Poor performance for trace calls #4028
Labels
A-rpc
Related to the RPC implementation
C-enhancement
New feature or request
C-perf
A change motivated by improving speed, memory usage or disk footprint
S-stale
This issue/PR is stale and will close with no further activity
Describe the feature
Im using debug_traceCall through IPC very extensively (executing a lot of simulations in parallel with arbitrary bytecode). I think it's around 100-1000 sims per block and up to 20-60 simultaneous requests. Previously I was running this same code on geth IPC and was getting decent times - like 200-400ms for 80 requests (it's 4 times * 20 simultaneous requests).
With reth my average time for these same requests are 400-800ms. Sometimes it becomes 2s+, while in geth I was getting everything under 1 second. I'm using
--rpc-max-tracing-requests 1000
.Is there anything I can tweak?
Additional context
No response
The text was updated successfully, but these errors were encountered: