Script 'mail_helper' called by obssrc Hello community, here is the log from the commit of package collectl for openSUSE:Factory checked in at 2021-05-01 00:46:33 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ Comparing /work/SRC/openSUSE:Factory/collectl (Old) and /work/SRC/openSUSE:Factory/.collectl.new.1947 (New) ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ Package is "collectl" Sat May 1 00:46:33 2021 rev:34 rq:888536 version:4.3.1 Changes: -------- --- /work/SRC/openSUSE:Factory/collectl/collectl.changes 2018-09-11 17:21:05.755061312 +0200 +++ /work/SRC/openSUSE:Factory/.collectl.new.1947/collectl.changes 2021-05-01 00:46:40.183459751 +0200 @@ -1,0 +2,11 @@ +Sat Nov 14 20:21:44 UTC 2020 - Egbert Eich <eich@suse.com> + +- Update to 4.3.1 + * Bugfix: If playing back a file with -P in its name, collectl + incorrectly interprets it as the plot format flag. + * Bugfix: incorrectly dividing $dskWaitR and $dskWaitW by $intSecs + * Added 'm' switch to vmsum to only report VMs whose instance id is + >- this minimum value +- Fix permissions of non-executible script files. + +------------------------------------------------------------------- Old: ---- collectl-4.3.0.src.tar.gz New: ---- collectl-4.3.1.src.tar.gz ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ Other differences: ------------------ ++++++ collectl.spec ++++++ --- /var/tmp/diff_new_pack.fBbRCg/_old 2021-05-01 00:46:40.743457256 +0200 +++ /var/tmp/diff_new_pack.fBbRCg/_new 2021-05-01 00:46:40.743457256 +0200 @@ -1,7 +1,7 @@ # # spec file for package collectl # -# Copyright (c) 2018 SUSE LINUX GmbH, Nuernberg, Germany. +# Copyright (c) 2020 SUSE LLC # # All modifications and additions to the file contributed by third parties # remain the property of their copyright owners, unless otherwise agreed @@ -12,17 +12,17 @@ # license that conforms to the Open Source Definition (Version 1.9) # published by the Open Source Initiative. -# Please submit bugfixes or comments via http://bugs.opensuse.org/ +# Please submit bugfixes or comments via https://bugs.opensuse.org/ # Name: collectl -Version: 4.3.0 +Version: 4.3.1 Release: 0 Summary: System status data collection utility License: Artistic-1.0 AND GPL-2.0-or-later Group: System/Monitoring -Url: http://collectl.sourceforge.net +URL: http://collectl.sourceforge.net Source0: http://sourceforge.net/projects/collectl/files/collectl/%{name}-%{version}/%{name}-%{version}.src.tar.gz Source1: collectl.service Source2: collectl.sysconfig @@ -58,13 +58,13 @@ mkdir -p %{buildroot}/%{_sbindir} ln -s %{_bindir}/collectl %{buildroot}/%{_sbindir}/collectl install -m 644 -D collectl.conf %{buildroot}/%{_sysconfdir}/collectl.conf -install -D formatit.ph %{buildroot}%{_datadir}/%{name}/formatit.ph -install -D lexpr.ph %{buildroot}%{_datadir}/%{name}/lexpr.ph -install -D gexpr.ph %{buildroot}%{_datadir}/%{name}/gexpr.ph -install -D misc.ph %{buildroot}%{_datadir}/%{name}/misc.ph -install -D hello.ph %{buildroot}%{_datadir}/%{name}/hello.ph -install -D graphite.ph %{buildroot}%{_datadir}/%{name}/graphite.ph -install -D vmstat.ph %{buildroot}%{_datadir}/%{name}/vmstat.ph +install -m 644 -D formatit.ph %{buildroot}%{_datadir}/%{name}/formatit.ph +install -m 644 -D lexpr.ph %{buildroot}%{_datadir}/%{name}/lexpr.ph +install -m 644 -D gexpr.ph %{buildroot}%{_datadir}/%{name}/gexpr.ph +install -m 644 -D misc.ph %{buildroot}%{_datadir}/%{name}/misc.ph +install -m 644 -D hello.ph %{buildroot}%{_datadir}/%{name}/hello.ph +install -m 644 -D graphite.ph %{buildroot}%{_datadir}/%{name}/graphite.ph +install -m 644 -D vmstat.ph %{buildroot}%{_datadir}/%{name}/vmstat.ph install -m 644 -D %{SOURCE1} %{buildroot}/%{_unitdir}/collectl.service ln -sf %{_sbindir}/service %{buildroot}%{_sbindir}/rccollectl install -m 644 -D %{SOURCE2} %{buildroot}%{_fillupdir}/sysconfig.collectl ++++++ collectl-4.3.0.src.tar.gz -> collectl-4.3.1.src.tar.gz ++++++ diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/collectl-4.3.0/RELEASE-collectl new/collectl-4.3.1/RELEASE-collectl --- old/collectl-4.3.0/RELEASE-collectl 2017-12-15 16:17:37.000000000 +0100 +++ new/collectl-4.3.1/RELEASE-collectl 2018-11-01 14:47:48.000000000 +0100 @@ -27,6 +27,13 @@ COLLECTL CHANGES +4.3.1 Sept 13, 2018 + - very minor bug. If playing back a file with -P in its name, collectl + incorrectly interprets it as the plot format flag! [thanks laurence] + - incorrectly dividing $dskWaitR and $dskWaitW by $intSecs [thanks Jan] + - added 'm' switch to vmsum to only report VMs whose instance id is + >- this minimum value + 4.3.0 Oct 3, 2017 - disable -sL, should have been done at same time -sl was @@ -141,6 +148,11 @@ COLMUX CHANGES +5.0.0 + - getHeader routine, removing -c/-i need to look for leading spaces + when stipping switches in case a UUID in command string which can + contain -c following by a hex string + 4.9.2 - if ping fails, it still tries to ssh and fails, generating meaninlgess uninitialized variable errors diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/collectl-4.3.0/collectl new/collectl-4.3.1/collectl --- old/collectl-4.3.0/collectl 2017-12-15 16:17:37.000000000 +0100 +++ new/collectl-4.3.1/collectl 2018-11-01 14:47:48.000000000 +0100 @@ -111,8 +111,8 @@ $rootFlag=(!$PcFlag && `whoami`=~/root/) ? 1 : 0; $SrcArch= $Config{"archname"}; -$Version= '4.3.0-1'; -$Copyright='Copyright 2003-2017 Hewlett-Packard Development Company, L.P.'; +$Version= '4.3.1-1'; +$Copyright='Copyright 2003-2018 Hewlett-Packard Development Company, L.P.'; $License= "collectl may be copied only under the terms of either the Artistic License\n"; $License.= "or the GNU General Public License, which may be found in the source kit"; @@ -363,7 +363,7 @@ $plotFlag=0; for (my $i=0; $i<scalar(@ARGV); $i++) { - $plotFlag=1 if $ARGV[$i]=~/-P|--plo/; # see if -P specified for setting --hr below + $plotFlag=1 if $ARGV[$i]=~/^-P|^--plo/; # see if -P specified for setting --hr below if ($ARGV[$i]=~/--to/) { diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/collectl-4.3.0/colmux new/collectl-4.3.1/colmux --- old/collectl-4.3.0/colmux 2017-12-15 16:17:37.000000000 +0100 +++ new/collectl-4.3.1/colmux 2018-11-01 14:47:48.000000000 +0100 @@ -73,8 +73,8 @@ my $Collectl="$BinDir/collectl"; my $Program='colmux'; -my $Version='4.9.2'; -my $Copyright='Copyright 2005-2017 Hewlett-Packard Development Company, L.P.'; +my $Version='5.0.0'; +my $Copyright='Copyright 2005-2018 Hewlett-Packard Development Company, L.P.'; my $License="colmux may be copied only under the terms of either the Artistic License\n"; $License.