forked from luck/tmp_suning_uos_patched
753ee72896
This is the core of the (much simplified) early reclaim. The goal of this patch is to reclaim some easily-freed pages from a zone before falling back onto another zone. One of the major uses of this is NUMA machines. With the default allocator behavior the allocator would look for memory in another zone, which might be off-node, before trying to reclaim from the current zone. This adds a zone tuneable to enable early zone reclaim. It is selected on a per-zone basis and is turned on/off via syscall. Adding some extra throttling on the reclaim was also required (patch 4/4). Without the machine would grind to a crawl when doing a "make -j" kernel build. Even with this patch the System Time is higher on average, but it seems tolerable. Here are some numbers for kernbench runs on a 2-node, 4cpu, 8Gig RAM Altix in the "make -j" run: wall user sys %cpu ctx sw. sleeps ---- ---- --- ---- ------ ------ No patch 1009 1384 847 258 298170 504402 w/patch, no reclaim 880 1376 667 288 254064 396745 w/patch & reclaim 1079 1385 926 252 291625 548873 These numbers are the average of 2 runs of 3 "make -j" runs done right after system boot. Run-to-run variability for "make -j" is huge, so these numbers aren't terribly useful except to seee that with reclaim the benchmark still finishes in a reasonable amount of time. I also looked at the NUMA hit/miss stats for the "make -j" runs and the reclaim doesn't make any difference when the machine is thrashing away. Doing a "make -j8" on a single node that is filled with page cache pages takes 700 seconds with reclaim turned on and 735 seconds without reclaim (due to remote memory accesses). The simple zone_reclaim syscall program is at http://www.bork.org/~mort/sgi/zone_reclaim.c Signed-off-by: Martin Hicks <mort@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
89 lines
2.3 KiB
C
89 lines
2.3 KiB
C
|
|
#include <linux/linkage.h>
|
|
#include <linux/errno.h>
|
|
|
|
#include <asm/unistd.h>
|
|
|
|
/*
|
|
* Non-implemented system calls get redirected here.
|
|
*/
|
|
asmlinkage long sys_ni_syscall(void)
|
|
{
|
|
return -ENOSYS;
|
|
}
|
|
|
|
cond_syscall(sys_nfsservctl);
|
|
cond_syscall(sys_quotactl);
|
|
cond_syscall(sys_acct);
|
|
cond_syscall(sys_lookup_dcookie);
|
|
cond_syscall(sys_swapon);
|
|
cond_syscall(sys_swapoff);
|
|
cond_syscall(sys_init_module);
|
|
cond_syscall(sys_delete_module);
|
|
cond_syscall(sys_socketpair);
|
|
cond_syscall(sys_bind);
|
|
cond_syscall(sys_listen);
|
|
cond_syscall(sys_accept);
|
|
cond_syscall(sys_connect);
|
|
cond_syscall(sys_getsockname);
|
|
cond_syscall(sys_getpeername);
|
|
cond_syscall(sys_sendto);
|
|
cond_syscall(sys_send);
|
|
cond_syscall(sys_recvfrom);
|
|
cond_syscall(sys_recv);
|
|
cond_syscall(sys_socket);
|
|
cond_syscall(sys_setsockopt);
|
|
cond_syscall(sys_getsockopt);
|
|
cond_syscall(sys_shutdown);
|
|
cond_syscall(sys_sendmsg);
|
|
cond_syscall(sys_recvmsg);
|
|
cond_syscall(sys_socketcall);
|
|
cond_syscall(sys_futex);
|
|
cond_syscall(compat_sys_futex);
|
|
cond_syscall(sys_epoll_create);
|
|
cond_syscall(sys_epoll_ctl);
|
|
cond_syscall(sys_epoll_wait);
|
|
cond_syscall(sys_semget);
|
|
cond_syscall(sys_semop);
|
|
cond_syscall(sys_semtimedop);
|
|
cond_syscall(sys_semctl);
|
|
cond_syscall(sys_msgget);
|
|
cond_syscall(sys_msgsnd);
|
|
cond_syscall(sys_msgrcv);
|
|
cond_syscall(sys_msgctl);
|
|
cond_syscall(sys_shmget);
|
|
cond_syscall(sys_shmat);
|
|
cond_syscall(sys_shmdt);
|
|
cond_syscall(sys_shmctl);
|
|
cond_syscall(sys_mq_open);
|
|
cond_syscall(sys_mq_unlink);
|
|
cond_syscall(sys_mq_timedsend);
|
|
cond_syscall(sys_mq_timedreceive);
|
|
cond_syscall(sys_mq_notify);
|
|
cond_syscall(sys_mq_getsetattr);
|
|
cond_syscall(compat_sys_mq_open);
|
|
cond_syscall(compat_sys_mq_timedsend);
|
|
cond_syscall(compat_sys_mq_timedreceive);
|
|
cond_syscall(compat_sys_mq_notify);
|
|
cond_syscall(compat_sys_mq_getsetattr);
|
|
cond_syscall(sys_mbind);
|
|
cond_syscall(sys_get_mempolicy);
|
|
cond_syscall(sys_set_mempolicy);
|
|
cond_syscall(compat_sys_mbind);
|
|
cond_syscall(compat_sys_get_mempolicy);
|
|
cond_syscall(compat_sys_set_mempolicy);
|
|
cond_syscall(sys_add_key);
|
|
cond_syscall(sys_request_key);
|
|
cond_syscall(sys_keyctl);
|
|
cond_syscall(compat_sys_keyctl);
|
|
cond_syscall(compat_sys_socketcall);
|
|
cond_syscall(sys_set_zone_reclaim);
|
|
|
|
/* arch-specific weak syscall entries */
|
|
cond_syscall(sys_pciconfig_read);
|
|
cond_syscall(sys_pciconfig_write);
|
|
cond_syscall(sys_pciconfig_iobase);
|
|
cond_syscall(sys32_ipc);
|
|
cond_syscall(sys32_sysctl);
|
|
cond_syscall(ppc_rtas);
|