Closed Notation closed 1 year ago
Thanks for the report. I'm just in the middle of looking at this now.
txSenderCacher
seems suspect.
ia@ianuc:~/Downloads$ go tool pprof profile\(2\)
File: geth Build ID: 2a4f22ee8855c29f44a2a89684537cf6e595fa37
Type: cpu
Time: Feb 6, 2023 at 11:07am (PST)
Duration: 5.18s, Total samples = 57.12s (1102.14%) Entering interactive mode (type "help" for commands, "o" for options)
(pprof) top
Showing nodes accounting for 57.04s, 99.86% of 57.12s total Dropped 34 nodes (cum <= 0.29s)
flat flat% sum% cum cum%
21.40s 37.46% 37.46% 57.05s 99.88% github.com/ethereum/go-ethereum/core.(*txSenderCacher).cache
15.99s 27.99% 65.46% 21.36s 37.39% runtime.chanrecv
14.28s 25.00% 90.46% 35.64s 62.39% runtime.selectnbrecv
5.37s 9.40% 99.86% 5.37s 9.40% runtime.empty (inline)
Hello, after upgrading from v1.12.8 to v1.12.9, the cpu usage of core-geth continues to be high. How can I solve this problem? HDD io is OK
System information
Expected behaviour
less cpu usage
Actual behaviour
v1.12.8
v1.12.9
Steps to reproduce the behaviour
upgrade from v1.12.8 to v1.12.9
Backtrace