Minki/linux
1
0
Fork 1
mirror of https://github.com/torvalds/linux.git synced 2024-11-27 14:41:39 +00:00
Code Issues Packages Projects Releases Wiki Activity
81440e7374
linux/fs/gfs2/trace_gfs2.h

559 lines
15 KiB
C
Raw Normal View History

tracing/events: Move TRACE_SYSTEM outside of include guard If TRACE_INCLDUE_FILE is defined, <trace/events/TRACE_INCLUDE_FILE.h> will be included and compiled, otherwise it will be <trace/events/TRACE_SYSTEM.h> So TRACE_SYSTEM should be defined outside of #if proctection, just like TRACE_INCLUDE_FILE. Imaging this scenario: #include <trace/events/foo.h> -> TRACE_SYSTEM == foo ... #include <trace/events/bar.h> -> TRACE_SYSTEM == bar ... #define CREATE_TRACE_POINTS #include <trace/events/foo.h> -> TRACE_SYSTEM == bar !!! and then bar.h will be included and compiled. Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <4A5A9CF1.2010007@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-13 02:33:21 +00:00
#undef TRACE_SYSTEM
#define TRACE_SYSTEM gfs2
GFS2: Add tracepoints This patch adds the ability to trace various aspects of the GFS2 filesystem. The trace points are divided into three groups, glocks, logging and bmap. These points have been chosen because they allow inspection of the major internal functions of GFS2 and they are also generic enough that they are unlikely to need any major changes as the filesystem evolves. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2009-06-12 07:49:20 +00:00
#if !defined(_TRACE_GFS2_H) || defined(TRACE_HEADER_MULTI_READ)
#define _TRACE_GFS2_H
#include <linux/tracepoint.h>
#include <linux/fs.h>
#include <linux/buffer_head.h>
#include <linux/dlmconstants.h>
#include <linux/gfs2_ondisk.h>
GFS2: Add an AIL writeback tracepoint Add a tracepoint for monitoring writeback of the AIL. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2011-04-18 13:18:38 +00:00
#include <linux/writeback.h>
GFS2: glock statistics gathering The stats are divided into two sets: those relating to the super block and those relating to an individual glock. The super block stats are done on a per cpu basis in order to try and reduce the overhead of gathering them. They are also further divided by glock type. In the case of both the super block and glock statistics, the same information is gathered in each case. The super block statistics are used to provide default values for most of the glock statistics, so that newly created glocks should have, as far as possible, a sensible starting point. The statistics are divided into three pairs of mean and variance, plus two counters. The mean/variance pairs are smoothed exponential estimates and the algorithm used is one which will be very familiar to those used to calculation of round trip times in network code. The three pairs of mean/variance measure the following things: 1. DLM lock time (non-blocking requests) 2. DLM lock time (blocking requests) 3. Inter-request time (again to the DLM) A non-blocking request is one which will complete right away, whatever the state of the DLM lock in question. That currently means any requests when (a) the current state of the lock is exclusive (b) the requested state is either null or unlocked or (c) the "try lock" flag is set. A blocking request covers all the other lock requests. There are two counters. The first is there primarily to show how many lock requests have been made, and thus how much data has gone into the mean/variance calculations. The other counter is counting queueing of holders at the top layer of the glock code. Hopefully that number will be a lot larger than the number of dlm lock requests issued. So why gather these statistics? There are several reasons we'd like to get a better idea of these timings: 1. To be able to better set the glock "min hold time" 2. To spot performance issues more easily 3. To improve the algorithm for selecting resource groups for allocation (to base it on lock wait time, rather than blindly using a "try lock") Due to the smoothing action of the updates, a step change in some input quantity being sampled will only fully be taken into account after 8 samples (or 4 for the variance) and this needs to be carefully considered when interpreting the results. Knowing both the time it takes a lock request to complete and the average time between lock requests for a glock means we can compute the total percentage of the time for which the node is able to use a glock vs. time that the rest of the cluster has its share. That will be very useful when setting the lock min hold time. The other point to remember is that all times are in nanoseconds. Great care has been taken to ensure that we measure exactly the quantities that we want, as accurately as possible. There are always inaccuracies in any measuring system, but I hope this is as accurate as we can reasonably make it. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2012-01-20 10:38:36 +00:00
#include <linux/ktime.h>
GFS2: Add tracepoints This patch adds the ability to trace various aspects of the GFS2 filesystem. The trace points are divided into three groups, glocks, logging and bmap. These points have been chosen because they allow inspection of the major internal functions of GFS2 and they are also generic enough that they are unlikely to need any major changes as the filesystem evolves. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2009-06-12 07:49:20 +00:00
#include "incore.h"
#include "glock.h"
GFS2: Reduce file fragmentation This patch reduces GFS2 file fragmentation by pre-reserving blocks. The resulting improved on disk layout greatly speeds up operations in cases which would have resulted in interlaced allocation of blocks previously. A typical example of this is 10 parallel dd processes, each writing to a file in a common dirctory. The implementation uses an rbtree of reservations attached to each resource group (and each inode). Signed-off-by: Bob Peterson <rpeterso@redhat.com> Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2012-07-19 12:12:40 +00:00
#include "rgrp.h"
GFS2: Add tracepoints This patch adds the ability to trace various aspects of the GFS2 filesystem. The trace points are divided into three groups, glocks, logging and bmap. These points have been chosen because they allow inspection of the major internal functions of GFS2 and they are also generic enough that they are unlikely to need any major changes as the filesystem evolves. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2009-06-12 07:49:20 +00:00
#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" })
GFS2: Reduce file fragmentation This patch reduces GFS2 file fragmentation by pre-reserving blocks. The resulting improved on disk layout greatly speeds up operations in cases which would have resulted in interlaced allocation of blocks previously. A typical example of this is 10 parallel dd processes, each writing to a file in a common dirctory. The implementation uses an rbtree of reservations attached to each resource group (and each inode). Signed-off-by: Bob Peterson <rpeterso@redhat.com> Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2012-07-19 12:12:40 +00:00
#define TRACE_RS_DELETE 0
#define TRACE_RS_TREEDEL 1
#define TRACE_RS_INSERT 2
#define TRACE_RS_CLAIM 3
#define rs_func_name(x) __print_symbolic(x, \
{ 0, "del " }, \
{ 1, "tdel" }, \
{ 2, "ins " }, \
{ 3, "clm " })
GFS2: Add tracepoints This patch adds the ability to trace various aspects of the GFS2 filesystem. The trace points are divided into three groups, glocks, logging and bmap. These points have been chosen because they allow inspection of the major internal functions of GFS2 and they are also generic enough that they are unlikely to need any major changes as the filesystem evolves. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2009-06-12 07:49:20 +00:00
#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" }, \
GFS2: Don't enforce min hold time when two demotes occur in rapid succession Due to the design of the VFS, it is quite usual for operations on GFS2 to consist of a lookup (requiring a shared lock) followed by an operation requiring an exclusive lock. If a remote node has cached an exclusive lock, then it will receive two demote events in rapid succession firstly for a shared lock and then to unlocked. The existing min hold time code was triggering in this case, even if the node was otherwise idle since the state change time was being updated by the initial demote. This patch introduces logic to skip the min hold timer in the case that a "double demote" of this kind has occurred. The min hold timer will still be used in all other cases. A new glock flag is introduced which is used to keep track of whether there have been any newly queued holders since the last glock state change. The min hold time is only applied if the flag is set. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com> Tested-by: Abhijith Das <adas@redhat.com>
2010-09-03 08:39:20 +00:00
{(1UL << GLF_FROZEN), "F" }, \
GFS2: Improve tracing support (adds two flags) This adds support for two new flags. One keeps track of whether the glock is on the LRU list or not. The other isn't really a flag as such, but an indication of whether the glock has an attached object or not. This indication is reported without any locking, which is ok since we do not dereference the object pointer but merely report whether it is NULL or not. Also, this fixes one place where a tracepoint was missing, which was at the point we remove deallocated blocks from the journal. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2011-04-14 13:09:52 +00:00
{(1UL << GLF_QUEUED), "q" }, \
{(1UL << GLF_LRU), "L" }, \
GFS2: glock statistics gathering The stats are divided into two sets: those relating to the super block and those relating to an individual glock. The super block stats are done on a per cpu basis in order to try and reduce the overhead of gathering them. They are also further divided by glock type. In the case of both the super block and glock statistics, the same information is gathered in each case. The super block statistics are used to provide default values for most of the glock statistics, so that newly created glocks should have, as far as possible, a sensible starting point. The statistics are divided into three pairs of mean and variance, plus two counters. The mean/variance pairs are smoothed exponential estimates and the algorithm used is one which will be very familiar to those used to calculation of round trip times in network code. The three pairs of mean/variance measure the following things: 1. DLM lock time (non-blocking requests) 2. DLM lock time (blocking requests) 3. Inter-request time (again to the DLM) A non-blocking request is one which will complete right away, whatever the state of the DLM lock in question. That currently means any requests when (a) the current state of the lock is exclusive (b) the requested state is either null or unlocked or (c) the "try lock" flag is set. A blocking request covers all the other lock requests. There are two counters. The first is there primarily to show how many lock requests have been made, and thus how much data has gone into the mean/variance calculations. The other counter is counting queueing of holders at the top layer of the glock code. Hopefully that number will be a lot larger than the number of dlm lock requests issued. So why gather these statistics? There are several reasons we'd like to get a better idea of these timings: 1. To be able to better set the glock "min hold time" 2. To spot performance issues more easily 3. To improve the algorithm for selecting resource groups for allocation (to base it on lock wait time, rather than blindly using a "try lock") Due to the smoothing action of the updates, a step change in some input quantity being sampled will only fully be taken into account after 8 samples (or 4 for the variance) and this needs to be carefully considered when interpreting the results. Knowing both the time it takes a lock request to complete and the average time between lock requests for a glock means we can compute the total percentage of the time for which the node is able to use a glock vs. time that the rest of the cluster has its share. That will be very useful when setting the lock min hold time. The other point to remember is that all times are in nanoseconds. Great care has been taken to ensure that we measure exactly the quantities that we want, as accurately as possible. There are always inaccuracies in any measuring system, but I hope this is as accurate as we can reasonably make it. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2012-01-20 10:38:36 +00:00
{(1UL << GLF_OBJECT), "o" }, \
{(1UL << GLF_BLOCKING), "b" })
GFS2: Add tracepoints This patch adds the ability to trace various aspects of the GFS2 filesystem. The trace points are divided into three groups, glocks, logging and bmap. These points have been chosen because they allow inspection of the major internal functions of GFS2 and they are also generic enough that they are unlikely to need any major changes as the filesystem evolves. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2009-06-12 07:49:20 +00:00
#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);
GFS2: Improve tracing support (adds two flags) This adds support for two new flags. One keeps track of whether the glock is on the LRU list or not. The other isn't really a flag as such, but an indication of whether the glock has an attached object or not. This indication is reported without any locking, which is ok since we do not dereference the object pointer but merely report whether it is NULL or not. Also, this fixes one place where a tracepoint was missing, which was at the point we remove deallocated blocks from the journal. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2011-04-14 13:09:52 +00:00
__entry->flags = gl->gl_flags | (gl->gl_object ? (1UL<<GLF_OBJECT) : 0);
GFS2: Add tracepoints This patch adds the ability to trace various aspects of the GFS2 filesystem. The trace points are divided into three groups, glocks, logging and bmap. These points have been chosen because they allow inspection of the major internal functions of GFS2 and they are also generic enough that they are unlikely to need any major changes as the filesystem evolves. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2009-06-12 07:49:20 +00:00
),
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);
GFS2: Improve tracing support (adds two flags) This adds support for two new flags. One keeps track of whether the glock is on the LRU list or not. The other isn't really a flag as such, but an indication of whether the glock has an attached object or not. This indication is reported without any locking, which is ok since we do not dereference the object pointer but merely report whether it is NULL or not. Also, this fixes one place where a tracepoint was missing, which was at the point we remove deallocated blocks from the journal. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2011-04-14 13:09:52 +00:00
__entry->flags = gl->gl_flags | (gl->gl_object ? (1UL<<GLF_OBJECT) : 0);
GFS2: Add tracepoints This patch adds the ability to trace various aspects of the GFS2 filesystem. The trace points are divided into three groups, glocks, logging and bmap. These points have been chosen because they allow inspection of the major internal functions of GFS2 and they are also generic enough that they are unlikely to need any major changes as the filesystem evolves. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2009-06-12 07:49:20 +00:00
),
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,
GFS2: Add origin indicator to glock demote tracing This adds the origin indicator to the trace point for glock demotion, so that it is possible to see where demote requests have come from. Note that requests generated from the demote_rq sysfs interface will show as remote, since they are intended to replicate exactly the effect of a demote reuqest from a remote node. It is still possible to tell these apart by looking at the process which initiated the demote request. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2013-04-10 09:32:05 +00:00
TP_PROTO(const struct gfs2_glock *gl, bool remote),
GFS2: Add tracepoints This patch adds the ability to trace various aspects of the GFS2 filesystem. The trace points are divided into three groups, glocks, logging and bmap. These points have been chosen because they allow inspection of the major internal functions of GFS2 and they are also generic enough that they are unlikely to need any major changes as the filesystem evolves. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2009-06-12 07:49:20 +00:00
GFS2: Add origin indicator to glock demote tracing This adds the origin indicator to the trace point for glock demotion, so that it is possible to see where demote requests have come from. Note that requests generated from the demote_rq sysfs interface will show as remote, since they are intended to replicate exactly the effect of a demote reuqest from a remote node. It is still possible to tell these apart by looking at the process which initiated the demote request. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2013-04-10 09:32:05 +00:00
TP_ARGS(gl, remote),
GFS2: Add tracepoints This patch adds the ability to trace various aspects of the GFS2 filesystem. The trace points are divided into three groups, glocks, logging and bmap. These points have been chosen because they allow inspection of the major internal functions of GFS2 and they are also generic enough that they are unlikely to need any major changes as the filesystem evolves. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2009-06-12 07:49:20 +00:00
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 )
GFS2: Add origin indicator to glock demote tracing This adds the origin indicator to the trace point for glock demotion, so that it is possible to see where demote requests have come from. Note that requests generated from the demote_rq sysfs interface will show as remote, since they are intended to replicate exactly the effect of a demote reuqest from a remote node. It is still possible to tell these apart by looking at the process which initiated the demote request. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2013-04-10 09:32:05 +00:00
__field( bool, remote )
GFS2: Add tracepoints This patch adds the ability to trace various aspects of the GFS2 filesystem. The trace points are divided into three groups, glocks, logging and bmap. These points have been chosen because they allow inspection of the major internal functions of GFS2 and they are also generic enough that they are unlikely to need any major changes as the filesystem evolves. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2009-06-12 07:49:20 +00:00
),
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);
GFS2: Improve tracing support (adds two flags) This adds support for two new flags. One keeps track of whether the glock is on the LRU list or not. The other isn't really a flag as such, but an indication of whether the glock has an attached object or not. This indication is reported without any locking, which is ok since we do not dereference the object pointer but merely report whether it is NULL or not. Also, this fixes one place where a tracepoint was missing, which was at the point we remove deallocated blocks from the journal. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2011-04-14 13:09:52 +00:00
