ZFS_IOC_COUNT_FILLED does unnecessary txg_wait_synced() #13368
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
behlendorf
reviewed
May 4, 2022
|
(polite ping! wondering if @behlendorf's review comment is a show-stopper.) |
|
The idea here is great. The issue caught by the test case failure just needs to be resolved before it can be merged. |
This was referenced Mar 8, 2023
`lseek(SEEK_DATA | SEEK_HOLE)` are only accurate when the on-disk blocks reflect all writes, i.e. when there are no dirty data blocks. To ensure this, if the target dnode is dirty, they wait for the open txg to be synced, so we can call them "stabilizing operations". If they cause txg_wait_synced often, it can be detrimental to performance. Typically, a group of files are all modified, and then SEEK_DATA/HOLE are performed on them. In this case, the first SEEK does a txg_wait_synced(), and subsequent SEEKs don't need to wait, so performance is good. However, if a workload involves an interleaved metadata modification, the subsequent SEEK may do a txg_wait_synced() unnecessarily. For example, if we do a `read()` syscall to each file before we do its SEEK. This applies even with `relatime=on`, when the `read()` is the first read after the last write. The txg_wait_synced() is unnecessary because the SEEK operations only care that the structure of the tree of indirect and data blocks is up to date on disk. They don't care about metadata like the contents of the bonus or spill blocks. (They also don't care if an existing data block is modified, but this would be more involved to filter out.) This commit changes the behavior of SEEK_DATA/HOLE operations such that they do not call txg_wait_synced() if there is only a pending change to the bonus or spill block. Signed-off-by: Matthew Ahrens <[email protected]>
behlendorf
approved these changes
Mar 14, 2023
behlendorf
added
Status: Accepted
behlendorf
pushed a commit
to behlendorf/zfs
that referenced
this pull request
Mar 14, 2023
`lseek(SEEK_DATA | SEEK_HOLE)` are only accurate when the on-disk blocks reflect all writes, i.e. when there are no dirty data blocks. To ensure this, if the target dnode is dirty, they wait for the open txg to be synced, so we can call them "stabilizing operations". If they cause txg_wait_synced often, it can be detrimental to performance. Typically, a group of files are all modified, and then SEEK_DATA/HOLE are performed on them. In this case, the first SEEK does a txg_wait_synced(), and subsequent SEEKs don't need to wait, so performance is good. However, if a workload involves an interleaved metadata modification, the subsequent SEEK may do a txg_wait_synced() unnecessarily. For example, if we do a `read()` syscall to each file before we do its SEEK. This applies even with `relatime=on`, when the `read()` is the first read after the last write. The txg_wait_synced() is unnecessary because the SEEK operations only care that the structure of the tree of indirect and data blocks is up to date on disk. They don't care about metadata like the contents of the bonus or spill blocks. (They also don't care if an existing data block is modified, but this would be more involved to filter out.) This commit changes the behavior of SEEK_DATA/HOLE operations such that they do not call txg_wait_synced() if there is only a pending change to the bonus or spill block. Reviewed-by: Brian Behlendorf <[email protected]> Reviewed-by: Alexander Motin <[email protected]> Signed-off-by: Matthew Ahrens <[email protected]> Closes openzfs#13368 Issue openzfs#14594 Issue openzfs#14512 Issue openzfs#14009
7 tasks
|
Hi, @ahrens Could we say the dnode is also clean if the blkid of lseek offset is bigger than the blkid of all dirty records and free ranges? |
|
@Finix1979 that is probably true, but it might take too long to determine that, with the current data structures. (dn_dirty_records is not sorted so you'd have to look through them all) |
behlendorf
pushed a commit
that referenced
this pull request
Mar 15, 2023
