Commit 6cb8a911 authored by Linus Torvalds's avatar Linus Torvalds
Browse files
parents 7f3591cf 3ea40058
EXTRA_CFLAGS := -I$(src)
obj-$(CONFIG_GFS2_FS) += gfs2.o
gfs2-y := acl.o bmap.o dir.o eaops.o eattr.o glock.o \
glops.o inode.o log.o lops.o main.o meta_io.o \
......
......@@ -25,6 +25,7 @@
#include "trans.h"
#include "dir.h"
#include "util.h"
#include "trace_gfs2.h"
/* This doesn't need to be that large as max 64 bit pointers in a 4k
* block is 512, so __u16 is fine for that. It saves stack space to
......@@ -589,6 +590,7 @@ int gfs2_block_map(struct inode *inode, sector_t lblock,
clear_buffer_mapped(bh_map);
clear_buffer_new(bh_map);
clear_buffer_boundary(bh_map);
trace_gfs2_bmap(ip, bh_map, lblock, create, 1);
if (gfs2_is_dir(ip)) {
bsize = sdp->sd_jbsize;
arr = sdp->sd_jheightsize;
......@@ -623,6 +625,7 @@ int gfs2_block_map(struct inode *inode, sector_t lblock,
ret = 0;
out:
release_metapath(&mp);
trace_gfs2_bmap(ip, bh_map, lblock, create, ret);
bmap_unlock(ip, create);
return ret;
......
......@@ -39,6 +39,8 @@
#include "super.h"
#include "util.h"
#include "bmap.h"
#define CREATE_TRACE_POINTS
#include "trace_gfs2.h"
struct gfs2_gl_hash_bucket {
struct hlist_head hb_list;
......@@ -155,7 +157,7 @@ static void glock_free(struct gfs2_glock *gl)
if (aspace)
gfs2_aspace_put(aspace);
trace_gfs2_glock_put(gl);
sdp->sd_lockstruct.ls_ops->lm_put_lock(gfs2_glock_cachep, gl);
}
......@@ -317,14 +319,17 @@ restart:
return 2;
gh->gh_error = ret;
list_del_init(&gh->gh_list);
trace_gfs2_glock_queue(gh, 0);
gfs2_holder_wake(gh);
goto restart;
}
set_bit(HIF_HOLDER, &gh->gh_iflags);
trace_gfs2_promote(gh, 1);
gfs2_holder_wake(gh);
goto restart;
}
set_bit(HIF_HOLDER, &gh->gh_iflags);
trace_gfs2_promote(gh, 0);
gfs2_holder_wake(gh);
continue;
}
......@@ -354,6 +359,7 @@ static inline void do_error(struct gfs2_glock *gl, const int ret)
else
continue;
list_del_init(&gh->gh_list);
trace_gfs2_glock_queue(gh, 0);
gfs2_holder_wake(gh);
}
}
......@@ -422,6 +428,7 @@ static void finish_xmote(struct gfs2_glock *gl, unsigned int ret)
int rv;
spin_lock(&gl->gl_spin);
trace_gfs2_glock_state_change(gl, state);
state_change(gl, state);
gh = find_first_waiter(gl);
......@@ -851,6 +858,7 @@ static void handle_callback(struct gfs2_glock *gl, unsigned int state,
gl->gl_demote_state != state) {
gl->gl_demote_state = LM_ST_UNLOCKED;
}
trace_gfs2_demote_rq(gl);
}
/**
......@@ -936,6 +944,7 @@ fail:
goto do_cancel;
return;
}
trace_gfs2_glock_queue(gh, 1);
list_add_tail(&gh->gh_list, insert_pt);
do_cancel:
gh = list_entry(gl->gl_holders.next, struct gfs2_holder, gh_list);
......@@ -1032,6 +1041,7 @@ void gfs2_glock_dq(struct gfs2_holder *gh)
!test_bit(GLF_DEMOTE, &gl->gl_flags))
fast_path = 1;
}
trace_gfs2_glock_queue(gh, 0);
spin_unlock(&gl->gl_spin);
if (likely(fast_path))
return;
......
