Linux kernel 6.1 is out now

The Rust support is going particularly well, since the new M1 stuff is being done in Rust and Linus himself is using an M1 machine. He said that the Rust support would have to be used so that it would actually be tested properly, and he's in a position to do that personally.

We don't know what the next LTS version is going to be, do we? I would stay on latest if it weren't for nvidia, but the nvidia drivers always make me nervous about updating the kernel.

We don't know what the next LTS is going to be do we? I would stay on latest, but the nvidia drivers make me nervous.

We don't know what the next LTS version is going to be, do we? I would stay on latest if it weren't for nvidia, but the nvidia drivers always make me nervous about updating the kernel.

Since DKMS became a thing, the Nvidia driver doesn't really care about kernel version. The module gets built against the kernel you have. Every now and then there's an issue with the driver having problems with building against a kernel that's newer than expected, but a new driver version tends to get rolled out quickly when that happens.

I've had problems in the past, but it's been a while. Perhaps I was being unnecessarily cautious, I'll experiment with 6.1.

I've had problems in the past, but it's been a while. Perhaps I was being unnecessarily cautious, I'll experiment with 6.1.

Historically, nvidia has been way better at this than AMD. When the FireGL drivers were a thing, you'd upgrade your system and the driver would be broken for months, either from a kernel upgrade or Xorg. I maintain this is the real reason they mainlined it into the kernel / mesa. They just didn't have the manpower to maintain a separate driver. It's also likely the reason they had like 4 different drivers at some point.

Just booted into 6.1 (actually it's an RC because the repos don't have latest yet) with no problems.

I tend to forget how incredibly easy Manjaro makes it to switch kernels.

Btrfs file system performance improvements.

Is long mounting of large HDD partitions fixed now?

What counts as large partitions and long time? I use BTRFS on several servers each with 153TB per partition and mounting is sub second and have been for many years.

edit: that said one of the listed items is improved mount times on large systems:

Hi,

please pull the following updates for btrfs. There's a bunch of
performance improvements, most notably the FIEMAP speedup, the new block
group tree to speed up mount on large filesystems, more io_uring
integration, some sysfs exports and the usual fixes and core updates.

Thanks.

---

Performance:

- outstanding FIEMAP speed improvement
- algorithmic change how extents are enumerated leads to orders of
magnitude speed boost (uncached and cached)
- extent sharing check speedup (2.2x uncached, 3x cached)
- add more cancellation points, allowing to interrupt seeking in files
with large number of extents
- more efficient hole and data seeking (4x uncached, 1.3x cached)
- sample results:
256M, 32K extents: 4s -> 29ms (~150x)
512M, 64K extents: 30s -> 59ms (~550x)
1G, 128K extents: 225s -> 120ms (~1800x)

- improved inode logging, especially for directories (on dbench workload
throughput +25%, max latency -21%)

- improved buffered IO, remove redundant extent state tracking, lowering
memory consumption and avoiding rb tree traversal

- add sysfs tunable to let qgroup temporarily skip exact accounting when
deleting snapshot, leading to a speedup but requiring a rescan after
that, will be used by snapper

- support io_uring and buffered writes, until now it was just for direct
IO, with the no-wait semantics implemented in the buffered write path
it now works and leads to speed improvement in IOPS (2x), throughput
(2.2x), latency (depends, 2x to 150x)

- small performance improvements when dropping and searching for extent
maps as well as when flushing delalloc in COW mode (throughput +5MB/s)

User visible changes:

- new incompatible feature block-group-tree adding a dedicated tree for
tracking block groups, this allows a much faster load during mount and
avoids seeking unlike when it's scattered in the extent tree items
- this reduces mount time for many-terabyte sized filesystems
- conversion tool will be provided so existing filesystem can also be
updated in place
- to reduce test matrix and feature combinations requires no-holes
and free-space-tree (mkfs defaults since 5.15)

- improved reporting of super block corruption detected by scrub

- scrub also tries to repair super block and does not wait until next
commit

- discard stats and tunables are exported in sysfs
(/sys/fs/btrfs/FSID/discard)

