glusterfs.git/libglusterfs/src/gfdb/gfdb_sqlite3.h, branch v3.12.5

cluster/tier: handle fast demotions

2016-10-19T19:51:48+00:00

Demote files on priority if hi-watermark has been breached and continue
to demote until the watermark drops below hi-watermark.

Monitor watermark more frequently.
Trigger demotion as soon as hi-watermark is breached.
Add cluster.tier-emergency-demote-query-limit option to limit number
of files returned from the database query for every iteration of
tier_migrate_using_query_file(). If watermark hasn't dropped below
hi-watermark during the first iteration, the next iteration will be
triggered approximately 1 second after tier_demote() returns to the
main tiering loop.
Update changetimerecorder xlator to handle query for emergency demote
mode.

Add tier-ctr-interface.h:
Move tier and ctr interface specific macros and struct definition from
libglusterfs/src/gfdb/gfdb_data_store.h to new header
libglusterfs/src/tier-ctr-interface.h

Change-Id: If56af78c6c81d37529b9b6e65ae606ba5c99a811
BUG: 1366648
Signed-off-by: Milind Changire 
Reviewed-on: http://review.gluster.org/15158
Smoke: Gluster Build System 
CentOS-regression: Gluster Build System 
NetBSD-regression: NetBSD Build System 
Reviewed-by: Dan Lambright

tier/ctr/sql : Dafault values for sql cache and wal size

2016-09-22T20:28:34+00:00

Setting default values for sql cache and wal size
cache : 12500 pages
wal   : 25000 pages
1 pages - 4096 bytes

Change-Id: Iae3927e021af2e3f7617d45f84e81de3b7d93f1c
BUG: 1377864
Signed-off-by: Dan Lambright 
Reviewed-on: http://review.gluster.org/15536
Smoke: Gluster Build System 
NetBSD-regression: NetBSD Build System 
CentOS-regression: Gluster Build System 
Reviewed-by: Milind Changire

cluster/tier: Adding compaction option for metadata databases

2016-09-05T01:37:57+00:00

Problem: As metadata in the database fills up, querying the database
take a long time. As a result, tier migration slows down.  To
counteract this, we added a way to enable the compaction methods of
the underlying database. The goal is to reduce the size of the
underlying file by eliminating database fragmentation.

NOTE: There is currently a bug where sometimes a brick will
attempt to activate compaction. This happens even compaction is already
turned on.

The cause is narrowed down to the compact_mode_switch flipping its value.

Changes: libglusterfs/src/gfdb - Added a gfdb function to compact the
underlying database, compact_db() This is a no-op if the database has
no such option.

- Added a compaction function for SQLite3 that does the following

1) Changes the auto_vacuum pragma of the database
2) Compacts the database according to the type of compaction requested

- Compaction type can be changed by changing the macro
  GF_SQL_COMPACT_DEF to one of the 4 compaction types in
  gfdb_sqlite3.h

  It is currently set to GF_SQL_COMPACT_INCR, or incremental
  vacuuming.

xlators/cluster/dht/src - Added the following command-line option to
enable SQLite3 compaction.

gluster volume set  tier-compact 

- Added the following command-line option to change the frequency the
  hot and cold tier are ordered to compact.

gluster volume set  tier-hot-compact-frequency 
gluster volume set  tier-cold-compact-frequency 

- tier daemon periodically sends the (new)
  GFDB_IPC_CTR_SET_COMPACT_PRAGMA IPC to the CTR xlator. The IPC
  triggers compaction of the database.

  The inputs are both gf_boolean_t.

  IPC Input:

  compact_active: Is compaction currently on for the db.
  compact_mode_switched: Did we flip the compaction switch recently?

  IPC Output:

  0 if the compaction succeeds.
  Non-zero otherwise.

xlators/features/changetimerecorder/src/ - When the CTR gets the
compaction IPC, it launches a thread that will perform the
compaction. The IPC ends after the thread is launched. To avoid extra
allocations, the parameters are passed using static variables.