= "or the GNU General Public License, which may be found in the source kit"; @@ -2140,8 +2140,8 @@ my $command=shift; # in case -c or -i included, they conflict with -showheader - $command=~s/-c\s*\S+//; - $command=~s/-i\s*:*\d+//; + $command=~s/ -c\s*\S+/ /; + $command=~s/ -i\s*:*\d+/ /; my $cmd="$access $Collectl $command --showcolheaders"; $cmd=~s/--fr\S+\s+\S*//; diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/collectl-4.3.0/docs/#Data-verbose.html# new/collectl-4.3.1/docs/#Data-verbose.html# --- old/collectl-4.3.0/docs/#Data-verbose.html# 2017-12-15 16:17:37.000000000 +0100 +++ new/collectl-4.3.1/docs/#Data-verbose.html# 1970-01-01 01:00:00.000000000 +0100 @@ -1,832 +0,0 @@ -<html> -<head> -<link rel=stylesheet href="style.css" type="text/css"> -<title>Verbose Data</title> -</head> - -<body> -<center><h1>Verbose Data</h1></center> -<p> - -Data is reported in this form when either --verbose is used OR if there is at least one -type of data requested that doesn't have a brief form such as any detail data or -ionodes, processes or slabs. Specifying some of the lustre output options with --lustopts -such as B, D and M will also force verbose format. - -<h3>Buddy (Memory Fragmentation) Data, <i>collectl -sb</i></h3> -<p> -<div class=terminal-wide14><pre> -# MEMORY FRAGMENTATION SUMMARY (4K pages) -# 1Pg 2Pgs 4Pgs 8Pgs 16Pgs 32Pgs 64Pgs 128Pgs 256Pgs 512Pgs 1024Pgs -</pre></div> - -This table shows the total number of memory fragments by pagesize in increasing powers of 2 for -all the memory types. -<p> -<p><h3>CPU, <i>collectl -sc</i></h3> - -<div class=terminal-wide14> -<pre> -# CPU SUMMARY (INTR, CTXSW & PROC /sec) -# User Nice Sys Wait IRQ Soft Steal Guest NiceG Idle CPUs Intr Ctxsw Proc RunQ Run Avg1 Avg5 Avg15 RunT BlkT -</pre> -</div> - -These are the percentage of time the system in running is one of the modes, noting that -these are averaged across all CPUs. While User and Sys modes are self-eplanitory, the others -may not be: -<p> -<table> -<tr valign=top><td><b>User</b></td> -<td>Time spent in User mode, not including time spend in "nice" mode.</td></tr> - -<tr valign=top><td><b>Nice</b></td> -<td>Time spent in Nice mode, that is lower priority as adjusted by -the nice command and have the "N" status flag set when examined with "ps".</td></tr> - -<tr valign=top><td><b>Sys</b></td> -<td>This is time spent in "pure" system time.</td></tr> - -<tr valign=top><td><b>Wait</b></td> -<td>Also known as "iowait", this is the time the CPU was idle during an -outstanding disk I/O request. This is not considered to be part of the total or -system times reported in brief mode.</td></tr> - -<tr valign=top><td><b>Irq</b></td> -<td>Time spent processing interrupts and also considered to be part of -the summary system time reported in "brief" mode.</td></tr> - -<tr valign=top><td><b>Soft</b></td> -<td>Time spent processing soft interrupts and also considered to be part -of the summary system time reported in "brief" mode.</td></tr> - -<tr valign=top><td><b>Steal</b></td> -<td>Time spent in other operating systems when running in a virtualized environment</td></tr> - -<tr valign=top><td><b>Guest</b></td> -<td>Time spent running a virtual CPU for guest operating systems under the control of the -Linux kernel, new since 2.6.24</td></tr> - -<tr valign=top><td><b>NiceG</b></td> -<td>Time spent running a niced guest (virtual CPU for guest operating systems under the -control of the Linux kernel), new since 2.6.33</td></tr> -</table> - -<p> -This next set of fields apply to processes -<p> -<table> -<tr><td><b>Proc</b></td><td>Process creations/sec.</li></td></tr> -<tr><td><b>Runq</b></td><td>Number of processes in the run queue.</li></td></tr> -<tr><td><b>Run</b></td><td>Number of processes in the run state.</li></td></tr> -<tr><td><b>Avg1, Avg5, Avg15</b></td><td>Load average over the last 1,5 and 15 minutes.</td></tr> -<tr><td><b>RunT</b></td><td>Total number of process in the run state, not counting collectl itself</td></tr> -<tr><td><b>BlkT</b></td><td>Total number of process blocked, waiting on I/O</td></tr> -</table> - -<p><h3>Disks, <i>collectl -sd</i></h3> -<p> -If you specify filtering with <i>--dskfilt</i>, the disks that match the pattern(s) -will either be included or excluded from the the summary data. However, the data will -<i>still</i> be collected so if recorded to a file can later be viewed. - -<div class=terminal-wide14> -<pre> -# DISK SUMMARY (/sec) -#KBRead RMerged Reads SizeKB KBWrit WMerged Writes SizeKB -</div></pre> - -<table> -<tr><td><b>KBRead</b></td><td>KB read/sec</td></tr> -<tr valign=top><td><b>RMerged</b></td><td>Read requests merged per second when being dequeued.</td></tr> -<tr><td><b>Reads</b></td><td>Number of reads/sec</td></tr> -<tr><td><b>SizeKB</b></td><td>Average read size in KB</td></tr> -<tr><td><b>KBWrite<b></td><td>KB written/sec</td></tr> -<tr valign=top><td><b>WMerged</b></td> -<td>Write requests merged per second when being dequeued.</tr></tr> -<tr><td><b>Writes</b></td><td>Number of writes/sec</td></tr> -<tr><td><b>SizeKB</b></td><td>Average write size in KB</td></tr> -</table> - -<p><h3>Inodes/Filesystem, <i>collectl -si</i></h3> - -<div class=terminal-wide14> -<pre> -# INODE SUMMARY -# Dentries File Handles Inodes -# Number Unused Alloc MaxPct Number - 40585 39442 576 0.17 38348 -</pre></div> - -<table> -<tr><td colspan=2>DCache</td></tr> -<tr><td><b>Dentries Number</b></td><td>Number of entries in directory cache</td</tr> -<tr><td><b>Dentried Unused</b></td><td>Number of unused entries in directory cache</td</tr> -<tr><td><b>Handles Alloc</b></td><td>Number of allocated file handles</td></tr> -<tr><td><b>handles % Max</b></td><td>Percentage of maximum available file handles</td></tr> -<tr><td><b>Inodes Number</b></td><td>Number of inodes in use</td></tr> -</table> - -<p><i>NOTE - as of this writing I'm baffled by the dentry unused field. No matter how -many files and/or directories I create, this number goes up! Sholdn't it go down?</i> - -<p><h3>Infiniband, <i>collectl -sx</i></h3> - -<div class=terminal-wide14> -<pre> -# INFINIBAND SUMMARY (/sec) -# KBIn PktIn SizeIn KBOut PktOut SizeOut Errors -</pre></div> -<table> -<tr><td><b>KBIn</b></td><td>KB received/sec.</td></tr> -<tr><td><b>PktIn</b></td><td>Packets received/sec.</td></tr> -<tr><td><b>SizeIn</b></td><td>Average incoming packet size in KB</td></tr> -<tr><td><b>KBOut</b></td><td>KB transmitted/sec.</td></tr> -<tr><td><b>PktOut</b></td><td>Packets transmitted/sec.