Pre-compiled regexp optimization #7110
Merged
Conversation
This file contains hidden or 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
baum
force-pushed
the
precompiled_regexp
branch
2 times, most recently
from
28526d1 to
e01b7f0
Compare
|
@baum can you also write what is the op size in the benchmarks you made above? and what is the backing store/namespace you used. thanks |
|
@guymguym the test is performed on RGW backing store, see https://bugzilla.redhat.com/show_bug.cgi?id=2106742 COSBench workstage definition <workstage name="randread" closuredelay="0" config="">
<auth type="none"/>
<storage type="s3" config="accesskey=XXXXX;secretkey=YYYYY;endpoint=http://s3-openshift-storage.apps.bm.example.com;path_style_access=true"/>
<work name="randread" type="normal" workers="76"
interval="5" division="object" runtime="900" rampup="0"
rampdown="0" afr="200000" totalOps="0" totalBytes="0" config="">
<auth type="none"/>
<operation type="read" ratio="100" division="object"
config="cprefix=tccmx7n2nq6gmrgz5x92;containers=u(1,100);objects=u(1,1000);hashCheck=true" id="op1"/>
</work>
</workstage> |
|
@baum, good change. LGTM |
dannyzaken
approved these changes
Nov 29, 2022
baum
force-pushed
the
precompiled_regexp
branch
2 times, most recently
from
fadefdb to
3171ee4
Compare
Baseline COSBENCH Op-Type Op-Count Byte-Count Avg-ResTime Avg-ProcTime Throughput Bandwidth Succ-Ratio op1: read 294.63 kops 2.95 GB 232.11 ms 232.11 ms 327.42 op/s 3.27 MB/S 100% PR COSBENCH Op-Type Op-Count Byte-Count Avg-ResTime Avg-ProcTime Throughput Bandwidth Succ-Ratio op1: read 339.79 kops 3.4 GB 201.28 ms 201.28 ms 377.58 op/s 3.78 MB/S 100% Signed-off-by: Alexander Indenbaum <[email protected]>
baum
force-pushed
the
precompiled_regexp
branch
from
3171ee4 to
c3393dc
Compare
|
@baum that read stage doesn't say the size - I think this is a result of the previous stages where it create objects by some size distribution. But if I divide the byte-count by the ops-count and get an average of 10 KB - sounds about right? |
2 tasks
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.
Pre-compiled regexp optimization
Improve performance by precompiling regular expressions that are used repeatedly.
COSBench
https://bugzilla.redhat.com/show_bug.cgi?id=2106742
Signed-off-by: Alexander Indenbaum [email protected]