In this second phase, scheduling is moved from PM to its own scheduler (see r6557 for phase one). In the next phase we hope to a) include useful information in the "out of quantum" message and b) create some simple scheduling policy that makes use of that information. When the system starts up, PM will iterate over its process table and ask SCHED to take over scheduling unprivileged processes. This is done by sending a SCHEDULING_START message to SCHED. This message includes the processes endpoint, the parent's endpoint and its nice level. The scheduler adds this process to its schedproc table, issues a schedctl, and returns its own endpoint to PM - as the endpoint of the effective scheduler. When a process terminates, a SCHEDULING_STOP message is sent to the scheduler. The reason for this effective endpoint is for future compatibility. Some day, we may have a scheduler that, instead of scheduling the process itself, forwards the SCHEDULING_START message on to another scheduler. PM has information on who schedules whom. As such, scheduling messages from user-land are sent through PM. An example is when processes change their priority, using nice(). In that case, a getsetpriority message is sent to PM, which then sends a SCHEDULING_SET_NICE to the process's effective scheduler. When a process is forked through PM, it inherits its parent's scheduler, but is spawned with an empty quantum. As before, a request to fork a process flows through VM before returning to PM, which then wakes up the child process. This flow has been modified slightly so that PM notifies the scheduler of the new process, before waking up the child process. If the scheduler fails to take over scheduling, the child process is torn down and the fork fails with an erroneous value. Process priority is entirely decided upon using nice levels. PM stores a copy of each process's nice level and when a child is forked, its parent's nice level is sent in the SCHEDULING_START message. How this level is mapped to a priority queue is up to the scheduler. It should be noted that the nice level is used to determine the max_priority and the parent could have been in a lower priority when it was spawned. To prevent a CPU intensive process from hawking the CPU by continuously forking children that get scheduled in the max_priority, the scheduler should determine in which queue the parent is currently scheduled, and schedule the child in that same queue. Other fixes: The USER_Q in kernel/proc.h was incorrectly defined as NR_SCHED_QUEUES/2. That results in a "off by one" error when converting priority->nice->priority for nice=0. This also had the side effect that if someone were to set the MAX_USER_Q to something else than 0, then USER_Q would be off.
85 lines
3.9 KiB
C
85 lines
3.9 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 */
|
|
endpoint_t mp_scheduler; /* scheduler endpoint id */
|
|
|
|
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 PM_SCHEDULED 0x40000 /* this process is scheduled by PM */
|
|
|
|
|