From todd.c.davis@intel.com Mon Sep 23 14:14:01 2002 Received: with ECARTIS (v1.0.0; list pcp); Mon, 23 Sep 2002 14:14:04 -0700 (PDT) Received: from momus.sc.intel.com (momus.sc.intel.com [143.183.152.8]) by oss.sgi.com (8.12.5/8.12.5) with SMTP id g8NLDttG016054; Mon, 23 Sep 2002 14:13:55 -0700 Received: from fmsmsxvs042.fm.intel.com (fmsmsxvs042.fm.intel.com [132.233.42.128]) by momus.sc.intel.com (8.11.6/8.11.6/d: solo.mc,v 1.46 2002/09/23 20:41:22 dmccart Exp $) with SMTP id g8NLDUb25405; Mon, 23 Sep 2002 21:13:40 GMT Received: from fmsmsx28.fm.intel.com ([132.233.42.28]) by fmsmsxvs042.fm.intel.com (NAVGW 2.5.2.11) with SMTP id M2002092314144102918 ; Mon, 23 Sep 2002 14:14:41 -0700 Received: by fmsmsx28.fm.intel.com with Internet Mail Service (5.5.2653.19) id ; Mon, 23 Sep 2002 14:13:19 -0700 Message-ID: <29AD895CE780D511A8870002A50A666D04F90831@hdsmsx106.hd.intel.com> From: "Davis, Todd C" To: "Mike Mason (mmlnx@us.ibm.com)" Cc: "Vincent, Perry G" , "'pcp@oss.sgi.com'" , "'pcp-owner@oss.sgi.com'" Subject: Performance Co-Pilot Date: Mon, 23 Sep 2002 14:19:39 -0700 MIME-Version: 1.0 X-Mailer: Internet Mail Service (5.5.2653.19) Content-Type: multipart/alternative; boundary="----_=_NextPart_001_01C26346.ED368930" X-archive-position: 2 X-ecartis-version: Ecartis v1.0.0 Sender: pcp-bounce@oss.sgi.com Errors-to: pcp-bounce@oss.sgi.com X-original-sender: todd.c.davis@intel.com Precedence: bulk X-list: pcp This message is in MIME format. Since your mail reader does not understand this format, some or all of this message may not be legible. ------_=_NextPart_001_01C26346.ED368930 Content-Type: text/plain Mike, I have started looking at SGI's Performance Co-Pilot for possible use in the Carrier Grade Linux Enhancements, see http://developer.osdl.org/projects/ . I am somewhat concerned with the lack of activity PCP is experiencing both from SGI and in the Linux community. Red Hat has not picked up the project but SUSE apparently has along with the only open source GUI available for PCP. From what few hits search engines have found was the IBM patches that you have posted. IBM does not list Performance Co-Pilot as a project but has these patches available. How does IBM distribute PCP? Do you roll your own RPM? Can one download a PCP tarball and/or RPMs form IBM? My initial investigations into PCP today turned up some problems with PCP on RedHat 7.3. The last release from SGI does not build an RPM on RedHat 7.3 correctly. Also the man pages only work from the command line but khelpcenter and man2html choke on the man pages from SGI. The source builds and installs but some metrics don't appear to be correct. Does IBM or SGI have any test suites to validate the PCP utilities, daemons, and programming interfaces? Is there an active maintainer for PCP? Do you have any insight into SGI's plans for PCP? They apparently GPL'ed the code in hopes of getting Linux community participation that has not materialized. Is this the reason why there is not any mailing list activity, new releases, or announcements since December 2001? Todd C. Davis These are my opinions and absolutely not official opinions of Intel Corp. Telco Systems Development Intel Corporation, Columbia Design Center CBA-2, Suite 100 250 Berry Hill Road Columbia, SC 29210 (803) 461-6108 fax:: (803) 461-6292 mailto:todd.c.davis@intel.com ------_=_NextPart_001_01C26346.ED368930 Content-Type: text/html

Mike,

I have started looking at SGI's Performance Co-Pilot for possible use in the Carrier Grade Linux Enhancements, see http://developer.osdl.org/projects/. I am somewhat concerned with the lack of activity PCP is experiencing both from SGI and in the Linux community. Red Hat has not picked up the project but SUSE apparently has along with the only open source GUI available for PCP. From what few hits search engines have found was the IBM patches that you have posted. IBM does not list Performance Co-Pilot as a project but has these patches available. How does IBM distribute PCP? Do you roll your own RPM? Can one download a PCP tarball and/or RPMs form IBM?

My initial investigations into PCP today turned up some problems with PCP on RedHat 7.3. The last release from SGI does not build an RPM on RedHat 7.3 correctly. Also the man pages only work from the command line but khelpcenter and man2html choke on the man pages from SGI. The source builds and installs but some metrics don't appear to be correct. Does IBM or SGI have any test suites to validate the PCP utilities, daemons, and programming interfaces?

Is there an active maintainer for PCP? Do you have any insight into SGI's plans for PCP? They apparently GPL'ed the code in hopes of getting Linux community participation that has not materialized. Is this the reason why there is not any mailing list activity, new releases, or announcements since December 2001?

Todd C. Davis

These are my opinions and absolutely not official opinions of Intel Corp.

