2009-07-13 09:33:21 +07:00
|
|
|
#undef TRACE_SYSTEM
|
|
|
|
|
#define TRACE_SYSTEM gfs2
|
|
|
|
|
|
2009-06-12 14:49:20 +07:00
|
|
|
#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>
|
2011-04-18 20:18:38 +07:00
|
|
|
#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 17:38:36 +07:00
|
|
|
#include <linux/ktime.h>
|
2009-06-12 14:49:20 +07:00
|
|
|
#include "incore.h"
|
|
|
|
|
#include "glock.h"
|
2012-07-19 19:12:40 +07:00
|
|
|
#include "rgrp.h"
|
2009-06-12 14:49:20 +07:00
|
|
|
|
|
|
|
|
#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" })
|
|
|
|
|
|
2012-07-19 19:12:40 +07:00
|
|
|
#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 " })
|
|
|
|
|
|
2009-06-12 14:49:20 +07:00
|
|
|
#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" }, \
|
2010-09-03 15:39:20 +07:00
|
|
|
{(1UL << GLF_FROZEN), "F" }, \
|
2011-04-14 20:09:52 +07:00
|
|
|
{(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 17:38:36 +07:00
|
|
|
{(1UL << GLF_OBJECT), "o" }, \
|
|
|
|
|
{(1UL << GLF_BLOCKING), "b" })
|
2009-06-12 14:49:20 +07:00
|
|
|
|
|
|
|
|
#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(
|
2015-03-16 23:52:05 +07:00
|
|
|
__entry->dev = gl->gl_name.ln_sbd->sd_vfs->s_dev;
|
2009-06-12 14:49:20 +07:00
|
|
|
__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);
|
2011-04-14 20:09:52 +07:00
|
|
|
__entry->flags = gl->gl_flags | (gl->gl_object ? (1UL<<GLF_OBJECT) : 0);
|
2009-06-12 14:49:20 +07:00
|
|
|
),
|
|
|
|
|
|
|
|
|
|
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(
|
2015-03-16 23:52:05 +07:00
|
|
|
__entry->dev = gl->gl_name.ln_sbd->sd_vfs->s_dev;
|
2009-06-12 14:49:20 +07:00
|
|
|
__entry->gltype = gl->gl_name.ln_type;
|
|
|
|
|
__entry->glnum = gl->gl_name.ln_number;
|
|
|
|
|
__entry->cur_state = glock_trace_state(gl->gl_state);
|
2011-04-14 20:09:52 +07:00
|
|
|
__entry->flags = gl->gl_flags | (gl->gl_object ? (1UL<<GLF_OBJECT) : 0);
|
2009-06-12 14:49:20 +07:00
|
|
|
),
|
|
|
|
|
|
|
|
|
|
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,
|
|
|
|
|
|
2013-04-10 16:32:05 +07:00
|
|
|
TP_PROTO(const struct gfs2_glock *gl, bool remote),
|
2009-06-12 14:49:20 +07:00
|
|
|
|
2013-04-10 16:32:05 +07:00
|
|
|
TP_ARGS(gl, remote),
|
2009-06-12 14:49:20 +07:00
|
|
|
|
|
|
|
|
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 )
|
2013-04-10 16:32:05 +07:00
|
|
|
__field( bool, remote )
|
2009-06-12 14:49:20 +07:00
|
|
|
),
|
|
|
|
|
|
|
|
|
|
TP_fast_assign(
|
2015-03-16 23:52:05 +07:00
|
|
|
__entry->dev = gl->gl_name.ln_sbd->sd_vfs->s_dev;
|
2009-06-12 14:49:20 +07:00
|
|
|
__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);
|
2011-04-14 20:09:52 +07:00
|
|
|
__entry->flags = gl->gl_flags | (gl->gl_object ? (1UL<<GLF_OBJECT) : 0);
|
