Re: There is a known problem with MIPS tinderbox.
On Fri, Apr 6, 2012 at 12:01 PM, Stanislav Sedov wrote: > > On Apr 5, 2012, at 11:08 PM, Jayachandran C. wrote: >> >> >> The asn1 library has a export map containing 'global: *', this exports >> two symbols _fdata and _ftext versioned. When libkafs5 is linked, >> these symbols confuse the bfd code and the entries corresponding to >> theses (index 13, and 16) are left un-initialized. >> >> One workaround I see is to change the export 'global: *' in >> kerberos5/lib/libasn1 to the actual list of exported symbols. >> > > Thanks. What I'm also trying right now is to add a version map to the > libkafs -- this might help binutils to link it properly as well. If it > fails, we can try adding a proper one for libasn1. The libasn1 workaround is here: http://people.freebsd.org/~jchandra/libasn1.diff I have not actually tested the resulting binaries, but this should help the build issue. JC. ___ freebsd-current@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to "freebsd-current-unsubscr...@freebsd.org"
Re: [regression] unable to boot: no GEOM devices found.
On Thursday, 5 April 2012 16:05:23 John Baldwin wrote: > On Thursday, April 05, 2012 4:40:32 am David Naylor wrote: > > I am no longer able to test on that machine. Booting of a USB stick > > doesn't work, the kernel says: WARNING WITNESS ENABLED then the computer > > restarts. This is with -current after you committed the patch and with > > stable-9. > > > > I have verified that the USB stick does boot off other computers. > > Hmm, I suspect this is a different issue seeing as it affects stable-9 > (assuming you tested stock 9 and not with this patch applied). Your assumption is correct. This error has nothing to do with your change. > It is up > to you how much time you want to spend on this as I do believe based on > other feedback I've gotten that the issue you initially reported should be > fixed. I don't have time to spend tracking down the error (I would use a binomial search to find when things stopped working). I will gladly test any patches (or reverse commits) if someone comes up with a suggestion. Also, of note, even though Windows 7 runs fine on the computer I cannot rule out some sort of hardware failure. Thanks for fixing the MCP51 issue. signature.asc Description: This is a digitally signed message part.
[head tinderbox] failure on mips/mips
TB --- 2012-04-06 10:01:38 - tinderbox 2.9 running on freebsd-current.sentex.ca TB --- 2012-04-06 10:01:38 - FreeBSD freebsd-current.sentex.ca 8.3-PRERELEASE FreeBSD 8.3-PRERELEASE #0: Mon Mar 26 13:54:12 EDT 2012 d...@freebsd-current.sentex.ca:/usr/obj/usr/src/sys/GENERIC amd64 TB --- 2012-04-06 10:01:38 - starting HEAD tinderbox run for mips/mips TB --- 2012-04-06 10:01:38 - cleaning the object tree TB --- 2012-04-06 10:02:24 - cvsupping the source tree TB --- 2012-04-06 10:02:24 - /usr/bin/csup -z -r 3 -g -L 1 -h cvsup.sentex.ca /tinderbox/HEAD/mips/mips/supfile TB --- 2012-04-06 10:03:10 - building world TB --- 2012-04-06 10:03:10 - CROSS_BUILD_TESTING=YES TB --- 2012-04-06 10:03:10 - MAKEOBJDIRPREFIX=/obj TB --- 2012-04-06 10:03:10 - PATH=/usr/bin:/usr/sbin:/bin:/sbin TB --- 2012-04-06 10:03:10 - SRCCONF=/dev/null TB --- 2012-04-06 10:03:10 - TARGET=mips TB --- 2012-04-06 10:03:10 - TARGET_ARCH=mips TB --- 2012-04-06 10:03:10 - TZ=UTC TB --- 2012-04-06 10:03:10 - __MAKE_CONF=/dev/null TB --- 2012-04-06 10:03:10 - cd /src TB --- 2012-04-06 10:03:10 - /usr/bin/make -B buildworld >>> World build started on Fri Apr 6 10:03:11 UTC 2012 >>> Rebuilding the temporary build tree >>> stage 1.1: legacy release compatibility shims >>> stage 1.2: bootstrap tools >>> stage 2.1: cleaning up the object tree >>> stage 2.2: rebuilding the object tree >>> stage 2.3: build tools >>> stage 3: cross tools >>> stage 4.1: building includes >>> stage 4.2: building libraries >>> stage 4.3: make dependencies >>> stage 4.4: building everything [...] cc -O -pipe -G0 -I/src/kerberos5/libexec/kfd/../../../crypto/heimdal/lib/asn1 -I/src/kerberos5/libexec/kfd/../../../crypto/heimdal/lib/roken -DHAVE_CONFIG_H -I/src/kerberos5/libexec/kfd/../../include -std=gnu99 -c /src/kerberos5/libexec/kfd/../../../crypto/heimdal/appl/kf/kfd.c cc -O -pipe -G0 -I/src/kerberos5/libexec/kfd/../../../crypto/heimdal/lib/asn1 -I/src/kerberos5/libexec/kfd/../../../crypto/heimdal/lib/roken -DHAVE_CONFIG_H -I/src/kerberos5/libexec/kfd/../../include -std=gnu99 -o kfd kfd.o -lkrb5 -lroken -lasn1 -lcrypto -lcrypt /obj/mips.mips/src/kerberos5/libexec/kfd/../../lib/libvers/libvers.a gzip -cn /src/kerberos5/libexec/kfd/../../../crypto/heimdal/appl/kf/kfd.8 > kfd.8.gz ===> kerberos5/libexec/kimpersonate (all) cc -O -pipe -G0 -I/src/kerberos5/libexec/kimpersonate/../../../crypto/heimdal/lib/hx509 -I/src/kerberos5/libexec/kimpersonate/../../../crypto/heimdal/lib/asn1 -I/src/kerberos5/libexec/kimpersonate/../../../crypto/heimdal/lib/roken -I/src/kerberos5/libexec/kimpersonate/../../../crypto/heimdal/lib/sl -I. -DHAVE_CONFIG_H -I/src/kerberos5/libexec/kimpersonate/../../include -std=gnu99 -c /src/kerberos5/libexec/kimpersonate/../../../crypto/heimdal/kuser/kimpersonate.c cc -O -pipe -G0 -I/src/kerberos5/libexec/kimpersonate/../../../crypto/heimdal/lib/hx509 -I/src/kerberos5/libexec/kimpersonate/../../../crypto/heimdal/lib/asn1 -I/src/kerberos5/libexec/kimpersonate/../../../crypto/heimdal/lib/roken -I/src/kerberos5/libexec/kimpersonate/../../../crypto/heimdal/lib/sl -I. -DHAVE_CONFIG_H -I/src/kerberos5/libexec/kimpersonate/../../include -std=gnu99 -o kimpersonate kimpersonate.o -lkafs5 -lkrb5 -lheimntlm -lroken -lasn1 -lcrypto -lcrypt /obj/mips.mips/src/kerberos5/libexec/kimpersonate/../../lib/libvers/libvers.a /obj/mips.mips/src/tmp/usr/bin/ld: /obj/mips.mips/src/tmp/usr/lib/libkafs5.so symbol number 13 references nonexistent SHT_SYMTAB_SHNDX section /obj/mips.mips/src/tmp/usr/lib/libkafs5.so: could not read symbols: File format not recognized *** Error code 1 Stop in /src/kerberos5/libexec/kimpersonate. *** Error code 1 Stop in /src/kerberos5/libexec. *** Error code 1 Stop in /src/kerberos5. *** Error code 1 Stop in /src. *** Error code 1 Stop in /src. *** Error code 1 Stop in /src. TB --- 2012-04-06 10:52:02 - WARNING: /usr/bin/make returned exit code 1 TB --- 2012-04-06 10:52:02 - ERROR: failed to build world TB --- 2012-04-06 10:52:02 - 2057.82 user 437.68 system 3023.44 real http://tinderbox.freebsd.org/tinderbox-head-HEAD-mips-mips.full ___ freebsd-current@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to "freebsd-current-unsubscr...@freebsd.org"
[head tinderbox] failure on ia64/ia64
TB --- 2012-04-06 09:06:09 - tinderbox 2.9 running on freebsd-current.sentex.ca TB --- 2012-04-06 09:06:09 - FreeBSD freebsd-current.sentex.ca 8.3-PRERELEASE FreeBSD 8.3-PRERELEASE #0: Mon Mar 26 13:54:12 EDT 2012 d...@freebsd-current.sentex.ca:/usr/obj/usr/src/sys/GENERIC amd64 TB --- 2012-04-06 09:06:09 - starting HEAD tinderbox run for ia64/ia64 TB --- 2012-04-06 09:06:09 - cleaning the object tree TB --- 2012-04-06 09:06:09 - cvsupping the source tree TB --- 2012-04-06 09:06:09 - /usr/bin/csup -z -r 3 -g -L 1 -h cvsup.sentex.ca /tinderbox/HEAD/ia64/ia64/supfile TB --- 2012-04-06 09:07:46 - building world TB --- 2012-04-06 09:07:46 - CROSS_BUILD_TESTING=YES TB --- 2012-04-06 09:07:46 - MAKEOBJDIRPREFIX=/obj TB --- 2012-04-06 09:07:46 - PATH=/usr/bin:/usr/sbin:/bin:/sbin TB --- 2012-04-06 09:07:46 - SRCCONF=/dev/null TB --- 2012-04-06 09:07:46 - TARGET=ia64 TB --- 2012-04-06 09:07:46 - TARGET_ARCH=ia64 TB --- 2012-04-06 09:07:46 - TZ=UTC TB --- 2012-04-06 09:07:46 - __MAKE_CONF=/dev/null TB --- 2012-04-06 09:07:46 - cd /src TB --- 2012-04-06 09:07:46 - /usr/bin/make -B buildworld >>> World build started on Fri Apr 6 09:07:47 UTC 2012 >>> Rebuilding the temporary build tree >>> stage 1.1: legacy release compatibility shims >>> stage 1.2: bootstrap tools >>> stage 2.1: cleaning up the object tree >>> stage 2.2: rebuilding the object tree >>> stage 2.3: build tools >>> stage 3: cross tools >>> stage 4.1: building includes >>> stage 4.2: building libraries >>> stage 4.3: make dependencies >>> stage 4.4: building everything >>> World build completed on Fri Apr 6 10:41:09 UTC 2012 TB --- 2012-04-06 10:41:09 - generating LINT kernel config TB --- 2012-04-06 10:41:09 - cd /src/sys/ia64/conf TB --- 2012-04-06 10:41:09 - /usr/bin/make -B LINT TB --- 2012-04-06 10:41:09 - cd /src/sys/ia64/conf TB --- 2012-04-06 10:41:09 - /usr/sbin/config -m LINT TB --- 2012-04-06 10:41:09 - building LINT kernel TB --- 2012-04-06 10:41:09 - CROSS_BUILD_TESTING=YES TB --- 2012-04-06 10:41:09 - MAKEOBJDIRPREFIX=/obj TB --- 2012-04-06 10:41:09 - PATH=/usr/bin:/usr/sbin:/bin:/sbin TB --- 2012-04-06 10:41:09 - SRCCONF=/dev/null TB --- 2012-04-06 10:41:09 - TARGET=ia64 TB --- 2012-04-06 10:41:09 - TARGET_ARCH=ia64 TB --- 2012-04-06 10:41:09 - TZ=UTC TB --- 2012-04-06 10:41:09 - __MAKE_CONF=/dev/null TB --- 2012-04-06 10:41:09 - cd /src TB --- 2012-04-06 10:41:09 - /usr/bin/make -B buildkernel KERNCONF=LINT >>> Kernel build for LINT started on Fri Apr 6 10:41:10 UTC 2012 >>> stage 1: configuring the kernel >>> stage 2.1: cleaning up the object tree >>> stage 2.2: rebuilding the object tree >>> stage 2.3: build tools >>> stage 3.1: making dependencies >>> stage 3.2: building everything >>> Kernel build for LINT completed on Fri Apr 6 11:16:28 UTC 2012 TB --- 2012-04-06 11:16:28 - cd /src/sys/ia64/conf TB --- 2012-04-06 11:16:28 - /usr/sbin/config -m GENERIC TB --- 2012-04-06 11:16:28 - building GENERIC kernel TB --- 2012-04-06 11:16:28 - CROSS_BUILD_TESTING=YES TB --- 2012-04-06 11:16:28 - MAKEOBJDIRPREFIX=/obj TB --- 2012-04-06 11:16:28 - PATH=/usr/bin:/usr/sbin:/bin:/sbin TB --- 2012-04-06 11:16:28 - SRCCONF=/dev/null TB --- 2012-04-06 11:16:28 - TARGET=ia64 TB --- 2012-04-06 11:16:28 - TARGET_ARCH=ia64 TB --- 2012-04-06 11:16:28 - TZ=UTC TB --- 2012-04-06 11:16:28 - __MAKE_CONF=/dev/null TB --- 2012-04-06 11:16:28 - cd /src TB --- 2012-04-06 11:16:28 - /usr/bin/make -B buildkernel KERNCONF=GENERIC >>> Kernel build for GENERIC started on Fri Apr 6 11:16:28 UTC 2012 >>> stage 1: configuring the kernel >>> stage 2.1: cleaning up the object tree >>> stage 2.2: rebuilding the object tree >>> stage 2.3: build tools >>> stage 3.1: making dependencies >>> stage 3.2: building everything [...] cc -c -O -pipe -std=c99 -g -Wall -Wredundant-decls -Wnested-externs -Wstrict-prototypes -Wmissing-prototypes -Wpointer-arith -Winline -Wcast-qual -Wundef -Wno-pointer-sign -fformat-extensions -Wmissing-include-dirs -fdiagnostics-show-option -nostdinc -I. -I/src/sys -I/src/sys/contrib/altq -I/src/sys/contrib/ia64/libuwx/src -D_KERNEL -DHAVE_KERNEL_OPTION_HEADERS -include opt_global.h -fno-common -finline-limit=15000 --param inline-unit-growth=100 --param large-function-growth=1000 -mconstant-gp -ffixed-r13 -mfixed-range=f32-f127 -fpic -ffreestanding -Werror /src/sys/libkern/strtoul.c cc -c -O -pipe -std=c99 -g -Wall -Wredundant-decls -Wnested-externs -Wstrict-prototypes -Wmissing-prototypes -Wpointer-arith -Winline -Wcast-qual -Wundef -Wno-pointer-sign -fformat-extensions -Wmissing-include-dirs -fdiagnostics-show-option -nostdinc -I. -I/src/sys -I/src/sys/contrib/altq -I/src/sys/contrib/ia64/libuwx/src -D_KERNEL -DHAVE_KERNEL_OPTION_HEADERS -include opt_global.h -fno-common -finline-limit=15000 --param inline-unit-growth=100 --param large-function-growth=1000 -mconstant-gp -ffixed-r13 -mfixed-range=f32-f127 -fpic -ffreestanding -Werror /src/sys/libkern/strtouq.c cc -c -O -pipe -std=c99 -g -Wall -Wredundant-decl
ECC memory driver in FreeBSD 10?
