summaryrefslogtreecommitdiffstats
path: root/meta-oe/recipes-benchmark
Commit message (Collapse)AuthorAgeFilesLines
* fio: fix build with muslMax Krummenacher2026-06-072-0/+34
| | | | | | | Backport the upstream fix. Signed-off-by: Max Krummenacher <max.oss.09@gmail.com> Signed-off-by: Khem Raj <khem.raj@oss.qualcomm.com>
* fio: upgrade 3.41 -> 3.42Gyorgy Sarvari2026-04-203-80/+2
| | | | | | | | | | | | | | | | Contains fix for CVE-2026-30656. Also mark this CVE as patched explicitly, as NVD tracks it without version info. Drop patches that are included in this release. Changelog: https://github.com/axboe/fio/releases/tag/fio-3.42 Signed-off-by: Gyorgy Sarvari <skandigraun@gmail.com> fio Signed-off-by: Khem Raj <khem.raj@oss.qualcomm.com>
* meta-oe/recipes: disable C23 support to fix configure checkKhem Raj2026-04-161-1/+1
| | | | | | | | Set ac_cv_prog_cc_c23=no to prevent autoconf from detecting C23 compiler support, avoiding potential build failures as the package is not yet fully ported to support C23 standard. Signed-off-by: Khem Raj <khem.raj@oss.qualcomm.com>
* iperf3: upgrade 3.20 -> 3.21Liu Yiding2026-04-151-3/+3
| | | | | | | | | | 1.ChangeLog: https://github.com/esnet/iperf/releases/tag/3.21 2.LIC_FILES_CHKSUM Changed as Copyright Year change from 2025 to 2026. Signed-off-by: Liu Yiding <liuyd.fnst@fujitsu.com> Signed-off-by: Khem Raj <khem.raj@oss.qualcomm.com>
* libhugetlbfs: add RISC-V to COMPATIBLE_HOSTSJoao Marcos Costa2026-04-151-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | A preliminar effort to support RISC-V was added in v2.23: a529598 Introduce basic riscv64 support [1] Following the guidelines in libhugetlbfs's HOWTO, here are the outputs of some commands in qemuriscv64: root@qemuriscv64:~# grep -i huge /proc/filesystems nodev hugetlbfs root@qemuriscv64:~# hugeadm --pool-list Size Minimum Current Maximum Default 65536 0 0 0 2097152 0 0 0 * root@qemuriscv64:~# hugeadm --pool-pages-min 2MB:10 --add-temp-swap root@qemuriscv64:~# hugeadm --pool-list Size Minimum Current Maximum Default 65536 0 0 0 2097152 10 10 10 * root@qemuriscv64:~# hugeadm --pool-pages-min 2MB:-5 root@qemuriscv64:~# hugeadm --pool-list Size Minimum Current Maximum Default 65536 0 0 0 2097152 5 5 10 * Regarding toolchains, libhugetlbfs for RISC-V builds fine with both clang and gcc. [1]: https://github.com/libhugetlbfs/libhugetlbfs/commit/a529598dd256c79799d5e43e6d79146ca15f1c16 Signed-off-by: João Marcos Costa <joaomarcos.costa@bootlin.com> Signed-off-by: Khem Raj <khem.raj@oss.qualcomm.com>
* CoreMark: Add CoreMark to benchmark CPU performanceAshwin Prabhakar2026-04-141-0/+23
| | | | | | | | | | | | | | | | | | | | | | Add support for CoreMark benchmark in recipes-benchmark. This package can be used to benchmark CPU performance in SOC's Application processor core. Signed-off-by: Ashwin Prabhakar <ashwin.prabhakar@qti.qualcomm.com> coremark: append LDFLAGS to TARGET_CC_ARCH to fix QA issue Signed-off-by: Ashwin Prabhakar <ashwin.prabhakar@qti.qualcomm.com> coremark: update to Apache-2.0 and LicenseRef-EEMBC-AUA Update the project license to Apache-2.0 combined with the EEMBC Acceptable Usage Agreement (AUA) as requested by the maintainer. This ensures compliance with EEMBC's updated licensing requirements for CoreMark. Signed-off-by: Ashwin Prabhakar <ashwin.prabhakar@qti.qualcomm.com> Signed-off-by: Khem Raj <khem.raj@oss.qualcomm.com>
* fio: fix musl buildsMax Krummenacher2026-03-172-1/+42
| | | | | | | | | | | | fio 3.40 added the commit 4175f4dbec5d ("oslib: blkzoned: add blkzoned_move_zone_wp() helper function") which uses FALLOC_FL_ZERO_RANGE which in a musl build is undefined without including its header. Backport the upstream fix. Signed-off-by: Max Krummenacher <max.oss.09@gmail.com> Signed-off-by: Khem Raj <raj.khem@gmail.com>
* iperf2: Update CVE_PRODUCTColin McAllister2026-02-241-1/+1
| | | | | | | | | CPEs are registered for iperf_project2:iperf2 in addition to iperf_project:iperf. By changing CVE_PRODUCT to an appends, this ensures that both iperf and iperf2 CPEs are used for CVE matching. Signed-off-by: Colin Pinnell McAllister <colin.mcallister@garmin.com> Signed-off-by: Khem Raj <raj.khem@gmail.com>
* nbench-byte: Fix sysinfo generation in parallel buildDaniel Klauer2026-02-103-1/+99
| | | | | | | | | | | | | | | | The project Makefile uses a script (sysinfo.sh) to non-atomically generate two .c files (sysinfo.c, sysinfoc.c) which are then included in the build. Since the script always overwrites both .c files, the Makefile should only invoke it once, not twice in parallel. Otherwise the .c files may be corrupted and cause random build failures in parallel builds. Requires at least GNU make 4.3, for Grouped Targets support [1]. [1] https://lists.gnu.org/archive/html/info-gnu/2020-01/msg00004.html Reviewed-by: Silvio Fricke <silvio.fricke@gin.de> Signed-off-by: Daniel Klauer <daniel.klauer@gin.de> Signed-off-by: Khem Raj <raj.khem@gmail.com>
* iozone3: upgrade 507 -> 508Gyorgy Sarvari2026-01-301-1/+1
| | | | | | | | Changelog: - Put an end to the (&*% stupid GCC breaking builds for no valid reason. Signed-off-by: Gyorgy Sarvari <skandigraun@gmail.com> Signed-off-by: Khem Raj <raj.khem@gmail.com>
* fio: upgrade 3.39 -> 3.41Gyorgy Sarvari2026-01-301-2/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Changelog: 3.41: - engines/io_uring: remove unnecessary SQ full check - io_uring: ensure accurate real_file_size setup for full device access with PI enabled - Fix: parse.c opt_len() to use minimal distance to delimiter to determine option length - io_u: fix offset calculation in randtrimwrite - engines/http: fix file name - engines/http: Add S3 security token support - io_u: get io_u from io_u_freelist when TD_FSYNCING - io_uring CQ reap cleanup - Add 'filetype' option - handle out-of-order write completions in verify state (Issue #1950) - engines/http: Add support for range reads - Makefile: fix man and share install paths on MacOS - Sprandom - Fix mandoc warnings - fio: fix formats under MIPS64/PPC - sprandom: Fix several issues found in the sprandom implementation - t/verify-state.c fixes/improvements 3.40: - t/read-to-pipe-async: fix -DNDEBUG support - docs: update docs for verify_mode=compare of io_uring_cmd - dfs: fix fail to load dfs engine - Fix spelling error in IO uring engine. - Fix hang on Windows when multiple --client args are present - Add important info about http_host and file formatting to s3 example - oslib: blkzoned: add missing blkzoned_move_zone_wp() stub Signed-off-by: Gyorgy Sarvari <skandigraun@gmail.com> Signed-off-by: Khem Raj <raj.khem@gmail.com>
* fio: ignore CVE-2025-10824Gyorgy Sarvari2025-12-161-0/+2
| | | | | | | | | | | | Details: https://nvd.nist.gov/vuln/detail/CVE-2025-10824 The upstream maintainer wasn't able to reproduce the issue[1], and the related bug is closed without further action. [1]: https://github.com/axboe/fio/issues/1981 Signed-off-by: Gyorgy Sarvari <skandigraun@gmail.com> Signed-off-by: Khem Raj <raj.khem@gmail.com>
* iperf3: Upgrade 3.18 -> 3.20Randy MacLeod2025-11-184-175/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Change summary from: https://software.es.net/iperf/news.html#iperf-3-19-released and RELNOTES links: iperf-3.20 fixes a number of bugs and also adds some minor enhancements. https://github.com/esnet/iperf/blob/master/RELNOTES.md#iperf-320-2025-11-14 iperf-3.19.1 is a security fix release to address three issues reported by Han Lee of Apple Information Security. https://github.com/esnet/iperf/blob/master/RELNOTES.md#iperf-3191-2025-07-25 iperf-3.19 includes support for MP-TCPv1 under Linux, keepalives on the control connection, support for the MSG_TRUNC receive option, and a number of minor bug fixes. https://github.com/esnet/iperf/blob/master/RELNOTES.md#iperf-319-2025-05-16 Drop 2 CVE patches that were backports. Drop 0001-configure.ac-check-for-CPP-prog.patch which is merged in: https://github.com/esnet/iperf/commit/beadb59b90e8 License-Update: The only changes were: ❯ git log --oneline 3.18..3.20 LICENSE 9f6dc21 Copyright updates for 2025. edf5c75 Fix typo in LICENSE Signed-off-by: Randy MacLeod <Randy.MacLeod@windriver.com> Signed-off-by: Khem Raj <raj.khem@gmail.com>
* libhugetlbfs: support reproducible buildsHongxu Jia2025-11-142-0/+52
| | | | | | | | | When compressing docs, do not save the original file name and timestamp by default (gzip -n). Make archives be reproducible at each build Signed-off-by: Hongxu Jia <hongxu.jia@windriver.com> Signed-off-by: Khem Raj <raj.khem@gmail.com>
* bonnie++: add UPSTREAM_CHECK_URIYi Zhao2025-11-121-0/+3
| | | | | | | | | | | | | | | | | | Add UPSTREAM_CHECK_URI and UPSTREAM_CHECK_REGEX to check the correct latest stable verison. Before the patch: $ devtool latest-version bonnie++ INFO: Current version: 2.00a INFO: Latest version: 1.04 After the patch: $ devtool latest-version bonnie++ INFO: Current version: 2.00a INFO: Latest version: 2.00a Signed-off-by: Yi Zhao <yi.zhao@windriver.com> Signed-off-by: Khem Raj <raj.khem@gmail.com>
* iperf3: add missing "libgcc" RDEPENDSMichael Opdenacker2025-10-241-0/+1
| | | | | | | | | | | | | | | | | | | | | | | | This fixes an issue observed with iperf3 added to core-image-minimal. The executable starts fine but at the end of a test, issues this error: iperf3 -c 172.24.0.1 Connecting to host 172.24.0.1, port 5201 [ 5] local 172.24.0.2 port 55444 connected to 172.24.0.1 port 5201 [ ID] Interval Transfer Bitrate Retr Cwnd [ 5] 0.00-1.00 sec 113 MBytes 945 Mbits/sec 0 396 KBytes [ 5] 1.00-2.00 sec 112 MBytes 941 Mbits/sec 0 396 KBytes [ 5] 2.00-3.00 sec 113 MBytes 946 Mbits/sec 0 417 KBytes [ 5] 3.00-4.00 sec 112 MBytes 937 Mbits/sec 1 417 KBytes [ 5] 4.00-5.00 sec 113 MBytes 946 Mbits/sec 0 424 KBytes [ 5] 5.00-6.00 sec 112 MBytes 938 Mbits/sec 0 424 KBytes [ 5] 6.00-7.00 sec 112 MBytes 943 Mbits/sec 0 428 KBytes [ 5] 7.00-8.00 sec 112 MBytes 942 Mbits/sec 0 445 KBytes [ 5] 8.00-9.00 sec 112 MBytes 944 Mbits/sec 0 457 KBytes libgcc_s.so.1 must be installed for pthread_cancel to work Aborted Signed-off-by: Michael Opdenacker <michael.opdenacker@rootcommit.com> Signed-off-by: Khem Raj <raj.khem@gmail.com>
* fio: fix CVE-2025-10823Saravanan2025-10-152-0/+39
| | | | | | | | | | | | Reference: https://nvd.nist.gov/vuln/detail/CVE-2025-10823 https://github.com/axboe/fio/issues/1982 Upstream-patch: https://github.com/axboe/fio/commit/6a39dfaffdb8a6c2080eec0dc7fb1ee532d54025 Signed-off-by: Saravanan <saravanan.kadambathursubramaniyam@windriver.com> Signed-off-by: Khem Raj <raj.khem@gmail.com>
* iperf2: ignore irrelevant CVEsGyorgy Sarvari2025-10-061-0/+3
| | | | | | | | | These CVEs are for iperf3 - which is a similar application in its goals (and name), but an independent project from this, and the projects are independent implementations also, they share no common code. Signed-off-by: Gyorgy Sarvari <skandigraun@gmail.com> Signed-off-by: Khem Raj <raj.khem@gmail.com>
* iperf3: Fix CVE-2025-54350Nitin Wankhade2025-09-232-0/+25
| | | | | | | | | | remove assert to prevent crash due to assertion failure on malformed authentication attempt Reference: https://github.com/esnet/iperf/commit/4eab661da0bbaac04493fa40164e928c6df7934a Signed-off-by: Nitin Wankhade <nitin.wankhade333@gmail.com> Signed-off-by: Khem Raj <raj.khem@gmail.com>
* iperf3: Fix CVE-2025-54349Nitin Wankhade2025-09-232-1/+82
