… | |
… | |
2368 | As you can see, the AnyEvent + EV combination even beats the |
2368 | As you can see, the AnyEvent + EV combination even beats the |
2369 | hand-optimised "raw sockets benchmark", while AnyEvent + its pure perl |
2369 | hand-optimised "raw sockets benchmark", while AnyEvent + its pure perl |
2370 | backend easily beats IO::Lambda and POE. |
2370 | backend easily beats IO::Lambda and POE. |
2371 | |
2371 | |
2372 | And even the 100% non-blocking version written using the high-level (and |
2372 | And even the 100% non-blocking version written using the high-level (and |
2373 | slow :) L<AnyEvent::Handle> abstraction beats both POE and IO::Lambda by a |
2373 | slow :) L<AnyEvent::Handle> abstraction beats both POE and IO::Lambda |
2374 | large margin, even though it does all of DNS, tcp-connect and socket I/O |
2374 | higher level ("unoptimised") abstractions by a large margin, even though |
2375 | in a non-blocking way. |
2375 | it does all of DNS, tcp-connect and socket I/O in a non-blocking way. |
2376 | |
2376 | |
2377 | The two AnyEvent benchmarks programs can be found as F<eg/ae0.pl> and |
2377 | The two AnyEvent benchmarks programs can be found as F<eg/ae0.pl> and |
2378 | F<eg/ae2.pl> in the AnyEvent distribution, the remaining benchmarks are |
2378 | F<eg/ae2.pl> in the AnyEvent distribution, the remaining benchmarks are |
2379 | part of the IO::lambda distribution and were used without any changes. |
2379 | part of the IO::Lambda distribution and were used without any changes. |
2380 | |
2380 | |
2381 | |
2381 | |
2382 | =head1 SIGNALS |
2382 | =head1 SIGNALS |
2383 | |
2383 | |
2384 | AnyEvent currently installs handlers for these signals: |
2384 | AnyEvent currently installs handlers for these signals: |