Skip to contentSkip to conversation

csa patch for 2.6.8

PATCH New Jay Lan 1 participant 1 message Aug 18, 2004

Subsystems (9)
Memory management VFS Block layer MM core +5 more subsystems
lore
Share & tools
lore

Jay Lan

author
#0 lore raw

PATCH 1/1 csa patch for 2.6.8

Attached is the Comprehensive System Accounting (CSA) patch to kernel 2.6.8.

This patch applies cleanly after PAGG and JOB patch to 2.6.8. There was no code changes since the 2.6.7 patch.

The project page of CSA is located at http://oss.sgi.com/projects/csa/

Any comment, suggestion, bug post/fix are very much welcome!

Signed-off-by Jay Lan <[email protected]>

---
Jay Lan - Linux System Software
Silicon Graphics Inc., Mountain View, CA

drivers/block/ll_rw_blk.c +4 -0
Index: linux/drivers/block/ll_rw_blk.c
===================================================================
@@ -1674,6 +1674,7 @@
 {
 	DEFINE_WAIT(wait);
 	struct request *rq;
+	unsigned long start_wait = jiffies;
 
 	generic_unplug_device(q);
 	do {

@@ -1702,6 +1703,7 @@
 		finish_wait(&rl->wait[rw], &wait);
 	} while (!rq);
 
+	current->bwtime += (unsigned long) jiffies - start_wait;
 	return rq;
 }
 

@@ -1948,10 +1950,12 @@
 
 	if (rw == READ) {
 		disk_stat_add(rq->rq_disk, read_sectors, nr_sectors);
+		current->rblk += nr_sectors;
 		if (!new_io)
 			disk_stat_inc(rq->rq_disk, read_merges);
 	} else if (rw == WRITE) {
 		disk_stat_add(rq->rq_disk, write_sectors, nr_sectors);
+		current->wblk += nr_sectors;
 		if (!new_io)
 			disk_stat_inc(rq->rq_disk, write_merges);
 	}
fs/exec.c +4 -0
Index: linux/fs/exec.c
===================================================================
@@ -47,6 +47,7 @@
 #include <linux/syscalls.h>
 #include <linux/rmap.h>
 #include <linux/pagg.h>
+#include <linux/csa_internal.h>
 
 #include <asm/uaccess.h>
 #include <asm/mmu_context.h>

@@ -1145,6 +1146,9 @@
 
 		/* execve success */
 		security_bprm_free(&bprm);
+		/* no-op if CONFIG_CSA not set */
+		csa_update_integrals();
+		update_mem_hiwater();
 		return retval;
 	}
fs/read_write.c +23 -2
Index: linux/fs/read_write.c
===================================================================
@@ -216,8 +216,11 @@
 				ret = file->f_op->read(file, buf, count, pos);
 			else
 				ret = do_sync_read(file, buf, count, pos);
-			if (ret > 0)
+			if (ret > 0) {
 				dnotify_parent(file->f_dentry, DN_ACCESS);
+				current->rchar += ret;
+			}
+			current->syscr++;
 		}
 	}
 

@@ -260,8 +263,11 @@
 				ret = file->f_op->write(file, buf, count, pos);
 			else
 				ret = do_sync_write(file, buf, count, pos);
-			if (ret > 0)
+			if (ret > 0) {
 				dnotify_parent(file->f_dentry, DN_MODIFY);
+				current->wchar += ret;
+			}
+			current->syscw++;
 		}
 	}
 

@@ -540,6 +546,10 @@
 		fput_light(file, fput_needed);
 	}
 
+	if (ret > 0) {
+		current->rchar += ret;
+	}
+	current->syscr++;
 	return ret;
 }
 

@@ -558,6 +568,10 @@
 		fput_light(file, fput_needed);
 	}
 
+	if (ret > 0) {
+		current->wchar += ret;
+	}
+	current->syscw++;
 	return ret;
 }
 

@@ -636,6 +650,13 @@
 
 	retval = in_file->f_op->sendfile(in_file, ppos, count, file_send_actor, out_file);
 
+	if (retval > 0) {
+		current->rchar += retval;
+		current->wchar += retval;
+	}
+	current->syscr++;
+	current->syscw++;
+
 	if (*ppos > max)
 		retval = -EOVERFLOW;
include/linux/csa.h new file +526 -0

526 lines not on this page · raw message

include/linux/csa_internal.h new file +85 -0

85 lines not on this page · raw message

include/linux/sched.h +23 -1
Index: linux/include/linux/sched.h
===================================================================
@@ -229,6 +229,8 @@
 	struct kioctx		*ioctx_list;
 
 	struct kioctx		default_kioctx;
+
+	unsigned long hiwater_rss, hiwater_vm;
 };
 
 extern int mmlist_nr;

@@ -455,6 +457,7 @@
 	unsigned long it_real_value, it_prof_value, it_virt_value;
 	unsigned long it_real_incr, it_prof_incr, it_virt_incr;
 	struct timer_list real_timer;
+	struct list_head posix_timers; /* POSIX.1b Interval Timers */
 	unsigned long utime, stime, cutime, cstime;
 	unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw; /* context switch counts */
 	u64 start_time;

@@ -473,6 +476,7 @@
 	char comm[16];
 /* file system info */
 	int link_count, total_link_count;
+	struct tty_struct *tty; /* NULL if no tty */
 /* ipc stuff */
 	struct sysv_sem sysvsem;
 /* CPU-specific state of this task */

@@ -533,7 +537,12 @@
 	struct list_head pagg_list;
 	struct rw_semaphore pagg_sem;
 #endif
-
+/* i/o counters(bytes read/written, blocks read/written, #syscalls, waittime */
+	unsigned long rchar, wchar, rblk, wblk, syscr, syscw, bwtime;
+#if defined(CONFIG_CSA) || defined(CONFIG_CSA_MODULE)       
+	unsigned long csa_rss_mem1, csa_vm_mem1;              
+	clock_t csa_stimexpd;                                 
+#endif                                                      
 };
 
 static inline pid_t process_group(struct task_struct *tsk)

@@ -870,6 +879,19 @@
 /* Remove the current tasks stale references to the old mm_struct */
 extern void mm_release(struct task_struct *, struct mm_struct *);
 
+/* Update highwater values */
+static inline void update_mem_hiwater(void)
+{
+	if (current->mm) {
+		if (current->mm->hiwater_rss < current->mm->rss) {
+			current->mm->hiwater_rss = current->mm->rss;
+		}
+		if (current->mm->hiwater_vm < current->mm->total_vm) {
+			current->mm->hiwater_vm = current->mm->total_vm;
+		}
+	}
+}
+
 extern int  copy_thread(int, unsigned long, unsigned long, unsigned long, struct task_struct *, struct pt_regs *);
 extern void flush_thread(void);
 extern void exit_thread(void);
init/Kconfig +25 -0
Index: linux/init/Kconfig
===================================================================
@@ -158,6 +158,31 @@
 	  a module, select this entry using M.  If you do not want support
 	  for jobs, select N.
 
+config CSA
+	tristate "  CSA Job Accounting"
+	depends on PAGG_JOB
+	help
+	  Comprehensive System Accounting (CSA) provides job level
+	  accounting of resource usage.  The accounting records are
+	  written by the kernel into a file.  CSA user level scripts
+	  and commands process the binary accounting records and
+	  combine them by job identifier within system boot uptime
+	  periods.  These accounting records are then used to produce
+	  reports and charge fees to users.
+
+	  Say Y here if you want job level accounting to be compiled
+	  into the kernel.  Say M here if you want the writing of
+	  accounting records portion of this feature to be a loadable
+	  module.  Say N here if you do not want job level accounting
+	  (the default).
+	
+	  The CSA commands and scripts package needs to be installed
+	  to process the CSA accounting records.  See
+	  http://oss.sgi.com/projects/csa for further information
+	  about CSA and download instructions for the CSA commands
+	  package and documentation.
+
+
 config SYSCTL
 	bool "Sysctl support"
 	---help---
kernel/Makefile +1 -0
Index: linux/kernel/Makefile
===================================================================
@@ -20,6 +20,7 @@
 obj-$(CONFIG_COMPAT) += compat.o
 obj-$(CONFIG_PAGG) += pagg.o
 obj-$(CONFIG_PAGG_JOB) += job.o
+obj-$(CONFIG_CSA) += csa.o
 obj-$(CONFIG_IKCONFIG) += configs.o
 obj-$(CONFIG_IKCONFIG_PROC) += configs.o
 obj-$(CONFIG_STOP_MACHINE) += stop_machine.o
kernel/csa.c new file +1664 -0