- qgroup status is exported in sysfs (/sys/sys/fs/btrfs/FSID/qgroups/)

- verify that super block was not modified when thawing filesystem

Fixes:

- FIEMAP fixes
- fix extent sharing status, does not depend on the cached status where
merged
- flush delalloc so compressed extents are reported correctly

- fix alignment of VMA for memory mapped files on THP

- send: fix failures when processing inodes with no links (orphan files
and directories)

- fix race between quota enable and quota rescan ioctl

- handle more corner cases for read-only compat feature verification

- fix missed extent on fsync after dropping extent maps

Core:

- lockdep annotations to validate various transactions states and state
transitions

- preliminary support for fs-verity in send

- more effective memory use in scrub for subpage where sector is smaller
than page

- block group caching progress logic has been removed, load is now
synchronous

- simplify end IO callbacks and bio handling, use chained bios instead
of own tracking

- add no-wait semantics to several functions (tree search, nocow,
flushing, buffered write

- cleanups and refactoring

MM changes:

- export balance_dirty_pages_ratelimited_flags

Last edited by F.Ultra on 12 December 2022 at 11:40 pm UTC

Btrfs file system performance improvements.

Is long mounting of large HDD partitions fixed now?

What counts as large partitions and long time? I use BTRFS on several servers each with 153TB per partition and mounting is sub second and have been for many years.

edit: that said one of the listed items is improved mount times on large systems:

Hi,

please pull the following updates for btrfs. There's a bunch of
performance improvements, most notably the FIEMAP speedup, the new block
group tree to speed up mount on large filesystems, more io_uring
integration, some sysfs exports and the usual fixes and core updates.

Thanks.

---

Performance:

- outstanding FIEMAP speed improvement
- algorithmic change how extents are enumerated leads to orders of
magnitude speed boost (uncached and cached)
- extent sharing check speedup (2.2x uncached, 3x cached)
- add more cancellation points, allowing to interrupt seeking in files
with large number of extents
- more efficient hole and data seeking (4x uncached, 1.3x cached)
- sample results:
256M, 32K extents: 4s -> 29ms (~150x)
512M, 64K extents: 30s -> 59ms (~550x)
1G, 128K extents: 225s -> 120ms (~1800x)

- improved inode logging, especially for directories (on dbench workload
throughput +25%, max latency -21%)

- improved buffered IO, remove redundant extent state tracking, lowering
memory consumption and avoiding rb tree traversal

- add sysfs tunable to let qgroup temporarily skip exact accounting when
deleting snapshot, leading to a speedup but requiring a rescan after
that, will be used by snapper

- support io_uring and buffered writes, until now it was just for direct
IO, with the no-wait semantics implemented in the buffered write path
it now works and leads to speed improvement in IOPS (2x), throughput
(2.2x), latency (depends, 2x to 150x)

- small performance improvements when dropping and searching for extent
maps as well as when flushing delalloc in COW mode (throughput +5MB/s)

User visible changes:

- new incompatible feature block-group-tree adding a dedicated tree for
tracking block groups, this allows a much faster load during mount and
avoids seeking unlike when it's scattered in the extent tree items
- this reduces mount time for many-terabyte sized filesystems
- conversion tool will be provided so existing filesystem can also be
updated in place
- to reduce test matrix and feature combinations requires no-holes
and free-space-tree (mkfs defaults since 5.15)

- improved reporting of super block corruption detected by scrub

- scrub also tries to repair super block and does not wait until next
commit

- discard stats and tunables are exported in sysfs
(/sys/fs/btrfs/FSID/discard)

- qgroup status is exported in sysfs (/sys/sys/fs/btrfs/FSID/qgroups/)

- verify that super block was not modified when thawing filesystem

Fixes:

- FIEMAP fixes
- fix extent sharing status, does not depend on the cached status where
merged
- flush delalloc so compressed extents are reported correctly

