The patch titled
per-task-delay-accounting: sync block I/O and swapin delay collection
has been added to the -mm tree. Its filename is
per-task-delay-accounting-sync-block-i-o-and-swapin-delay-collection.patch
See http://www.zip.com.au/~akpm/linux/patches/stuff/added-to-mm.txt to find
out what to do about this
From: Balbir Singh <balbir@xxxxxxxxxx>
Unlike earlier iterations of the delay accounting patches, now delays are only
collected for the actual I/O waits rather than try and cover the delays seen
in I/O submission paths.
Account separately for block I/O delays incurred as a result of swapin page
faults whose frequency can be affected by the task/process' rss limit. Hence
swapin delays can act as feedback for rss limit changes independent of I/O
priority changes.
Signed-off-by: Shailabh Nagar <nagar@xxxxxxxxxxxxxx>
Signed-off-by: Balbir Singh <balbir@xxxxxxxxxx>
Cc: Jes Sorensen <jes@xxxxxxx>
Cc: Peter Chubb <peterc@xxxxxxxxxxxxxxxxxx>
Cc: Erich Focht <efocht@xxxxxxxxxx>
Cc: Levent Serinol <lserinol@xxxxxxxxx>
Cc: Jay Lan <jlan@xxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxx>
---
include/linux/delayacct.h | 25 +++++++++++++++++++++++++
include/linux/sched.h | 6 ++++++
kernel/delayacct.c | 19 +++++++++++++++++++
kernel/sched.c | 5 +++++
mm/memory.c | 4 ++++
5 files changed, 59 insertions(+)
diff -puN include/linux/delayacct.h~per-task-delay-accounting-sync-block-i-o-and-swapin-delay-collection include/linux/delayacct.h
--- 25/include/linux/delayacct.h~per-task-delay-accounting-sync-block-i-o-and-swapin-delay-collection Mon May 8 14:33:34 2006
+++ 25-akpm/include/linux/delayacct.h Mon May 8 14:33:34 2006
@@ -19,6 +19,13 @@
#include <linux/sched.h>
+/*
+ * Per-task flags relevant to delay accounting
+ * maintained privately to avoid exhausting similar flags in sched.h:PF_*
+ * Used to set current->delays->flags
+ */
+#define DELAYACCT_PF_SWAPIN 0x00000001 /* I am doing a swapin */
+
#ifdef CONFIG_TASK_DELAY_ACCT
extern int delayacct_on; /* Delay accounting turned on/off */
@@ -26,6 +33,8 @@ extern kmem_cache_t *delayacct_cache;
extern void delayacct_init(void);
extern void __delayacct_tsk_init(struct task_struct *);
extern void __delayacct_tsk_exit(struct task_struct *);
+extern void __delayacct_blkio_start(void);
+extern void __delayacct_blkio_end(void);
static inline void delayacct_set_flag(int flag)
{
@@ -53,6 +62,18 @@ static inline void delayacct_tsk_exit(st
__delayacct_tsk_exit(tsk);
}
+static inline void delayacct_blkio_start(void)
+{
+ if (current->delays)
+ __delayacct_blkio_start();
+}
+
+static inline void delayacct_blkio_end(void)
+{
+ if (current->delays)
+ __delayacct_blkio_end();
+}
+
#else
static inline void delayacct_set_flag(int flag)
{}
@@ -64,6 +85,10 @@ static inline void delayacct_tsk_init(st
{}
static inline void delayacct_tsk_exit(struct task_struct *tsk)
{}
+static inline void delayacct_blkio_start(void)
+{}
+static inline void delayacct_blkio_end(void)
+{}
#endif /* CONFIG_TASK_DELAY_ACCT */
#endif
diff -puN include/linux/sched.h~per-task-delay-accounting-sync-block-i-o-and-swapin-delay-collection include/linux/sched.h
--- 25/include/linux/sched.h~per-task-delay-accounting-sync-block-i-o-and-swapin-delay-collection Mon May 8 14:33:34 2006
+++ 25-akpm/include/linux/sched.h Mon May 8 14:33:34 2006
@@ -550,6 +550,12 @@ struct task_delay_info {
* Atomicity of updates to XXX_delay, XXX_count protected by
* single lock above (split into XXX_lock if contention is an issue).
*/
+
+ struct timespec blkio_start, blkio_end; /* Shared by blkio, swapin */
+ u64 blkio_delay; /* wait for sync block io completion */
+ u64 swapin_delay; /* wait for swapin block io completion */
+ u32 blkio_count;
+ u32 swapin_count;
};
#endif
diff -puN kernel/delayacct.c~per-task-delay-accounting-sync-block-i-o-and-swapin-delay-collection kernel/delayacct.c
--- 25/kernel/delayacct.c~per-task-delay-accounting-sync-block-i-o-and-swapin-delay-collection Mon May 8 14:33:34 2006
+++ 25-akpm/kernel/delayacct.c Mon May 8 14:33:34 2006
@@ -85,3 +85,22 @@ static inline void delayacct_end(struct
spin_unlock(¤t->delays->lock);
}
+void __delayacct_blkio_start(void)
+{
+ delayacct_start(¤t->delays->blkio_start);
+}
+
+void __delayacct_blkio_end(void)
+{
+ if (current->delays->flags & DELAYACCT_PF_SWAPIN)
+ /* Swapin block I/O */
+ delayacct_end(¤t->delays->blkio_start,
+ ¤t->delays->blkio_end,
+ ¤t->delays->swapin_delay,
+ ¤t->delays->swapin_count);
+ else /* Other block I/O */
+ delayacct_end(¤t->delays->blkio_start,
+ ¤t->delays->blkio_end,
+ ¤t->delays->blkio_delay,
+ ¤t->delays->blkio_count);
+}
diff -puN kernel/sched.c~per-task-delay-accounting-sync-block-i-o-and-swapin-delay-collection kernel/sched.c
--- 25/kernel/sched.c~per-task-delay-accounting-sync-block-i-o-and-swapin-delay-collection Mon May 8 14:33:34 2006
+++ 25-akpm/kernel/sched.c Mon May 8 14:33:34 2006
@@ -50,6 +50,7 @@
#include <linux/times.h>
#include <linux/acct.h>
#include <linux/kprobes.h>
+#include <linux/delayacct.h>
#include <asm/tlb.h>
#include <asm/unistd.h>
@@ -4173,9 +4174,11 @@ void __sched io_schedule(void)
{
struct runqueue *rq = &per_cpu(runqueues, raw_smp_processor_id());
+ delayacct_blkio_start();
atomic_inc(&rq->nr_iowait);
schedule();
atomic_dec(&rq->nr_iowait);
+ delayacct_blkio_end();
}
EXPORT_SYMBOL(io_schedule);
@@ -4185,9 +4188,11 @@ long __sched io_schedule_timeout(long ti
struct runqueue *rq = &per_cpu(runqueues, raw_smp_processor_id());
long ret;
+ delayacct_blkio_start();
atomic_inc(&rq->nr_iowait);
ret = schedule_timeout(timeout);
atomic_dec(&rq->nr_iowait);
+ delayacct_blkio_end();
return ret;
}
diff -puN mm/memory.c~per-task-delay-accounting-sync-block-i-o-and-swapin-delay-collection mm/memory.c
--- 25/mm/memory.c~per-task-delay-accounting-sync-block-i-o-and-swapin-delay-collection Mon May 8 14:33:34 2006
+++ 25-akpm/mm/memory.c Mon May 8 14:33:34 2006
@@ -48,6 +48,7 @@
#include <linux/rmap.h>
#include <linux/module.h>
#include <linux/init.h>
+#include <linux/delayacct.h>
#include <asm/pgalloc.h>
#include <asm/uaccess.h>
@@ -1898,6 +1899,7 @@ static int do_swap_page(struct mm_struct
migration_entry_wait(mm, pmd, address);
goto out;
}
+ delayacct_set_flag(DELAYACCT_PF_SWAPIN);
page = lookup_swap_cache(entry);
if (!page) {
swapin_readahead(entry, address, vma);
@@ -1910,6 +1912,7 @@ static int do_swap_page(struct mm_struct
page_table = pte_offset_map_lock(mm, pmd, address, &ptl);
if (likely(pte_same(*page_table, orig_pte)))
ret = VM_FAULT_OOM;
+ delayacct_clear_flag(DELAYACCT_PF_SWAPIN);
goto unlock;
}
@@ -1919,6 +1922,7 @@ static int do_swap_page(struct mm_struct
grab_swap_token();
}
+ delayacct_clear_flag(DELAYACCT_PF_SWAPIN);
mark_page_accessed(page);
lock_page(page);
_
Patches currently in -mm which might be from balbir@xxxxxxxxxx are
fix-dcache-race-during-umount.patch
fix-dcache-race-during-umount-fix.patch
prune_one_dentry-tweaks.patch
per-task-delay-accounting-setup.patch
per-task-delay-accounting-sync-block-i-o-and-swapin-delay-collection.patch
per-task-delay-accounting-cpu-delay-collection-via-schedstats.patch
per-task-delay-accounting-utilities-for-genetlink-usage.patch
per-task-delay-accounting-taskstats-interface.patch
per-task-delay-accounting-delay-accounting-usage-of-taskstats-interface.patch
per-task-delay-accounting-documentation.patch
per-task-delay-accounting-proc-export-of-aggregated-block-i-o-delays.patch
-
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
