glusterfs.git/xlators/debug/io-stats, branch v3.7dev

debug/io-stats: Free conf on init failures

2014-06-30T10:44:00+00:00

Change-Id: I1d227f7b2b8f8ad8d44df8711654ee885e79cf38
BUG: 1111557
Signed-off-by: Pranith Kumar K 
Reviewed-on: http://review.gluster.org/8148
Tested-by: Gluster Build System 
Reviewed-by: Krutika Dhananjay 
Reviewed-by: Vijay Bellur

libglusterfs: Don't allow '-0' as input value for numbers

2014-06-23T03:40:57+00:00

Problem:
io-stats tries to init log-buf-size as uint32. All gf_string2u*** functions
which get the unsigned values from string don't want the string to contain '-'.
So the GF_OPTION_INIT with '-0' as value fails init in io-stats, but by that
time 'ret' is already reset to 0. Io-stats ends up returning 0 even when init
failed. Because of this caller of init thinks initialization is successful when
it is not. iostat_xlator->private is still NULL.  Because of this when a fop
tries to access members of io-stat-private structure, it crashes.

Fix:
I initially thought may be we should fix all gf_string2u*** functions to
accept '-0'. But all these functions are used only for setting volume options.
If we accept '-0', gluster volume info shows output as follows:

diagnostics.brick-log-buf-size: -0

This seemed ugly, so I felt it is better to disallow '-0' as valid input for
numbers.

Also fixed return value in cases of failures in io-stats.

Change-Id: I67ac92853b6d2be70516ad1d07505ffd9f058aa4
BUG: 1111557
Signed-off-by: Pranith Kumar K 
Reviewed-on: http://review.gluster.org/8129
Reviewed-by: Krutika Dhananjay 
Tested-by: Gluster Build System 
Reviewed-by: Harshavardhana 
Tested-by: Harshavardhana 
Reviewed-by: Vijay Bellur

logging: Introduce suppression of repetitive log messages

2014-05-01T06:52:28+00:00

Change-Id: I8efa08cc9832ad509fba65a88bb0cddbaf056404
BUG: 1075611
Signed-off-by: Krutika Dhananjay 
Reviewed-on: http://review.gluster.org/7475
Tested-by: Gluster Build System 
Reviewed-by: Vijay Bellur

build: MacOSX Porting fixes

2014-04-24T21:41:48+00:00

git@forge.gluster.org:~schafdog/glusterfs-core/osx-glusterfs

Working functionality on MacOSX

 - GlusterD (management daemon)
 - GlusterCLI (management cli)
 - GlusterFS FUSE (using OSXFUSE)
 - GlusterNFS (without NLM - issues with rpc.statd)

Change-Id: I20193d3f8904388e47344e523b3787dbeab044ac
BUG: 1089172
Signed-off-by: Harshavardhana 
Signed-off-by: Dennis Schafroth 
Tested-by: Harshavardhana 
Tested-by: Dennis Schafroth 
Reviewed-on: http://review.gluster.org/7503
Tested-by: Gluster Build System 
Reviewed-by: Anand Avati

logging: Make logger and log format configurable through cli

2014-04-12T01:00:54+00:00

Change-Id: Ic4b701a6621578848ff67ae4ecb5a10b5f32f93b
BUG: 1075611
Signed-off-by: Krutika Dhananjay 
Reviewed-on: http://review.gluster.org/7372
Tested-by: Gluster Build System 
Reviewed-by: Krishnan Parthasarathi 
Reviewed-by: Vijay Bellur

debug/io-stats:fix compile warning

2014-03-22T12:27:26+00:00

Compiler Warning:
---------------------------------------------------------
io-stats.c: In function 'io_stats_dump':
io-stats.c:950:24: warning: comparison between 'gf1_cli_stats_op' and
'enum gf1_cli_info_op' [-Wenum-compare]
                 if (op == GF_CLI_INFO_ALL ||
io-stats.c:951:24: warning: comparison between 'gf1_cli_stats_op' and
'enum gf1_cli_info_op' [-Wenum-compare]
                     op == GF_CLI_INFO_CUMULATIVE)
                        ^
---------------------------------------------------------
Fix: Use the appropriate enum in function defintion of io_stats_dump().
Note: Using the same BZ ID as the commit that introduced this argument.

Change-Id: I24e1aaf9ab86b4f337e3daa729d561ec208f2a95
BUG: 1030580
Signed-off-by: Ravishankar N 
Reviewed-on: http://review.gluster.org/7217
Tested-by: Gluster Build System 
Reviewed-by: Vijay Bellur

cli: Add options to the CLI that let the user control the reset of

2014-01-24T10:05:35+00:00

stats

"volume profile info" automatically clears incremental stats. There
isn't a command to:
- fetch stats without clearing incremental stats and
- clear cumulative and incremental stats

This change introduces two arguments (i.e. peek and clear). 'clear'
will wipe both incremental and cumulative stats. 'peek' fetches stats
without wiping incremental stats.

'volume profile info peek' - fetches incremental and cumulative stats
                             without wiping incremental stats

'volume profile info incremental peek' - fetches incremental stats
                                     without wiping incremental stats

'volume profile info clear' - clears both incremental and cumultiave
                              stats

Change-Id: I91834515ad672eca5f882809941147d7d997c4c9
BUG: 1047416
Signed-off-by: Dawit Alemu 
Reviewed-on: http://review.gluster.org/6620
Tested-by: Gluster Build System 
Reviewed-by: Kaushal M 
Reviewed-by: Vijay Bellur

cli: Add an option to fetch just incremental or cumulative I/0

2013-12-04T02:09:29+00:00

information

'volume profile info' fetches both cumulative and incremental
I/O statistics. There isn't a way to fetch just cumulative or
incremental statistics.

This change introduces two optional arguments, namely "incremental"
and "cumulative", that can be tacked on to 'volume profile info'.
In other words, the new command format is

volume profile  {start | info [incremental | cumulative]
| stop} [nfs]

'volume profile info incremental' - fetches incremental stats
'volume profile info cumulative' - fetches cumulative stats
'volume profile info' - fetches incremental and cumulative stats

Change-Id: I5ddb45d990542ea611d23d251efebfec46f472d0
BUG: 1030580
Signed-off-by: Dawit Alemu 
Reviewed-on: http://review.gluster.org/6264
Tested-by: Gluster Build System 
Reviewed-by: Krishnan Parthasarathi

zerofill: Change the type of len argument of glfs_zerofill() to off_t

2013-11-15T07:29:48+00:00

glfs_zerofill() can be potentially called to zero-out entire file and
hence allow for bigger value of length parameter.

Change-Id: I75f1d11af298915049a3f3a7cb3890a2d72fca63
BUG: 1028673
Signed-off-by: Bharata B Rao 
Reviewed-on: http://review.gluster.org/6266
Tested-by: Gluster Build System 
Reviewed-by: M. Mohan Kumar 
Tested-by: M. Mohan Kumar 
Reviewed-by: Anand Avati

glusterfs: zerofill support

2013-11-11T05:25:49+00:00

Add support for a new ZEROFILL fop. Zerofill writes zeroes to a file in
the specified range. This fop will be useful when a whole file needs to
be initialized with zero (could be useful for zero filled VM disk image
provisioning or  during scrubbing of VM disk images).

Client/application can issue this FOP for zeroing out. Gluster server
will zero out required range of bytes ie server offloaded zeroing. In
the absence of this fop,  client/application has to repetitively issue
write (zero) fop to the server, which is very inefficient method because
of the overheads involved in RPC calls  and acknowledgements.

WRITESAME is a  SCSI T10 command that takes a block of data as input and
writes the same data to other blocks and this write is handled
completely within the storage and hence is known as offload . Linux ,now
has support for SCSI WRITESAME command which is exposed to the user in
the form of BLKZEROOUT ioctl.  BD Xlator can exploit BLKZEROOUT ioctl to
implement this fop. Thus zeroing out operations can be completely
offloaded to the storage device , making it highly efficient.

The fop takes two arguments offset and size. It zeroes out 'size' number
of bytes in an opened file starting from 'offset' position.

This patch adds zerofill support to the following areas:
	- libglusterfs
	- io-stats
	- performance/md-cache,open-behind
	- quota
	- cluster/afr,dht,stripe
	- rpc/xdr
	- protocol/client,server
	- io-threads
	- marker
	- storage/posix
	- libgfapi

Client applications can exloit this fop by using glfs_zerofill introduced in
libgfapi.FUSE support to this fop has not been added as there is no system call
for this fop.

Changes from previous version 3:
* Removed redundant memory failure log messages

Changes from previous version 2:
* Rebased and fixed build error

Changes from previous version 1:
* Rebased for latest master

TODO :
     * Add zerofill support to trace xlator
     * Expose zerofill capability as part of gluster volume info

Here is a performance comparison of server offloaded zeofill vs zeroing
out using repeated writes.

[root@llmvm02 remote]# time ./offloaded aakash-test log 20

real	3m34.155s
user	0m0.018s
sys	0m0.040s
[root@llmvm02 remote]# time ./manually aakash-test log 20

real	4m23.043s
user	0m2.197s
sys	0m14.457s
[root@llmvm02 remote]# time ./offloaded aakash-test log 25;

real	4m28.363s
user	0m0.021s
sys	0m0.025s
[root@llmvm02 remote]# time ./manually aakash-test log 25

real	5m34.278s
user	0m2.957s
sys	0m18.808s

The argument log is a file which we want to set for logging purpose and
the third argument is size in GB .

As we can see there is a performance improvement of around 20% with this
fop.

Change-Id: I081159f5f7edde0ddb78169fb4c21c776ec91a18
BUG: 1028673
Signed-off-by: Aakash Lal Das 
Signed-off-by: M. Mohan Kumar 
Reviewed-on: http://review.gluster.org/5327
Tested-by: Gluster Build System 
Reviewed-by: Vijay Bellur