[GitHub] [incubator-pagespeed-mod] Ungov77 commented on issue #2089: High TTFB with PageSpeed
Ungov77 commented on issue #2089: URL: https://github.com/apache/incubator-pagespeed-mod/issues/2089#issuecomment-1098556400 Hi, Makes sense. I didn't understand how it was faster with Memcached failing lol I don't think the rewrite deadline is being overwritten. I have not modified any conf file, the entire config is in Plesk GUI except for ModPagespeedCreateSharedMemoryMetadataCache I have looked at the histograms but I'm not sure how to interpret the data  You can check the admin section, I put it public temporarily again https://www.keinegotterkeinemeister.de/pagespeed_admin/ -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: dev-unsubscr...@pagespeed.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org
[GitHub] [incubator-pagespeed-mod] jmarantz commented on issue #2089: High TTFB with PageSpeed
jmarantz commented on issue #2089: URL: https://github.com/apache/incubator-pagespeed-mod/issues/2089#issuecomment-1098084824 It's possible the reason that TTFB was good for a while is that the memcached code is good at failing-fast if it looks like memcached is not working. I can think of three reasons generally that PageSpeed would make TTFB noticeably worse: * HTML parsing overhead: Running with ?PageSpeedFilters=+debug shows us that parsing overhead is less than 6ms so I don't think it's that. * Rewrite Deadlines: in the config you pasted above it looks like that's set to 20ms which should be fine. But it might be worth looking at the config again to see if anything deadline-related is overridden * General overhead and queuing on your server. PageSpeed keeps a limited number of threads for each process, with work queues for each thread, and at some scale the queue-depths might start growing. There are histograms for that on /pagespeed_admin. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: dev-unsubscr...@pagespeed.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org
