b4cf88a04f
- cotributed by Bjorn Swift - In this first phase, scheduling is moved from the kernel to the PM server. The next steps are to a) moving scheduling to its own server and b) include useful information in the "out of quantum" message, so that the scheduler can make use of this information. - The kernel process table now keeps record of who is responsible for scheduling each process (p_scheduler). When this pointer is NULL, the process will be scheduled by the kernel. If such a process runs out of quantum, the kernel will simply renew its quantum an requeue it. - When PM loads, it will take over scheduling of all running processes, except system processes, using sys_schedctl(). Essentially, this only results in taking over init. As children inherit a scheduler from their parent, user space programs forked by init will inherit PM (for now) as their scheduler. - Once a process has been assigned a scheduler, and runs out of quantum, its RTS_NO_QUANTUM flag will be set and the process dequeued. The kernel will send a message to the scheduler, on the process' behalf, informing the scheduler that it has run out of quantum. The scheduler can take what ever action it pleases, based on its policy, and then reschedule the process using the sys_schedule() system call. - Balance queues does not work as before. While the old in-kernel function used to renew the quantum of processes in the highest priority run queue, the user-space implementation only acts on processes that have been bumped down to a lower priority queue. This approach reacts slower to changes than the old one, but saves us sending a sys_schedule message for each process every time we balance the queues. Currently, when processes are moved up a priority queue, their quantum is also renewed, but this can be fiddled with. - do_nice has been removed from kernel. PM answers to get- and setpriority calls, updates it's own nice variable as well as the max_run_queue. This will be refactored once scheduling is moved to a separate server. We will probably have PM update it's local nice value and then send a message to whoever is scheduling the process. - changes to fix an issue in do_fork() where processes could run out of quantum but bypassing the code path that handles it correctly. The future plan is to remove the policy from do_fork() and implement it in userspace too.
88 lines
4 KiB
C
88 lines
4 KiB
C
/* This table has one slot per process. It contains all the process management
|
|
* information for each process. Among other things, it defines the text, data
|
|
* and stack segments, uids and gids, and various flags. The kernel and file
|
|
* systems have tables that are also indexed by process, with the contents
|
|
* of corresponding slots referring to the same process in all three.
|
|
*/
|
|
#include <limits.h>
|
|
#include <timers.h>
|
|
#include <signal.h>
|
|
|
|
/* Needs to be included here, for 'ps' etc */
|
|
#include "const.h"
|
|
|
|
EXTERN struct mproc {
|
|
char mp_exitstatus; /* storage for status when process exits */
|
|
char mp_sigstatus; /* storage for signal # for killed procs */
|
|
pid_t mp_pid; /* process id */
|
|
endpoint_t mp_endpoint; /* kernel endpoint id */
|
|
pid_t mp_procgrp; /* pid of process group (used for signals) */
|
|
pid_t mp_wpid; /* pid this process is waiting for */
|
|
int mp_parent; /* index of parent process */
|
|
int mp_tracer; /* index of tracer process, or NO_TRACER */
|
|
|
|
/* Child user and system times. Accounting done on child exit. */
|
|
clock_t mp_child_utime; /* cumulative user time of children */
|
|
clock_t mp_child_stime; /* cumulative sys time of children */
|
|
|
|
/* Real and effective uids and gids. */
|
|
uid_t mp_realuid; /* process' real uid */
|
|
uid_t mp_effuid; /* process' effective uid */
|
|
gid_t mp_realgid; /* process' real gid */
|
|
gid_t mp_effgid; /* process' effective gid */
|
|
|
|
/* Supplemental groups. */
|
|
int mp_ngroups; /* number of supplemental groups */
|
|
gid_t mp_sgroups[NGROUPS_MAX];/* process' supplemental groups */
|
|
|
|
/* Signal handling information. */
|
|
sigset_t mp_ignore; /* 1 means ignore the signal, 0 means don't */
|
|
sigset_t mp_catch; /* 1 means catch the signal, 0 means don't */
|
|
sigset_t mp_sigmask; /* signals to be blocked */
|
|
sigset_t mp_sigmask2; /* saved copy of mp_sigmask */
|
|
sigset_t mp_sigpending; /* pending signals to be handled */
|
|
sigset_t mp_sigtrace; /* signals to hand to tracer first */
|
|
struct sigaction mp_sigact[_NSIG]; /* as in sigaction(2) */
|
|
vir_bytes mp_sigreturn; /* address of C library __sigreturn function */
|
|
struct timer mp_timer; /* watchdog timer for alarm(2), setitimer(2) */
|
|
clock_t mp_interval[NR_ITIMERS]; /* setitimer(2) repetition intervals */
|
|
|
|
unsigned mp_flags; /* flag bits */
|
|
unsigned mp_trace_flags; /* trace options */
|
|
vir_bytes mp_procargs; /* ptr to proc's initial stack arguments */
|
|
message mp_reply; /* reply message to be sent to one */
|
|
|
|
/* Scheduling priority. */
|
|
signed int mp_nice; /* nice is PRIO_MIN..PRIO_MAX, standard 0. */
|
|
|
|
/* User space scheduling */
|
|
int mp_max_priority; /* this process' highest allowed priority */
|
|
int mp_priority; /* the process' current priority */
|
|
int mp_time_slice; /* this process's scheduling queue */
|
|
|
|
char mp_name[PROC_NAME_LEN]; /* process name */
|
|
} mproc[NR_PROCS];
|
|
|
|
/* Flag values */
|
|
#define IN_USE 0x00001 /* set when 'mproc' slot in use */
|
|
#define WAITING 0x00002 /* set by WAIT system call */
|
|
#define ZOMBIE 0x00004 /* waiting for parent to issue WAIT call */
|
|
#define PAUSED 0x00008 /* set by PAUSE system call */
|
|
#define ALARM_ON 0x00010 /* set when SIGALRM timer started */
|
|
#define EXITING 0x00020 /* set by EXIT, process is now exiting */
|
|
#define TOLD_PARENT 0x00040 /* parent wait() completed, ZOMBIE off */
|
|
#define STOPPED 0x00080 /* set if process stopped for tracing */
|
|
#define SIGSUSPENDED 0x00100 /* set by SIGSUSPEND system call */
|
|
#define REPLY 0x00200 /* set if a reply message is pending */
|
|
#define FS_CALL 0x00400 /* set if waiting for FS (normal calls) */
|
|
#define PM_SIG_PENDING 0x00800 /* process got a signal while waiting for FS */
|
|
#define UNPAUSED 0x01000 /* process is not in a blocking call */
|
|
#define PRIV_PROC 0x02000 /* system process, special privileges */
|
|
#define PARTIAL_EXEC 0x04000 /* process got a new map but no content */
|
|
#define TRACE_EXIT 0x08000 /* tracer is forcing this process to exit */
|
|
#define TRACE_ZOMBIE 0x10000 /* waiting for tracer to issue WAIT call */
|
|
#define DELAY_CALL 0x20000 /* waiting for call before sending signal */
|
|
|
|
#define NIL_MPROC ((struct mproc *) 0)
|
|
|