfs: use checkpoint latency instead of cumulative + latency + +Signed-off-by: Kai Krakow +--- + fs/btrfs/volumes.c | 33 +++++++++++++++++++++------------ + fs/btrfs/volumes.h | 7 +++++++ + 2 files changed, 28 insertions(+), 12 deletions(-) + +diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c +index 070e26fda91f8a..c8a1028852b00e 100644 +--- a/fs/btrfs/volumes.c ++++ b/fs/btrfs/volumes.c +@@ -6013,17 +6013,21 @@ static int btrfs_read_preferred(struct btrfs_chunk_map *map, int first, + * Compute the average latency of the device by dividing total latency by + * number of IOs. + */ +-#define BTRFS_MAX_AGE_FOR_VALID_LATENCY 1000 ++#define BTRFS_MAX_AGE_FOR_VALID_LATENCY 10000 + static u64 btrfs_device_read_latency(struct btrfs_device *device) + { + u64 read_wait = part_stat_read(device->bdev, nsecs[READ]); ++ u64 last_nsecs_read = (u64)atomic64_read(&device->last_nsecs_read); + unsigned long read_ios = part_stat_read(device->bdev, ios[READ]); ++ unsigned long last_ios_read = (unsigned long)atomic64_read(&device->last_ios_read); + u64 last_io_age = (u64)atomic64_read(&device->last_io_age); + u64 avg_wait = 0; ++ s64 delta_read_wait = read_wait - last_nsecs_read; ++ s64 delta_read_ios = read_ios - last_ios_read; + + if (last_io_age >= 0 && last_io_age < BTRFS_MAX_AGE_FOR_VALID_LATENCY +- && read_wait && read_ios && read_wait >= read_ios) +- avg_wait = div_u64(read_wait, read_ios); ++ && delta_read_wait > 0 && delta_read_ios > 0 && delta_read_wait >= delta_read_ios) ++ avg_wait = div_u64(delta_read_wait, delta_read_ios); + + return avg_wait; + } +@@ -6178,7 +6182,7 @@ static int btrfs_read_fastest_rr(struct btrfs_fs_info *fs_info, + } + #endif + +-#define BTRFS_OLD_AGE_IO_BURST 20 ++#define BTRFS_OLD_AGE_IO_BURST 100 + static int find_live_mirror(struct btrfs_fs_info *fs_info, + struct btrfs_chunk_map *map, int first, + int dev_replace_is_ongoing) +@@ -6260,19 +6264,24 @@ static int find_live_mirror(struct btrfs_fs_info *fs_info, + + out: + #ifdef CONFIG_BTRFS_EXPERIMENTAL +- /* reset age of selected stripe */ +- s64 current_age, new_age; + do { +- current_age = atomic64_read(&map->stripes[preferred_mirror].dev->last_io_age); ++ /* reset age of selected stripe */ ++ s64 current_age; ++ struct btrfs_device *pref_dev = map->stripes[preferred_mirror].dev; + ++ spin_lock(&pref_dev->latency_lock); ++ ++ current_age = atomic64_read(&pref_dev->last_io_age); + if (current_age >= BTRFS_MAX_AGE_FOR_VALID_LATENCY) { +- new_age = -BTRFS_OLD_AGE_IO_BURST; ++ atomic64_set(&pref_dev->last_io_age, -BTRFS_OLD_AGE_IO_BURST); ++ atomic64_set(&pref_dev->last_nsecs_read, part_stat_read(pref_dev->bdev, nsecs[READ])); ++ atomic64_set(&pref_dev->last_ios_read, part_stat_read(pref_dev->bdev, ios[READ])); + } else if (current_age >= 0) { +- new_age = 0; +- } else { +- return preferred_mirror; ++ atomic64_set(&pref_dev->last_io_age, 0); + } +- } while (unlikely(atomic64_cmpxchg(&map->stripes[preferred_mirror].dev->last_io_age, current_age, new_age) != current_age)); ++ ++ spin_unlock(&pref_dev->latency_lock); ++ } while (0); + #endif + + /* we couldn't find one that doesn't fail. Just return something +diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h +index f2807a7463bf17..cea9df414d3f61 100644 +--- a/fs/btrfs/volumes.h ++++ b/fs/btrfs/volumes.h +@@ -201,6 +201,13 @@ struct btrfs_device { + #ifdef CONFIG_BTRFS_EXPERIMENTAL + /* store an age of last read access */ + atomic64_t last_io_age; ++ ++ /* lock while updating values */ ++ spinlock_t latency_lock; ++ ++ /* last latency values for short term latency calculation */ ++ atomic64_t last_nsecs_read; ++ atomic64_t last_ios_read; + #endif + }; + + +From de919ef3e87eeed3b3d9487314b0b27221f8d868 Mon Sep 17 00:00:00 2001 +From: Kai Krakow +Date: Sun, 20 Apr 2025 22:10:02 +0200 +Subject: [PATCH 29/31] btrfs: stat latency checkpoints to get more insight + +Signed-off-by: Kai Krakow +--- + fs/btrfs/sysfs.c | 17 ++++++++++++++--- + fs/btrfs/volumes.c | 1 + + fs/btrfs/volumes.h | 1 + + 3 files changed, 16 insertions(+), 3 deletions(-) + +diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c +index fd4583b8b27a56..f6af3de5dbed36 100644 +--- a/fs/btrfs/sysfs.c ++++ b/fs/btrfs/sysfs.c +@@ -2186,15 +2186,26 @@ static ssize_t btrfs_devinfo_read_stats_show(struct kobject *kobj, + struct btrfs_device *device = container_of(kobj, struct btrfs_device, + devid_kobj); + u64 read_wait = part_stat_read(device->bdev, nsecs[READ]); ++ u64 last_nsecs_read = (u64)atomic64_read(&device->last_nsecs_read); + unsigned long read_ios = part_stat_read(device->bdev, ios[READ]); ++ unsigned long last_ios_read = (unsigned long)atomic64_read(&device->last_ios_read); ++ s64 delta_read_wait = read_wait - last_nsecs_read; ++ long delta_read_ios = read_ios - last_ios_read; ++ u64 avg_wait = 0, delta_avg_wait = 0; + +- u64 avg_wait = 0; + if (read_wait && read_ios && read_wait >= read_ios) + avg_wait = div_u64(read_wait, read_ios); + +- return scnprintf(buf, PAGE_SIZE, "ios %lu wait %llu avg %llu age %lld\n", ++ if (delta_read_wait > 0 && delta_read_ios > 0 && delta_read_wait >= delta_read_ios) ++ delta_avg_wait = div_u64(delta_read_wait, delta_read_ios); ++ ++ return scnprintf(buf, PAGE_SIZE, ++ "cumulative ios %lu wait %llu avg %llu " ++ "checkpoint ios %ld wait %lld avg %llu " ++ "age %lld count %llu\n", + read_ios, read_wait, avg_wait, +- atomic64_read(&device->last_io_age)); ++ delta_read_ios, delta_read_wait, delta_avg_wait, ++ atomic64_read(&device->last_io_age), atomic64_read(&device->checkpoints)); + } + BTRFS_ATTR(devid, read_stats, btrfs_devinfo_read_stats_show); + #endif +diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c +index c8a1028852b00e..edad363b8bf067 100644 +--- a/fs/btrfs/volumes.c ++++ b/fs/btrfs/volumes.c +@@ -6273,6 +6273,7 @@ static int find_live_mirror(struct btrfs_fs_info *fs_info, + + current_age = atomic64_read(&pref_dev->last_io_age); + if (current_age >= BTRFS_MAX_AGE_FOR_VALID_LATENCY) { ++ atomic64_inc(&pref_dev->checkpoints); + atomic64_set(&pref_dev->last_io_age, -BTRFS_OLD_AGE_IO_BURST); + atomic64_set(&pref_dev->last_nsecs_read, part_stat_read(pref_dev->bdev, nsecs[READ])); + atomic64_set(&pref_dev->last_ios_read, part_stat_read(pref_dev->bdev, ios[READ])); +diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h +index cea9df414d3f61..88aa0057b51d50 100644 +--- a/fs/btrfs/volumes.h ++++ b/fs/btrfs/volumes.h +@@ -201,6 +201,7 @@ struct btrfs_device { + #ifdef CONFIG_BTRFS_EXPERIMENTAL + /* store an age of last read access */ + atomic64_t last_io_age; ++ atomic64_t checkpoints; + + /* lock while updating values */ + spinlock_t latency_lock; + +From 48e811bf475762c7d66195dfb3d60873a636f417 Mon Sep 17 00:00:00 2001 +From: Kai Krakow +Date: Sun, 20 Apr 2025 23:10:29 +0200 +Subject: [PATCH 30/31] btrfs: rename thresholds to better match with the + checkpoint logic + +Signed-off-by: Kai Krakow +--- + fs/btrfs/volumes.c | 10 +++++----- + 1 file changed, 5 insertions(+), 5 deletions(-) + +diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c +index edad363b8bf067..236ba74f104411 100644 +--- a/fs/btrfs/volumes.c ++++ b/fs/btrfs/volumes.c +@@ -6013,7 +6013,7 @@ static int btrfs_read_preferred(struct btrfs_chunk_map *map, int first, + * Compute the average latency of the device by dividing total latency by + * number of IOs. + */ +-#define BTRFS_MAX_AGE_FOR_VALID_LATENCY 10000 ++#define BTRFS_DEVICE_LATENCY_CHECKPOINT_AGE 10000 + static u64 btrfs_device_read_latency(struct btrfs_device *device) + { + u64 read_wait = part_stat_read(device->bdev, nsecs[READ]); +@@ -6025,7 +6025,7 @@ static u64 btrfs_device_read_latency(struct btrfs_device *device) + s64 delta_read_wait = read_wait - last_nsecs_read; + s64 delta_read_ios = read_ios - last_ios_read; + +- if (last_io_age >= 0 && last_io_age < BTRFS_MAX_AGE_FOR_VALID_LATENCY ++ if (last_io_age >= 0 && last_io_age < BTRFS_DEVICE_LATENCY_CHECKPOINT_AGE + && delta_read_wait > 0 && delta_read_ios > 0 && delta_read_wait >= delta_read_ios) + avg_wait = div_u64(delta_read_wait, delta_read_ios); + +@@ -6182,7 +6182,7 @@ static int btrfs_read_fastest_rr(struct btrfs_fs_info *fs_info, + } + #endif + +-#define BTRFS_OLD_AGE_IO_BURST 100 ++#define BTRFS_DEVICE_LATENCY_CHECKPOINT_BURST_IO 100 + static int find_live_mirror(struct btrfs_fs_info *fs_info, + struct btrfs_chunk_map *map, int first, + int dev_replace_is_ongoing) +@@ -6272,9 +6272,9 @@ static int find_live_mirror(struct btrfs_fs_info *fs_info, + spin_lock(&pref_dev->latency_lock); + + current_age = atomic64_read(&pref_dev->last_io_age); +- if (current_age >= BTRFS_MAX_AGE_FOR_VALID_LATENCY) { ++ if (current_age >= BTRFS_DEVICE_LATENCY_CHECKPOINT_AGE) { + atomic64_inc(&pref_dev->checkpoints); +- atomic64_set(&pref_dev->last_io_age, -BTRFS_OLD_AGE_IO_BURST); ++ atomic64_set(&pref_dev->last_io_age, -BTRFS_DEVICE_LATENCY_CHECKPOINT_BURST_IO); + atomic64_set(&pref_dev->last_nsecs_read, part_stat_read(pref_dev->bdev, nsecs[READ])); + atomic64_set(&pref_dev->last_ios_read, part_stat_read(pref_dev->bdev, ios[READ])); + } else if (current_age >= 0) { + +From 5e140ba573925f30df00aece605fa1255d0ac50d Mon Sep 17 00:00:00 2001 +From: Kai Krakow +Date: Sun, 20 Apr 2025 23:12:56 +0200 +Subject: [PATCH 31/31] btrfs: add a stripe ignored counter + +To get some more insights, we can count how often a stripe has been +ignored relative to its neighbors. We simply increase the counter for +all candidates, then decrease it after selection. + +This should show how evenly distributed one of the read balancing +algorithms is. + +Signed-off-by: Kai Krakow +--- + fs/btrfs/sysfs.c | 5 +++-- + fs/btrfs/volumes.c | 4 +++- + fs/btrfs/volumes.h | 1 + + 3 files changed, 7 insertions(+), 3 deletions(-) + +diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c +index f6af3de5dbed36..9bb159527b4be1 100644 +--- a/fs/btrfs/sysfs.c ++++ b/fs/btrfs/sysfs.c +@@ -2202,10 +2202,11 @@ static ssize_t btrfs_devinfo_read_stats_show(struct kobject *kobj, + return scnprintf(buf, PAGE_SIZE, + "cumulative ios %lu wait %llu avg %llu " + "checkpoint ios %ld wait %lld avg %llu " +- "age %lld count %llu\n", ++ "age %lld count %llu ignored %lld\n", + read_ios, read_wait, avg_wait, + delta_read_ios, delta_read_wait, delta_avg_wait, +- atomic64_read(&device->last_io_age), atomic64_read(&device->checkpoints)); ++ atomic64_read(&device->last_io_age), atomic64_read(&device->checkpoints), ++ atomic64_read(&device->stripe_ignored)); + } + BTRFS_ATTR(devid, read_stats, btrfs_devinfo_read_stats_show); + #endif +diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c +index 236ba74f104411..22bcadb266c2b7 100644 +--- a/fs/btrfs/volumes.c ++++ b/fs/btrfs/volumes.c +@@ -6206,6 +6206,7 @@ static int find_live_mirror(struct btrfs_fs_info *fs_info, + /* age each possible stripe by 1 IO */ + for (int i = first; i < first + num_stripes; i++) { + atomic64_inc(&map->stripes[i].dev->last_io_age); ++ atomic64_inc(&map->stripes[i].dev->stripe_ignored); + } + #endif + +@@ -6277,9 +6278,10 @@ static int find_live_mirror(struct btrfs_fs_info *fs_info, + atomic64_set(&pref_dev->last_io_age, -BTRFS_DEVICE_LATENCY_CHECKPOINT_BURST_IO); + atomic64_set(&pref_dev->last_nsecs_read, part_stat_read(pref_dev->bdev, nsecs[READ])); + atomic64_set(&pref_dev->last_ios_read, part_stat_read(pref_dev->bdev, ios[READ])); +- } else if (current_age >= 0) { ++ } else if (current_age > 0) { + atomic64_set(&pref_dev->last_io_age, 0); + } ++ atomic64_dec(&pref_dev->stripe_ignored); + + spin_unlock(&pref_dev->latency_lock); + } while (0); +diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h +index 88aa0057b51d50..8906edbec4fd1e 100644 +--- a/fs/btrfs/volumes.h ++++ b/fs/btrfs/volumes.h +@@ -202,6 +202,7 @@ struct btrfs_device { + /* store an age of last read access */ + atomic64_t last_io_age; + atomic64_t checkpoints; ++ atomic64_t stripe_ignored; + + /* lock while updating values */ + spinlock_t latency_lock;