2013-04-10 16:32:05 +07:00
|
|
|
__entry->remote = remote;
|
2009-06-12 14:49:20 +07:00
|
|
|
),
|
|
|
|
|
|
2013-04-10 16:32:05 +07:00
|
|
|
TP_printk("%u,%u glock %d:%lld demote %s to %s flags:%s %s",
|
2009-06-12 14:49:20 +07:00
|
|
|
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),
|
2013-04-10 16:32:05 +07:00
|
|
|
show_glock_flags(__entry->flags),
|
|
|
|
|
__entry->remote ? "remote" : "local")
|
2009-06-12 14:49:20 +07:00
|
|
|
|
|
|
|
|
);
|
|
|
|
|
|
|
|
|
|
/* 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(
|
2015-03-16 23:52:05 +07:00
|
|
|
__entry->dev = gh->gh_gl->gl_name.ln_sbd->sd_vfs->s_dev;
|
2009-06-12 14:49:20 +07:00
|
|
|
__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(
|
2015-03-16 23:52:05 +07:00
|
|
|
__entry->dev = gh->gh_gl->gl_name.ln_sbd->sd_vfs->s_dev;
|
2009-06-12 14:49:20 +07:00
|
|
|
__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 17:38:36 +07:00
|
|
|
/* 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 )
|
2015-08-28 00:51:45 +07:00
|
|
|
__field( u64, srtt )
|
|
|
|
|
__field( u64, srttvar )
|
|
|
|
|
__field( u64, srttb )
|
|
|
|
|
__field( u64, srttvarb )
|
|
|
|
|
__field( u64, sirt )
|
|
|
|
|
__field( u64, sirtvar )
|
|
|
|
|
__field( u64, dcount )
|
|
|
|
|
__field( u64, qcount )
|
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 17:38:36 +07:00
|
|
|
),
|
|
|
|
|
|
|
|
|
|
TP_fast_assign(
|
2015-03-16 23:52:05 +07:00
|
|
|
__entry->dev = gl->gl_name.ln_sbd->sd_vfs->s_dev;
|
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 17:38:36 +07:00
|
|
|
__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)
|
|
|
|
|
);
|
|
|
|
|
|
2009-06-12 14:49:20 +07:00
|
|
|
/* 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(
|
2015-03-16 23:52:05 +07:00
|
|
|
__entry->dev = bd->bd_gl->gl_name.ln_sbd->sd_vfs->s_dev;
|
2009-06-12 14:49:20 +07:00
|
|
|
__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)
|
|
|
|
|
);
|
|
|
|
|
|
2011-04-18 20:18:38 +07:00
|
|
|
/* 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)
|
|
|
|
|
);
|
|
|
|
|
|
2009-06-12 14:49:20 +07:00
|
|
|
/* 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(
|
2015-03-16 23:52:05 +07:00
|
|
|
__entry->dev = ip->i_gl->gl_name.ln_sbd->sd_vfs->s_dev;
|
2009-06-12 14:49:20 +07:00
|
|
|
__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,
|
|
|
|
|
|
2012-05-09 23:11:35 +07:00
|
|
|
TP_PROTO(const struct gfs2_inode *ip, struct gfs2_rgrpd *rgd,
|
|
|
|
|
u64 block, unsigned len, u8 block_state),
|
2009-06-12 14:49:20 +07:00
|
|
|
|
2012-05-09 23:11:35 +07:00
|
|
|
TP_ARGS(ip, rgd, block, len, block_state),
|
2009-06-12 14:49:20 +07:00
|
|
|
|
|
|
|
|
TP_STRUCT__entry(
|
|
|
|
|
__field( dev_t, dev )
|