1,664 lines not on this page · raw message

kernel/exit.c +8 -0
Index: linux/kernel/exit.c
===================================================================
@@ -23,6 +23,7 @@
 #include <linux/mount.h>
 #include <linux/proc_fs.h>
 #include <linux/mempolicy.h>
+#include <linux/csa_internal.h>
 
 #include <asm/uaccess.h>
 #include <asm/unistd.h>

@@ -31,6 +32,8 @@
 
 extern void sem_exit (void);
 extern struct task_struct *child_reaper;
+void (*do_csa_acct) (int, struct task_struct *) = NULL;
+EXPORT_SYMBOL(do_csa_acct);
 
 int getrusage(struct task_struct *, int, struct rusage __user *);
 

@@ -820,7 +823,12 @@
 		ptrace_notify((PTRACE_EVENT_EXIT << 8) | SIGTRAP);
 	}
 
+	/* no-op if CONFIG_CSA not set */
+	csa_update_integrals();
+	update_mem_hiwater();
 	acct_process(code);
+	/* no-op if CONFIG_CSA not set */
+	csa_acct(code, tsk);
 	__exit_mm(tsk);
 
 	exit_sem(tsk);
kernel/fork.c +8 -1
Index: linux/kernel/fork.c
===================================================================
@@ -37,7 +37,7 @@
 #include <linux/audit.h>
 #include <linux/rmap.h>
 #include <linux/pagg.h>
-
+#include <linux/csa_internal.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
 #include <asm/uaccess.h>

@@ -578,6 +578,9 @@
 	if (retval)
 		goto free_pt;
 
+	mm->hiwater_rss = mm->rss;
+	mm->hiwater_vm = mm->total_vm;	
+
 good_mm:
 	tsk->mm = mm;
 	tsk->active_mm = mm;

@@ -966,6 +969,10 @@
 
 	p->utime = p->stime = 0;
 	p->cutime = p->cstime = 0;
+	p->rchar = p->wchar = p->rblk = p->wblk = p->syscr = p->syscw = 0;
+	p->bwtime = 0;
+	/* no-op if CONFIG_CSA not set */
+	csa_clear_integrals(p);
 	p->lock_depth = -1;		/* -1 = no lock */
 	p->start_time = get_jiffies_64();
 	p->security = NULL;
mm/memory.c +19 -2
Index: linux/mm/memory.c
===================================================================
@@ -44,6 +44,7 @@
 #include <linux/highmem.h>
 #include <linux/pagemap.h>
 #include <linux/rmap.h>
+#include <linux/csa_internal.h>
 #include <linux/module.h>
 #include <linux/init.h>
 

@@ -605,6 +606,8 @@
 	tlb = tlb_gather_mmu(mm, 0);
 	unmap_vmas(&tlb, mm, vma, address, end, &nr_accounted, details);
 	tlb_finish_mmu(tlb, address, end);
+	/* no-op unless CONFIG_CSA is set */
+        csa_update_integrals();
 	spin_unlock(&mm->page_table_lock);
 }
 

@@ -1095,9 +1098,12 @@
 	spin_lock(&mm->page_table_lock);
 	page_table = pte_offset_map(pmd, address);
 	if (likely(pte_same(*page_table, pte))) {
-		if (PageReserved(old_page))
+		if (PageReserved(old_page)) {
 			++mm->rss;
-		else
+			/* no-op if CONFIG_CSA not set */
+			csa_update_integrals();
+			update_mem_hiwater();
+		} else
 			page_remove_rmap(old_page);
 		break_cow(vma, new_page, address, page_table);
 		lru_cache_add_active(new_page);

@@ -1378,6 +1384,10 @@
 		remove_exclusive_swap_page(page);
 
 	mm->rss++;
+	/* no-op if CONFIG_CSA not set */
+	csa_update_integrals();
+	update_mem_hiwater();
+  
 	pte = mk_pte(page, vma->vm_page_prot);
 	if (write_access && can_share_swap_page(page)) {
 		pte = maybe_mkwrite(pte_mkdirty(pte), vma);

@@ -1443,6 +1453,9 @@
 			goto out;
 		}
 		mm->rss++;
+		/* no-op if CONFIG_CSA not set */
+		csa_update_integrals();
+		update_mem_hiwater();
 		entry = maybe_mkwrite(pte_mkdirty(mk_pte(page,
 							 vma->vm_page_prot)),
 				      vma);