......@@ -28,6 +28,7 @@
#include "meta_io.h"
#include "util.h"
#include "dir.h"
#include "trace_gfs2.h"
#define PULL 1
......@@ -313,6 +314,7 @@ int gfs2_log_reserve(struct gfs2_sbd *sdp, unsigned int blks)
gfs2_log_lock(sdp);
}
atomic_sub(blks, &sdp->sd_log_blks_free);
trace_gfs2_log_blocks(sdp, -blks);
gfs2_log_unlock(sdp);
mutex_unlock(&sdp->sd_log_reserve_mutex);
......@@ -333,6 +335,7 @@ void gfs2_log_release(struct gfs2_sbd *sdp, unsigned int blks)
gfs2_log_lock(sdp);
atomic_add(blks, &sdp->sd_log_blks_free);
trace_gfs2_log_blocks(sdp, blks);
gfs2_assert_withdraw(sdp,
atomic_read(&sdp->sd_log_blks_free) <= sdp->sd_jdesc->jd_blocks);
gfs2_log_unlock(sdp);
......@@ -558,6 +561,7 @@ static void log_pull_tail(struct gfs2_sbd *sdp, unsigned int new_tail)
gfs2_log_lock(sdp);
atomic_add(dist, &sdp->sd_log_blks_free);
trace_gfs2_log_blocks(sdp, dist);
gfs2_assert_withdraw(sdp, atomic_read(&sdp->sd_log_blks_free) <= sdp->sd_jdesc->jd_blocks);
gfs2_log_unlock(sdp);
......@@ -715,6 +719,7 @@ void __gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl)
up_write(&sdp->sd_log_flush_lock);
return;
}
trace_gfs2_log_flush(sdp, 1);
ai = kzalloc(sizeof(struct gfs2_ail), GFP_NOFS | __GFP_NOFAIL);
INIT_LIST_HEAD(&ai->ai_ail1_list);
......@@ -746,6 +751,7 @@ void __gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl)
else if (sdp->sd_log_tail != current_tail(sdp) && !sdp->sd_log_idle){
gfs2_log_lock(sdp);
atomic_dec(&sdp->sd_log_blks_free); /* Adjust for unreserved buffer */
trace_gfs2_log_blocks(sdp, -1);
gfs2_log_unlock(sdp);
log_write_header(sdp, 0, PULL);
}
......@@ -763,7 +769,7 @@ void __gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl)
ai = NULL;
}
gfs2_log_unlock(sdp);
trace_gfs2_log_flush(sdp, 0);
up_write(&sdp->sd_log_flush_lock);
kfree(ai);
......@@ -787,6 +793,7 @@ static void log_refund(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
gfs2_assert_withdraw(sdp, sdp->sd_log_blks_reserved + tr->tr_reserved >= reserved);
unused = sdp->sd_log_blks_reserved - reserved + tr->tr_reserved;
atomic_add(unused, &sdp->sd_log_blks_free);
trace_gfs2_log_blocks(sdp, unused);
gfs2_assert_withdraw(sdp, atomic_read(&sdp->sd_log_blks_free) <=
sdp->sd_jdesc->jd_blocks);
sdp->sd_log_blks_reserved = reserved;
......
......@@ -27,6 +27,7 @@
#include "rgrp.h"
#include "trans.h"
#include "util.h"
#include "trace_gfs2.h"
/**
* gfs2_pin - Pin a buffer in memory
......@@ -53,6 +54,7 @@ static void gfs2_pin(struct gfs2_sbd *sdp, struct buffer_head *bh)
if (bd->bd_ail)
list_move(&bd->bd_ail_st_list, &bd->bd_ail->ai_ail2_list);
get_bh(bh);
trace_gfs2_pin(bd, 1);
}
/**
......@@ -89,6 +91,7 @@ static void gfs2_unpin(struct gfs2_sbd *sdp, struct buffer_head *bh,
bd->bd_ail = ai;
list_add(&bd->bd_ail_st_list, &ai->ai_ail1_list);
clear_bit(GLF_LFLUSH, &bd->bd_gl->gl_flags);
trace_gfs2_pin(bd, 0);
gfs2_log_unlock(sdp);
unlock_buffer(bh);
}
......
......@@ -33,6 +33,7 @@
#include "log.h"
#include "quota.h"
#include "dir.h"
#include "trace_gfs2.h"
#define DO 0
#define UNDO 1
......@@ -775,6 +776,7 @@ static int init_journal(struct gfs2_sbd *sdp, int undo)
/* Map the extents for this journal's blocks */
map_journal_extents(sdp);
}
trace_gfs2_log_blocks(sdp, atomic_read(&sdp->sd_log_blks_free));
if (sdp->sd_lockstruct.ls_first) {
unsigned int x;
......
......@@ -29,6 +29,7 @@
#include "util.h"
#include "log.h"
#include "inode.h"
#include "trace_gfs2.h"
#define BFITNOENT ((u32)~0)
#define NO_BLOCK ((u64)~0)
......@@ -1519,7 +1520,7 @@ int gfs2_alloc_block(struct gfs2_inode *ip, u64 *bn, unsigned int *n)
spin_lock(&sdp->sd_rindex_spin);
rgd->rd_free_clone -= *n;
spin_unlock(&sdp->sd_rindex_spin);
trace_gfs2_block_alloc(ip, block, *n, GFS2_BLKST_USED);
*bn = block;
return 0;
......@@ -1571,7 +1572,7 @@ u64 gfs2_alloc_di(struct gfs2_inode *dip, u64 *generation)
spin_lock(&sdp->sd_rindex_spin);
rgd->rd_free_clone--;
spin_unlock(&sdp->sd_rindex_spin);
trace_gfs2_block_alloc(dip, block, 1, GFS2_BLKST_DINODE);
return block;
}
......@@ -1591,7 +1592,7 @@ void gfs2_free_data(struct gfs2_inode *ip, u64 bstart, u32 blen)
rgd = rgblk_free(sdp, bstart, blen, GFS2_BLKST_FREE);
if (!rgd)
return;
trace_gfs2_block_alloc(ip, bstart, blen, GFS2_BLKST_FREE);
rgd->rd_free += blen;
gfs2_trans_add_bh(rgd->rd_gl, rgd->rd_bits[0].bi_bh, 1);
......@@ -1619,7 +1620,7 @@ void gfs2_free_meta(struct gfs2_inode *ip, u64 bstart, u32 blen)
rgd = rgblk_free(sdp, bstart, blen, GFS2_BLKST_FREE);
if (!rgd)
return;
trace_gfs2_block_alloc(ip, bstart, blen, GFS2_BLKST_FREE);
rgd->rd_free += blen;
gfs2_trans_add_bh(rgd->rd_gl, rgd->rd_bits[0].bi_bh, 1);
......@@ -1642,6 +1643,7 @@ void gfs2_unlink_di(struct inode *inode)
rgd = rgblk_free(sdp, blkno, 1, GFS2_BLKST_UNLINKED);
if (!rgd)
return;
trace_gfs2_block_alloc(ip, blkno, 1, GFS2_BLKST_UNLINKED);
gfs2_trans_add_bh(rgd->rd_gl, rgd->rd_bits[0].bi_bh, 1);
gfs2_rgrp_out(rgd, rgd->rd_bits[0].bi_bh->b_data);
gfs2_trans_add_rg(rgd);
......@@ -1673,6 +1675,7 @@ static void gfs2_free_uninit_di(struct gfs2_rgrpd *rgd, u64 blkno)
void gfs2_free_di(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip)
{
gfs2_free_uninit_di(rgd, ip->i_no_addr);
trace_gfs2_block_alloc(ip, ip->i_no_addr, 1, GFS2_BLKST_FREE);
gfs2_quota_change(ip, -1, ip->i_inode.i_uid, ip->i_inode.i_gid);
gfs2_meta_wipe(ip, ip->i_no_addr, 1);
}
......
......@@ -719,8 +719,6 @@ static void gfs2_put_super(struct super_block *sb)
int error;
struct gfs2_jdesc *jd;
lock_kernel();
/* Unfreeze the filesystem, if we need to */
mutex_lock(&sdp->sd_freeze_lock);
......@@ -787,8 +785,6 @@ restart:
/* At this point, we're through participating in the lockspace */
gfs2_sys_fs_del(sdp);
unlock_kernel();
}
/**
......
#if !defined(_TRACE_GFS2_H) || defined(TRACE_HEADER_MULTI_READ)
#define _TRACE_GFS2_H
#include <linux/tracepoint.h>
#undef TRACE_SYSTEM
#define TRACE_SYSTEM gfs2
#define TRACE_INCLUDE_FILE trace_gfs2
#include <linux/fs.h>
#include <linux/buffer_head.h>
#include <linux/dlmconstants.h>
#include <linux/gfs2_ondisk.h>
#include "incore.h"
#include "glock.h"
#define dlm_state_name(nn) { DLM_LOCK_##nn, #nn }
#define glock_trace_name(x) __print_symbolic(x, \
dlm_state_name(IV), \
dlm_state_name(NL), \
dlm_state_name(CR), \
dlm_state_name(CW), \
dlm_state_name(PR), \
dlm_state_name(PW), \
dlm_state_name(EX))
#define block_state_name(x) __print_symbolic(x, \
{ GFS2_BLKST_FREE, "free" }, \
{ GFS2_BLKST_USED, "used" }, \
{ GFS2_BLKST_DINODE, "dinode" }, \
{ GFS2_BLKST_UNLINKED, "unlinked" })
#define show_glock_flags(flags) __print_flags(flags, "", \
{(1UL << GLF_LOCK), "l" }, \
{(1UL << GLF_DEMOTE), "D" }, \
{(1UL << GLF_PENDING_DEMOTE), "d" }, \
{(1UL << GLF_DEMOTE_IN_PROGRESS), "p" }, \
{(1UL << GLF_DIRTY), "y" }, \
{(1UL << GLF_LFLUSH), "f" }, \
{(1UL << GLF_INVALIDATE_IN_PROGRESS), "i" }, \
{(1UL << GLF_REPLY_PENDING), "r" }, \
{(1UL << GLF_INITIAL), "I" }, \
{(1UL << GLF_FROZEN), "F" })
#ifndef NUMPTY
#define NUMPTY
static inline u8 glock_trace_state(unsigned int state)
{
switch(state) {
case LM_ST_SHARED:
return DLM_LOCK_PR;
case LM_ST_DEFERRED:
return DLM_LOCK_CW;
case LM_ST_EXCLUSIVE:
return DLM_LOCK_EX;
}
return DLM_LOCK_NL;
}
#endif
/* Section 1 - Locking
*
* Objectives:
* Latency: Remote demote request to state change
* Latency: Local lock request to state change
* Latency: State change to lock grant
* Correctness: Ordering of local lock state vs. I/O requests
* Correctness: Responses to remote demote requests
*/
/* General glock state change (DLM lock request completes) */
TRACE_EVENT(gfs2_glock_state_change,
TP_PROTO(const struct gfs2_glock *gl, unsigned int new_state),
TP_ARGS(gl, new_state),
TP_STRUCT__entry(
__field( dev_t, dev )
__field( u64, glnum )
__field( u32, gltype )
__field( u8, cur_state )
__field( u8, new_state )
__field( u8, dmt_state )
__field( u8, tgt_state )
__field( unsigned long, flags )
),
TP_fast_assign(
__entry->dev = gl->gl_sbd->sd_vfs->s_dev;
__entry->glnum = gl->gl_name.ln_number;
__entry->gltype = gl->gl_name.ln_type;
__entry->cur_state = glock_trace_state(gl->gl_state);
__entry->new_state = glock_trace_state(new_state);
__entry->tgt_state = glock_trace_state(gl->gl_target);
__entry->dmt_state = glock_trace_state(gl->gl_demote_state);
__entry->flags = gl->gl_flags;
),
