[Pvfs2-users] problem with pvfs2 over diskless cluster

Mon Oct 16 01:52:45 EDT 2006

Hi Wenbin,

> I think you are right. One thing is wrong with the system is that the 
> kernel does not have aio support. However, I did not see any way I can 
> configure the kernel to support it. From discussions I have seen, aio 
> is included in kernel 2.6, and is not needed to be configured to 
> support? Then why in the config log for pvfs2 it say:
>
I am not sure if configuration/detection for aio support should even 
cause the previous issue. THis seems like an unrelated setup issue if at 
all.
Do provide a path to the kernel 2.6 headers to configure like so
./configure --with-kernel=</path/to/k2.6/headers> ..
and see if the aio misdetection persists.
More than the output of configure, the config.log file will have better 
information to help resolve the problem.
> checking for aio support in kernel... no
>
> I have also attached the config output in this email, I hope you can 
> help me to identify what is wrong. My config command is:
>
> ./configure -with-db=/usr/local/BerkeleyDB.4.0 
> --disable-karma-mem-usage-stats --disable-mmap-recache --disable-karma 
> --enable-strict --enable-verbose-build --with-berkdb-debug
>
> I did switch back to berkeleydb.4.0, and you were right, it is not a 
> db issue. I guess it is the AIO issue, however, what should I do to 
> enable it? I reconfigured linux-2.6.17 and linux-2.6.18.1, nothing was 
> found related to AIO.
I am not entirely whats wrong with your setup at this point.
Can you try the above and let us know?
thanks,
Murali
>
> Thanks,
>
> wenbin.
>
>
>> thanks,
>> Murali
>>> Hi, Murali,
>>>
>>> On Fri, 13 Oct 2006, Murali Vilayannur wrote:
>>>
>>>> Hi Wenbin,
>>>>> +++ module.mk   2006-10-12 16:35:32.000000000 -0600
>>>>> @@ -17,4 +17,4 @@
>>>>>         $(DIR)/dbpf-sync.c
>>>>>
>>>>>  # grab trove-ledger.h from handle-mgmt.
>>>>> -MODCFLAGS_$(DIR) = -I$(srcdir)/src/io/trove/trove-handle-mgmt
>>>>> +MODCFLAGS_$(DIR) = -I$(srcdir)/src/io/trove/trove-handle-mgmt 
>>>>> -I/usr/local/BerkeleyDB.4.5/include
>>>>>
>>>> Didn't you run configure with --with-db option?
>>>> If so you should not need the above
>>>>> 2. src/apps/admin/pvfs2-migrate-collection.c
>>>>> [root at phoenix admin]# diff -u pvfs2-migrate-collection.c.oct12 
>>>>> pvfs2-migrate-collection.c
>>>>> --- pvfs2-migrate-collection.c.oct12    2006-10-12 
>>>>> 02:50:15.000000000 -0600
>>>>> +++ pvfs2-migrate-collection.c  2006-10-12 16:38:05.000000000 -0600
>>>>> @@ -24,7 +24,7 @@
>>>>>  #include <dirent.h>
>>>>>  #include <limits.h>
>>>>>
>>>>> -#include <db.h>
>>>>> +#include "/usr/local/BerkeleyDB.4.5/include/db.h"
>>>> or this..
>>>> i/.e run configure --with-db=/usr/local/BerkeleyDB.4.5/ and things 
>>>> should build fine..
>>>> If not do let us know.
>>>
>>> I did run configure with --with-db=/usr/local/BerkeleyDB.4.5, I 
>>> checked the Makefile, SERVERCFLAGS has the include path right, 
>>> however, those two directories still cannot see the db.h. Maybe they 
>>> do not use SERVERCFLAGS, but the normal CFLAGS?
>>>
>>> wenbin.
>>>
>>>> thanks,
>>>> Murali
>>>>
>>>>
>>>
>>
> ------------------------------------------------------------------------
>
> checking build system type... x86_64-unknown-linux-gnu
> checking host system type... x86_64-unknown-linux-gnu
> checking for gcc... gcc
> checking for C compiler default output file name... a.out
> checking whether the C compiler works... yes
> checking whether we are cross compiling... no
> checking for suffix of executables... 