I'm looking for a way to force FreeBSD 10 to maintain/watch ECC errors reported by UEFI (or BIOS). Since ECC is said to be essential for server systems both in buisness and science and I do not question this, I was wondering if I can not report ECC errors via a watchdog or UEFI (ACPI?) report to syslog facility on FreeBSD. FreeBSD is supposed to be a server operating system, as far as I know, so I believe there must be something which didn't have revealed itself to me, yet. Thanks in advance, Oliver signature.asc Description: OpenPGP digital signature
Problem with r233937 on i386
Kernel build @ r233941 failed for me this morning, running: FreeBSD g1-227.catwhisker.org 10.0-CURRENT FreeBSD 10.0-CURRENT #525 233918M: Thu Apr 5 04:42:37 PDT 2012 r...@g1-227.catwhisker.org:/usr/obj/usr/src/sys/CANARY i386 thus: ... ototypes -Wmissing-prototypes -Wpointer-arith -Winline -Wcast-qual -Wundef -Wno-pointer-sign -fformat-extensions -Wmissing-include-dirs -fdiagnostics-show-option -nostdinc -I. -I/usr/src/sys -I/usr/src/sys/contrib/altq -D_KERNEL -DHAVE_KERNEL_OPTION_HEADERS -include opt_global.h -fno-common -finline-limit=8000 --param inline-unit-growth=100 --param large-function-growth=1000 -mno-align-long-strings -mpreferred-stack-boundary=2 -mno-mmx -mno-sse -msoft-float -ffreestanding -fstack-protector -Werror /usr/src/sys/net/bpf.c /usr/src/sys/net/bpf.c: In function 'bpf_setf': /usr/src/sys/net/bpf.c:1683: error: 'need_upgrade' undeclared (first use in this function) /usr/src/sys/net/bpf.c:1683: error: (Each undeclared identifier is reported only once /usr/src/sys/net/bpf.c:1683: error: for each function it appears in.) *** [bpf.o] Error code 1 Stop in /common/S4/obj/usr/src/sys/CANARY. *** [buildkernel] Error code 1 Stop in /usr/src. *** [buildkernel] Error code 1 Stop in /usr/src. It looks to me as if perhaps the problem is that in net/bpf.c, the int need_upgrade = 0; on line 1601 is in the block (lines 1598 - 1611) controlled by #ifdef COMPAT_FREEBSD32 And in FreeBSD/i386, I believe that means the block in question is not getting compiled. So I moved the line in question above the #ifdef; that seems to get beyond the above failure, but I have no idea if it's correct. Peace, david -- David H. Wolfskill da...@catwhisker.org Depriving a girl or boy of an opportunity for education is evil. See http://www.catwhisker.org/~david/publickey.gpg for my public key. pgpz2ztRnayMS.pgp Description: PGP signature
Re: Scheduler + IPC performance on FreeBSD 7.4, 8.2, 9.0 and -CURRENT
Am 04/05/12 20:03, schrieb Arnaud Lacombe: > Hi folks, > > Over the past months, I ran on a couple of unused box the > `hackbench'[HACKBENCH] benchmark used by the Linux folks for tracking > down various kind of regression/improvement. `hackbench' is a > scheduler + IPC test (socket xor pipe). It creates producers/consumers > groups and let a variable quantity of small messages flow happily. > Producers and consumers are either processes xor threads. > > Tested platforms were > - Atom D510, Intel, (incomplete) > - Core 2 Quad Q9560, Intel > - Soekris net5501, AMD (incomplete) > - Xeon E5645, Intel (incomplete) > - Xeon E5620 (dual package), Intel > - Xeon E5-1650 (pending completion) > - Vortex86, DMP > > Tested kernel were: > - FreeBSD 7.4-RELEASE > - FreeBSD 8.2-RELEASE > - FreeBSD 9.0-RC3 and FreeBSD 9.0-RELEASE > - FreeBSD 10-CURRENT as of r231573 > > on the following architecture: > - amd64 (if supported, incomplete) > - i386 > > 1) DISCLAMER > > Let me start by pointing out something important: > > [I] "I am _not_ interested in testing released version FOO with > feature BAR enabled, if enabling BAR require a kernel rebuild." > > All tests for release kernels were made for the kernel shipped > officially, it is the developers responsability to decide whether or > not enable a feature by default, not mine. If option BAR gives a 20% > performance improvement, enable it, don't complain the test to be 20% > slower. > > [II] "I am _not_ interested in altering any hints, tunables or > sysctl, unless they prevent the execution of the test." > > The exception added to the above rule is due to limitation introduced > by `kern.threads.max_threads_per_proc' and `kern.ipc.maxpipekva'. > Those were respectively set to 8192 and between 16M/64M. > > note: rule [I] is alleviated for -CURRENT kernels, which were built > with the same alteration made to GENERIC during the CURRENT->RELEASE > transition (ie. WITNESS and a couple of other option disabled). > > > 2) Tests description > > `hackbench' has the following tunable: > - IPC to use for messaging, either `pipe' or `socket'. > - Threading model, either `thread' or `process' > - Number of iteration to run > - Number of group to create > > The tests covered all of these adjustments more or less heavily > depending on the platform capability. > > > 3) Scripts > > Test scripts are available in the `master' branch of the git repository at: > > https://github.com/lacombar/hackbench > > in the `hackbench/' directory. > > > 4) Results > > Full results are available in the `runs/*' branches of the GitHub repository. > > > 5) Quick results summary > > * UP case > > FreeBSD 9.0 behaves better than FreeBSD 8.2 in process mode, > especially with sockets. Results are comparable with thread. 9.0-RC3 > shows a 10% hits in thread/socket mode on the LX800, this will need > confirmation. > > Linux is stable and scales linearly in all situation. It is only > beaten by FreeBSD 8.2-RELEASE with thread/socket. > > * MP case > > These is a pretty bad regression with FreeBSD 9.0 in thread/pipe mode, > which scale almost in O(N^2), ending up in way worse performance than > FreeBSD 7.4 or 8.2 on the Core 2 Quad. Beside that, it is really > difficult to draw a general trends, ie. whether FreeBSD 9.0 behaves > better than FreeBSD 8.2, or the other way around. Pretty much all > situation arises, FreeBSD 9.0 can beat FreeBSD 8.2 on some workload, > behave the same, or be beaten on others. None really scales regularly > either. Pretty much every runs shows thresholds where scheduling > decision change and/or became erratic. > > 6) Anticipated question and remarks > > Q1: "You should truly enable kick-ass feature BAZ in the kernel." > R1: "I'm lazy. Do your job as a developer to integrate the feature. If > it should be the default, make it the default." > > Q2: "You should set `kern.vm.whatever' to 42, or enable feature BAZ in > the kernel, to get full performance from the Warp engine on > Constellation-class starship." > R2: "Would you ask Lt. Worf to re-aligh plasma injectors or would ask > Lt. Commander La Forge to plan an assault, seriously ?" > > Q3: "You built the Linux kernel, why can't you rebuild FreeBSD's ?" > For a couple of reason: > > - the Linux kernel does not provide binary release per-se. > > - the Linux kernel was not the focus of the tests, but merely a > comparative of what others-can-do. > > - I did not tweak the Linux kernel configuration. The kernels > configuration tested derived from the `defconfig', with very few > amendment[0], mostly about hardware support not enabled by default > > Q3: "Could you post all the graph ?" > R3: I could, but there is really tons of them, so posting a subset of > them would be subjective, all the materials is available on the git > repository. > > Q4: "So, how can I get all the graph ?" > R4: All you need is git, a posix shell, a couple of utility (find, > sort, ...), a recent gn
Re: "trim/discard" success story
On Tue, Apr 03, 2012 at 06:18:43PM -0700, Julian Elischer wrote: > for flash drives this is great news.. > Now if ZFS would get trim support, that too would be great. I'm working on it. -- Pawel Jakub Dawidek http://www.wheelsystems.com FreeBSD committer http://www.FreeBSD.org Am I Evil? Yes, I Am! http://tupytaj.pl pgpnW1D0zD64a.pgp Description: PGP signature
Re: ECC memory driver in FreeBSD 10?
On 6 Apr 2012, at 12:48, "O. Hartmann" wrote: > I'm looking for a way to force FreeBSD 10 to maintain/watch ECC errors > reported by UEFI (or BIOS). > Since ECC is said to be essential for server systems both in buisness > and science and I do not question this, I was wondering if I can not > report ECC errors via a watchdog or UEFI (ACPI?) report to syslog > facility on FreeBSD. > FreeBSD is supposed to be a server operating system, as far as I know, > so I believe there must be something which didn't have revealed itself > to me, yet. FreeBSD logs ECC errors it finds (I don't know how but I doubt it's via the BIOS) by default: I had some RAM go bad a few months ago and messages appeared in dmesg. Is there something in addition you need? -- Bruce Cran___ freebsd-current@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to "freebsd-current-unsubscr...@freebsd.org"
[head tinderbox] failure on powerpc/powerpc
TB --- 2012-04-06 10:52:02 - tinderbox 2.9 running on freebsd-current.sentex.ca TB --- 2012-04-06 10:52:02 - FreeBSD freebsd-current.sentex.ca 8.3-PRERELEASE FreeBSD 8.3-PRERELEASE #0: Mon Mar 26 13:54:12 EDT 2012 d...@freebsd-current.sentex.ca:/usr/obj/usr/src/sys/GENERIC amd64 TB --- 2012-04-06 10:52:02 - starting HEAD tinderbox run for powerpc/powerpc TB --- 2012-04-06 10:52:02 - cleaning the object tree TB --- 2012-04-06 10:52:02 - cvsupping the source tree TB --- 2012-04-06 10:52:02 - /usr/bin/csup -z -r 3 -g -L 1 -h cvsup.sentex.ca /tinderbox/HEAD/powerpc/powerpc/supfile TB --- 2012-04-06 10:52:42 - building world TB --- 2012-04-06 10:52:42 - CROSS_BUILD_TESTING=YES TB --- 2012-04-06 10:52:42 - MAKEOBJDIRPREFIX=/obj TB --- 2012-04-06 10:52:42 - PATH=/usr/bin:/usr/sbin:/bin:/sbin TB --- 2012-04-06 10:52:42 - SRCCONF=/dev/null TB --- 2012-04-06 10:52:42 - TARGET=powerpc TB --- 2012-04-06 10:52:42 - TARGET_ARCH=powerpc TB --- 2012-04-06 10:52:42 - TZ=UTC TB --- 2012-04-06 10:52:42 - __MAKE_CONF=/dev/null TB --- 2012-04-06 10:52:42 - cd /src TB --- 2012-04-06 10:52:42 - /usr/bin/make -B buildworld >>> World build started on Fri Apr 6 10:52:43 UTC 2012 >>> Rebuilding the temporary build tree >>> stage 1.1: legacy release compatibility shims >>> stage 1.2: bootstrap tools >>> stage 2.1: cleaning up the object tree >>> stage 2.2: rebuilding the object tree >>> stage 2.3: build tools >>> stage 3: cross tools >>> stage 4.1: building includes >>> stage 4.2: building libraries >>> stage 4.3: make dependencies >>> stage 4.4: building everything >>> World build completed on Fri Apr 6 13:05:25 UTC 2012 TB --- 2012-04-06 13:05:25 - generating LINT kernel config TB --- 2012-04-06 13:05:25 - cd /src/sys/powerpc/conf TB --- 2012-04-06 13:05:25 - /usr/bin/make -B LINT TB --- 2012-04-06 13:05:25 - cd /src/sys/powerpc/conf TB --- 2012-04-06 13:05:25 - /usr/sbin/config -m LINT TB --- 2012-04-06 13:05:25 - building LINT kernel TB --- 2012-04-06 13:05:25 - CROSS_BUILD_TESTING=YES TB --- 2012-04-06 13:05:25 - MAKEOBJDIRPREFIX=/obj TB --- 2012-04-06 13:05:25 - PATH=/usr/bin:/usr/sbin:/bin:/sbin TB --- 2012-04-06 13:05:25 - SRCCONF=/dev/null TB --- 2012-04-06 13:05:25 - TARGET=powerpc TB --- 2012-04-06 13:05:25 - TARGET_ARCH=powerpc TB --- 2012-04-06 13:05:25 - TZ=UTC TB --- 2012-04-06 13:05:25 - __MAKE_CONF=/dev/null TB --- 2012-04-06 13:05:25 - cd /src TB --- 2012-04-06 13:05:25 - /usr/bin/make -B buildkernel KERNCONF=LINT >>> Kernel build for LINT started on Fri Apr 6 13:05:26 UTC 2012 >>> stage 1: configuring the kernel >>> stage 2.1: cleaning up the object tree >>> stage 2.2: rebuilding the object tree >>> stage 2.3: build tools >>> stage 3.1: making dependencies >>> stage 3.2: building everything [...] cc -c -O -pipe -std=c99 -Wall -Wredundant-decls -Wnested-externs -Wstrict-prototypes -Wmissing-prototypes -Wpointer-arith -Winline -Wcast-qual -Wundef -Wno-pointer-sign -fformat-extensions -Wmissing-include-dirs -fdiagnostics-show-option -nostdinc -I. -I/src/sys -I/src/sys/contrib/altq -I/src/sys/contrib/libfdt -D_KERNEL -DHAVE_KERNEL_OPTION_HEADERS -include opt_global.h -fno-common -finline-limit=15000 --param inline-unit-growth=100 --param large-function-growth=1000 -fno-builtin -msoft-float -Wa,-many -fno-omit-frame-pointer -msoft-float -mno-altivec -ffreestanding -fstack-protector -Werror /src/sys/libkern/strtoul.c cc -c -O -pipe -std=c99 -Wall -Wredundant-decls -Wnested-externs -Wstrict-prototypes -Wmissing-prototypes -Wpointer-arith -Winline -Wcast-qual -Wundef -Wno-pointer-sign -fformat-extensions -Wmissing-include-dirs -fdiagnostics-show-option -nostdinc -I. -I/src/sys -I/src/sys/contrib/altq -I/src/sys/contrib/libfdt -D_KERNEL -DHAVE_KERNEL_OPTION_HEADERS -include opt_global.h -fno-common -finline-limit=15000 --param inline-unit-growth=100 --param large-function-growth=1000 -fno-builtin -msoft-float -Wa,-many -fno-omit-frame-pointer -msoft-float -mno-altivec -ffreestanding -fstack-protector -Werror /src/sys/libkern/strtouq.c cc -c -O -pipe -std=c99 -Wall -Wredundant-decls -Wnested-externs -Wstrict-prototypes -Wmissing-prototypes -Wpointer-arith -Winline -Wcast-qual -Wundef -Wno-pointer-sign -fformat-extensions -Wmissing-include-dirs -fdiagnostics-show-option -nostdinc -I. -I/src/sys -I/src/sys/contrib/altq -I/src/sys/contrib/libfdt -D_KERNEL -DHAVE_KERNEL_OPTION_HEADERS -include opt_global.h -fno-common -finline-limit=15000 --param inline-unit-growth=100 --param large-function-growth=1000 -fno-builtin -msoft-float -Wa,-many -fno-omit-frame-pointer -msoft-float -mno-altivec -ffreestanding -fstack-protector -Werror /src/sys/libkern/strvalid.c cc -c -O -pipe -std=c99 -Wall -Wredundant-decls -Wnested-externs -Wstrict-prototypes -Wmissing-prototypes -Wpointer-arith -Winline -Wcast-qual -Wundef -Wno-pointer-sign -fformat-extensions -Wmissing-include-dirs -fdiagnostics-show-option -nostdinc -I. -I/src/sys -I/src/sys/contrib/altq -I/src/sys/contrib/
Re: Problem with r233937 on i386
On 06.04.2012 16:09, David Wolfskill wrote: Kernel build @ r233941 failed for me this morning, running: FreeBSD g1-227.catwhisker.org 10.0-CURRENT FreeBSD 10.0-CURRENT #525 233918M: Thu Apr 5 04:42:37 PDT 2012 r...@g1-227.catwhisker.org:/usr/obj/usr/src/sys/CANARY i386 thus: ... ototypes -Wmissing-prototypes -Wpointer-arith -Winline -Wcast-qual -Wundef -Wno-pointer-sign -fformat-extensions -Wmissing-include-dirs -fdiagnostics-show-option -nostdinc -I. -I/usr/src/sys -I/usr/src/sys/contrib/altq -D_KERNEL -DHAVE_KERNEL_OPTION_HEADERS -include opt_global.h -fno-common -finline-limit=8000 --param inline-unit-growth=100 --param large-function-growth=1000 -mno-align-long-strings -mpreferred-stack-boundary=2 -mno-mmx -mno-sse -msoft-float -ffreestanding -fstack-protector -Werror /usr/src/sys/net/bpf.c /usr/src/sys/net/bpf.c: In function 'bpf_setf': /usr/src/sys/net/bpf.c:1683: error: 'need_upgrade' undeclared (first use in this function) /usr/src/sys/net/bpf.c:1683: error: (Each undeclared identifier is reported only once /usr/src/sys/net/bpf.c:1683: error: for each function it appears in.) *** [bpf.o] Error code 1 Stop in /common/S4/obj/usr/src/sys/CANARY. *** [buildkernel] Error code 1 Stop in /usr/src. *** [buildkernel] Error code 1 Stop in /usr/src. Fixed in r233946. Thanks! -- WBR, Alexander ___ freebsd-current@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to "freebsd-current-unsubscr...@freebsd.org"
[head tinderbox] failure on sparc64/sparc64
TB --- 2012-04-06 12:55:13 - tinderbox 2.9 running on freebsd-current.sentex.ca TB --- 2012-04-06 12:55:13 - FreeBSD freebsd-current.sentex.ca 8.3-PRERELEASE FreeBSD 8.3-PRERELEASE #0: Mon Mar 26 13:54:12 EDT 2012 d...@freebsd-current.sentex.ca:/usr/obj/usr/src/sys/GENERIC amd64 TB --- 2012-04-06 12:55:13 - starting HEAD tinderbox run for sparc64/sparc64 TB --- 2012-04-06 12:55:13 - cleaning the object tree TB --- 2012-04-06 12:55:13 - cvsupping the source tree TB --- 2012-04-06 12:55:13 - /usr/bin/csup -z -r 3 -g -L 1 -h cvsup.sentex.ca /tinderbox/HEAD/sparc64/sparc64/supfile TB --- 2012-04-06 12:56:16 - building world TB --- 2012-04-06 12:56:16 - CROSS_BUILD_TESTING=YES TB --- 2012-04-06 12:56:16 - MAKEOBJDIRPREFIX=/obj TB --- 2012-04-06 12:56:16 - PATH=/usr/bin:/usr/sbin:/bin:/sbin TB --- 2012-04-06 12:56:16 - SRCCONF=/dev/null TB --- 2012-04-06 12:56:16 - TARGET=sparc64 TB --- 2012-04-06 12:56:16 - TARGET_ARCH=sparc64 TB --- 2012-04-06 12:56:16 - TZ=UTC TB --- 2012-04-06 12:56:16 - __MAKE_CONF=/dev/null TB --- 2012-04-06 12:56:16 - cd /src TB --- 2012-04-06 12:56:16 - /usr/bin/make -B buildworld >>> World build started on Fri Apr 6 12:56:17 UTC 2012 >>> Rebuilding the temporary build tree >>> stage 1.1: legacy release compatibility shims >>> stage 1.2: bootstrap tools >>> stage 2.1: cleaning up the object tree >>> stage 2.2: rebuilding the object tree >>> stage 2.3: build tools >>> stage 3: cross tools >>> stage 4.1: building includes >>> stage 4.2: building libraries >>> stage 4.3: make dependencies >>> stage 4.4: building everything >>> World build completed on Fri Apr 6 13:54:35 UTC 2012 TB --- 2012-04-06 13:54:35 - generating LINT kernel config TB --- 2012-04-06 13:54:35 - cd /src/sys/sparc64/conf TB --- 2012-04-06 13:54:35 - /usr/bin/make -B LINT TB --- 2012-04-06 13:54:35 - cd /src/sys/sparc64/conf TB --- 2012-04-06 13:54:35 - /usr/sbin/config -m LINT TB --- 2012-04-06 13:54:35 - building LINT kernel TB --- 2012-04-06 13:54:35 - CROSS_BUILD_TESTING=YES TB --- 2012-04-06 13:54:35 - MAKEOBJDIRPREFIX=/obj TB --- 2012-04-06 13:54:35 - PATH=/usr/bin:/usr/sbin:/bin:/sbin TB --- 2012-04-06 13:54:35 - SRCCONF=/dev/null TB --- 2012-04-06 13:54:35 - TARGET=sparc64 TB --- 2012-04-06 13:54:35 - TARGET_ARCH=sparc64 TB --- 2012-04-06 13:54:35 - TZ=UTC TB --- 2012-04-06 13:54:35 - __MAKE_CONF=/dev/null TB --- 2012-04-06 13:54:35 - cd /src TB --- 2012-04-06 13:54:35 - /usr/bin/make -B buildkernel KERNCONF=LINT >>> Kernel build for LINT started on Fri Apr 6 13:54:36 UTC 2012 >>> stage 1: configuring the kernel >>> stage 2.1: cleaning up the object tree >>> stage 2.2: rebuilding the object tree >>> stage 2.3: build tools >>> stage 3.1: making dependencies >>> stage 3.2: building everything [...] cc -c -O2 -pipe -fno-strict-aliasing -std=c99 -Wall -Wredundant-decls -Wnested-externs -Wstrict-prototypes -Wmissing-prototypes -Wpointer-arith -Winline -Wcast-qual -Wundef -Wno-pointer-sign -fformat-extensions -Wmissing-include-dirs -fdiagnostics-show-option -nostdinc -I. -I/src/sys -I/src/sys/contrib/altq -D_KERNEL -DHAVE_KERNEL_OPTION_HEADERS -include opt_global.h -fno-common -finline-limit=15000 --param inline-unit-growth=100 --param large-function-growth=1000 -fno-builtin -mcmodel=medany -msoft-float -ffreestanding -fstack-protector -Werror /src/sys/libkern/strtoul.c cc -c -O2 -pipe -fno-strict-aliasing -std=c99 -Wall -Wredundant-decls -Wnested-externs -Wstrict-prototypes -Wmissing-prototypes -Wpointer-arith -Winline -Wcast-qual -Wundef -Wno-pointer-sign -fformat-extensions -Wmissing-include-dirs -fdiagnostics-show-option -nostdinc -I. -I/src/sys -I/src/sys/contrib/altq -D_KERNEL -DHAVE_KERNEL_OPTION_HEADERS -include opt_global.h -fno-common -finline-limit=15000 --param inline-unit-growth=100 --param large-function-growth=1000 -fno-builtin -mcmodel=medany -msoft-float -ffreestanding -fstack-protector -Werror /src/sys/libkern/strtouq.c cc -c -O2 -pipe -fno-strict-aliasing -std=c99 -Wall -Wredundant-decls -Wnested-externs -Wstrict-prototypes -Wmissing-prototypes -Wpointer-arith -Winline -Wcast-qual -Wundef -Wno-pointer-sign -fformat-extensions -Wmissing-include-dirs -fdiagnostics-show-option -nostdinc -I. -I/src/sys -I/src/sys/contrib/altq -D_KERNEL -DHAVE_KERNEL_OPTION_HEADERS -include opt_global.h -fno-common -finline-limit=15000 --param inline-unit-growth=100 --param large-function-growth=1000 -fno-builtin -mcmodel=medany -msoft-float -ffreestanding -fstack-protector -Werror /src/sys/libkern/strvalid.c cc -c -O2 -pipe -fno-strict-aliasing -std=c99 -Wall -Wredundant-decls -Wnested-externs -Wstrict-prototypes -Wmissing-prototypes -Wpointer-arith -Winline -Wcast-qual -Wundef -Wno-pointer-sign -fformat-extensions -Wmissing-include-dirs -fdiagnostics-show-option -nostdinc -I. -I/src/sys -I/src/sys/contrib/altq -D_KERNEL -DHAVE_KERNEL_OPTION_HEADERS -include opt_global.h -fno-common -finline-limit=15000 --param inline-unit-growth=100 --param large-fun
[head tinderbox] failure on powerpc64/powerpc
TB --- 2012-04-06 11:22:51 - tinderbox 2.9 running on freebsd-current.sentex.ca TB --- 2012-04-06 11:22:51 - FreeBSD freebsd-current.sentex.ca 8.3-PRERELEASE FreeBSD 8.3-PRERELEASE #0: Mon Mar 26 13:54:12 EDT 2012 d...@freebsd-current.sentex.ca:/usr/obj/usr/src/sys/GENERIC amd64 TB --- 2012-04-06 11:22:51 - starting HEAD tinderbox run for powerpc64/powerpc TB --- 2012-04-06 11:22:51 - cleaning the object tree TB --- 2012-04-06 11:22:51 - cvsupping the source tree TB --- 2012-04-06 11:22:51 - /usr/bin/csup -z -r 3 -g -L 1 -h cvsup.sentex.ca /tinderbox/HEAD/powerpc64/powerpc/supfile TB --- 2012-04-06 11:23:29 - building world TB --- 2012-04-06 11:23:29 - CROSS_BUILD_TESTING=YES TB --- 2012-04-06 11:23:29 - MAKEOBJDIRPREFIX=/obj TB --- 2012-04-06 11:23:29 - PATH=/usr/bin:/usr/sbin:/bin:/sbin TB --- 2012-04-06 11:23:29 - SRCCONF=/dev/null TB --- 2012-04-06 11:23:29 - TARGET=powerpc TB --- 2012-04-06 11:23:29 - TARGET_ARCH=powerpc64 TB --- 2012-04-06 11:23:29 - TZ=UTC TB --- 2012-04-06 11:23:29 - __MAKE_CONF=/dev/null TB --- 2012-04-06 11:23:29 - cd /src TB --- 2012-04-06 11:23:29 - /usr/bin/make -B buildworld >>> World build started on Fri Apr 6 11:23:30 UTC 2012 >>> Rebuilding the temporary build tree >>> stage 1.1: legacy release compatibility shims >>> stage 1.2: bootstrap tools >>> stage 2.1: cleaning up the object tree >>> stage 2.2: rebuilding the object tree >>> stage 2.3: build tools >>> stage 3: cross tools >>> stage 4.1: building includes >>> stage 4.2: building libraries >>> stage 4.3: make dependencies >>> stage 4.4: building everything >>> stage 5.1: building 32 bit shim libraries >>> World build completed on Fri Apr 6 13:57:35 UTC 2012 TB --- 2012-04-06 13:57:35 - generating LINT kernel config TB --- 2012-04-06 13:57:35 - cd /src/sys/powerpc/conf TB --- 2012-04-06 13:57:35 - /usr/bin/make -B LINT TB --- 2012-04-06 13:57:35 - cd /src/sys/powerpc/conf TB --- 2012-04-06 13:57:35 - /usr/sbin/config -m LINT TB --- 2012-04-06 13:57:35 - building LINT kernel TB --- 2012-04-06 13:57:35 - CROSS_BUILD_TESTING=YES TB --- 2012-04-06 13:57:35 - MAKEOBJDIRPREFIX=/obj TB --- 2012-04-06 13:57:35 - PATH=/usr/bin:/usr/sbin:/bin:/sbin TB --- 2012-04-06 13:57:35 - SRCCONF=/dev/null TB --- 2012-04-06 13:57:35 - TARGET=powerpc TB --- 2012-04-06 13:57:35 - TARGET_ARCH=powerpc64 TB --- 2012-04-06 13:57:35 - TZ=UTC TB --- 2012-04-06 13:57:35 - __MAKE_CONF=/dev/null TB --- 2012-04-06 13:57:35 - cd /src TB --- 2012-04-06 13:57:35 - /usr/bin/make -B buildkernel KERNCONF=LINT >>> Kernel build for LINT started on Fri Apr 6 13:57:36 UTC 2012 >>> stage 1: configuring the kernel >>> stage 2.1: cleaning up the object tree >>> stage 2.2: rebuilding the object tree >>> stage 2.3: build tools >>> stage 3.1: making dependencies >>> stage 3.2: building everything [...] cc -c -O -pipe -std=c99 -Wall -Wredundant-decls -Wnested-externs -Wstrict-prototypes -Wmissing-prototypes -Wpointer-arith -Winline -Wcast-qual -Wundef -Wno-pointer-sign -fformat-extensions -Wmissing-include-dirs -fdiagnostics-show-option -nostdinc -I. -I/src/sys -I/src/sys/contrib/altq -I/src/sys/contrib/libfdt -D_KERNEL -DHAVE_KERNEL_OPTION_HEADERS -include opt_global.h -fno-common -finline-limit=15000 --param inline-unit-growth=100 --param large-function-growth=1000 -fno-builtin -msoft-float -Wa,-many -fno-omit-frame-pointer -msoft-float -mno-altivec -mcall-aixdesc -ffreestanding -fstack-protector -Werror /src/sys/libkern/strtoul.c cc -c -O -pipe -std=c99 -Wall -Wredundant-decls -Wnested-externs -Wstrict-prototypes -Wmissing-prototypes -Wpointer-arith -Winline -Wcast-qual -Wundef -Wno-pointer-sign -fformat-extensions -Wmissing-include-dirs -fdiagnostics-show-option -nostdinc -I. -I/src/sys -I/src/sys/contrib/altq -I/src/sys/contrib/libfdt -D_KERNEL -DHAVE_KERNEL_OPTION_HEADERS -include opt_global.h -fno-common -finline-limit=15000 --param inline-unit-growth=100 --param large-function-growth=1000 -fno-builtin -msoft-float -Wa,-many -fno-omit-frame-pointer -msoft-float -mno-altivec -mcall-aixdesc -ffreestanding -fstack-protector -Werror /src/sys/libkern/strtouq.c cc -c -O -pipe -std=c99 -Wall -Wredundant-decls -Wnested-externs -Wstrict-prototypes -Wmissing-prototypes -Wpointer-arith -Winline -Wcast-qual -Wundef -Wno-pointer-sign -fformat-extensions -Wmissing-include-dirs -fdiagnostics-show-option -nostdinc -I. -I/src/sys -I/src/sys/contrib/altq -I/src/sys/contrib/libfdt -D_KERNEL -DHAVE_KERNEL_OPTION_HEADERS -include opt_global.h -fno-common -finline-limit=15000 --param inline-unit-growth=100 --param large-function-growth=1000 -fno-builtin -msoft-float -Wa,-many -fno-omit-frame-pointer -msoft-float -mno-altivec -mcall-aixdesc -ffreestanding -fstack-protector -Werror /src/sys/libkern/strvalid.c cc -c -O -pipe -std=c99 -Wall -Wredundant-decls -Wnested-externs -Wstrict-prototypes -Wmissing-prototypes -Wpointer-arith -Winline -Wcast-qual -Wundef -Wno-pointer-sign -fformat-extensions -Wmissing-include-dirs