@@ -1552,6 +1565,10 @@
 	if (pte_none(*page_table)) {
 		if (!PageReserved(new_page))
 			++mm->rss;
+		/* no-op if CONFIG_CSA not set */
+		csa_update_integrals();
+		update_mem_hiwater();
+
 		flush_icache_page(vma, new_page);
 		entry = mk_pte(new_page, vma->vm_page_prot);
 		if (write_access)
mm/mmap.c +10 -0
Index: linux/mm/mmap.c
===================================================================
@@ -20,6 +20,7 @@
 #include <linux/hugetlb.h>
 #include <linux/profile.h>
 #include <linux/module.h>
+#include <linux/csa_internal.h>
 #include <linux/mount.h>
 #include <linux/mempolicy.h>
 #include <linux/rmap.h>

@@ -988,6 +989,9 @@
 					pgoff, flags & MAP_NONBLOCK);
 		down_write(&mm->mmap_sem);
 	}
+	/* no-op if CONFIG_CSA not set */
+	csa_update_integrals();
+	update_mem_hiwater();
 	return addr;
 
 unmap_and_free_vma:

@@ -1227,6 +1231,9 @@
 	vma->vm_mm->total_vm += grow;
 	if (vma->vm_flags & VM_LOCKED)
 		vma->vm_mm->locked_vm += grow;
+	/* no-op if CONFIG_CSA_JOB_ACCT not set */
+	csa_update_integrals();
+	update_mem_hiwater();
 	anon_vma_unlock(vma);
 	return 0;
 }

@@ -1688,6 +1695,9 @@
 		mm->locked_vm += len >> PAGE_SHIFT;
 		make_pages_present(addr, addr + len);
 	}
+	/* no-op if CONFIG_CSA not set */
+	csa_update_integrals();
+	update_mem_hiwater();
 	return addr;
 }
mm/mremap.c +8 -0
Index: linux/mm/mremap.c
===================================================================
@@ -16,6 +16,7 @@
 #include <linux/fs.h>
 #include <linux/highmem.h>
 #include <linux/security.h>
+#include <linux/csa_internal.h>
 
 #include <asm/uaccess.h>
 #include <asm/cacheflush.h>

@@ -231,6 +232,10 @@
 					   new_addr + new_len);
 	}
 
+	/* no-op if CONFIG_CSA not set */
+	csa_update_integrals();
+	update_mem_hiwater();
+
 	return new_addr;
 }
 

@@ -363,6 +368,9 @@
 				make_pages_present(addr + old_len,
 						   addr + new_len);
 			}
+			/* no-op if CONFIG_CSA not set */
+			csa_update_integrals();
+			update_mem_hiwater();
 			ret = addr;
 			goto out;
 		}
mm/rmap.c +5 -0
Index: linux/mm/rmap.c
===================================================================
@@ -29,6 +29,7 @@
 #include <linux/swapops.h>
 #include <linux/slab.h>
 #include <linux/init.h>
+#include <linux/csa_internal.h>
 #include <linux/rmap.h>
 
 #include <asm/tlbflush.h>

@@ -515,6 +516,8 @@
 	mm->rss--;
 	BUG_ON(!page->mapcount);
 	page->mapcount--;
+	/* no-op if CONFIG_CSA not set */
+	csa_update_integrals();
 	page_cache_release(page);
 
 out_unmap:

@@ -614,6 +617,8 @@
 
 		page_remove_rmap(page);
 		page_cache_release(page);
+		/* no-op if CONFIG_CSA not set */
+		csa_update_integrals();
 		mm->rss--;
 		(*mapcount)--;
 	}
mm/swapfile.c +4 -0
Index: linux/mm/swapfile.c
===================================================================
@@ -24,6 +24,7 @@
 #include <linux/module.h>
 #include <linux/rmap.h>
 #include <linux/security.h>
+#include <linux/csa_internal.h>
 #include <linux/backing-dev.h>
 
 #include <asm/pgtable.h>

@@ -435,6 +436,9 @@
 	set_pte(dir, pte_mkold(mk_pte(page, vma->vm_page_prot)));
 	page_add_anon_rmap(page, vma, address);
 	swap_free(entry);
+	/* no-op if CONFIG_CSA not set */
+	csa_update_integrals();
+	update_mem_hiwater();
 }
 
 /* vma->vm_mm->page_table_lock is held */