linux/fs/gfs2/trace_gfs2.h

628 lines
17 KiB
C
Raw Normal View History

License cleanup: add SPDX GPL-2.0 license identifier to files with no license Many source files in the tree are missing licensing information, which makes it harder for compliance tools to determine the correct license. By default all files without license information are under the default license of the kernel, which is GPL version 2. Update the files which contain no license information with the 'GPL-2.0' SPDX license identifier. The SPDX identifier is a legally binding shorthand, which can be used instead of the full boiler plate text. This patch is based on work done by Thomas Gleixner and Kate Stewart and Philippe Ombredanne. How this work was done: Patches were generated and checked against linux-4.14-rc6 for a subset of the use cases: - file had no licensing information it it. - file was a */uapi/* one with no licensing information in it, - file was a */uapi/* one with existing licensing information, Further patches will be generated in subsequent months to fix up cases where non-standard license headers were used, and references to license had to be inferred by heuristics based on keywords. The analysis to determine which SPDX License Identifier to be applied to a file was done in a spreadsheet of side by side results from of the output of two independent scanners (ScanCode & Windriver) producing SPDX tag:value files created by Philippe Ombredanne. Philippe prepared the base worksheet, and did an initial spot review of a few 1000 files. The 4.13 kernel was the starting point of the analysis with 60,537 files assessed. Kate Stewart did a file by file comparison of the scanner results in the spreadsheet to determine which SPDX license identifier(s) to be applied to the file. She confirmed any determination that was not immediately clear with lawyers working with the Linux Foundation. Criteria used to select files for SPDX license identifier tagging was: - Files considered eligible had to be source code files. - Make and config files were included as candidates if they contained >5 lines of source - File already had some variant of a license header in it (even if <5 lines). All documentation files were explicitly excluded. The following heuristics were used to determine which SPDX license identifiers to apply. - when both scanners couldn't find any license traces, file was considered to have no license information in it, and the top level COPYING file license applied. For non */uapi/* files that summary was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 11139 and resulted in the first patch in this series. If that file was a */uapi/* path one, it was "GPL-2.0 WITH Linux-syscall-note" otherwise it was "GPL-2.0". Results of that was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 WITH Linux-syscall-note 930 and resulted in the second patch in this series. - if a file had some form of licensing information in it, and was one of the */uapi/* ones, it was denoted with the Linux-syscall-note if any GPL family license was found in the file or had no licensing in it (per prior point). Results summary: SPDX license identifier # files ---------------------------------------------------|------ GPL-2.0 WITH Linux-syscall-note 270 GPL-2.0+ WITH Linux-syscall-note 169 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) 21 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) 17 LGPL-2.1+ WITH Linux-syscall-note 15 GPL-1.0+ WITH Linux-syscall-note 14 ((GPL-2.0+ WITH Linux-syscall-note) OR BSD-3-Clause) 5 LGPL-2.0+ WITH Linux-syscall-note 4 LGPL-2.1 WITH Linux-syscall-note 3 ((GPL-2.0 WITH Linux-syscall-note) OR MIT) 3 ((GPL-2.0 WITH Linux-syscall-note) AND MIT) 1 and that resulted in the third patch in this series. - when the two scanners agreed on the detected license(s), that became the concluded license(s). - when there was disagreement between the two scanners (one detected a license but the other didn't, or they both detected different licenses) a manual inspection of the file occurred. - In most cases a manual inspection of the information in the file resulted in a clear resolution of the license that should apply (and which scanner probably needed to revisit its heuristics). - When it was not immediately clear, the license identifier was confirmed with lawyers working with the Linux Foundation. - If there was any question as to the appropriate license identifier, the file was flagged for further research and to be revisited later in time. In total, over 70 hours of logged manual review was done on the spreadsheet to determine the SPDX license identifiers to apply to the source files by Kate, Philippe, Thomas and, in some cases, confirmation by lawyers working with the Linux Foundation. Kate also obtained a third independent scan of the 4.13 code base from FOSSology, and compared selected files where the other two scanners disagreed