Re: [RFT][patch] Scheduling for HTT and not only
Il 05 aprile 2012 19:12, Arnaud Lacombe ha scritto: > Hi, > > [Sorry for the delay, I got a bit sidetrack'ed...] > > 2012/2/17 Alexander Motin : >> On 17.02.2012 18:53, Arnaud Lacombe wrote: >>> >>> On Fri, Feb 17, 2012 at 11:29 AM, Alexander Motin wrote: On 02/15/12 21:54, Jeff Roberson wrote: > > On Wed, 15 Feb 2012, Alexander Motin wrote: >> >> I've decided to stop those cache black magic practices and focus on >> things that really exist in this world -- SMT and CPU load. I've >> dropped most of cache related things from the patch and made the rest >> of things more strict and predictable: >> http://people.freebsd.org/~mav/sched.htt34.patch > > > This looks great. I think there is value in considering the other > approach further but I would like to do this part first. It would be > nice to also add priority as a greater influence in the load balancing > as well. I haven't got good idea yet about balancing priorities, but I've rewritten balancer itself. As soon as sched_lowest() / sched_highest() are more intelligent now, they allowed to remove topology traversing from the balancer itself. That should fix double-swapping problem, allow to keep some affinity while moving threads and make balancing more fair. I did number of tests running 4, 8, 9 and 16 CPU-bound threads on 8 CPUs. With 4, 8 and 16 threads everything is stationary as it should. With 9 threads I see regular and random load move between all 8 CPUs. Measurements on 5 minutes run show deviation of only about 5 seconds. It is the same deviation as I see caused by only scheduling of 16 threads on 8 cores without any balancing needed at all. So I believe this code works as it should. Here is the patch: http://people.freebsd.org/~mav/sched.htt40.patch I plan this to be a final patch of this series (more to come :)) and if there will be no problems or objections, I am going to commit it (except some debugging KTRs) in about ten days. So now it's a good time for reviews and testing. :) >>> is there a place where all the patches are available ? >> >> >> All my scheduler patches are cumulative, so all you need is only the last >> mentioned here sched.htt40.patch. >> > You may want to have a look to the result I collected in the > `runs/freebsd-experiments' branch of: > > https://github.com/lacombar/hackbench/ > > and compare them with vanilla FreeBSD 9.0 and -CURRENT results > available in `runs/freebsd'. On the dual package platform, your patch > is not a definite win. > >> But in some cases, especially for multi-socket systems, to let it show its >> best, you may want to apply additional patch from avg@ to better detect CPU >> topology: >> https://gitorious.org/~avg/freebsd/avgbsd/commit/6bca4a2e4854ea3fc275946a023db65c483cb9dd >> > test I conducted specifically for this patch did not showed much > improvement... Can you please clarify on this point? The test you did included cases where the topology was detected badly against cases where the topology was detected correctly as a patched kernel (and you still didn't see a performance improvement), in terms of cache line sharing? Attilio -- Peace can only be achieved by understanding - A. Einstein ___ freebsd-current@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to "freebsd-current-unsubscr...@freebsd.org"
Re: Scheduler + IPC performance on FreeBSD 7.4, 8.2, 9.0 and -CURRENT
On 05.04.12 20:03, Arnaud Lacombe wrote: Hi folks, Hi, Over the past months, I ran on a couple of unused box the `hackbench'[HACKBENCH] benchmark used by the Linux folks for tracking down various kind of regression/improvement. `hackbench' is a scheduler + IPC test (socket xor pipe). It creates producers/consumers groups and let a variable quantity of small messages flow happily. Producers and consumers are either processes xor threads. [Lots of likely very interesting and valuable data.] Q4: "So, how can I get all the graph ?" R4: All you need is git, a posix shell, a couple of utility (find, sort, ...), a recent gnuplot, and a ruby interpreter. Can you give us some hints on *how* to get the results? I checked the repo out but it's not immediately obvious what to do and how to get the graphs, as staring at thousands of numbers in lots of different files isn't exactly practical. Thanks, Florian ___ freebsd-current@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to "freebsd-current-unsubscr...@freebsd.org"
Re: [RFT][patch] Scheduling for HTT and not only
On 04/06/12 17:13, Attilio Rao wrote: Il 05 aprile 2012 19:12, Arnaud Lacombe ha scritto: Hi, [Sorry for the delay, I got a bit sidetrack'ed...] 2012/2/17 Alexander Motin: On 17.02.2012 18:53, Arnaud Lacombe wrote: On Fri, Feb 17, 2012 at 11:29 AM, Alexander Motinwrote: On 02/15/12 21:54, Jeff Roberson wrote: On Wed, 15 Feb 2012, Alexander Motin wrote: I've decided to stop those cache black magic practices and focus on things that really exist in this world -- SMT and CPU load. I've dropped most of cache related things from the patch and made the rest of things more strict and predictable: http://people.freebsd.org/~mav/sched.htt34.patch This looks great. I think there is value in considering the other approach further but I would like to do this part first. It would be nice to also add priority as a greater influence in the load balancing as well. I haven't got good idea yet about balancing priorities, but I've rewritten balancer itself. As soon as sched_lowest() / sched_highest() are more intelligent now, they allowed to remove topology traversing from the balancer itself. That should fix double-swapping problem, allow to keep some affinity while moving threads and make balancing more fair. I did number of tests running 4, 8, 9 and 16 CPU-bound threads on 8 CPUs. With 4, 8 and 16 threads everything is stationary as it should. With 9 threads I see regular and random load move between all 8 CPUs. Measurements on 5 minutes run show deviation of only about 5 seconds. It is the same deviation as I see caused by only scheduling of 16 threads on 8 cores without any balancing needed at all. So I believe this code works as it should. Here is the patch: http://people.freebsd.org/~mav/sched.htt40.patch I plan this to be a final patch of this series (more to come :)) and if there will be no problems or objections, I am going to commit it (except some debugging KTRs) in about ten days. So now it's a good time for reviews and testing. :) is there a place where all the patches are available ? All my scheduler patches are cumulative, so all you need is only the last mentioned here sched.htt40.patch. You may want to have a look to the result I collected in the `runs/freebsd-experiments' branch of: https://github.com/lacombar/hackbench/ and compare them with vanilla FreeBSD 9.0 and -CURRENT results available in `runs/freebsd'. On the dual package platform, your patch is not a definite win. But in some cases, especially for multi-socket systems, to let it show its best, you may want to apply additional patch from avg@ to better detect CPU topology: https://gitorious.org/~avg/freebsd/avgbsd/commit/6bca4a2e4854ea3fc275946a023db65c483cb9dd test I conducted specifically for this patch did not showed much improvement... Can you please clarify on this point? The test you did included cases where the topology was detected badly against cases where the topology was detected correctly as a patched kernel (and you still didn't see a performance improvement), in terms of cache line sharing? At this moment SCHED_ULE does almost nothing in terms of cache line sharing affinity (though it probably worth some further experiments). What this patch may improve is opposite case -- reduce cache sharing pressure for cache-hungry applications. For example, proper cache topology detection (such as lack of global L3 cache, but shared L2 per pairs of cores on Core2Quad class CPUs) increases pbzip2 performance when number of threads is less then number of CPUs (i.e. when there is place for optimization). -- Alexander Motin ___ freebsd-current@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to "freebsd-current-unsubscr...@freebsd.org"
Re: [RFT][patch] Scheduling for HTT and not only
Il 06 aprile 2012 15:27, Alexander Motin ha scritto: > On 04/06/12 17:13, Attilio Rao wrote: >> >> Il 05 aprile 2012 19:12, Arnaud Lacombe ha scritto: >>> >>> Hi, >>> >>> [Sorry for the delay, I got a bit sidetrack'ed...] >>> >>> 2012/2/17 Alexander Motin: On 17.02.2012 18:53, Arnaud Lacombe wrote: > > > On Fri, Feb 17, 2012 at 11:29 AM, Alexander Motin > wrote: >> >> >> On 02/15/12 21:54, Jeff Roberson wrote: >>> >>> >>> On Wed, 15 Feb 2012, Alexander Motin wrote: I've decided to stop those cache black magic practices and focus on things that really exist in this world -- SMT and CPU load. I've dropped most of cache related things from the patch and made the rest of things more strict and predictable: http://people.freebsd.org/~mav/sched.htt34.patch >>> >>> >>> >>> This looks great. I think there is value in considering the other >>> approach further but I would like to do this part first. It would be >>> nice to also add priority as a greater influence in the load >>> balancing >>> as well. >> >> >> >> I haven't got good idea yet about balancing priorities, but I've >> rewritten >> balancer itself. As soon as sched_lowest() / sched_highest() are more >> intelligent now, they allowed to remove topology traversing from the >> balancer itself. That should fix double-swapping problem, allow to >> keep >> some >> affinity while moving threads and make balancing more fair. I did >> number >> of >> tests running 4, 8, 9 and 16 CPU-bound threads on 8 CPUs. With 4, 8 >> and >> 16 >> threads everything is stationary as it should. With 9 threads I see >> regular >> and random load move between all 8 CPUs. Measurements on 5 minutes run >> show >> deviation of only about 5 seconds. It is the same deviation as I see >> caused >> by only scheduling of 16 threads on 8 cores without