TP_printk("%u,%u glock %d:%lld state %s to %s tgt:%s dmt:%s flags:%s",
MAJOR(__entry->dev), MINOR(__entry->dev), __entry->gltype,
(unsigned long long)__entry->glnum,
glock_trace_name(__entry->cur_state),
glock_trace_name(__entry->new_state),
glock_trace_name(__entry->tgt_state),
glock_trace_name(__entry->dmt_state),
show_glock_flags(__entry->flags))
);
/* State change -> unlocked, glock is being deallocated */
TRACE_EVENT(gfs2_glock_put,
TP_PROTO(const struct gfs2_glock *gl),
TP_ARGS(gl),
TP_STRUCT__entry(
__field( dev_t, dev )
__field( u64, glnum )
__field( u32, gltype )
__field( u8, cur_state )
__field( unsigned long, flags )
),
TP_fast_assign(
__entry->dev = gl->gl_sbd->sd_vfs->s_dev;
__entry->gltype = gl->gl_name.ln_type;
__entry->glnum = gl->gl_name.ln_number;
__entry->cur_state = glock_trace_state(gl->gl_state);
__entry->flags = gl->gl_flags;
),
TP_printk("%u,%u glock %d:%lld state %s => %s flags:%s",
MAJOR(__entry->dev), MINOR(__entry->dev),
__entry->gltype, (unsigned long long)__entry->glnum,
glock_trace_name(__entry->cur_state),
glock_trace_name(DLM_LOCK_IV),
show_glock_flags(__entry->flags))
);
/* Callback (local or remote) requesting lock demotion */
TRACE_EVENT(gfs2_demote_rq,
TP_PROTO(const struct gfs2_glock *gl),
TP_ARGS(gl),
TP_STRUCT__entry(
__field( dev_t, dev )
__field( u64, glnum )
__field( u32, gltype )
__field( u8, cur_state )
__field( u8, dmt_state )
__field( unsigned long, flags )
),
TP_fast_assign(
__entry->dev = gl->gl_sbd->sd_vfs->s_dev;
__entry->gltype = gl->gl_name.ln_type;
__entry->glnum = gl->gl_name.ln_number;
__entry->cur_state = glock_trace_state(gl->gl_state);
__entry->dmt_state = glock_trace_state(gl->gl_demote_state);
__entry->flags = gl->gl_flags;
),
TP_printk("%u,%u glock %d:%lld demote %s to %s flags:%s",
MAJOR(__entry->dev), MINOR(__entry->dev), __entry->gltype,
(unsigned long long)__entry->glnum,
glock_trace_name(__entry->cur_state),
glock_trace_name(__entry->dmt_state),
show_glock_flags(__entry->flags))
);
/* Promotion/grant of a glock */
TRACE_EVENT(gfs2_promote,
TP_PROTO(const struct gfs2_holder *gh, int first),
TP_ARGS(gh, first),
TP_STRUCT__entry(
__field( dev_t, dev )
__field( u64, glnum )
__field( u32, gltype )
__field( int, first )
__field( u8, state )
),
TP_fast_assign(
__entry->dev = gh->gh_gl->gl_sbd->sd_vfs->s_dev;
__entry->glnum = gh->gh_gl->gl_name.ln_number;
__entry->gltype = gh->gh_gl->gl_name.ln_type;
__entry->first = first;
__entry->state = glock_trace_state(gh->gh_state);
),
TP_printk("%u,%u glock %u:%llu promote %s %s",
MAJOR(__entry->dev), MINOR(__entry->dev), __entry->gltype,
(unsigned long long)__entry->glnum,
__entry->first ? "first": "other",
glock_trace_name(__entry->state))
);
/* Queue/dequeue a lock request */
TRACE_EVENT(gfs2_glock_queue,
TP_PROTO(const struct gfs2_holder *gh, int queue),
TP_ARGS(gh, queue),
TP_STRUCT__entry(
__field( dev_t, dev )
__field( u64, glnum )
__field( u32, gltype )
__field( int, queue )
__field( u8, state )
),