Change-Id: I5e1433becb9eeff2afe8dcb4a5798977bf5ba0dd
Signed-off-by: Diogenes Nunez 
Reviewed-on: http://review.gluster.org/15031
Reviewed-by: Milind Changire 
Reviewed-by: Dan Lambright 
Tested-by: Dan Lambright 
CentOS-regression: Gluster Build System 
NetBSD-regression: NetBSD Build System 
Smoke: Gluster Build System

ctr/sql: Providing for vol set for sqlcachesize and sqlWALsize and skip recording path

2015-12-22T15:14:10+00:00

1. Providing vol set option for cache size and wal autocheck point
   so that performance can be tuned.
2. Removed recording of file path in the db. Trimming database columns.
   Path need not be stored in the db, as PARGFID, GFID, Basename is suffice
   to derive the path during migration.

Change-Id: I2cb590451a6d244bc91fe66c6dbffe2c2059dfb8
BUG: 1293034
Signed-off-by: Joseph Fernandes 
Reviewed-on: http://review.gluster.org/12972
Reviewed-by: N Balachandran 
Tested-by: Gluster Build System 
Tested-by: NetBSD Build System 
Reviewed-by: Dan Lambright 
Tested-by: Dan Lambright

tier/libgfdb: Replacing ASCII query file with binary

2015-11-06T18:30:45+00:00

Earlier, when the database was queried we used to save
all the queried records in an ASCII format in the query file.
This caused issues like filename having ASCII delimiter and used
to take a lot of space. The tier.c file also had a lot of parsing code.

Here we changed the format of the query file to binary.
All the logic of serialization and formating of query record is done
by libgfdb. Libgfdb provides API,
gfdb_write_query_record() and gfdb_read_query_record(),
which the user i.e tier migrator and CTR xlator can use to
write to and read from query file.
With this binary format we save on disk space i.e reduce to 50% atleast
as we are saving GFID's in binary format 16 bytes and not the string format
which takes 36 bytes + We are not saving path of the file + we are also saving on
ASCII delimiters.

The on disk format of query record is as follows,

+---------------------------------------------------------------------------+
| Length of serialized query record |       Serialized Query Record         |
+---------------------------------------------------------------------------+
             4 bytes                     Length of serialized query record
                                                      |
                                                      |
     -------------------------------------------------|
     |
     |
     V
   Serialized Query Record Format:
   +---------------------------------------------------------------------------+
   | GFID |  Link count   |    |.....                      | FOOTER |
   +---------------------------------------------------------------------------+
     16 B        4 B         Link Length                                  4 B
                                |                                          |
                                |                                          |
   -----------------------------|                                          |
   |                                                                       |
   |                                                                       |
   V                                                                       |
   Each  will be serialized as                                  |
   +-----------------------------------------------+                       |
   | PGID | BASE_NAME_LENGTH |      BASE_NAME      |                       |
   +-----------------------------------------------+                       |
     16 B       4 B             BASE_NAME_LENGTH                           |
                                                                           |
                                                                           |
   ------------------------------------------------------------------------|
   |
   |
   V
   FOOTER is a magic number 0xBAADF00D indicating the end of the record.
   This also serves as a serialized schema validator.

Change-Id: I9db7416fd421e118dd44eafab8b535caafe50d5a
BUG: 1272207
Signed-off-by: Joseph Fernandes 
Reviewed-on: http://review.gluster.org/12354
Reviewed-by: N Balachandran 
Tested-by: Gluster Build System 
Reviewed-by: Dan Lambright 
Tested-by: Dan Lambright

tier/ctr: Solution for db locks for tier migrator and ctr using sqlite version less than 3.7 i.e rhel 6.7

2015-10-08T19:00:31+00:00

Problem: On RHEL 6.7, we have sqlite version 3.6.2 which doesnt support
WAL journaling mode, as this journaling mode is only available in sqlite 3.7 and above.
As a result we cannot have to progreses concurrently accessing sqlite, without
running into db locks! Well WAL is also need for performace on CTR side.

Solution: This solution is to use CTR db connection for doing queries when WAL mode is
absent. i,e tier migrator will send sync_op ipc calls to CTR, which in turn will
do the query and create/update the query file suggested by tier migrator.

Pending: Well this solution will stop the db locks but the performance is still an issue for CTR.
We are developing an in-Memory Transaction Log (iMeTaL) which will help boost the CTR
performance by doing in memory udpates on the IO path and later flush the updates to
the db in a batch/segment flush.

Change-Id: Ie3149643ded159234b5cc6aa6cf93b9022c2f124
BUG: 1240577
Signed-off-by: Joseph Fernandes 
Signed-off-by: Dan Lambright 
Signed-off-by: Joseph Fernandes 
Reviewed-on: http://review.gluster.org/12191
Tested-by: Gluster Build System 
Reviewed-by: Luis Pabon

tier/ctr: Solving DB Lock issue due to write contention from db connections

2015-09-08T12:13:00+00:00

Problem: The DB on the brick is been accessed by CTR, for write and
tier migrator, for read and write. The write from tier migrator is reseting
the heat counters after a cycle. Since we are using sqlite, two connections
trying to write would cause a db lock contention. As a result CTR used to fail
to update the db.

Solution: Using the same db connection of CTR for reseting the heat counters.
1) Introducted a new IPC FOP for CTR
2) After the query do a ipc syncop to the underlying client xlator associated
   to the brick.
3) CTR in brick will catch the IPC FOP and cleat the heat counters.

Change-Id: I53306bfc08dcdba479deb4ccc154896521336150
BUG: 1260730
Signed-off-by: Joseph Fernandes 
Reviewed-on: http://review.gluster.org/12031
Tested-by: NetBSD Build System 
Tested-by: Gluster Build System 
Reviewed-by: Dan Lambright 
Tested-by: Dan Lambright

gfdb/libglusterfs : Porting to a new logging framework

2015-06-10T08:54:14+00:00

Change-Id: I61874561fdf2c175d2b3eec0c85c25f12dc60552
BUG: 1194640
Signed-off-by: Mohamed Ashiq 
Reviewed-on: http://review.gluster.org/10819
Tested-by: NetBSD Build System 
Tested-by: Gluster Build System 
Reviewed-by: Joseph Fernandes

build: do not #include "config.h" in each file

2015-05-29T12:43:17+00:00

Instead of including config.h in each file, and have the additional
config.h included from the compiler commandline (-include option).

When a .c file tests for a certain #define, and config.h was not
included, incorrect assumtions were made. With this change, it can not
happen again.

BUG: 1222319
Change-Id: I4f9097b8740b81ecfe8b218d52ca50361f74cb64
Signed-off-by: Niels de Vos 
Reviewed-on: http://review.gluster.org/10808
Tested-by: Gluster Build System 
Tested-by: NetBSD Build System
Reviewed-by: Kaleb KEITHLEY 
Reviewed-by: Pranith Kumar Karampuri

cluster/dht: Add tier translator.

2015-03-21T16:50:29+00:00

The tier translator shares most of DHT's code. It differs in how
subvolumes are chosen for I/Os, and how file migration (cache promotion
and demotion) is managed. That different functionality is split to either
DHT or tier logic according to the "tier_methods" structure.

A cache promotion and demotion thread is created in a manner
similar to the rebalance daemon. The thread operates a timing
wheel which periodically checks for promotion and demotion candidates
(files). Candidates are queued and then migrated. Candidates must exist on
the same node as the daemon and meet other critera per caching policies.

This patch has two authors (Dan Lambright and Joseph Fernandes). Dan
did the DHT changes and Joe wrote the cache policies. The fix depends on
DHT readidr changes and the database library which have been submitted
separately.  Header files in libglusterfs/src/gfdb should be reviewed in
patch 9683.

For more background and design see the feature page [1].

[1]
http://www.gluster.org/community/documentation/index.php/Features/data-classification

Change-Id: Icc26c517ccecf5c42aef039f5b9c6f7afe83e46c
BUG: 1194753
Signed-off-by: Dan Lambright 
Reviewed-on: http://review.gluster.org/9724
Reviewed-by: Vijay Bellur 
Tested-by: Vijay Bellur