any balancing >> needed >> at >> all. So I believe this code works as it should. >> >> Here is the patch: http://people.freebsd.org/~mav/sched.htt40.patch >> >> I plan this to be a final patch of this series (more to come :)) and >> if >> there will be no problems or objections, I am going to commit it >> (except >> some debugging KTRs) in about ten days. So now it's a good time for >> reviews >> and testing. :) >> > is there a place where all the patches are available ? All my scheduler patches are cumulative, so all you need is only the last mentioned here sched.htt40.patch. >>> You may want to have a look to the result I collected in the >>> `runs/freebsd-experiments' branch of: >>> >>> https://github.com/lacombar/hackbench/ >>> >>> and compare them with vanilla FreeBSD 9.0 and -CURRENT results >>> available in `runs/freebsd'. On the dual package platform, your patch >>> is not a definite win. >>> But in some cases, especially for multi-socket systems, to let it show its best, you may want to apply additional patch from avg@ to better detect CPU topology: https://gitorious.org/~avg/freebsd/avgbsd/commit/6bca4a2e4854ea3fc275946a023db65c483cb9dd >>> test I conducted specifically for this patch did not showed much >>> improvement... >> >> >> Can you please clarify on this point? >> The test you did included cases where the topology was detected badly >> against cases where the topology was detected correctly as a patched >> kernel (and you still didn't see a performance improvement), in terms >> of cache line sharing? > > > At this moment SCHED_ULE does almost nothing in terms of cache line sharing > affinity (though it probably worth some further experiments). What this > patch may improve is opposite case -- reduce cache sharing pressure for > cache-hungry applications. For example, proper cache topology detection > (such as lack of global L3 cache, but shared L2 per pairs of cores on > Core2Quad class CPUs) increases pbzip2 performance when number of threads is > less then number of CPUs (i.e. when there is place for optimization). My asking is not referred to your patch really. I just wanted to know if he correctly benchmark a case where the topology was screwed up and then correctly recognized by avg's patch in terms of cache level aggregation (it wasn't referred to your patch btw). Attilio -- Peace can only be achieved by understanding - A. Einstein ___ freebsd-current@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to "freebsd-current-unsubscr...@freebsd.org"
Re: [RFT][patch] Scheduling for HTT and not only
On 04/06/12 17:30, Attilio Rao wrote: Il 06 aprile 2012 15:27, Alexander Motin ha scritto: On 04/06/12 17:13, Attilio Rao wrote: Il 05 aprile 2012 19:12, Arnaud Lacombeha scritto: Hi, [Sorry for the delay, I got a bit sidetrack'ed...] 2012/2/17 Alexander Motin: On 17.02.2012 18:53, Arnaud Lacombe wrote: On Fri, Feb 17, 2012 at 11:29 AM, Alexander Motin wrote: On 02/15/12 21:54, Jeff Roberson wrote: On Wed, 15 Feb 2012, Alexander Motin wrote: I've decided to stop those cache black magic practices and focus on things that really exist in this world -- SMT and CPU load. I've dropped most of cache related things from the patch and made the rest of things more strict and predictable: http://people.freebsd.org/~mav/sched.htt34.patch This looks great. I think there is value in considering the other approach further but I would like to do this part first. It would be nice to also add priority as a greater influence in the load balancing as well. I haven't got good idea yet about balancing priorities, but I've rewritten balancer itself. As soon as sched_lowest() / sched_highest() are more intelligent now, they allowed to remove topology traversing from the balancer itself. That should fix double-swapping problem, allow to keep some affinity while moving threads and make balancing more fair. I did number of tests running 4, 8, 9 and 16 CPU-bound threads on 8 CPUs. With 4, 8 and 16 threads everything is stationary as it should. With 9 threads I see regular and random load move between all 8 CPUs. Measurements on 5 minutes run show deviation of only about 5 seconds. It is the same deviation as I see caused by only scheduling of 16 threads on 8 cores without any balancing needed at all. So I believe this code works as it should. Here is the patch: http://people.freebsd.org/~mav/sched.htt40.patch I plan this to be a final patch of this series (more to come :)) and if there will be no problems or objections, I am going to commit it (except some debugging KTRs) in about ten days. So now it's a good time for reviews and testing. :) is there a place where all the patches are available ? All my scheduler patches are cumulative, so all you need is only the last mentioned here sched.htt40.patch. You may want to have a look to the result I collected in the `runs/freebsd-experiments' branch of: https://github.com/lacombar/hackbench/ and compare them with vanilla FreeBSD 9.0 and -CURRENT results available in `runs/freebsd'. On the dual package platform, your patch is not a definite win. But in some cases, especially for multi-socket systems, to let it show its best, you may want to apply additional patch from avg@ to better detect CPU topology: https://gitorious.org/~avg/freebsd/avgbsd/commit/6bca4a2e4854ea3fc275946a023db65c483cb9dd test I conducted specifically for this patch did not showed much improvement... Can you please clarify on this point? The test you did included cases where the topology was detected badly against cases where the topology was detected correctly as a patched kernel (and you still didn't see a performance improvement), in terms of cache line sharing? At this moment SCHED_ULE does almost nothing in terms of cache line sharing affinity (though it probably worth some further experiments). What this patch may improve is opposite case -- reduce cache sharing pressure for cache-hungry applications. For example, proper cache topology detection (such as lack of global L3 cache, but shared L2 per pairs of cores on Core2Quad class CPUs) increases pbzip2 performance when number of threads is less then number of CPUs (i.e. when there is place for optimization). My asking is not referred to your patch really. I just wanted to know if he correctly benchmark a case where the topology was screwed up and then correctly recognized by avg's patch in terms of cache level aggregation (it wasn't referred to your patch btw). I understand. I've just described test case when properly detected topology could give benefit. What the test really does is indeed a good question. -- Alexander Motin ___ freebsd-current@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to "freebsd-current-unsubscr...@freebsd.org"
Re: Scheduler + IPC performance on FreeBSD 7.4, 8.2, 9.0 and -CURRENT
Il 05 aprile 2012 19:03, Arnaud Lacombe ha scritto: > Hi folks, > > Over the past months, I ran on a couple of unused box the > `hackbench'[HACKBENCH] benchmark used by the Linux folks for tracking > down various kind of regression/improvement. `hackbench' is a > scheduler + IPC test (socket xor pipe). It creates producers/consumers > groups and let a variable quantity of small messages flow happily. > Producers and consumers are either processes xor threads. > > Tested platforms were > - Atom D510, Intel, (incomplete) > - Core 2 Quad Q9560, Intel > - Soekris net5501, AMD (incomplete) > - Xeon E5645, Intel (incomplete) > - Xeon E5620 (dual package), Intel > - Xeon E5-1650 (pending completion) > - Vortex86, DMP > > Tested kernel were: > - FreeBSD 7.4-RELEASE > - FreeBSD 8.2-RELEASE > - FreeBSD 9.0-RC3 and FreeBSD 9.0-RELEASE > - FreeBSD 10-CURRENT as of r231573 Which means you run 10-CURRENT with all the kernel debugging options on and MALLOC_DEBUG on? Attilio -- Peace can only be achieved by understanding - A. Einstein ___ freebsd-current@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to "freebsd-current-unsubscr...@freebsd.org"
[head tinderbox] failure on arm/arm
TB --- 2012-04-06 14:10:00 - tinderbox 2.9 running on freebsd-current.sentex.ca TB --- 2012-04-06 14:10:00 - FreeBSD freebsd-current.sentex.ca 8.3-PRERELEASE FreeBSD 8.3-PRERELEASE #0: Mon Mar 26 13:54:12 EDT 2012 d...@freebsd-current.sentex.ca:/usr/obj/usr/src/sys/GENERIC amd64 TB --- 2012-04-06 14:10:00 - starting HEAD tinderbox run for arm/arm TB --- 2012-04-06 14:10:00 - cleaning the object tree TB --- 2012-04-06 14:10:00 - cvsupping the source tree TB --- 2012-04-06 14:10:00 - /usr/bin/csup -z -r 3 -g -L 1 -h cvsup.sentex.ca /tinderbox/HEAD/arm/arm/supfile TB --- 2012-04-06 14:16:21 - building world TB --- 2012-04-06 14:16:21 - CROSS_BUILD_TESTING=YES TB --- 2012-04-06 14:16:21 - MAKEOBJDIRPREFIX=/obj TB --- 2012-04-06 14:16:21 - PATH=/usr/bin:/usr/sbin:/bin:/sbin TB --- 2012-04-06 14:16:21 - SRCCONF=/dev/null TB --- 2012-04-06 14:16:21 - TARGET=arm TB --- 2012-04-06 14:16:21 - TARGET_ARCH=arm TB --- 2012-04-06 14:16:21 - TZ=UTC TB --- 2012-04-06 14:16:21 - __MAKE_CONF=/dev/null TB --- 2012-04-06 14:16:21 - cd /src TB --- 2012-04-06 14:16:21 - /usr/bin/make -B buildworld >>> World build started on Fri Apr 6 14:16:22 UTC 2012 >>> Rebuilding the temporary build tree >>> stage 1.1: legacy release compatibility shims >>> stage 1.2: bootstrap tools >>> stage 2.1: cleaning up the object tree >>> stage 2.2: rebuilding the object tree >>> stage 2.3: build tools >>> stage 3: cross tools >>> stage 4.1: building includes >>> stage 4.2: building libraries >>> stage 4.3: make dependencies >>> stage 4.4: building everything >>> World build completed on Fri Apr 6 15:18:15 UTC 2012 TB --- 2012-04-06 15:18:15 - cd /src/sys/arm/conf TB --- 2012-04-06 15:18:15 - /usr/sbin/config -m AVILA TB --- 2012-04-06 15:18:15 - building AVILA kernel TB --- 2012-04-06 15:18:15 - CROSS_BUILD_TESTING=YES TB --- 2012-04-06 15:18:15 - MAKEOBJDIRPREFIX=/obj TB --- 2012-04-06 15:18:15 - PATH=/usr/bin:/usr/sbin:/bin:/sbin TB --- 2012-04-06 15:18:15 - SRCCONF=/dev/null TB --- 2012-04-06 15:18:15 - TARGET=arm TB --- 2012-04-06 15:18:15 - TARGET_ARCH=arm TB --- 2012-04-06 15:18:15 - TZ=UTC TB --- 2012-04-06 15:18:15 - __MAKE_CONF=/dev/null TB --- 2012-04-06 15:18:15 - cd /src TB --- 2012-04-06 15:18:15 - /usr/bin/make -B buildkernel KERNCONF=AVILA >>> Kernel build for AVILA started on Fri Apr 6 15:18:15 UTC 2012 >>> stage 1: configuring the kernel >>> stage 2.1: cleaning up the object tree >>> stage 2.2: rebuilding the object tree >>> stage 2.3: build tools >>> stage 3.1: making dependencies >>> stage 3.2: building everything [...] cc -mbig-endian -c -O -pipe -std=c99 -g -Wall -Wredundant-decls -Wnested-externs -Wstrict-prototypes -Wmissing-prototypes -Wpointer-arith -Winline -Wcast-qual -Wundef -Wno-pointer-sign -fformat-extensions -Wmissing-include-dirs -fdiagnostics-show-option -nostdinc -I. -I/src/sys -I/src/sys/contrib/altq -I/src/sys/contrib/libfdt -D_KERNEL -DHAVE_KERNEL_OPTION_HEADERS -include opt_global.h -fno-common -finline-limit=8000 --param inline-unit-growth=100 --param large-function-growth=1000 -mcpu=xscale -ffreestanding -Werror /src/sys/libkern/strtoul.c cc -mbig-endian -c -O -pipe -std=c99 -g -Wall -Wredundant-decls -Wnested-externs -Wstrict-prototypes -Wmissing-prototypes -Wpointer-arith -Winline -Wcast-qual -Wundef -Wno-pointer-sign -fformat-extensions -Wmissing-include-dirs -fdiagnostics-show-option -nostdinc -I. -I/src/sys -I/src/sys/contrib/altq -I/src/sys/contrib/libfdt -D_KERNEL -DHAVE_KERNEL_OPTION_HEADERS -include opt_global.h -fno-common -finline-limit=8000 --param inline-unit-growth=100 --param large-function-growth=1000 -mcpu=xscale -ffreestanding -Werror /src/sys/libkern/strtouq.c cc -mbig-endian -c -O -pipe -std=c99 -g -Wall -Wredundant-decls -Wnested-externs -Wstrict-prototypes -Wmissing-prototypes -Wpointer-arith -Winline -Wcast-qual -Wundef -Wno-pointer-sign -fformat-extensions -Wmissing-include-dirs -fdiagnostics-show-option -nostdinc -I. -I/src/sys -I/src/sys/contrib/altq -I/src/sys/contrib/libfdt -D_KERNEL -DHAVE_KERNEL_OPTION_HEADERS -include opt_global.h -fno-common -finline-limit=8000 --param inline-unit-growth=100 --param large-function-growth=1000 -mcpu=xscale -ffreestanding -Werror /src/sys/libkern/strvalid.c cc -mbig-endian -c -O -pipe -std=c99 -g -Wall -Wredundant-decls -Wnested-externs -Wstrict-prototypes -Wmissing-prototypes -Wpointer-arith -Winline -Wcast-qual -Wundef -Wno-pointer-sign -fformat-extensions -Wmissing-include-dirs -fdiagnostics-show-option -nostdinc -I. -I/src/sys -I/src/sys/contrib/altq -I/src/sys/contrib/libfdt -D_KERNEL -DHAVE_KERNEL_OPTION_HEADERS -include opt_global.h -fno-common -finline-limit=8000 --param inline-unit-growth=100 --param large-function-growth=1000 -mcpu=xscale -ffreestanding -Werror /src/sys/net/bpf.c /src/sys/net/bpf.c: In function 'bpf_setf': /src/sys/net/bpf.c:1683: error: 'need_upgrade' undeclared (first use in this function) /src/sys/net/bpf.c:1683: error: (Each undeclared ident
