Re: measuring lwlock-related latency spikes
| От | Simon Riggs |
|---|---|
| Тема | Re: measuring lwlock-related latency spikes |
| Дата | |
| Msg-id | CA+U5nMLjfzfy4fWmD_EPP4hAnGbbBKN+wqDxrUngeJsFJkPTng@mail.gmail.com обсуждение исходный текст |
| Ответ на | Re: measuring lwlock-related latency spikes (Greg Stark <stark@mit.edu>) |
| Ответы |
Re: measuring lwlock-related latency spikes
|
| Список | pgsql-hackers |
On Mon, Apr 2, 2012 at 11:49 AM, Greg Stark <stark@mit.edu> wrote: > On Mon, Apr 2, 2012 at 8:15 AM, Simon Riggs <simon@2ndquadrant.com> wrote: >> Not true, please refer to code at line 544, as I already indicated. >> >> My understanding of the instrumentation is that the lock acquired at >> line 526 will show as the blocker until we reach line 555, so anything >> in between could be responsible for the wait. > > Hm, but then wouldn't the lock acquisition at line 544 be showing up as well? Some time ago on this thread, I wrote: "Anyway, just to note that it might not be I/O and we need to find out." Do you consider this proof that it can only be I/O? Or do we still need to find out? -- Simon Riggs http://www.2ndQuadrant.com/ PostgreSQL Development, 24x7 Support, Training & Services
В списке pgsql-hackers по дате отправления: