Hello Marc, To summarise, I tried to save a memcpy() but it inevitably backfires with more costly user/kernel interactions. Thanks for clarifying that.
I overlooked that pthread_yield() is a technique from single-core CPU days. My mentioning of spinlocks was based the same oversight. Again, thanks for pointing that out. I fear I cannot continue to use one thread per TLS session; this works fine for the short-lived connections of HTTP and SMTP, but the thread stack requirements are likely to become a bottleneck for IMAP, XMPP or other long-lived, low-traffic connections. Thanks, -Rick _______________________________________________ libev mailing list libev@lists.schmorp.de http://lists.schmorp.de/cgi-bin/mailman/listinfo/libev