[head tinderbox] failure on i386/pc98
TB --- 2012-04-06 14:10:00 - tinderbox 2.9 running on freebsd-current.sentex.ca TB --- 2012-04-06 14:10:00 - FreeBSD freebsd-current.sentex.ca 8.3-PRERELEASE FreeBSD 8.3-PRERELEASE #0: Mon Mar 26 13:54:12 EDT 2012 d...@freebsd-current.sentex.ca:/usr/obj/usr/src/sys/GENERIC amd64 TB --- 2012-04-06 14:10:00 - starting HEAD tinderbox run for i386/pc98 TB --- 2012-04-06 14:10:00 - cleaning the object tree TB --- 2012-04-06 14:10:00 - cvsupping the source tree TB --- 2012-04-06 14:10:00 - /usr/bin/csup -z -r 3 -g -L 1 -h cvsup.sentex.ca /tinderbox/HEAD/i386/pc98/supfile TB --- 2012-04-06 14:12:14 - building world TB --- 2012-04-06 14:12:14 - CROSS_BUILD_TESTING=YES TB --- 2012-04-06 14:12:14 - MAKEOBJDIRPREFIX=/obj TB --- 2012-04-06 14:12:14 - PATH=/usr/bin:/usr/sbin:/bin:/sbin TB --- 2012-04-06 14:12:14 - SRCCONF=/dev/null TB --- 2012-04-06 14:12:14 - TARGET=pc98 TB --- 2012-04-06 14:12:14 - TARGET_ARCH=i386 TB --- 2012-04-06 14:12:14 - TZ=UTC TB --- 2012-04-06 14:12:14 - __MAKE_CONF=/dev/null TB --- 2012-04-06 14:12:14 - cd /src TB --- 2012-04-06 14:12:14 - /usr/bin/make -B buildworld >>> World build started on Fri Apr 6 14:12:14 UTC 2012 >>> Rebuilding the temporary build tree >>> stage 1.1: legacy release compatibility shims >>> stage 1.2: bootstrap tools >>> stage 2.1: cleaning up the object tree >>> stage 2.2: rebuilding the object tree >>> stage 2.3: build tools >>> stage 3: cross tools >>> stage 4.1: building includes >>> stage 4.2: building libraries >>> stage 4.3: make dependencies >>> stage 4.4: building everything >>> World build completed on Fri Apr 6 16:34:30 UTC 2012 TB --- 2012-04-06 16:34:30 - generating LINT kernel config TB --- 2012-04-06 16:34:30 - cd /src/sys/pc98/conf TB --- 2012-04-06 16:34:30 - /usr/bin/make -B LINT TB --- 2012-04-06 16:34:30 - cd /src/sys/pc98/conf TB --- 2012-04-06 16:34:30 - /usr/sbin/config -m LINT TB --- 2012-04-06 16:34:30 - building LINT kernel TB --- 2012-04-06 16:34:30 - CROSS_BUILD_TESTING=YES TB --- 2012-04-06 16:34:30 - MAKEOBJDIRPREFIX=/obj TB --- 2012-04-06 16:34:30 - PATH=/usr/bin:/usr/sbin:/bin:/sbin TB --- 2012-04-06 16:34:30 - SRCCONF=/dev/null TB --- 2012-04-06 16:34:30 - TARGET=pc98 TB --- 2012-04-06 16:34:30 - TARGET_ARCH=i386 TB --- 2012-04-06 16:34:30 - TZ=UTC TB --- 2012-04-06 16:34:30 - __MAKE_CONF=/dev/null TB --- 2012-04-06 16:34:30 - cd /src TB --- 2012-04-06 16:34:30 - /usr/bin/make -B buildkernel KERNCONF=LINT >>> Kernel build for LINT started on Fri Apr 6 16:34:30 UTC 2012 >>> stage 1: configuring the kernel >>> stage 2.1: cleaning up the object tree >>> stage 2.2: rebuilding the object tree >>> stage 2.3: build tools >>> stage 3.1: making dependencies >>> stage 3.2: building everything [...] cc -c -O2 -pipe -fno-strict-aliasing -std=c99 -Wall -Wredundant-decls -Wnested-externs -Wstrict-prototypes -Wmissing-prototypes -Wpointer-arith -Winline -Wcast-qual -Wundef -Wno-pointer-sign -fformat-extensions -Wmissing-include-dirs -fdiagnostics-show-option -nostdinc -I. -I/src/sys -I/src/sys/contrib/altq -D_KERNEL -DHAVE_KERNEL_OPTION_HEADERS -include opt_global.h -fno-common -finline-limit=8000 --param inline-unit-growth=100 --param large-function-growth=1000 -DGPROF -falign-functions=16 -DGPROF4 -DGUPROF -fno-builtin -mno-align-long-strings -mpreferred-stack-boundary=2 -mno-mmx -mno-sse -msoft-float -ffreestanding -fstack-protector -Werror -pg -mprofiler-epilogue /src/sys/libkern/strtoul.c cc -c -O2 -pipe -fno-strict-aliasing -std=c99 -Wall -Wredundant-decls -Wnested-externs -Wstrict-prototypes -Wmissing-prototypes -Wpointer-arith -Winline -Wcast-qual -Wundef -Wno-pointer-sign -fformat-extensions -Wmissing-include-dirs -fdiagnostics-show-option -nostdinc -I. -I/src/sys -I/src/sys/contrib/altq -D_KERNEL -DHAVE_KERNEL_OPTION_HEADERS -include opt_global.h -fno-common -finline-limit=8000 --param inline-unit-growth=100 --param large-function-growth=1000 -DGPROF -falign-functions=16 -DGPROF4 -DGUPROF -fno-builtin -mno-align-long-strings -mpreferred-stack-boundary=2 -mno-mmx -mno-sse -msoft-float -ffreestanding -fstack-protector -Werror -pg -mprofiler-epilogue /src/sys/libkern/strtouq.c cc -c -O2 -pipe -fno-strict-aliasing -std=c99 -Wall -Wredundant-decls -Wnested-externs -Wstrict-prototypes -Wmissing-prototypes -Wpointer-arith -Winline -Wcast-qual -Wundef -Wno-pointer-sign -fformat-extensions -Wmissing-include-dirs -fdiagnostics-show-option -nostdinc -I. -I/src/sys -I/src/sys/contrib/altq -D_KERNEL -DHAVE_KERNEL_OPTION_HEADERS -include opt_global.h -fno-common -finline-limit=8000 --param inline-unit-growth=100 --param large-function-growth=1000 -DGPROF -falign-functions=16 -DGPROF4 -DGUPROF -fno-builtin -mno-align-long-strings -mpreferred-stack-boundary=2 -mno-mmx -mno-sse -msoft-float -ffreestanding -fstack-protector -Werror -pg -mprofiler-epilogue /src/sys/libkern/strvalid.c cc -c -O2 -pipe -fno-strict-aliasing -std=c99 -Wall -Wredundant-decls -Wnested-externs -Wstrict-prototypes -Wmiss
[head tinderbox] failure on i386/i386
TB --- 2012-04-06 14:10:00 - tinderbox 2.9 running on freebsd-current.sentex.ca TB --- 2012-04-06 14:10:00 - FreeBSD freebsd-current.sentex.ca 8.3-PRERELEASE FreeBSD 8.3-PRERELEASE #0: Mon Mar 26 13:54:12 EDT 2012 d...@freebsd-current.sentex.ca:/usr/obj/usr/src/sys/GENERIC amd64 TB --- 2012-04-06 14:10:00 - starting HEAD tinderbox run for i386/i386 TB --- 2012-04-06 14:10:00 - cleaning the object tree TB --- 2012-04-06 14:10:00 - cvsupping the source tree TB --- 2012-04-06 14:10:00 - /usr/bin/csup -z -r 3 -g -L 1 -h cvsup.sentex.ca /tinderbox/HEAD/i386/i386/supfile TB --- 2012-04-06 14:12:02 - building world TB --- 2012-04-06 14:12:02 - CROSS_BUILD_TESTING=YES TB --- 2012-04-06 14:12:02 - MAKEOBJDIRPREFIX=/obj TB --- 2012-04-06 14:12:02 - PATH=/usr/bin:/usr/sbin:/bin:/sbin TB --- 2012-04-06 14:12:02 - SRCCONF=/dev/null TB --- 2012-04-06 14:12:02 - TARGET=i386 TB --- 2012-04-06 14:12:02 - TARGET_ARCH=i386 TB --- 2012-04-06 14:12:02 - TZ=UTC TB --- 2012-04-06 14:12:02 - __MAKE_CONF=/dev/null TB --- 2012-04-06 14:12:02 - cd /src TB --- 2012-04-06 14:12:02 - /usr/bin/make -B buildworld >>> World build started on Fri Apr 6 14:12:04 UTC 2012 >>> Rebuilding the temporary build tree >>> stage 1.1: legacy release compatibility shims >>> stage 1.2: bootstrap tools >>> stage 2.1: cleaning up the object tree >>> stage 2.2: rebuilding the object tree >>> stage 2.3: build tools >>> stage 3: cross tools >>> stage 4.1: building includes >>> stage 4.2: building libraries >>> stage 4.3: make dependencies >>> stage 4.4: building everything >>> World build completed on Fri Apr 6 16:33:59 UTC 2012 TB --- 2012-04-06 16:33:59 - generating LINT kernel config TB --- 2012-04-06 16:33:59 - cd /src/sys/i386/conf TB --- 2012-04-06 16:33:59 - /usr/bin/make -B LINT TB --- 2012-04-06 16:34:00 - cd /src/sys/i386/conf TB --- 2012-04-06 16:34:00 - /usr/sbin/config -m LINT TB --- 2012-04-06 16:34:00 - building LINT kernel TB --- 2012-04-06 16:34:00 - CROSS_BUILD_TESTING=YES TB --- 2012-04-06 16:34:00 - MAKEOBJDIRPREFIX=/obj TB --- 2012-04-06 16:34:00 - PATH=/usr/bin:/usr/sbin:/bin:/sbin TB --- 2012-04-06 16:34:00 - SRCCONF=/dev/null TB --- 2012-04-06 16:34:00 - TARGET=i386 TB --- 2012-04-06 16:34:00 - TARGET_ARCH=i386 TB --- 2012-04-06 16:34:00 - TZ=UTC TB --- 2012-04-06 16:34:00 - __MAKE_CONF=/dev/null TB --- 2012-04-06 16:34:00 - cd /src TB --- 2012-04-06 16:34:00 - /usr/bin/make -B buildkernel KERNCONF=LINT >>> Kernel build for LINT started on Fri Apr 6 16:34:00 UTC 2012 >>> stage 1: configuring the kernel >>> stage 2.1: cleaning up the object tree >>> stage 2.2: rebuilding the object tree >>> stage 2.3: build tools >>> stage 3.1: making dependencies >>> stage 3.2: building everything [...] cc -c -O2 -pipe -fno-strict-aliasing -std=c99 -Wall -Wredundant-decls -Wnested-externs -Wstrict-prototypes -Wmissing-prototypes -Wpointer-arith -Winline -Wcast-qual -Wundef -Wno-pointer-sign -fformat-extensions -Wmissing-include-dirs -fdiagnostics-show-option -nostdinc -I. -I/src/sys -I/src/sys/contrib/altq -D_KERNEL -DHAVE_KERNEL_OPTION_HEADERS -include opt_global.h -fno-common -finline-limit=8000 --param inline-unit-growth=100 --param large-function-growth=1000 -DGPROF -falign-functions=16 -DGPROF4 -DGUPROF -fno-builtin -mno-align-long-strings -mpreferred-stack-boundary=2 -mno-mmx -mno-sse -msoft-float -ffreestanding -fstack-protector -Werror -pg -mprofiler-epilogue /src/sys/libkern/strtoul.c cc -c -O2 -pipe -fno-strict-aliasing -std=c99 -Wall -Wredundant-decls -Wnested-externs -Wstrict-prototypes -Wmissing-prototypes -Wpointer-arith -Winline -Wcast-qual -Wundef -Wno-pointer-sign -fformat-extensions -Wmissing-include-dirs -fdiagnostics-show-option -nostdinc -I. -I/src/sys -I/src/sys/contrib/altq -D_KERNEL -DHAVE_KERNEL_OPTION_HEADERS -include opt_global.h -fno-common -finline-limit=8000 --param inline-unit-growth=100 --param large-function-growth=1000 -DGPROF -falign-functions=16 -DGPROF4 -DGUPROF -fno-builtin -mno-align-long-strings -mpreferred-stack-boundary=2 -mno-mmx -mno-sse -msoft-float -ffreestanding -fstack-protector -Werror -pg -mprofiler-epilogue /src/sys/libkern/strtouq.c cc -c -O2 -pipe -fno-strict-aliasing -std=c99 -Wall -Wredundant-decls -Wnested-externs -Wstrict-prototypes -Wmissing-prototypes -Wpointer-arith -Winline -Wcast-qual -Wundef -Wno-pointer-sign -fformat-extensions -Wmissing-include-dirs -fdiagnostics-show-option -nostdinc -I. -I/src/sys -I/src/sys/contrib/altq -D_KERNEL -DHAVE_KERNEL_OPTION_HEADERS -include opt_global.h -fno-common -finline-limit=8000 --param inline-unit-growth=100 --param large-function-growth=1000 -DGPROF -falign-functions=16 -DGPROF4 -DGUPROF -fno-builtin -mno-align-long-strings -mpreferred-stack-boundary=2 -mno-mmx -mno-sse -msoft-float -ffreestanding -fstack-protector -Werror -pg -mprofiler-epilogue /src/sys/libkern/strvalid.c cc -c -O2 -pipe -fno-strict-aliasing -std=c99 -Wall -Wredundant-decls -Wnested-externs -Wstrict-prototypes -Wmiss
[head tinderbox] failure on mips/mips