- fix alignment of VMA for memory mapped files on THP

- send: fix failures when processing inodes with no links (orphan files
and directories)

- fix race between quota enable and quota rescan ioctl

- handle more corner cases for read-only compat feature verification

- fix missed extent on fsync after dropping extent maps

Core:

- lockdep annotations to validate various transactions states and state
transitions

- preliminary support for fs-verity in send

- more effective memory use in scrub for subpage where sector is smaller
than page

- block group caching progress logic has been removed, load is now
synchronous

- simplify end IO callbacks and bio handling, use chained bios instead
of own tracking

- add no-wait semantics to several functions (tree search, nocow,
flushing, buffered write

- cleanups and refactoring

MM changes:

- export balance_dirty_pages_ratelimited_flags

I wonder how long it would take me to fill up 153TB with my Steam Library on my 2gbit fiber line...

https://kernelnewbies.org/LinuxChanges is my favorite site for keeping up to date with changes in the Linux kernel.

Just booted into 6.1 (actually it's an RC because the repos don't have latest yet) with no problems.

I tend to forget how incredibly easy Manjaro makes it to switch kernels.

I just did the same on my Manjaro install on the Steam Deck, after Manjaro complained about the 5.19 kernel. I installed the 6.1, rebooted, and X would not start
I had to connect to the machine with ssh, because the console screen is the steam deck monitor flipped on the side and very tiny :-)
After uninstalling the linux61 package and running mkinitcpio -P it worked again

Just booted into 6.1 (actually it's an RC because the repos don't have latest yet) with no problems.

I tend to forget how incredibly easy Manjaro makes it to switch kernels.

I just did the same on my Manjaro install on the Steam Deck, after Manjaro complained about the 5.19 kernel. I installed the 6.1, rebooted, and X would not start
I had to connect to the machine with ssh, because the console screen is the steam deck monitor flipped on the side and very tiny :-)
After uninstalling the linux61 package and running mkinitcpio -P it worked again

Can't you just use grub to boot back into the old kernel? I assume steamdeck uses grub?

I wonder how long it would take me to fill up 153TB with my Steam Library on my 2gbit fiber line...

You clearly need a GoFundMe to answer this question!

I wonder how long it would take me to fill up 153TB with my Steam Library on my 2gbit fiber line...

You clearly need a GoFundMe to answer this question!

I agree!!

Btrfs file system performance improvements.

Is long mounting of large HDD partitions fixed now?

What counts as large partitions and long time? I use BTRFS on several servers each with 153TB per partition and mounting is sub second and have been for many years.

edit: that said one of the listed items is improved mount times on large systems:

Hi,

please pull the following updates for btrfs. There's a bunch of
performance improvements, most notably the FIEMAP speedup, the new block
group tree to speed up mount on large filesystems, more io_uring
integration, some sysfs exports and the usual fixes and core updates.

Thanks.

---

Performance:

- outstanding FIEMAP speed improvement
- algorithmic change how extents are enumerated leads to orders of
magnitude speed boost (uncached and cached)
- extent sharing check speedup (2.2x uncached, 3x cached)
- add more cancellation points, allowing to interrupt seeking in files
with large number of extents
- more efficient hole and data seeking (4x uncached, 1.3x cached)
- sample results:
256M, 32K extents: 4s -> 29ms (~150x)
512M, 64K extents: 30s -> 59ms (~550x)
1G, 128K extents: 225s -> 120ms (~1800x)

- improved inode logging, especially for directories (on dbench workload
throughput +25%, max latency -21%)

- improved buffered IO, remove redundant extent state tracking, lowering
memory consumption and avoiding rb tree traversal

- add sysfs tunable to let qgroup temporarily skip exact accounting when
deleting snapshot, leading to a speedup but requiring a rescan after
that, will be used by snapper

- support io_uring and buffered writes, until now it was just for direct
IO, with the no-wait semantics implemented in the buffered write path
it now works and leads to speed improvement in IOPS (2x), throughput
(2.2x), latency (depends, 2x to 150x)