Telco Systems Development

Intel Corporation, Columbia Design Center

CBA-2, Suite 100

250 Berry Hill Road

Columbia, SC 29210

(803) 461-6108

fax:: (803) 461-6292

mailto:todd.c.davis@intel.com

------_=_NextPart_001_01C26346.ED368930-- From dawson@fnal.gov Mon Sep 23 14:42:59 2002 Received: with ECARTIS (v1.0.0; list pcp); Mon, 23 Sep 2002 14:43:00 -0700 (PDT) Received: from fnal.gov (heffalump.fnal.gov [131.225.9.20]) by oss.sgi.com (8.12.5/8.12.5) with SMTP id g8NLgwtG016764; Mon, 23 Sep 2002 14:42:58 -0700 Received: from fnal.gov ([131.225.80.75]) by smtp.fnal.gov (PMDF V6.0-24 #37519) with ESMTP id <0H2W005H9UZLTL@smtp.fnal.gov>; Mon, 23 Sep 2002 16:42:58 -0500 (CDT) Date: Mon, 23 Sep 2002 16:42:56 -0500 From: Troy Dawson Subject: Re: Performance Co-Pilot To: "Davis, Todd C" Cc: "Mike Mason (mmlnx@us.ibm.com)" , "Vincent, Perry G" , "'pcp@oss.sgi.com'" , "'pcp-owner@oss.sgi.com'" Message-id: <3D8F8AE0.3040809@fnal.gov> MIME-version: 1.0 Content-type: text/plain; format=flowed; charset=us-ascii Content-transfer-encoding: 7bit X-Accept-Language: en-us, en User-Agent: Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.1) Gecko/20020826 References: <29AD895CE780D511A8870002A50A666D04F90831@hdsmsx106.hd.intel.com> X-archive-position: 3 X-ecartis-version: Ecartis v1.0.0 Sender: pcp-bounce@oss.sgi.com Errors-to: pcp-bounce@oss.sgi.com X-original-sender: dawson@fnal.gov Precedence: bulk X-list: pcp I am not an official person to answer most of these questions, but I am a user, so I figure I'll just say a few things. Although there might be some metrics that don't work on RedHat 7.3, I haven't found them. (I use what I use, and what I don't, I don't) I recompiled the rpm and it's working fine. As far as lack of noise on this mailing list ... well ... it's working just the way I want it, so I haven't had to say anthing. I do pipe up every now and then. I actually haven't lookad at the archives, but I've gotten 77 messages since January of this year on this mailling list, so there obviously are people here. It's definatly not as much as alot of lists, but definatly not completely dead. Troy Davis, Todd C wrote: > Mike, > > I have started looking at SGI's Performance Co-Pilot for > possible use in the Carrier Grade Linux Enhancements, see > http://developer.osdl.org/projects/. I am somewhat concerned with the > lack of activity PCP is experiencing both from SGI and in the Linux > community. Red Hat has not picked up the project but SUSE apparently has > along with the only open source GUI available for PCP. From what few > hits search engines have found was the IBM patches that you have posted. > IBM does not list Performance Co-Pilot as a project but has these > patches available. How does IBM distribute PCP? Do you roll your own > RPM? Can one download a PCP tarball and/or RPMs form IBM? > > > > My initial investigations into PCP today turned up some problems with > PCP on RedHat 7.3. The last release from SGI does not build an RPM on > RedHat 7.3 correctly. Also the man pages only work from the command line > but khelpcenter and man2html choke on the man pages from SGI. The source > builds and installs but some metrics don't appear to be correct. Does > IBM or SGI have any test suites to validate the PCP utilities, daemons, > and programming interfaces? > > > > Is there an active maintainer for PCP? Do you have any insight into > SGI's plans for PCP? They apparently GPL'ed the code in hopes of getting > Linux community participation that has not materialized. Is this the > reason why there is not any mailing list activity, new releases, or > announcements since December 2001? > > > > Todd C. Davis > > These are my opinions and absolutely **not** official opinions of Intel > Corp. > > Telco Systems Development > > Intel Corporation, Columbia Design Center > > CBA-2, Suite 100 > > 250 Berry Hill Road > > Columbia, SC 29210 > > (803) 461-6108 > > fax:: (803) 461-6292 > > mailto:todd.c.davis@intel.com > > > -- __________________________________________________ Troy Dawson dawson@fnal.gov (630)840-6468 Fermilab ComputingDivision/OSS CSI Group __________________________________________________ From markgw@sgi.com Mon Sep 23 21:55:23 2002 Received: with ECARTIS (v1.0.0; list pcp); Mon, 23 Sep 2002 21:55:25 -0700 (PDT) Received: from deliverator.sgi.com (deliverator.SGI.COM [204.94.214.10] (may be forged)) by oss.sgi.com (8.12.5/8.12.5) with SMTP id g8O4tNtG005191 for ; Mon, 23 Sep 2002 21:55:23 -0700 Received: from larry.melbourne.sgi.com (larry.melbourne.sgi.com [134.14.52.130]) by deliverator.sgi.com (980327.SGI.8.8.8-aspam/980304.SGI-aspam: SGI does not authorize the use of its proprietary systems or networks for unsolicited or bulk email from the Internet.) via SMTP id VAA04623 for ; Mon, 23 Sep 2002 21:55:21 -0700 (PDT) mail_from (markgw@sgi.com) Received: from sherman.melbourne.sgi.com (sherman.melbourne.sgi.com [134.14.55.232]) by larry.melbourne.sgi.com (950413.SGI.8.6.12/950213.SGI.AUTOCF) via ESMTP id OAA29566; Tue, 24 Sep 2002 14:54:01 +1000 Date: Tue, 24 Sep 2002 14:54:01 +1000 (EST) From: Mark Goodwin X-X-Sender: markgw@sherman.melbourne.sgi.com To: Troy Dawson cc: "Davis, Todd C" , "Mike Mason (mmlnx@us.ibm.com)" , "Vincent, Perry G" , "'pcp@oss.sgi.com'" Subject: Re: Performance Co-Pilot In-Reply-To: <3D8F8AE0.3040809@fnal.gov> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII X-archive-position: 4 X-ecartis-version: Ecartis v1.0.0 Sender: pcp-bounce@oss.sgi.com Errors-to: pcp-bounce@oss.sgi.com X-original-sender: markgw@sgi.com Precedence: bulk X-list: pcp On Mon, 23 Sep 2002, Troy Dawson wrote: > . It's definatly not as much as alot of lists, but definatly not > completely dead. I'm the PCP maintainer, and PCP is not dead, but yes there hasn't been a release for quite a while, so maybe I should roll out a new version with some RH7.3 fixes (mostly to work with rpm v4). I've actually been waiting for Mike Mason to send me some patches with support for new per-process metrics and a back-end for libgtop, but he's too busy and we all have other commitments. So I guess I'll ship the new version without Mike's changes. -- Mark From mmlnx@us.ibm.com Tue Sep 24 10:10:36 2002 Received: with ECARTIS (v1.0.0; list pcp); Tue, 24 Sep 2002 10:10:39 -0700 (PDT) Received: from e2.ny.us.ibm.com (e2.ny.us.ibm.com [32.97.182.102]) by oss.sgi.com (8.12.5/8.12.5) with SMTP id g8OHAZtG022910; Tue, 24 Sep 2002 10:10:35 -0700 Received: from northrelay04.pok.ibm.com (northrelay04.pok.ibm.com [9.56.224.206]) by e2.ny.us.ibm.com (8.12.2/8.12.2) with ESMTP id g8OHAS4x281956; Tue, 24 Sep 2002 13:10:28 -0400 Received: from us.ibm.com (sig-9-65-17-33.mts.ibm.com [9.65.17.33]) by northrelay04.pok.ibm.com (8.12.3/NCO/VER6.4) with ESMTP id g8OHAOYa018482; Tue, 24 Sep 2002 13:10:25 -0400 Message-ID: <3D909C83.1040306@us.ibm.com> Date: Tue, 24 Sep 2002 10:10:27 -0700 From: Mike Mason User-Agent: Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.0.1) Gecko/20020823 Netscape/7.0 X-Accept-Language: en-us, en MIME-Version: 1.0 To: "Davis, Todd C" CC: "Vincent, Perry G" , "'pcp@oss.sgi.com'" , "'pcp-owner@oss.sgi.com'" Subject: Re: Performance Co-Pilot References: <29AD895CE780D511A8870002A50A666D04F90831@hdsmsx106.hd.intel.com> Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit X-archive-position: 5 X-ecartis-version: Ecartis v1.0.0 Sender: pcp-bounce@oss.sgi.com Errors-to: pcp-bounce@oss.sgi.com X-original-sender: mmlnx@us.ibm.com Precedence: bulk X-list: pcp Todd, Sorry for not responding sooner. I'm just catching up with my email. Comments below... Davis, Todd C wrote: > Mike, > > I have started looking at SGI's Performance Co-Pilot for > possible use in the Carrier Grade Linux Enhancements, see > http://developer.osdl.org/projects/. I am somewhat concerned with the > lack of activity PCP is experiencing both from SGI and in the Linux > community. Red Hat has not picked up the project but SUSE apparently has I'm also concerned about the lack of activity, but I still think PCP has a role to play for customers. PCP has no kernel components and, I assume, is of little interest to kernel developers so you won't see it mentioned in those forums. On the other hand, I know from past experience that many customers require performance data collection tools like PCP. I don't know of any similar projects for Linux right now, at least not anything with the same breadth of features. As for why only SUSE has picked it up, the SGI folks will have to answer that one. I think it's worth promoting to the other distributions. > along with the only open source GUI available for PCP. From what few > hits search engines have found was the IBM patches that you have posted. > IBM does not list Performance Co-Pilot as a project but has these > patches available. How does IBM distribute PCP? Do you roll your own > RPM? Can one download a PCP tarball and/or RPMs form IBM? Actually, for legal reasons, I don't think IBM distributes any projects where we aren't the maintainers. The projects you see distributed on IBM's OSS site are those that we originated and/or are the maintainers. PCP users have to get PCP from SGI's OSS site. > My initial investigations into PCP today turned up some problems with > PCP on RedHat 7.3. The last release from SGI does not build an RPM on > RedHat 7.3 correctly. Also the man pages only work from the command line > but khelpcenter and man2html choke on the man pages from SGI. The source > builds and installs but some metrics don't appear to be correct. Does All fixable in the next release, I assume. Which metrics don't appear to be correct? > IBM or SGI have any test suites to validate the PCP utilities, daemons, > and programming interfaces? IBM doesn't have any test suites for PCP, but I assume SGI does. > Is there an active maintainer for PCP? Do you have any insight into > SGI's plans for PCP? They apparently GPL'ed the code in hopes of getting > Linux community participation that has not materialized. Is this the > reason why there is not any mailing list activity, new releases, or > announcements since December 2001? There has been a little mailing list activity since December, but last I checked the archive on SGI's site isn't up-to-date. Mike Mason Software Engineer IBM Linux Technology Center, RAS Group Beaverton, Oregon phone: (503) 578-4123 tie line: 775-4123 mmlnx@us.ibm.com fax: (503) 578-3228 From todd.c.davis@intel.com Tue Sep 24 13:27:24 2002 Received: with ECARTIS (v1.0.0; list pcp); Tue, 24 Sep 2002 13:27:28 -0700 (PDT) Received: from momus.sc.intel.com (momus.sc.intel.com [143.183.152.8]) by oss.sgi.com (8.12.5/8.12.5) with SMTP id g8OKROtG025486 for ; Tue, 24 Sep 2002 13:27:24 -0700 Received: from fmsmsxvs042.fm.intel.com (fmsmsxvs042.fm.intel.com [132.233.42.128]) by momus.sc.intel.com (8.11.6/8.11.6/d: solo.mc,v 1.46 2002/09/23 20:41:22 dmccart Exp $) with SMTP id g8OKQxr14453 for ; Tue, 24 Sep 2002 20:27:09 GMT Received: from fmsmsx28.fm.intel.com ([132.233.42.28]) by fmsmsxvs042.fm.intel.com (NAVGW 2.5.2.11) with SMTP id M2002092413282130858 for ; Tue, 24 Sep 2002 13:28:21 -0700 Received: by fmsmsx28.fm.intel.com with Internet Mail Service (5.5.2653.19) id ; Tue, 24 Sep 2002 13:26:59 -0700 Message-ID: <29AD895CE780D511A8870002A50A666D04F90839@hdsmsx106.hd.intel.com> From: "Davis, Todd C" To: "'pcp@oss.sgi.com'" Subject: RedHat 7.3 Performance Co-Pilot Date: Tue, 24 Sep 2002 13:33:16 -0700 MIME-Version: 1.0 X-Mailer: Internet Mail Service (5.5.2653.19) Content-Type: text/plain X-archive-position: 6 X-ecartis-version: Ecartis v1.0.0 Sender: pcp-bounce@oss.sgi.com Errors-to: pcp-bounce@oss.sgi.com X-original-sender: todd.c.davis@intel.com Precedence: bulk X-list: pcp On a Redhat 7.3 system I have encountered the following problems: 1. in man pages the following line causes khelpcenter and man2html to fail: .TH \*(x} I commented out that line and replaced it with: .TH PMIECONF 4 "February 2001" "SGI pcp 2.2" "Performance Co-Pilot" the distributed man pages work using man from the command line but would like to see them work with these other man utilities. (I don't know troff well enough to fix it any better) 2. The HTML tutorial referred to in the man pages is missing. 3. when running "/etc/init.d/pcp start", in rc-proc.sh the following line failed because "chkconfig --add pcp" must be run first: if chkconfig --list "$_flag" 2>&1 | grep $_rl":on" >/dev/null 2>&1 4. When attempting to make an RPM the GNUmakefile in build/rpm encounters the following error: [root@Reliab07 src]# ./Makepkgs == configuring, log is in Logs/configure == Building pcp, log is in Logs/pcp == Packaging pcp, log is in Logs/pcp Packaging failed, see log in Logs/pcp -e's|@pcp_log_dir@|/var/log/pcp|g' \ -e's|@pcp_tmp_dir@|/var/tmp|g' \ -e's|@make@|/usr/bin/make|g' < pcp.spec.in > pcp.spec /bin/rpm -ba --rcfile rpm-4.rc \ --target=i386-pc-linux \ pcp.spec --target=i386-pc-linux: unknown option make[1]: *** [pack_pcp] Error 1 gmake: *** [pack_pcp] Error 2 gmake: Leaving directory `/CGL/rh-72/builds/components/pcp/src/build' [root@Reliab07 src]# (Mark Goodwin posted a fix for this problem in an email Troy Dawson kindly forwarded to me) Todd C. Davis These are my opinions and absolutely not official opinions of Intel Corp. From markgw@sgi.com Tue Sep 24 13:41:05 2002 Received: with ECARTIS (v1.0.0; list pcp); Tue, 24 Sep 2002 13:41:09 -0700 (PDT) Received: from deliverator.sgi.com (deliverator.SGI.COM [204.94.214.10] (may be forged)) by oss.sgi.com (8.12.5/8.12.5) with SMTP id g8OKf4tG025863 for ; Tue, 24 Sep 2002 13:41:05 -0700 Received: from larry.melbourne.sgi.com (larry.melbourne.sgi.com [134.14.52.130]) by deliverator.sgi.com (980327.SGI.8.8.8-aspam/980304.SGI-aspam: SGI does not authorize the use of its proprietary systems or networks for unsolicited or bulk email from the Internet.) via SMTP id NAA03871 for ; Tue, 24 Sep 2002 13:41:03 -0700 (PDT) mail_from (markgw@sgi.com) Received: from sherman.melbourne.sgi.com (sherman.melbourne.sgi.com [134.14.55.232]) by larry.melbourne.sgi.com (950413.SGI.8.6.12/950213.SGI.AUTOCF) via ESMTP id GAA05975; Wed, 25 Sep 2002 06:39:45 +1000 Date: Wed, 25 Sep 2002 06:39:45 +1000 (EST) From: Mark Goodwin X-X-Sender: markgw@sherman.melbourne.sgi.com To: "Davis, Todd C" cc: "'pcp@oss.sgi.com'" Subject: Re: RedHat 7.3 Performance Co-Pilot In-Reply-To: <29AD895CE780D511A8870002A50A666D04F90839@hdsmsx106.hd.intel.com> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII X-archive-position: 7 X-ecartis-version: Ecartis v1.0.0 Sender: pcp-bounce@oss.sgi.com Errors-to: pcp-bounce@oss.sgi.com X-original-sender: markgw@sgi.com Precedence: bulk X-list: pcp Todd, are these the only problems with RH7.3 you know of? Didn't you mention there are some incorrect metrics too? If so, which metrics? thanks -- Mark On Tue, 24 Sep 2002, Davis, Todd C wrote: > On a Redhat 7.3 system I have encountered the following problems: > > 1. in man pages the following line causes khelpcenter and man2html to fail: > .TH \*(x} > I commented out that line and replaced it with: > .TH PMIECONF 4 "February 2001" "SGI pcp 2.2" "Performance Co-Pilot" > the distributed man pages work using man from the command line but would > like to see them work with these other man utilities. > (I don't know troff well enough to fix it any better) > > 2. The HTML tutorial referred to in the man pages is missing. > > 3. when running "/etc/init.d/pcp start", in rc-proc.sh the following line > failed because "chkconfig --add pcp" must be run first: > if chkconfig --list "$_flag" 2>&1 | grep $_rl":on" >/dev/null 2>&1 > > 4. When attempting to make an RPM the GNUmakefile in build/rpm encounters > the following error: > [root@Reliab07 src]# ./Makepkgs > > == configuring, log is in Logs/configure > > == Building pcp, log is in Logs/pcp > > == Packaging pcp, log is in Logs/pcp > Packaging failed, see log in Logs/pcp > -e's|@pcp_log_dir@|/var/log/pcp|g' \ > -e's|@pcp_tmp_dir@|/var/tmp|g' \ > -e's|@make@|/usr/bin/make|g' < pcp.spec.in > pcp.spec > /bin/rpm -ba --rcfile rpm-4.rc \ > --target=i386-pc-linux \ > pcp.spec > --target=i386-pc-linux: unknown option > make[1]: *** [pack_pcp] Error 1 > gmake: *** [pack_pcp] Error 2 > gmake: Leaving directory `/CGL/rh-72/builds/components/pcp/src/build' > [root@Reliab07 src]# > (Mark Goodwin posted a fix for this problem in an email Troy Dawson kindly > forwarded to me) > > > Todd C. Davis > These are my opinions and absolutely not official opinions of Intel Corp. > > > From mmlnx@us.ibm.com Tue Sep 24 14:34:37 2002 Received: with ECARTIS (v1.0.0; list pcp); Tue, 24 Sep 2002 14:34:39 -0700 (PDT) Received: from e35.co.us.ibm.com (e35.co.us.ibm.com [32.97.110.133]) by oss.sgi.com (8.12.5/8.12.5) with SMTP id g8OLYbtG026477 for ; Tue, 24 Sep 2002 14:34:37 -0700 Received: from westrelay01.boulder.ibm.com (westrelay01.boulder.ibm.com [9.17.194.22]) by e35.co.us.ibm.com (8.12.2/8.12.2) with ESMTP id g8OLYVwM029018; Tue, 24 Sep 2002 17:34:31 -0400 Received: from us.ibm.com (sig-9-65-10-198.mts.ibm.com [9.65.10.198]) by westrelay01.boulder.ibm.com (8.12.3/NCO/VER6.4) with ESMTP id g8OLYTTn082636; Tue, 24 Sep 2002 15:34:29 -0600 Message-ID: <3D90DA07.5090405@us.ibm.com> Date: Tue, 24 Sep 2002 14:32:55 -0700 From: Mike Mason User-Agent: Mozilla/5.0 (X11; U; Linux i686; en-US; rv:0.9.4.1) Gecko/20020314 Netscape6/6.2.2 X-Accept-Language: en-us MIME-Version: 1.0 To: Mark Goodwin , pcp@oss.sgi.com Subject: PCP patch for top/libgtop conversion Content-Type: multipart/mixed; boundary="------------020200090508080803060405" X-archive-position: 8 X-ecartis-version: Ecartis v1.0.0 Sender: pcp-bounce@oss.sgi.com Errors-to: pcp-bounce@oss.sgi.com X-original-sender: mmlnx@us.ibm.com Precedence: bulk X-list: pcp This is a multi-part message in MIME format. --------------020200090508080803060405 Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit Mark, Here's my long awaited patch. As you know, most of the changes were made to support conversion of top and libgtop to use PCP. I also made a few small bug fixes, some in comments. I added some "this code provided by ..." comments which you can modify or remove if you'd like. I'm not sure how much of this type of comment you want to include. The patch should be applied to the 2.2.2 source currently available from the SGI PCP site. The changes to top and libgtop to use PCP are essentially done, but I don't yet have a way to release them. We go through a formal process at IBM to get permission to contribute to outside projects. I don't have permission to contribute to procps or libgtop. I'll work on that. Please let me know of any changes you want me to make. Regards, Mike Here's what was added and/or modified: (new) Total idle time since boot kernel.all.idletime (new) current # of user sessions kernel.all.nusers (new) Last pid used kernel.all.lastpid (new) Filesystem blocksize from statfs() filesys.blocksize (new) Filesystem free space available to non-superusers from statfs() filesys.avail (modified) Per process command name proc.psinfo.cmd (new) Per process command line from /proc//cmdline proc.psinfo.psargs (new) Per process CPU number from /proc//stat proc.psinfo.processor (new) Per process wait channel symbol name proc.psinfo.wchan_s (new) Per process signal info from /proc//status proc.psinfo.signal_s proc.psinfo.blocked_s proc.psinfo.sigignore_s proc.psinfo.sigcatch_s (new) Per process map info from /proc//maps proc.memory.maps (new) Per process memory info from /proc//status proc.memory.vmsize proc.memory.vmlock proc.memory.vmrss proc.memory.vmdata proc.memory.vmstack proc.memory.vmexe proc.memory.vmlib (new) Per process user and group ids from /proc//status proc.id.uid proc.id.euid proc.id.suid proc.id.fsuid proc.id.gid proc.id.egid proc.id.sgid proc.id.fsgid (new) Per process user and group ids converted to names proc.id.uid_nm proc.id.euid_nm proc.id.suid_nm proc.id.fsuid_nm proc.id.gid_nm proc.id.egid_nm proc.id.sgid_nm proc.id.fsgid_nm (new) Semaphore limits from semctl()(needed by libgtop) ipc.sem.max_semmap ipc.sem.max_semid ipc.sem.max_sem ipc.sem.num_undo ipc.sem.max_perid ipc.sem.max_ops ipc.sem.max_undoent ipc.sem.sz_semundo ipc.sem.max_semval ipc.sem.max_exit (new) Message queue limits from msgctl()(needed by libgtop) ipc.msg.sz_pool ipc.msg.mapent ipc.msg.max_msgsz ipc.msg.max_defmsgq ipc.msg.max_msgqid ipc.msg.max_msgseg ipc.msg.num_smsghdr ipc.msg.max_seg (new) Shared memory limits from shmctl() (needed by libgtop) ipc.shm.max_segsz ipc.shm.min_segsz ipc.shm.max_seg ipc.shm.max_segproc ipc.shm.max_shmsys -- Mike Mason IBM Linux Technology Center, RAS Group Beaverton, OR, USA mmlnx@us.ibm.com (503) 578-4123 --------------020200090508080803060405 Content-Type: application/octet-stream; name="pcp-2.2.2.patch.gz" Content-Transfer-Encoding: base64 Content-Disposition: attachment; filename="pcp-2.2.2.patch.gz" H4sICIy5kD0AA3BjcC0yLjIuMi5wYXRjaADsPGtX28iSn+FXdNiTxMbCYENekOSGISTjM0A4 QCabnZnjK0ttS4Neo5Z4zE7++1ZVd0uth8FmMud+WeZekFvV1dX1rup2XH86ZRt5esISJ9kY 9uG/TZE6m0no2mIz8KP8ZvPjyefQvuRTP+AlVP/40/vRh9Hh+7vAVzc2NhZDvHIcR+w9d9hg iw1e7D4b7m69ZMOtrcFqr9dbclXCdc4TNtxmg53dwbPdbcI1XH33jm3svLAGO6yHf16wd+9W 2coKY1l2G9kh7zssSWNnHPFsLGLnUmR2psfSPPoDnn+VE0qwKEw0iHCEr5+nYnwzFbUJMJjY Mz7JpxrMSXI/msbmwpmT0LSNYpoI7ImEWu21DDLBw3Hgh36G64ViVn4QnvHmV2N2nmQ+7fdS 3IbwZxX++/HD6OjwfGXlDXPj0PajvqdWQi6o55CHtKj6GMS2a1/N4GOdLy6/0kB+lPE0hRUF jKCAxC0+iWs7kVD1uWni6LmJ7xaPdpr5mR9HomVKIS3PkJZXE1N1GknLq0jLa4jJqwhCS8ur SsurScQzGL3oFC0dQ5aeKUvPlKVXESIsh+I7Oj87IAkykKDHg4SlcZyNyTzko5/6NwDpLmDz NH8Bs0O4e6wcQZrmPRgsZd4Fkrl2vf1saD1nPfwj7fodu+RpxIO+HQR9EEM/8h3OsjizA0aP ueApOzj9zJCLLORZ6jtsmsYh20T2bqI+sWmcMkCAcKIFJ6iyQolPfxOZ7waaQHpcCl2vgi7C zQkW5eEENhlP5WYFFwINiAEjgd6Mh0gF6OR1nF72yU6ntsPhqT+5zbjQr1jKnSv4ZbtMjhuU AMgmmDFLAL8GLzDNRZ/YziXP2hbQb/72EuBz4rRtBfVi4QUoamztoHbtbD2zXirt0p5smnIK O4KdlNyOQAixY2fcBUSxy4nlYZxHOKJmKvZrPPTW9VMaUOKRU1gSAzWVNXMQO1Dr8CgDT4VL lkhhRRQ3aoSGnwToH/0/OTvHXwDObcdjNNxOGev8gJLumljsK9sP2IVUd5ATZ7h30FgWxdGG yIEgqXZzMP40kShhI9r5E4LEuxW+g0hhVOIk9CZgwKNZ5tVAcUcmUGjf0Dj89cM8lEBqZkdA gGe2qGMEWsnFdKWcn22B++jtPNsu5IzRCHZ1xdM+6AY4byeOIubkYR7YmX+lLRZ4KqHY2ekB uzg4LTQpsG9hFGdxB+MXaOEfORcZuQDUv36EvwXIDcwaBBrxODdtF9+C5fJyQiIoakB01C/B Y4Au+FOfp6sbNShhpzMBBIShHblMgC+JZijXFiBSrLshndAtIDBpqhMlcLAgCx0VN4gDOaDE RWfQ7fbBm4NIAhFLBBi0la8T/cZeabN2ytEemnuuQ8/SpACbpXGemMAk6ZcvyKJfDazhUIm6 ss2ItMchA0QhoJ3RUAx6bmfSj07JAfMbH3Xd8fzABQLrqPD1WPgzcAos8zi7soOco5XiB/Ml EBe4pElZmjsZy2xxOVbP6OwRXm2qvobKYEkiiAHULUvjAFR7htktA42HmGcxwLL2rzXmT9Fm eV0CJbJ+Q0HkujA/sEUmY1NJDrsGywL5RbheHNUnXzueHY1FQZ0dMX6FksRdXXs++CITmQ96 E3CeILIOkDoJ7OjSqoOo5bpA6oUHnyX3Is5dwWyHoMA12bRo4APN5FhxRUCCrn61Z7sgLyE2 sngD8uBJHEgKs9SOREAy7rMRsqqKZLUHy5E3tCcBl4QpVEhYkvqR9Pzg92y3zy48XiBY7REZ YQ64QjtTO3fylDT7iLI1GchBNWwnC25pf6B73E4BOrHBaWllqG4NiQI2gNTja7EL+eTmBNK+ zXNyv+Ack41/57S/jfTfLW9xKPAnm2Hs5uC0N0vgGlAuUkrQZGpWfWd+qvkF0nFQgoRHLkpW DgjggsBwq9wN7g1ihRGdX4Plv6WMJ5fxyMRKIYy7gFY9fR+0gATQxCkHxPLh+yF2UOqA17Hz mZc9EK02fyjI4vS2T7G9Gj+u/DTLMVKqiK8sxwK1coKcJEA+LUMdZujN0d0o15OnvF9fIxX1 EAUKT171+60hPPDwtVXsUPtgCcQICFNRsAEyN+WCfAznYBZpGTGZ9PWvKHt7Ntixtgemr1er gtYvsDmEsmF5B/I5kFaSaBp4uW+Qn8xy6ku4drY4/xhA22DwsxBe3oUURHx7H7cyD0oFDxzD hHPMy1yMgXdR3qsuAjsVSoAl0nL7hUOuam5DcRFNHfVVSBuXCZTWV7XC/RZVIKEsVln/w7Gg eAqBPBwNia42HbJil3w2vVwCGbyArc3DJt8ugY7f8LnIMIXXGg5wTi5FTsq+jCz8ydwlJHof rPJ+hL7bzyHhg4ItkLXr6H1Tp+Qkcw7HSXw6xUz7ii8zU+BMYV8BrUvMmtI0o8hZYu5M70/m pwtucFbZ4DJTxazY4TLTpjTP2OIyk4E74yg0xEgpxcRGlaBKaHnxIr6ahKtIHyx+xGxoQBXr w1QDUda1o4r3wbpT8FXKo4Wxy+pVlbNtaB+ueCVv2/A+UCtr3G3DvJTeFvGV2sdYX5APnFeX FwAd5HgeMSjrc94tsw9Llb9Pz55ifExEdQGdsd5b91NHJyr66D6uSQVSscD71gWKIur+FTRo gfFcY8QE6uWLgbXNeq8Gz62h7q6Cd+8X/Wt8EH1b6kaJXw3QW2waQGUkkB7qPjnwi8/BJFMC 1awt0C2PB7NPMYZij1rt5s7xBe6QUOBL1C6fej1YvtyM4S/kLKxoJpVzIUGgKAazMUsDKA8K BMyJVGCDMSjcOv2+NTo9GI9OPnyy+v1ut2UF8KxN/CXKsmchlkZ9F2KZrqm23KJ4Ac84j9zY 7CrjxyKbfxBWpBbkczcjBLVmzS7SMujjRLQgN9o4CfXGwzgBXQqC5ZAjCzBjbC5AzNG6kpRV yeL4xZ8oSMlkVSGobhAeE9H4slpxhRWhobKSaNmRWgoX9q2Y7f6OfQyMDPjxAehCMcNtJnFc VqohMAmrRhoElbr0g1ieO0iUMOc+lLBBFMocm9ULlBa7EMqbMfwVf5btZUVviRCwL03ozdjl U3j8g8FfOw+yO/BTgFma5D9ajauKs+lplmAJnxXYVNEqaV8YEboWAQ+em5rmr85AFGqP2+7S 5BFtc/euqF0Qp/C0GVW0QHYjKhuv6QFMvBevH2m8fvQ98c7lQRV/i+9eGDn6tQUWaHGBCy7h hXi6qlcoOxxqBVVnlhvAxIXi+z3LLHQUrm5ILHBILSHvOQ6XQCtfgG48EN8esMHz3a0t+B8b vHr+atEDcYXmAkyXjsR32GCw++zl7sA4Et+ytlhvYO0M6Cirt7m+2mPr7CBOblMfO48dp0vA 7NwPfAec+McU4oLvQN46ipw+Y/sQDM8QVLAzTqdbbp9w0K8L1XybpXaIvWd5cBdPs2uQyh67 jXMIp1iKuD52hiY5HgRl2AXcjFPZiAKhZYQLYhmXLW3IcUM6WLkCW8fTsiF+wDcfTz6zjzyC qB2w03wCJLMj3+GRwGM9wpLgqPDK7tYHJOlckcQ+gN64sqs/fxclsa4+ovEgVZBtNCD/Os4D wE/F5TQPLAaghOjL6OLHT58v2P7JV/Zl/+xs/+Ti6x41JeM8o+MOQuaHSYD9N6AohZT8FnZH 048Pzw5+hDn7P4yORhdf8aDmw+ji5PD8nH34dMb22en+2cXo4PPR/hk7/Xx2+un80NjFhzzF xqclO6JaCPX9aGLs6LZcX2/MlzwkKSqOk5rAJpkT2H4oD26o6Zq6aM2CCs2Znbqyxphi+4+j sRMmdUYR+JccdQlmBkpcwO4rCDguuPSU+5HFrj1OfVvNnDiVGHDw2hfcYnaCb/BoObjFY53q PrHKgzVOoXIBz6CWwaam5C1QbdUXZZjIxhkhJoxQVkDlUB7sZaZiIOdKkoqF6TwNeVK0nV3M zq6BpSLmeGRciugr2IPwSHs8KHfxQgL3sey1YenkdhEtD2I8jgVc1Oo2CdyTJ3oZsDL1M36n 8kvrttizV9IAODCds9MAD/Q32HmO87e3tyz2QywyEPHxPtsaDgaDjcH21guLfT7fN3Z1EENZ CVvGmisNCf/uHH9igacDL7cfwhjQZ2dA1enl9a0l9R+dug1y+dnn1xY72Gfs1c7WzjayeLdc z8uyZHdz8/r6GtsKfRAaM6wApDGVlmASZCgp8Qz4RGehgvNd1kAdC6FRY4/gd+5kYhMkMgKE m+cfRx9Pj04IweFNEtjRJs6FX4V/JYdCbVM6g1WmBw7pGAyBHdtoNa/DMIhu3uWi709CXOlt KVbPj/T1F92gh/oFz07Q58dYzGiy+sXa/+VHeODC2WuRuX7c995Wx9AyG4Nu4E9qgzxNo8bs W7EpL5o1hvOMTvtrb2SEUv679g5EwW+qY2sUy7w13Icqb3CErePvsc3esJPPR0d78BJSoLF8 ObbHkCq9YVt7OGu15+NZsh+5Y/g/v+nkwfOdcUZnsniyAS4hln89H8L+/wLb4Ac/QwG+Jz+p sSnrBDF7i4BMweFPyqHAjdjGQEF/MydhFf8GlmA91ul4PhhREHfZJht290qsSAt780ZR/wvM +a1PY3/9xcp1JNjbJtSTJ7Qb9tp41RvIl902UsudfWM8AO9RENHE3sW7h2qewUXJPlrIQoYA vhVEdRc0MhpmbAwQ+psUjgNpGlsnUNSW8eR2jMCmlKpS8W+AnwWvSx5KuolaAmmsDk6r1I4N NjAFADNes61ug1FKueS4GlMM8m9+6yPF5VYKPXPzhDbT8VXtf2OxitbJTSNIbW8WnjJVtoZn Ix2ftJn5QCShg8deryZYATBgIU6YdDSFkkCLup56t3rHOOEtbNnQL/yZpNy+bAEF5dyqLDhH df1CaVjtR3Hvp/Ovx+MPnz6fvN+rwkjluXfW+Hh0frx/cfCjMf1bi92ZE08+XRRLKlltrrMf Ukw6gb8O5iERt1N9jQICvssx14RR3CS6WnXtQjkuWgPiUXmjQd7XAE5RbqQuu1QnQRJC/t+N uYieZpLQWW5jqoXRuMRFh+FNPJTNaN9PV9YIxST3A5dyTUjVnuJZbpZRwgwJNoQzD907293o UjhANbuyAx/CPR+Dm4blOngzGGww0Yqp6C1101BexXYCzG4Tbn6+REX7ZTB8+VthM9ceXj7p TAVk+9MOLrH2+OiGPXbYY7FmsSfSHp4gJkvOlw4LjBiUS+uzVGNNllRGhNGeBr3BSpv4yU9U PA3dNqp4F1oOG9uQTRHMnzyNVfgotraelKEGwE3NB7sAbdoqLvmE3I4oj6D2lJScvBGJ/F9Z QUxPcA3tMsmOOon2WRU3KF24Ygksg9E6gXRwytZAeOM1zDEDblP+sjZeE5TqcSyj8axWLqg4 GSErUQA00WI7JiMT1nvDdpCiFSUy3PEb9nT8FMPLeiLBer3EYLX+gRHF76TqDckpYEseNFfu B9IeAQoYQ1Rc5xA5Kp+HpcbVYv0AmNOpjHUZ1zGgBjtsgx0WGiljxWDjbREyh/K56f2LKFOd 8/auOXqK+rh1B0MoRPznGSIpLWwNtyntjXYpTbK6C7wpPUZMolMSSGYCSCb5lFwA5lT4PHz2 /DfNRky2ONQYkElaMpBrI9MuqOAeZIJjXEmuY+kn8AElCLlcgKJkUIwT+mzJjwCoBirhVBqz gsfbcm/Ymjzto7G1ipqAv0KjhAo/6pRTwILStS4ZDzqEFrWhRLnAtImFUJigUQHNeQAE8Jsk 1dftr6lbgDEHlAIeDGrIfgtiACtQAyhQfzpPStacHY4xzJ3j08fxyeGXo9HJ4V/4fPjfF4cn 7w/fA7WP6gEcWYyX3TskDAOdlKFFTcV42pEfu2b+MKVLjPjKpclrj8Wv0ZqeaUJi579TZFoV D33Hnq6wWaF3NYZfPx+efY/NEd5/dHvywVRHtD1TVbt0jBQ7nUFBQvkaQnSh8n30ECKf9Ar8 VbV+KGJsPDRQozAeVciGyuNRdcE7FL2Uqo73M56JDjmAghr61LWAvSQwsh2UWYkWLGUUOeBd sJ+RpvYtTbWaMU1PKPN+zOlfg0uBLdWz1BIAQtzo5OAM9Gr0P4d7bVAtnhJvSyBbJYBZQ6wb OqRnVBSpSmKLw7iLn4bBlOxVXDolT4FJqyVvoMr2RSxUK9KNMb+U/sSJ05TjVeEG5zrkZblj +hIlsqYSWk2qC76VrndL5RQNIRQ/1WHYy0eeFamTSaHJPL3AL1DUpuFYxKhAG01R4w8EGPaG tcziMVR9rdj2mlgoX0puO9pbEF+ghm+db+GidcErLBgC4e1vQNPTX7eetgHJ3FivhPkxZsZG mUmZRm3mN9NwDFaaV9XvZefwfnZWcs6Pp0efTo6+jhmErylWtYBxir3DxlJ6OZ13tvJvWPBv TWOGnb8s8tI6Qvxppx8s+2ULaxfSjuEc7RjO1w7qBAGmt7UoQm2Fdrrlwk3whaheSBuH30Ub 79EApV76/EXk08X0oOFrKrG4LTTNczj6pxqcFnA9pejLaXXX0HjTKv5vi7Ct1ibCyCKTTzNQ A01lEK7zrIFhbvzAn3kxZD6FWqtq6yyqXlAOVhI6/aMckfymCFMY8ToZF3gAc69T2nmQj9+Z Y8U788Vo7FsR+7dkpHH8LSm1yETinSOVnbuM/tucplrbxlVvwwSryemm12vtuRVVTsoDSt3y iG51UwIl0zh9wcasZ/ybimgXzr+gbLw38bo36WoTQ0WZzXME/6ao5f4QcZo1U0GrjSCrWe13 C0RTJ4BsDQpMTXala1AglnV3myKxSjGuGnmLVeMWfU/sl+c78LS+Pg2zvXldvqJgRx+f0qGp 8Sa0f4/pDCDCP4lRa9eqecUVdSCEf5tlvtxBS20vX5S1fKFup7AJ+haf43HnkhrlRguVvvSm 9U0atcaE837BEGio31rj63DYn7zjffWl+dW4x2Iu2Lwvx1Wh2sdRi5WiVlSGvojXeQJM7Zrc OQC9yHgZqM1vMMYsiGPJsWoP27RPlZYC3r4ybMxN3T79DxNUJf4nSv5PSAG6UIVtsztaaUIV 16rQWPtZEjh+nAPOnw7PTg6PxlDun48+nXRaFKxb2eQXO7iEiieN85nXED599xE3qr53xOJI lUeqVV8QSd+7bTKqX/CDDmHAUDCDM5Roj5H1MPhVO47Ru5T9IoSymMHJuq8yG01Gi6n1wKXe vMeeuiytW0JO/TiHNlN3PcWLpBkHWtz8e9/F6hJ71cyWZwnzdGiaFP5XdrAbrZUvdoonHLvs 5zoekiF20SmxfPRrtCaTjvko2r5UbIgTv1QZIcIJZzAVr1csgnVf1qYcv0MYBDhZqrT63lLb ouq7vSV24BpduFDUyKAom/P1873S9RdnfCuyhV9L02RDfgWv5DRe7bVNkv5pzjT1kiZ+I7pK ADlaP3DXI+VZe3Ecs6HPY1YKpTm2L2H7ecrZNX8Kv8EK0eomfObLr4XLU7aK1075NehYI0be 2U+VXygrmqktemk2G6UJUa/x/Ov58f7pHV1G7b/McPSQHpxE0N6CqyG/t8FcMoWa6WbaUOHX Gf3TJvhlhoCONFud/v+37r5z6+6fbtlp7S17dnXdmldDV/SsVjov3aCrIFu8Q9c2jcq3dnyL 9uh67dP/kRbdnL6c+fFBPbrqFrYfxtHteRzd/k/1teZ1sdrJe7jE2lqj7837HIr/+E9iBFg+ 0fXwslztN9YcwRy8u1QEMeMf9eBC5pP9hijlnZzajaAbZI6l7gE1T5S0FNSdm+r1FZA97gXm 4p3ctlbbck2nlfbMwvB2CLFSd3E4Nrd3pIU7R3i1rjYQaJSbFSZU2w0k1/Kumsme6rWgVvuY n92dq4xM393whYy9E55d4z+JULuUYx7OYub2WDyqHQ1ScvXwFDWEyKlyVNtx8v9r70u700iW RD/jX5GjnusGAxbFKqSx35Nl2a1zreUIqXt83B4OhpKoMVtTIFndR//9RUQulZm1UIWRnz+g bkuQFRkVGblFRsYyB0E/ECN1u4som6dMOpiNKVwSt8l4iWXzGha5HCepUvA/Mq5QNgyw1Czn IKHk0RTuH8VIEEsXHpxJ/pbyzFStGxRxDZ2N9KOOxYGwaou39OTs5CokxER2RTBlE5kAPbZC 82VPiBm/Gd855Z4xIhgdys43PZAA+bFG2i1pBxY5CDlj1UkhdKmvW4cU5KjsWXPHm/sLcQIy FFgHBA/LqzH1CPIxvUfOMLWXzDCNR85wMx45w+QglcIjp7F1yNk65GwdcrYOOVuHnJ/EISdv O+QUFJZfBu4NHiqCbZ3tOe2q/kAqLVi10dSrKJ2T3Jd3/if/qVJu98o3h+V3n/+plx4LrJj/ 9D/ss/xbLORZ8c8/P4kvf/75ufB//nPHQEkmc2wlyj8XiOzPRRpswgCPsL18UehevnyhI90r Pf7njt6wCKGcwcHVAlCHGklrJQqDLrc4+BI0FAco2IIwNB50Fc4y/otfXx3YnkJC+okxYX8h XDiCAq4JRWmRULnfYI+bsLDxOEpD4mGcQHmQ0ovYCMueQprQ4VfILzrod0sxBrI0skyrtpVl trLMVpbZyjJbWebnkGWinYstN+FIR1/NTVhs093udee4i8PGEaf8v5beXCgQZDQNJoDxHaZ/ MEbxCHsNY2wWLNV9gPVUF8ITmLy10AgFPs6xmdLdF4PhF+cuLCb+sBtUzAcf8aIu+MZNZqT/ lxAc4DH2ovx7oHy+/kO8TtzLBi+nG8/c2B377kJ7F3mdCqWNTgHpbHKPCq8ILgPAKgqJUgaN /b+8QXfgo27uuaCoQO6qnIiQepajDV5Xfg2fKV7SK9mil6LkIAyI+hYDjpvlhMG+2WDfosAm XyywyZdIMM8G8yLAfNKhaWA+6fVssMVfVlOhIAqbe2thc295V6PJ65JHCScdleXMlVGmS6WN 0uHTy3Tfr5kykKWR6ertrUy3lem2Mt1WptvKdD+HTJegn5LqEiFKoLygNCdkwivEAHLyiIqw mP/K8/LwfdCui6IBiX6/WGEU9SCKMTW/8Zrx8Qyj64H4QPXi4iGakQtjcHjmu39JDnkYiQQl D44kKrhhZBWUQgJuxQQwjH4ZCCbxFKsgenRLpiWGE9owoaXixuKJgvGL1Cor/JxOWcUhV4g0 HCgi0WM7UyY4DU18jscGpfZplEiOYebp4w4T/b22SzHAUVR5dISj5QLTCRpFs/uBVXI7Jxim odyZwWzx8ISjleEehkVIeauClLdqJccxSd+Z6XkKd6KeqJyF4adBnsEd/dA107MIGk/0NIQ7 Cec0rcYwpga/F91BPogTGCcJPncXuZz6cmA+F5kmFYj4fkBsalOuP6dSKcEwQj7pNQNWQGWr xHqJyM6oXiK+W1CSewG5ouBAHVMDfsHRU/4EhQGgcUaVP0GhhnEYhXEYxqh1YgCpFR5onIf1 IZfrev7bzjkdaPEU9KrCThhILD026LljmFawxPC0KdXKHiZDq1YrIqWi1AocfbjuXB1fdjt/ HF68Pf49l2viwiUyE95jvhDEYUOfHV91z951crlWAI2Z9+Yz+Hvja8Y3WukgEtXFydtu5+rw KrcXoApCuWOVclyV01w7qs6Yay+yVnoeynESTS+K4lcn52edHAxYhSlIaRrLsM750b+ppbAg GFyTGU8jawoni+uzw9PjnFPFmtyHpCD3JAp0DVWpn6GD96Cfa1VMjRvV0UcX16iwyOUcjeFi ssSSjjnw1MVO26R+0Z9F1ut8OHyjXwhVNW7JWRfZU53j0+6Hk9OTK3EzViV2ieDTUuESan0I zWnnvYmGeCdUN+nRdH6zqKkRNcOM1Mjhdy3R1KNG4dKPrHx23Tm+7GisbGBlMyNodM3ri6uT 02Otpja9+ZrC1wg1x86uT7uiMkxvznr0xBlPyY4SzvRDOBi6vgzIjbnyRksfI1jp77fQtLKh gVUOBGqGp7fRSKYRZP5yNpvO1dkcJO2L07eHcGwhTyHK3oAy7QMpNNF8ngsQ1TruwMV6vVqq 8h2G//xD1bsXpydv86qzoYdK9b1CCZ51rz5eHHevYSbhl5Ozt+enXbTQoq84Rt+edI4uj6+O S0yiFAivz2C05CulslNySpUSooJOgDpH+Pno/Prsqnt+dlxgjyX4H1orjw9Gvwh+0INrXqQy PuH6inllqbQ3GGRQHGNPaNlltUHAmUJNfFZexaN2Oh6dnAH42RWwqBzJIpNDv51fX0ayqBhP Dh/hpUpWeoop6EnsMZ2Lqi+kjaHk42rCnR9LuJxYfKgJSUyNNZwwjRpl02w061JyjW/Dh/PD t4e/vze4/w4KgU7xiLcl1IyYGaP+A4IFoxHKZDYmrcQMonBESTf0s/SKbBFL2S9qEYjpF7tF RasHZL5i2QNM7uQtp0nnh/qesWytZBgTa8kblScYFwue7zfbSoFjPJx1mPPS4GQUHyl9+cdO KbROiAdx46IYaqRDDUS4i8Oj4+6bj8BsbPAjcVMnkjcShgWP36eyekakNc7YCsdYXmBmfHcz /h1uB40KkdLYHA9chncqtSYmuIXD0l5VZrqNo1zKGyWnGhrIl+dHFt32VrZylJWB7cI6nsSW l0u1/AVP6Ji61PYXye8UVNdSUE3L2/FlKZJmxW9aEE9xRUwg348j31+P/PqPJb8fy/7+mvxv /OAGxHZAf80eaD5hA/hsbDfxSO04IFjyM7VF+dz3u3M44memvZpm9FiS1aptJ/16pG0k1kyA I26XlNtmg4gbTpMUXUWnWmkD85vpFqda6ykWJ3sIiUwlcCrIKjKs3CCCloQPDYktCXeI3pJH KSlEJgY32V/ORlvn6vLk7P2KIZWive2sONfrO+l29XQ9V6+sxZ0VfRcag35vfkvN0NP2brgl zhO1hF+wh1QV+gn1SJzes4uYWn7RrC2+7kSc+7572ulEuetRFT48bJQqfz2qMkqCWam6WZOs NKLed5B1uxZRabbg7xlX61GVRir7nnG1HlVpRK3vGlfrkZVRtshKlkgJnJ2ulLvxd65a69GW clf/zrVrPdqclBv19y5ha1KXcvP9vpVsTdqqTz/k1ieu9vRjbn3i6j9gzK1PXeNpqZMnP+92 0ht1U2vNdAqbP0K4Ftm316Ow9SMoBBZSGCF3PRrXO8Blp7FPsa/WIjHzeTATiTwv6Mu7cRYd tC76pjknJNG2Wn1rEYpDch1C0xwdNkro3F+nv6tpDhMbpXPQW/TWITTN8WKjhMLpeL2uz6b2 2wCl7re15lKaU8hm55L3ZR0605xLvoNOeZEXsiQK3eU51QrdqTr1yp5+qZrUgNNUx6ok9dpK Da/NaLJ5ejJF22npSXZa8zpVM8MK9ULVadWwF6q1VhsEu4bohpV6eWExVWKR9Cfe1qdSegYq Nt+FLhiiiQy3DNyQho0ScLsyx/c4iCK5su8CUywMO2gPxzQX4ik2eIu89Gd9nbr1ruuzU7cO beGtcsO0TZbj7nIymK5DXHh7fALGzdz5et0a3hKfgLrpLLUEpNMW3gafgDbs1iAPQyb6wvvH hunz/8YZse7AC6vnnmbG3vVG65CX1QhwLfIwI9k6xKW0vstMHG000lFl43sQOovDmCFPpZSN Dox4N7IBcZGIJYqeklLYJjNMPJ3QJ92LOGnf0CcIIyNnp+5JdyNJ3cC9gY9/rUPfk25IGvf+ Sr8j6eQ96Y6kd657uw55G9uUWBJ9PnwYDubrEPiku5Kibz3mPdWWxIX7YQ/N3PlZ6wkE/KHc 8TKsC4FzwwaXV7W6xiyuRKk3WZ/SDayvGSjNNpx0Op9W7g9ow5PvOvQ9regv6RuO/Yf08vVv Ty/702SznWe0iShnlWZyPslkNczddZ7kxIzZhAIfQIxkJ9y+HDJGrDaaTmlP6ZcwVs3EdQdd 4Uj8Kcod7XOBA+ektzE5HE7cRVf6peWfh4oKSEY58R1S7/MZk9MmQpx+FiGoN4ILQTg6/EkE vu5g482Gz7yBaC98omYms1L3zwNsvDfq5NRabeztlRzeHSuwoLNcmBbpJicIkl+DqNnx+NRh 4bMR3psjD7xZ88+DzynQBptlFFrNTf25FrIpBbW/JVI71KgdZqCWe9hEodR8agVv+Rfs70fT yVb06B6fX816XZtffYzdHmgw98VESh7CGCg/BdwpAZZzdk6oVQPaiMMvKmvEKu/VNCQrYE60 pIU40qy1Sw6ypN3eK9W4TjtHuHqL6bj8eolBnZRH+Mvh34hAYoC1I6doqrf3xdccLM7lXI5F eah5EzacLuf+syKBioAS+1pILVhOjy8vaSk+EFAi4rliInykV5ojZJ88jAJPuGLOv/cwrUDe G8zKr72FO+bBu6huZZ/niMLfkZTmgVTf7U8nAx9nNAJZ0UB2br3R6GGH/Rf9/b/utx6srUKq I/hoG9GdKDGQXrCLbNP4nl92MV5MIU+xEPIUWL7Adlle7xB4T7NCvwqSX3bXiYAC0vucA0lm cnY4sexQTnEGQ4qRDFnRyCJvZDEXGlyCQvkufZCVxYBUQ4VFD5WyGCos9xiMceE232y2S21W rFVgRecRKEygshrFlgPZvu20Nu0NenckRlIdMcTMEVYORlg8Xv4sqroaoCGPueDlnCWU0XPi LzDrgFMwJ+6NZK2oJWt/qnw+EJCUp5TzZ4+uVGqVRlPyRwEIrCbL8WZEorEHUgo/vxUDJWaQ qJZwjBT8T3ZhThsefIsIjxDsdGrunkNBPWoObAdONWgvNWCPGiCd0W6W3BPc4C3FHqxUXlYw rQz9fcHyg+nyy8gt+F+WN8D97heKwrUbLicXPH2AQyvoxW3jxYGrXrarvJzBN/VWxMQzSVhv dSrGa5Xz3ZrvpGUr3+0uYc+lgM15RQKhLmBCNoMq4JFTqdYN4tLNeCZmPPVpuw5CWg06FeNe CVfLnEBz113gbySNvhSAWi+PmWMECKe+jzEYb0E8Fh4aXRLacIKVsHqJiXJe71Hudmqd0jZD kibkdt49On2r9kbtVeTmXn7Ng2HH7KomIvx1vK/6LuItMgVhHud/dzbuQntgCxoN8uJtFOWF Z4JSi07BSj4UNdeDTibaMYWUY5Z+8hfzkTvJy++FsqPlitJGXgz9F53Dy/edfftNGpfgna1U qASfGO1ofO/moVTlPsuHTLOO0mCt1sDVjw8Y1Qcsrg9+x7jy+/F9dNnp7MfXhqfdSxCSTeIo 3BfupncuRUZYTBkPASYIbQlCm1UU1jilIj0aZUZbUmI0MQX58FSLwO4rMb+0LZWoi+UetUCX BjBUTzR5wY7+vYMuZswltVLfIl7wF/P4HRRbyF5b1JCJ7ZtrkiLjn3dWPD8SCHiftfd4n7Wb pVolos8GQWtEl1nzX5eNI972B8aaTHyIOQTenH9AWSOX4ylNZUR9MXXS9prISZbD1TLiRakX kBW9KUZcjgclxMGmcoTBkNMT+AHdGPjYhd4eyCqHKRWuOTVmqflqRGIb4rkok8Jylt33gWc8 MYHMTKCaUlCg+jIG689gOYOKMl+ZSKwWAbqzI0Fk/jHxS1/19M1RrSMqhN3A7Xvj3ohOvtqS V6s4TQzQVazVa62S09B0GoaUqk6v+2hftIJNp93Tw4sONDoXZYikrQ48rAvsHS6ap0rlTBfB xC4baGzSrQ7hbQKRdSmsWDHgMEt8P1l7JREQJVEKARimqsmc169YhT1/Hqxz7L/YGTDUYBgf ICsrhvj89uTy6mOBGoQU7Wod7vE7zuBckDirxwmLcYK8z4dQs0ULW71dEw7TaWXvMh3jmS40 RQ4+pa/gS2nNabfpjc1qo1TlmbqSXxTIZOY6ys9ctMiscVEjVo3IiXJNO+Y/q4Y697hca7DT Zhipz4jeAq473euTtzH7Azw8TnzaSXz6LvkxPOyenSa/OhGgswrgnQ7BV1ARbHXW8/37AXsx u3dT73FLv4spgn30BSvpW502Pf/F6gUUeTe21VmzP7qJ5qYDbeIHlNk9UAobD4wofd9RWaJj dx/AUH49u+9q+cpzdMgP70HXZ/8+O//jbEflwIzYgyL75n3iqEt82kl8+i758ftVo24VQGcV wDsdwhh1t/PpcsZe3M7XGHS3P9Wge28POmgTH3S381scdLdxgy5B6AEc5de3c2PYJYg/5tBL lIKiO/Lk/dnhh321GGu4V/YGbKezyaAU5nkMy1cS8+bD+dG/j9+uTc2X0dcNUgOsOcLcYGuT 079dbJYc6Kvzy+O16QHpZ4P0/H7KD/dpzrOKCu7NFEGFpoer0PvVUrtinqagE0dVZjpH/aix 9JRkSlVCFirnvv+DqXx7eHWYmUx0ZPrBdMKHNXrdX/zoXj/+7+xzyP32w6fQyZvsM8j78lRU rr4KzYXvQTd9ngkMDpCO5PvTXLxPinkHEUQu5yBG0+WtUQQ2YdmZhIwnLLKQVaOQrUblR6Cq GagMB41EXMsIXPUQWYE/RRIyfxSBrBFCNlXKllhU09k4AlUzhEr3VkhAt+SXyRa6loHOci5I wsazSlnY9qL6UvoCJGC7G3+LwNYOYVOm+wm4eq7FttVT9WlnaWC/k36W2lb7Rnu1HAJajrLY OWrZ1Segip7tVQuTbgafiCyqT2shZLrVehI6nhQtdpZGGJknYotaiho2/zWT8ARkfuRcaBrI cDHSDbgT0IlMbLET1ba3toxQ9Ky/BZtSyt72E82NwAgtww4WMro2V4MgkQZ8jB6FjonMsItO QuZNkjcwy3Q5CVXkAKxFoVKWxgnoQh1r72Fhw+AEbL3R6OcaJty4Vyltd9GWaQnrGWbdiorI r1Q9mGiGvVguDqz2csHPh6ZgArM8l+/uh97IBelyueA6FPFM3RCR6LlcAIpFF7NGoViJhNF9 wXGnU8AbAQmA2pNPlc+ocME79YLQBUkayGJQqEjcyUAjwzKdC7T1EYp+oUQXplRc/15tkR1s rV1vo4kFqd9vZnNvsrjJ+4uBO5+DeHt2fnVydLwPLMMkXSE3bgzmP/D8r+xk95zMMv0/JzsF 7U2U/5H376XbG7AO3eTiNqOlIcHMNf5Ldu3zS+jFvDfxR72Fy+57sI3jddzEHQm7yRfy7tC1 bw8BA39R6htDPgRiko0zcRfjTaCtMNAfpH0qpT0QFum+is0v0pXqpppwpFAJS/XygmQQJVqS pSbIQbrMUbr9VLoMUkaNVZmkDODvzygVRhefWYpMueoqIY5K9nTTnyxGVv4olWNXzym1GHjx eXdZKHOTpIsSKFGk/SpdqTZqekwIumi/GS8+NeufRSfiFd3NQPuCS7/8PF9OJhjkvMQm+Bb/ gOf27Q0oOyWlOVziqKcw4kxe8umZcflsNpLjlmVuXJ1wPTuuXl5Q5qMZKvGkumoSK8LyN0jC FETE/A6fuqICnIHPu5dvz88+fCyofLrIxWabuNhy5BIj55WImP+CVV5WKupXgzm7zRYMr0az xifzB2FnmHJXEFiFHSd0eH/2kIcOw5P6DaP/cX0qxj5l/xrs/mvA4FgvOSAO+/n+FG0yualF gS5asSb0xnOddeXXgUWmvAwMPXLiH1U/S/LEz3rY06CoIopghD7nQ3RFXd4dgevFrpHel2n3 t5U11rBU6X3NGlnWsGHEGra3/hq2IslvjXJE1JpiDXvGQhkkiV03gG7BZKfUPtMaATtHg3ZI p8FAmqTHrHfnzmU2R6xpiPBM2c+yR2ZOZuqsiMyFOpQ1/9mLLFsQOh8t+rMMW5Cqkab7FHC4 ++BD5u4z0cV3H7cmDm9BamtZsQX1sb8zbEGSLtqCUvMeujwD3wk6Dc8JcDP8DlDF8topNTAf dkNE6ofVG1Z+xKDHb/oHBcwSGbo8ytMCT42cBFriut4SmhBp1WCToMhEoaTblWxJtxEHNWGP DAPpNzaCTLRCvmvKZAQmmLITeYbOBVJi8ErsqyZA4NcSihRhWYPvRDP9G+xKn9Ay8vOBiPvf wnxz+McJEpKgzJ73XlUOmAc7taSi/Bp+DXv+8OWQjMqZVyxymySCn0wH7qsIWPj1yYMlC5/L O2Px7RX9Kb+ewMoTWDe5eAUY8IH08bTccGC8fpGWrC4c7u96Iw9lDvxMhotkeuPqRWOtrIJ1 H40NzEBTOQg/s9DGgYxTwCz9FUBkxxYN8mjJWzALqA9rZCXl1GvqkEYjwZTGSBzRJDA0O+M8 z/niSEcgO/+qNAcMpDXg/cjzF9B33EiV8H0FdCicAmKUT2+KLSUdwjc8377maMvcvh6H29di yzQH38WT3nh659JYoKzxmLx7Osc89NMx648HeO0iLLcZJjt/kIabu2kPb7ICH5vw/hYMOhjN X1mRNeEjH7tFae6AhE4+4zGcjtjKPEGWs1/Zr5ZZAhO/+qOp7wJDCpZjQsUhJ1JHevRyjqB3 SF4NKmSa4m4wjqA4sOmJqjgWNYtBTWkAaRoDqVrysaKSKs7m6B0RGHKId8VOY2PKCm8I7kjU psbuQWO5Rf2jlsuKhjPrRaQgCBL+QSnBpj2aU/+GF4lnxTjLO1gpByUWvbwWsbvl0sk/+bCG C+WOPLLlut3Z+DdgxBklURFLmCzsuL05eXRpBn6Kf9RVYWpdUpLbC7MoedFfznEecOUNecnS G7XuFXI0LanwPdXKKZFFrUhiTSjaawI/ycG5h1eA1QFrk5Cv7lFjVxo869FY5CwtkyCkbkv5 OjWx1hV7VVmBI1CqTXgj+EwVwMJdRTc7shgAbxm5EzS8nQRTP/z8FR8G4YfIdnHsg1aMRtO+ hR026IKxfOABHY+WNpgJaz79NLEda6RtlNBk9nyU9tlsCl2HmqfFFOSBgXfnDZa9EaOrbPTD BVQ3rrw7EINM2y2X0o5aU2TCUjzpj2d5AQ1D4tob7O9gkAfJsAARvNP9FoD++ufk14LyGgqo RR0rey5M6E7eSnWrRoYyzuQWZb47yz8PKOB6xKgat8k1tHaJZ7paNtzU38cdGIzY2lZBnyPU ChEPhtIwllGL7LuC04Pp5NcFHKpgE6UVjrtGAggOdNnaCOpFkOTEJkdWG/W/rlEL4wdnr0XR fLNX8xfrkIhxbtdgh/dlRS1hihjd6x3v9mIyiOl1HlKdjXv+14Se5DaFmUnnxn/rVMPZv0a1 /u1iVTV+jYB6h3v317mLg9uVDTctOlOuA8bapYlQ5nwOBGFHXGiI3QuXdrkpWLug+Ep766OW mjFGChlbQgjP2BghWXCXhAbXOrdKzUDnq72RX2moMDUR7yTnmLDc88fh5dnJ2ft9doWZkfs9 WKZddudiqKne/Nb9D8bOJ6MHWOK/UjVvgcP2YbpktOE8UFwJKH35JEKU8NTZgAiFH/hWWvn/ IFFJIXi2mLNXcsCkE67WEa/Ms9xK4QrBNypa8Rkp7yJXyVivtSUOu6gYiDv2GUMIS/DHFJf0 5/Q4mO4mgCYwMV1iks9LzEJnS09GRxqYi/TesqJdCFpaDUvK4igjzt6OOq5C+2Fnh2WvB/8m U4aAJfgNk0u9l6QuELmoDiwKPfa3O58iMbeLoTjLvmQXRxewdro+igYjnJw4vGQVceBV8pvm rBjirr4hxXF2zBnr6Gu/2UVOJAtw5tiwZWbJnuaa/bju6izjfx9/W8x7fX4P7wHD8jwJMOxI vXmPbrrIPJNrCHpKmQWCLNewXUG9G2+OshbB0X2Yz3oL6oaXGdWl6W8ZCDqtujTqdmGNG9IA Vay6tLWHCr0i/GnwfeqXgXuD27Lp6HrW+ePwAg/9tUYcyFEA04yDOf7vkyvhfQFgrWfFaDBh 3HB+yfVZtb04wKurjxiPSyq+au04QN1RFwDrldhXU4wBpWmrOyJDamDyQcOGzkeG7iBY5nef lSVu27ETmaM1xn6s6/hYvSo0I2WK1QtTvk9v3bXlEhHMNxZg6Wff6yOZwz33AgrjmCg8+BSc Ew/X0eGq8XDvdMBaPNx7nb56An06YCOBPh2umUSfBhg3rpXno4CLG9aBBySHixvVgSOk4HNC h7zTIZ2EHnmvU+gkdMmxDukk9EnHAEzolHc6pJPUK7SCSBoTukX4VgnAhH5RfkYEmNAx0j+K Y0zoGe4pJEd2Qs9wVx0JmNAz5Cyj5kpCz3B/FQmY0DPCYUQAJvQMeWyoVyf0DDlNKMCmiLAZ LJ5ymaLdObxQGWuPvTpeB8sy4G4ZkczjV0f23ChDUUUc3SLbcNrFboN1uhILAL0Azx3aPttV 2j6dmlOqNuP3T7Q4fXOJ1eqxENBnBBG3wQrvfoCIG/A8zoJcg1LuW+NUG9cpvLYV3zVyvYAl jSd9H7hz746iIPOe4UZ/8p3GqyJ3dLFRhswceLw0EluXFOAr+H5rfedKFbvoy+irXeTdTuyi /u3CKOKqNqto1P9qlcx93yoRZz0D08Ku5n4LofbQ8vyR6QoYYXwRbfkBBwE8AAwO6Bgyw6Mw Hn7ZV/eBbD/ooDCheB+AcwICMzdYFxnuybLKweBB7SCoLKGUt08g2mvXw7ncC/lARcfbfREx +YRxo7IziQQKz1C9nkWMujw9CD+RdJYtOsdCUa1YLH5CD/FkJn/0Q17cY/nCMGYtzEhsy5d+ iD/6G0zVVgQJxqVDXPOUll6rIcaTgYXKAosfTXERPez4jTJdXTrtmrQK2E2rPqOeFYZEYU1J TACWhalUItOxYvwr7XtD4nKWd/L7wNBLi3EvDavsMr1Sas8iXoiMda2Tr3XwNc+9wd2N5DJf WwwXRl5UwkFFvEx99BXRONMbC8kKaQ7AEjb3BzQKz8A1B4S8/UoF/geRq9nOdAZW2BKPwZUS LoClPYrDJcWKkEFPNZtBD+KgX6SqBWpu570x83y6omf+9GZx35u7B6SdRUXu3B14vgiXiopb WLh3YRhRkNgHKCBcywnsrTQG0B7Cx539zp37HhBVxS/45P3ZNXvvTtw5LPgXyy9AMvvg9d2J 77IePwzOsNQf8gMhVnmHJHUESezdFF7TQ8P8hFYExOL+QliG0xnQNYQdHsi/ny5hPH5x8QLv ZjkiO2Wuwj65+u38+oodnn1Edfbl4dnVxwN2D2N6ulww987lyLzxbISxce/RsGOyeIDWUfXT 40s8zV8dvjn5cHL1kQGL3p1cnR2DcPzu/JId8uDHR9cfDi/ZxfXlxXnnWGvFu+UcVXQleAW0 QXaC3R5JTG/yELxfNszjPKReFBynYQKNhAW9542xFGvCK+YDNoPumWLv3vbmAxSDvMkN6u/c MSwEhGnKOxT1fDiWJpg2gncXsPvOw3M7ahW9SYndD10kXzFnynNKTLHw3vPdEuvN8AkMDLwG QB8Io50YxhPecdFD7w/5GhjGHuctUF2yX8oGUzIvR8SEsT8df0FDHPLbIAZoAwM5F5CkXlzC RiJPeDFAD3AfuQeW+lPo8rnWRR9hPvhDGj3D3h0w1+27JE324NWzhzSjHM1YCReSYxB4gEpa aA6wcu4t3MTBz2d3iTXafAK4wHQQWEe47pZZZ4n1MZooezP1F9DFp4esUnUcBzbGSqvErjuH WquOppMFLt94AzwfE/79mPWkBOsdrHWHYygD+noLoOri6/1DiY9/9EPqQb/87rn3JXYEJ712 vVKvIYv3g/cNF4vZ/u7u/f095sVG5Q7TZgH0xg2fCTpB2iAlngGfgKMl2GTcfRZCPfV9iRrX 2v91+wt/F3rkBBDuwln+/cWHM0Jw/G026k12taQLwYLSx+sUK0x0uoQoESazkeaxWuFyAnN8 YBUqP5BilM+HVrqjbyjDHXwWxI9ngWNFhUQENNssRgWi1z6rqzERlp7fjqlbqb3KZ3kXhncx dFPBbbw5PAZok/GwpUpd9/ggpzTN3aOYM/w9JBLLc0OSVpC+YQJz2GWDQ0Z6bAQK/eCySUOV xo4nHotxpwBfA+M7fuvwrJiTroDKJ+SZdNKKd8LgnhsYhEFy5rnkb3CLyB+VX4sg8GH31yCI ugGvoqSHa5idaLpBqIuQirgHySqjpb+hkBUyyGjDjcpoK64qhIxWr21ltK2MtpXRtjLaVkb7 6WW0sAI3Z7qaBbulWa7tiY/MEEtol4xzQYsWsUhMSLNxzqfTRXfEXYBW710B9IotMwCMcINy Mt3rW6ji3aDqPBG98CHCn283Pv+Awc9B4BFfALlQLc76TNjjD73JndDxNRroNNKgqNASk//g w3D8mss1Yb/fd+qqtN8bjagU6OGFw79zAqy+x/WyvFtkYVv4HwaFVRAjBEFiDMhihxeLJG3G DwI0ZD2ZUMQGQJqoeVrykf5sKRra3iOOVaqlel21FC22MCIAkeBU9+vCcA95JW4jfHfMP4z9 W1EyxGlM0q6IJCRhgyhYvE2OJFkFtJLljlEuS6uSAzzMlCyuBcAUMUqW14Py6cyXpY2gVMRx kk+agn4Vkkk+aBnU3PVG8sFe8AADJcnittZ8YItiFQ8vxKGqQdtnioaq3nCK+SPLq0G5CN8j n9SMGn/J5lf15vNANPJBI2CjCJAjnzT1hir4lt6bQ6s3FY011SAZ3EWWOxFYa3qLRMgV+URr EY+eIh/UhS0UTlp59bPUx2eDlwlpU5Y2RZgOGuG1VkVLbYYCEqV2IdgGgFLxGPevgTcXpS0B vBTTuyE7PkhCY0y1xr6Y1zxbTGiuNvadiszAdt+bYeqVf0SwhjYGSSjWGzXd0XDm4waowmNM 5w/CoHY5+UuuFXLtQka+5BUki2Y4JpDuPeiiMkfYm9/6okx0T3+soMTi5SvW7kFvcVQzMb72 oJd4ye18JkrqvA0NdPQt1tuNUq0WrCTYUFlTdFPfKBSsx3nU5Xbj8kmLEy2yy8hS0QXYXjgs TtW1D2dxAGBVEz1DuQm65jLKGyFGscGiuuARp8ushkMT1vuWNiLcgQEiIPYUDsAynbsajIBo K4h+D69GfBsHGlI84lecjtTT0PFiOi6tJV/DywHcCAiBVrw3FkDMyJsICA4g1prbWBrEmuNG QHAAufjGArQkDWEIDrCn+NCdjKMA2gEfbAjBqErAiBgIR+OEBSIgqooVMWQ4tYAXMW+pB8yI gWho3Iimo6kvCML9RqwyTbq3bNSqJSfY60fel7nPB3x7X8g0cMYIysSshWVx8SCK1H4xswQS oqIt+0y46tBPTgw5Rz7CCWM+qspH6HPDn8hHNfmIHGuMWnX1LjjDWBgb8hm6yJgYm4oO74tG vnzc0rmI6y3wMI0orUVITHVNqMOvEKd10O9WQBnI0uifWu2t/mmrf9rqn7b6p63+6afXP61x RwjHrV1UW/m8XFgpdrvXneMuDieHMR567a+lN0ezG2DTyQWmhn53zgQ0mbEaGPHoGH4PBhm2 Lxm1DSnbHaOW7Tv4iOovLfU3XTDiJRjHKdRyqHnA45L4exAALCfY46QNYHAcyHrNGLxZv2XU qSuINH3z25c8fod+PQYTfI7qO/Zco0zzHnLH/cUoXyHcsgtKSGeKa8iAiPJrEZj8lWSAFobc Bpt4FhgPqhoC820wPxJsaYMto8D8kQXGI35bYNPZ2AQT0bwtsCXdQWpgIkq3Deb/bYHxkMMW 2N34mwkm4mpbYD3Xoo2HzN7Mdac+YzKKfKsuO3XQTYqa6a46m9urzq2ouRU1t6LmVtT8SUTN vC1qFjRR8wZvOilDCvy7Puten709fndydvyW7MVvR96XPqu+dNAxHAcEtJWLiz4XsErknIGh rb2FfEKERaGEkSyCj+NSLcROLqdNab3y5mx6z9dLIE+X42QAhrselyICGXDQxXgzIjmqJYVR /lAS0axKKDi+6Aong0f494s7GeD8Tb79JXGWi1koTv+C0wgN4z0eewhFhBm8mBznuWQQqgqi F1Yd977x6kEdWC4mC+/GU87x4bp+TF3+dootDlVR0RxReXkgfKsoBjzmLuFNXGJ9UfneG7gx LwfxTb5c4NBeP8M5MIiuiRKdVROzumAVesrwAja6Kkp5VlUiXPJ8xpfBQBALIQD5j2L0khCv HR20jDd2HRQGqY7Wm988oAUH3zKGPSgaYqXe4H+X/gKHM+VgQcKDWo9aCpZ4m4CYI1F6gwAt SUE6LeYwvRZzuEkt5jCrFtPZipZb0XIrWm5Fy61o+XOIlhvRYkZqKzenrhxGqCuH66orh8He PDTUlcNV6sqhUFcOpVIwm1JyGKmUHNpKSU3ROJSKxkDLmNeI4XIzqik5RWnUj0NNP0Y5o3hK JK4fU0mkbDBvYoHx9FA2GNdSamBCS2mCYc4oA0ykdLLAUKQ0wHiupg3p7oYZdXfD9Lq74SZ1 d8OMurt6cytgbQWsrYC1FbC2AtbPIWAl6O5WKqr4hiz0J6TA8Ic9FKdgy8S5R1IEy395WLh+ IUqtwbdqQuBN1kQQ6LsIQRDaR+BYqXriO3x8K1ZqgfjeH4FAmNfp78+jm4Foy6OW7TFBWxMn EVIw7v8HJPPEVfhKAQA= --------------020200090508080803060405-- From markgw@sgi.com Tue Sep 24 16:07:23 2002 Received: with ECARTIS (v1.0.0; list pcp); Tue, 24 Sep 2002 16:07:26 -0700 (PDT) Received: from deliverator.sgi.com (deliverator.SGI.COM [204.94.214.10] (may be forged)) by oss.sgi.com (8.12.5/8.12.5) with SMTP id g8ON7NtG002314 for ; Tue, 24 Sep 2002 16:07:23 -0700 Received: from larry.melbourne.sgi.com (larry.melbourne.sgi.com [134.14.52.130]) by deliverator.sgi.com (980327.SGI.8.8.8-aspam/980304.SGI-aspam: SGI does not authorize the use of its proprietary systems or networks for unsolicited or bulk email from the Internet.) via SMTP id QAA09196 for ; Tue, 24 Sep 2002 16:07:22 -0700 (PDT) mail_from (markgw@sgi.com) Received: from sherman.melbourne.sgi.com (sherman.melbourne.sgi.com [134.14.55.232]) by larry.melbourne.sgi.com (950413.SGI.8.6.12/950213.SGI.AUTOCF) via ESMTP id JAA07279; Wed, 25 Sep 2002 09:06:02 +1000 Date: Wed, 25 Sep 2002 09:06:02 +1000 (EST) From: Mark Goodwin X-X-Sender: markgw@sherman.melbourne.sgi.com To: "Davis, Todd C" cc: pcp@oss.sgi.com Subject: RE: RedHat 7.3 Performance Co-Pilot In-Reply-To: <29AD895CE780D511A8870002A50A666D04F9083A@hdsmsx106.hd.intel.com> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII X-archive-position: 9 X-ecartis-version: Ecartis v1.0.0 Sender: pcp-bounce@oss.sgi.com Errors-to: pcp-bounce@oss.sgi.com X-original-sender: markgw@sgi.com Precedence: bulk X-list: pcp On Tue, 24 Sep 2002, Davis, Todd C wrote: > I was using pcpmon and I couldn't get the CPU utilization to change > significantly on a dual CPU system but top was showing the fluctuations. I > want to verify what I observed once I learn PCP better. I'll probably do > that tomorrow. This is all I have noticed so far since I am just coming up > to speed on PCP. Well that could be a pcpmon problem; it's a client of PCP and I don't maintain it. We don't seem to have any evidence of PCP itself having this problem, so I guess maybe you should use one of the legacy PCP tools to test (pmstat would be a good choice). - Mark From todd.c.davis@intel.com Tue Sep 24 16:27:31 2002 Received: with ECARTIS (v1.0.0; list pcp); Tue, 24 Sep 2002 16:27:34 -0700 (PDT) Received: from petasus.ch.intel.com (petasus.ch.intel.com [143.182.124.5]) by oss.sgi.com (8.12.5/8.12.5) with SMTP id g8ONRVtG002415 for ; Tue, 24 Sep 2002 16:27:31 -0700 Received: from fmsmsxvs043.fm.intel.com (fmsmsxvs043.fm.intel.com [132.233.42.129]) by petasus.ch.intel.com (8.11.6/8.11.6/d: solo.mc,v 1.46 2002/09/23 20:41:22 dmccart Exp $) with SMTP id g8ONT9F26569 for ; Tue, 24 Sep 2002 23:29:09 GMT Received: from fmsmsx019.fm.intel.com ([132.233.42.130]) by fmsmsxvs043.fm.intel.com (NAVGW 2.5.2.11) with SMTP id M2002092416254809600 ; Tue, 24 Sep 2002 16:25:48 -0700 Received: by fmsmsx019.fm.intel.com with Internet Mail Service (5.5.2653.19) id ; Tue, 24 Sep 2002 16:27:25 -0700 Message-ID: <29AD895CE780D511A8870002A50A666D04F9083B@hdsmsx106.hd.intel.com> From: "Davis, Todd C" To: Mike Mason , Mark Goodwin , pcp@oss.sgi.com Subject: RE: PCP patch for top/libgtop conversion Date: Tue, 24 Sep 2002 16:33:47 -0700 MIME-Version: 1.0 X-Mailer: Internet Mail Service (5.5.2653.19) Content-Type: text/plain X-archive-position: 10 X-ecartis-version: Ecartis v1.0.0 Sender: pcp-bounce@oss.sgi.com Errors-to: pcp-bounce@oss.sgi.com X-original-sender: todd.c.davis@intel.com Precedence: bulk X-list: pcp How are patches like this and other changes to PCP tested and verified to be correct? I think enterprise class system utilities like PCP require a much higher level of qualify assurance than the typical open source project. What verification procedures does SGI go through before making a source tarball release? I think test suites should be made available to developers to use when making enhancements and bug fixes so changes can be verified. Tests could also be submitted with any enhancements before being accepted by the PCP project. Test suites can also be useful in verifying an installation of PCP. Todd C. Davis These are my opinions and absolutely not official opinions of Intel Corp. -----Original Message----- From: Mike Mason [mailto:mmlnx@us.ibm.com] Sent: Tuesday, September 24, 2002 5:33 