TB --- 2012-04-06 16:48:56 - tinderbox 2.9 running on freebsd-current.sentex.ca TB --- 2012-04-06 16:48:56 - FreeBSD freebsd-current.sentex.ca 8.3-PRERELEASE FreeBSD 8.3-PRERELEASE #0: Mon Mar 26 13:54:12 EDT 2012 d...@freebsd-current.sentex.ca:/usr/obj/usr/src/sys/GENERIC amd64 TB --- 2012-04-06 16:48:56 - starting HEAD tinderbox run for mips/mips TB --- 2012-04-06 16:48:56 - cleaning the object tree TB --- 2012-04-06 16:49:43 - cvsupping the source tree TB --- 2012-04-06 16:49:43 - /usr/bin/csup -z -r 3 -g -L 1 -h cvsup.sentex.ca /tinderbox/HEAD/mips/mips/supfile TB --- 2012-04-06 16:50:29 - building world TB --- 2012-04-06 16:50:29 - CROSS_BUILD_TESTING=YES TB --- 2012-04-06 16:50:29 - MAKEOBJDIRPREFIX=/obj TB --- 2012-04-06 16:50:29 - PATH=/usr/bin:/usr/sbin:/bin:/sbin TB --- 2012-04-06 16:50:29 - SRCCONF=/dev/null TB --- 2012-04-06 16:50:29 - TARGET=mips TB --- 2012-04-06 16:50:29 - TARGET_ARCH=mips TB --- 2012-04-06 16:50:29 - TZ=UTC TB --- 2012-04-06 16:50:29 - __MAKE_CONF=/dev/null TB --- 2012-04-06 16:50:29 - cd /src TB --- 2012-04-06 16:50:29 - /usr/bin/make -B buildworld >>> World build started on Fri Apr 6 16:50:30 UTC 2012 >>> Rebuilding the temporary build tree >>> stage 1.1: legacy release compatibility shims >>> stage 1.2: bootstrap tools >>> stage 2.1: cleaning up the object tree >>> stage 2.2: rebuilding the object tree >>> stage 2.3: build tools >>> stage 3: cross tools >>> stage 4.1: building includes >>> stage 4.2: building libraries >>> stage 4.3: make dependencies >>> stage 4.4: building everything [...] cc -O -pipe -G0 -I/src/kerberos5/libexec/kfd/../../../crypto/heimdal/lib/asn1 -I/src/kerberos5/libexec/kfd/../../../crypto/heimdal/lib/roken -DHAVE_CONFIG_H -I/src/kerberos5/libexec/kfd/../../include -std=gnu99 -c /src/kerberos5/libexec/kfd/../../../crypto/heimdal/appl/kf/kfd.c cc -O -pipe -G0 -I/src/kerberos5/libexec/kfd/../../../crypto/heimdal/lib/asn1 -I/src/kerberos5/libexec/kfd/../../../crypto/heimdal/lib/roken -DHAVE_CONFIG_H -I/src/kerberos5/libexec/kfd/../../include -std=gnu99 -o kfd kfd.o -lkrb5 -lroken -lasn1 -lcrypto -lcrypt /obj/mips.mips/src/kerberos5/libexec/kfd/../../lib/libvers/libvers.a gzip -cn /src/kerberos5/libexec/kfd/../../../crypto/heimdal/appl/kf/kfd.8 > kfd.8.gz ===> kerberos5/libexec/kimpersonate (all) cc -O -pipe -G0 -I/src/kerberos5/libexec/kimpersonate/../../../crypto/heimdal/lib/hx509 -I/src/kerberos5/libexec/kimpersonate/../../../crypto/heimdal/lib/asn1 -I/src/kerberos5/libexec/kimpersonate/../../../crypto/heimdal/lib/roken -I/src/kerberos5/libexec/kimpersonate/../../../crypto/heimdal/lib/sl -I. -DHAVE_CONFIG_H -I/src/kerberos5/libexec/kimpersonate/../../include -std=gnu99 -c /src/kerberos5/libexec/kimpersonate/../../../crypto/heimdal/kuser/kimpersonate.c cc -O -pipe -G0 -I/src/kerberos5/libexec/kimpersonate/../../../crypto/heimdal/lib/hx509 -I/src/kerberos5/libexec/kimpersonate/../../../crypto/heimdal/lib/asn1 -I/src/kerberos5/libexec/kimpersonate/../../../crypto/heimdal/lib/roken -I/src/kerberos5/libexec/kimpersonate/../../../crypto/heimdal/lib/sl -I. -DHAVE_CONFIG_H -I/src/kerberos5/libexec/kimpersonate/../../include -std=gnu99 -o kimpersonate kimpersonate.o -lkafs5 -lkrb5 -lheimntlm -lroken -lasn1 -lcrypto -lcrypt /obj/mips.mips/src/kerberos5/libexec/kimpersonate/../../lib/libvers/libvers.a /obj/mips.mips/src/tmp/usr/bin/ld: /obj/mips.mips/src/tmp/usr/lib/libkafs5.so symbol number 13 references nonexistent SHT_SYMTAB_SHNDX section /obj/mips.mips/src/tmp/usr/lib/libkafs5.so: could not read symbols: File format not recognized *** Error code 1 Stop in /src/kerberos5/libexec/kimpersonate. *** Error code 1 Stop in /src/kerberos5/libexec. *** Error code 1 Stop in /src/kerberos5. *** Error code 1 Stop in /src. *** Error code 1 Stop in /src. *** Error code 1 Stop in /src. TB --- 2012-04-06 17:41:01 - WARNING: /usr/bin/make returned exit code 1 TB --- 2012-04-06 17:41:01 - ERROR: failed to build world TB --- 2012-04-06 17:41:01 - 2098.24 user 447.10 system 3125.41 real http://tinderbox.freebsd.org/tinderbox-head-HEAD-mips-mips.full ___ freebsd-current@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to "freebsd-current-unsubscr...@freebsd.org"
Re: Scheduler + IPC performance on FreeBSD 7.4, 8.2, 9.0 and -CURRENT
Hi, On Fri, Apr 6, 2012 at 10:24 AM, Florian Smeets wrote: > On 05.04.12 20:03, Arnaud Lacombe wrote: >> >> Hi folks, > > Hi, >> >> Over the past months, I ran on a couple of unused box the >> `hackbench'[HACKBENCH] benchmark used by the Linux folks for tracking >> down various kind of regression/improvement. `hackbench' is a >> scheduler + IPC test (socket xor pipe). It creates producers/consumers >> groups and let a variable quantity of small messages flow happily. >> Producers and consumers are either processes xor threads. > [Lots of likely very interesting and valuable data.] > >> >> Q4: "So, how can I get all the graph ?" >> R4: All you need is git, a posix shell, a couple of utility (find, >> sort, ...), a recent gnuplot, and a ruby interpreter. >> > > Can you give us some hints on *how* to get the results? I checked the repo > out but it's not immediately obvious what to do and how to get the graphs, > as staring at thousands of numbers in lots of different files isn't exactly > practical. > To just get all the graph, merge the runs/* branch you want, and just run the `results.sh' script: # sh results.sh To gather result, build `hackbench': # eval $(sed '/#gcc/!d; s/.//' hackbench.c) then, reboot in single mode, mount / read-write, adjust whatever you have to adjust and run the script: # sh hackbench.sh [light|medium|heavy] $(pwd)/hackbench this will run a complete iterations over all the possible tunables and gives you a `results.yml' that you can feed to the previous script. - Arnaud > Thanks, > Florian ___ freebsd-current@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to "freebsd-current-unsubscr...@freebsd.org"
Re: Scheduler + IPC performance on FreeBSD 7.4, 8.2, 9.0 and -CURRENT
Hi, On Fri, Apr 6, 2012 at 10:58 AM, Attilio Rao wrote: > Il 05 aprile 2012 19:03, Arnaud Lacombe ha scritto: >> Hi folks, >> >> Over the past months, I ran on a couple of unused box the >> `hackbench'[HACKBENCH] benchmark used by the Linux folks for tracking >> down various kind of regression/improvement. `hackbench' is a >> scheduler + IPC test (socket xor pipe). It creates producers/consumers >> groups and let a variable quantity of small messages flow happily. >> Producers and consumers are either processes xor threads. >> >> Tested platforms were >> - Atom D510, Intel, (incomplete) >> - Core 2 Quad Q9560, Intel >> - Soekris net5501, AMD (incomplete) >> - Xeon E5645, Intel (incomplete) >> - Xeon E5620 (dual package), Intel >> - Xeon E5-1650 (pending completion) >> - Vortex86, DMP >> >> Tested kernel were: >> - FreeBSD 7.4-RELEASE >> - FreeBSD 8.2-RELEASE >> - FreeBSD 9.0-RC3 and FreeBSD 9.0-RELEASE >> - FreeBSD 10-CURRENT as of r231573 > > Which means you run 10-CURRENT with all the kernel debugging options > on and MALLOC_DEBUG on? > I already answered that question. Namely: << note: rule [I] is alleviated for -CURRENT kernels, which were built with the same alteration made to GENERIC during the CURRENT->RELEASE transition (ie. WITNESS and a couple of other option disabled). >> this translates into the following patch (for amd64): diff --git a/sys/amd64/conf/GENERIC b/sys/amd64/conf/GENERIC index 8db8e27..9d61f25 100644 --- a/sys/amd64/conf/GENERIC +++ b/sys/amd64/conf/GENERIC @@ -67,20 +67,6 @@ options MAC # TrustedBSD MAC Framework #options KDTRACE_HOOKS # Kernel DTrace hooks optionsINCLUDE_CONFIG_FILE # Include this file in kernel -# Debugging support. Always need this: -optionsKDB # Enable kernel debugger support. -# For minimum debugger support (stable branch) use: -#options KDB_TRACE # Print a stack trace for a panic. -# For full debugger support use this instead: -optionsDDB # Support DDB. -optionsGDB # Support remote GDB. -optionsDEADLKRES # Enable the deadlock resolver -optionsINVARIANTS # Enable calls of extra sanity checking -optionsINVARIANT_SUPPORT # Extra sanity checks of internal structures, required by INVARIANTS -optionsWITNESS # Enable checks to detect deadlocks and cycles -optionsWITNESS_SKIPSPIN# Don't run witness on spinlocks for speed -optionsMALLOC_DEBUG_MAXZONES=8 # Separate malloc(9) zones - Arnaud > Attilio > > > -- > Peace can only be achieved by understanding - A. Einstein ___ freebsd-current@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to "freebsd-current-unsubscr...@freebsd.org"
Re: Scheduler + IPC performance on FreeBSD 7.4, 8.2, 9.0 and -CURRENT
Il 06 aprile 2012 18:54, Arnaud Lacombe ha scritto: > Hi, > > On Fri, Apr 6, 2012 at 10:58 AM, Attilio Rao wrote: >> Il 05 aprile 2012 19:03, Arnaud Lacombe ha scritto: >>> Hi folks, >>> >>> Over the past months, I ran on a couple of unused box the >>> `hackbench'[HACKBENCH] benchmark used by the Linux folks for tracking >>> down various kind of regression/improvement. `hackbench' is a >>> scheduler + IPC test (socket xor pipe). It creates producers/consumers >>> groups and let a variable quantity of small messages flow happily. >>> Producers and consumers are either processes xor threads. >>> >>> Tested platforms were >>> - Atom D510, Intel, (incomplete) >>> - Core 2 Quad Q9560, Intel >>> - Soekris net5501, AMD (incomplete) >>> - Xeon E5645, Intel (incomplete) >>> - Xeon E5620 (dual package), Intel >>> - Xeon E5-1650 (pending completion) >>> - Vortex86, DMP >>> >>> Tested kernel were: >>> - FreeBSD 7.4-RELEASE >>> - FreeBSD 8.2-RELEASE >>> - FreeBSD 9.0-RC3 and FreeBSD 9.0-RELEASE >>> - FreeBSD 10-CURRENT as of r231573 >> >> Which means you run 10-CURRENT with all the kernel debugging options >> on and MALLOC_DEBUG on? >> > I already answered that question. Namely: > > << > note: rule [I] is alleviated for -CURRENT kernels, which were built > with the same alteration made to GENERIC during the CURRENT->RELEASE > transition (ie. WITNESS and a couple of other option disabled). >>> > > this translates into the following patch (for amd64): Did you enable MALLOC_PRODUCTION and rebuilt libc? Attilio -- Peace can only be achieved by understanding - A. Einstein ___ freebsd-current@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to "freebsd-current-unsubscr...@freebsd.org"
Re: Scheduler + IPC performance on FreeBSD 7.4, 8.2, 9.0 and -CURRENT
Hi, On Fri, Apr 6, 2012 at 1:55 PM, Attilio Rao wrote: > Il 06 aprile 2012 18:54, Arnaud Lacombe ha scritto: >> Hi, >> >> On Fri, Apr 6, 2012 at 10:58 AM, Attilio Rao wrote: >>> Il 05 aprile 2012 19:03, Arnaud Lacombe ha scritto: Hi folks, Over the past months, I ran on a couple of unused box the `hackbench'[HACKBENCH] benchmark used by the Linux folks for tracking down various kind of regression/improvement. `hackbench' is a scheduler + IPC test (socket xor pipe). It creates producers/consumers groups and let a variable quantity of small messages flow happily. Producers and consumers are either processes xor threads. Tested platforms were - Atom D510, Intel, (incomplete) - Core 2 Quad Q9560, Intel - Soekris net5501, AMD (incomplete) - Xeon E5645, Intel (incomplete) - Xeon E5620 (dual package), Intel - Xeon E5-1650 (pending completion) - Vortex86, DMP Tested kernel were: - FreeBSD 7.4-RELEASE - FreeBSD 8.2-RELEASE - FreeBSD 9.0-RC3 and FreeBSD 9.0-RELEASE - FreeBSD 10-CURRENT as of r231573 >>> >>> Which means you run 10-CURRENT with all the kernel debugging options >>> on and MALLOC_DEBUG on? >>> >> I already answered that question. Namely: >> >> << >> note: rule [I] is alleviated for -CURRENT kernels, which were built >> with the same alteration made to GENERIC during the CURRENT->RELEASE >> transition (ie. WITNESS and a couple of other option disabled). >> >> this translates into the following patch (for amd64): > > Did you enable MALLOC_PRODUCTION and rebuilt libc? > Userland originates from FreeBSD 7.4-RELEASE and was not changed for any of the tests, which are exclusively focused on the kernel. Doing otherwise would mean changing too many variables. - Arnaud ___ freebsd-current@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to "freebsd-current-unsubscr...@freebsd.org"
Re: There is a known problem with MIPS tinderbox.