- small performance improvements when dropping and searching for extent
maps as well as when flushing delalloc in COW mode (throughput +5MB/s)

User visible changes:

- new incompatible feature block-group-tree adding a dedicated tree for
tracking block groups, this allows a much faster load during mount and
avoids seeking unlike when it's scattered in the extent tree items
- this reduces mount time for many-terabyte sized filesystems
- conversion tool will be provided so existing filesystem can also be
updated in place
- to reduce test matrix and feature combinations requires no-holes
and free-space-tree (mkfs defaults since 5.15)

- improved reporting of super block corruption detected by scrub

- scrub also tries to repair super block and does not wait until next
commit

- discard stats and tunables are exported in sysfs
(/sys/fs/btrfs/FSID/discard)

- qgroup status is exported in sysfs (/sys/sys/fs/btrfs/FSID/qgroups/)

- verify that super block was not modified when thawing filesystem

Fixes:

- FIEMAP fixes
- fix extent sharing status, does not depend on the cached status where
merged
- flush delalloc so compressed extents are reported correctly

- fix alignment of VMA for memory mapped files on THP

- send: fix failures when processing inodes with no links (orphan files
and directories)

- fix race between quota enable and quota rescan ioctl

- handle more corner cases for read-only compat feature verification

- fix missed extent on fsync after dropping extent maps

Core:

- lockdep annotations to validate various transactions states and state
transitions

- preliminary support for fs-verity in send

- more effective memory use in scrub for subpage where sector is smaller
than page

- block group caching progress logic has been removed, load is now
synchronous

- simplify end IO callbacks and bio handling, use chained bios instead
of own tracking

- add no-wait semantics to several functions (tree search, nocow,
flushing, buffered write

- cleanups and refactoring

MM changes:

- export balance_dirty_pages_ratelimited_flags

known issue for HDD (rotational disks)
https://bbs.archlinux.org/viewtopic.php?id=272376
https://lore.kernel.org/linux-btrfs/CAMQzBqCSzr4UO1VFTjtSDPt+0ukhf6yqK=q+eLA+Tp1hiB_weA@mail.gmail.com/t/#u
https://lore.kernel.org/linux-btrfs/CAHQ7scVGPAwEGQOq3Kmn75GJzyzSQ9qrBBZrHFu+4YWQhGE0Lw@mail.gmail.com/t/#u
That guy has 16TB disk and it takes under 1 minute to mount it.
I have 3.2TB partition and it mounts in 17 seconds, with defragmented extents.

Well I use rotational HDD:s as well (so ok they are SAS and not SATA drives but that shouldn't matter), in the latest machine I configured it was 36 x Seagate Exos X18 3.5 HDD 16TB SAS and it mounts almost instantly.

edit: not saying that it doesn't happen to people because it obviously are, just that it does not seem to be universal. Anyway here is to hoping that the changes in 6.1 solves it for the people that are experiencing this issue.


Last edited by F.Ultra on 13 December 2022 at 11:45 pm UTC

Btrfs file system performance improvements.

Is long mounting of large HDD partitions fixed now?

What counts as large partitions and long time? I use BTRFS on several servers each with 153TB per partition and mounting is sub second and have been for many years.

edit: that said one of the listed items is improved mount times on large systems:

Hi,

please pull the following updates for btrfs. There's a bunch of
performance improvements, most notably the FIEMAP speedup, the new block
group tree to speed up mount on large filesystems, more io_uring
integration, some sysfs exports and the usual fixes and core updates.

Thanks.