PM To: Mark Goodwin; pcp@oss.sgi.com Subject: PCP patch for top/libgtop conversion Mark, Here's my long awaited patch. As you know, most of the changes were made to support conversion of top and libgtop to use PCP. I also made a few small bug fixes, some in comments. I added some "this code provided by ..." comments which you can modify or remove if you'd like. I'm not sure how much of this type of comment you want to include. The patch should be applied to the 2.2.2 source currently available from the SGI PCP site. The changes to top and libgtop to use PCP are essentially done, but I don't yet have a way to release them. We go through a formal process at IBM to get permission to contribute to outside projects. I don't have permission to contribute to procps or libgtop. I'll work on that. Please let me know of any changes you want me to make. Regards, Mike Here's what was added and/or modified: (new) Total idle time since boot kernel.all.idletime (new) current # of user sessions kernel.all.nusers (new) Last pid used kernel.all.lastpid (new) Filesystem blocksize from statfs() filesys.blocksize (new) Filesystem free space available to non-superusers from statfs() filesys.avail (modified) Per process command name proc.psinfo.cmd (new) Per process command line from /proc//cmdline proc.psinfo.psargs (new) Per process CPU number from /proc//stat proc.psinfo.processor (new) Per process wait channel symbol name proc.psinfo.wchan_s (new) Per process signal info from /proc//status proc.psinfo.signal_s proc.psinfo.blocked_s proc.psinfo.sigignore_s proc.psinfo.sigcatch_s (new) Per process map info from /proc//maps proc.memory.maps (new) Per process memory info from /proc//status proc.memory.vmsize proc.memory.vmlock proc.memory.vmrss proc.memory.vmdata proc.memory.vmstack proc.memory.vmexe proc.memory.vmlib (new) Per process user and group ids from /proc//status proc.id.uid proc.id.euid proc.id.suid proc.id.fsuid proc.id.gid proc.id.egid proc.id.sgid proc.id.fsgid (new) Per process user and group ids converted to names proc.id.uid_nm proc.id.euid_nm proc.id.suid_nm proc.id.fsuid_nm proc.id.gid_nm proc.id.egid_nm proc.id.sgid_nm proc.id.fsgid_nm (new) Semaphore limits from semctl()(needed by libgtop) ipc.sem.max_semmap ipc.sem.max_semid ipc.sem.max_sem ipc.sem.num_undo ipc.sem.max_perid ipc.sem.max_ops ipc.sem.max_undoent ipc.sem.sz_semundo ipc.sem.max_semval ipc.sem.max_exit (new) Message queue limits from msgctl()(needed by libgtop) ipc.msg.sz_pool ipc.msg.mapent ipc.msg.max_msgsz ipc.msg.max_defmsgq ipc.msg.max_msgqid ipc.msg.max_msgseg ipc.msg.num_smsghdr ipc.msg.max_seg (new) Shared memory limits from shmctl() (needed by libgtop) ipc.shm.max_segsz ipc.shm.min_segsz ipc.shm.max_seg ipc.shm.max_segproc ipc.shm.max_shmsys -- Mike Mason IBM Linux Technology Center, RAS Group Beaverton, OR, USA mmlnx@us.ibm.com (503) 578-4123 From markgw@sgi.com Tue Sep 24 16:49:07 2002 Received: with ECARTIS (v1.0.0; list pcp); Tue, 24 Sep 2002 16:49:09 -0700 (PDT) Received: from deliverator.sgi.com (deliverator.SGI.COM [204.94.214.10] (may be forged)) by oss.sgi.com (8.12.5/8.12.5) with SMTP id g8ONn7tG002505 for ; Tue, 24 Sep 2002 16:49:07 -0700 Received: from larry.melbourne.sgi.com (larry.melbourne.sgi.com [134.14.52.130]) by deliverator.sgi.com (980327.SGI.8.8.8-aspam/980304.SGI-aspam: SGI does not authorize the use of its proprietary systems or networks for unsolicited or bulk email from the Internet.) via SMTP id QAA05513 for ; Tue, 24 Sep 2002 16:49:05 -0700 (PDT) mail_from (markgw@sgi.com) Received: from sherman.melbourne.sgi.com (sherman.melbourne.sgi.com [134.14.55.232]) by larry.melbourne.sgi.com (950413.SGI.8.6.12/950213.SGI.AUTOCF) via ESMTP id JAA07689; Wed, 25 Sep 2002 09:47:46 +1000 Date: Wed, 25 Sep 2002 09:47:46 +1000 (EST) From: Mark Goodwin X-X-Sender: markgw@sherman.melbourne.sgi.com To: "Davis, Todd C" cc: Mike Mason , Subject: RE: PCP patch for top/libgtop conversion In-Reply-To: <29AD895CE780D511A8870002A50A666D04F9083B@hdsmsx106.hd.intel.com> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII X-archive-position: 11 X-ecartis-version: Ecartis v1.0.0 Sender: pcp-bounce@oss.sgi.com Errors-to: pcp-bounce@oss.sgi.com X-original-sender: markgw@sgi.com Precedence: bulk X-list: pcp On Tue, 24 Sep 2002, Davis, Todd C wrote: > How are patches like this and other changes to PCP tested and verified to be > correct? I think enterprise class system utilities like PCP require a much > higher level of qualify assurance than the typical open source project. What > verification procedures does SGI go through before making a source tarball > release? I think test suites should be made available to developers to use > when making enhancements and bug fixes so changes can be verified. Tests > could also be submitted with any enhancements before being accepted by the > PCP project. Test suites can also be useful in verifying an installation of > PCP. PCP has a suite of approx 600 scripts for testing and quality assurance (QA) - this suite was originally developed for the proprietary version of PCP on IRIX over many years, and has been ported to Linux but has not been released open source. Although it's a reasonable request, the work to release it open source would be hard for me to justify. In any case, I always run the QA suite before shipping any open source PCP release. Given it's been so long since the last release, I think I'll merge Mike's patch, run the QA suite and then ship a "release candidate" for testing. This might not happen until next week because I also have to deal with some minor legal issues associated with accepting Mike's patch. thanks -- Mark From markgw@sgi.com Tue Sep 24 23:07:58 2002 Received: with ECARTIS (v1.0.0; list pcp); Tue, 24 Sep 2002 23:08:00 -0700 (PDT) Received: from deliverator.sgi.com (deliverator.SGI.COM [204.94.214.10] (may be forged)) by oss.sgi.com (8.12.5/8.12.5) with SMTP id g8P67wtG014486 for ; Tue, 24 Sep 2002 23:07:58 -0700 Received: from larry.melbourne.sgi.com (larry.melbourne.sgi.com [134.14.52.130]) by deliverator.sgi.com (980327.SGI.8.8.8-aspam/980304.SGI-aspam: SGI does not authorize the use of its proprietary systems or networks for unsolicited or bulk email from the Internet.) via SMTP id XAA03860 for ; Tue, 24 Sep 2002 23:07:56 -0700 (PDT) mail_from (markgw@sgi.com) Received: from sherman.melbourne.sgi.com (sherman.melbourne.sgi.com [134.14.55.232]) by larry.melbourne.sgi.com (950413.SGI.8.6.12/950213.SGI.AUTOCF) via ESMTP id QAA10559; Wed, 25 Sep 2002 16:05:15 +1000 Date: Wed, 25 Sep 2002 16:05:15 +1000 (EST) From: Mark Goodwin X-X-Sender: markgw@sherman.melbourne.sgi.com To: Mike Mason cc: pcp@oss.sgi.com Subject: Re: PCP patch for top/libgtop conversion In-Reply-To: <3D90DA07.5090405@us.ibm.com> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII X-archive-position: 12 X-ecartis-version: Ecartis v1.0.0 Sender: pcp-bounce@oss.sgi.com Errors-to: pcp-bounce@oss.sgi.com X-original-sender: markgw@sgi.com Precedence: bulk X-list: pcp On Tue, 24 Sep 2002, Mike Mason wrote: > > Here's my long awaited patch. As you know, most of the changes were > made to support conversion of top and libgtop to use PCP. I also made a > few small bug fixes, some in comments. I added some "this code provided > by ..." comments which you can modify or remove if you'd like. I'm not > sure how much of this type of comment you want to include. > > The patch should be applied to the 2.2.2 source currently available from > the SGI PCP site. I applied the patch to SGI internal top-of-tree, with a few mismatches in pmda.c (expected since it's so huge and changes often) but otherwise a clean patch. > The changes to top and libgtop to use PCP are essentially done, but I > don't yet have a way to release them. We go through a formal process at > IBM to get permission to contribute to outside projects. I don't have > permission to contribute to procps or libgtop. I'll work on that. OK, let me know when that will proceed - we should talk to the relevant maintainers. > Please let me know of any changes you want me to make. see comments below. > Here's what was added and/or modified: > > (new) Total idle time since boot > kernel.all.idletime I've added help text for this > (new) current # of user sessions > kernel.all.nusers OK > (new) Last pid used > kernel.all.lastpid added help text > (new) Filesystem blocksize from statfs() > filesys.blocksize OK > (new) Filesystem free space available to non-superusers from statfs() > filesys.avail OK > (modified) Per process command name > proc.psinfo.cmd > (new) Per process command line from /proc//cmdline > proc.psinfo.psargs OK, though not sure if they are needed since the instance name for each value already gives this info. > > (new) Per process CPU number from /proc//stat > proc.psinfo.processor OK > (new) Per process wait channel symbol name > proc.psinfo.wchan_s Looks OK. I assume a zero length string means the processes is not blocked. Also, my pmcd log reported : Warning: proc.psinfo.wchan_s symbol names may not be accurate! > (new) Per process signal info from /proc//status > proc.psinfo.signal_s > proc.psinfo.blocked_s > proc.psinfo.sigignore_s > proc.psinfo.sigcatch_s Seems OK, however I'm getting possibly unexpected values for swapped processes, e.g. for proc.psinfo.signal_s (pending signals mask) : inst [959 or "000959 (nfsd)"] value "fffffffffffffef8" Did a signed int go negative or something? > (new) Per process map info from /proc//maps > proc.memory.maps Seems OK. Did you need this to be specifically the same as cat /proc/*/maps i.e. a very long string? Does it still work OK if the maps for a particular process exceeds the copyout limit (one page)? > (new) Per process memory info from /proc//status > proc.memory.vmsize > proc.memory.vmlock > proc.memory.vmrss > proc.memory.vmdata > proc.memory.vmstack > proc.memory.vmexe > proc.memory.vmlib The values for these metrics all seem to be off by one line in /proc/PID/status. e.g. pminfo reports: proc.memory.vmsize inst [20396 or "020396 -tcsh"] value 0 proc.memory.vmlock inst [20396 or "020396 -tcsh"] value 1528 proc.memory.vmrss inst [20396 or "020396 -tcsh"] value 756 proc.memory.vmdata inst [20396 or "020396 -tcsh"] value 172 proc.memory.vmstack inst [20396 or "020396 -tcsh"] value 268 proc.memory.vmexe inst [20396 or "020396 -tcsh"] value 1456 proc.memory.vmlib: pmLookupDesc: Unknown or illegal metric identifier but /proc/20396/status reports: # cat /proc/20396/status | grep '^Vm' VmSize: 2804 kB VmLck: 0 kB VmRSS: 1528 kB VmData: 756 kB VmStk: 172 kB VmExe: 268 kB VmLib: 1456 kB The fix is probably trivial ... > (new) Per process user and group ids from /proc//status > proc.id.uid > proc.id.euid > proc.id.suid > proc.id.fsuid > proc.id.gid > proc.id.egid > proc.id.sgid > proc.id.fsgid > > (new) Per process user and group ids converted to names > proc.id.uid_nm > proc.id.euid_nm > proc.id.suid_nm > proc.id.fsuid_nm > proc.id.gid_nm > proc.id.egid_nm > proc.id.sgid_nm > proc.id.fsgid_nm all seem to be OK > (new) Semaphore limits from semctl()(needed by libgtop) > ipc.sem.max_semmap > ipc.sem.max_semid > ipc.sem.max_sem > ipc.sem.num_undo > ipc.sem.max_perid > ipc.sem.max_ops > ipc.sem.max_undoent > ipc.sem.sz_semundo > ipc.sem.max_semval > ipc.sem.max_exit > > (new) Message queue limits from msgctl()(needed by libgtop) > ipc.msg.sz_pool > ipc.msg.mapent > ipc.msg.max_msgsz > ipc.msg.max_defmsgq > ipc.msg.max_msgqid > ipc.msg.max_msgseg > ipc.msg.num_smsghdr > ipc.msg.max_seg > > (new) Shared memory limits from shmctl() (needed by libgtop) > ipc.shm.max_segsz > ipc.shm.min_segsz > ipc.shm.max_seg > ipc.shm.max_segproc > ipc.shm.max_shmsys OK, all seem straight forward. thanks -- Mark From mmlnx@us.ibm.com Wed Sep 25 09:57:49 2002 Received: with ECARTIS (v1.0.0; list pcp); Wed, 25 Sep 2002 09:57:52 -0700 (PDT) Received: from e3.ny.us.ibm.com (e3.ny.us.ibm.com [32.97.182.103]) by oss.sgi.com (8.12.5/8.12.5) with SMTP id g8PGvmtG004549 for ; Wed, 25 Sep 2002 09:57:49 -0700 Received: from northrelay04.pok.ibm.com (northrelay04.pok.ibm.com [9.56.224.206]) by e3.ny.us.ibm.com (8.12.2/8.12.2) with ESMTP id g8PGvgd3103282; Wed, 25 Sep 2002 12:57:42 -0400 Received: from us.ibm.com (sig-9-65-12-128.mts.ibm.com [9.65.12.128]) by northrelay04.pok.ibm.com (8.12.3/NCO/VER6.4) with ESMTP id g8PGvdw2150558; Wed, 25 Sep 2002 12:57:40 -0400 Message-ID: <3D91EB06.9070200@us.ibm.com> Date: Wed, 25 Sep 2002 09:57:42 -0700 From: Mike Mason User-Agent: Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.0.1) Gecko/20020823 Netscape/7.0 X-Accept-Language: en-us, en MIME-Version: 1.0 To: Jan-Frode Myklebust CC: pcp@oss.sgi.com Subject: Re: PCP patch for top/libgtop conversion References: <3D90DA07.5090405@us.ibm.com> <20020925093928.D25641@ii.uib.no> Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit X-archive-position: 13 X-ecartis-version: Ecartis v1.0.0 Sender: pcp-bounce@oss.sgi.com Errors-to: pcp-bounce@oss.sgi.com X-original-sender: mmlnx@us.ibm.com Precedence: bulk X-list: pcp Yes, the top conversion can access remote pmcd's, but currently only one at a time. What's the consensus of the people on this list? Would displaying data from multiple hosts in a single top session be generally useful? Jan-Frode Myklebust wrote: > On Tue, Sep 24, 2002 at 02:32:55PM -0700, Mike Mason wrote: > >>Here's my long awaited patch. As you know, most of the changes were >>made to support conversion of top and libgtop to use PCP. >> > > > Will this enable us to run remote 'top' sessions via 'pmcd'? What > would be extremely cool is if it would allow us to run 'top' on > cluster frontends, showing collected process info for all nodes in > the cluster. > > > -jf (crossing fingers hoping IBMs involvement in PCP might mean > they're also considering porting it to AIX :) > From mmlnx@us.ibm.com Wed Sep 25 10:17:46 2002 Received: with ECARTIS (v1.0.0; list pcp); Wed, 25 Sep 2002 10:17:50 -0700 (PDT) Received: from e3.ny.us.ibm.com (e3.ny.us.ibm.com [32.97.182.103]) by oss.sgi.com (8.12.5/8.12.5) with SMTP id g8PHHjtG004783 for ; Wed, 25 Sep 2002 10:17:46 -0700 Received: from northrelay04.pok.ibm.com (northrelay04.pok.ibm.com [9.56.224.206]) by e3.ny.us.ibm.com (8.12.2/8.12.2) with ESMTP id g8PHHdd3178158; Wed, 25 Sep 2002 13:17:39 -0400 Received: from us.ibm.com (sig-9-65-12-128.mts.ibm.com [9.65.12.128]) by northrelay04.pok.ibm.com (8.12.3/NCO/VER6.4) with ESMTP id g8PHHbw2167238; Wed, 25 Sep 2002 13:17:37 -0400 Message-ID: <3D91EFB4.20404@us.ibm.com> Date: Wed, 25 Sep 2002 10:17:40 -0700 From: Mike Mason User-Agent: Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.0.1) Gecko/20020823 Netscape/7.0 X-Accept-Language: en-us, en MIME-Version: 1.0 To: Mark Goodwin CC: pcp@oss.sgi.com Subject: Re: PCP patch for top/libgtop conversion References: Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit X-archive-position: 14 X-ecartis-version: Ecartis v1.0.0 Sender: pcp-bounce@oss.sgi.com Errors-to: pcp-bounce@oss.sgi.com X-original-sender: mmlnx@us.ibm.com Precedence: bulk X-list: pcp Mark, Sorry for missing some of the help text. I thought I'd taken care of that :-) See comments below: Mark Goodwin wrote: >>(modified) Per process command name >> proc.psinfo.cmd >>(new) Per process command line from /proc//cmdline >> proc.psinfo.psargs > > > OK, though not sure if they are needed since the instance name for > each value already gives this info. > First, I got these backwards: proc.psinfo.cmd is new and proc.psinfo.psargs is modified. Top sometimes needs the full command line. Until this patch, neither psargs nor the instance name actually gave the full command line. Now they both do. Top also wants just the command name at times, so I added proc.psinfo.cmd. I could parse the command name out of the instance name, but I thought it was easier to use proc.psinfo.cmd, which grabs the command name from /proc//status. Either way works