On Fri, 6 Apr 2012 13:08:12 +0530
"Jayachandran C." mentioned:
> On Fri, Apr 6, 2012 at 12:01 PM, Stanislav Sedov wrote:
> >
> > On Apr 5, 2012, at 11:08 PM, Jayachandran C. wrote:
> >>
> >>
> >> The asn1 library has a export map containing 'global: *', this exports
> >> two symbols _fdata and _ftext versioned. When libkafs5 is linked,
> >> these symbols confuse the bfd code and the entries corresponding to
> >> theses (index 13, and 16) are left un-initialized.
> >>
> >> One workaround I see is to change the export 'global: *' in
> >> kerberos5/lib/libasn1 to the actual list of exported symbols.
> >>
> >
> > Thanks. What I'm also trying right now is to add a version map to the
> > libkafs -- this might help binutils to link it properly as well. If it
> > fails, we can try adding a proper one for libasn1.
>
> The libasn1 workaround is here:
> http://people.freebsd.org/~jchandra/libasn1.diff
>
Thanks!
My idea of adding a version map to libkafs worked as well.
Can you, please, test if it fixes the issue for you?
It seems to be a less complicated way to solve it.
Index: kerberos5/lib/libkafs5/version.map
===
--- kerberos5/lib/libkafs5/version.map (revision 0)
+++ kerberos5/lib/libkafs5/version.map (revision 0)
@@ -0,0 +1,19 @@
+HEIMDAL_KAFS5_1.0 {
+ global:
+ k_afs_cell_of_file;
+ k_hasafs;
+ k_hasafs_recheck;
+ k_pioctl;
+ k_setpag;
+ k_unlog;
+ kafs_set_verbose;
+ kafs_settoken5;
+ kafs_settoken_rxkad;
+ krb5_afslog;
+ krb5_afslog_home;
+ krb5_afslog_uid;
+ krb5_afslog_uid_home;
+ krb5_realm_of_cell;
+ local:
+ *;
+};
Index: kerberos5/lib/libkafs5/Makefile
===
--- kerberos5/lib/libkafs5/Makefile (revision 233932)
+++ kerberos5/lib/libkafs5/Makefile (working copy)
@@ -1,20 +1,13 @@
# $FreeBSD$
LIB= kafs5
-LDADD= -lasn1 -lroken
+LDADD= -lasn1 -lroken -lkrb5
+LDFLAGS= -Wl,--no-undefined
DPADD= ${LIBASN1} ${LIBKRB5} ${LIBROKEN}
INCS= kafs.h
MAN= kafs5.3
+VERSION_MAP= ${.CURDIR}/version.map
-#
-# Linking with libkrb5 uncovers a bug in binutils.
-# See
http://repo.or.cz/w/binutils.git/commit/ee05170bf71819c99cb5a36a44735c231ae03c56
.
-#
-.if ${MACHINE} != "mips"
-LDADD+=-lkrb5
-LDFLAGS= -Wl,--no-undefined
-.endif
-
MLINKS=kafs5.3 k_afs_cell_of_file.3 \
kafs5.3 k_hasafs.3 \
kafs5.3 k_pioctl.3 \
--
Stanislav Sedov
ST4096-RIPE
() ascii ribbon campaign - against html e-mail
/\ www.asciiribbon.org - against proprietary attachments
___
freebsd-current@freebsd.org mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-current
To unsubscribe, send any mail to "freebsd-current-unsubscr...@freebsd.org"
[head tinderbox] failure on mips/mips
TB --- 2012-04-07 00:12:41 - tinderbox 2.9 running on freebsd-current.sentex.ca TB --- 2012-04-07 00:12:41 - FreeBSD freebsd-current.sentex.ca 8.3-PRERELEASE FreeBSD 8.3-PRERELEASE #0: Mon Mar 26 13:54:12 EDT 2012 d...@freebsd-current.sentex.ca:/usr/obj/usr/src/sys/GENERIC amd64 TB --- 2012-04-07 00:12:41 - starting HEAD tinderbox run for mips/mips TB --- 2012-04-07 00:12:41 - cleaning the object tree TB --- 2012-04-07 00:13:23 - cvsupping the source tree TB --- 2012-04-07 00:13:23 - /usr/bin/csup -z -r 3 -g -L 1 -h cvsup.sentex.ca /tinderbox/HEAD/mips/mips/supfile TB --- 2012-04-07 00:14:00 - building world TB --- 2012-04-07 00:14:00 - CROSS_BUILD_TESTING=YES TB --- 2012-04-07 00:14:00 - MAKEOBJDIRPREFIX=/obj TB --- 2012-04-07 00:14:00 - PATH=/usr/bin:/usr/sbin:/bin:/sbin TB --- 2012-04-07 00:14:00 - SRCCONF=/dev/null TB --- 2012-04-07 00:14:00 - TARGET=mips TB --- 2012-04-07 00:14:00 - TARGET_ARCH=mips TB --- 2012-04-07 00:14:00 - TZ=UTC TB --- 2012-04-07 00:14:00 - __MAKE_CONF=/dev/null TB --- 2012-04-07 00:14:00 - cd /src TB --- 2012-04-07 00:14:00 - /usr/bin/make -B buildworld >>> World build started on Sat Apr 7 00:14:01 UTC 2012 >>> Rebuilding the temporary build tree >>> stage 1.1: legacy release compatibility shims >>> stage 1.2: bootstrap tools >>> stage 2.1: cleaning up the object tree >>> stage 2.2: rebuilding the object tree >>> stage 2.3: build tools >>> stage 3: cross tools >>> stage 4.1: building includes >>> stage 4.2: building libraries >>> stage 4.3: make dependencies >>> stage 4.4: building everything [...] cc -O -pipe -G0 -I/src/kerberos5/libexec/kfd/../../../crypto/heimdal/lib/asn1 -I/src/kerberos5/libexec/kfd/../../../crypto/heimdal/lib/roken -DHAVE_CONFIG_H -I/src/kerberos5/libexec/kfd/../../include -std=gnu99 -c /src/kerberos5/libexec/kfd/../../../crypto/heimdal/appl/kf/kfd.c cc -O -pipe -G0 -I/src/kerberos5/libexec/kfd/../../../crypto/heimdal/lib/asn1 -I/src/kerberos5/libexec/kfd/../../../crypto/heimdal/lib/roken -DHAVE_CONFIG_H -I/src/kerberos5/libexec/kfd/../../include -std=gnu99 -o kfd kfd.o -lkrb5 -lroken -lasn1 -lcrypto -lcrypt /obj/mips.mips/src/kerberos5/libexec/kfd/../../lib/libvers/libvers.a gzip -cn /src/kerberos5/libexec/kfd/../../../crypto/heimdal/appl/kf/kfd.8 > kfd.8.gz ===> kerberos5/libexec/kimpersonate (all) cc -O -pipe -G0 -I/src/kerberos5/libexec/kimpersonate/../../../crypto/heimdal/lib/hx509 -I/src/kerberos5/libexec/kimpersonate/../../../crypto/heimdal/lib/asn1 -I/src/kerberos5/libexec/kimpersonate/../../../crypto/heimdal/lib/roken -I/src/kerberos5/libexec/kimpersonate/../../../crypto/heimdal/lib/sl -I. -DHAVE_CONFIG_H -I/src/kerberos5/libexec/kimpersonate/../../include -std=gnu99 -c /src/kerberos5/libexec/kimpersonate/../../../crypto/heimdal/kuser/kimpersonate.c cc -O -pipe -G0 -I/src/kerberos5/libexec/kimpersonate/../../../crypto/heimdal/lib/hx509 -I/src/kerberos5/libexec/kimpersonate/../../../crypto/heimdal/lib/asn1 -I/src/kerberos5/libexec/kimpersonate/../../../crypto/heimdal/lib/roken -I/src/kerberos5/libexec/kimpersonate/../../../crypto/heimdal/lib/sl -I. -DHAVE_CONFIG_H -I/src/kerberos5/libexec/kimpersonate/../../include -std=gnu99 -o kimpersonate kimpersonate.o -lkafs5 -lkrb5 -lheimntlm -lroken -lasn1 -lcrypto -lcrypt /obj/mips.mips/src/kerberos5/libexec/kimpersonate/../../lib/libvers/libvers.a /obj/mips.mips/src/tmp/usr/bin/ld: /obj/mips.mips/src/tmp/usr/lib/libkafs5.so symbol number 13 references nonexistent SHT_SYMTAB_SHNDX section /obj/mips.mips/src/tmp/usr/lib/libkafs5.so: could not read symbols: File format not recognized *** Error code 1 Stop in /src/kerberos5/libexec/kimpersonate. *** Error code 1 Stop in /src/kerberos5/libexec. *** Error code 1 Stop in /src/kerberos5. *** Error code 1 Stop in /src. *** Error code 1 Stop in /src. *** Error code 1 Stop in /src. TB --- 2012-04-07 01:03:21 - WARNING: /usr/bin/make returned exit code 1 TB --- 2012-04-07 01:03:21 - ERROR: failed to build world TB --- 2012-04-07 01:03:21 - 2075.28 user 442.60 system 3039.98 real http://tinderbox.freebsd.org/tinderbox-head-HEAD-mips-mips.full ___ freebsd-current@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to "freebsd-current-unsubscr...@freebsd.org"
(unionfs) panic: excl->share with r230341 and above
Starting with r230341, I get the following panic when trying to run an executable on a unionfs filesystem: exclusive lock of (lockmgr) ufs @ /usr/src/sys/modules/unionfs/../../fs/unionfs/union_vnops.c:1843 while share locked from /usr/src/sys/modules/unionfs/../../fs/unionfs/union_vnops.c:1843 panic: excl->share cpuid = 0 KDB: enter: panic Narrowing down with a binary search: r230340 (no panic), r230341 (panic). How to repeat: # uuname -a FreeBSD 10.0-CURRENT FreeBSD 10.0-CURRENT #5 r233946M: Fri Apr 6 21:09:32 EDT 2012 kwhite@demo:/usr/src/obj/usr/src/sys/GENERIC i386 # mkdir /tmp/local # mount -t unionfs -o noatime /tmp/local /usr/local # cp /bin/ls /usr/local/bin/ls # /usr/local/bin/ls exclusive lock of (lockmgr) ufs @ /usr/src/sys/modules/unionfs/../../fs/unionfs/union_vnops.c:1843 while share locked from /usr/src/sys/modules/unionfs/../../fs/unionfs/union_vnops.c:1843 panic: excl->share cpuid = 0 KDB: enter: panic [ thread pid 68 tid 100054 ] Stopped at kdb_enter+0x3b: movl$0,kdb_why db> show all locks Process 68 (ls) thread 0xc578 (100054) exclusive sleep mutex vnode interlock (vnode interlock) r = 0 (0xc57cec28) locked @ /usr/src/sys/modules/unionfs/../../fs/unionfs/union_vnops.c:1835 shared lockmgr ufs (ufs) r = 0 (0xc57cec08) locked @ /usr/src/sys/modules/unionfs/../../fs/unionfs/union_vnops.c:1843 db> Workaround? After reverting the change from LK_EXCLUSIVE to LK_SHARED in sys/kern/kern_exec.c, executables on union filesystems no longer cause a panic. ...keith ___ freebsd-current@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to "freebsd-current-unsubscr...@freebsd.org"
Re: ECC memory driver in FreeBSD 10?
On Apr 6, 2012, at 2:48 PM, O. Hartmann wrote: > I'm looking for a way to force FreeBSD 10 to maintain/watch ECC errors > reported by UEFI (or BIOS). > Since ECC is said to be essential for server systems both in buisness > and science and I do not question this, I was wondering if I can not > report ECC errors via a watchdog or UEFI (ACPI?) report to syslog > facility on FreeBSD. > FreeBSD is supposed to be a server operating system, as far as I know, > so I believe there must be something which didn't have revealed itself > to me, yet. > > Thanks in advance, > Oliver > If the hardware supports it, such errors should be logged as MCEs (Machine Check Exceptions). I can say for sure it works pretty well with Dell servers, as I had one with failing RAM module, and it reported the corrected ECC errors in dmesg. ___ freebsd-current@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to "freebsd-current-unsubscr...@freebsd.org"
Re: There is a known problem with MIPS tinderbox.
2012/4/7 Stanislav Sedov : > On Fri, 6 Apr 2012 13:08:12 +0530 > "Jayachandran C." mentioned: > >> On Fri, Apr 6, 2012 at 12:01 PM, Stanislav Sedov wrote: >> > >> > On Apr 5, 2012, at 11:08 PM, Jayachandran C. wrote: >> >> >> >> >> >> The asn1 library has a export map containing 'global: *', this exports >> >> two symbols _fdata and _ftext versioned. When libkafs5 is linked, >> >> these symbols confuse the bfd code and the entries corresponding to >> >> theses (index 13, and 16) are left un-initialized. >> >> >> >> One workaround I see is to change the export 'global: *' in >> >> kerberos5/lib/libasn1 to the actual list of exported symbols. >> >> >> > >> > Thanks. What I'm also trying right now is to add a version map to the >> > libkafs -- this might help binutils to link it properly as well. If it >> > fails, we can try adding a proper one for libasn1. >> >> The libasn1 workaround is here: >> http://people.freebsd.org/~jchandra/libasn1.diff >> > > Thanks! > > My idea of adding a version map to libkafs worked as well. > Can you, please, test if it fixes the issue for you? > It seems to be a less complicated way to solve it. I would still suggest the asn1 change if we are doing a temporary fix, because: - It does not add any new symbol versioning, it just converts the 'global: *' to an explicit list of symbols. - there are other libraries lined to asn1 which may have the same issue as libkafs5 (I haven't really looked at this. The only downside I see is that libasn1 has a lot of symbols. JC. ___ freebsd-current@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to "freebsd-current-unsubscr...@freebsd.org"
