glusterfs.git/xlators/performance/nl-cache, branch v4.1dev

all: Simplify component message id's definition

2017-12-14T02:33:51+00:00

This patch creates a new way of defining message id's that is easier
and less error prone because it doesn't require so many manual changes
each time a new component is defined or a new message created.

Change-Id: I71ba8af9ac068f5add7e74f316a2478bc991c67b
Signed-off-by: Xavier Hernandez

libglusterfs/atomic: Improved atomic support

2017-11-14T05:22:00+00:00

This patch solves a detection problem in configure.ac that prevented
that compilation detects builtin __atomic or __sync functions.

It also adds more atomic types and support for other atomic functions.

An special case has been added to support 64-bit atomics on 32-bit
systems. The solution is to fallback to the mutex solution only for
64-bit atomics, but smaller atomic types will still take advantage
of builtins if available.

Change-Id: I6b9afc7cd6e66b28a33278715583552872278801
BUG: 1510397
Signed-off-by: Xavier Hernandez

Fix the conditional

2017-09-07T17:54:27+00:00

Clang complain about it on FreeBSD

   In file included from xlators/performance/nl-cache/src/nl-cache-helper.c:11:
   In file included from xlators/performance/nl-cache/src/nl-cache.h:14:
   xlators/performance/nl-cache/src/nl-cache-mem-types.h:12:9: warning: '__NL_CACHe_MEM_TYPES_H__' is used as a header guard here, followed by #define of a different macro [-Wheader-guard]
   #ifndef __NL_CACHe_MEM_TYPES_H__

Change-Id: I4327c7dacf10f2690bd33bf2b37dbb7d9b52bdd5
BUG: 1488840
Signed-off-by: Michael Scherer 
Reviewed-on: https://review.gluster.org/18216
Smoke: Gluster Build System 
Tested-by: Michael Scherer 
CentOS-regression: Gluster Build System 
Reviewed-by: Jeff Darcy

nl-cache: Fix a possible crash and stale cache

2017-06-13T05:01:17+00:00

Issue1:
Consider the followinf sequence of operations:
   ...
   nlc_ctx = nlc_ctx_get (inode i1)
   ....... -> nlc_clear_cache (i1) gets called as a part of nlc_invalidate
                                   or any other callers
              ...
              GF_FREE (ii nlc_ctx)
   LOCK (nlc_ctx->lock);  ->  This will result in crash as the ctx
                              got freed in nlc_clear_cache.

Issue2:
   lookup on dir1/file1 result in ENOENT
   add cache to dir1 at time T1
   ....
   CHILD_DOWN at T2
   lookup on dir1/file2 result in ENOENT
   add cache to dir1, but the cache time is still T1
   lookup on dir1/file2 - should have been served from cache
                          but the cache time is T1 < T2, hence
                          cache is considered as invalid.
So, after CHILD_DOWN the right thing would be to clear the cache
and restart caching on that inode.

Solution:
Do not free nlc_ctx in nlc_clear_cache, but only in inode_forget()
The fix for both issue1 and 2 is interleaved hence sending it as
single patch.

Change-Id: I83d8ed36c049a93567c6d7e63d045dc14ccbb397
BUG: 1458539
Signed-off-by: Poornima G 
Reviewed-on: https://review.gluster.org/17453
Smoke: Gluster Build System 
NetBSD-regression: NetBSD Build System 
Reviewed-by: Pranith Kumar Karampuri 
CentOS-regression: Gluster Build System

core: fix spelling errors

2017-06-02T11:50:43+00:00

fixes for various minor spelling errors and typos

Reported-by: Patrick Matthäi 
Change-Id: Ic1be36f82e3d822bbdc9559878bd79520fc0fcd5
BUG: 1457808
Signed-off-by: Kaleb S. KEITHLEY 
Reviewed-on: https://review.gluster.org/17442
NetBSD-regression: NetBSD Build System 
CentOS-regression: Gluster Build System 
Reviewed-by: Niels de Vos 
Smoke: Gluster Build System

nl-cache: Remove null check validation for frame->local in lookup cbk

2017-05-30T15:34:51+00:00

For nameless lookups, nl-cache does not init frame local, so the cbk
throws up messages like these flooding the logs, especially whenenver
gfid lookup on '/' is done (i.e. loc.path="/" and loc.gfid=1).

[2017-05-30 04:35:31.628443] E [nl-cache.c:201:nlc_lookup_cbk]
(-->/usr/lib64/glusterfs/3.8.4/xlator/performance/io-cache.so(+0x3d81)
[0x7f0883005d81]
-->/usr/lib64/glusterfs/3.8.4/xlator/performance/quick-read.so(+0x3127)
[0x7f0882dfb127]
-->/usr/lib64/glusterfs/3.8.4/xlator/performance/nl-cache.so(+0x4cd3)
[0x7f08829e0cd3] ) 0-distrep-nl-cache: invalid argument: local [Invalid
argument]

Fixed it.

Change-Id: I21cb44a9d2a324617e43f46fed83c9a0942d3a0b
BUG: 1456653
Signed-off-by: Ravishankar N 
Reviewed-on: https://review.gluster.org/17417
Tested-by: Pranith Kumar Karampuri 
Smoke: Gluster Build System 
Reviewed-by: Poornima G 
NetBSD-regression: NetBSD Build System 
CentOS-regression: Gluster Build System

nl-cache: In case of nameless operations do not cache

2017-05-22T12:39:59+00:00

Issue:
In nameless lookup/other fops, parent inode will be NULL, when we try
to add the cache to the NULL inode, it causes a crash.

Hence handle the scenario of nameless fops, and do not cache/serve
the nameless fops.

Change-Id: I3b90f882ac89e6aaf3419db89e6f890797f37700
BUG: 1451588
Signed-off-by: Poornima G 
Reviewed-on: https://review.gluster.org/17316
Smoke: Gluster Build System 
NetBSD-regression: NetBSD Build System 
Reviewed-by: Pranith Kumar Karampuri 
CentOS-regression: Gluster Build System

nl-cache: Remove the max limit for nl-cache-limit and nl-cache-timeout

2017-05-15T12:18:08+00:00

The max limit is better unset when arbitrary. Otherwise in the future
if max has to be changed, it can break backward compatility.

Change-Id: I4337a3789a2d0d5cc8e2bf687a22536c97608461
BUG: 1442569
Signed-off-by: Poornima G 
Reviewed-on: https://review.gluster.org/17261
Smoke: Gluster Build System 
NetBSD-regression: NetBSD Build System 
CentOS-regression: Gluster Build System 
Reviewed-by: Jeff Darcy

nl-cache: free nlc_conf_t in fini()

2017-05-02T15:25:08+00:00

The (xlator_t*)->private structure in negative-lookup-cache is allocated
in the init() function of the xlator, but never free'd. Valgrind
detected this as:

    656 bytes in 1 blocks are definitely lost in loss record X of Y
       at 0x..+ calloc (/builddir/build/BUILD/valgrind-3.11.0/coregrind/m_replacemalloc/vg_replace_malloc.c:711)
       by 0x.. __gf_calloc (/usr/src/debug/glusterfs-3.11dev/libglusterfs/src/mem-pool.c:117)
       by 0x.. init (/usr/src/debug/glusterfs-3.11dev/xlators/performance/nl-cache/src/nl-cache.c:669)
       by 0x.. __xlator_init (/usr/src/debug/glusterfs-3.11dev/libglusterfs/src/xlator.c:472)
       by 0x.. xlator_init (/usr/src/debug/glusterfs-3.11dev/libglusterfs/src/xlator.c:498)
       by 0x.. glusterfs_graph_init (/usr/src/debug/glusterfs-3.11dev/libglusterfs/src/graph.c:321)
       by 0x.. glusterfs_graph_activate (/usr/src/debug/glusterfs-3.11dev/libglusterfs/src/graph.c:693)
       by 0x.. glfs_process_volfp (/usr/src/debug/glusterfs-3.11dev/api/src/glfs-mgmt.c:79)
       by 0x.. glfs_volumes_init (/usr/src/debug/glusterfs-3.11dev/api/src/glfs.c:160)
       by 0x.. glfs_init_common (/usr/src/debug/glusterfs-3.11dev/api/src/glfs.c:868)
       by 0x.. glfs_init@@GFAPI_3.4.0 (/usr/src/debug/glusterfs-3.11dev/api/src/glfs.c:913)
       by 0x.. main (/root/gluster-debug/gfapi-load-volfile/gfapi-load-volfile.c:54)

When the xlators is unloaded, it should free the resources it allocated.
This can easily be done in the fini() function.

Change-Id: I079e78cc207145bc542e2282fc4cf2bb4dadc28a
BUG: 1442569
Signed-off-by: Niels de Vos 
Reviewed-on: https://review.gluster.org/17143
Smoke: Gluster Build System 
NetBSD-regression: NetBSD Build System 
CentOS-regression: Gluster Build System 
Reviewed-by: Jeff Darcy

core: make the per glusterfs_ctx_t timer-wheel refcounted

2017-05-01T09:30:14+00:00

xlators can use a 'global' timer-wheel for scheduling events. This
timer-wheel is managed per glusterfs_ctx_t, but does not need to be
allocated for every graph. When an xlator wants to use the timer-wheel,
it will be instanciated on demand, and provided to xlators that request
it later on.

By adding a reference counter to the glusterfs_ctx_t for the
timer-wheel, the threads and structures can be cleaned up when the last
xlator does not have a need for it anymore. In general, the xlators
request the timer-wheel in init(), and they should return it in fini().

Because the timer-wheel is managed per glusterfs_ctx_t, the functions
can be added to ctx.c and do not need to live in their very minimal
tw.[ch] files.

Change-Id: I19d225b39aaa272d9005ba7adc3104c3764f1572
BUG: 1442788
Reported-by: Poornima G 
Signed-off-by: Niels de Vos 
Reviewed-on: https://review.gluster.org/17068
NetBSD-regression: NetBSD Build System 
CentOS-regression: Gluster Build System 
Smoke: Gluster Build System 
Reviewed-by: Amar Tumballi 
Reviewed-by: Zhou Zhengping 
Reviewed-by: Kaleb KEITHLEY