for me. It's your call. > >>(new) Per process wait channel symbol name >> proc.psinfo.wchan_s > > > Looks OK. I assume a zero length string means the processes is not blocked. > Also, my pmcd log reported : > > Warning: proc.psinfo.wchan_s symbol names may not be accurate! > You should have also seen a warning about an address mismatch between System.map and /proc/ksyms. Did that message appear as well? Yes, a zero length string means the wait channel address is 0 and the process is not blocked. > >>(new) Per process signal info from /proc//status >> proc.psinfo.signal_s >> proc.psinfo.blocked_s >> proc.psinfo.sigignore_s >> proc.psinfo.sigcatch_s > > > Seems OK, however I'm getting possibly unexpected values for swapped > processes, e.g. for proc.psinfo.signal_s (pending signals mask) : > > inst [959 or "000959 (nfsd)"] value "fffffffffffffef8" > > Did a signed int go negative or something? I'm just passing through the output from /proc//status. I'll have to check what's output when a process is swapped. > > >>(new) Per process map info from /proc//maps >> proc.memory.maps > > > Seems OK. Did you need this to be specifically the same as cat /proc/*/maps > i.e. a very long string? Does it still work OK if the maps for a particular > process exceeds the copyout limit (one page)? > > This is needed by libgtop. I couldn't think of any other way to represent the maps in PCP. As far as I know, there's no way to represent instances within instances. Have you ever considered adding the capability? I don't think the copyout limit is an issue for PCP. There's code in proc/array.c to handle maps files greater than 4K. We just read it, so I don't think we need to do anything special. >>(new) Per process memory info from /proc//status >> proc.memory.vmsize >> proc.memory.vmlock >> proc.memory.vmrss >> proc.memory.vmdata >> proc.memory.vmstack >> proc.memory.vmexe >> proc.memory.vmlib > > > The values for these metrics all seem to be off by > one line in /proc/PID/status. e.g. pminfo reports: > > proc.memory.vmsize > inst [20396 or "020396 -tcsh"] value 0 > proc.memory.vmlock > inst [20396 or "020396 -tcsh"] value 1528 > proc.memory.vmrss > inst [20396 or "020396 -tcsh"] value 756 > proc.memory.vmdata > inst [20396 or "020396 -tcsh"] value 172 > proc.memory.vmstack > inst [20396 or "020396 -tcsh"] value 268 > proc.memory.vmexe > inst [20396 or "020396 -tcsh"] value 1456 > proc.memory.vmlib: pmLookupDesc: Unknown or illegal metric identifier > > but /proc/20396/status reports: > > # cat /proc/20396/status | grep '^Vm' > VmSize: 2804 kB > VmLck: 0 kB > VmRSS: 1528 kB > VmData: 756 kB > VmStk: 172 kB > VmExe: 268 kB > VmLib: 1456 kB > > The fix is probably trivial ... I'll look into this. What version of Linux are you using? Regards, Mike -- Mike Mason IBM Linux Technology Center, RAS Group Beaverton, OR, USA mmlnx@us.ibm.com (503) 578-4123 From mmlnx@us.ibm.com Wed Sep 25 12:09:28 2002 Received: with ECARTIS (v1.0.0; list pcp); Wed, 25 Sep 2002 12:09:30 -0700 (PDT) Received: from e6.ny.us.ibm.com (e6.ny.us.ibm.com [32.97.182.106]) by oss.sgi.com (8.12.5/8.12.5) with SMTP id g8PJ9RtG006428 for ; Wed, 25 Sep 2002 12:09:28 -0700 Received: from northrelay01.pok.ibm.com (northrelay01.pok.ibm.com [9.56.224.149]) by e6.ny.us.ibm.com (8.12.2/8.12.2) with ESMTP id g8PJ9LGb234276; Wed, 25 Sep 2002 15:09:21 -0400 Received: from us.ibm.com (dyn9-47-18-222.beaverton.ibm.com [9.47.18.222]) by northrelay01.pok.ibm.com (8.12.3/NCO/VER6.4) with ESMTP id g8PJ9IB8158296; Wed, 25 Sep 2002 15:09:19 -0400 Message-ID: <3D92097E.7070901@us.ibm.com> Date: Wed, 25 Sep 2002 12:07:42 -0700 From: Mike Mason User-Agent: Mozilla/5.0 (X11; U; Linux i686; en-US; rv:0.9.4.1) Gecko/20020314 Netscape6/6.2.2 X-Accept-Language: en-us MIME-Version: 1.0 To: Mark Goodwin CC: "Davis, Todd C" , pcp@oss.sgi.com Subject: Re: PCP patch for top/libgtop conversion References: Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit X-archive-position: 15 X-ecartis-version: Ecartis v1.0.0 Sender: pcp-bounce@oss.sgi.com Errors-to: pcp-bounce@oss.sgi.com X-original-sender: mmlnx@us.ibm.com Precedence: bulk X-list: pcp Mark Goodwin wrote: > On Tue, 24 Sep 2002, Davis, Todd C wrote: > > PCP has a suite of approx 600 scripts for testing and quality assurance > (QA) - this suite was originally developed for the proprietary version of > PCP on IRIX over many years, and has been ported to Linux but has not > been released open source. Although it's a reasonable request, the work > to release it open source would be hard for me to justify. > Todd, is the lack of these test suites in open source a show stopper for CGLE? Mark, what work is required to release the tests into open source? Is it mainly getting approvals from SGI legal or something else? Is there something that PCP contributors can do to help? Regards, Mike -- Mike Mason IBM Linux Technology Center, RAS Group Beaverton, OR, USA mmlnx@us.ibm.com (503) 578-4123 From janfrode@ii.uib.no Wed Sep 25 12:49:08 2002 Received: with ECARTIS (v1.0.0; list pcp); Wed, 25 Sep 2002 12:49:15 -0700 (PDT) Received: from ii.uib.no (eik.ii.uib.no [129.177.16.3]) by oss.sgi.com (8.12.5/8.12.5) with SMTP id g8PJn6tG007944 for ; Wed, 25 Sep 2002 12:49:07 -0700 Received: from granbar-192.ii.uib.no (granbar.ii.uib.no) [129.177.192.137] by ii.uib.no with esmtp (Exim 3.03) id 17u6le-00009k-00 ; Wed, 25 Sep 2002 09:39:30 +0200 Received: (from janfrode@localhost) by granbar.ii.uib.no (8.11.6+Sun/8.11.6) id g8P7dSj25809; Wed, 25 Sep 2002 09:39:28 +0200 (MEST) Date: Wed, 25 Sep 2002 09:39:28 +0200 From: Jan-Frode Myklebust To: Mike Mason Cc: pcp@oss.sgi.com Subject: Re: PCP patch for top/libgtop conversion Message-ID: <20020925093928.D25641@ii.uib.no> Mail-Followup-To: Mike Mason , pcp@oss.sgi.com References: <3D90DA07.5090405@us.ibm.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <3D90DA07.5090405@us.ibm.com>; from mmlnx@us.ibm.com on Tue, Sep 24, 2002 at 02:32:55PM -0700 X-Scanner: exiscan *17u6le-00009k-00*.KZV0ZyfNrw* (ii.uib.no) X-archive-position: 16 X-ecartis-version: Ecartis v1.0.0 Sender: pcp-bounce@oss.sgi.com Errors-to: pcp-bounce@oss.sgi.com X-original-sender: janfrode@parallab.no Precedence: bulk X-list: pcp On Tue, Sep 24, 2002 at 02:32:55PM -0700, Mike Mason wrote: > > Here's my long awaited patch. As you know, most of the changes were > made to support conversion of top and libgtop to use PCP. > Will this enable us to run remote 'top' sessions via 'pmcd'? What would be extremely cool is if it would allow us to run 'top' on cluster frontends, showing collected process info for all nodes in the cluster. -jf (crossing fingers hoping IBMs involvement in PCP might mean they're also considering porting it to AIX :) From dtj@uberh4x0r.org Wed Sep 25 13:04:29 2002 Received: with ECARTIS (v1.0.0; list pcp); Wed, 25 Sep 2002 13:04:30 -0700 (PDT) Received: from mhro1.mayo.edu (mhro1.mayo.edu [129.176.212.21]) by oss.sgi.com (8.12.5/8.12.5) with SMTP id g8PK4RtG008559 for ; Wed, 25 Sep 2002 13:04:28 -0700 Received: from daytona.mayo.edu by mhro1.mayo.edu with ESMTP; Wed, 25 Sep 2002 15:03:56 -0500 Received: from samer ([129.176.201.182]) by daytona.mayo.edu (SGI-8.9.3/8.9.3) with ESMTP id PAA53975; Wed, 25 Sep 2002 15:03:56 -0500 (CDT) Subject: Re: PCP patch for top/libgtop conversion From: Dean Johnson To: Jan-Frode Myklebust Cc: Mike Mason , pcp@oss.sgi.com In-Reply-To: <20020925093928.D25641@ii.uib.no> References: <3D90DA07.5090405@us.ibm.com> <20020925093928.D25641@ii.uib.no> Content-Type: text/plain Content-Transfer-Encoding: 7bit X-Mailer: Ximian Evolution 1.0.8 Date: 25 Sep 2002 15:03:54 -0500 Message-Id: <1032984235.31445.130.camel@samer> Mime-Version: 1.0 X-archive-position: 17 X-ecartis-version: Ecartis v1.0.0 Sender: pcp-bounce@oss.sgi.com Errors-to: pcp-bounce@oss.sgi.com X-original-sender: dtj@uberh4x0r.org Precedence: bulk X-list: pcp On Wed, 2002-09-25 at 02:39, Jan-Frode Myklebust wrote: > > -jf (crossing fingers hoping IBMs involvement in PCP might mean > they're also considering porting it to AIX :) You should port it yourself, it shouldn't be too tough, and don't forget to pass the bits back to Mark. ;-) -Dean From ahoyt@moser-inc.com Wed Sep 25 14:42:41 2002 Received: with ECARTIS (v1.0.0; list pcp); Wed, 25 Sep 2002 14:42:45 -0700 (PDT) Received: from grumpy.moser-inc.net ([207.250.3.115]) by oss.sgi.com (8.12.5/8.12.5) with SMTP id g8PLgetG011605 for ; Wed, 25 Sep 2002 14:42:41 -0700 Received: from moser-inc.com (r9100-vpn.moser-inc.net [207.250.3.126] (may be forged)) by grumpy.moser-inc.net (8.11.6/8.11.6) with ESMTP id g8PLm2809583; Wed, 25 Sep 2002 16:48:02 -0500 Message-ID: <3D922DC7.80101@moser-inc.com> Date: Wed, 25 Sep 2002 16:42:31 -0500 From: Alan Hoyt User-Agent: Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.1) Gecko/20020826 X-Accept-Language: en-us, en MIME-Version: 1.0 To: Mike Mason CC: Mark Goodwin , "Davis, Todd C" , pcp@oss.sgi.com Subject: Re: PCP patch for top/libgtop conversion References: <3D92097E.7070901@us.ibm.com> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-archive-position: 18 X-ecartis-version: Ecartis v1.0.0 Sender: pcp-bounce@oss.sgi.com Errors-to: pcp-bounce@oss.sgi.com X-original-sender: ahoyt@moser-inc.com Precedence: bulk X-list: pcp If there is something that PCP contributors can do to help - I would be willing. Those scripts would be of enormous benefit. - Alan - Mike Mason wrote: > Mark Goodwin wrote: > >> On Tue, 24 Sep 2002, Davis, Todd C wrote: >> > >> PCP has a suite of approx 600 scripts for testing and quality assurance >> (QA) - this suite was originally developed for the proprietary >> version of >> PCP on IRIX over many years, and has been ported to Linux but has not >> been released open source. Although it's a reasonable request, the work >> to release it open source would be hard for me to justify. >> > > > Todd, is the lack of these test suites in open source a show stopper > for CGLE? > > Mark, what work is required to release the tests into open source? > Is it mainly getting approvals from SGI legal or something else? > > Is there something that PCP contributors can do to help? > > > Regards, > > Mike > > > From dtj@uberh4x0r.org Wed Sep 25 15:09:45 2002 Received: with ECARTIS (v1.0.0; list pcp); Wed, 25 Sep 2002 15:09:47 -0700 (PDT) Received: from mhro1.mayo.edu (mhro1.mayo.edu [129.176.212.21]) by oss.sgi.com (8.12.5/8.12.5) with SMTP id g8PM9itG014248 for ; Wed, 25 Sep 2002 15:09:45 -0700 Received: from daytona.mayo.edu by mhro1.mayo.edu with ESMTP; Wed, 25 Sep 2002 17:09:36 -0500 Received: from samer ([129.176.201.182]) by daytona.mayo.edu (SGI-8.9.3/8.9.3) with ESMTP id RAA53543; Wed, 25 Sep 2002 17:09:34 -0500 (CDT) Subject: Re: PCP patch for top/libgtop conversion From: Dean Johnson To: Alan Hoyt Cc: Mike Mason , Mark Goodwin , "Davis, Todd C" , pcp@oss.sgi.com In-Reply-To: <3D922DC7.80101@moser-inc.com> References: <3D92097E.7070901@us.ibm.com> <3D922DC7.80101@moser-inc.com> Content-Type: text/plain Content-Transfer-Encoding: 7bit X-Mailer: Ximian Evolution 1.0.8 Date: 25 Sep 2002 17:09:32 -0500 Message-Id: <1032991775.29866.275.camel@samer> Mime-Version: 1.0 X-archive-position: 19 X-ecartis-version: Ecartis v1.0.0 Sender: pcp-bounce@oss.sgi.com Errors-to: pcp-bounce@oss.sgi.com X-original-sender: dtj@uberh4x0r.org Precedence: bulk X-list: pcp On Wed, 2002-09-25 at 16:42, Alan Hoyt wrote: > If there is something that PCP contributors can do to help - I would be > willing. Those scripts would be of enormous benefit. > Perhaps this would be a good contribution of PCP users back to PCP, namely the generation of a bunch of tests for an open source test suite. With a small bit of guidance from Mark (and crew), along with a bit of discussion, everyone could write up a simple test or two. Time to pass the intellectual hat... The frequent nightmares about dealing with SGI lawyers about intellectual property issues has nearly subsided. ;-) Thats not an SGI slam, as I believe that most large corps would yield the same level of IP "entertainment". Just my $.02 -Dean From kenmcd@melbourne.sgi.com Wed Sep 25 15:55:26 2002 Received: with ECARTIS (v1.0.0; list pcp); Wed, 25 Sep 2002 15:55:28 -0700 (PDT) Received: from deliverator.sgi.com (deliverator.SGI.COM [204.94.214.10] (may be forged)) by oss.sgi.com (8.12.5/8.12.5) with SMTP id g8PMtPtG019218 for ; Wed, 25 Sep 2002 15:55:26 -0700 Received: from rattle.melbourne.sgi.com (rattle.melbourne.sgi.com [134.14.55.145]) by deliverator.sgi.com (980327.SGI.8.8.8-aspam/980304.SGI-aspam: SGI does not authorize the use of its proprietary systems or networks for unsolicited or bulk email from the Internet.) via ESMTP id PAA09853 for ; Wed, 25 Sep 2002 15:55:24 -0700 (PDT) mail_from (kenmcd@melbourne.sgi.com) Received: from localhost (kenmcd@localhost) by rattle.melbourne.sgi.com (SGI-8.9.3/8.9.3) with ESMTP id IAA28147; Thu, 26 Sep 2002 08:54:04 +1000 (EST) X-Authentication-Warning: rattle.melbourne.sgi.com: kenmcd owned process doing -bs Date: Thu, 26 Sep 2002 08:54:04 +1000 From: Ken McDonell To: Alan Hoyt cc: Mike Mason , Mark Goodwin , "Davis, Todd C" , Subject: Access to the PCP QA Suite In-Reply-To: <3D922DC7.80101@moser-inc.com> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII X-archive-position: 20 X-ecartis-version: Ecartis v1.0.0 Sender: pcp-bounce@oss.sgi.com Errors-to: pcp-bounce@oss.sgi.com X-original-sender: kenmcd@melbourne.sgi.com Precedence: bulk X-list: pcp I've been lurking (and enjoying the sudden flurry of activity on the list!). The issues for the PCP QA are as follows: 0. The value to PCP developers and PCP in general is beyond dispute, so this is _not_ an issue. 1. It is _big_ - 600+ scripts, 180+ source files with 42,000+ lines of code. 2. The whole suite runs daily on a number of machines within SGI, and has a fair degree of local customization ... hostnames where various versions of PCP are running, ip addr of a friednly Cisco router, hostname where a promiscuous X server is hiding, etc 3. It has a lot of multi-platform infrastructre with individual tests that are skipped on IRIX or some IRIX versions, ia32 Linux, ia64 Linux, some versions of PCP, etc. As more platforms are added to the mix this will grow. 4. There is a large potential for gatekeeper load to answer questions based on 1. to 3. above and to reconcile changes back from the community. There is little point in making the suite available and then not following up with the gatekeeper function. 