glusterfs.git/libglusterfs/src/glusterfs, branch v9dev

Posix: Optimize posix code to improve file creation

2020-04-06T10:43:26+00:00

Problem: Before executing a fop in POSIX xlator it builds an internal
         path based on GFID.To validate the path it call's (l)stat
         system call and while .glusterfs is heavily loaded kernel takes
         time to lookup inode and due to that performance drops

Solution: In this patch we followed two ways to improve the performance.
          1) Keep open fd specific to first level directory(gfid[0])
             in .glusterfs, it would force to kernel keep the inodes
             from all those files in cache. In case of memory pressure
             kernel won't uncache first level inodes. We need to open
             256 fd's per brick to access the entry faster.
          2) Use at based call's to access relative path to reduce
             path based lookup time.

Note: To verify the patch we have executed kernel untar 100 times on 6
      different clients after enabling metadata group-cache and some
      other option.We were getting more than 20 percent improvement in
      kenel untar after applying the patch.

Credits: Xavi Hernandez 
Change-Id: I1643e6b01ed669b2bb148d02f4e6a8e08da45343
updates: #891
Signed-off-by: Mohit Agrawal

Posix: Use simple approach to close fd

2020-03-20T04:08:42+00:00

Problem: posix_release(dir) functions add the fd's into a ctx->janitor_fds
         and janitor thread closes the fd's.In brick_mux environment it is
         difficult to handle race condition in janitor threads because brick
         spawns a single janitor thread for all bricks.

Solution: Use synctask to execute posix_release(dir) functions instead of 
          using background a thread to close fds.

Credits: Pranith Karampuri 
Change-Id: Iffb031f0695a7da83d5a2f6bac8863dad225317e
Fixes: bz#1811631
Signed-off-by: Mohit Agrawal

utime: resolve an issue of permission denied logs

2020-03-13T12:15:21+00:00

In case where uid is not set to be 0, there are possible errors
from acl xlator. So, set `uid = 0;` with pid indicating this is
set from UTIME activity.

The message "E [MSGID: 148002] [utime.c:146:gf_utime_set_mdata_setxattr_cbk] 0-dev_SNIP_data-utime: dict set of key for set-ctime-mdata failed [Permission denied]" repeated 2 times between [2019-12-19 21:27:55.042634] and [2019-12-19 21:27:55.047887]

Change-Id: Ieadf329835a40a13ac0bf908dac776e66954466c
Fixes: #832
Signed-off-by: Amar Tumballi

core: fix memory pool management races

2020-02-18T17:29:51+00:00

Objects allocated from a per-thread memory pool keep a reference to it
to be able to return the object to the pool when not used anymore. The
object holding this reference can have a long life cycle that could
survive a glfs_fini() call.

This means that it's unsafe to destroy memory pools from glfs_fini().

Another side effect of destroying memory pools from glfs_fini() is that
the TLS variable that points to one of those pools cannot be reset for
all alive threads.  This means that any attempt to allocate memory from
those threads will access already free'd memory, which is very
dangerous.

To fix these issues, mem_pools_fini() doesn't destroy pool lists
anymore. Only at process termination the pools are destroyed.

Change-Id: Ib189a5510ab6bdac78983c6c65a022e9634b0965
Fixes: bz#1801684
Signed-off-by: Xavi Hernandez

libglusterfs-xlator: structure logging

2020-02-14T07:16:48+00:00

convert all gf_msg() to gf_smsg()

Change-Id: Id542e05faadb8041b472a2298c71fe62730e65fc
Updates: #657
Signed-off-by: yatipadia

volgen: make thin-arbiter name unique in 'pending-xattr' option

2020-02-12T16:16:46+00:00

Thin-arbiter module makes use of 'pending-xattr' name for the translator
as the filename which gets created in thin-arbiter node. By making this
unique, we can host single thin-arbiter node for multiple clusters.

Updates: #763
Change-Id: Ib3c732e7e04e6dba229e71ae3e64f1f3cb6d794d
Signed-off-by: Amar Tumballi

libglusterfs-options: structure logging

2020-02-09T02:53:40+00:00

convert all gf_msg() to gf_smsg()

Change-Id: I8f1ff462b9c8012ed676c51450930a65ac403bf3
Updates: #657
Signed-off-by: yatipadia

bitrot: Make number of signer threads configurable

2020-02-07T06:30:19+00:00

The number of signing process threads (glfs_brpobj)
is set to 4 by default. The recommendation is to set
it to number of cores available. This patch makes it
configurable as follows

gluster vol bitrot  signer-threads 

fixes: bz#1797869
Change-Id: Ia883b3e5e34e0bc8d095243508d320c9c9c58adc
Signed-off-by: Kotresh HR

libglusterfs-event-epoll: structure logging

2020-02-06T05:27:18+00:00

convert gf_msg() to gf_smsg()

Change-Id: Idf5bfc826b0c9f1a2674eea2a2e6164f30806b00
Updates: #657
Signed-off-by: yatipadia

glusterfsd: structure logging

2020-02-06T05:27:03+00:00

convert gf_msg() to gf_smsg()

Change-Id: I1cd6a5ac6f4361195d5d925efb2cc194045d0bba
Updates: #657
Signed-off-by: yatip