| | | | | | | | | This commit fix heap overflow for iperf3 package Reference: https://github.com/esnet/iperf/commit/4e5313bab0b9b3fe03513ab54f722c8a3e4b7bdf Signed-off-by: Nitin Wankhade <nitin.wankhade333@gmail.com> Signed-off-by: Khem Raj <raj.khem@gmail.com>
* libc-bench: Always use libgcc runtime with clang on x86Khem Raj2025-07-201-1/+2
| | | | Signed-off-by: Khem Raj <raj.khem@gmail.com>
* libhugetlbfs: Always use ligcc for compiler runtime with clang on x86Khem Raj2025-07-201-0/+3
| | | | | | | | glibc objects here expect libgcc to be linked in sadly compiler-rt does not provide all the needed function implementations e.g. __unordtf2 __letf2, __multf3, __addtf3 needed for 128 bit data types Signed-off-by: Khem Raj <raj.khem@gmail.com>
* libhugetlbfs: Do not add LDFLAGS to compilerKhem Raj2025-07-202-2/+34
| | | | | | | | | | | Add LDFLAGS in makefile for linking the helper libraries instead when linking with LLD it ends up with errors i686-yoe-linux-clang: warning: -Wl,-O1: 'linker' input unused [-Wunused-command-line-argument] i686-yoe-linux-clang: warning: -Wl,--hash-style=gnu: 'linker' input unused [-Wunused-command-line-argument] i686-yoe-linux-clang: warning: -Wl,--as-needed: 'linker' input unused [-Wunused-command-line-argument] Signed-off-by: Khem Raj <raj.khem@gmail.com>
* meta-openembedded/all: adapt to UNPACKDIR changesAlexander Kanavin2025-06-2517-19/+5
| | | | | | | | | | | | | Please see https://git.yoctoproject.org/poky/commit/?id=4dd321f8b83afecd962393101b2a6861275b5265 for what changes are needed, and sed commands that can be used to make them en masse. I've verified that bitbake -c patch world works with these, but did not run a world build; the majority of recipes shouldn't need further fixups, but if there are some that still fall out, they can be fixed in followups. Signed-off-by: Alexander Kanavin <alex@linutronix.de> Signed-off-by: Khem Raj <raj.khem@gmail.com>
* libhugetlbfs: remove obsolete python/perl dependenciesRoss Burton2025-06-121-2/+2
| | | | | | | There is no perl used in the build, and no python installed in ${PN}. Signed-off-by: Ross Burton <ross.burton@arm.com> Signed-off-by: Khem Raj <raj.khem@gmail.com>
* libhugetlbfs: remove sysfsutils DEPENDSRoss Burton2025-06-121-1/+0
| | | | | | | This doesn't appear to have ever been needed as a build dependency. Signed-off-by: Ross Burton <ross.burton@arm.com> Signed-off-by: Khem Raj <raj.khem@gmail.com>
* iperf3: enable native buildsDenis Mukhin2025-05-131-0/+2
| | | | | | | Enable native variants of iperf3 tool for SDK builds. Signed-off-by: Denis Mukhin <dmukhin@ford.com> Signed-off-by: Khem Raj <raj.khem@gmail.com>
* dhrystone: fix build error with gcc-15mark.yang2025-04-102-24/+33
| | | | | | | | | | | | | | * fix too many arguments error dhry_1.c: In function 'main': dhry_1.c:176:23: error: too many arguments to function 'Func_1'; expected 0, have 2 176 | if (Enum_Loc == Func_1 (Ch_Index, 'C')) | ^~~~~~ ~~~~~~~~ dhry_1.c:33:17: note: declared here 33 | Enumeration Func_1 (); | ^~~~~~ Signed-off-by: mark.yang <mark.yang@lge.com> Signed-off-by: Khem Raj <raj.khem@gmail.com>
* lmbench: fix build error with gcc-15mark.yang2025-04-102-0/+253
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | * see more details http://errors.yoctoproject.org/Errors/Details/851798/ lat_rpc.c:172:1: error: conflicting types for 'client_rpc_xact_1'; have 'char *(char *, CLIENT *)' {aka 'char *(char *, struct __rpc_client *)'} 172 | client_rpc_xact_1(char *argp, CLIENT *clnt) | ^~~~~~~~~~~~~~~~~ bench.h:349:14: note: previous declaration of 'client_rpc_xact_1' with type 'char *(void)' 349 | extern char *client_rpc_xact_1(); | ^~~~~~~~~~~~~~~~~ lat_rpc.c: In function 'rpc_xact_1': lat_rpc.c:189:1: warning: old-style function definition [-Wold-style-definition] 189 | rpc_xact_1(msg, transp) | ^~~~~~~~~~ lat_rpc.c:192:1: error: number of arguments doesn't match prototype 192 | { | ^ bench.h:348:14: error: prototype declaration 348 | extern char *rpc_xact_1(); | ^~~~~~~~~~ Fix errors due to old-style function declarations The code was using old-style function declarations without proper prototypes, which causes compilation errors with newer GCC versions. This patch updates the function declarations to use modern C syntax with proper parameter types. Signed-off-by: mark.yang <mark.yang@lge.com> Signed-off-by: Khem Raj <raj.khem@gmail.com>
