Guy Arbitman
Guy Arbitman
/remove
rebased on top of main, without changing anything
@Yumasi please add detailed explanation in the PR description (or better, in a doc) about the new algorithm with references for the TLS RFCs or wire-protocol
> This change was tested in system-probe-test-environments using the tcp-load-test. Initial results showed: > > Average CPU usage up ~27% > Max CPU usage up ~42% That seems like a...
p.s., you didn't set `qa/done` tag nor described qa steps in the description
@amarziali why is the PR based on the java spring parsing? I think you should base the logic on top of main and make it to the mainline
please set the milestone `7.53` and add `qa/done` label (since you have UTs)
@amarziali since we're still reviewing the PR, please try to avoid rebase as Github does not allow to show the differences between reviews cycles
We had the notion to bump the kernel limitation of http2 to 5.4 instead of 5.2 In 5.3 bounded loops introduced we means we could remove unroll from the code