5. We have a potential takeback assignment problem ... the PCP QA suite is used within SGI as QA for the proprietary version of PCP ... not everyone would be happy to have changes taken back by SGI to be used in this way. Note there is no issue associated with IP or releasing this to the open source community as a matter of principle (I'm a member of the SGI committee that judges these matters, so I'm pretty sure of this). The _big_ item is 4. ... I just do not have the resources to sign up to this at the level required to ensure the test suite remains useful to SGI and the community. I'm open to any creative suggestions that would help us more forward on this matter. From kenmcd@melbourne.sgi.com Wed Sep 25 17:12:21 2002 Received: with ECARTIS (v1.0.0; list pcp); Wed, 25 Sep 2002 17:12:22 -0700 (PDT) Received: from deliverator.sgi.com (deliverator.SGI.COM [204.94.214.10] (may be forged)) by oss.sgi.com (8.12.5/8.12.5) with SMTP id g8Q0CKtG021996 for ; Wed, 25 Sep 2002 17:12:20 -0700 Received: from rattle.melbourne.sgi.com (rattle.melbourne.sgi.com [134.14.55.145]) by deliverator.sgi.com (980327.SGI.8.8.8-aspam/980304.SGI-aspam: SGI does not authorize the use of its proprietary systems or networks for unsolicited or bulk email from the Internet.) via ESMTP id RAA03539 for ; Wed, 25 Sep 2002 17:12:19 -0700 (PDT) mail_from (kenmcd@melbourne.sgi.com) Received: from localhost (kenmcd@localhost) by rattle.melbourne.sgi.com (SGI-8.9.3/8.9.3) with ESMTP id KAA98478; Thu, 26 Sep 2002 10:10:57 +1000 (EST) X-Authentication-Warning: rattle.melbourne.sgi.com: kenmcd owned process doing -bs Date: Thu, 26 Sep 2002 10:10:57 +1000 From: Ken McDonell To: "Davis, Todd C" cc: Mike Mason , Mark Goodwin , Subject: RE: PCP patch for top/libgtop conversion In-Reply-To: <29AD895CE780D511A8870002A50A666D04F9083B@hdsmsx106.hd.intel.com> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII X-archive-position: 21 X-ecartis-version: Ecartis v1.0.0 Sender: pcp-bounce@oss.sgi.com Errors-to: pcp-bounce@oss.sgi.com X-original-sender: kenmcd@melbourne.sgi.com Precedence: bulk X-list: pcp On Tue, 24 Sep 2002, Davis, Todd C wrote: > How are patches like this and other changes to PCP tested and verified to be > correct? I think enterprise class system utilities like PCP require a much > higher level of qualify assurance than the typical open source project. ... Agreed. I think Mark has responded to this, but I'd like to add ... - for about 6 years before we made the open source release, PCP was a successful production-hardened proprietary product deployed on varied and some very large (500+ CPUs, multi-Tb memory, 10's of Tb of disk, ...) systems, so we are very QA-sensitive. - the PCP QA infrastructure grew with PCP, it is not an after thought - we use common source code internally to generate both the proprietary and the open source versions, so we have a vested interest in quality that extends beyond the open source code base - as all those who've worked with me on PCP will attest, I'm inclined to be obsessive about QA! > ... What > verification procedures does SGI go through before making a source tarball > release? I think test suites should be made available to developers to use > when making enhancements and bug fixes so changes can be verified. Tests > could also be submitted with any enhancements before being accepted by the > PCP project. Test suites can also be useful in verifying an installation of > PCP. I posted a detailed response on this topic earlier today. From kenmcd@melbourne.sgi.com Wed Sep 25 17:36:27 2002 Received: with ECARTIS (v1.0.0; list pcp); Wed, 25 Sep 2002 17:36:30 -0700 (PDT) Received: from deliverator.sgi.com (deliverator.SGI.COM [204.94.214.10] (may be forged)) by oss.sgi.com (8.12.5/8.12.5) with SMTP id g8Q0aQtG023071 for ; Wed, 25 Sep 2002 17:36:27 -0700 Received: from rattle.melbourne.sgi.com (rattle.melbourne.sgi.com [134.14.55.145]) by deliverator.sgi.com (980327.SGI.8.8.8-aspam/980304.SGI-aspam: SGI does not authorize the use of its proprietary systems or networks for unsolicited or bulk email from the Internet.) via ESMTP id RAA01033 for ; Wed, 25 Sep 2002 17:36:23 -0700 (PDT) mail_from (kenmcd@melbourne.sgi.com) Received: from localhost (kenmcd@localhost) by rattle.melbourne.sgi.com (SGI-8.9.3/8.9.3) with ESMTP id KAA23060; Thu, 26 Sep 2002 10:35:02 +1000 (EST) X-Authentication-Warning: rattle.melbourne.sgi.com: kenmcd owned process doing -bs Date: Thu, 26 Sep 2002 10:35:02 +1000 From: Ken McDonell To: Mike Mason cc: Jan-Frode Myklebust , Subject: Re: PCP patch for top/libgtop conversion In-Reply-To: <3D91EB06.9070200@us.ibm.com> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII X-archive-position: 22 X-ecartis-version: Ecartis v1.0.0 Sender: pcp-bounce@oss.sgi.com Errors-to: pcp-bounce@oss.sgi.com X-original-sender: kenmcd@melbourne.sgi.com Precedence: bulk X-list: pcp On Wed, 25 Sep 2002, Mike Mason wrote: > Yes, the top conversion can access remote pmcd's, but currently only one > at a time. What's the consensus of the people on this list? Would > displaying data from multiple hosts in a single top session be generally > useful? I think this would be a dramatic demonstration of one of the biggest *wins* that the distributed PCP model delivers ... it is less dramatic with the one-host-only variant (even if that one host may be remote). I know this is more work, but not a bucket load (multiple PMAPI contexts, and a PMAPI context field in your local variant of the per-process data) ... I'm sure if the PCP-aware version of the top source code was available, a multi-host version would appear pretty quick smart. From kenmcd@melbourne.sgi.com Wed Sep 25 19:09:08 2002 Received: with ECARTIS (v1.0.0; list pcp); Wed, 25 Sep 2002 19:09:11 -0700 (PDT) Received: from deliverator.sgi.com (deliverator.SGI.COM [204.94.214.10] (may be forged)) by oss.sgi.com (8.12.5/8.12.5) with SMTP id g8Q297tG026015 for ; Wed, 25 Sep 2002 19:09:08 -0700 Received: from rattle.melbourne.sgi.com (rattle.melbourne.sgi.com [134.14.55.145]) by deliverator.sgi.com (980327.SGI.8.8.8-aspam/980304.SGI-aspam: SGI does not authorize the use of its proprietary systems or networks for unsolicited or bulk email from the Internet.) via ESMTP id TAA08047 for ; Wed, 25 Sep 2002 19:09:06 -0700 (PDT) mail_from (kenmcd@melbourne.sgi.com) Received: from localhost (kenmcd@localhost) by rattle.melbourne.sgi.com (SGI-8.9.3/8.9.3) with ESMTP id MAA30178; Thu, 26 Sep 2002 12:07:47 +1000 (EST) X-Authentication-Warning: rattle.melbourne.sgi.com: kenmcd owned process doing -bs Date: Thu, 26 Sep 2002 12:07:47 +1000 From: Ken McDonell To: Mike Mason cc: Mark Goodwin , Subject: Re: PCP patch for top/libgtop conversion In-Reply-To: <3D91EFB4.20404@us.ibm.com> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII X-archive-position: 23 X-ecartis-version: Ecartis v1.0.0 Sender: pcp-bounce@oss.sgi.com Errors-to: pcp-bounce@oss.sgi.com X-original-sender: kenmcd@melbourne.sgi.com Precedence: bulk X-list: pcp On Wed, 25 Sep 2002, Mike Mason wrote: > Mark, > ... > > > > > > >>(new) Per process map info from /proc//maps > >> proc.memory.maps > > > > > > Seems OK. Did you need this to be specifically the same as cat /proc/*/maps > > i.e. a very long string? Does it still work OK if the maps for a particular > > process exceeds the copyout limit (one page)? > > > > > > This is needed by libgtop. I couldn't think of any other way to > represent the maps in PCP. As far as I know, there's no way to > represent instances within instances. Have you ever considered adding > the capability? > > I don't think the copyout limit is an issue for PCP. There's code in > proc/array.c to handle maps files greater than 4K. We just read it, so > I don't think we need to do anything special. Seems like there are several issues sort of intermingled here ... 1. The copyout problem ... I think there remains a systemic Linux issue with any /proc "file" that is longer than your page size du jour ... if the underlying data is subject to change, there is no way a user space app (cat(1) is the simplest example) is guaranteed to see a consistent view ... you may miss whole lines, you may see some lines more than once. If this assertion is not correct, I'd like to understand why. This is pretty much independent of what PCP chooses to do with the data. 2. The n-dimensional instance domain issue ... this is a PCP matter. The set-based {metric} x {instance} data model is fundamental to PCP and something I would defend to the death. On the other hand from the outset, we strove for simplicity, light-weight collection cost and fought off all suggestions for premature optimizations. This is how we got to treating instance domains as a 1-dimensional vector indexed by an almost 32-bit instance identifier (2^31-1 is special, aka PM_IN_NULL, so the PMDA gets the instances 0 thru 2^31-2 to play with) and allowing up to 256 PMDAs each with up to 4194304 (2^22) independent instance domains. The limit on the size of a "string" value that can be returned from a PMDA for a single metric-instance pair is 16777215 (2^24-1) bytes. In practice we've alwys been able to accommodate the apparent need for a multi-dimensional instance domain by either: (a) casting one of the dimensions into the namespace, i.e. enumerate named metrics for each row or column in one of the dimensions, e.g. table.row1 ["col1"] val table.row1 ["col2"] val ... table.row2 ["col1"] val table.row2 ["col2"] val ... and/or (b) encoding a set of values for one of the dimensions in a string value associated with one of the other dimensions, e.g. table ["row1"] "col1-val:col2-val:..." table ["row2"] "col1-val:col2-val:..." ... So we have definitely considered this capability (many times over), but so far resisted the monumental changes that embracing this would entail. Counter-arguments, as always, would be most welcome. From ahoyt@moser-inc.com Thu Sep 26 07:43:31 2002 Received: with ECARTIS (v1.0.0; list pcp); Thu, 26 Sep 2002 07:43:34 -0700 (PDT) Received: from grumpy.moser-inc.net ([207.250.3.115]) by oss.sgi.com (8.12.5/8.12.5) with SMTP id g8QEhUtG006105 for ; Thu, 26 Sep 2002 07:43:31 -0700 Received: from moser-inc.com (r9100-vpn.moser-inc.net [207.250.3.126] (may be forged)) by grumpy.moser-inc.net (8.11.6/8.11.6) with ESMTP id g8QEmr829773; Thu, 26 Sep 2002 09:48:53 -0500 Message-ID: <3D931D05.8020603@moser-inc.com> Date: Thu, 26 Sep 2002 09:43:17 -0500 From: Alan Hoyt User-Agent: Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.1) Gecko/20020826 X-Accept-Language: en-us, en MIME-Version: 1.0 To: Ken McDonell CC: Mike Mason , Mark Goodwin , "Davis, Todd C" , pcp@oss.sgi.com Subject: Re: Access to the PCP QA Suite References: Content-Type: text/plain; charset=windows-1252; format=flowed Content-Transfer-Encoding: 7bit X-archive-position: 24 X-ecartis-version: Ecartis v1.0.0 Sender: pcp-bounce@oss.sgi.com Errors-to: pcp-bounce@oss.sgi.com X-original-sender: ahoyt@moser-inc.com Precedence: bulk X-list: pcp Yes, this is rather problematic. Not having seen the code, I am flying blind here - but wouldnt large portions of the QA code base be relatively constant/stable? Couldn't most of the hard coded dependencies be abstracted into configuration/initialization files to minimize architectural /topological dependencies? In other words, could we substantially reduce the gatekeeper load through well conceived code changes/clean ups (sounds like a catch 22)? If not, the simplest solution would be to release PCP along with the QA scripts that were used to validate it (i.e. without accepting QA script patches). At least the community would have tools to exhaustively verify PCP changes before they were submitted/deployed. Possibly, you could monitor QA script changes made by the community and determine (at that time) whether there is any benefit for SGI to incorporate those changes. - Alan - Ken McDonell wrote: >I've been lurking (and enjoying the sudden flurry of activity on the >list!). > >The issues for the PCP QA are as follows: > >0. The value to PCP developers and PCP in general is beyond dispute, > so this is _not_ an issue. > >1. It is _big_ - 600+ scripts, 180+ source files with 42,000+ lines of > code. > >2. The whole suite runs daily on a number of machines within SGI, and > has a fair degree of local customization ... hostnames where various > versions of PCP are running, ip addr of a friednly Cisco router, > hostname where a promiscuous X server is hiding, etc > >3. It has a lot of multi-platform infrastructre with individual tests > that are skipped on IRIX or some IRIX versions, ia32 Linux, ia64 > Linux, some versions of PCP, etc. As more platforms are added to > the mix this will grow. > >4. There is a large potential for gatekeeper load to answer questions > based on 1. to 3. above and to reconcile changes back from the > community. There is little point in making the suite available > and then not following up with the gatekeeper function. > >5. We have a potential takeback assignment problem ... the PCP QA suite > is used within SGI as QA for the proprietary version of PCP ... not > everyone would be happy to have changes taken back by SGI to be used > in this way. > >Note there is no issue associated with IP or releasing this to the open >source community as a matter of principle (I'm a member of the SGI >committee that judges these matters, so I'm pretty sure of this). > >The _big_ item is 4. ... I just do not have the resources to sign up to >this at the level required to ensure the test suite remains useful to >SGI and the community. > >I'm open to any creative suggestions that would help us more forward on >this matter. > > > > From dtj@uberh4x0r.org Thu Sep 26 08:12:38 2002 Received: with ECARTIS (v1.0.0; list pcp); Thu, 26 Sep 2002 08:12:42 -0700 (PDT) Received: from mhro1.mayo.edu (mhro1.mayo.edu [129.176.212.21]) by oss.sgi.com (8.12.5/8.12.5) with SMTP id g8QFCctG008101 for ; Thu, 26 Sep 2002 08:12:38 -0700 Received: from daytona.mayo.edu by mhro1.mayo.edu with ESMTP for pcp@oss.sgi.com; Thu, 26 Sep 2002 10:12:36 -0500 Received: from samer ([129.176.201.182]) by daytona.mayo.edu (SGI-8.9.3/8.9.3) with ESMTP id KAA42807 for ; Thu, 26 Sep 2002 10:12:36 -0500 (CDT) Subject: Re: Access to the PCP QA Suite From: Dean Johnson To: pcp@oss.sgi.com In-Reply-To: <3D931D05.8020603@moser-inc.com> References: <3D931D05.8020603@moser-inc.com> Content-Type: text/plain Content-Transfer-Encoding: 7bit X-Mailer: Ximian Evolution 1.0.8 Date: 26 Sep 2002 10:12:35 -0500 Message-Id: <1033053155.31445.1313.camel@samer> Mime-Version: 1.0 X-archive-position: 25 X-ecartis-version: Ecartis v1.0.0 Sender: pcp-bounce@oss.sgi.com Errors-to: pcp-bounce@oss.sgi.com X-original-sender: dtj@uberh4x0r.org Precedence: bulk X-list: pcp On Thu, 2002-09-26 at 09:43, Alan Hoyt wrote: > Yes, this is rather problematic. > > Not having seen the code, I am flying blind here - but wouldnt large > portions of the QA code base be relatively constant/stable? > > Couldn't most of the hard coded dependencies be abstracted into > configuration/initialization files to minimize architectural > /topological dependencies? > > In other words, could we substantially reduce the gatekeeper load > through well conceived code changes/clean ups (sounds like a catch 22)? > > If not, the simplest solution would be to release PCP along with the QA > scripts that were used to validate it (i.e. without accepting QA script > patches). At least the community would have tools to exhaustively verify > PCP changes before they were submitted/deployed. > > Possibly, you could monitor QA script changes made by the community and > determine (at that time) whether there is any benefit for SGI to > incorporate those changes. > I suspect that its a great deal like renovating houses, at some point the renovations become so massive and complex that its just easier to tear it down and start from scratch. I believe the easiest and best way to approach this is to have bribe Ken (and Co.) to write a small document that would outline the steps to creating a PCP test base and what actually constitutes effective PCP QA (what!?!?! "it compiles" doesn't count? ;-)). Once the community has an idea of where to start, then its a matter of mapping out areas for interested people to focus on. Perhaps, if things go well, Ken can throw some tests over the wall to be added, not to mention he could incorporate some of the open source tests. I suspect, based on personal experience, that Ken already has a very clear idea of how it would be structured and its a matter of getting it down on paper. Of course I am in no position to volunteer Ken for anything. ;-) -Dean From ahoyt@moser-inc.com Thu Sep 26 09:13:57 2002 Received: with ECARTIS (v1.0.0; list pcp); Thu, 26 Sep 2002 09:13:59 -0700 (PDT) Received: from grumpy.moser-inc.net ([207.250.3.115]) by oss.sgi.com (8.12.5/8.12.5) with SMTP id g8QGDvtG011526 for ; Thu, 26 Sep 2002 09:13:57 -0700 Received: from moser-inc.com (r9100-vpn.moser-inc.net [207.250.3.126] (may be forged)) by grumpy.moser-inc.net (8.11.6/8.11.6) with ESMTP id g8QGJL832663; Thu, 26 Sep 2002 11:19:21 -0500 Message-ID: <3D933239.5090809@moser-inc.com> Date: Thu, 26 Sep 2002 11:13:45 -0500 From: Alan Hoyt User-Agent: Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.1) Gecko/20020826 X-Accept-Language: en-us, en MIME-Version: 1.0 To: Dean Johnson CC: pcp@oss.sgi.com Subject: Re: Access to the PCP QA Suite References: <3D931D05.8020603@moser-inc.com> <1033053155.31445.1313.camel@samer> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-archive-position: 26 X-ecartis-version: Ecartis v1.0.0 Sender: pcp-bounce@oss.sgi.com Errors-to: pcp-bounce@oss.sgi.com X-original-sender: ahoyt@moser-inc.com Precedence: bulk X-list: pcp Given a choice - I would have a propensity to NOT reinvent the wheel - we cannot presuppose that the scripts are filled with bloat and cruft - maybe SGI had prudent maintainers. Most likely, any QA scripts supporting the diversity of architectures supported by PCP would eventually be of comparable size and complexity, regardless of being community driven. Your approach would result in the same effect as branching. - Alan - Dean Johnson wrote: > >I suspect that its a great deal like renovating houses, at some point >the renovations become so massive and complex that its just easier to >tear it down and start from scratch. > >I believe the easiest and best way to approach this is to have bribe Ken >(and Co.) to write a small document that would outline the steps to >creating a PCP test base and what actually constitutes effective PCP QA >(what!?!?! "it compiles" doesn't count? ;-)). Once the community has an >idea of where to start, then its a matter of mapping out areas for >interested people to focus on. Perhaps, if things go well, Ken can throw >some tests over the wall to be added, not to mention he could >incorporate some of the open source tests. I suspect, based on personal >experience, that Ken already has a very clear idea of how it would be >structured and its a matter of getting it down on paper. > >Of course I am in no position to volunteer Ken for anything. ;-) > > -Dean > > > > > From mmlnx@us.ibm.com Thu Sep 26 13:35:57 2002 Received: with ECARTIS (v1.0.0; list pcp); Thu, 26 Sep 2002 13:35:59 -0700 (PDT) Received: from e35.co.us.ibm.com (e35.co.us.ibm.com [32.97.110.133]) by oss.sgi.com (8.12.5/8.12.5) with SMTP id g8QKZutG031597 for ; Thu, 26 Sep 2002 13:35:57 -0700 Received: from westrelay01.boulder.ibm.com (westrelay01.boulder.ibm.com [9.17.194.22]) by e35.co.us.ibm.com (8.12.2/8.12.2) with ESMTP id g8QKZegF070886; Thu, 26 Sep 2002 16:35:40 -0400 Received: from us.ibm.com (sig-9-65-51-227.mts.ibm.com [9.65.51.227]) by westrelay01.boulder.ibm.com (8.12.3/NCO/VER6.4) with ESMTP id g8QKZcKG026210; Thu, 26 Sep 2002 14:35:39 -0600 Message-ID: <3D936F9D.5010401@us.ibm.com> Date: Thu, 26 Sep 2002 13:35:41 -0700 From: Mike Mason User-Agent: Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.0.1) Gecko/20020823 Netscape/7.0 X-Accept-Language: en-us, en MIME-Version: 1.0 To: Ken McDonell CC: Alan Hoyt , Mark Goodwin , "Davis, Todd C" , pcp@oss.sgi.com Subject: Re: Access to the PCP QA Suite References: Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit X-archive-position: 27 X-ecartis-version: Ecartis v1.0.0 Sender: pcp-bounce@oss.sgi.com Errors-to: pcp-bounce@oss.sgi.com X-original-sender: mmlnx@us.ibm.com Precedence: bulk X-list: pcp How would you feel about a separate open source QA suite that uses the existing suite (or a subset) as a starting point, then evolves separately from the proprietary suite. I know it's not ideal, but it's better than no open source suite or starting from scratch in my opinion. SGI could contribute the existing suite with the caveat that it has limited resources to contribute or answer questions. PCP contributors and others, like the CGL validation team, could modify the test suite into something suitable for the open source community. Distros and groups like CGL would be more likely to adopt PCP if this suite existed. Ken McDonell wrote: > I've been lurking (and enjoying the sudden flurry of activity on the > list!). > > The issues for the PCP QA are as follows: > > 0. The value to PCP developers and PCP in general is beyond dispute, > so this is _not_ an issue. > > 1. It is _big_ - 600+ scripts, 180+ source files with 42,000+ lines of > code. > > 2. The whole suite runs daily on a number of machines within SGI, and > has a fair degree of local customization ... hostnames where various > versions of PCP are running, ip addr of a friednly Cisco router, > hostname where a promiscuous X server is hiding, etc > > 3. It has a lot of multi-platform infrastructre with individual tests > that are skipped on IRIX or some IRIX versions, ia32 Linux, ia64 > Linux, some versions of PCP, etc. As more platforms are added to > the mix this will grow. > > 4. There is a large potential for gatekeeper load to answer questions > based on 1. to 3. above and to reconcile changes back from the > community. There is little point in making the suite available > and then not following up with the gatekeeper function. > > 5. We have a potential takeback assignment problem ... the PCP QA suite > is used within SGI as QA for the proprietary version of PCP ... not > everyone would be happy to have changes taken back by SGI to be used > in this way. > > Note there is no issue associated with IP or releasing this to the open > source community as a matter of principle (I'm a member of the SGI > committee that judges these matters, so I'm pretty sure of this). > > The _big_ item is 4. ... I just do not have the resources to sign up to > this at the level required to ensure the test suite remains useful to > SGI and the community. > > I'm open to any creative suggestions that would help us more forward on > this matter. > > -- Mike Mason IBM Linux Technology Center, RAS Group Beaverton, OR, USA mmlnx@us.ibm.com (503) 578-4123 From kenmcd@melbourne.sgi.com Thu Sep 26 17:22:03 2002 Received: with ECARTIS (v1.0.0; list pcp); Thu, 26 Sep 2002 17:22:06 -0700 (PDT) Received: from deliverator.sgi.com (deliverator.SGI.COM [204.94.214.10] (may be forged)) by oss.sgi.com (8.12.5/8.12.5) with SMTP id g8R0M3tG026349 for ; Thu, 26 Sep 2002 17:22:03 -0700 Received: from larry.melbourne.sgi.com (larry.melbourne.sgi.com [134.14.52.130]) by deliverator.sgi.com (980327.SGI.8.8.8-aspam/980304.SGI-aspam: SGI does not authorize the use of its proprietary systems or networks for unsolicited or bulk email from the Internet.) via SMTP id RAA05847 for ; Thu, 26 Sep 2002 17:22:01 -0700 (PDT) mail_from (kenmcd@melbourne.sgi.com) From: kenmcd@melbourne.sgi.com Received: from kenj-ppp.melbourne.sgi.com (kenj-ppp.melbourne.sgi.com [134.14.55.215]) by larry.melbourne.sgi.com (950413.SGI.8.6.12/950213.SGI.AUTOCF) via ESMTP id KAA29613; Fri, 27 Sep 2002 10:20:39 +1000 Date: Fri, 27 Sep 2002 10:21:54 +1000 (EST) Reply-To: kenmcd@melbourne.sgi.com To: "Davis, Todd C" cc: "'Mike Mason'" , Subject: RE: CGLE (was Re: PCP patch for top/libgtop conversion) In-Reply-To: <29AD895CE780D511A8870002A50A666D04F90841@hdsmsx106.hd.intel.com> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII X-archive-position: 28 X-ecartis-version: Ecartis v1.0.0 Sender: pcp-bounce@oss.sgi.com Errors-to: pcp-bounce@oss.sgi.com X-original-sender: kenmcd@melbourne.sgi.com Precedence: bulk X-list: pcp On Thu, 26 Sep 2002, Davis, Todd C wrote: > I would say that PCP fully meets the CGLE requirements and I don't have any > technical issues at this time but then my exposure to PCP is less than a > week old. My biggest issue at this time is the documentation. It is very > good documentation but there is no distinction between the open source and > SGI proprietary components. I personally would like to see the open source > docs scrubbed of all SGI proprietary references. Could I ask which documentation you are referring to? Options might be ... - man pages in the oss.sgi.com rpms ... these should be OK I believe - html tutorial (that I don't think we've released to open source, but certainly could ... it is a resource issue, so if someone volunteered to audit, cleanup and edit the html we could certainly work together on this) - the User and Administrator Guide and the Programmer's Guide from techpubs.sgi.com ... the Programmer's Guide is platform agnostic I believe, the other Guide is IRIX-centric and we're in the process of splitting this into an IRIX version and a Linux version - perhaps something else, if so what? From mmlnx@us.ibm.com Fri Sep 27 10:07:31 2002 Received: with ECARTIS (v1.0.0; list pcp); Fri, 27 Sep 2002 10:07:35 -0700 (PDT) Received: from e2.ny.us.ibm.com (e2.ny.us.ibm.com [32.97.182.102]) by oss.sgi.com (8.12.5/8.12.5) with SMTP id g8RH7VtG016735 for ; Fri, 27 Sep 2002 10:07:31 -0700 Received: from northrelay01.pok.ibm.com (northrelay01.pok.ibm.com [9.56.224.149]) by e2.ny.us.ibm.com (8.12.2/8.12.2) with ESMTP id g8RH7PVL246726; Fri, 27 Sep 2002 13:07:25 -0400 Received: from us.ibm.com (sig-9-65-26-54.mts.ibm.com [9.65.26.54]) by northrelay01.pok.ibm.com (8.12.3/NCO/VER6.4) with ESMTP id g8RH7MaE125936; Fri, 27 Sep 2002 13:07:22 -0400 Message-ID: <3D94904E.9050905@us.ibm.com> Date: Fri, 27 Sep 2002 10:07:26 -0700 From: Mike Mason User-Agent: Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.0.1) Gecko/20020823 Netscape/7.0 X-Accept-Language: en-us, en MIME-Version: 1.0 To: Mark Goodwin CC: pcp@oss.sgi.com Subject: Fix for /proc//status problem References: Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit X-archive-position: 29 X-ecartis-version: Ecartis v1.0.0 Sender: pcp-bounce@oss.sgi.com Errors-to: pcp-bounce@oss.sgi.com X-original-sender: mmlnx@us.ibm.com Precedence: bulk X-list: pcp Here's a patch to fix the "one off" problem in proc.memory.vm* . I had started numbering the status cluster at 1 instead of 0 in root_linux. Mike --- pcp-2.2.2/src/pmdas/linux/root_linux Fri Sep 27 09:51:55 2002 +++ pcp-2.2.2.PATCHED/src/pmdas/linux/root_linux Fri Sep 27 09:42:55 2002 @@ -499,29 +499,29 @@ ttyname 60:8:39 wchan_s 60:8:40 psargs 60:8:41 - signal_s 60:24:17 - blocked_s 60:24:18 - sigignore_s 60:24:19 - sigcatch_s 60:24:20 + signal_s 60:24:16 + blocked_s 60:24:17 + sigignore_s 60:24:18 + sigcatch_s 60:24:19 } proc.id { - uid 60:24:1 - euid 60:24:2 - suid 60:24:3 - fsuid 60:24:4 - gid 60:24:5 - egid 60:24:6 - sgid 60:24:7 - fsgid 60:24:8 - uid_nm 60:24:9 - euid_nm 60:24:10 - suid_nm 60:24:11 - fsuid_nm 60:24:12 - gid_nm 60:24:13 - egid_nm 60:24:14 - sgid_nm 60:24:15 - fsgid_nm 60:24:16 + uid 60:24:0 + euid 60:24:1 + suid 60:24:2 + fsuid 60:24:3 + gid 60:24:4 + egid 60:24:5 + sgid 60:24:6 + fsgid 60:24:7 + uid_nm 60:24:8 + euid_nm 60:24:9 + suid_nm 60:24:10 + fsuid_nm 60:24:11 + gid_nm 60:24:12 + egid_nm 60:24:13 + sgid_nm 60:24:14 + fsgid_nm 60:24:15 } proc.memory { @@ -533,13 +533,13 @@ datrss 60:9:5 dirty 60:9:6 maps 60:9:7 - vmsize 60:24:21 - vmlock 60:24:22 - vmrss 60:24:23 - vmdata 60:24:24 - vmstack 60:24:25 - vmexe 60:24:26 - vmlib 60:24:27 + vmsize 60:24:20 + vmlock 60:24:21 + vmrss 60:24:22 + vmdata 60:24:23 + vmstack 60:24:24 + vmexe 60:24:25 + vmlib 60:24:26 } proc.runq { From todd.c.davis@intel.com Mon Sep 30 08:13:46 2002 Received: with ECARTIS (v1.0.0; list pcp); Mon, 30 Sep 2002 08:13:48 -0700 (PDT) Received: from momus.sc.intel.com (momus.sc.intel.com [143.183.152.8]) by oss.sgi.com (8.12.5/8.12.5) with SMTP id g8UFDatG026671 for ; Mon, 30 Sep 2002 08:13:36 -0700 Received: from fmsmsxvs042.fm.intel.com (fmsmsxvs042.fm.intel.com [132.233.42.128]) by momus.sc.intel.com (8.11.6/8.11.6/d: solo.mc,v 1.46 2002/09/23 20:41:22 dmccart Exp $) with SMTP id g8UFDBp11338 for ; Mon, 30 Sep 2002 15:13:21 GMT Received: from FMSMSX018.fm.intel.com ([132.233.42.197]) by fmsmsxvs042.fm.intel.com (NAVGW 2.5.2.11) with SMTP id M2002093008140414885 ; Mon, 30 Sep 2002 08:14:04 -0700 Received: by fmsmsx018.fm.intel.com with Internet Mail Service (5.5.2653.19) id ; Mon, 30 Sep 2002 08:12:35 -0700 Message-ID: <29AD895CE780D511A8870002A50A666D04F90845@hdsmsx106.hd.intel.com> From: "Davis, Todd C" To: "'kenmcd@melbourne.sgi.com'" , "Davis, Todd C" Cc: "'Mike Mason'" , pcp@oss.sgi.com Subject: RE: CGLE (was Re: PCP patch for top/libgtop conversion) Date: Mon, 30 Sep 2002 08:19:03 -0700 MIME-Version: 1.0 X-Mailer: Internet Mail Service (5.5.2653.19) Content-Type: text/plain X-archive-position: 30 X-ecartis-version: Ecartis v1.0.0 Sender: pcp-bounce@oss.sgi.com Errors-to: pcp-bounce@oss.sgi.com X-original-sender: todd.c.davis@intel.com Precedence: bulk X-list: pcp Todd C. Davis These are my opinions and absolutely not official opinions of Intel Corp. -----Original Message----- From: kenmcd@melbourne.sgi.com [mailto:kenmcd@melbourne.sgi.com] Sent: Thursday, September 26, 2002 8:22 PM To: Davis, Todd C Cc: 'Mike Mason'; pcp@oss.sgi.com Subject: RE: CGLE (was Re: PCP patch for top/libgtop conversion) On Thu, 26 Sep 2002, Davis, Todd C wrote: > I would say that PCP fully meets the CGLE requirements and I don't have any > technical issues at this time but then my exposure to PCP is less than a > week old. My biggest issue at this time is the documentation. It is very > good documentation but there is no distinction between the open source and > SGI proprietary components. I personally would like to see the open source > docs scrubbed of all SGI proprietary references. Could I ask which documentation you are referring to? Options might be ... - man pages in the oss.sgi.com rpms ... these should be OK I believe [Todd Davis] There are many references in the open source man pages to man pages for proprietary SGI utilities that are not included in the open source distribution. - html tutorial (that I don't think we've released to open source, but certainly could ... it is a resource issue, so if someone volunteered to audit, cleanup and edit the html we could certainly work together on this) [Todd Davis] I would be inclined to help here since I am still learning PCP and would like to view the tutorial myself. - the User and Administrator Guide and the Programmer's Guide from techpubs.sgi.com ... the Programmer's Guide is platform agnostic I believe, the other Guide is IRIX-centric and we're in the process of splitting this into an IRIX version and a Linux version [Todd Davis] Good. - perhaps something else, if so what? That is all. My main concern is the man pages. The Tutorial would be nice to have in open source. From markgw@sgi.com Mon Sep 30 22:18:47 2002 Received: with ECARTIS (v1.0.0; list pcp); Mon, 30 Sep 2002 22:18:48 -0700 (PDT) Received: from deliverator.sgi.com (deliverator.SGI.COM [204.94.214.10] (may be forged)) by oss.sgi.com (8.12.5/8.12.5) with SMTP id g915IktG016204 for ; Mon, 30 Sep 2002 22:18:46 -0700 Received: from larry.melbourne.sgi.com (larry.melbourne.sgi.com [134.14.52.130]) by deliverator.sgi.com (980327.SGI.8.8.8-aspam/980304.SGI-aspam: SGI does not authorize the use of its proprietary systems or networks for unsolicited or bulk email from the Internet.) via SMTP id WAA00764 for ; Mon, 30 Sep 2002 22:18:45 -0700 (PDT) mail_from (markgw@sgi.com) Received: from sherman.melbourne.sgi.com (sherman.melbourne.sgi.com [134.14.55.232]) by larry.melbourne.sgi.com (950413.SGI.8.6.12/950213.SGI.AUTOCF) via ESMTP id PAA04020; Tue, 1 Oct 2002 15:17:24 +1000 Date: Tue, 1 Oct 2002 15:17:24 +1000 (EST) From: Mark Goodwin X-X-Sender: markgw@sherman.melbourne.sgi.com To: Mike Mason cc: pcp@oss.sgi.com Subject: Re: Fix for /proc//status problem In-Reply-To: <3D94904E.9050905@us.ibm.com> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII X-archive-position: 31 X-ecartis-version: Ecartis v1.0.0 Sender: pcp-bounce@oss.sgi.com Errors-to: pcp-bounce@oss.sgi.com X-original-sender: markgw@sgi.com Precedence: bulk X-list: pcp On Fri, 27 Sep 2002, Mike Mason wrote: > Here's a patch to fix the "one off" problem in proc.memory.vm* . I had > started numbering the status cluster at 1 instead of 0 in root_linux. thanks Mike, this patch fixes it. Sorry for the delay, I was out of town for three days. Also note: Ken is out of the office all this week, so don't expect any progress on the PCP QA questions/debate until next week. -- Mark