`lseek(SEEK_DATA | SEEK_HOLE)` are only accurate when the on-disk blocks reflect all writes, i.e. when there are no dirty data blocks. To ensure this, if the target dnode is dirty, they wait for the open txg to be synced, so we can call them "stabilizing operations". If they cause txg_wait_synced often, it can be detrimental to performance. Typically, a group of files are all modified, and then SEEK_DATA/HOLE are performed on them. In this case, the first SEEK does a txg_wait_synced(), and subsequent SEEKs don't need to wait, so performance is good. However, if a workload involves an interleaved metadata modification, the subsequent SEEK may do a txg_wait_synced() unnecessarily. For example, if we do a `read()` syscall to each file before we do its SEEK. This applies even with `relatime=on`, when the `read()` is the first read after the last write. The txg_wait_synced() is unnecessary because the SEEK operations only care that the structure of the tree of indirect and data blocks is up to date on disk. They don't care about metadata like the contents of the bonus or spill blocks. (They also don't care if an existing data block is modified, but this would be more involved to filter out.) This commit changes the behavior of SEEK_DATA/HOLE operations such that they do not call txg_wait_synced() if there is only a pending change to the bonus or spill block. Reviewed-by: Brian Behlendorf <[email protected]> Reviewed-by: Alexander Motin <[email protected]> Signed-off-by: Matthew Ahrens <[email protected]> Closes #13368 Issue #14594 Issue #14512 Issue #14009
lundman
pushed a commit
to openzfsonwindows/openzfs
that referenced
this pull request
Mar 17, 2023
`lseek(SEEK_DATA | SEEK_HOLE)` are only accurate when the on-disk blocks reflect all writes, i.e. when there are no dirty data blocks. To ensure this, if the target dnode is dirty, they wait for the open txg to be synced, so we can call them "stabilizing operations". If they cause txg_wait_synced often, it can be detrimental to performance. Typically, a group of files are all modified, and then SEEK_DATA/HOLE are performed on them. In this case, the first SEEK does a txg_wait_synced(), and subsequent SEEKs don't need to wait, so performance is good. However, if a workload involves an interleaved metadata modification, the subsequent SEEK may do a txg_wait_synced() unnecessarily. For example, if we do a `read()` syscall to each file before we do its SEEK. This applies even with `relatime=on`, when the `read()` is the first read after the last write. The txg_wait_synced() is unnecessary because the SEEK operations only care that the structure of the tree of indirect and data blocks is up to date on disk. They don't care about metadata like the contents of the bonus or spill blocks. (They also don't care if an existing data block is modified, but this would be more involved to filter out.) This commit changes the behavior of SEEK_DATA/HOLE operations such that they do not call txg_wait_synced() if there is only a pending change to the bonus or spill block. Reviewed-by: Brian Behlendorf <[email protected]> Reviewed-by: Alexander Motin <[email protected]> Signed-off-by: Matthew Ahrens <[email protected]> Closes openzfs#13368 Issue openzfs#14594 Issue openzfs#14512 Issue openzfs#14009
lundman
pushed a commit
to openzfsonwindows/openzfs
that referenced
this pull request
Mar 17, 2023
`lseek(SEEK_DATA | SEEK_HOLE)` are only accurate when the on-disk blocks reflect all writes, i.e. when there are no dirty data blocks. To ensure this, if the target dnode is dirty, they wait for the open txg to be synced, so we can call them "stabilizing operations". If they cause txg_wait_synced often, it can be detrimental to performance. Typically, a group of files are all modified, and then SEEK_DATA/HOLE are performed on them. In this case, the first SEEK does a txg_wait_synced(), and subsequent SEEKs don't need to wait, so performance is good. However, if a workload involves an interleaved metadata modification, the subsequent SEEK may do a txg_wait_synced() unnecessarily. For example, if we do a `read()` syscall to each file before we do its SEEK. This applies even with `relatime=on`, when the `read()` is the first read after the last write. The txg_wait_synced() is unnecessary because the SEEK operations only care that the structure of the tree of indirect and data blocks is up to date on disk. They don't care about metadata like the contents of the bonus or spill blocks. (They also don't care if an existing data block is modified, but this would be more involved to filter out.) This commit changes the behavior of SEEK_DATA/HOLE operations such that they do not call txg_wait_synced() if there is only a pending change to the bonus or spill block. Reviewed-by: Brian Behlendorf <[email protected]> Reviewed-by: Alexander Motin <[email protected]> Signed-off-by: Matthew Ahrens <[email protected]> Closes openzfs#13368 Issue openzfs#14594 Issue openzfs#14512 Issue openzfs#14009
lundman
pushed a commit
to openzfsonwindows/openzfs
that referenced
this pull request
Mar 17, 2023
