9d03c3f56c
Memory unmapping causes slow address space fragmentation, leading in extreme cases to failing to allocate pages at all. Removing this problem by keeping all the pages allocated to us, yet calling madvise() to let kernel dispose of them. This adds a little complexity and overhead as we have to keep the pointers to the free pages, therefore to hold e.g. 1 GB of 4K pages with 8B pointers, we have to store 2 MB of data. |
||
---|---|---|
.. | ||
bsd.h | ||
linux.h | ||
README |
Available configuration variables: ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ CONFIG_AUTO_ROUTES Device routes are added automagically by the kernel CONFIG_SELF_CONSCIOUS We're able to recognize whether route was installed by us CONFIG_MULTIPLE_TABLES The kernel supports multiple routing tables CONFIG_SINGLE_ROUTE There is only one route per network CONFIG_MC_PROPER_SRC Multicast packets have source address according to socket saddr field CONFIG_SKIP_MC_BIND Don't call bind on multicast socket (def for *BSD) CONFIG_NO_IFACE_BIND Bind to iface is not available, use workarounds (def for *BSD) CONFIG_UNIX_DONTROUTE Use setsockopts DONTROUTE (undef for *BSD) CONFIG_DONTROUTE_UNICAST Use MSG_DONTROUTE flag for unicast packets (def for FreeBSD) CONFIG_USE_HDRINCL Use IP_HDRINCL instead of control messages for source address on raw IP sockets. CONFIG_RESTRICTED_PRIVILEGES Implements restricted privileges using drop_uid()