* memtester: Upgrade 4.6.0 -> 4.7.1mark.yang2025-04-101-1/+1
| | | | | | | | | | | | | | | | | | | | | | | Upgrade to release 4.7.1: - Change log: https://pyropus.ca./software/memtester/CHANGELOG Version 4.7.1 16 December 2024 -fix compile error with stricter C23/gcc-15 due to incompatible type declaration. Thanks: Rudi Heitbaum. Version 4.7.0 28 November 2024 -fix alignment issue causing crash when specifying a memory amount to test that is more than the minimum 1 page of memory, but less than 2 full pages. Thanks: Erwan Szymanski. Also reported by Chenghan Lee and K R Pallavi. -add `-u` option to allow uncached memory semantics on some systems when using the -p option. Thanks: Florian Fainelli. -fix manpage highlighting of args. Thanks: László Böszörményi. -add missing option documentation to man page. Signed-off-by: mark.yang <mark.yang@lge.com> Signed-off-by: Khem Raj <raj.khem@gmail.com>
* nbench-byte: fix build error with gcc-15mark.yang2025-04-102-1/+36
| | | | | | | | | | | | | | * Fix the following build error with gcc-15: nbench1.c:3520:13: error: conflicting types for 'adjust_mid_wts'; have 'void(int)' 3520 | static void adjust_mid_wts(int patt) | ^~~~~~~~~~~~~~ In file included from nbench1.c:64: nbench1.h:373:13: note: previous declaration of 'adjust_mid_wts' with type 'void(void)' 373 | static void adjust_mid_wts(); | ^~~~~~~~~~~~~~ Signed-off-by: mark.yang <mark.yang@lge.com> Signed-off-by: Khem Raj <raj.khem@gmail.com>
* linpack: fix build with gcc-15.0.1mark.yang2025-04-012-0/+53
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | * fix following error: linpacknew.c: In function 'dgefa': linpacknew.c:257:9: error: conflicting types for 'idamax'; have 'int(void)' 257 | int idamax(),j,k,kp1,l,nm1; | ^~~~~~ linpacknew.c:63:13: note: previous declaration of 'idamax' with type 'int(int, REAL *, int)' {aka 'int(int, double *, int)'} 63 | static int idamax (int n,REAL *dx,int incx); | ^~~~~~ linpacknew.c:272:21: error: too many arguments to function 'idamax'; expected 0, have 3 272 | l = idamax(n-k,&a[lda*k+k],1) + k; | ^~~~~~ ~~~ linpacknew.c:257:9: note: declared here 257 | int idamax(),j,k,kp1,l,nm1; | ^~~~~~ linpacknew.c:326:21: error: too many arguments to function 'idamax'; expected 0, have 3 326 | l = idamax(n-k,&a[lda*k+k],1) + k; | ^~~~~~ ~~~ linpacknew.c:257:9: note: declared here 257 | int idamax(),j,k,kp1,l,nm1; | ^~~~~~ The function was already declared as static int idamax(int n, REAL *dx, int incx); on line 63, but it was redeclared as int idamax() inside the dgefa function on line 257, causing a conflict. where functions are redeclared without parameters, causing conflicts with the original function definitions. Signed-off-by: mark.yang <mark.yang@lge.com> Signed-off-by: Khem Raj <raj.khem@gmail.com>
* iperf2: Add _GNU_SOURCE in checksums.cKhem Raj2025-03-282-0/+27
| | | | | | | | | | | | | | | | | | | | | | | glibc defines struct udphdr as a union where members have aliased names uh_sport -> source uh_dport -> uh_dport uh_dport -> len check -> check But musl only defines the aliases if _GNU_SOURCE is defined, ideally iperf2 should be using uh_* names of the members so it is portable across musl and glibc but thats for upstream to consider. Fixes | ../../iperf-2.2.1/src/checksums.c:175:19: error: no member named 'check' in 'struct udphdr' | 175 | if (!udp_hdr->check) { | | ~~~~~~~ ^ | 1 error generated. | make[2]: *** [Makefile:539: checksums.o] Error 1 Signed-off-by: Khem Raj <raj.khem@gmail.com> Cc: Randy MacLeod <Randy.MacLeod@windriver.com>
