summaryrefslogtreecommitdiffstats
path: root/xlators/cluster/dht/src/tier.h
Commit message (Collapse)AuthorAgeFilesLines
* cluster/tier: handle fast demotionsMilind Changire2016-10-191-1/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | 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 <mchangir@redhat.com> Reviewed-on: http://review.gluster.org/15158 Smoke: Gluster Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.org> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> Reviewed-by: Dan Lambright <dlambrig@redhat.com>
* cluster/tier: Adding compaction option for metadata databasesDiogenes Nunez2016-09-041-0/+6
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | 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 <vol-name> tier-compact <off|on> - Added the following command-line option to change the frequency the hot and cold tier are ordered to compact. gluster volume set <vol-name> tier-hot-compact-frequency <int> gluster volume set <vol-name> tier-cold-compact-frequency <int> - 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 <dnunez@redhat.com> Reviewed-on: http://review.gluster.org/15031 Reviewed-by: Milind Changire <mchangir@redhat.com> Reviewed-by: Dan Lambright <dlambrig@redhat.com> Tested-by: Dan Lambright <dlambrig@redhat.com> CentOS-regression: Gluster Build System <jenkins@build.gluster.org> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> Smoke: Gluster Build System <jenkins@build.gluster.org>
* cluster/tier: make promotion and demotion independantDan Lambright2016-02-281-1/+2
| | | | | | | | | | | | | | | | | | | | Currently a main loop in tiering spawns promotion and demotion threads, and does a join to wait for them to complete. When one of the two threads takes a long time, the main thread waits for it before exiting the join. It may wait so long the scheduled time for the other thread is skipped. In the case of demotion, it may be a long time before another attempt. This patch fixes that by making the promotion and demotion activities independant. A side effect of this change is the logic is significantly simplified. Change-Id: I1196bd4bbfc95e8aa326a9bd4ebf395032369d1c BUG: 1306852 Signed-off-by: Dan Lambright <dlambrig@redhat.com> Reviewed-on: http://review.gluster.org/13433 Smoke: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Joseph Fernandes NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.com>
* tier/gfdb : Round-Robin read of query filesJoseph Fernandes2016-02-031-6/+20
| | | | | | | | | | | | | | | | | | | 1. Each brick on a host will get a separate query file. 2. While reading query record from these query files we read them in a Round-Robin manner. 3. When an error occurs during migration we rename it to query file with an time stamp and .err extension for better debugging. Change-Id: I27c4285d24fd695d2d5cbd9fd7db3879d277ecc8 BUG: 1302772 Signed-off-by: Joseph Fernandes <josferna@redhat.com> Reviewed-on: http://review.gluster.org/13293 Smoke: Gluster Build System <jenkins@build.gluster.com> Tested-by: N Balachandran <nbalacha@redhat.com> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> Reviewed-by: Dan Lambright <dlambrig@redhat.com> CentOS-regression: Gluster Build System <jenkins@build.gluster.com>
* cluster/tier: readdirp to cold tier onlyDan Lambright2015-11-231-1/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | It is possible a file would get migrated in the middle of a readdir operation. If there are four subvolumes A,B,C,D, and if readdir reads them in order and reaches subvol B, then, if a file is moved from D to A, it will not be included in the readdir output. This phenonema has pre-existed in DHT migration but is more apparent in tiering. When a file is moved off the hashed subvolume a T file is created. For tiering, we will make the cold subvolume the hashed subvolume. This will ensure the creation of a T file. Readdir will not skip T files in the tier translator. Making the cold subvolume the hashed subvolume ensures the T files created on promotions or creates will be less likely to fill the volume. Creates still put the data on the hot subvolume. Change-Id: Ifde557d3d0e94a4570ca9f115adee3db2ee75407 BUG: 1281598 Signed-off-by: Dan Lambright <dlambrig@redhat.com> Reviewed-on: http://review.gluster.org/12530 Tested-by: Gluster Build System <jenkins@build.gluster.com> Tested-by: NetBSD Build System <jenkins@build.gluster.org> Reviewed-by: N Balachandran <nbalacha@redhat.com> Reviewed-by: Raghavendra G <rgowdapp@redhat.com>