</td></tr> -<tr><td><b>SizeOut</b></td><td>Average outgoing packet size in KB</td></tr> -<tr valign=top><td><b>Errs</b></td><td>Count of current errors. Since these -are typically infrequent, it is felt that reporting them as a rate would result -in either not seeing them OR round-off hiding their values.</td></tr> -</table> - -<p><h3>Lustre</h3> - -<p><b>Lustre Client</b>, <i>collectl -sl</i> -<p>There are several formats here controlled by the --lustopts switch. There is -also detail data for these available as well. Specifying -sL results in -data broken out by the file system and --lustopts O further breaks it out by OST. -Also note the average read/write sizes are only reported when --lustopts is <i>not</i> specified. - -<div class=terminal-wide14> -<pre> -# LUSTRE CLIENT SUMMARY -# KBRead Reads SizeKB KBWrite Writes SizeKB -</pre></div> - -<table> -<tr><td><b>KBRead</b></td><td>KB/sec delivered to the client.</td></tr> -<tr><td valign=top><b>Reads</b></td><td>Reads/sec delivered to the client, -not necessarily from the lustre storage servers.</td></tr> -<tr><td><b>SizeKB</b></td><td>Average read size in KB</td></tr> -<tr><td><b>KBWrite</b></td><td>KB Writes/sec delievered to the storage servers.</td></tr> -<tr><td><b>Writes</b></td><td>Writes/sec delievered to the storage servers.</td></tr> -<tr><td><b>SizeKB</b></td><td>Average write size in KB</td></tr> -</table> - -<div class=terminal-wide14> -<pre> -# LUSTRE CLIENT SUMMARY: METADATA -# KBRead Reads KBWrite Writes Open Close GAttr SAttr Seek Fsynk DrtHit DrtMis -</pre></div> - -<table> -<tr><td><b>KBRead</b></td><td>KB/sec delivered to the client.</td></tr> -<tr><td valign=top><b>Reads</b></td><td>Reads/sec delivered to the client, -not necessarily from the lustre storage servers.</td></tr> -<tr><td><b>KBWrite</b></td><td>KB Writes/sec delievered to the storage servers.</td></tr> -<tr><td><b>Writes</b></td><td>Writes/sec delievered to the storage servers.</td></tr> -<tr><td><b>Open</b></td><td>File opens/sec</td></tr> -<tr><td><b>Close</b></td><td>File closes/sec</td></tr> -<tr><td><b>GAttr</b></td><td>getattrs/sec</td></tr> -<tr><td><b>Seek</b></td><td>seeks/sec</td></tr> -<tr><td><b>Fsync</b></td><td>fsyncs/sec</td></tr> -<tr><td><b>DrtHit</b></td><td>dirty hits/sec</td></tr> -<tr><td><b>DrtMis</b></td><td>dirty misses/sec</td></tr> -</table> - -<div class=terminal-wide14> -<pre> -# LUSTRE CLIENT SUMMARY: READAHEAD -# KBRead Reads KBWrite Writes Pend Hits Misses NotCon MisWin FalGrb LckFal Discrd ZFile ZerWin RA2Eof HitMax Wrong -</pre></div> - -<table> -<tr><td><b>KBRead</b></td><td>KB/sec delivered to the client.</td></tr> -<tr><td valign=top><b>Reads</b></td><td>Reads/sec delivered to the client, -not necessarily from the lustre storage servers.</td></tr> -<tr><td><b>KBWrite</b></td><td>KB Writes/sec delievered to the storage servers.</td></tr> -<tr><td><b>Writes</b></td><td>Writes/sec delievered to the storage servers.</td></tr> -<tr><td><b>Pend</b></td><td>Pending issued pages</td></tr> -<tr><td><b>Hits</b></td><td>prefetch cache hits</td></tr> -<tr><td><b>Misses</b></td><td>prefetch cache misses</td></tr> -<tr><td><b>NotCon</b></td><td>The current pages read that were not consecutive with the previous ones./td></tr> -<tr><td><b>MisWin</b></td><td>Miss inside window. The pages that were expected to be in the - prefetch cache but weren't. They were probably - reclaimed due to memory pressure</td></tr> -<tr><td><b>LckFal</b></td><td>Failed grab_cache_pages. Tried to prefetch page but it was locked.</td></tr> -<tr><td><b>Discrd</b></td><td>Read but discarded. Prefetched pages (but not read by applicatin) - have been discarded either becuase of memory pressure or lock - revocation.</td></tr> -<tr><td><b>ZFile</b></td><td>Zero length file.</td></tr> -<tr><td><b>ZerWin</b></td><td>Zero size window.</td></tr> -<tr><td><b>RA2Eof</b></td><td>Read ahead to end of file</td></tr> -<tr><td><b>HitMax</b></td><td>Hit maximum readahead issue. The read-ahead window has grown to the - maximum specified by <i>max_read_ahead_mb</i></td></tr> -</table> - -<div class=terminal-wide14> -<pre> -# LUSTRE CLIENT SUMMARY: RPC-BUFFERS (pages) -#RdK Rds 1K 2K ... WrtK Wrts 1K 2K ... -</pre></div> - -This display shows the size of rpc buffer distribution buckets in K-pages. You can find the -page size for you system in the header (<i>collectl --showheader</i>). -<p> -<table> -<tr><td valign=top><b>RdK</b></td><td>KBs read/sec</td></tr> -<tr><td valign=top><b>Rds</b></td><td>Reads/sec</td></tr> -<tr><td valign=top><b>nK</b></td><td>Number of pages of of this size read</td></tr> -<tr><td valign=top><b>WrtK</b></td><td>KBs written/sec</td></tr> -<tr><td valign=top><b>Wrts</b></td><td>Writes/sec</td></tr> -<tr><td valign=top><b>nK</b></td><td>Number of pages of of this size written</td></tr> -</table> - -<p><b>Lustre Meta-Data Server</b>, <i>collectl -sl</i> -<p>As of Lustre 1.6.5, the data reported for the MDS had changed, breaking out the <i>Reint</i> -data into 5 individual buckets which are the last 5 fields described below. For earlier -versions those 5 fields will be replaced by a single one named <i>Reint</i>. - -<div class=terminal-wide14> -<pre> -# LUSTRE MDS SUMMARY -#Getattr GttrLck StatFS Sync Gxattr Sxattr Connect Disconn Create Link Setattr Rename Unlink -</pre></div> - -<table> -<tr><td valign=top><b>Getattr</b></td><td>Number of getattr calls, for example <i>lfs osts</i>. -Note that this counter is <i>not</i> incremented as the result of <i>ls</i> - see <i>Gxattr</i></td></tr> -<tr><td><b>GttrLck</b></td><td>These are getattrs that also return a lock on the file</td></tr> -<tr><td valign=top><b>StatFS</b></td><td>Number of stat calls, for example <i>df</i> or <i>lfs df</i>. -Note that lustre caches data for up to a second so many calls within a second may only show -up as a single <i>statfs</i></td></tr> -<tr><td><b>Sync</b></td><td>Number of sync calls</td></tr> -<tr><td valign=top><b>Gxattr</b></td><td>Extended attribute get operations, for example <i>getfattr</i>, -<i>getfacl</i> or even <i>ls.</i> Note that the MDS must have been mounted with <i>-o acl</i> -for this counter to be enabled.</td></tr> -<tr><td><b>Sxattr</b></td><td>Extended attribute set operations, for example <i>setfattr</i> or <i>setfacl</i></td></tr> -<tr><td><b>Connect</b></td><td>Client mount operations</td></tr> -<tr><td><b>Disconn</b></td><td>Client umount operations</td></tr> -<tr><td><b>Create</b></td><td>Count of mknod and mkdir operations, also used by NFS servers internally when creating files</td></tr> -<tr><td><b>Link</b></td><td>Hard and symbolic links, for example <i>ln</i></td></tr> -<tr><td><b>Setattr</b></td><td>All operations that modify inode attributes including chmod, chown, touch, etc</td></tr> -<tr><td><b>Rename</b></td><td>File and directory renames, for example <i>mv</i></td></tr> -<tr><td><b>Unlink</b></td><td>File/directory removals, for example <i>rm</i> or <i>rmdir</i></td></tr> -</table> -<p> -The following display is very similar the the RPC buffers in that the sizes of different size -I/O requests are reported. In this case there are requests sent to the disk driver. -Note that this report is only available for HP's SFS. - -<div class=terminal-wide14> -<pre> -# LUSTRE DISK BLOCK LEVEL SUMMARY -#Rds RdK 0.5K 1K ... Wrts WrtK 0.5K 1K ... -</pre></div> - -<table> -<tr><td valign=top><b>Rds</b></td><td>Reads/sec</td></tr> -<tr><td valign=top><b>RdK</b></td><td>KBs read/sec</td></tr> -<tr><td valign=top><b>nK</b></td><td>Number of blocks of of this size read</td></tr> -<tr><td valign=top><b>Wrts</b></td><td>Writes/sec</td></tr> -<tr><td valign=top><b>WrtK</b></td><td>KBs written/sec</td></tr> -<tr><td valign=top><b>nK</b></td><td>Number of blocks of of this size written</td></tr> -</table> - -<p><b>Lustre Object Storage Server</b>, <i>collectl -sl</i> -<div class=terminal-wide14> -<pre> -# LUSTRE OST SUMMARY -# KBRead Reads SizeKB KBWrite Writes SizeKB -</pre></div> - -<table> -<tr><td><b>KBRead</b></td><td>KB/sec read</td></tr> -<tr><td><b>Reads</b></td><td>Reads/sec</td></tr> -<tr><td><b>SizeKB</b></td><td>Average read size in KB</td></tr> -<tr><td><b>KBWrite</b></td><td>KB/sec written</td></tr> -<tr><td><b>Writes</b></td><td>Writes/sec</li> -<tr><td><b>SizeKB</b></td><td>Average write size in KB</td></tr> -</table> - -<p><b>Lustre Object Storage Server</b>, <i>collectl -sl --lustopts B</i> -<p> -As with client data, when you only get read/write average sizes when ---lustopt is <i>not</i> specified. -<div class=terminal-wide14> -<pre> -# LUSTRE OST SUMMARY -#<--------reads-----------|----writes----------------- -#RdK Rds 1K 2K ... WrtK Wrts 1K 2K .... -</pre></div> - -<table> -<tr><td valign=top><b>RdK</b></td><td>KBs read/sec</td></tr> -<tr><td valign=top><b>Rds</b></td><td>Reads/sec</td></tr> -<tr><td valign=top><b>nK</b></td><td>Number of pages of of this size read</td></tr> -<tr><td valign=top><b>WrtK</b></td><td>KBs written/sec</td></tr> -<tr><td valign=top><b>Wrts</b></td><td>Writes/sec</td></tr> -<tr><td valign=top><b>nK</b></td><td>Number of pages of of this size written</td></tr> -</table> - -<p><b>Lustre Object Storage Server</b>, <i>collectl -sl --lustopts D</i> - -<div class=terminal-wide14> -<pre> -# LUSTRE DISK BLOCK LEVEL SUMMARY -#RdK Rds 0.5K 1K ... WrtK Wrts 0.5K 1K ... -</pre></div> - -<table> -<tr><td valign=top><b>RdK</b></td><td>KBs read/sec</td></tr> -<tr><td valign=top><b>Rds</b></td><td>Reads/sec</td></tr> -<tr><td valign=top><b>nK</b></td><td>Number of blocks of of this size read</td></tr> -<tr><td valign=top><b>WrtK</b></td><td>KBs written/sec</td></tr> -<tr><td valign=top><b>Wrts</b></td><td>Writes/sec</td></tr> -<tr><td valign=top><b>nK</b></td><td>Number of blocks of of this size written</td></tr> -</table> - -<p><h3>Memory, <i>collectl -sm</i></h3> - -<div class=terminal-wide14> -<pre> -# MEMORY SUMMARY -#<-------------------------------Physical Memory-------------------------------------><-----------Swap------------><-------Paging------> -# Total Used Free Buff Cached Slab Mapped Anon Commit Locked Inact Total Used Free In Out Fault MajFt In Out -</pre></div> - -<table> -<tr><td><b>Total</b></td> -<td>Total physical memory</td></tr> - -<tr valign=top><td><b>Used</b></td> -<td>Used physical memory. This does not include memory used by the kernel itself.</td></tr> - -<tr valign=top><td><b>Free</b></td> -<td>Unallocated memory</td></tr> - -<tr valign=top><td><b>Buff</b></td> -<td>Memory used for system buffers</td></tr> - -<tr valign=top><td><b>Cached</b></td> -<td>Memory used for caching data beween the kernel and disk, noting direct I/O does not use the cache</td></tr> - -<tr valign=top><td><b>Slab</b></td> -<td>Memory used for slabs, see <i>collectl -sY</i></td></tr> - -<tr valign=top><td><b>Mapped</b></td> -<td>Memory mapped by processes</td></tr> - -<tr valign=top><td><b>Anon</b></td> -<td>Anonymous memory. <i>NOTE - this </i>is included<i> with mapped memory in brief format</i></td></tr> - -<tr valign=top><td><b>Commit</b></td> -<td>According to RedHat: <i>"An estimate of how much RAM you would need to make a 99.99% guarantee -that there never is OOM (out of memory) for this workload."</i></td></tr> - -<tr valign=top><td><b>Locked</b></td> -<td>Locked Memory</td> - -<tr valign=top><td><b>Inactive</b></td> -<td>Inactive pages. On ealier kernels this number is the sum of the clean, dirty -and laundry pages.</td></tr> - -<tr><td><b>Swap Total</b></td> -<td>Total Swap</td></tr> - -<tr><td><b>Swap Used</b></td> -<td>Used Swap</td></tr> - -<tr><td><b>Swap Free</b></td> -<td>Free Swap</td></tr> - -<tr><td><b>Swap In</b></td> -<td>Kb swapped in/sec</td></tr> - -<tr><td><b>Swap Out</b></td> -<td>Kb swapped out/sec</td></tr> - -<tr><td><b>Fault</b></td> -<td>Page faults/sec resolved by not going to disk</td></tr> - -<tr><td><b>MajFt</b></td> -<td>These page faults are resolved by going to disk</td></tr> - -<tr><td><b>Paging In</b></td> -<td>Total number of pages read by block devices</td></tr> - -<tr><td><b>Paging Out</b></td> -<td>Total number of pages written by block devices</td></tr> -</table> -<p> -<center><b><i>Notes</i></b></center> -If you include <i>--memopts R</i>, memory and swap values wil be displayed as changes/sec between intervals -rather than absolute values in addition to page fault information, which is already displayed as rates. -This switch will also honor -on in that the values will not be normalized to a rate but rather displayed -as changes in size per interval. -<p> -If you include <i>--memopts</i> with P or V, collectl will only display Physical or Virtual memory. -The default is PV and will display both. - -<p><h3>Memory, <i>collectl -sm --memopts ps</i></h3> -<p> -The p and s options allow you to display data about page and/or steal and scan information. If you want this data combined with -the standard physical or virtual data you must explicitly request them as well. The columns show how the memory is allocated -for the respective sections. - -<div class=terminal-wide14> -<pre> -# MEMORY SUMMARY -#<---Other---|-------Page Alloc------|------Page Refill-----><------Page Steal-------|-------Scan KSwap------|------Scan Direct-----> -# Free Activ Dma Dma32 Norm Move Dma Dma32 Norm Move Dma Dma32 Norm Move