__entry->flags = gl->gl_flags | (gl->gl_object ? (1UL<<GLF_OBJECT) : 0);
GFS2: Add origin indicator to glock demote tracing This adds the origin indicator to the trace point for glock demotion, so that it is possible to see where demote requests have come from. Note that requests generated from the demote_rq sysfs interface will show as remote, since they are intended to replicate exactly the effect of a demote reuqest from a remote node. It is still possible to tell these apart by looking at the process which initiated the demote request. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2013-04-10 09:32:05 +00:00
__entry->remote = remote;
GFS2: Add tracepoints This patch adds the ability to trace various aspects of the GFS2 filesystem. The trace points are divided into three groups, glocks, logging and bmap. These points have been chosen because they allow inspection of the major internal functions of GFS2 and they are also generic enough that they are unlikely to need any major changes as the filesystem evolves. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2009-06-12 07:49:20 +00:00
),
GFS2: Add origin indicator to glock demote tracing This adds the origin indicator to the trace point for glock demotion, so that it is possible to see where demote requests have come from. Note that requests generated from the demote_rq sysfs interface will show as remote, since they are intended to replicate exactly the effect of a demote reuqest from a remote node. It is still possible to tell these apart by looking at the process which initiated the demote request. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2013-04-10 09:32:05 +00:00
TP_printk("%u,%u glock %d:%lld demote %s to %s flags:%s %s",
GFS2: Add tracepoints This patch adds the ability to trace various aspects of the GFS2 filesystem. The trace points are divided into three groups, glocks, logging and bmap. These points have been chosen because they allow inspection of the major internal functions of GFS2 and they are also generic enough that they are unlikely to need any major changes as the filesystem evolves. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2009-06-12 07:49:20 +00:00
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),
GFS2: Add origin indicator to glock demote tracing This adds the origin indicator to the trace point for glock demotion, so that it is possible to see where demote requests have come from. Note that requests generated from the demote_rq sysfs interface will show as remote, since they are intended to replicate exactly the effect of a demote reuqest from a remote node. It is still possible to tell these apart by looking at the process which initiated the demote request. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2013-04-10 09:32:05 +00:00
show_glock_flags(__entry->flags),
__entry->remote ? "remote" : "local")
GFS2: Add tracepoints This patch adds the ability to trace various aspects of the GFS2 filesystem. The trace points are divided into three groups, glocks, logging and bmap. These points have been chosen because they allow inspection of the major internal functions of GFS2 and they are also generic enough that they are unlikely to need any major changes as the filesystem evolves. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2009-06-12 07:49:20 +00:00
);
/* 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))
);
GFS2: glock statistics gathering The stats are divided into two sets: those relating to the super block and those relating to an individual glock. The super block stats are done on a per cpu basis in order to try and reduce the overhead of gathering them. They are also further divided by glock type. In the case of both the super block and glock statistics, the same information is gathered in each case. The super block statistics are used to provide default values for most of the glock statistics, so that newly created glocks should have, as far as possible, a sensible starting point. The statistics are divided into three pairs of mean and variance, plus two counters. The mean/variance pairs are smoothed exponential estimates and the algorithm used is one which will be very familiar to those used to calculation of round trip times in network code. The three pairs of mean/variance measure the following things: 1. DLM lock time (non-blocking requests) 2. DLM lock time (blocking requests) 3. Inter-request time (again to the DLM) A non-blocking request is one which will complete right away, whatever the state of the DLM lock in question. That currently means any requests when (a) the current state of the lock is exclusive (b) the requested state is either null or unlocked or (c) the "try lock" flag is set. A blocking request covers all the other lock requests. There are two counters. The first is there primarily to show how many lock requests have been made, and thus how much data has gone into the mean/variance calculations. The other counter is counting queueing of holders at the top layer of the glock code. Hopefully that number will be a lot larger than the number of dlm lock requests issued. So why gather these statistics? There are several reasons we'd like to get a better idea of these timings: 1. To be able to better set the glock "min hold time" 2. To spot performance issues more easily 3. To improve the algorithm for selecting resource groups for allocation (to base it on lock wait time, rather than blindly using a "try lock") Due to the smoothing action of the updates, a step change in some input quantity being sampled will only fully be taken into account after 8 samples (or 4 for the variance) and this needs to be carefully considered when interpreting the results. Knowing both the time it takes a lock request to complete and the average time between lock requests for a glock means we can compute the total percentage of the time for which the node is able to use a glock vs. time that the rest of the cluster has its share. That will be very useful when setting the lock min hold time. The other point to remember is that all times are in nanoseconds. Great care has been taken to ensure that we measure exactly the quantities that we want, as accurately as possible. There are always inaccuracies in any measuring system, but I hope this is as accurate as we can reasonably make it. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2012-01-20 10:38:36 +00:00
/* DLM sends a reply to GFS2 */
TRACE_EVENT(gfs2_glock_lock_time,