* cluster/tier: Do not delete linkto file on demotionN Balachandran2015-11-181-0/+2
| | | | | | | | | | | | | | | | | The current DHT migration code will always delete the src linkto file after migration as dht always moves files to the hashed subvol. This is not the case in tiering. The lack of linkto files causes rename to fail leaving 2 files with the same name but different gfids on the volume. Modified to leave the linkto file behind if the source volume is the hashed subvolume. Change-Id: I2b99f7d34b4b719aee6232dc40c6a8f8ba88225d BUG: 1279376 Signed-off-by: N Balachandran <nbalacha@redhat.com> Reviewed-on: http://review.gluster.org/12551 Reviewed-by: Dan Lambright <dlambrig@redhat.com> Tested-by: Dan Lambright <dlambrig@redhat.com>
* tier/libgfdb: Replacing ASCII query file with binaryJoseph Fernandes2015-11-061-3/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | 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 | <LINK INFO> |..... | FOOTER | +---------------------------------------------------------------------------+ 16 B 4 B Link Length 4 B | | | | -----------------------------| | | | | | V | Each <Link Info> 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 <josferna@redhat.com> Reviewed-on: http://review.gluster.org/12354 Reviewed-by: N Balachandran <nbalacha@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Dan Lambright <dlambrig@redhat.com> Tested-by: Dan Lambright <dlambrig@redhat.com>
* cluster/tier: add watermarks and policy driverDan Lambright2015-10-101-5/+19
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This fix introduces infrastructure to support different policies for promotion and demotion. Currently the tier feature automatically promotes and demotes files periodically based on access. This is good for testing but too stringent for most real workloads. It makes it difficult to fully utilize a hot tier- data will be demoted before it is touched- its unlikely a 100GB hot SSD will have all its data touched in a window of time. A new parameter "mode" allows the user to pick promotion/demotion polcies. The "test mode" will be used for *.t and other general testing. This is the current mechanism. The "cache mode" introduces watermarks. The watermarks represent levels of data residing on the hot tier. "cache mode" policy: The % the hot tier is full is called P. Do not promote or demote more than D MB or F files. A random number [0-100] is called R. Rules for migration: if (P < watermark_low) don't demote, always promote. if (P >= watermark_low) && (P < watermark_hi) demote if R < P; promote if R > P. if (P > watermark_hi) always demote, don't promote. gluster volume set {vol} cluster.watermark-hi % gluster volume set {vol} cluster.watermark-low % gluster volume set {vol} cluster.tier-max-mb {D} gluster volume set {vol} cluster.tier-max-files {F} gluster volume set {vol} cluster.tier-mode {test|cache} Change-Id: I157f19667ec95aa1d53406041c1e3b073be127c2 BUG: 1257911 Signed-off-by: Dan Lambright <dlambrig@redhat.com> Reviewed-on: http://review.gluster.org/12039 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Atin Mukherjee <amukherj@redhat.com>
* cluster/tier fix bug with sql includes introduced by 12031Dan Lambright2015-09-111-1/+0
| | | | | | | | | | | | We accidentally introduced a bug where client translators have a dependency on sql. This broke freebsd smoke tests. Fix is to abstract from the client those dependencies. Change-Id: I7152573a489bacc8f32e6eb139f9ff4408288f5b BUG: 1260730 Signed-off-by: Dan Lambright <dlambrig@redhat.com> Reviewed-on: http://review.gluster.org/12155 Tested-by: NetBSD Build System <jenkins@build.gluster.org>
* tier/ctr: Solving DB Lock issue due to write contention from db connectionsJoseph Fernandes2015-09-081-1/+8
