GFPCOPY(1) | Gfarm | GFPCOPY(1) |
gfpcopy - copy Gfarm files in parallel
gfpcopy [-nqvdpPU] [-X regexp] [-S source-domainname] [-h source-hostfile] [-D destination-domainname] [-H destination-hostfile] [-j num-of-processes] [-J num-of-processes] [-M limit-byte] [-z minimum-byte] [-Z maximum-byte] [-w way-of-scheduling] [-W kilobytes-for-threshold] [-s KB/s-to-simulate] [-F num-for-readahead] [-b bufsize] [-f] [-e] [-k] source-path destination-path
gfpcopy copies files in parallel.
When the source-path is a directory, files under the directory will be copied recursively.
When the destination-path does not exist, the directory is created. When the destination-path exists, a directory of the same name as the source-path is created under the destination-path.
A set of source/destination hosts can be specified by a domain name and/or a hostlist file. When both a domain name and a hostlist file are specified, a set of hosts is determined by both conditions. When a set of source hosts is specified, only files stored on the source hosts are copied.
gfpcopy also retrieves the directory entries in parallel.
source-path must be one of the following formats. Files on HPSS cannot be copied.
path-name
gfarm:...
file:...
destination-path must be one of the following formats.
path-name
gfarm:...
file:...
hpss:...
These are options only for gfpcopy.
-b bufsize
The default value is 64 KiB (64 * 1024).
-f
Without the -f option, existing files will be overwritten when they are older than the corresponding source files in the modification time.
-e
-k
The following options are common options for gfprep and gfpcopy.
-X regexp
-S source-domainname
-h source-hostfile
If ``-'' is specified, standard input is used to read the host list.
-L
-D destination-domainname
If neither this nor the -H option is specified, replicas may be copied to any available host.
-H destination-hostfile
If ``-'' is specified, standard input is used to read the host list.
-j num-of-processes
The default value is the parameter of client_parallel_copy in gfarm2.conf. (see man gfarm2.conf)
The maximum number of process per file system node for source or destination is the number of CPUs (see man gfhost).
-J num-of-processes
The default value is 8.
-M total-byte
The default value is unlimited.
-z minimum-byte
The default value is unlimited.
-Z maximum-byte
The default value is unlimited.
-w way-of-scheduling
The default behavior is ``noplan''.
``greedy'' scheduling cannot use with the -N option and -m option.
-W kibibytes
This option is effective with -w greedy.
The default value is 50*1024 KiB (50 MiB).
-I sec-to-update
Default is 300 seconds.
-B
High loaded node is defined by having more CPU load than schedule_busy_load_thresh * number of CPUs. For details of schedule_busy_load_thresh, refer to a manual page of gfarm2.conf.
-U
-F num-of-dirents
The default value is 10000.
-s kilobytes-per-second
-n
-p
-P
-q
-v
-d
-?
To copy files under the directory recursively.
$ gfpcopy gfarm:///dir file:///tmp/dir
$ gfpcopy file:///tmp/dir gfarm:///dir
$ gfpcopy gfarm:///dir1 gfarm:///dir2
$ gfpcopy gfarm:///dir hpss:///tmp/dir
$ cd /mnt/gfarm2fs $ gfpcopy dir /tmp/dir
To copy a file.
$ gfpcopy gfarm:///dir/file file:///dir
$ cd /mnt/gfarm2fs $ gfpcopy file /tmp/dir
To retrieve the directory entries efficiently, it is better to execute gfpcopy command near the metadata server. When you need to execute gfpcopy command far from the metadata server, increase the parallelism by the -j and -J options.
27 Aug 2015 | Gfarm |