Re: Re: Re: mod_fcgid concurrency bottleneck, issue#53693

2012-09-04 Thread pqf
ULL) = 0 4622 13:17:16.746765 epoll_ctl(11, EPOLL_CTL_ADD, 12, {EPOLLIN, {u32=158210764, u64=158210764}} 4622 13:17:16.746833 <... epoll_ctl resumed> ) = 0 4622 13:17:16.747587 gettimeofday( 4622 13:17:16.747904 <... gettimeofday resumed> {1346217436, 747649}, NULL) = 0 4622 13:17:1

Re: Re: Re: Re: mod_fcgid concurrency bottleneck, issue#53693

2012-08-28 Thread Lazy
ef look, it seems not necessary. I will move it out of loop and > test. > > 2012-08-28 > > pqf > > 发件人:Lazy > 发送时间:2012-08-27 21:47 > 主题:Re: Re: Re: mod_fcgid concurrency bottleneck, issue#53693 > 收件人:"

回复: Re: Re: Re: mod_fcgid concurrency bottleneck, issue#53693

2012-08-27 Thread pqf
:Lazy 发送时间:2012-08-27 21:47 主题:Re: Re: Re: mod_fcgid concurrency bottleneck, issue#53693 收件人:"dev" 抄送: 2012/8/16 pqf : > How about this: > 1. procmgr_post_spawn_cmd() now return a status code from PM, so process > handler now know the spawn request is denyed or not. > 2. i

Re: Re: Re: mod_fcgid concurrency bottleneck, issue#53693

2012-08-27 Thread Lazy
sary to call procmgr_init_spawn_cmd() from inside the for loop ? > > 2012-08-16 > > pqf > ____________ > 发件人:Lazy > 发送时间:2012-08-16 16:47 > 主题:Re: Re: mod_fcgid concurrency bottleneck, issue#53693 > 收件人:"

回复: Re: Re: mod_fcgid concurrency bottleneck, issue#53693

2012-08-16 Thread pqf
: Re: mod_fcgid concurrency bottleneck, issue#53693 收件人:"dev" 抄送: 2012/8/16 pqf : > Hi, Michal > My solution do "add availability to each class", which is the > procmgr_post_spawn_cmd() call in each loop do. > The sleep() call is intrudused for a stress test witho

Re: Re: mod_fcgid concurrency bottleneck, issue#53693

2012-08-16 Thread Lazy
2012/8/16 pqf : > Hi, Michal > My solution do "add availability to each class", which is the > procmgr_post_spawn_cmd() call in each loop do. > The sleep() call is intrudused for a stress test without warm up time, in > this case, mod_fcgid will create more processes than a slow start one(each > pr

Re: Re: mod_fcgid concurrency bottleneck, issue#53693

2012-08-16 Thread pqf
procmgr_post_spawn_cmd(maybe it should be renamed to procmgr_send_spawn_cmd) will keep blocking while PM is creating a new process, after procmgr_post_spawn_cmd() return, there should be a process ready there waiting for accept. 2012-08-16 pqf 发件人:William A. Rowe Jr. 发送时间:2012-08-16 15:23

Re: Re: mod_fcgid concurrency bottleneck, issue#53693

2012-08-15 Thread pqf
Hi, Michal My solution do "add availability to each class", which is the procmgr_post_spawn_cmd() call in each loop do. The sleep() call is intrudused for a stress test without warm up time, in this case, mod_fcgid will create more processes than a slow start one(each process handler can't apply