against that SPDX file, to see if there was new insights. The Windriver scanner is based on an older version of FOSSology in part, so they are related. Thomas did random spot checks in about 500 files from the spreadsheets for the uapi headers and agreed with SPDX license identifier in the files he inspected. For the non-uapi files Thomas did random spot checks in about 15000 files. In initial set of patches against 4.14-rc6, 3 files were found to have copy/paste license identifier errors, and have been fixed to reflect the correct identifier. Additionally Philippe spent 10 hours this week doing a detailed manual inspection and review of the 12,461 patched files from the initial patch version early this week with: - a full scancode scan run, collecting the matched texts, detected license ids and scores - reviewing anything where there was a license detected (about 500+ files) to ensure that the applied SPDX license was correct - reviewing anything where there was no detection but the patch license was not GPL-2.0 WITH Linux-syscall-note to ensure that the applied SPDX license was correct This produced a worksheet with 20 files needing minor correction. This worksheet was then exported into 3 different .csv files for the different types of files to be modified. These .csv files were then reviewed by Greg. Thomas wrote a script to parse the csv files and add the proper SPDX tag to the file, in the format that the file expected. This script was further refined by Greg based on the output to detect more types of files automatically and to distinguish between header and source .c files (which need different comment types.) Finally Greg ran the script using the .csv files to generate the patches. Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org> Reviewed-by: Philippe Ombredanne <pombredanne@nexb.com> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2017-11-01 22:07:57 +08:00
/* SPDX-License-Identifier: GPL-2.0 */
#undef TRACE_SYSTEM
#define TRACE_SYSTEM gfs2
#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>
#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 18:38:36 +08:00
#include <linux/ktime.h>
#include <linux/iomap.h>
#include "incore.h"
#include "glock.h"
#include "rgrp.h"
#define dlm_state_name(nn) { DLM_LOCK_##nn, #nn }
#define glock_trace_name(x) __print_symbolic(x, \
dlm_state_name(IV), \
dlm_state_name(NL), \
dlm_state_name(CR), \
dlm_state_name(CW), \
dlm_state_name(PR), \
dlm_state_name(PW), \
dlm_state_name(EX))
#define block_state_name(x) __print_symbolic(x, \
{ GFS2_BLKST_FREE, "free" }, \
{ GFS2_BLKST_USED, "used" }, \
{ GFS2_BLKST_DINODE, "dinode" }, \
{ GFS2_BLKST_UNLINKED, "unlinked" })
#define 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 " })
#define show_glock_flags(flags) __print_flags(flags, "", \
{(1UL << GLF_LOCK), "l" }, \
{(1UL << GLF_DEMOTE), "D" }, \
{(1UL << GLF_PENDING_DEMOTE), "d" }, \
{(1UL << GLF_DEMOTE_IN_PROGRESS), "p" }, \
{(1UL << GLF_DIRTY), "y" }, \
{(1UL << GLF_LFLUSH), "f" }, \
{(1UL << GLF_INVALIDATE_IN_PROGRESS), "i" }, \
{(1UL << GLF_REPLY_PENDING), "r" }, \
{(1UL << GLF_INITIAL), "I" }, \
{(1UL << GLF_FROZEN), "F" }, \
{(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 18:38:36 +08:00
{(1UL << GLF_OBJECT), "o" }, \
{(1UL << GLF_BLOCKING), "b" })
#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_name.ln_sbd->sd_vfs->s_dev;
__entry->glnum = gl->gl_name.ln_number;
__entry->gltype = gl->gl_name.ln_type;
__entry->cur_state = glock_trace_state(gl->gl_state);
__entry->new_state = glock_trace_state(new_state);
__entry->tgt_state = glock_trace_state(gl->gl_target);
__entry->dmt_state = glock_trace_state(gl->gl_demote_state);
__entry->flags = gl->gl_flags | (gl->gl_object ? (1UL<<GLF_OBJECT) : 0);
),
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_name.ln_sbd->sd_vfs->s_dev;
__entry->gltype = gl->gl_name.ln_type;
__entry->glnum = gl->gl_name.ln_number;
__entry->cur_state = glock_trace_state(gl->gl_state);
__entry->flags = gl->gl_flags | (gl->gl_object ? (1UL<<GLF_OBJECT) : 0);
),
TP_printk("%u,%u glock %d:%lld state %s => %s flags:%s",
MAJOR(__entry->dev), MINOR(__entry->dev),
__entry->gltype, (unsigned long long)__entry->glnum,
glock_trace_name(__entry->cur_state),
glock_trace_name(DLM_LOCK_IV),
show_glock_flags(__entry->flags))
);
/* Callback (local or remote) requesting lock demotion */
TRACE_EVENT(gfs2_demote_rq,
TP_PROTO(const struct gfs2_glock *gl, bool remote),
TP_ARGS(gl, remote),
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 )
__field( bool, remote )
),
TP_fast_assign(
__entry->dev = gl->gl_name.ln_sbd->sd_vfs->s_dev;
__entry->gltype = gl->gl_name.ln_type;
__entry->glnum = gl->gl_name.ln_number;
__entry->cur_state = glock_trace_state(gl->gl_state);
__entry->dmt_state = glock_trace_state(gl->gl_demote_state);
__entry->flags = gl->gl_flags | (gl->gl_object ? (1UL<<GLF_OBJECT) : 0);
__entry->remote = remote;
),