`lseek(SEEK_DATA | SEEK_HOLE)` are only accurate when the on-disk blocks reflect all writes, i.e. when there are no dirty data blocks. To ensure this, if the target dnode is dirty, they wait for the open txg to be synced, so we can call them "stabilizing operations". If they cause txg_wait_synced often, it can be detrimental to performance. Typically, a group of files are all modified, and then SEEK_DATA/HOLE are performed on them. In this case, the first SEEK does a txg_wait_synced(), and subsequent SEEKs don't need to wait, so performance is good. However, if a workload involves an interleaved metadata modification, the subsequent SEEK may do a txg_wait_synced() unnecessarily. For example, if we do a `read()` syscall to each file before we do its SEEK. This applies even with `relatime=on`, when the `read()` is the first read after the last write. The txg_wait_synced() is unnecessary because the SEEK operations only care that the structure of the tree of indirect and data blocks is up to date on disk. They don't care about metadata like the contents of the bonus or spill blocks. (They also don't care if an existing data block is modified, but this would be more involved to filter out.) This commit changes the behavior of SEEK_DATA/HOLE operations such that they do not call txg_wait_synced() if there is only a pending change to the bonus or spill block. Reviewed-by: Brian Behlendorf <[email protected]> Reviewed-by: Alexander Motin <[email protected]> Signed-off-by: Matthew Ahrens <[email protected]> Closes openzfs#13368 Issue openzfs#14594 Issue openzfs#14512 Issue openzfs#14009
lundman
pushed a commit
to openzfsonwindows/openzfs
that referenced
this pull request
Mar 17, 2023
`lseek(SEEK_DATA | SEEK_HOLE)` are only accurate when the on-disk blocks reflect all writes, i.e. when there are no dirty data blocks. To ensure this, if the target dnode is dirty, they wait for the open txg to be synced, so we can call them "stabilizing operations". If they cause txg_wait_synced often, it can be detrimental to performance. Typically, a group of files are all modified, and then SEEK_DATA/HOLE are performed on them. In this case, the first SEEK does a txg_wait_synced(), and subsequent SEEKs don't need to wait, so performance is good. However, if a workload involves an interleaved metadata modification, the subsequent SEEK may do a txg_wait_synced() unnecessarily. For example, if we do a `read()` syscall to each file before we do its SEEK. This applies even with `relatime=on`, when the `read()` is the first read after the last write. The txg_wait_synced() is unnecessary because the SEEK operations only care that the structure of the tree of indirect and data blocks is up to date on disk. They don't care about metadata like the contents of the bonus or spill blocks. (They also don't care if an existing data block is modified, but this would be more involved to filter out.) This commit changes the behavior of SEEK_DATA/HOLE operations such that they do not call txg_wait_synced() if there is only a pending change to the bonus or spill block. Reviewed-by: Brian Behlendorf <[email protected]> Reviewed-by: Alexander Motin <[email protected]> Signed-off-by: Matthew Ahrens <[email protected]> Closes openzfs#13368 Issue openzfs#14594 Issue openzfs#14512 Issue openzfs#14009
|
This seems to cause #14753. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Motivation and Context
lseek(SEEK_DATA | SEEK_HOLE)are only accurate when the on-disk blocksreflect all writes, i.e. when there are no dirty data blocks. To ensure
this, if the target dnode is dirty, they wait for the open txg to be
synced, so we can call them "stabilizing operations". If they cause
txg_wait_synced often, it can be detrimental to performance.
Typically, a group of files are all modified, and then SEEK_DATA/HOLE
are performed on them. In this case, the first SEEK does a
txg_wait_synced(), and subsequent SEEKs don't need to wait, so
performance is good.
However, if a workload involves an interleaved metadata modification,
the subsequent SEEK may do a txg_wait_synced() unnecessarily. For
example, if we do a
read()syscall to each file before we do its SEEK.This applies even with
relatime=on, when theread()is the firstread after the last write. The txg_wait_synced() is unnecessary because
the SEEK operations only care that the structure of the tree of indirect
and data blocks is up to date on disk. They don't care about metadata
like the contents of the bonus or spill blocks. (They also don't care
if an existing data block is modified, but this would be more involved
to filter out.)
Description
This commit changes the behavior of SEEK_DATA/HOLE operations such that
they do not call txg_wait_synced() if there is only a pending change to
the bonus or spill block.
How Has This Been Tested?
Tested with a workload that does:
Previously, the first SEEK_DATA of each file caused a txg_wait_synced(). Now only the first SEEK_DATA of the first file causes a txg_wait_synced().
Types of changes
Checklist:
Signed-off-by.