---

Performance:

- outstanding FIEMAP speed improvement
- algorithmic change how extents are enumerated leads to orders of
magnitude speed boost (uncached and cached)
- extent sharing check speedup (2.2x uncached, 3x cached)
- add more cancellation points, allowing to interrupt seeking in files
with large number of extents
- more efficient hole and data seeking (4x uncached, 1.3x cached)
- sample results:
256M, 32K extents: 4s -> 29ms (~150x)
512M, 64K extents: 30s -> 59ms (~550x)
1G, 128K extents: 225s -> 120ms (~1800x)

- improved inode logging, especially for directories (on dbench workload
throughput +25%, max latency -21%)

- improved buffered IO, remove redundant extent state tracking, lowering
memory consumption and avoiding rb tree traversal

- add sysfs tunable to let qgroup temporarily skip exact accounting when
deleting snapshot, leading to a speedup but requiring a rescan after
that, will be used by snapper

- support io_uring and buffered writes, until now it was just for direct
IO, with the no-wait semantics implemented in the buffered write path
it now works and leads to speed improvement in IOPS (2x), throughput
(2.2x), latency (depends, 2x to 150x)

- small performance improvements when dropping and searching for extent
maps as well as when flushing delalloc in COW mode (throughput +5MB/s)

User visible changes:

- new incompatible feature block-group-tree adding a dedicated tree for
tracking block groups, this allows a much faster load during mount and
avoids seeking unlike when it's scattered in the extent tree items
- this reduces mount time for many-terabyte sized filesystems
- conversion tool will be provided so existing filesystem can also be
updated in place
- to reduce test matrix and feature combinations requires no-holes
and free-space-tree (mkfs defaults since 5.15)

- improved reporting of super block corruption detected by scrub

- scrub also tries to repair super block and does not wait until next
commit

- discard stats and tunables are exported in sysfs
(/sys/fs/btrfs/FSID/discard)

- qgroup status is exported in sysfs (/sys/sys/fs/btrfs/FSID/qgroups/)

- verify that super block was not modified when thawing filesystem

Fixes:

- FIEMAP fixes
- fix extent sharing status, does not depend on the cached status where
merged
- flush delalloc so compressed extents are reported correctly

- fix alignment of VMA for memory mapped files on THP

- send: fix failures when processing inodes with no links (orphan files
and directories)

- fix race between quota enable and quota rescan ioctl

- handle more corner cases for read-only compat feature verification

- fix missed extent on fsync after dropping extent maps

Core:

- lockdep annotations to validate various transactions states and state
transitions

- preliminary support for fs-verity in send

- more effective memory use in scrub for subpage where sector is smaller
than page

- block group caching progress logic has been removed, load is now
synchronous

- simplify end IO callbacks and bio handling, use chained bios instead
of own tracking

- add no-wait semantics to several functions (tree search, nocow,
flushing, buffered write

- cleanups and refactoring

MM changes:

- export balance_dirty_pages_ratelimited_flags

I wonder how long it would take me to fill up 153TB with my Steam Library on my 2gbit fiber line...

Well if you start at 0 and then manages to fully saturate that 2Gbps line of yours and pay for all the games, and being able to do so in a manner that would keep the line saturated still and if we assume that this line would be dedicated to just the downloading of said games and not for other Internet usages (such as e.g visiting the Steam store) then it would take aprox 8 days.


Last edited by F.Ultra on 13 December 2022 at 11:53 pm UTC

Can't you just use grub to boot back into the old kernel? I assume steamdeck uses grub?

I assume you can, but I needed a web browser anyway, to help me find the solution to the problem

Btrfs file system performance improvements.

Is long mounting of large HDD partitions fixed now?

What counts as large partitions and long time? I use BTRFS on several servers each with 153TB per partition and mounting is sub second and have been for many years.

edit: that said one of the listed items is improved mount times on large systems:

Hi,

please pull the following updates for btrfs. There's a bunch of
performance improvements, most notably the FIEMAP speedup, the new block
group tree to speed up mount on large filesystems, more io_uring
integration, some sysfs exports and the usual fixes and core updates.

Thanks.

---

Performance:

- outstanding FIEMAP speed improvement
- algorithmic change how extents are enumerated leads to orders of
magnitude speed boost (uncached and cached)
- extent sharing check speedup (2.2x uncached, 3x cached)
- add more cancellation points, allowing to interrupt seeking in files
with large number of extents
- more efficient hole and data seeking (4x uncached, 1.3x cached)
- sample results:
256M, 32K extents: 4s -> 29ms (~150x)
512M, 64K extents: 30s -> 59ms (~550x)
1G, 128K extents: 225s -> 120ms (~1800x)

- improved inode logging, especially for directories (on dbench workload
throughput +25%, max latency -21%)

- improved buffered IO, remove redundant extent state tracking, lowering
memory consumption and avoiding rb tree traversal

- add sysfs tunable to let qgroup temporarily skip exact accounting when
deleting snapshot, leading to a speedup but requiring a rescan after
that, will be used by snapper

- support io_uring and buffered writes, until now it was just for direct
IO, with the no-wait semantics implemented in the buffered write path
it now works and leads to speed improvement in IOPS (2x), throughput
(2.2x), latency (depends, 2x to 150x)

- small performance improvements when dropping and searching for extent
maps as well as when flushing delalloc in COW mode (throughput +5MB/s)

User visible changes:

- new incompatible feature block-group-tree adding a dedicated tree for
tracking block groups, this allows a much faster load during mount and
avoids seeking unlike when it's scattered in the extent tree items
- this reduces mount time for many-terabyte sized filesystems
- conversion tool will be provided so existing filesystem can also be
updated in place
- to reduce test matrix and feature combinations requires no-holes
and free-space-tree (mkfs defaults since 5.15)

- improved reporting of super block corruption detected by scrub

- scrub also tries to repair super block and does not wait until next
commit

- discard stats and tunables are exported in sysfs
(/sys/fs/btrfs/FSID/discard)

- qgroup status is exported in sysfs (/sys/sys/fs/btrfs/FSID/qgroups/)

- verify that super block was not modified when thawing filesystem

Fixes:

- FIEMAP fixes
- fix extent sharing status, does not depend on the cached status where
merged
- flush delalloc so compressed extents are reported correctly

- fix alignment of VMA for memory mapped files on THP

- send: fix failures when processing inodes with no links (orphan files
and directories)

- fix race between quota enable and quota rescan ioctl

- handle more corner cases for read-only compat feature verification

- fix missed extent on fsync after dropping extent maps

Core:

- lockdep annotations to validate various transactions states and state
transitions

- preliminary support for fs-verity in send

- more effective memory use in scrub for subpage where sector is smaller
than page

- block group caching progress logic has been removed, load is now
synchronous

- simplify end IO callbacks and bio handling, use chained bios instead
of own tracking

- add no-wait semantics to several functions (tree search, nocow,
flushing, buffered write

- cleanups and refactoring

MM changes:

- export balance_dirty_pages_ratelimited_flags

I wonder how long it would take me to fill up 153TB with my Steam Library on my 2gbit fiber line...

Well if you start at 0 and then manages to fully saturate that 2Gbps line of yours and pay for all the games, and being able to do so in a manner that would keep the line saturated still and if we assume that this line would be dedicated to just the downloading of said games and not for other Internet usages (such as e.g visiting the Steam store) then it would take aprox 8 days.

Haha! I mean I likely have enough in my steam library where I could fill up that much. Too many games that are 100GB+ these days... hell, the libraries of most of the 16/32bit era aren't even close to 100GB.

Btrfs file system performance improvements.

Is long mounting of large HDD partitions fixed now?

What counts as large partitions and long time? I use BTRFS on several servers each with 153TB per partition and mounting is sub second and have been for many years.

edit: that said one of the listed items is improved mount times on large systems:

Hi,

please pull the following updates for btrfs. There's a bunch of
performance improvements, most notably the FIEMAP speedup, the new block
group tree to speed up mount on large filesystems, more io_uring
integration, some sysfs exports and the usual fixes and core updates.

Thanks.

