Greetings, I cannot seem to get valgrind to work with more than 24GB (or so) memory. Others report going much higher than that, so I must be doing something wrong.
Starting with valgrind 3.11.0 from the SVN, built with no modifications on a 64 bit Centos 6.8 system it did this: ~/bin/valgrind testprogram (huge dump of aspacem and other valgrind messages, then) ==10243== Valgrind's memory management: out of memory: ==10243== newSuperblock's request for 784732160 bytes failed. ==10243== 23,404,695,552 bytes have already been mmap-ed ANONYMOUS. ==10243== Valgrind cannot continue. Sorry. Followed the instructions here https://bugs.kde.org/show_bug.cgi?id=229500 to make these changes: --- memcheck/mc_main.c.dist 2015-08-12 16:06:56.303580600 -0700 +++ memcheck/mc_main.c 2016-07-20 12:34:08.659419705 -0700 @@ -176,7 +176,7 @@ /* Just handle the first 64G fast and the rest via auxiliary primaries. If you change this, Memcheck will assert at startup. See the definition of UNALIGNED_OR_HIGH for extensive comments. */ -# define N_PRIMARY_BITS 20 +# define N_PRIMARY_BITS 22 #endif @@ -7737,11 +7737,11 @@ tl_assert(sizeof(Addr) == 8); tl_assert(sizeof(UWord) == 8); tl_assert(sizeof(Word) == 8); - tl_assert(MAX_PRIMARY_ADDRESS == 0xFFFFFFFFFULL); - tl_assert(MASK(1) == 0xFFFFFFF000000000ULL); - tl_assert(MASK(2) == 0xFFFFFFF000000001ULL); - tl_assert(MASK(4) == 0xFFFFFFF000000003ULL); - tl_assert(MASK(8) == 0xFFFFFFF000000007ULL); + tl_assert(MAX_PRIMARY_ADDRESS == 0x3FFFFFFFFFULL); + tl_assert(MASK(1) == 0xFFFFFFC000000000ULL); + tl_assert(MASK(2) == 0xFFFFFFC000000001ULL); + tl_assert(MASK(4) == 0xFFFFFFC000000003ULL); + tl_assert(MASK(8) == 0xFFFFFFC000000007ULL); # endif } --- coregrind/m_aspacemgr/aspacemgr-linux.c.dist 2015-08-12 16:11:55.422717467 -0700 +++ coregrind/m_aspacemgr/aspacemgr-linux.c 2016-07-20 12:36:12.307343249 -0700 @@ -1608,7 +1608,7 @@ aspacem_cStart = aspacem_minAddr; aspacem_vStart = 0xf0000000; // 0xc0000000..0xf0000000 available # else - aspacem_maxAddr = (Addr) 0x7fffffffffff; + aspacem_maxAddr = (Addr) 0x4000000000 - 1; // 256G aspacem_cStart = aspacem_minAddr; aspacem_vStart = 0x700000000000; // 0x7000:00000000..0x7fff:5c000000 avail ran it again and had: ~/bin/valgrind testprogram (huge dump of aspacem and other valgrind messages, then) ==14718== Valgrind's memory management: out of memory: ==14718== newSuperblock's request for 783163392 bytes failed. ==14718== 23,401,435,136 bytes have already been mmap-ed ANONYMOUS. ==14718== Valgrind cannot continue. Sorry. ulimit -a core file size (blocks, -c) 0 data seg size (kbytes, -d) unlimited scheduling priority (-e) 0 file size (blocks, -f) unlimited pending signals (-i) 2067197 max locked memory (kbytes, -l) 64 max memory size (kbytes, -m) unlimited open files (-n) 1024 pipe size (512 bytes, -p) 8 POSIX message queues (bytes, -q) 819200 real-time priority (-r) 0 stack size (kbytes, -s) 10240 cpu time (seconds, -t) unlimited max user processes (-u) 1024 virtual memory (kbytes, -v) unlimited file locks (-x) unlimited kernel is 2.6.32-642.1.1.el6.x86_64 Any ideas??? Thank you, David Mathog mat...@caltech.edu Manager, Sequence Analysis Facility, Biology Division, Caltech ------------------------------------------------------------------------------ What NetFlow Analyzer can do for you? Monitors network bandwidth and traffic patterns at an interface-level. Reveals which users, apps, and protocols are consuming the most bandwidth. Provides multi-vendor support for NetFlow, J-Flow, sFlow and other flows. Make informed decisions using capacity planning reports.http://sdm.link/zohodev2dev _______________________________________________ Valgrind-users mailing list Valgrind-users@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/valgrind-users