| | | | | | | | | | | | | | | | | | | | | | | 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 <josferna@redhat.com> Reviewed-on: http://review.gluster.org/12031 Tested-by: NetBSD Build System <jenkins@build.gluster.org> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Dan Lambright <dlambrig@redhat.com> Tested-by: Dan Lambright <dlambrig@redhat.com>
* tier/ctr: Ignore creation of T file and Ctr Lookup heal improvememntsJoseph Fernandes2015-06-261-3/+2
| | | | | | | | | | | | | | | | | | 1) Ignore creation of T file in ctr_mknod 2) Ignore lookup for T file in ctr_lookup 3) Ctr_lookup: a. If the gfid and pgfid in empty dont record b. Decreased log level for multiple heal attempts c. Inode/File heal happens after an expiry period, which is configurable. d. Hardlink heal happens after an expiry period, which is configurable. Change-Id: Id8eb5092e78beaec22d05f5283645081619e2452 BUG: 1235269 Signed-off-by: Joseph Fernandes <josferna@redhat.com> Reviewed-on: http://review.gluster.org/11334 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Dan Lambright <dlambrig@redhat.com> Tested-by: Dan Lambright <dlambrig@redhat.com>
* build: do not #include "config.h" in each fileNiels de Vos2015-05-291-5/+0
| | | | | | | | | | | | | | | | | | 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 <ndevos@redhat.com> Reviewed-on: http://review.gluster.org/10808 Tested-by: Gluster Build System <jenkins@build.gluster.com> Tested-by: NetBSD Build System Reviewed-by: Kaleb KEITHLEY <kkeithle@redhat.com> Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com>
* glusterd: Support distributed replicated volumes on hot tierDan Lambright2015-04-081-0/+1
| | | | | | | | | | | | | | We did not set up the graph properly for hot tiers with replicated subvolumes. Also add check that the file has not already been moved by another replicated brick on the same node. Change-Id: I9adef565ab60f6774810962d912168b77a6032fa BUG: 1206517 Signed-off-by: Dan Lambright <dlambrig@redhat.com> Reviewed-on: http://review.gluster.org/10054 Reviewed-by: Joseph Fernandes <josferna@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Kaleb KEITHLEY <kkeithle@redhat.com>
* cluster/dht: fix tier.c problems found prior to feature freezeDan Lambright2015-04-061-4/+6
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch resolves tiering translator issues taken from the list in bug 1203776. These issues have been selected to be fixed first. The rest will be fixed in a subsequent patch (or are not a problem). 3. Replace hardcoded #defines of promote/demote file names 6. Use loc_wipe() in migrate_using_query_file() 9. Only promote/demote files on the same node on which they reside. 14. Replace calloc with GF_CALLOC in tier.c and ensure freeing done properly. 15. Handle if parse_query_str fails 22. Only load gfdb library on server side, remove SQL references from client. Change-Id: I6563b11e58ab2e4c6b1ce44db755781ad6d930fb BUG: 1203776 Signed-off-by: Dan Lambright <dlambrig@redhat.com> Reviewed-on: http://review.gluster.org/9987 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: N Balachandran <nbalacha@redhat.com> Reviewed-by: Niels de Vos <ndevos@redhat.com>
* build: tier.h does not need to include sys/xattr.hNiels de Vos2015-03-231-1/+0
| | | | | | | | | | | | | FreeBSD does not have sys/xattr.h, including it in tier.h breaks building on FreeBSD. There is nothing in tier.h that seems to require definitions from the sys/xattr.h header, just remove it. BUG: 1194753 Change-Id: If970272a0ce7728e0f18e5ae026880688ac31408 Signed-off-by: Niels de Vos <ndevos@redhat.com> Reviewed-on: http://review.gluster.org/9965 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Sachin Pandit <spandit@redhat.com>
* cluster/dht: Add tier translator.Dan Lambright2015-03-211-0/+71
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 <dlambrig@redhat.com> Reviewed-on: http://review.gluster.org/9724 Reviewed-by: Vijay Bellur <vbellur@redhat.com> Tested-by: Vijay Bellur <vbellur@redhat.com>
generated by cgit (git 2.34.1) at 2024-05-01 09:54:35 +0000