|
|
|
|
__field( u64, start )
|
|
|
|
|
__field( u64, inum )
|
|
|
|
|
__field( u32, len )
|
|
|
|
|
__field( u8, block_state )
|
2012-05-09 23:11:35 +07:00
|
|
|
__field( u64, rd_addr )
|
|
|
|
|
__field( u32, rd_free_clone )
|
2012-07-19 19:12:40 +07:00
|
|
|
__field( u32, rd_reserved )
|
2009-06-12 14:49:20 +07:00
|
|
|
),
|
|
|
|
|
|
|
|
|
|
TP_fast_assign(
|
2015-03-16 23:52:05 +07:00
|
|
|
__entry->dev = rgd->rd_gl->gl_name.ln_sbd->sd_vfs->s_dev;
|
2009-06-12 14:49:20 +07:00
|
|
|
__entry->start = block;
|
|
|
|
|
__entry->inum = ip->i_no_addr;
|
|
|
|
|
__entry->len = len;
|
|
|
|
|
__entry->block_state = block_state;
|
2012-05-09 23:11:35 +07:00
|
|
|
__entry->rd_addr = rgd->rd_addr;
|
|
|
|
|
__entry->rd_free_clone = rgd->rd_free_clone;
|
2012-07-19 19:12:40 +07:00
|
|
|
__entry->rd_reserved = rgd->rd_reserved;
|
2009-06-12 14:49:20 +07:00
|
|
|
),
|
|
|
|
|
|
2012-07-19 19:12:40 +07:00
|
|
|
TP_printk("%u,%u bmap %llu alloc %llu/%lu %s rg:%llu rf:%u rr:%lu",
|
2009-06-12 14:49:20 +07:00
|
|
|
MAJOR(__entry->dev), MINOR(__entry->dev),
|
|
|
|
|
(unsigned long long)__entry->inum,
|
|
|
|
|
(unsigned long long)__entry->start,
|
|
|
|
|
(unsigned long)__entry->len,
|
2012-05-09 23:11:35 +07:00
|
|
|
block_state_name(__entry->block_state),
|
|
|
|
|
(unsigned long long)__entry->rd_addr,
|
2012-07-19 19:12:40 +07:00
|
|
|
__entry->rd_free_clone, (unsigned long)__entry->rd_reserved)
|
|
|
|
|
);
|
|
|
|
|
|
|
|
|
|
/* Keep track of multi-block reservations as they are allocated/freed */
|
|
|
|
|
TRACE_EVENT(gfs2_rs,
|
|
|
|
|
|
2012-08-23 21:37:59 +07:00
|
|
|
TP_PROTO(const struct gfs2_blkreserv *rs, u8 func),
|
2012-07-19 19:12:40 +07:00
|
|
|
|
2012-08-23 21:37:59 +07:00
|
|
|
TP_ARGS(rs, func),
|
2012-07-19 19:12:40 +07:00
|
|
|
|
|
|
|
|
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(
|
2012-08-23 21:37:59 +07:00
|
|
|
__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;
|
2012-07-31 21:21:20 +07:00
|
|
|
__entry->start = gfs2_rbm_to_block(&rs->rs_rbm);
|
2012-07-19 19:12:40 +07:00
|
|
|
__entry->free = rs->rs_free;
|
|
|
|
|
__entry->func = func;
|
|
|
|
|
),
|
|
|
|
|
|
2012-08-23 21:37:59 +07:00
|
|
|
TP_printk("%u,%u bmap %llu resrv %llu rg:%llu rf:%lu rr:%lu %s f:%lu",
|
2012-07-19 19:12:40 +07:00
|
|
|
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)
|
2009-06-12 14:49:20 +07:00
|
|
|
);
|
|
|
|
|
|
|
|
|
|
#endif /* _TRACE_GFS2_H */
|
|
|
|
|
|
|
|
|
|
/* This part must be outside protection */
|
|
|
|
|
#undef TRACE_INCLUDE_PATH
|
|
|
|
|
#define TRACE_INCLUDE_PATH .
|
2009-07-13 09:33:21 +07:00
|
|
|
#define TRACE_INCLUDE_FILE trace_gfs2
|
2009-06-12 14:49:20 +07:00
|
|
|
#include <trace/define_trace.h>
|
|
|
|
|
|