TP_printk("%u,%u glock %d:%lld demote %s to %s flags:%s %s",
MAJOR(__entry->dev), MINOR(__entry->dev), __entry->gltype,
(unsigned long long)__entry->glnum,
glock_trace_name(__entry->cur_state),
glock_trace_name(__entry->dmt_state),
show_glock_flags(__entry->flags),
__entry->remote ? "remote" : "local")
);
/* 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_name.ln_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_name.ln_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 18:38:36 +08:00
/* 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( 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 18:38:36 +08:00
),
TP_fast_assign(
__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 18:38:36 +08:00
__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)
);
/* 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_name.ln_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, u32 flags),
TP_ARGS(sdp, start, flags),
TP_STRUCT__entry(
__field( dev_t, dev )
__field( int, start )
__field( u64, log_seq )
__field( u32, flags )
),
TP_fast_assign(
__entry->dev = sdp->sd_vfs->s_dev;
__entry->start = start;
__entry->log_seq = sdp->sd_log_sequence;
__entry->flags = flags;
),
TP_printk("%u,%u log flush %s %llu %llx",
MAJOR(__entry->dev), MINOR(__entry->dev),
__entry->start ? "start" : "end",
(unsigned long long)__entry->log_seq,
(unsigned long long)__entry->flags)
);
/* 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)
);
/* 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)
);
/* 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_name.ln_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)
);
TRACE_EVENT(gfs2_iomap_start,
TP_PROTO(const struct gfs2_inode *ip, loff_t pos, ssize_t length,
u16 flags),
TP_ARGS(ip, pos, length, flags),
TP_STRUCT__entry(
__field( dev_t, dev )
__field( u64, inum )
__field( loff_t, pos )
__field( ssize_t, length )
__field( u16, flags )
),
TP_fast_assign(
__entry->dev = ip->i_gl->gl_name.ln_sbd->sd_vfs->s_dev;
__entry->inum = ip->i_no_addr;
__entry->pos = pos;
__entry->length = length;
__entry->flags = flags;
),
TP_printk("%u,%u bmap %llu iomap start %llu/%lu flags:%08x",
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->inum,
(unsigned long long)__entry->pos,
(unsigned long)__entry->length, (u16)__entry->flags)
);
TRACE_EVENT(gfs2_iomap_end,
TP_PROTO(const struct gfs2_inode *ip, struct iomap *iomap, int ret),
TP_ARGS(ip, iomap, ret),
TP_STRUCT__entry(
__field( dev_t, dev )
__field( u64, inum )
__field( loff_t, offset )
__field( ssize_t, length )
__field( u16, flags )
__field( u16, type )
__field( int, ret )
),
TP_fast_assign(
__entry->dev = ip->i_gl->gl_name.ln_sbd->sd_vfs->s_dev;
__entry->inum = ip->i_no_addr;
__entry->offset = iomap->offset;
__entry->length = iomap->length;
__entry->flags = iomap->flags;
__entry->type = iomap->type;
__entry->ret = ret;
),
TP_printk("%u,%u bmap %llu iomap end %llu/%lu ty:%d flags:%08x rc:%d",
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->inum,
(unsigned long long)__entry->offset,
(unsigned long)__entry->length, (u16)__entry->type,
(u16)__entry->flags, __entry->ret)
);
/* Keep track of blocks as they are allocated/freed */
TRACE_EVENT(gfs2_block_alloc,
TP_PROTO(const struct gfs2_inode *ip, struct gfs2_rgrpd *rgd,
u64 block, unsigned len, u8 block_state),
TP_ARGS(ip, rgd, block, len, block_state),
TP_STRUCT__entry(
__field( dev_t, dev )
__field( u64, start )
__field( u64, inum )
__field( u32, len )
__field( u8, block_state )
__field( u64, rd_addr )
__field( u32, rd_free_clone )
__field( u32, rd_reserved )
),
TP_fast_assign(
__entry->dev = rgd->rd_gl->gl_name.ln_sbd->sd_vfs->s_dev;
__entry->start = block;
__entry->inum = ip->i_no_addr;
__entry->len = len;
__entry->block_state = block_state;
__entry->rd_addr = rgd->rd_addr;
__entry->rd_free_clone = rgd->rd_free_clone;
__entry->rd_reserved = rgd->rd_reserved;
),
TP_printk("%u,%u bmap %llu alloc %llu/%lu %s rg:%llu rf:%u rr:%lu",
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->inum,
(unsigned long long)__entry->start,
(unsigned long)__entry->len,
block_state_name(__entry->block_state),
(unsigned long long)__entry->rd_addr,
__entry->rd_free_clone, (unsigned long)__entry->rd_reserved)
);
/* Keep track of multi-block reservations as they are allocated/freed */
TRACE_EVENT(gfs2_rs,
TP_PROTO(const struct gfs2_blkreserv *rs, u8 func),
TP_ARGS(rs, func),
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(
__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;
__entry->start = gfs2_rbm_to_block(&rs->rs_rbm);
__entry->free = rs->rs_free;
__entry->func = func;
),
TP_printk("%u,%u bmap %llu resrv %llu rg:%llu rf:%lu rr:%lu %s f:%lu",
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)
);
#endif /* _TRACE_GFS2_H */
/* This part must be outside protection */
#undef TRACE_INCLUDE_PATH
#define TRACE_INCLUDE_PATH .
#define TRACE_INCLUDE_FILE trace_gfs2
#include <trace/define_trace.h>