[jira] [Updated] (IGNITE-7998) SQL: Improve MVCC vacuum performance by iterating over data pages instead of cache tree.
[ https://issues.apache.org/jira/browse/IGNITE-7998?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Vladimir Ozerov updated IGNITE-7998: Component/s: (was: sql) > SQL: Improve MVCC vacuum performance by iterating over data pages instead of > cache tree. > - > > Key: IGNITE-7998 > URL: https://issues.apache.org/jira/browse/IGNITE-7998 > Project: Ignite > Issue Type: Improvement > Components: mvcc >Reporter: Roman Kondakov >Priority: Major > > At the moment vacuum process uses cache trees to find outdated (dead) entries > and cache and index trees to cleanup them. It is not efficient due to several > reasons. For example, we should lock a datapage for each cache tree entry to > find out if entry is dead. > We can consider a direct iteration over datapages as a possible improvement > of the vacuum process. Data page iteration prototype demonstrated 5-10 times > time improvement over the tree iteration. > At first stage we need to implement direct datapages iteration only for > collecting dead entries links. > At the second stage we need to consider removing links to dead entries from > index pages directly. In other words, we need to efficiently remove batches > of dead links from indexes without traversing cache and index tree one dead > link by one. -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Updated] (IGNITE-7998) SQL: Improve MVCC vacuum performance by iterating over data pages instead of cache tree.
[ https://issues.apache.org/jira/browse/IGNITE-7998?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Vladimir Ozerov updated IGNITE-7998: Component/s: mvcc > SQL: Improve MVCC vacuum performance by iterating over data pages instead of > cache tree. > - > > Key: IGNITE-7998 > URL: https://issues.apache.org/jira/browse/IGNITE-7998 > Project: Ignite > Issue Type: Improvement > Components: mvcc, sql >Reporter: Roman Kondakov >Priority: Major > > At the moment vacuum process uses cache trees to find outdated (dead) entries > and cache and index trees to cleanup them. It is not efficient due to several > reasons. For example, we should lock a datapage for each cache tree entry to > find out if entry is dead. > We can consider a direct iteration over datapages as a possible improvement > of the vacuum process. Data page iteration prototype demonstrated 5-10 times > time improvement over the tree iteration. > At first stage we need to implement direct datapages iteration only for > collecting dead entries links. > At the second stage we need to consider removing links to dead entries from > index pages directly. In other words, we need to efficiently remove batches > of dead links from indexes without traversing cache and index tree one dead > link by one. -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Updated] (IGNITE-7998) SQL: Improve MVCC vacuum performance by iterating over data pages instead of cache tree.
[ https://issues.apache.org/jira/browse/IGNITE-7998?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Vladimir Ozerov updated IGNITE-7998: Labels: (was: iep-3) > SQL: Improve MVCC vacuum performance by iterating over data pages instead of > cache tree. > - > > Key: IGNITE-7998 > URL: https://issues.apache.org/jira/browse/IGNITE-7998 > Project: Ignite > Issue Type: Improvement > Components: mvcc, sql >Reporter: Roman Kondakov >Priority: Major > > At the moment vacuum process uses cache trees to find outdated (dead) entries > and cache and index trees to cleanup them. It is not efficient due to several > reasons. For example, we should lock a datapage for each cache tree entry to > find out if entry is dead. > We can consider a direct iteration over datapages as a possible improvement > of the vacuum process. Data page iteration prototype demonstrated 5-10 times > time improvement over the tree iteration. > At first stage we need to implement direct datapages iteration only for > collecting dead entries links. > At the second stage we need to consider removing links to dead entries from > index pages directly. In other words, we need to efficiently remove batches > of dead links from indexes without traversing cache and index tree one dead > link by one. -- This message was sent by Atlassian JIRA (v7.6.3#76005)