* iperf2: upgrade 2.0.13 -> 2.2.1Randy MacLeod2025-03-282-62/+1
| | | | | | | | | | | Release notes: https://sourceforge.net/p/iperf2/code/ci/2-2-1/tree/NEWS.md Drop the stdbool patch. It seems to have been fixed upstream by: ae0284e4 2020-10-22 Replace DAST_CHECK_BOOL with AC_HEADER_STDBOOL Signed-off-by: Randy MacLeod <Randy.MacLeod@windriver.com> Signed-off-by: Khem Raj <raj.khem@gmail.com>
* iperf3: upgrade 3.17.1 -> 3.18Martin Siegumfeldt2025-03-252-32/+1
| | | | | | | drop backported patch Signed-off-by: Martin Siegumfeldt <mns@gomspace.com> Signed-off-by: Khem Raj <raj.khem@gmail.com>
* iperf3: fix build with gcc-15Martin Jansa2025-03-212-0/+67
| | | | | | | | * fixes: http://errors.yoctoproject.org/Errors/Details/848456/ Signed-off-by: Martin Jansa <martin.jansa@gmail.com> Signed-off-by: Khem Raj <raj.khem@gmail.com>
* recipes: Fix variable assignment whitespaceRichard Purdie2025-03-202-2/+2
| | | | | Signed-off-by: Richard Purdie <richard.purdie@linuxfoundation.org> Signed-off-by: Khem Raj <raj.khem@gmail.com>
* fio: pass pkgconf args to configure scriptGyorgy Sarvari2025-03-131-1/+1
| | | | | | | | | | | | | This application uses a custom configure script, which is called explicitly from a do_configure task. This however means that the recipe needs to take care of passing the dynamic arguments based on the PACKAGECONFIG values. Pass the value of PACKAGECONFIG_CONFARGS to the configure script to ensure that the PACKAGECONFIG changes take effect. Signed-off-by: Gyorgy Sarvari <skandigraun@gmail.com> Signed-off-by: Khem Raj <raj.khem@gmail.com>
* iozone3: upgrade 506 -> 507Wang Mingyu2025-03-112-37/+2
| | | | | | | | | | | 0001-let-system-headers-provide-pread64.patch removed since it's not available in 507 License-Update: file location of Copyright changed. Signed-off-by: Wang Mingyu <wangmy@fujitsu.com> Signed-off-by: Khem Raj <raj.khem@gmail.com>
* fio: upgrade 3.38 -> 3.39Yi Zhao2025-03-101-1/+1
| | | | | | | | ChangeLog: https://github.com/axboe/fio/releases/tag/fio-3.39 Signed-off-by: Yi Zhao <yi.zhao@windriver.com> Signed-off-by: Khem Raj <raj.khem@gmail.com>
* phoronix-test-suite: add missing fontPaul Le Guen de Kerneizon2025-02-281-0/+3
| | | | | | | | The `ttf-dejavu-sans` font is needed by SVG charts rendered in phoronix-test-suite PDF reports. Signed-off-by: Paul Le Guen de Kerneizon <paul.leguendekerneizon@savoirfairelinux.com> Signed-off-by: Khem Raj <raj.khem@gmail.com>
* iperf3: throughput fixTrevor Woerner2025-02-272-0/+31
| | | | | | | | | This is a backport of a fix to iperf3. The author saw a 40% improvement in their network throughput, we've seen around a 55% improvement in our tests. Link: https://github.com/esnet/iperf/pull/1708/commits/ac6b9f7fd335ddebc5212eed40083ef4cd3cb86d Signed-off-by: Trevor Woerner <twoerner@gmail.com> Signed-off-by: Khem Raj <raj.khem@gmail.com>
* recipes: drop ld-is-gold supportYi Zhao2025-02-231-6/+0
| | | | | | | | | | The gold linker support has been dropped in oe-core[1]. Remove related special cases and patches in recipes. [1] https://git.openembedded.org/openembedded-core/commit/?id=a4addb9ab63011e7c604fc5daff95559e7d214e7 Signed-off-by: Yi Zhao <yi.zhao@windriver.com> Signed-off-by: Khem Raj <raj.khem@gmail.com>
* recipes: Fix variable assignment whitespaceRichard Purdie2025-01-311-1/+1
| | | | | | | | | | | | Recipes are much more readable with whitespace around the assignment operators. Fix various assignments in meta-openembedded recipes to show this is definitely the preferred formatting. This fixes recipes with larger numbers of issues but there are just under 100 other references left to fix. Signed-off-by: Richard Purdie <richard.purdie@linuxfoundation.org> Signed-off-by: Khem Raj <raj.khem@gmail.com>
* Drop unnecessary SRC_URI md5sum from the recipes in meta-oe.J. S.2024-11-059-9/+0
| | | | | Signed-off-by: Jason Schonberg <schonm@gmail.com> Signed-off-by: Khem Raj <raj.khem@gmail.com>
* fio: upgrade 3.37 -> 3.38Yi Zhao2024-10-101-1/+1
| | | | | Signed-off-by: Yi Zhao <yi.zhao@windriver.com> Signed-off-by: Khem Raj <raj.khem@gmail.com>
* libhugetlbfs: Fix contains reference to TMPDIR [buildpaths] erroralperak2024-10-091-0/+1
| | | | | | | | ERROR: libhugetlbfs-1_2.24-r0 do_package_qa: QA Issue: File /usr/lib/libhugetlbfs/tests/obj64/dummy.ldscript in package libhugetlbfs-tests contains reference to TMPDIR [buildpaths] ERROR: libhugetlbfs-1_2.24-r0 do_package_qa: Fatal QA errors were found, failing task. Signed-off-by: alperak <alperyasinak1@gmail.com> Signed-off-by: Khem Raj <raj.khem@gmail.com>
* libhugetlbfs: Use linker wrapper during buildKhem Raj2024-10-081-1/+9
| | | | | | | | | | | | | | | | | ld.hugetlbfs is munging certain linker commandline options and presenting a differently named options to its users, in summary its expecting linker process to call ld.hugetlbfs which calls the final linker with additional decorations. This patch makes space for that by adding -B option to compiler so it finds this the linker in S and then we creates symlinks for linker name that clang/gcc are expecting. Fixes libhugetlbfs/2.24/recipe-sysroot-native/usr/bin/x86_64-yoe-linux/x86_64-yoe-linux-ld.bfd: unrecognized option '--hugetlbfs-link=B' Signed-off-by: Khem Raj <raj.khem@gmail.com>
* libhugetlbfs: upgrade 2.23 -> 2.24Yi Zhao2024-10-0716-330/+149
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ChangeLog: https://github.com/libhugetlbfs/libhugetlbfs/blob/2.24/NEWS * Refresh patches * Drop backport patches * Inherit autotools-brokensep since it has switched to automake * Add a patch to fix build on musl Test Results: $ mkdir -p /mnt/hugetlbfs $ mount -t hugetlbfs none /mnt/hugetlbfs $ hugeadm --pool-pages-min 2MB:64 $ hugeadm --pool-pages-max 2MB:256 $ cd /usr/lib/libhugetlbfs/tests/ $ ./run_tests.py PASS zero_filesize_segment (2M: 64): PASS test_root (2M: 64): PASS meminfo_nohuge (2M: 64): PASS gethugepagesize (2M: 64): PASS gethugepagesizes (2M: 64): PASS HUGETLB_VERBOSE=1 empty_mounts (2M: 64): PASS HUGETLB_VERBOSE=1 large_mounts (2M: 64): PASS find_path (2M: 64): PASS unlinked_fd (2M: 64): PASS readback (2M: 64): PASS truncate (2M: 64): PASS shared (2M: 64): PASS mprotect (2M: 64): PASS mlock (2M: 64): PASS misalign (2M: 64): PASS fallocate_basic.sh (2M: 64): PASS fallocate_align.sh (2M: 64): PASS ptrace-write-hugepage (2M: 64): PASS icache-hygiene (2M: 64): PASS slbpacaflush (2M: 64): PASS (inconclusive) straddle_4GB_static (2M: 64): PASS huge_at_4GB_normal_below_static (2M: 64): PASS huge_below_4GB_normal_above_static (2M: 64): PASS map_high_truncate_2 (2M: 64): PASS misaligned_offset (2M: 64): PASS (inconclusive) truncate_above_4GB (2M: 64): PASS brk_near_huge (2M: 64): Fatal glibc error: malloc.c:2599 (sysmalloc): assertion failed: (old_top == initial_top (av) && old_size = = 0) || ((unsigned long) (old_size) >= MINSIZE && prev_inuse (old_top) && ((unsigned long) old_end & (pagesize - 1)) == 0) task-size-overrun (2M: 64): PASS stack_grow_into_huge (2M: 64): PASS corrupt-by-cow-opt (2M: 64): PASS noresv-preserve-resv-page (2M: 64): PASS noresv-regarded-as-resv (2M: 64): PASS readahead_reserve.sh (2M: 64): PASS madvise_reserve.sh (2M: 64): PASS fadvise_reserve.sh (2M: 64): PASS mremap-expand-slice-collision.sh (2M: 64): PASS mremap-fixed-normal-near-huge.sh (2M: 64): PASS mremap-fixed-huge-near-normal.sh (2M: 64): PASS set shmmax limit to 67108864 shm-perms (2M: 64): PASS private (2M: 64): PASS fork-cow (2M: 64): PASS direct (2M: 64): PASS malloc (2M: 64): PASS LD_PRELOAD=libhugetlbfs.so HUGETLB_MORECORE=yes malloc (2M: 64): SKIPPED LD_PRELOAD=libhugetlbfs.so HUGETLB_MORECORE=yes HUGETLB_RESTRICT_EXE=unknown:none malloc (2M: 64): SKIPPED LD_PRELOAD=libhugetlbfs.so HUGETLB_MORECORE=yes HUGETLB_RESTRICT_EXE=unknown:malloc malloc (2M: 64): SKIPPED malloc_manysmall (2M: 64): PASS LD_PRELOAD=libhugetlbfs.so HUGETLB_MORECORE=yes malloc_manysmall (2M: 64): SKIPPED GLIBC_TUNABLES=glibc.malloc.tcache_count=0 heapshrink (2M: 64): PASS GLIBC_TUNABLES=glibc.malloc.tcache_count=0 LD_PRELOAD=libheapshrink.so heapshrink (2M: 64): PASS GLIBC_TUNABLES=glibc.malloc.tcache_count=0 LD_PRELOAD=libhugetlbfs.so HUGETLB_MORECORE=yes heapshrink (2M: 64): SKIPPED GLIBC_TUNABLES=glibc.malloc.tcache_count=0 LD_PRELOAD=libhugetlbfs.so libheapshrink.so HUGETLB_MORECORE=yes heapshrink (2M: 64): SKIPPED GLIBC_TUNABLES=glibc.malloc.tcache_count=0 LD_PRELOAD=libheapshrink.so HUGETLB_MORECORE=yes HUGETLB_MORECORE_SHRINK=yes heapshrink (2M: 64): SKIPPED GLIBC_TUNABLES=glibc.malloc.tcache_count=0 LD_PRELOAD=libhugetlbfs.so libheapshrink.so HUGETLB_MORECORE=yes HUGETLB_MORECORE_SHRINK=yes heapshrink (2M: 64): SKIPPED HUGETLB_VERBOSE=1 HUGETLB_MORECORE=yes heap-overflow (2M: 64): SKIPPED HUGETLB_VERBOSE=0 linkhuge_nofd (2M: 64): PASS LD_PRELOAD=libhugetlbfs.so HUGETLB_VERBOSE=0 linkhuge_nofd (2M: 64): PASS linkhuge (2M: 64): PASS LD_PRELOAD=libhugetlbfs.so linkhuge (2M: 64): PASS linkhuge_rw (2M: 64): PASS HUGETLB_ELFMAP=R linkhuge_rw (2M: 64): PASS HUGETLB_ELFMAP=W linkhuge_rw (2M: 64): PASS HUGETLB_ELFMAP=RW linkhuge_rw (2M: 64): PASS HUGETLB_ELFMAP=no linkhuge_rw (2M: 64): PASS HUGETLB_MINIMAL_COPY=no HUGETLB_ELFMAP=R linkhuge_rw (2M: 64): PASS HUGETLB_MINIMAL_COPY=no HUGETLB_ELFMAP=W linkhuge_rw (2M: 64): PASS HUGETLB_MINIMAL_COPY=no HUGETLB_ELFMAP=RW linkhuge_rw (2M: 64): PASS HUGETLB_ELFMAP=R HUGETLB_SHARE=0 linkhuge_rw (2M: 64): PASS HUGETLB_ELFMAP=R HUGETLB_SHARE=1 linkhuge_rw (2M: 64): PASS HUGETLB_ELFMAP=W HUGETLB_SHARE=0 linkhuge_rw (2M: 64): PASS HUGETLB_ELFMAP=W HUGETLB_SHARE=1 linkhuge_rw (2M: 64): PASS HUGETLB_ELFMAP=RW HUGETLB_SHARE=0 linkhuge_rw (2M: 64): PASS HUGETLB_ELFMAP=RW HUGETLB_SHARE=1 linkhuge_rw (2M: 64): PASS chunk-overcommit (2M: 64): PASS alloc-instantiate-race shared (2M: 64): PASS alloc-instantiate-race private (2M: 64): PASS truncate_reserve_wraparound (2M: 64): PASS truncate_sigbus_versus_oom (2M: 64): PASS get_huge_pages (2M: 64): PASS shmoverride_linked (2M: 64): PASS HUGETLB_SHM=yes shmoverride_linked (2M: 64): PASS LD_PRELOAD=libhugetlbfs.so shmoverride_unlinked (2M: 64): PASS LD_PRELOAD=libhugetlbfs.so HUGETLB_SHM=yes shmoverride_unlinked (2M: 64): PASS quota.sh (2M: 64): PASS counters.sh (2M: 64): PASS mmap-gettest 10 64 (2M: 64): PASS mmap-cow 63 64 (2M: 64): PASS set shmmax limit to 134217728 shm-fork 10 32 (2M: 64): PASS set shmmax limit to 134217728 shm-fork 10 64 (2M: 64): PASS set shmmax limit to 134217728 shm-getraw 64 /dev/full (2M: 64): PASS fallocate_stress.sh (2M: 64): PASS ********** TEST SUMMARY * 2M * 32-bit 64-bit * Total testcases: 0 91 * Skipped: 0 9 * PASS: 0 81 * FAIL: 0 0 * Killed by signal: 0 1 * Bad configuration: 0 0 * Expected FAIL: 0 0 * Unexpected PASS: 0 0 * Test not present: 0 0 * Strange test result: 0 0 ********** Signed-off-by: Yi Zhao <yi.zhao@windriver.com> Signed-off-by: Khem Raj <raj.khem@gmail.com>
* fio: upgrade 3.36 -> 3.37Yi Zhao2024-09-291-2/+3
| | | | | | | | * Add UPSTREAM_CHECK_GITTAGREGEX to check the correct latest stable version. Signed-off-by: Yi Zhao <yi.zhao@windriver.com> Signed-off-by: Khem Raj <raj.khem@gmail.com>
generated by cgit v1.2.3-54-g00ecf (git 2.39.0) at 2026-07-21 05:13:04 +0000