Dma Dma32 Norm Move Dma Dma32 Norm Move - 14M 136K 2 69 13M 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 -</pre></div> - -<p><h3>Network, <i>collectl -sn</i></h3> -<p> - -The entries for error counts in the following are actually the total of several -types of errors. To get individual error counts, you must either include <i>--netopts e</i> -or report details on individual interfaces in plot format by specifying -P. -Transmission errors are categorized by errors, dropped, fifo, collisions and carrier. -Receive errors are broken out for errors, dropped, fifo and framing errors. -<p> -If you specify filtering with <i>--netfilt</i>, the names that match the pattern(s) -will either be included or excluded from the the summary data. However, the data will -<i>still</i> be collected so if recorded to a file can later be viewed. - -<div class=terminal-wide14> -<pre> -# NETWORK SUMMARY (/sec) -# KBIn PktIn SizeIn MultI CmpI ErrsI KBOut PktOut SizeO CmpO ErrsO -</pre></div> - -<table> -<tr><td><b>KBIn</b></td> -<td>Incoming KB/sec</td></tr> - -<tr><td><b>PktIn</b></td> -<td>Incoming packets/sec</td></tr> - -<tr><td><b>SizeI</b></td> -<td>Average incoming packet size in bytes</td></tr> - -<tr><td><b>MultI</b></td> -<td>Incoming multicast packets/sec</td></tr> - -<tr><td><b>CmpI</b></td> -<td>Incoming compressed packets/sec</td></tr> - -<tr valign=top><td><b>ErrsI</b></td> -<td>Total incoming errors/sec. This is an aggregation of incoming error counters. To see explicit -error counters use <i>--netopts e</i></td></tr> - -<tr><td><b>KBOut</b></td> -<td>Outgoing KB/sec</td></tr> - -<tr><td><b>PktOut</b></td> -<td>Outgoing packets/sec</td></tr> - -<tr><td><b>SizeO</b></td> -<td>Average outgoing packet size in bytes</td></tr> - -<tr><td><b>CmpO</b></td> -<td>Outgoing compressed packets/sec</td></tr> - -<tr valign=top><td><b>ErrsO</b></td> -<td>Total outgoing errors/sec. This is an aggregation of outgoing error counters. To see explicit -error counters use <i>--netopts e</i> </td></tr> -</table> - -<p><h3>Network, <i>collectl -sn --netopts e</i></h3> -<p> -This alternative format, which is displayed when you specify <i>--netopts e</i> enumerates -the individual error types. You cannot see both output formats at the same time. - -<div class=terminal-wide14> -<pre> -# NETWORK ERRORS SUMMARY (/sec) -# ErrIn DropIn FifoIn FrameIn ErrOut DropOut FifoOut CollOut CarrOut -</pre></div> - -<table> -<tr><td><b>ErrIn</b></td> -<td>Receive errors/sec detected by the device driver</td></tr> -<tr><td><b>DropIn</b></td> -<td>Receive packets dropped/sec</td></tr> -<tr><td><b>FifoIn</b></td> -<td>Receive packet FIFO buffer errors/sec</td></tr> -<tr><td><b>FrameIn</b></td> -<td>Receive packet framing errors/sec</td></tr> -<tr><td><b>ErrOut</b></td> -<td>Transmit errors/sec detected by the device driver</td></tr> -<tr><td><b>DropOut</b></td> -<td>Transmit packets dropped/sec</td></tr> -<tr><td><b>FifoOut</b></td> -<td>Transmit packet FIFO buffer errors/sec</td></tr> -<tr><td><b>CollOut</b></td> -<td>Transmit collisions/sec detected on the interface</td></tr> -<tr><td><b>CarrOut</b></td> -<td>Transmit packet carrier loss errors detected/sec</td></tr> -</table> - -<p><h3>NFS, <i>collectl -sf</i></h3> -<p> -As of version 3.2.1, by default collectl collects and reports on all versions of nfs data, -both clients and servers. One can limit the types of data reported with <i>--nfsfilt</i> -and if only server or client data has been selected, only that type of data will be -reported as shown in the 2 forms below. When both server and client data are being -reported they will be displayed side by side. As with brief format, if filters have been -selected they will be displayed in the header. - -<div class=terminal-wide14> -<pre> -# NFS SUMMARY (/sec) -#<---------------------------server---------------------------> -# Reads Writes Meta Comm UDP TCP TCPConn BadAuth BadClnt -</pre></div> - -<table> -<tr><td><b>Reads</b></td><td>Total reads/sec</td></tr> -<tr><td><b>Writes</b></td><td>Total writes/sec</td></tr> -<tr><td><b>Meta</b></td><td>Total nfs meta data calls/sec, where meta data is -considered to be any of: lookup, access, getattr, setattr, readdir and readdirplus, -noting that not all types of nfs version report all as V3 clients/servers do.</td></tr> -<tr><td><b>Comm</b></td><td>Total commits/sec</td></tr> -<tr><td><b>UDP</b></td><td>Number of UDP packets/sec</td></tr> -<tr><td><b>TCP</b></td><td>Number of TCP packets/sec</td></tr> -<tr><td><b>TCPConn</b></td><td>Number of TCP connections/sec</td></tr> -<tr><td><b>BadAuth</b></td><td>Number of authentication failures/sec</td></tr> -<tr><td><b>BadClnt</b></td><td>Number of unknown clients/sec</td></tr> -</table> - -<div class=terminal-wide14> -<pre> -# NFS SUMMARY (/sec) -#<----------------client----------------> -# Reads Writes Meta Comm Retrans Authref -</pre></div> - -<table> -<tr><td><b>Reads</b></td><td>Total reads/sec</td></tr> -<tr><td><b>Writes</b></td><td>Total writes/sec</td></tr> -<tr><td><b>Meta</b></td><td>Total nfs meta data calls/sec, where meta data is -considered to be any of: lookup, access, getattr, setattr, readdir and readdirplus, -noting that not all types of nfs version report all as V3 clients/servers do.</td></tr> -<tr><td><b>Comm</b></td><td>Total commits/sec</td></tr> -<tr><td><b>Retrans</b></td><td>Number of retransmissions/sec</td></tr> -<tr><td><b>Authref</b></td><td>Number of authrefreshes/sec</td></tr> -</table - -<p><h3>NFS, <i>collectl -sf -nfsopts C</i></h3> -<p>The data reported for clients is slightly different, specifically the -retrans and authref fields. - -<div class=terminal-wide14> -<pre> -# NFS CLIENT (/sec) -#<----------RPC---------><---NFS V3---> -#CALLS RETRANS AUTHREF READ WRITE -</pre></div> - -<table> -<tr><td><b>Calls</b></td><td>Number of RPC calls/sec</td></tr> -<tr><td><b>Retrans</b></td><td>Retransmitted calls</td></tr> -<tr><td><b>Authref</b></td><td>Authentication failed</td></tr> -<tr><td><b>Read</b></td><td>Number of reads/sec</td></tr> -<tr><td><b>Write</b></td><td>Number of writes/sec</td></tr> -</table> - -<p><h3>Slabs, <i>collectl -sy</i></h3> -<p>As of the 2.6.22 kernel, there is a new slab allocator, called SLUB, and since -there is not a 1:1 mapping between what it reports and the older slab allocator, -the format of this listing will depend on which allocator is being used. The following -format is for the older allocator. - -<div class=terminal-wide14> -<pre> -# SLAB SUMMARY -#<------------Objects------------><--------Slab Allocation-------><--Caches---> -# InUse Bytes Alloc Bytes InUse Bytes Total Bytes InUse Total -</pre></div> - -<table> -<tr><td colspan=2>Objects</td></tr> -<tr valign=top><td><b>InUse</b></td> -<td>Total number of objects that are currently in use.