Epic: productionize tiered compaction #7554
Assignees
Labels
c/storage/pageserver
Component: storage: pageserver
Comments
This was referenced Apr 30, 2024
This was referenced May 10, 2024
arpad-m
added a commit
that referenced
this issue
May 10, 2024
The old test based on the immutable `target_file_size` that was a parameter to the function. It makes no sense to go further once `current_level_target_height` has reached `u64::MAX`, as lsn's are u64 typed. In practice, we should only run into this if there is a bug, as the practical lsn range usually ends much earlier. Testing on `target_file_size` makes less sense, it basically implements an invocation mode that turns off the looping and only runs one iteration of it. @hlinnaka agrees that `current_level_target_height` is better here. Part of #7554
arpad-m
added a commit
that referenced
this issue
May 13, 2024
In general, tiered compaction is splitting delta layers along the key dimension, but this can only continue until a single key is reached: if the changes from a single key don't fit into one layer file, we used to create layer files of unbounded sizes. This patch implements the method listed as TODO/FIXME in the source code. It does the following things: * Make `accum_key_values` take the target size and if one key's modifications exceed it, make it fill `partition_lsns`, a vector of lsns to use for partitioning. * Have `retile_deltas` use that `partition_lsns` to create delta layers separated by lsn. * Adjust the `test_many_updates_for_single_key` to allow layer files below 0.5 the target size. This situation can create arbitarily small layer files: The amount of data is arbitrary that sits between having just cut a new delta, and then stumbling upon the key that needs to be split along lsn. This data will end up in a dedicated layer and it can be arbitrarily small. * Ignore single-key delta layers for depth calculation: in theory we might have only single-key delta layers in a tier, and this might confuse depth calculation as well, but this should be unlikely. Fixes #7243 Part of #7554 --------- Co-authored-by: Heikki Linnakangas <heikki@neon.tech>
arpad-m
added a commit
that referenced
this issue
May 15, 2024
Adds a test that is a reproducer for many tiered compaction bugs, both ones that have since been fixed as well as still unfxied ones: * (now fixed) #7296 * #7707 * #7759 * Likely also #7244 but I haven't tried that. The key ordering bug can be reproduced by switching to `merge_delta_keys` instead of `merge_delta_keys_buffered`, so reverting a big part of #7661, although it only sometimes reproduces (30-50% of cases). part of #7554
a-masterov
pushed a commit
that referenced
this issue
May 20, 2024
The old test based on the immutable `target_file_size` that was a parameter to the function. It makes no sense to go further once `current_level_target_height` has reached `u64::MAX`, as lsn's are u64 typed. In practice, we should only run into this if there is a bug, as the practical lsn range usually ends much earlier. Testing on `target_file_size` makes less sense, it basically implements an invocation mode that turns off the looping and only runs one iteration of it. @hlinnaka agrees that `current_level_target_height` is better here. Part of #7554
a-masterov
pushed a commit
that referenced
this issue
May 20, 2024
In general, tiered compaction is splitting delta layers along the key dimension, but this can only continue until a single key is reached: if the changes from a single key don't fit into one layer file, we used to create layer files of unbounded sizes. This patch implements the method listed as TODO/FIXME in the source code. It does the following things: * Make `accum_key_values` take the target size and if one key's modifications exceed it, make it fill `partition_lsns`, a vector of lsns to use for partitioning. * Have `retile_deltas` use that `partition_lsns` to create delta layers separated by lsn. * Adjust the `test_many_updates_for_single_key` to allow layer files below 0.5 the target size. This situation can create arbitarily small layer files: The amount of data is arbitrary that sits between having just cut a new delta, and then stumbling upon the key that needs to be split along lsn. This data will end up in a dedicated layer and it can be arbitrarily small. * Ignore single-key delta layers for depth calculation: in theory we might have only single-key delta layers in a tier, and this might confuse depth calculation as well, but this should be unlikely. Fixes #7243 Part of #7554 --------- Co-authored-by: Heikki Linnakangas <heikki@neon.tech>
a-masterov
pushed a commit
that referenced
this issue
May 20, 2024
Adds a test that is a reproducer for many tiered compaction bugs, both ones that have since been fixed as well as still unfxied ones: * (now fixed) #7296 * #7707 * #7759 * Likely also #7244 but I haven't tried that. The key ordering bug can be reproduced by switching to `merge_delta_keys` instead of `merge_delta_keys_buffered`, so reverting a big part of #7661, although it only sometimes reproduces (30-50% of cases). part of #7554
problame
changed the title
problame
changed the title
|
productinizing tiered compaction is on hold, remaining Q2 work tracked in #8001 |
|
Closing, we're not planning to continue working on this in 2024. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
https://www.notion.so/neondatabase/Compaction-2024Q2-eca9b06aa1ae4c62bdf6cf40ab002eb6?pvs=4
Fix bugs (continued from Q1)
identify_levelsbails too early #7775basic functional testing
=tiered#7749Must get done before ship
Backlog
The text was updated successfully, but these errors were encountered: