alistair23-linux/include/linux/genhd.h

570 lines
17 KiB
C
Raw Normal View History

#ifndef _LINUX_GENHD_H
#define _LINUX_GENHD_H
/*
* genhd.h Copyright (C) 1992 Drew Eckhardt
* Generic hard disk header file by
* Drew Eckhardt
*
* <drew@colorado.edu>
*/
#include <linux/types.h>
#include <linux/kdev_t.h>
#include <linux/rcupdate.h>
[PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-09-30 12:45:40 -06:00
#ifdef CONFIG_BLOCK
#define kobj_to_dev(k) container_of((k), struct device, kobj)
#define dev_to_disk(device) container_of((device), struct gendisk, part0.__dev)
#define dev_to_part(device) container_of((device), struct hd_struct, __dev)
#define disk_to_dev(disk) (&(disk)->part0.__dev)
#define part_to_dev(part) (&((part)->__dev))
extern struct device_type part_type;
extern struct kobject *block_depr;
extern struct class block_class;
enum {
/* These three have identical behaviour; use the second one if DOS FDISK gets
confused about extended/logical partitions starting past cylinder 1023. */
DOS_EXTENDED_PARTITION = 5,
LINUX_EXTENDED_PARTITION = 0x85,
WIN98_EXTENDED_PARTITION = 0x0f,
SUN_WHOLE_DISK = DOS_EXTENDED_PARTITION,
LINUX_SWAP_PARTITION = 0x82,
LINUX_DATA_PARTITION = 0x83,
LINUX_LVM_PARTITION = 0x8e,
LINUX_RAID_PARTITION = 0xfd, /* autodetect RAID partition */
SOLARIS_X86_PARTITION = LINUX_SWAP_PARTITION,
NEW_SOLARIS_X86_PARTITION = 0xbf,
DM6_AUX1PARTITION = 0x51, /* no DDO: use xlated geom */
DM6_AUX3PARTITION = 0x53, /* no DDO: use xlated geom */
DM6_PARTITION = 0x54, /* has DDO: use xlated geom & offset */
EZD_PARTITION = 0x55, /* EZ-DRIVE */
FREEBSD_PARTITION = 0xa5, /* FreeBSD Partition ID */
OPENBSD_PARTITION = 0xa6, /* OpenBSD Partition ID */
NETBSD_PARTITION = 0xa9, /* NetBSD Partition ID */
BSDI_PARTITION = 0xb7, /* BSDI Partition ID */
MINIX_PARTITION = 0x81, /* Minix Partition ID */
UNIXWARE_PARTITION = 0x63, /* Same as GNU_HURD and SCO Unix */
};
#define DISK_MAX_PARTS 256
#define DISK_NAME_LEN 32
#include <linux/major.h>
#include <linux/device.h>
#include <linux/smp.h>
#include <linux/string.h>
#include <linux/fs.h>
#include <linux/workqueue.h>
struct partition {
unsigned char boot_ind; /* 0x80 - active */
unsigned char head; /* starting head */
unsigned char sector; /* starting sector */
unsigned char cyl; /* starting cylinder */
unsigned char sys_ind; /* What partition type */
unsigned char end_head; /* end head */
unsigned char end_sector; /* end sector */
unsigned char end_cyl; /* end cylinder */
__le32 start_sect; /* starting sector counting from 0 */
__le32 nr_sects; /* nr of sectors in partition */
} __attribute__((packed));
struct disk_stats {
unsigned long sectors[2]; /* READs and WRITEs */
unsigned long ios[2];
unsigned long merges[2];
unsigned long ticks[2];
unsigned long io_ticks;
unsigned long time_in_queue;
};
struct hd_struct {
sector_t start_sect;
sector_t nr_sects;
sector_t alignment_offset;
struct device __dev;
struct kobject *holder_dir;
int policy, partno;
#ifdef CONFIG_FAIL_MAKE_REQUEST
int make_it_fail;
#endif
unsigned long stamp;
Revert "Seperate read and write statistics of in_flight requests" This reverts commit a9327cac440be4d8333bba975cbbf76045096275. Corrado Zoccolo <czoccolo@gmail.com> reports: "with 2.6.32-rc1 I started getting the following strange output from "iostat -kx 2": Linux 2.6.31bisect (et2) 04/10/2009 _i686_ (2 CPU) avg-cpu: %user %nice %system %iowait %steal %idle 10,70 0,00 3,16 15,75 0,00 70,38 Device: rrqm/s wrqm/s r/s w/s rkB/s wkB/s avgrq-sz avgqu-sz await svctm %util sda 18,22 0,00 0,67 0,01 14,77 0,02 43,94 0,01 10,53 39043915,03 2629219,87 sdb 60,89 9,68 50,79 3,04 1724,43 50,52 65,95 0,70 13,06 488437,47 2629219,87 avg-cpu: %user %nice %system %iowait %steal %idle 2,72 0,00 0,74 0,00 0,00 96,53 Device: rrqm/s wrqm/s r/s w/s rkB/s wkB/s avgrq-sz avgqu-sz await svctm %util sda 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 100,00 sdb 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 100,00 avg-cpu: %user %nice %system %iowait %steal %idle 6,68 0,00 0,99 0,00 0,00 92,33 Device: rrqm/s wrqm/s r/s w/s rkB/s wkB/s avgrq-sz avgqu-sz await svctm %util sda 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 100,00 sdb 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 100,00 avg-cpu: %user %nice %system %iowait %steal %idle 4,40 0,00 0,73 1,47 0,00 93,40 Device: rrqm/s wrqm/s r/s w/s rkB/s wkB/s avgrq-sz avgqu-sz await svctm %util sda 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 100,00 sdb 0,00 4,00 0,00 3,00 0,00 28,00 18,67 0,06 19,50 333,33 100,00 Global values for service time and utilization are garbage. For interval values, utilization is always 100%, and service time is higher than normal. I bisected it down to: [a9327cac440be4d8333bba975cbbf76045096275] Seperate read and write statistics of in_flight requests and verified that reverting just that commit indeed solves the issue on 2.6.32-rc1." So until this is debugged, revert the bad commit. Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-10-04 13:04:38 -06:00
int in_flight;
#ifdef CONFIG_SMP
struct disk_stats *dkstats;
#else
struct disk_stats dkstats;
#endif
struct rcu_head rcu_head;
};
#define GENHD_FL_REMOVABLE 1
#define GENHD_FL_DRIVERFS 2
#define GENHD_FL_MEDIA_CHANGE_NOTIFY 4
#define GENHD_FL_CD 8
#define GENHD_FL_UP 16
#define GENHD_FL_SUPPRESS_PARTITION_INFO 32
#define GENHD_FL_EXT_DEVT 64 /* allow extended devt */
#define GENHD_FL_NATIVE_CAPACITY 128
#define BLK_SCSI_MAX_CMDS (256)
#define BLK_SCSI_CMD_PER_LONG (BLK_SCSI_MAX_CMDS / (sizeof(long) * 8))
struct blk_scsi_cmd_filter {
unsigned long read_ok[BLK_SCSI_CMD_PER_LONG];
unsigned long write_ok[BLK_SCSI_CMD_PER_LONG];
struct kobject kobj;
};
struct disk_part_tbl {
struct rcu_head rcu_head;
int len;
struct hd_struct *last_lookup;
struct hd_struct *part[];
};
struct gendisk {
/* major, first_minor and minors are input parameters only,
* don't use directly. Use disk_devt() and disk_max_parts().
*/
int major; /* major number of driver */
int first_minor;
int minors; /* maximum number of minors, =1 for
* disks that can't be partitioned. */
char disk_name[DISK_NAME_LEN]; /* name of major driver */
char *(*devnode)(struct gendisk *gd, mode_t *mode);
/* Array of pointers to partitions indexed by partno.
* Protected with matching bdev lock but stat and other
* non-critical accesses use RCU. Always access through
* helpers.
*/
struct disk_part_tbl *part_tbl;
struct hd_struct part0;
const struct block_device_operations *fops;
struct request_queue *queue;
void *private_data;
int flags;
struct device *driverfs_dev; // FIXME: remove
struct kobject *slave_dir;
struct timer_rand_state *random;
atomic_t sync_io; /* RAID */
struct work_struct async_notify;
#ifdef CONFIG_BLK_DEV_INTEGRITY
struct blk_integrity *integrity;
#endif
int node_id;
};
static inline struct gendisk *part_to_disk(struct hd_struct *part)
{
if (likely(part)) {
if (part->partno)
return dev_to_disk(part_to_dev(part)->parent);
else
return dev_to_disk(part_to_dev(part));
}
return NULL;
}
static inline int disk_max_parts(struct gendisk *disk)
{
if (disk->flags & GENHD_FL_EXT_DEVT)
return DISK_MAX_PARTS;
return disk->minors;
}
static inline bool disk_partitionable(struct gendisk *disk)
{
return disk_max_parts(disk) > 1;
}
static inline dev_t disk_devt(struct gendisk *disk)
{
return disk_to_dev(disk)->devt;
}
static inline dev_t part_devt(struct hd_struct *part)
{
return part_to_dev(part)->devt;
}
extern struct hd_struct *disk_get_part(struct gendisk *disk, int partno);
static inline void disk_put_part(struct hd_struct *part)
{
if (likely(part))
put_device(part_to_dev(part));
}
/*
* Smarter partition iterator without context limits.
*/
#define DISK_PITER_REVERSE (1 << 0) /* iterate in the reverse direction */
#define DISK_PITER_INCL_EMPTY (1 << 1) /* include 0-sized parts */
#define DISK_PITER_INCL_PART0 (1 << 2) /* include partition 0 */
#define DISK_PITER_INCL_EMPTY_PART0 (1 << 3) /* include empty partition 0 */
struct disk_part_iter {
struct gendisk *disk;
struct hd_struct *part;
int idx;
unsigned int flags;
};
extern void disk_part_iter_init(struct disk_part_iter *piter,
struct gendisk *disk, unsigned int flags);
extern struct hd_struct *disk_part_iter_next(struct disk_part_iter *piter);
extern void disk_part_iter_exit(struct disk_part_iter *piter);
extern struct hd_struct *disk_map_sector_rcu(struct gendisk *disk,
sector_t sector);
/*
* Macros to operate on percpu disk statistics:
*
* {disk|part|all}_stat_{add|sub|inc|dec}() modify the stat counters
* and should be called between disk_stat_lock() and
* disk_stat_unlock().
*
* part_stat_read() can be called at any time.
*
* part_stat_{add|set_all}() and {init|free}_part_stats are for
* internal use only.
*/
#ifdef CONFIG_SMP
#define part_stat_lock() ({ rcu_read_lock(); get_cpu(); })
#define part_stat_unlock() do { put_cpu(); rcu_read_unlock(); } while (0)
#define __part_stat_add(cpu, part, field, addnd) \
(per_cpu_ptr((part)->dkstats, (cpu))->field += (addnd))
#define part_stat_read(part, field) \
({ \
typeof((part)->dkstats->field) res = 0; \
int i; \
for_each_possible_cpu(i) \
res += per_cpu_ptr((part)->dkstats, i)->field; \
res; \
})
static inline void part_stat_set_all(struct hd_struct *part, int value)
{
int i;
for_each_possible_cpu(i)
memset(per_cpu_ptr(part->dkstats, i), value,
sizeof(struct disk_stats));
}
static inline int init_part_stats(struct hd_struct *part)
{
part->dkstats = alloc_percpu(struct disk_stats);
if (!part->dkstats)
return 0;
return 1;
}
static inline void free_part_stats(struct hd_struct *part)
{
free_percpu(part->dkstats);
}
#else /* !CONFIG_SMP */
#define part_stat_lock() ({ rcu_read_lock(); 0; })
#define part_stat_unlock() rcu_read_unlock()
#define __part_stat_add(cpu, part, field, addnd) \
((part)->dkstats.field += addnd)
#define part_stat_read(part, field) ((part)->dkstats.field)
static inline void part_stat_set_all(struct hd_struct *part, int value)
{
memset(&part->dkstats, value, sizeof(struct disk_stats));
}
static inline int init_part_stats(struct hd_struct *part)
{
return 1;
}
static inline void free_part_stats(struct hd_struct *part)
{
}
#endif /* CONFIG_SMP */
#define part_stat_add(cpu, part, field, addnd) do { \
__part_stat_add((cpu), (part), field, addnd); \
if ((part)->partno) \
__part_stat_add((cpu), &part_to_disk((part))->part0, \
field, addnd); \
} while (0)
#define part_stat_dec(cpu, gendiskp, field) \
part_stat_add(cpu, gendiskp, field, -1)
#define part_stat_inc(cpu, gendiskp, field) \
part_stat_add(cpu, gendiskp, field, 1)
#define part_stat_sub(cpu, gendiskp, field, subnd) \
part_stat_add(cpu, gendiskp, field, -subnd)
Revert "Seperate read and write statistics of in_flight requests" This reverts commit a9327cac440be4d8333bba975cbbf76045096275. Corrado Zoccolo <czoccolo@gmail.com> reports: "with 2.6.32-rc1 I started getting the following strange output from "iostat -kx 2": Linux 2.6.31bisect (et2) 04/10/2009 _i686_ (2 CPU) avg-cpu: %user %nice %system %iowait %steal %idle 10,70 0,00 3,16 15,75 0,00 70,38 Device: rrqm/s wrqm/s r/s w/s rkB/s wkB/s avgrq-sz avgqu-sz await svctm %util sda 18,22 0,00 0,67 0,01 14,77 0,02 43,94 0,01 10,53 39043915,03 2629219,87 sdb 60,89 9,68 50,79 3,04 1724,43 50,52 65,95 0,70 13,06 488437,47 2629219,87 avg-cpu: %user %nice %system %iowait %steal %idle 2,72 0,00 0,74 0,00 0,00 96,53 Device: rrqm/s wrqm/s r/s w/s rkB/s wkB/s avgrq-sz avgqu-sz await svctm %util sda 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 100,00 sdb 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 100,00 avg-cpu: %user %nice %system %iowait %steal %idle 6,68 0,00 0,99 0,00 0,00 92,33 Device: rrqm/s wrqm/s r/s w/s rkB/s wkB/s avgrq-sz avgqu-sz await svctm %util sda 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 100,00 sdb 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 100,00 avg-cpu: %user %nice %system %iowait %steal %idle 4,40 0,00 0,73 1,47 0,00 93,40 Device: rrqm/s wrqm/s r/s w/s rkB/s wkB/s avgrq-sz avgqu-sz await svctm %util sda 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 100,00 sdb 0,00 4,00 0,00 3,00 0,00 28,00 18,67 0,06 19,50 333,33 100,00 Global values for service time and utilization are garbage. For interval values, utilization is always 100%, and service time is higher than normal. I bisected it down to: [a9327cac440be4d8333bba975cbbf76045096275] Seperate read and write statistics of in_flight requests and verified that reverting just that commit indeed solves the issue on 2.6.32-rc1." So until this is debugged, revert the bad commit. Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-10-04 13:04:38 -06:00
static inline void part_inc_in_flight(struct hd_struct *part)
{
Revert "Seperate read and write statistics of in_flight requests" This reverts commit a9327cac440be4d8333bba975cbbf76045096275. Corrado Zoccolo <czoccolo@gmail.com> reports: "with 2.6.32-rc1 I started getting the following strange output from "iostat -kx 2": Linux 2.6.31bisect (et2) 04/10/2009 _i686_ (2 CPU) avg-cpu: %user %nice %system %iowait %steal %idle 10,70 0,00 3,16 15,75 0,00 70,38 Device: rrqm/s wrqm/s r/s w/s rkB/s wkB/s avgrq-sz avgqu-sz await svctm %util sda 18,22 0,00 0,67 0,01 14,77 0,02 43,94 0,01 10,53 39043915,03 2629219,87 sdb 60,89 9,68 50,79 3,04 1724,43 50,52 65,95 0,70 13,06 488437,47 2629219,87 avg-cpu: %user %nice %system %iowait %steal %idle 2,72 0,00 0,74 0,00 0,00 96,53 Device: rrqm/s wrqm/s r/s w/s rkB/s wkB/s avgrq-sz avgqu-sz await svctm %util sda 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 100,00 sdb 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 100,00 avg-cpu: %user %nice %system %iowait %steal %idle 6,68 0,00 0,99 0,00 0,00 92,33 Device: rrqm/s wrqm/s r/s w/s rkB/s wkB/s avgrq-sz avgqu-sz await svctm %util sda 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 100,00 sdb 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 100,00 avg-cpu: %user %nice %system %iowait %steal %idle 4,40 0,00 0,73 1,47 0,00 93,40 Device: rrqm/s wrqm/s r/s w/s rkB/s wkB/s avgrq-sz avgqu-sz await svctm %util sda 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 100,00 sdb 0,00 4,00 0,00 3,00 0,00 28,00 18,67 0,06 19,50 333,33 100,00 Global values for service time and utilization are garbage. For interval values, utilization is always 100%, and service time is higher than normal. I bisected it down to: [a9327cac440be4d8333bba975cbbf76045096275] Seperate read and write statistics of in_flight requests and verified that reverting just that commit indeed solves the issue on 2.6.32-rc1." So until this is debugged, revert the bad commit. Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-10-04 13:04:38 -06:00
part->in_flight++;
if (part->partno)
Revert "Seperate read and write statistics of in_flight requests" This reverts commit a9327cac440be4d8333bba975cbbf76045096275. Corrado Zoccolo <czoccolo@gmail.com> reports: "with 2.6.32-rc1 I started getting the following strange output from "iostat -kx 2": Linux 2.6.31bisect (et2) 04/10/2009 _i686_ (2 CPU) avg-cpu: %user %nice %system %iowait %steal %idle 10,70 0,00 3,16 15,75 0,00 70,38 Device: rrqm/s wrqm/s r/s w/s rkB/s wkB/s avgrq-sz avgqu-sz await svctm %util sda 18,22 0,00 0,67 0,01 14,77 0,02 43,94 0,01 10,53 39043915,03 2629219,87 sdb 60,89 9,68 50,79 3,04 1724,43 50,52 65,95 0,70 13,06 488437,47 2629219,87 avg-cpu: %user %nice %system %iowait %steal %idle 2,72 0,00 0,74 0,00 0,00 96,53 Device: rrqm/s wrqm/s r/s w/s rkB/s wkB/s avgrq-sz avgqu-sz await svctm %util sda 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 100,00 sdb 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 100,00 avg-cpu: %user %nice %system %iowait %steal %idle 6,68 0,00 0,99 0,00 0,00 92,33 Device: rrqm/s wrqm/s r/s w/s rkB/s wkB/s avgrq-sz avgqu-sz await svctm %util sda 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 100,00 sdb 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 100,00 avg-cpu: %user %nice %system %iowait %steal %idle 4,40 0,00 0,73 1,47 0,00 93,40 Device: rrqm/s wrqm/s r/s w/s rkB/s wkB/s avgrq-sz avgqu-sz await svctm %util sda 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 100,00 sdb 0,00 4,00 0,00 3,00 0,00 28,00 18,67 0,06 19,50 333,33 100,00 Global values for service time and utilization are garbage. For interval values, utilization is always 100%, and service time is higher than normal. I bisected it down to: [a9327cac440be4d8333bba975cbbf76045096275] Seperate read and write statistics of in_flight requests and verified that reverting just that commit indeed solves the issue on 2.6.32-rc1." So until this is debugged, revert the bad commit. Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-10-04 13:04:38 -06:00
part_to_disk(part)->part0.in_flight++;
}
Revert "Seperate read and write statistics of in_flight requests" This reverts commit a9327cac440be4d8333bba975cbbf76045096275. Corrado Zoccolo <czoccolo@gmail.com> reports: "with 2.6.32-rc1 I started getting the following strange output from "iostat -kx 2": Linux 2.6.31bisect (et2) 04/10/2009 _i686_ (2 CPU) avg-cpu: %user %nice %system %iowait %steal %idle 10,70 0,00 3,16 15,75 0,00 70,38 Device: rrqm/s wrqm/s r/s w/s rkB/s wkB/s avgrq-sz avgqu-sz await svctm %util sda 18,22 0,00 0,67 0,01 14,77 0,02 43,94 0,01 10,53 39043915,03 2629219,87 sdb 60,89 9,68 50,79 3,04 1724,43 50,52 65,95 0,70 13,06 488437,47 2629219,87 avg-cpu: %user %nice %system %iowait %steal %idle 2,72 0,00 0,74 0,00 0,00 96,53 Device: rrqm/s wrqm/s r/s w/s rkB/s wkB/s avgrq-sz avgqu-sz await svctm %util sda 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 100,00 sdb 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 100,00 avg-cpu: %user %nice %system %iowait %steal %idle 6,68 0,00 0,99 0,00 0,00 92,33 Device: rrqm/s wrqm/s r/s w/s rkB/s wkB/s avgrq-sz avgqu-sz await svctm %util sda 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 100,00 sdb 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 100,00 avg-cpu: %user %nice %system %iowait %steal %idle 4,40 0,00 0,73 1,47 0,00 93,40 Device: rrqm/s wrqm/s r/s w/s rkB/s wkB/s avgrq-sz avgqu-sz await svctm %util sda 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 100,00 sdb 0,00 4,00 0,00 3,00 0,00 28,00 18,67 0,06 19,50 333,33 100,00 Global values for service time and utilization are garbage. For interval values, utilization is always 100%, and service time is higher than normal. I bisected it down to: [a9327cac440be4d8333bba975cbbf76045096275] Seperate read and write statistics of in_flight requests and verified that reverting just that commit indeed solves the issue on 2.6.32-rc1." So until this is debugged, revert the bad commit. Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-10-04 13:04:38 -06:00
static inline void part_dec_in_flight(struct hd_struct *part)
{
Revert "Seperate read and write statistics of in_flight requests" This reverts commit a9327cac440be4d8333bba975cbbf76045096275. Corrado Zoccolo <czoccolo@gmail.com> reports: "with 2.6.32-rc1 I started getting the following strange output from "iostat -kx 2": Linux 2.6.31bisect (et2) 04/10/2009 _i686_ (2 CPU) avg-cpu: %user %nice %system %iowait %steal %idle 10,70 0,00 3,16 15,75 0,00 70,38 Device: rrqm/s wrqm/s r/s w/s rkB/s wkB/s avgrq-sz avgqu-sz await svctm %util sda 18,22 0,00 0,67 0,01 14,77 0,02 43,94 0,01 10,53 39043915,03 2629219,87 sdb 60,89 9,68 50,79 3,04 1724,43 50,52 65,95 0,70 13,06 488437,47 2629219,87 avg-cpu: %user %nice %system %iowait %steal %idle 2,72 0,00 0,74 0,00 0,00 96,53 Device: rrqm/s wrqm/s r/s w/s rkB/s wkB/s avgrq-sz avgqu-sz await svctm %util sda 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 100,00 sdb 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 100,00 avg-cpu: %user %nice %system %iowait %steal %idle 6,68 0,00 0,99 0,00 0,00 92,33 Device: rrqm/s wrqm/s r/s w/s rkB/s wkB/s avgrq-sz avgqu-sz await svctm %util sda 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 100,00 sdb 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 100,00 avg-cpu: %user %nice %system %iowait %steal %idle 4,40 0,00 0,73 1,47 0,00 93,40 Device: rrqm/s wrqm/s r/s w/s rkB/s wkB/s avgrq-sz avgqu-sz await svctm %util sda 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 100,00 sdb 0,00 4,00 0,00 3,00 0,00 28,00 18,67 0,06 19,50 333,33 100,00 Global values for service time and utilization are garbage. For interval values, utilization is always 100%, and service time is higher than normal. I bisected it down to: [a9327cac440be4d8333bba975cbbf76045096275] Seperate read and write statistics of in_flight requests and verified that reverting just that commit indeed solves the issue on 2.6.32-rc1." So until this is debugged, revert the bad commit. Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-10-04 13:04:38 -06:00
part->in_flight--;
if (part->partno)
Revert "Seperate read and write statistics of in_flight requests" This reverts commit a9327cac440be4d8333bba975cbbf76045096275. Corrado Zoccolo <czoccolo@gmail.com> reports: "with 2.6.32-rc1 I started getting the following strange output from "iostat -kx 2": Linux 2.6.31bisect (et2) 04/10/2009 _i686_ (2 CPU) avg-cpu: %user %nice %system %iowait %steal %idle 10,70 0,00 3,16 15,75 0,00 70,38 Device: rrqm/s wrqm/s r/s w/s rkB/s wkB/s avgrq-sz avgqu-sz await svctm %util sda 18,22 0,00 0,67 0,01 14,77 0,02 43,94 0,01 10,53 39043915,03 2629219,87 sdb 60,89 9,68 50,79 3,04 1724,43 50,52 65,95 0,70 13,06 488437,47 2629219,87 avg-cpu: %user %nice %system %iowait %steal %idle 2,72 0,00 0,74 0,00 0,00 96,53 Device: rrqm/s wrqm/s r/s w/s rkB/s wkB/s avgrq-sz avgqu-sz await svctm %util sda 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 100,00 sdb 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 100,00 avg-cpu: %user %nice %system %iowait %steal %idle 6,68 0,00 0,99 0,00 0,00 92,33 Device: rrqm/s wrqm/s r/s w/s rkB/s wkB/s avgrq-sz avgqu-sz await svctm %util sda 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 100,00 sdb 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 100,00 avg-cpu: %user %nice %system %iowait %steal %idle 4,40 0,00 0,73 1,47 0,00 93,40 Device: rrqm/s wrqm/s r/s w/s rkB/s wkB/s avgrq-sz avgqu-sz await svctm %util sda 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 100,00 sdb 0,00 4,00 0,00 3,00 0,00 28,00 18,67 0,06 19,50 333,33 100,00 Global values for service time and utilization are garbage. For interval values, utilization is always 100%, and service time is higher than normal. I bisected it down to: [a9327cac440be4d8333bba975cbbf76045096275] Seperate read and write statistics of in_flight requests and verified that reverting just that commit indeed solves the issue on 2.6.32-rc1." So until this is debugged, revert the bad commit. Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-10-04 13:04:38 -06:00
part_to_disk(part)->part0.in_flight--;
}
/* block/blk-core.c */
extern void part_round_stats(int cpu, struct hd_struct *part);
/* block/genhd.c */
extern void add_disk(struct gendisk *disk);
extern void del_gendisk(struct gendisk *gp);
extern void unlink_gendisk(struct gendisk *gp);
extern struct gendisk *get_gendisk(dev_t dev, int *partno);
extern struct block_device *bdget_disk(struct gendisk *disk, int partno);
extern void set_device_ro(struct block_device *bdev, int flag);
extern void set_disk_ro(struct gendisk *disk, int flag);
static inline int get_disk_ro(struct gendisk *disk)
{
return disk->part0.policy;
}
/* drivers/char/random.c */
extern void add_disk_randomness(struct gendisk *disk);
extern void rand_initialize_disk(struct gendisk *disk);
static inline sector_t get_start_sect(struct block_device *bdev)
{
return bdev->bd_part->start_sect;
}
static inline sector_t get_capacity(struct gendisk *disk)
{
return disk->part0.nr_sects;
}
static inline void set_capacity(struct gendisk *disk, sector_t size)
{
disk->part0.nr_sects = size;
}
#ifdef CONFIG_SOLARIS_X86_PARTITION
#define SOLARIS_X86_NUMSLICE 16
#define SOLARIS_X86_VTOC_SANE (0x600DDEEEUL)
struct solaris_x86_slice {
__le16 s_tag; /* ID tag of partition */
__le16 s_flag; /* permission flags */
__le32 s_start; /* start sector no of partition */
__le32 s_size; /* # of blocks in partition */
};
struct solaris_x86_vtoc {
unsigned int v_bootinfo[3]; /* info needed by mboot (unsupported) */
__le32 v_sanity; /* to verify vtoc sanity */
__le32 v_version; /* layout version */
char v_volume[8]; /* volume name */
__le16 v_sectorsz; /* sector size in bytes */
__le16 v_nparts; /* number of partitions */
unsigned int v_reserved[10]; /* free space */
struct solaris_x86_slice
v_slice[SOLARIS_X86_NUMSLICE]; /* slice headers */
unsigned int timestamp[SOLARIS_X86_NUMSLICE]; /* timestamp (unsupported) */
char v_asciilabel[128]; /* for compatibility */
};
#endif /* CONFIG_SOLARIS_X86_PARTITION */
#ifdef CONFIG_BSD_DISKLABEL
/*
* BSD disklabel support by Yossi Gottlieb <yogo@math.tau.ac.il>
* updated by Marc Espie <Marc.Espie@openbsd.org>
*/
/* check against BSD src/sys/sys/disklabel.h for consistency */
#define BSD_DISKMAGIC (0x82564557UL) /* The disk magic number */
#define BSD_MAXPARTITIONS 16
#define OPENBSD_MAXPARTITIONS 16
#define BSD_FS_UNUSED 0 /* disklabel unused partition entry ID */
struct bsd_disklabel {
__le32 d_magic; /* the magic number */
__s16 d_type; /* drive type */
__s16 d_subtype; /* controller/d_type specific */
char d_typename[16]; /* type name, e.g. "eagle" */
char d_packname[16]; /* pack identifier */
__u32 d_secsize; /* # of bytes per sector */
__u32 d_nsectors; /* # of data sectors per track */
__u32 d_ntracks; /* # of tracks per cylinder */
__u32 d_ncylinders; /* # of data cylinders per unit */
__u32 d_secpercyl; /* # of data sectors per cylinder */
__u32 d_secperunit; /* # of data sectors per unit */
__u16 d_sparespertrack; /* # of spare sectors per track */
__u16 d_sparespercyl; /* # of spare sectors per cylinder */
__u32 d_acylinders; /* # of alt. cylinders per unit */
__u16 d_rpm; /* rotational speed */
__u16 d_interleave; /* hardware sector interleave */
__u16 d_trackskew; /* sector 0 skew, per track */
__u16 d_cylskew; /* sector 0 skew, per cylinder */
__u32 d_headswitch; /* head switch time, usec */
__u32 d_trkseek; /* track-to-track seek, usec */
__u32 d_flags; /* generic flags */
#define NDDATA 5
__u32 d_drivedata[NDDATA]; /* drive-type specific information */
#define NSPARE 5
__u32 d_spare[NSPARE]; /* reserved for future use */
__le32 d_magic2; /* the magic number (again) */
__le16 d_checksum; /* xor of data incl. partitions */
/* filesystem and partition information: */
__le16 d_npartitions; /* number of partitions in following */
__le32 d_bbsize; /* size of boot area at sn0, bytes */
__le32 d_sbsize; /* max size of fs superblock, bytes */
struct bsd_partition { /* the partition table */
__le32 p_size; /* number of sectors in partition */
__le32 p_offset; /* starting sector */
__le32 p_fsize; /* filesystem basic fragment size */
__u8 p_fstype; /* filesystem type, see below */
__u8 p_frag; /* filesystem fragments per block */
__le16 p_cpg; /* filesystem cylinders per group */
} d_partitions[BSD_MAXPARTITIONS]; /* actually may be more */
};
#endif /* CONFIG_BSD_DISKLABEL */
#ifdef CONFIG_UNIXWARE_DISKLABEL
/*
* Unixware slices support by Andrzej Krzysztofowicz <ankry@mif.pg.gda.pl>
* and Krzysztof G. Baranowski <kgb@knm.org.pl>
*/
#define UNIXWARE_DISKMAGIC (0xCA5E600DUL) /* The disk magic number */
#define UNIXWARE_DISKMAGIC2 (0x600DDEEEUL) /* The slice table magic nr */
#define UNIXWARE_NUMSLICE 16
#define UNIXWARE_FS_UNUSED 0 /* Unused slice entry ID */
struct unixware_slice {
__le16 s_label; /* label */
__le16 s_flags; /* permission flags */
__le32 start_sect; /* starting sector */
__le32 nr_sects; /* number of sectors in slice */
};
struct unixware_disklabel {
__le32 d_type; /* drive type */
__le32 d_magic; /* the magic number */
__le32 d_version; /* version number */
char d_serial[12]; /* serial number of the device */
__le32 d_ncylinders; /* # of data cylinders per device */
__le32 d_ntracks; /* # of tracks per cylinder */
__le32 d_nsectors; /* # of data sectors per track */
__le32 d_secsize; /* # of bytes per sector */
__le32 d_part_start; /* # of first sector of this partition */
__le32 d_unknown1[12]; /* ? */
__le32 d_alt_tbl; /* byte offset of alternate table */
__le32 d_alt_len; /* byte length of alternate table */
__le32 d_phys_cyl; /* # of physical cylinders per device */
__le32 d_phys_trk; /* # of physical tracks per cylinder */
__le32 d_phys_sec; /* # of physical sectors per track */
__le32 d_phys_bytes; /* # of physical bytes per sector */
__le32 d_unknown2; /* ? */
__le32 d_unknown3; /* ? */
__le32 d_pad[8]; /* pad */
struct unixware_vtoc {
__le32 v_magic; /* the magic number */
__le32 v_version; /* version number */
char v_name[8]; /* volume name */
__le16 v_nslices; /* # of slices */
__le16 v_unknown1; /* ? */
__le32 v_reserved[10]; /* reserved */
struct unixware_slice
v_slice[UNIXWARE_NUMSLICE]; /* slice headers */
} vtoc;
}; /* 408 */
#endif /* CONFIG_UNIXWARE_DISKLABEL */
#ifdef CONFIG_MINIX_SUBPARTITION
# define MINIX_NR_SUBPARTITIONS 4
#endif /* CONFIG_MINIX_SUBPARTITION */
#define ADDPART_FLAG_NONE 0
#define ADDPART_FLAG_RAID 1
#define ADDPART_FLAG_WHOLEDISK 2
extern int blk_alloc_devt(struct hd_struct *part, dev_t *devt);
extern void blk_free_devt(dev_t devt);
extern dev_t blk_lookup_devt(const char *name, int partno);
extern char *disk_name (struct gendisk *hd, int partno, char *buf);
extern int disk_expand_part_tbl(struct gendisk *disk, int target);
extern int rescan_partitions(struct gendisk *disk, struct block_device *bdev);
extern struct hd_struct * __must_check add_partition(struct gendisk *disk,
int partno, sector_t start,
sector_t len, int flags);
extern void delete_partition(struct gendisk *, int);
extern void printk_all_partitions(void);
extern struct gendisk *alloc_disk_node(int minors, int node_id);
extern struct gendisk *alloc_disk(int minors);
extern struct kobject *get_disk(struct gendisk *disk);
extern void put_disk(struct gendisk *disk);
extern void blk_register_region(dev_t devt, unsigned long range,
struct module *module,
struct kobject *(*probe)(dev_t, int *, void *),
int (*lock)(dev_t, void *),
void *data);
extern void blk_unregister_region(dev_t devt, unsigned long range);
extern ssize_t part_size_show(struct device *dev,
struct device_attribute *attr, char *buf);
extern ssize_t part_stat_show(struct device *dev,
struct device_attribute *attr, char *buf);
#ifdef CONFIG_FAIL_MAKE_REQUEST
extern ssize_t part_fail_show(struct device *dev,
struct device_attribute *attr, char *buf);
extern ssize_t part_fail_store(struct device *dev,
struct device_attribute *attr,
const char *buf, size_t count);
#endif /* CONFIG_FAIL_MAKE_REQUEST */
#else /* CONFIG_BLOCK */
static inline void printk_all_partitions(void) { }
static inline dev_t blk_lookup_devt(const char *name, int partno)
{
dev_t devt = MKDEV(0, 0);
return devt;
}
#endif /* CONFIG_BLOCK */
[PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-09-30 12:45:40 -06:00
#endif /* _LINUX_GENHD_H */