---

Performance:

- outstanding FIEMAP speed improvement
- algorithmic change how extents are enumerated leads to orders of
magnitude speed boost (uncached and cached)
- extent sharing check speedup (2.2x uncached, 3x cached)
- add more cancellation points, allowing to interrupt seeking in files
with large number of extents
- more efficient hole and data seeking (4x uncached, 1.3x cached)
- sample results:
256M, 32K extents: 4s -> 29ms (~150x)
512M, 64K extents: 30s -> 59ms (~550x)
1G, 128K extents: 225s -> 120ms (~1800x)

- improved inode logging, especially for directories (on dbench workload
throughput +25%, max latency -21%)

- improved buffered IO, remove redundant extent state tracking, lowering
memory consumption and avoiding rb tree traversal

- add sysfs tunable to let qgroup temporarily skip exact accounting when
deleting snapshot, leading to a speedup but requiring a rescan after
that, will be used by snapper

- support io_uring and buffered writes, until now it was just for direct
IO, with the no-wait semantics implemented in the buffered write path
it now works and leads to speed improvement in IOPS (2x), throughput
(2.2x), latency (depends, 2x to 150x)

- small performance improvements when dropping and searching for extent
maps as well as when flushing delalloc in COW mode (throughput +5MB/s)

User visible changes:

- new incompatible feature block-group-tree adding a dedicated tree for
tracking block groups, this allows a much faster load during mount and
avoids seeking unlike when it's scattered in the extent tree items
- this reduces mount time for many-terabyte sized filesystems
- conversion tool will be provided so existing filesystem can also be
updated in place
- to reduce test matrix and feature combinations requires no-holes
and free-space-tree (mkfs defaults since 5.15)

- improved reporting of super block corruption detected by scrub

- scrub also tries to repair super block and does not wait until next
commit

- discard stats and tunables are exported in sysfs
(/sys/fs/btrfs/FSID/discard)

- qgroup status is exported in sysfs (/sys/sys/fs/btrfs/FSID/qgroups/)

- verify that super block was not modified when thawing filesystem

Fixes:

- FIEMAP fixes
- fix extent sharing status, does not depend on the cached status where
merged
- flush delalloc so compressed extents are reported correctly

- fix alignment of VMA for memory mapped files on THP

- send: fix failures when processing inodes with no links (orphan files
and directories)

- fix race between quota enable and quota rescan ioctl

- handle more corner cases for read-only compat feature verification

- fix missed extent on fsync after dropping extent maps

Core:

- lockdep annotations to validate various transactions states and state
transitions

- preliminary support for fs-verity in send

- more effective memory use in scrub for subpage where sector is smaller
than page

- block group caching progress logic has been removed, load is now
synchronous

- simplify end IO callbacks and bio handling, use chained bios instead
of own tracking

- add no-wait semantics to several functions (tree search, nocow,
flushing, buffered write

- cleanups and refactoring

MM changes:

- export balance_dirty_pages_ratelimited_flags

I wonder how long it would take me to fill up 153TB with my Steam Library on my 2gbit fiber line...

Well if you start at 0 and then manages to fully saturate that 2Gbps line of yours and pay for all the games, and being able to do so in a manner that would keep the line saturated still and if we assume that this line would be dedicated to just the downloading of said games and not for other Internet usages (such as e.g visiting the Steam store) then it would take aprox 8 days.

Haha! I mean I likely have enough in my steam library where I could fill up that much. Too many games that are 100GB+ these days... hell, the libraries of most of the 16/32bit era aren't even close to 100GB.

Imagine how worse it will become once they decide to ship textures for 8K gaming...

Btrfs file system performance improvements.

Is long mounting of large HDD partitions fixed now?

What counts as large partitions and long time? I use BTRFS on several servers each with 153TB per partition and mounting is sub second and have been for many years.

edit: that said one of the listed items is improved mount times on large systems:

Hi,

please pull the following updates for btrfs. There's a bunch of
performance improvements, most notably the FIEMAP speedup, the new block
group tree to speed up mount on large filesystems, more io_uring
integration, some sysfs exports and the usual fixes and core updates.

Thanks.