TP_PROTO(const struct gfs2_glock *gl, s64 tdiff),
TP_ARGS(gl, tdiff),
TP_STRUCT__entry(
__field( dev_t, dev )
__field( u64, glnum )
__field( u32, gltype )
__field( int, status )
__field( char, flags )
__field( s64, tdiff )
__field( s64, srtt )
__field( s64, srttvar )
__field( s64, srttb )
__field( s64, srttvarb )
__field( s64, sirt )
__field( s64, sirtvar )
__field( s64, dcount )
__field( s64, qcount )
),
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->status = gl->gl_lksb.sb_status;
__entry->flags = gl->gl_lksb.sb_flags;
__entry->tdiff = tdiff;
__entry->srtt = gl->gl_stats.stats[GFS2_LKS_SRTT];
__entry->srttvar = gl->gl_stats.stats[GFS2_LKS_SRTTVAR];
__entry->srttb = gl->gl_stats.stats[GFS2_LKS_SRTTB];
__entry->srttvarb = gl->gl_stats.stats[GFS2_LKS_SRTTVARB];
__entry->sirt = gl->gl_stats.stats[GFS2_LKS_SIRT];
__entry->sirtvar = gl->gl_stats.stats[GFS2_LKS_SIRTVAR];
__entry->dcount = gl->gl_stats.stats[GFS2_LKS_DCOUNT];
__entry->qcount = gl->gl_stats.stats[GFS2_LKS_QCOUNT];
),
TP_printk("%u,%u glock %d:%lld status:%d flags:%02x tdiff:%lld srtt:%lld/%lld srttb:%lld/%lld sirt:%lld/%lld dcnt:%lld qcnt:%lld",
MAJOR(__entry->dev), MINOR(__entry->dev), __entry->gltype,
(unsigned long long)__entry->glnum,
__entry->status, __entry->flags,
(long long)__entry->tdiff,
(long long)__entry->srtt,
(long long)__entry->srttvar,
(long long)__entry->srttb,
(long long)__entry->srttvarb,
(long long)__entry->sirt,
(long long)__entry->sirtvar,
(long long)__entry->dcount,
(long long)__entry->qcount)
);
GFS2: Add tracepoints This patch adds the ability to trace various aspects of the GFS2 filesystem. The trace points are divided into three groups, glocks, logging and bmap. These points have been chosen because they allow inspection of the major internal functions of GFS2 and they are also generic enough that they are unlikely to need any major changes as the filesystem evolves. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2009-06-12 07:49:20 +00:00
/* 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)
);
GFS2: Add an AIL writeback tracepoint Add a tracepoint for monitoring writeback of the AIL. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2011-04-18 13:18:38 +00:00
/* Writing back the AIL */
TRACE_EVENT(gfs2_ail_flush,
TP_PROTO(const struct gfs2_sbd *sdp, const struct writeback_control *wbc, int start),
TP_ARGS(sdp, wbc, start),
TP_STRUCT__entry(
__field( dev_t, dev )
__field( int, start )
__field( int, sync_mode )
__field( long, nr_to_write )
),
TP_fast_assign(
__entry->dev = sdp->sd_vfs->s_dev;
__entry->start = start;
__entry->sync_mode = wbc->sync_mode;
__entry->nr_to_write = wbc->nr_to_write;
),
TP_printk("%u,%u ail flush %s %s %ld", MAJOR(__entry->dev),
MINOR(__entry->dev), __entry->start ? "start" : "end",
__entry->sync_mode == WB_SYNC_ALL ? "all" : "none",
__entry->nr_to_write)
);
GFS2: Add tracepoints This patch adds the ability to trace various aspects of the GFS2 filesystem. The trace points are divided into three groups, glocks, logging and bmap. These points have been chosen because they allow inspection of the major internal functions of GFS2 and they are also generic enough that they are unlikely to need any major changes as the filesystem evolves. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2009-06-12 07:49:20 +00:00
/* 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;
__entry->state = bh->b_state;
__entry->len = bh->b_size;
__entry->create = create;
__entry->errno = errno;
),
TP_printk("%u,%u bmap %llu map %llu/%lu to %llu flags:%08lx %s %d",
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->inum,
(unsigned long long)__entry->lblock,
(unsigned long)__entry->len,
(unsigned long long)__entry->pblock,
__entry->state, __entry->create ? "create " : "nocreate",
__entry->errno)
);
/* Keep track of blocks as they are allocated/freed */
TRACE_EVENT(gfs2_block_alloc,
GFS2: Add rgrp information to block_alloc trace point This is a second attempt at a patch that adds rgrp information to the block allocation trace point for GFS2. As suggested, the patch was modified to list the rgrp information _after_ the fields that exist today. Again, the reason for this patch is to allow us to trace and debug problems with the block reservations patch, which is still in the works. We can debug problems with reservations if we can see what block allocations result from the block reservations. It may also be handy in figuring out if there are problems in rgrp free space accounting. In other words, we can use it to track the rgrp and its free space along side the allocations that are taking place. Signed-off-by: Bob Peterson <rpeterso@redhat.com> Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2012-05-09 16:11:35 +00:00
TP_PROTO(const struct gfs2_inode *ip, struct gfs2_rgrpd *rgd,
u64 block, unsigned len, u8 block_state),
GFS2: Add tracepoints This patch adds the ability to trace various aspects of the GFS2 filesystem. The trace points are divided into three groups, glocks, logging and bmap. These points have been chosen because they allow inspection of the major internal functions of GFS2 and they are also generic enough that they are unlikely to need any major changes as the filesystem evolves. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2009-06-12 07:49:20 +00:00
GFS2: Add rgrp information to block_alloc trace point This is a second attempt at a patch that adds rgrp information to the block allocation trace point for GFS2. As suggested, the patch was modified to list the rgrp information _after_ the fields that exist today. Again, the reason for this patch is to allow us to trace and debug problems with the block reservations patch, which is still in the works. We can debug problems with reservations if we can see what block allocations result from the block reservations. It may also be handy in figuring out if there are problems in rgrp free space accounting. In other words, we can use it to track the rgrp and its free space along side the allocations that are taking place. Signed-off-by: Bob Peterson <rpeterso@redhat.com> Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2012-05-09 16:11:35 +00:00
TP_ARGS(ip, rgd, block, len, block_state),
GFS2: Add tracepoints This patch adds the ability to trace various aspects of the GFS2 filesystem. The trace points are divided into three groups, glocks, logging and bmap. These points have been chosen because they allow inspection of the major internal functions of GFS2 and they are also generic enough that they are unlikely to need any major changes as the filesystem evolves. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2009-06-12 07:49:20 +00:00
