Message183486
| Author |
neologix |
| Recipients |
neologix, pitrou, sbt |
| Date |
2013年03月04日.19:24:12 |
| SpamBayes Score |
-1.0 |
| Marked as misclassified |
Yes |
| Message-id |
<CAH_1eM3svV1ZUzTS0xBeL=NL02YWwwFOmuXe+_XA7KoktraEKQ@mail.gmail.com> |
| In-reply-to |
<CAH_1eM1ppRR4CztNANjEuexjmw4SyB2ba+n9gPRKBjF9Lp2ztw@mail.gmail.com> |
| Content |
So, what do you think?
Is the simple version offloading the serialization to queue enough, or
should we go for a full-blown atomic Connection/Pipe/etc?
I find the performance gain quite appreciable (basically queue didn't
scale at all, now it scales with the number of cores). |
|
History
|
|---|
| Date |
User |
Action |
Args |
| 2013年03月04日 19:24:13 | neologix | set | recipients:
+ neologix, pitrou, sbt |
| 2013年03月04日 19:24:13 | neologix | link | issue17025 messages |
| 2013年03月04日 19:24:12 | neologix | create |
|