TP_fast_assign(
__entry->dev = gh->gh_gl->gl_sbd->sd_vfs->s_dev;
__entry->glnum = gh->gh_gl->gl_name.ln_number;
__entry->gltype = gh->gh_gl->gl_name.ln_type;
__entry->queue = queue;
__entry->state = glock_trace_state(gh->gh_state);
),
TP_printk("%u,%u glock %u:%llu %squeue %s",
MAJOR(__entry->dev), MINOR(__entry->dev), __entry->gltype,
(unsigned long long)__entry->glnum,
__entry->queue ? "" : "de",
glock_trace_name(__entry->state))
);
/* Section 2 - Log/journal
*
* Objectives:
* Latency: Log flush time
* Correctness: pin/unpin vs. disk I/O ordering
* Performance: Log usage stats
*/
/* Pin/unpin a block in the log */
TRACE_EVENT(gfs2_pin,
TP_PROTO(const struct gfs2_bufdata *bd, int pin),
TP_ARGS(bd, pin),
TP_STRUCT__entry(
__field( dev_t, dev )
__field( int, pin )
__field( u32, len )
__field( sector_t, block )
__field( u64, ino )
),
TP_fast_assign(
__entry->dev = bd->bd_gl->gl_sbd->sd_vfs->s_dev;
__entry->pin = pin;
__entry->len = bd->bd_bh->b_size;
__entry->block = bd->bd_bh->b_blocknr;
__entry->ino = bd->bd_gl->gl_name.ln_number;
),
TP_printk("%u,%u log %s %llu/%lu inode %llu",
MAJOR(__entry->dev), MINOR(__entry->dev),
__entry->pin ? "pin" : "unpin",
(unsigned long long)__entry->block,
(unsigned long)__entry->len,
(unsigned long long)__entry->ino)
);
/* Flushing the log */
TRACE_EVENT(gfs2_log_flush,
TP_PROTO(const struct gfs2_sbd *sdp, int start),
TP_ARGS(sdp, start),
TP_STRUCT__entry(
__field( dev_t, dev )
__field( int, start )
__field( u64, log_seq )
),
TP_fast_assign(
__entry->dev = sdp->sd_vfs->s_dev;
__entry->start = start;
__entry->log_seq = sdp->sd_log_sequence;
),
TP_printk("%u,%u log flush %s %llu",
MAJOR(__entry->dev), MINOR(__entry->dev),
__entry->start ? "start" : "end",
(unsigned long long)__entry->log_seq)
);
/* Reserving/releasing blocks in the log */
TRACE_EVENT(gfs2_log_blocks,
TP_PROTO(const struct gfs2_sbd *sdp, int blocks),
TP_ARGS(sdp, blocks),
TP_STRUCT__entry(
__field( dev_t, dev )
__field( int, blocks )
),
TP_fast_assign(
__entry->dev = sdp->sd_vfs->s_dev;
__entry->blocks = blocks;
),
TP_printk("%u,%u log reserve %d", MAJOR(__entry->dev),
MINOR(__entry->dev), __entry->blocks)
);
/* Section 3 - bmap
*
* Objectives:
* Latency: Bmap request time
* Performance: Block allocator tracing
* Correctness: Test of disard generation vs. blocks allocated
*/
/* Map an extent of blocks, possibly a new allocation */
TRACE_EVENT(gfs2_bmap,
TP_PROTO(const struct gfs2_inode *ip, const struct buffer_head *bh,
sector_t lblock, int create, int errno),
TP_ARGS(ip, bh, lblock, create, errno),
TP_STRUCT__entry(
__field( dev_t, dev )
__field( sector_t, lblock )
__field( sector_t, pblock )
__field( u64, inum )
__field( unsigned long, state )
__field( u32, len )
__field( int, create )
__field( int, errno )
),
TP_fast_assign(
__entry->dev = ip->i_gl->gl_sbd->sd_vfs->s_dev;
__entry->lblock = lblock;
__entry->pblock = buffer_mapped(bh) ? bh->b_blocknr : 0;
__entry->inum = ip->i_no_addr;