TP_STRUCT__entry(
__field( dev_t, dev )
__field( u64, start )
__field( u64, inum )
__field( u32, len )
__field( u8, block_state )
GFS2: Add rgrp information to block_alloc trace point This is a second attempt at a patch that adds rgrp information to the block allocation trace point for GFS2. As suggested, the patch was modified to list the rgrp information _after_ the fields that exist today. Again, the reason for this patch is to allow us to trace and debug problems with the block reservations patch, which is still in the works. We can debug problems with reservations if we can see what block allocations result from the block reservations. It may also be handy in figuring out if there are problems in rgrp free space accounting. In other words, we can use it to track the rgrp and its free space along side the allocations that are taking place. Signed-off-by: Bob Peterson <rpeterso@redhat.com> Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2012-05-09 16:11:35 +00:00
__field( u64, rd_addr )
__field( u32, rd_free_clone )
GFS2: Reduce file fragmentation This patch reduces GFS2 file fragmentation by pre-reserving blocks. The resulting improved on disk layout greatly speeds up operations in cases which would have resulted in interlaced allocation of blocks previously. A typical example of this is 10 parallel dd processes, each writing to a file in a common dirctory. The implementation uses an rbtree of reservations attached to each resource group (and each inode). Signed-off-by: Bob Peterson <rpeterso@redhat.com> Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2012-07-19 12:12:40 +00:00
__field( u32, rd_reserved )
GFS2: Add tracepoints This patch adds the ability to trace various aspects of the GFS2 filesystem. The trace points are divided into three groups, glocks, logging and bmap. These points have been chosen because they allow inspection of the major internal functions of GFS2 and they are also generic enough that they are unlikely to need any major changes as the filesystem evolves. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2009-06-12 07:49:20 +00:00
),
TP_fast_assign(
GFS2: don't reference inode's glock during block allocation trace This patch changes the block allocation trace so that it references the rgd's glock rather than the inode's glock. Now that the order of inode creation is switched, this prevents a reference to the glock which may not be set yet. Signed-off-by: Bob Peterson <rpeterso@redhat.com> Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2012-11-16 14:04:16 +00:00
__entry->dev = rgd->rd_gl->gl_sbd->sd_vfs->s_dev;
GFS2: Add tracepoints This patch adds the ability to trace various aspects of the GFS2 filesystem. The trace points are divided into three groups, glocks, logging and bmap. These points have been chosen because they allow inspection of the major internal functions of GFS2 and they are also generic enough that they are unlikely to need any major changes as the filesystem evolves. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2009-06-12 07:49:20 +00:00
__entry->start = block;
__entry->inum = ip->i_no_addr;
__entry->len = len;
__entry->block_state = block_state;
GFS2: Add rgrp information to block_alloc trace point This is a second attempt at a patch that adds rgrp information to the block allocation trace point for GFS2. As suggested, the patch was modified to list the rgrp information _after_ the fields that exist today. Again, the reason for this patch is to allow us to trace and debug problems with the block reservations patch, which is still in the works. We can debug problems with reservations if we can see what block allocations result from the block reservations. It may also be handy in figuring out if there are problems in rgrp free space accounting. In other words, we can use it to track the rgrp and its free space along side the allocations that are taking place. Signed-off-by: Bob Peterson <rpeterso@redhat.com> Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2012-05-09 16:11:35 +00:00
__entry->rd_addr = rgd->rd_addr;
__entry->rd_free_clone = rgd->rd_free_clone;
GFS2: Reduce file fragmentation This patch reduces GFS2 file fragmentation by pre-reserving blocks. The resulting improved on disk layout greatly speeds up operations in cases which would have resulted in interlaced allocation of blocks previously. A typical example of this is 10 parallel dd processes, each writing to a file in a common dirctory. The implementation uses an rbtree of reservations attached to each resource group (and each inode). Signed-off-by: Bob Peterson <rpeterso@redhat.com> Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2012-07-19 12:12:40 +00:00
__entry->rd_reserved = rgd->rd_reserved;
GFS2: Add tracepoints This patch adds the ability to trace various aspects of the GFS2 filesystem. The trace points are divided into three groups, glocks, logging and bmap. These points have been chosen because they allow inspection of the major internal functions of GFS2 and they are also generic enough that they are unlikely to need any major changes as the filesystem evolves. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2009-06-12 07:49:20 +00:00
),
GFS2: Reduce file fragmentation This patch reduces GFS2 file fragmentation by pre-reserving blocks. The resulting improved on disk layout greatly speeds up operations in cases which would have resulted in interlaced allocation of blocks previously. A typical example of this is 10 parallel dd processes, each writing to a file in a common dirctory. The implementation uses an rbtree of reservations attached to each resource group (and each inode). Signed-off-by: Bob Peterson <rpeterso@redhat.com> Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2012-07-19 12:12:40 +00:00
TP_printk("%u,%u bmap %llu alloc %llu/%lu %s rg:%llu rf:%u rr:%lu",
GFS2: Add tracepoints This patch adds the ability to trace various aspects of the GFS2 filesystem. The trace points are divided into three groups, glocks, logging and bmap. These points have been chosen because they allow inspection of the major internal functions of GFS2 and they are also generic enough that they are unlikely to need any major changes as the filesystem evolves. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2009-06-12 07:49:20 +00:00
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->inum,
(unsigned long long)__entry->start,
