Improving performance #117
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
dutow
force-pushed
the
perffix2
branch
2 times, most recently
from
f8876c2 to
b6af70c
Compare
dAdAbird
approved these changes
Feb 14, 2024
src/include/encryption/enc_tuple.h
Outdated
Comment on lines
19
to
22
| extern void | ||
| pg_tde_crypt_simple(const char* iv_prefix, uint32 start_offset, const char* data, uint32 data_len, char* out, RelKeysData* keys, const char* context); | ||
| extern void | ||
| pg_tde_crypt_complex(const char* iv_prefix, uint32 start_offset, const char* data, uint32 data_len, char* out, RelKeysData* keys, const char* context); |
There was a problem hiding this comment.
Just a minor thing - should those be "external" (I mean to it looks like rather "private" functions)
There was a problem hiding this comment.
Originally I considered simply calling the simple function at some places, but it is safer to always call the main function and it doesn't matter that much. I'll remove these from the header.
This commit tries to improve the performance of our encryption, based on the results reported in percona#89. It contains two main changes which results in improvents: * Our pg_tde_crypt loop has several conditions to support all possible cornercases it might encounter. These conditions are not neccessary most of the time, but slow down our throughput considerably. This commit introduces a "simple" version of the function for smaller data sizes, which only has a simple one instruction for loop. * OpenSSL supports in place encryption when certain conditions are met - which is true for our zeroblocks function. The zero block function no longer uses an additional local array, and the filling of the input data is also simplified. These changes together results in the following encryption overheads: * json testcase: 140% -> 120% * jsonb testcase: 230% -> 175% Closes percona#89
codeforall
reviewed
Feb 28, 2024
| uint64 aes_block_no = start_offset % AES_BLOCK_SIZE; | ||
| char ivp_debug[33]; | ||
| iv_prefix_debug(iv_prefix, ivp_debug); | ||
| ereport(LOG, |
There was a problem hiding this comment.
Do we need to log this?
There was a problem hiding this comment.
It's inside an ENCRYPTION_DEBUG macro
codeforall
approved these changes
Feb 29, 2024
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.
This commit tries to improve the performance of our encryption, based on the results reported in #89.
It contains two main changes which results in improvents:
These changes together results in the following encryption overheads:
Closes #89