---

Performance:

- outstanding FIEMAP speed improvement
- algorithmic change how extents are enumerated leads to orders of
magnitude speed boost (uncached and cached)
- extent sharing check speedup (2.2x uncached, 3x cached)
- add more cancellation points, allowing to interrupt seeking in files
with large number of extents
- more efficient hole and data seeking (4x uncached, 1.3x cached)
- sample results:
256M, 32K extents: 4s -> 29ms (~150x)
512M, 64K extents: 30s -> 59ms (~550x)
1G, 128K extents: 225s -> 120ms (~1800x)

- improved inode logging, especially for directories (on dbench workload
throughput +25%, max latency -21%)

- improved buffered IO, remove redundant extent state tracking, lowering
memory consumption and avoiding rb tree traversal

- add sysfs tunable to let qgroup temporarily skip exact accounting when
deleting snapshot, leading to a speedup but requiring a rescan after
that, will be used by snapper

- support io_uring and buffered writes, until now it was just for direct
IO, with the no-wait semantics implemented in the buffered write path
it now works and leads to speed improvement in IOPS (2x), throughput
(2.2x), latency (depends, 2x to 150x)

- small performance improvements when dropping and searching for extent
maps as well as when flushing delalloc in COW mode (throughput +5MB/s)

User visible changes:

- new incompatible feature block-group-tree adding a dedicated tree for
tracking block groups, this allows a much faster load during mount and
avoids seeking unlike when it's scattered in the extent tree items
- this reduces mount time for many-terabyte sized filesystems
- conversion tool will be provided so existing filesystem can also be
updated in place
- to reduce test matrix and feature combinations requires no-holes
and free-space-tree (mkfs defaults since 5.15)

- improved reporting of super block corruption detected by scrub

- scrub also tries to repair super block and does not wait until next
commit

- discard stats and tunables are exported in sysfs
(/sys/fs/btrfs/FSID/discard)

- qgroup status is exported in sysfs (/sys/sys/fs/btrfs/FSID/qgroups/)

- verify that super block was not modified when thawing filesystem

Fixes:

- FIEMAP fixes
- fix extent sharing status, does not depend on the cached status where
merged
- flush delalloc so compressed extents are reported correctly

- fix alignment of VMA for memory mapped files on THP

- send: fix failures when processing inodes with no links (orphan files
and directories)

- fix race between quota enable and quota rescan ioctl

- handle more corner cases for read-only compat feature verification

- fix missed extent on fsync after dropping extent maps

Core:

- lockdep annotations to validate various transactions states and state
transitions

- preliminary support for fs-verity in send

- more effective memory use in scrub for subpage where sector is smaller
than page

- block group caching progress logic has been removed, load is now
synchronous

- simplify end IO callbacks and bio handling, use chained bios instead
of own tracking

- add no-wait semantics to several functions (tree search, nocow,
flushing, buffered write

- cleanups and refactoring

MM changes:

- export balance_dirty_pages_ratelimited_flags

I wonder how long it would take me to fill up 153TB with my Steam Library on my 2gbit fiber line...

Well if you start at 0 and then manages to fully saturate that 2Gbps line of yours and pay for all the games, and being able to do so in a manner that would keep the line saturated still and if we assume that this line would be dedicated to just the downloading of said games and not for other Internet usages (such as e.g visiting the Steam store) then it would take aprox 8 days.

Haha! I mean I likely have enough in my steam library where I could fill up that much. Too many games that are 100GB+ these days... hell, the libraries of most of the 16/32bit era aren't even close to 100GB.

Imagine how worse it will become once they decide to ship textures for 8K gaming...

No kidding! As amazing as games look now, I feel like we more or less have just gotten to the point where it's just a resolution thing... sure, some games can be optimized terribly, so they require newer and newer graphics cards. The only other thing I can see upgrading for is higher settings for VR titles.

Still think it takes more talent to edge out graphics and performance out of 8bit/16bit computers, than it does to just throw art at an engine and compile, like so many Unity/Unreal based games these days.

This game still impresses me highly! https://www.youtube.com/watch?v=zRGpT-Kjxs8