(unsigned long)__entry->len,
GFS2: Add rgrp information to block_alloc trace point This is a second attempt at a patch that adds rgrp information to the block allocation trace point for GFS2. As suggested, the patch was modified to list the rgrp information _after_ the fields that exist today. Again, the reason for this patch is to allow us to trace and debug problems with the block reservations patch, which is still in the works. We can debug problems with reservations if we can see what block allocations result from the block reservations. It may also be handy in figuring out if there are problems in rgrp free space accounting. In other words, we can use it to track the rgrp and its free space along side the allocations that are taking place. Signed-off-by: Bob Peterson <rpeterso@redhat.com> Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2012-05-09 16:11:35 +00:00
block_state_name(__entry->block_state),
(unsigned long long)__entry->rd_addr,
GFS2: Reduce file fragmentation This patch reduces GFS2 file fragmentation by pre-reserving blocks. The resulting improved on disk layout greatly speeds up operations in cases which would have resulted in interlaced allocation of blocks previously. A typical example of this is 10 parallel dd processes, each writing to a file in a common dirctory. The implementation uses an rbtree of reservations attached to each resource group (and each inode). Signed-off-by: Bob Peterson <rpeterso@redhat.com> Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2012-07-19 12:12:40 +00:00
__entry->rd_free_clone, (unsigned long)__entry->rd_reserved)
);
/* Keep track of multi-block reservations as they are allocated/freed */
TRACE_EVENT(gfs2_rs,
GFS2: Improve block reservation tracing This patch improves the tracing of block reservations by removing some corner cases and also providing more useful detail in the traces. A new field is added to the reservation structure to contain the inode number. This is used since in certain contexts it is not possible to access the inode itself to obtain this information. As a result we can then display the inode number for all tracepoints and also in case we dump the resource group. The "del" tracepoint operation has been removed. This could be called with the reservation rgrp set to NULL. That resulted in not printing the device number, and thus making the information largely useless anyway. Also, the conditional on the rgrp being NULL can then be removed from the tracepoint. After this change, all the block reservation tracepoint calls will be called with the rgrp information. The existing ins,clm and tdel calls to the block reservation tracepoint are sufficient to track the entire life of the block reservation. In gfs2_block_alloc() the error detection is updated to print out the inode number of the problematic inode. This can then be compared against the information in the glock dump,tracepoints, etc. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2012-08-23 14:37:59 +00:00
TP_PROTO(const struct gfs2_blkreserv *rs, u8 func),
GFS2: Reduce file fragmentation This patch reduces GFS2 file fragmentation by pre-reserving blocks. The resulting improved on disk layout greatly speeds up operations in cases which would have resulted in interlaced allocation of blocks previously. A typical example of this is 10 parallel dd processes, each writing to a file in a common dirctory. The implementation uses an rbtree of reservations attached to each resource group (and each inode). Signed-off-by: Bob Peterson <rpeterso@redhat.com> Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2012-07-19 12:12:40 +00:00
GFS2: Improve block reservation tracing This patch improves the tracing of block reservations by removing some corner cases and also providing more useful detail in the traces. A new field is added to the reservation structure to contain the inode number. This is used since in certain contexts it is not possible to access the inode itself to obtain this information. As a result we can then display the inode number for all tracepoints and also in case we dump the resource group. The "del" tracepoint operation has been removed. This could be called with the reservation rgrp set to NULL. That resulted in not printing the device number, and thus making the information largely useless anyway. Also, the conditional on the rgrp being NULL can then be removed from the tracepoint. After this change, all the block reservation tracepoint calls will be called with the rgrp information. The existing ins,clm and tdel calls to the block reservation tracepoint are sufficient to track the entire life of the block reservation. In gfs2_block_alloc() the error detection is updated to print out the inode number of the problematic inode. This can then be compared against the information in the glock dump,tracepoints, etc. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2012-08-23 14:37:59 +00:00
TP_ARGS(rs, func),
GFS2: Reduce file fragmentation This patch reduces GFS2 file fragmentation by pre-reserving blocks. The resulting improved on disk layout greatly speeds up operations in cases which would have resulted in interlaced allocation of blocks previously. A typical example of this is 10 parallel dd processes, each writing to a file in a common dirctory. The implementation uses an rbtree of reservations attached to each resource group (and each inode). Signed-off-by: Bob Peterson <rpeterso@redhat.com> Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2012-07-19 12:12:40 +00:00
TP_STRUCT__entry(
__field( dev_t, dev )
__field( u64, rd_addr )
__field( u32, rd_free_clone )
__field( u32, rd_reserved )
__field( u64, inum )
__field( u64, start )
__field( u32, free )
__field( u8, func )
),
TP_fast_assign(
GFS2: Improve block reservation tracing This patch improves the tracing of block reservations by removing some corner cases and also providing more useful detail in the traces. A new field is added to the reservation structure to contain the inode number. This is used since in certain contexts it is not possible to access the inode itself to obtain this information. As a result we can then display the inode number for all tracepoints and also in case we dump the resource group. The "del" tracepoint operation has been removed. This could be called with the reservation rgrp set to NULL. That resulted in not printing the device number, and thus making the information largely useless anyway. Also, the conditional on the rgrp being NULL can then be removed from the tracepoint. After this change, all the block reservation tracepoint calls will be called with the rgrp information. The existing ins,clm and tdel calls to the block reservation tracepoint are sufficient to track the entire life of the block reservation. In gfs2_block_alloc() the error detection is updated to print out the inode number of the problematic inode. This can then be compared against the information in the glock dump,tracepoints, etc. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2012-08-23 14:37:59 +00:00