</td></tr> -<tr valign=top><td><b>Bytes</b></td> -<td>Total size of all the objects in use.</td></tr> -<tr valign=top><td><b>Alloc</b></td> -<td>Total number of objects that have been allocated but not necessarily in use.</td></tr> -<tr valign=top><td><b>Bytes</b></td> -<td>Total size of all the allocated objects whether in use or not.</td></tr> - -<tr><td colspan=2>Slab Allocation</td></tr> -<tr valign=top><td><b>InUse</b></td> -<td>Number of slabs that have at least one active object in them.</td></tr> -<tr valign=top><td><b>Bytes</b></td> -<td>Total size of all the slabs.</td></tr> -<tr valign=top><td><b>Total</b></td> -<td>Total number of slabs that have been allocated whether in use or not.</td></tr> -<tr valign=top><td><b> Bytes</b></td> -<td>Total size of all the slabs that have been allocted whether in use or not.</td></tr> - -<tr><td colspan=2>Caches</td></tr> -<tr valign=top><td><b>InUse</b></td> -<td>Not all caches are actully in use. This included only those with non-zero -counts.</td></tr> -<tr valign=top><td><b>Total</b></td> -<td>This is the count of all caches, whether currently in use or not.</td></tr> -</table> - -<p>This is format for the new <i>slub</i> allocator - -<div class=terminal-wide14> -<pre> -# SLAB SUMMARY -#<---Objects---><-Slabs-><-----memory-----> -# In Use Avail Number Used Total -</pre></div> - -One should note that this report summarizes those slabs being monitored. In general -this represents all slabs, but if filering is being used these numbers will only -apply to those slabs that have matched the filter. -<p> -<table> -<tr><td colspan=2>Objects</td></tr> -<tr><td><b>InUse</b></td> -<td>The total number of objects that have been allocated to processes.</td></tr> -<tr valign=top><td><b>Avail</b></td> -<td>The total number of objects that are available in the currently allocated slabs. -This includes those that have already been allocated toprocesses.</td></tr> - -<tr><td colspan=2>Slabs</td></tr> -<tr valign=top><td><b>Number</b></td> -<td>This is the number of individual slabs that have been allocated and -taking physical memory.</td></tr> - -<tr><td colspan=2>Memory</td></tr> -<tr valign=top><td><b>Used</b></td> -<td>Used memory corresponds to those objects that have been allocated to -processes.</td></tr> - -<tr valign=top><td><b>Total</b></td> -<td>Total physical memory allocated to processes. When there is no filtering -in effect, this number will be equal to the Slabs field reported by -sm.</td></tr> -</table> - -<p><h3>Sockets, <i>collectl -ss</i></h3> - -<div class=terminal-wide14> -<pre> -# SOCKET STATISTICS -# <-------------Tcp-------------> Udp Raw <---Frag--> -#Used Inuse Orphan Tw Alloc Mem Inuse Inuse Inuse Mem -</pre></div> - -<table> -<tr><td valign=top><b>Used</b></td><td>Total number if socket allocated which can include additional types such as domain.</td></tr> -<tr><td colspan=2>Tcp</td></tr> -<tr><td><b>Inuse</td><td>Number of TCP connections in use</td></tr> -<tr><td><b>Orphan</td><td>Number of TCP orphaned connections</td></tr> -<tr><td><b>Tw</td><td>Number of connections in <i>TIME_WAIT</i></td></tr> -<tr><td><b>Alloc</td><td>TCP sockets allocated</td></tr> -<tr><td><b>Mem</td><td></td></tr> -<tr><td colspan=2>Udp</td></tr> -<tr><td><b>Inuse</td><td>Number of UCP connections in use</td></tr> -<tr><td colspan=2>Raw</td></tr> -<tr><td><b>Inuse</td><td>Number of RAW connections in use</td></tr> -<tr><td colspan=2>Frag</td></tr> -<tr><td><b>Inuse</td><td></td></tr> -<tr><td><b>Mem</td><td></td></tr> -</table> - -<p><h3>TCP, <i>collectl -st</i></h3> - -These are the counters one sees when running the command <i>netstat -s</i>, whose output is very verbose. Since this -format is an attemt to compress those field names to 6 characters or less, sometime something gets lost in the translation. - -As described in the <a href=Data-brief.html>brief</a> data formats, the actual TCP data displayed is based on the value of -<i>--tcpfilt</i> and like brief data, everything is displayed on a single line which can be quite wide, even more reason to -use this switch, espcially since the default format is over 200 columns wide! The following definitions are based the -value of that filter: - -<p><b>--tcpfilt i</b> -<div class=terminal-wide14> -<pre> -# TCP SUMMARY (/sec)# TCP STACK SUMMARY (/sec) -#<----------------------------------IpPkts-----------------------------------> -# Receiv Delivr Forwrd DiscdI InvAdd Sent DiscrO ReasRq ReasOK FragOK FragCr -</pre></div> - -<table> -<tr><td><b>Receiv</b><td></td><td>- total packets received/sec</td></tr> -<tr><td><b>Delivr</b><td></td><td>- incoming packets delivered/sec</td></tr> -<tr><td><b>Forwrd</b><td></td><td>- packets forwarded</td></tr> -<tr><td><b>DiscdI</b><td></td><td>- discarded incoming packets</td></tr> -<tr><td><b>InvAdd</b><td></td><td>- packets received with invalid addresses</td></tr> -<tr><td><b>Sent</b><td></td><td> - requests sent out/sec</td></tr> -<tr><td><b>DiscrO</b><td></td><td>- discarded outbound requests</td></tr> -<tr><td><b>ReasRq</b><td></td><td>- reassembled requests</td></tr> -<tr><td><b>ReasOK</b><td></td><td>- reassembled OK</td></tr> -<tr><td><b>FragOK</b><td></td><td>- fragments received OK</td></tr> -<tr><td><b>FragCr</b><td></td><td>- fragments created</td></tr> -</table> - -<p><b>--tcpfilt t</b> -<div class=terminal-wide14> -<pre> -# TCP SUMMARY (/sec)# TCP STACK SUMMARY (/sec) -#<---------------------------------Tcp---------------------------------> -# ActOpn PasOpn Failed ResetR Estab SegIn SegOut SegRtn SegBad SegRes -</pre></div> - -<table> -<tr><td><b>ActOpn</b></td><td>- active connections opened/sec</td></tr> -<tr><td><b>PasOpn</b></td><td>- passive connection opened/sec</td></tr> -<tr><td><b>Failed</b></td><td>- failed connection attempts</td></tr> -<tr><td><b>ResetR</b></td><td>- connection resets received</td></tr> -<tr><td><b>Estab</b></td><td> - connections established</td></tr> -<tr><td><b>SegIn</b></td><td> - segments received/sec</td></tr> -<tr><td><b>SegOut</b></td><td>- segments sent out/sec</td></tr> -<tr><td><b>SegRtn</b></td><td>- segments retransmitted</td></tr> -<tr><td><b>SegBad</b></td><td>- bad segments received</td></tr> -<tr><td><b>SegRes</b></td><td>- resets sent</td></tr> -</table> - -<p><b>--tcpfilt u</b> -<div class=terminal-wide14> -<pre> -# TCP SUMMARY (/sec)# TCP STACK SUMMARY (/sec) -#<------------Udp-----------> -# InDgm OutDgm NoPort Errors -</pre></div> - -<table> -<tr><td><b>InDgm</b></td><td>- packets received/sec</tr> -<tr><td><b>OutDgm</b></td><td>- packets sent/sec</tr> -<tr><td><b>NoPort</b></td><td>- packets received to unknown port</tr> -<tr><td><b>Errors</b></td><td>- packet receive errors</tr> -</table> - -<p><b>--tcpfilt c</b> -<div class=terminal-wide14> -<pre> -# TCP SUMMARY (/sec)# TCP STACK SUMMARY (/sec) -#<----------------------------Icmp---------------------------> -# Recvd FailI UnreI EchoI ReplI Trans FailO UnreO EchoO ReplO -</pre></div> - -<table> -<tr><td><b>Recvd</b></td><td>- ICMP messages received</td></tr> -<tr><td><b>FailI</b></td><td>- incoming ICMP messages failed</td></tr> -<tr><td><b>UnreI</b></td><td>- input destination unreachable</td></tr> -<tr><td><b>EchoI</b></td><td>- input echo requests</td></tr> -<tr><td><b>ReplI</b></td><td>- input echo reploes</td></tr> -<tr><td><b>Trans</b></td><td>- ICMP messages sent</td></tr> -<tr><td><b>FailO</b></td><td>- outbound ICMP messages failed</td></tr> -<tr><td><b>UnreO</b></td-><td>- output destination unreachable</td></tr> -<tr><td><b>EchoO</b></td><td> - output echo requests</td></tr> -<tr><td><b>ReplO</b></td><td> - output echo replies</td></tr> -</table> - -<p><b>--tcpfilt T</b> -<div class=terminal-wide14> -<pre> -# TCP SUMMARY (/sec)# TCP STACK SUMMARY (/sec) -#<-------------------------------------------------TcpExt------------------------------------------------> -# FasTim Reject DelAck QikAck PktQue PreQuB HdPdct PurAck HPAcks DsAcks RUData REClos SackS PkLoss FTrans -</pre></div> - -<table> -<tr><td><b>FasTim</b></td><td>- TCP sockets finished time wait in fast timer</td></tr> -<tr><td><b>Reject</b></td><td>- packet rejects in established connections because of timestamp</td></tr> -<tr><td><b>DelAck</b></td><td>- delayed ACKs sent</td></tr> -<tr><td><b>QikAck</b></td><td>- times quick ACK mode activated </td></tr> -<tr><td><b>PktQue</b></td><td>- packets directly queued to recvmsg prequeue</td></tr> -<tr><td><b>PreQuB</b></td><td>- bytes directly received in process context from prequeue</td></tr> -<tr><td><b>HdPdct</b></td><td>- packet headers predicted</td></tr> -<tr><td><b>PurAck</b></td><td>- acknowledgements for received packets not containing data, PureAcks in older versions </td></tr> -<tr><td><b>PurAck</b></td><td>- predicted acknowledgements</td></tr> -<tr><td><b>HPAcks</b></td><td>- DSACKS sent for old packets</td></tr> -<tr><td><b>RUData</b></td><td>- connections reset to do unexpected data</td></tr> -<tr><td><b>REClos</b></td><td>- connections reset due to early close</td></tr> -<tr><td><b>SackS</b></td><td>- SackShiftFallback</td></tr> -<tr><td><b>PkLoss</b></td><td>- Packet Loss</td></tr> -<tr><td><b>FTrans</b></td><td>- Fast Retransmission</td></tr> -</table> - -<table width=100%><tr><td align=right><i>updated Nov 02, 2016</i></td></tr></colgroup></table> - -<script type="text/javascript"> -var gaJsHost = (("https:" == document.location.protocol) ? "https://ssl." : "http://www."); -document.write(unescape("%3Cscript src='" + gaJsHost + "google-analytics.com/ga.js' type='text/javascript'%3E%3C/script%3E")); -</script> -<script type="text/javascript"> -try { -var pageTracker = _gat._getTracker("UA-6408045-1"); -pageTracker._trackPageview(); -} catch(err) {}</script> - -</body> -</html> diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/collectl-4.3.0/docs/markseger,collectl@web.sourceforge.net new/collectl-4.3.1/docs/markseger,collectl@web.sourceforge.net --- old/collectl-4.3.0/docs/markseger,collectl@web.sourceforge.net 2017-12-15 16:17:37.000000000 +0100 +++ new/collectl-4.3.1/docs/markseger,collectl@web.sourceforge.net 1970-01-01 01:00:00.000000000 +0100 @@ -1,134 +0,0 @@ -<html> -<head> -<link rel=stylesheet href="style.css" type="text/css"> -<title>Exporting Data to Graphite</title> -</head> - -<body> -<center><h1>Exporting Data to Graphite</h1></center> -<p> -<h3>Introduction</h3> -<p> -With the release of Collectl Version 3.6.1, you can now send collectl data directly to <a href=http://graphite.wikidot.com> -graphite </a>. For existing collectl users this now provides you with yet another way to store/plot collectl data, whether on -a single system or hundreds. For graphite users who are not yet collectl users, you now have access to literally hundreds -of performance metrics: -<p> -<ul> -<li>Since all collectl instances collect this data at the same time, system noise on -clusters running fine-grained parallel jobs is reduced, though for larger clusters.</li> -<li>You can still log all the data collectl collects locally and only send a subset -to graphite, reducing the load on both graphite and your network.</li> -<li>You can monitor as infrequently as you like and send data to graphite at a -coarser frequency of either of the average, minimum or maximum values over that interval.</li> -<li>The r= switch, something unique to the graphite plugin, can help reduce the instantaneous -load on the graphite server itself.</li> -<li>All this at collectl's low monitoring overhead</li> -</ul> - -<h3>Usage</h3> -<p> -You use this export like any other, the only required option being the address to send the data to as in -the following example: - -<div class=terminal> -<pre> -collectl --export graphite,192.168.1.113 -</pre></div> - -However you should also note that since by design this export does not provide any terminal output, there -are only 2 real ways to make sure it is doing what you expect, the first being to inspect graphite's -whisper storage area for your particular host name and make sure the data you're collecting is in fact -showing up there: - -<div class=terminal> -<pre> -ls /opt/graphite/storage/whisper/poker -cpuload cputotals ctxint disktotals nettotals -</pre></div> - -or to simply run with the debug mask set to 1, which tells the graphite module to echo all the data it is -sending to graphite, noting in this case even though collectl is collecting cpu, disk and network data we're -not sending cpu data to graphite. This is something you might do if logging more data to disk than you are -sending to graphite, which in this case we are: - -<div class=terminal> -<pre> -collectl --export graphite,192.168.1.113,d=1,s=dn -rawtoo -f /var/log/collectl -poker.disktotals.reads 0 1325609789 -poker.disktotals.readkbs 0 1325609789 -poker.disktotals.writes 0 1325609789 -poker.disktotals.writekbs 0 1325609789 -poker.nettotals.kbin 0 1325609789 -poker.nettotals.pktin 1 1325609789 -poker.nettotals.kbout 0 1325609789 -poker.nettotals.pktout 0 1325609789 -</pre></div> - -<b><i>tip</i></b> - if you add 8 to the debug flag, eg <i>d=9</i>, this tells the graphite module not to -actually establish the connection with graphite's carbon listener but to only echo the data that would -have been sent. -<p> -Once you're happy with the switch settings, be sure to update the <i>DaemonCommands</i> in /etc/collectl.conf -and restart the collectl daemon to make them take effect. -<p> -<h3>Switches unique to graphite</h3> -<b>e=escape</b> -<br>When sending data to graphite, collectl prefaces each line item with the hostname. If that name includes -a domain name, extra <i>dots</i> add additional levels the the variable names which may not be desireable. By including -an escape character, those <i>dots</i> will be replaced by that character. -<p> -<b>r=seconds</b> -<br> -By design, collectl calls the export module as soon as the required data has been collected and collection -is synchronized to the nearest milli-seconds across a cluster, this means all instances of collectl will send -their data to graphite at almost exactly the same time. This high burst of data can overwhelm graphite and -so to reduce the load when that is found to be a problem, OR if you just want to smooth out the load you can -use <i>r=seconds</i> which literally means <i>delay sending your data to ganglia by a random number of micro-seconds -<= seconds</i>. -<p> -There is an additional caveat and that is that this stall must have completed by the end of the -current data collection periods and so you're restricted to a maximum delay of the interval less 1 second. -This means if you run collectl with -i1, you can't use -r. However, since most users run collectl with -intervals of 5 or 10 seconds, values of 4 or 9 should be more than sufficient. And if you choose a collection -interval of 30 seconds you may still want to use a value of r closer to 5 or 10 seconds so that the data will -arrive at graphite reasonablly close together. -<p> -For help with what other valid switches are, you can actually get the graphite module itself to tell -you like this: -<div class=terminal> -<pre> -collectl --export graphite,h -</pre></div> - -<h3>Communications</h3> -<p> -Collectl will attempt to establish a TCP connection to the specified address/port, noting the default port is 2003. -If that connection cannot be established, collectl will report an error but <i>not</i> exit! This is because -graphite itself may be down and need to be restarted. - -<div class=terminal> -<pre> -collectl --export graphite,192.168.1.113,d=1,s=dn -Could not create socket to 192.168.1.113:2003. Reason: Connection refused -</pre></div> - -By design when collectl assumes the graphite address is correct and will try to reconnect every monitoring -interval. Further, to avoid generating too many errors, it will silently continue to retry and only report -the connection failure every 100 times, a constant you can modify in the graphite.ph header if you really -care. Once graphite comes back online collectl will again start sending data to it. -<p> -<table width=100%><tr><td align=right><i>updated November 9, 2012</i></td></tr></colgroup></table> - -<script type="text/javascript"> -var gaJsHost = (("https:" == document.location.protocol) ? "https://ssl." : "http://www."); -document.write(unescape("%3Cscript src='" + gaJsHost + "google-analytics.com/ga.js' type='text/javascript'%3E%3C/script%3E")); -</script> -<script type="text/javascript"> -try { -var pageTracker = _gat._getTracker("UA-6408045-1"); -pageTracker._trackPageview(); -} catch(err) {}</script> - -</body> -</html> diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/collectl-4.3.0/formatit.ph new/collectl-4.3.1/formatit.ph --- old/collectl-4.3.0/formatit.ph 2017-12-15 16:17:37.000000000 +0100 +++ new/collectl-4.3.1/formatit.ph 2018-11-01 14:47:48.000000000 +0100 @@ -5326,8 +5326,8 @@ my $i=$disks{$dskName}; $dskRecord=sprintf("%s$SEP%$FS$SEP%$FS$SEP%$FS$SEP%$FS$SEP%$FS$SEP%$FS$SEP%$FS$SEP%$FS$SEP%$FS$SEP%$FS$SEP%$FS$SEP%$FS$SEP%$FS", $dskName, - $dskRead[$i]/$intSecs, $dskReadMrg[$i]/$intSecs, $dskReadKB[$i]/$intSecs, $dskWaitR[$i]/$intSecs, - $dskWrite[$i]/$intSecs, $dskWriteMrg[$i]/$intSecs, $dskWriteKB[$i]/$intSecs, $dskWaitW[$i]/$intSecs, + $dskRead[$i]/$intSecs, $dskReadMrg[$i]/$intSecs, $dskReadKB[$i]/$intSecs, $dskWaitR[$i], + $dskWrite[$i]/$intSecs, $dskWriteMrg[$i]/$intSecs, $dskWriteKB[$i]/$intSecs, $dskWaitW[$i], $dskRqst[$i], $dskQueLen[$i], $dskWait[$i], $dskSvcTime[$i], $dskUtil[$i]); } else diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/collectl-4.3.0/vmsum.ph new/collectl-4.3.1/vmsum.ph --- old/collectl-4.3.0/vmsum.ph 2017-12-15 16:17:37.000000000 +0100 +++ new/collectl-4.3.1/vmsum.ph 2018-11-01 14:47:48.000000000 +0100 @@ -18,7 +18,7 @@ my $program='vmsum V1.0'; my %instances; my $oneMB=1024*1024; -my ($debug, $helpFlag, $versionFlag, $zeroFlag); +my ($debug, $helpFlag, $instMin, $versionFlag, $zeroFlag); my $Ssh= '/usr/bin/ssh'; my $Ping='/bin/ping'; @@ -78,6 +78,7 @@ # for now, if called via lexpr, we report data a different way! $lexprFlag=1 if $export=~/lexpr/; + $instMin=''; $startFlag=0; $uuidFlag=0; $debug=$helpFlag=$versionFlag=$zeroFlag=0; @@ -87,10 +88,11 @@ last if $option eq ''; my ($name, $value)=split(/=/, $option); - error2("valid options are: [adhsStuv]") if $name!~/^[adhsStuvz]$/; + error2("valid options are: [adhmsStuv]") if $name!~/^[adhmsStuvz]$/; $addrFlag=1 if $name eq 'a'; $debug=$value if $name eq 'd'; $helpFlag=1 if $name eq 'h'; + $instMin=$value if $name eq 'm'; $startFlag|=1 if $name eq 's'; $startFlag|=2 if $name eq 'S'; $textDir=$value if $name eq 't'; @@ -113,6 +115,7 @@ error2("--procopts s OR s/S flags but not both") if $startFlag && $procOpts=~/s/i; error2("t= only with lexpr") if $textDir ne '' && !$lexprFlag; error2("'$textDir' doesn't exist or is not a directory") if $textDir ne '' && (!-e $textDir || !-d $textDir); + error2("instance specified by -m must be exactly 8 chars") if $instMin ne '' && length($instMin) != 8; # set up some things in collectl itself (requires DEEP knowledge) setOutputFormat(); @@ -249,8 +252,9 @@ # we'll probably catch the full string in the next cycle (or two). also the command # itself looks different for qemu and kvm $cmd1=~/instance-(\w+)/; - my $instance=$1; - #print "INST: $instance\n"; + my $instance=(defined($1)) ? $1 : ''; + next if $instMin ne '' && $instance lt $instMin; + next if !defined($uuid) || !defined($instance); # only if no network problems, noting problems are rare, we need to find the index