Re: Squid 2.4-DEVEL-ntlm performing MUCH worse than 2.3-STABLE?

You might want to try again. There was some critical bugs in 2.3.STABLE3
which only recenlty made it into the 2.4.DEVEL releases.

/Henrik

Chemolli Francesco (USI) wrote:
>
> While deploying squid-2.4-DEVEL-ntlm, I noticed that it seemed to perform
> MUCH worse
> than 2.3-STABLE1 (I'm talking about a factor of 50 - roughly the same HTTP
> load
> costs with 2.4 50 times the CPU it does with 2.3)
> It appears to be true, however I have NO clue as to why it happens.
> In particular, it _seems_ (I might be misinterpreting the profiling output)
> to be spending inordinate amounts of CPU time in comm_poll:
>
> Flat profile:
> % cumulative self self total
> time seconds seconds calls us/call us/call name
> 61.87 5.81 5.81 1131303 5.14 7.06 comm_poll
> 7.67 6.53 0.72 8426632 0.09 0.16 commDeferRead
> 3.51 6.86 0.33 1131303 0.29 0.29 storeDirCallback
> 3.41 7.18 0.32 4285511 0.07 0.07 clientReadDefer
> 2.02 7.37 0.19 1131303 0.17 0.17 eventNextTime
> 1.38 7.50 0.13 1131303 0.11 0.82 eventRun
> 1.28 7.62 0.12 main
> ...
>
> Call graph:
> index % time self children called name
> ...
> 5.81 2.18 1131303/1131303 main [1]
> [2] 85.1 5.81 2.18 1131303 comm_poll [2]
> 0.72 0.61 8421295/8426632 commDeferRead [3]
> 0.33 0.00 1131303/1131303 storeDirCallback [7]
> 0.08 0.10 1131302/1256566 statHistCount [12]
> 0.00 0.10 780/780 commHandleWrite [22]
> 0.00 0.10 513/513 httpReadReply [23]
> 0.01 0.06 108594/108594 comm_poll_dns_incoming [30]
> 0.00 0.04 295/1994 clientReadRequest <cycle 1>
> [41]
> 0.01 0.00 66647/66647 comm_poll_icp_incoming
> [102]
> 0.00 0.01 75/1994 commConnectHandle <cycle 1>
> [156]
> 0.01 0.00 1114/1819 ignoreErrno [111]
> 0.00 0.00 5337/5337 comm_poll_http_incoming
> [155]
> 0.00 0.00 11/11 pconnRead [182]
> 0.00 0.00 93/93 checkTimeouts [198]
> 0.00 0.00 28/28 snmpHandleUdp [233]
> 0.00 0.00 2/2 helperHandleRead [263]
> 0.00 0.00 2026/2026 fdIsIcp [534]
> 0.00 0.00 2026/2026 fdIsDns [533]
> 0.00 0.00 1749/1749 fdIsHttp [540]
> ...
>
> However, a quick comparision on that function didn't show up any significant
> change since 2.3STABLE.
>
> Any idea on what's going on?
> Thanks in advance.
>
> Francesco Chemolli
Received on Mon Jul 31 2000 - 17:14:30 MDT