__entry->dev = rs->rs_rbm.rgd->rd_sbd->sd_vfs->s_dev;
__entry->rd_addr = rs->rs_rbm.rgd->rd_addr;
__entry->rd_free_clone = rs->rs_rbm.rgd->rd_free_clone;
__entry->rd_reserved = rs->rs_rbm.rgd->rd_reserved;
__entry->inum = rs->rs_inum;
GFS2: Add structure to contain rgrp, bitmap, offset tuple This patch introduces a new structure, gfs2_rbm, which is a tuple of a resource group, a bitmap within the resource group and an offset within that bitmap. This is designed to make manipulating these sets of variables easier. There is also a new helper function which converts this representation back to a disk block address. In addition, the rbtree nodes which are used for the reservations were not being correctly initialised, which is now fixed. Also, the tracing was not passing through the inode where it should have been. That is mostly fixed aside from one corner case. This needs to be revisited since there can also be a NULL rgrp in some cases which results in the device being incorrect in the trace. This is intended to be the first step towards cleaning up some of the allocation code, and some further bug fixes. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2012-07-31 14:21:20 +00:00
__entry->start = gfs2_rbm_to_block(&rs->rs_rbm);
GFS2: Reduce file fragmentation This patch reduces GFS2 file fragmentation by pre-reserving blocks. The resulting improved on disk layout greatly speeds up operations in cases which would have resulted in interlaced allocation of blocks previously. A typical example of this is 10 parallel dd processes, each writing to a file in a common dirctory. The implementation uses an rbtree of reservations attached to each resource group (and each inode). Signed-off-by: Bob Peterson <rpeterso@redhat.com> Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2012-07-19 12:12:40 +00:00
__entry->free = rs->rs_free;
__entry->func = func;
),
GFS2: Improve block reservation tracing This patch improves the tracing of block reservations by removing some corner cases and also providing more useful detail in the traces. A new field is added to the reservation structure to contain the inode number. This is used since in certain contexts it is not possible to access the inode itself to obtain this information. As a result we can then display the inode number for all tracepoints and also in case we dump the resource group. The "del" tracepoint operation has been removed. This could be called with the reservation rgrp set to NULL. That resulted in not printing the device number, and thus making the information largely useless anyway. Also, the conditional on the rgrp being NULL can then be removed from the tracepoint. After this change, all the block reservation tracepoint calls will be called with the rgrp information. The existing ins,clm and tdel calls to the block reservation tracepoint are sufficient to track the entire life of the block reservation. In gfs2_block_alloc() the error detection is updated to print out the inode number of the problematic inode. This can then be compared against the information in the glock dump,tracepoints, etc. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2012-08-23 14:37:59 +00:00
TP_printk("%u,%u bmap %llu resrv %llu rg:%llu rf:%lu rr:%lu %s f:%lu",
GFS2: Reduce file fragmentation This patch reduces GFS2 file fragmentation by pre-reserving blocks. The resulting improved on disk layout greatly speeds up operations in cases which would have resulted in interlaced allocation of blocks previously. A typical example of this is 10 parallel dd processes, each writing to a file in a common dirctory. The implementation uses an rbtree of reservations attached to each resource group (and each inode). Signed-off-by: Bob Peterson <rpeterso@redhat.com> Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2012-07-19 12:12:40 +00:00
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->inum,
(unsigned long long)__entry->start,
(unsigned long long)__entry->rd_addr,
(unsigned long)__entry->rd_free_clone,
(unsigned long)__entry->rd_reserved,
rs_func_name(__entry->func), (unsigned long)__entry->free)
GFS2: Add tracepoints This patch adds the ability to trace various aspects of the GFS2 filesystem. The trace points are divided into three groups, glocks, logging and bmap. These points have been chosen because they allow inspection of the major internal functions of GFS2 and they are also generic enough that they are unlikely to need any major changes as the filesystem evolves. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2009-06-12 07:49:20 +00:00
);
#endif /* _TRACE_GFS2_H */
/* This part must be outside protection */
#undef TRACE_INCLUDE_PATH
#define TRACE_INCLUDE_PATH .
tracing/events: Move TRACE_SYSTEM outside of include guard If TRACE_INCLDUE_FILE is defined, <trace/events/TRACE_INCLUDE_FILE.h> will be included and compiled, otherwise it will be <trace/events/TRACE_SYSTEM.h> So TRACE_SYSTEM should be defined outside of #if proctection, just like TRACE_INCLUDE_FILE. Imaging this scenario: #include <trace/events/foo.h> -> TRACE_SYSTEM == foo ... #include <trace/events/bar.h> -> TRACE_SYSTEM == bar ... #define CREATE_TRACE_POINTS #include <trace/events/foo.h> -> TRACE_SYSTEM == bar !!! and then bar.h will be included and compiled. Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <4A5A9CF1.2010007@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-13 02:33:21 +00:00
#define TRACE_INCLUDE_FILE trace_gfs2
GFS2: Add tracepoints This patch adds the ability to trace various aspects of the GFS2 filesystem. The trace points are divided into three groups, glocks, logging and bmap. These points have been chosen because they allow inspection of the major internal functions of GFS2 and they are also generic enough that they are unlikely to need any major changes as the filesystem evolves. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2009-06-12 07:49:20 +00:00
#include <trace/define_trace.h>
Reference in New Issue Copy Permalink