> checking for suffix of object files... o
> checking whether we are using the GNU C compiler... yes
> checking whether gcc accepts -g... yes
> checking for gcc option to accept ANSI C... none needed
> checking how to run the C preprocessor... gcc -E
> checking for egrep... grep -E
> checking for ANSI C header files... yes
> checking for sys/types.h... yes
> checking for sys/stat.h... yes
> checking for stdlib.h... yes
> checking for string.h... yes
> checking for memory.h... yes
> checking for strings.h... yes
> checking for inttypes.h... yes
> checking for stdint.h... yes
> checking for unistd.h... yes
> checking sys/vfs.h usability... yes
> checking sys/vfs.h presence... yes
> checking for sys/vfs.h... yes
> checking sys/mount.h usability... yes
> checking sys/mount.h presence... yes
> checking for sys/mount.h... yes
> checking mntent.h, usability... no
> checking mntent.h, presence... no
> checking for mntent.h,... no
> checking fstab.h usability... yes
> checking fstab.h presence... yes
> checking for fstab.h... yes
> checking stdarg.h usability... yes
> checking stdarg.h presence... yes
> checking for stdarg.h... yes
> checking attr/xattr.h usability... no
> checking attr/xattr.h presence... no
> checking for attr/xattr.h... no
> checking sys/xattr.h usability... yes
> checking sys/xattr.h presence... yes
> checking for sys/xattr.h... yes
> checking for long int... yes
> checking size of long int... 8
> checking for a BSD-compatible install... /usr/bin/install -c
> checking for gcc... (cached) gcc
> checking whether we are using the GNU C compiler... (cached) yes
> checking whether gcc accepts -g... (cached) yes
> checking for gcc option to accept ANSI C... (cached) none needed
> checking for required gcc... checking how to run the C preprocessor... gcc -E
> checking for perl... yes
> checking for find... yes
> checking for bison... no
> checking for flex... no
> checking for client library thread safety support... yes
> checking for tagged Redhat releases (must patch)... no
> checking whether byte ordering is bigendian... no
> checking for void *... yes
> checking size of void *... 8
> checking for i_size_write in kernel... yes
> checking for i_size_read in kernel... yes
> checking for parent_ino in kernel... yes
> checking for memory_backed in struct backing_dev_info in kernel... no
> checking for aio support in kernel... no
> checking for touch_atime support in kernel... no
> checking for xattr support in kernel... no
> checking for 6th argument to sysctl proc handlers... no
> checking for linux/posix_acl.h... no
> checking for linux/posix_acl_xattr.h... no
> checking for linux/xattr_acl.h... no
> checking for linux/ioctl32.h... no
> checking for linux/compat.h... no
> checking for linux/syscalls.h... no
> checking for asm/ioctl32.h... no
> checking for generic_permission api in kernel... yes
> checking for generic_getxattr api in kernel... yes
> checking for arg member in read_descriptor_t in kernel... no
> checking for second arg type int in address_space_operations releasepage... no
> checking for int return in inode_operations follow_link... no
> checking for older int return in invalidatepage... NO
> checking for compat_ioctl member in file_operations structure... no
> checking for register_ioctl32_conversion kernel exports... yes
> checking sys/epoll.h usability... yes
> checking sys/epoll.h presence... yes
> checking for sys/epoll.h... yes
> checking for epoll functions... checking whether cc is an Intel compiler... no
> checking for db library... db
> checking for dbenv parameter to DB error callback function... no
> checking for DB stat with malloc function ptr... no
> checking for txnid parameter to DB stat function... no
> checking for txnid parameter to DB open function... no
> checking for DB_DIRTY_READ flag... yes
> checking for DB_BUFFER_SMALL error... no
> checking if server lib needs -lrt... yes
> checking netdb.h usability... yes
> checking netdb.h presence... yes
> checking for netdb.h... yes
> checking arpa/inet.h usability... yes
> checking arpa/inet.h presence... yes
> checking for arpa/inet.h... yes
> checking sys/socket.h usability... yes
> checking sys/socket.h presence... yes
> checking for sys/socket.h... yes
> checking for gethostbyname... yes
> checking for gethostbyaddr... yes
> checking for fgetxattr extra arguments... no
> checking sys/sysinfo.h usability... yes
> checking sys/sysinfo.h presence... yes
> checking for sys/sysinfo.h... yes
> checking for strnlen... yes
> checking for strtoull... yes
> checking for strstr... yes
> checking for fgetxattr... yes
> checking for fgetxattr prototype... yes
> checking for fgetxattr extra arguments... no
> checking for getmntent in -lsun... no
> checking for getmntent in -lseq... no
> checking for getmntent in -lgen... no
> checking for getmntent... yes
> checking malloc.h usability... yes
> checking malloc.h presence... yes
> checking for malloc.h... yes
> checking mntent.h usability... yes
> checking mntent.h presence... yes
> checking for mntent.h... yes
> checking execinfo.h usability... yes
> checking execinfo.h presence... yes
> checking for execinfo.h... yes
> checking for SDL... no
> checking for GNU-style strerror_r... no
> configure: creating ./config.status
> config.status: creating Makefile
> config.status: creating module.mk
> config.status: creating src/apps/admin/module.mk
> config.status: creating src/apps/admin/pvfs2-config
> config.status: creating src/apps/karma/module.mk
> config.status: creating src/apps/vis/module.mk
> config.status: creating src/apps/kernel/linux/module.mk
> config.status: creating src/io/trove/module.mk
> config.status: creating src/io/trove/trove-handle-mgmt/module.mk
> config.status: creating src/io/trove/trove-dbpf/module.mk
> config.status: creating src/common/misc/module.mk
> config.status: creating src/common/quickhash/module.mk
> config.status: creating src/common/quicklist/module.mk
> config.status: creating src/common/dotconf/module.mk
> config.status: creating src/common/id-generator/module.mk
> config.status: creating src/common/gossip/module.mk
> config.status: creating src/common/gen-locks/module.mk
> config.status: creating src/common/llist/module.mk
> config.status: creating src/common/statecomp/module.mk
> config.status: creating src/io/bmi/module.mk
> config.status: creating src/io/bmi/bmi_tcp/module.mk
> config.status: creating src/io/bmi/bmi_gm/module.mk
> config.status: creating src/io/bmi/bmi_ib/module.mk
> config.status: creating src/io/description/module.mk
> config.status: creating src/io/flow/module.mk
> config.status: creating src/io/flow/flowproto-bmi-trove/module.mk
> config.status: creating src/io/flow/flowproto-template/module.mk
> config.status: creating src/io/flow/flowproto-dump-offsets/module.mk
> config.status: creating src/io/flow/flowproto-bmi-cache/module.mk
> config.status: creating src/io/buffer/module.mk
> config.status: creating src/io/job/module.mk
> config.status: creating src/io/dev/module.mk
> config.status: creating src/proto/module.mk
> config.status: creating src/server/module.mk
> config.status: creating src/server/request-scheduler/module.mk
> config.status: creating src/client/sysint/module.mk
> config.status: creating src/kernel/linux-2.6/Makefile
> config.status: creating src/kernel/linux-2.4/Makefile
> config.status: creating doc/module.mk
> config.status: creating doc/coding/module.mk
> config.status: creating doc/design/module.mk
> config.status: creating doc/random/module.mk
> config.status: creating examples/pvfs2-server.rc
> config.status: creating doc/doxygen/pvfs2-doxygen.conf
> config.status: creating pvfs2-config.h
> config.status: pvfs2-config.h is unchanged
>
> ***** Displaying PVFS2 Configuration Information *****
> ------------------------------------------------------
> PVFS2 configured to build karma gui               :  no
> PVFS2 configured to use epoll                     : yes
> PVFS2 configured to perform coverage analysis     :  no
> PVFS2 configured for aio threaded callbacks       : yes
> PVFS2 configured for the 2.6.x kernel module      :  no
> PVFS2 configured for the 2.4.x kernel module      :  no
> PVFS2 configured for using the mmap-ra-cache      :  no
> PVFS2 configured for using trusted connections    :  no
> PVFS2 configured for a thread-safe client library : yes
> PVFS2 will use workaround for redhat 2.4 kernels  :  no
> PVFS2 will use workaround for buggy NPTL          :  no
> PVFS2 server will be built                        : yes
>
> PVFS2 version string: 1.5.1
>
>   