[jira] [Commented] (CASSANDRA-9197) Startup slowdown due to preloading jemalloc
[ https://issues.apache.org/jira/browse/CASSANDRA-9197?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14538002#comment-14538002 ] Philip Thompson commented on CASSANDRA-9197: [~snazy], +1 to the patch. Startup slowdown due to preloading jemalloc --- Key: CASSANDRA-9197 URL: https://issues.apache.org/jira/browse/CASSANDRA-9197 Project: Cassandra Issue Type: Bug Reporter: Sylvain Lebresne Assignee: Robert Stupp Priority: Minor Fix For: 3.x Attachments: 9197.txt On my box, it seems that the jemalloc loading from CASSANDRA-8714 made the process take ~10 seconds to even start (I have no explication for it). I don't know if it's specific to my machine or not, so that ticket is mainly so someone else can check if it sees the same, in particular for jenkins. If it does sees the same slowness, we might want to at least disable jemalloc for dtests. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (CASSANDRA-9197) Startup slowdown due to preloading jemalloc
[ https://issues.apache.org/jira/browse/CASSANDRA-9197?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14536362#comment-14536362 ] Robert Stupp commented on CASSANDRA-9197: - ping [~philipthompson] ;) Startup slowdown due to preloading jemalloc --- Key: CASSANDRA-9197 URL: https://issues.apache.org/jira/browse/CASSANDRA-9197 Project: Cassandra Issue Type: Bug Reporter: Sylvain Lebresne Assignee: Robert Stupp Priority: Minor Fix For: 3.x Attachments: 9197.txt On my box, it seems that the jemalloc loading from CASSANDRA-8714 made the process take ~10 seconds to even start (I have no explication for it). I don't know if it's specific to my machine or not, so that ticket is mainly so someone else can check if it sees the same, in particular for jenkins. If it does sees the same slowness, we might want to at least disable jemalloc for dtests. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (CASSANDRA-9197) Startup slowdown due to preloading jemalloc
[ https://issues.apache.org/jira/browse/CASSANDRA-9197?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14536616#comment-14536616 ] Philip Thompson commented on CASSANDRA-9197: Sorry, [~snazy], I never got the email notication for this. I'll check it out on Monday. Startup slowdown due to preloading jemalloc --- Key: CASSANDRA-9197 URL: https://issues.apache.org/jira/browse/CASSANDRA-9197 Project: Cassandra Issue Type: Bug Reporter: Sylvain Lebresne Assignee: Robert Stupp Priority: Minor Fix For: 3.x Attachments: 9197.txt On my box, it seems that the jemalloc loading from CASSANDRA-8714 made the process take ~10 seconds to even start (I have no explication for it). I don't know if it's specific to my machine or not, so that ticket is mainly so someone else can check if it sees the same, in particular for jenkins. If it does sees the same slowness, we might want to at least disable jemalloc for dtests. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (CASSANDRA-9197) Startup slowdown due to preloading jemalloc
[ https://issues.apache.org/jira/browse/CASSANDRA-9197?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14504542#comment-14504542 ] Sylvain Lebresne commented on CASSANDRA-9197: - bq. hardcoding the path as you stated does improve the startup time Out of curiosity, does it make it like without jemalloc? In other words, is it the {{find_library}} method that improve the startup time, or is it both that and loading jemalloc? Startup slowdown due to preloading jemalloc --- Key: CASSANDRA-9197 URL: https://issues.apache.org/jira/browse/CASSANDRA-9197 Project: Cassandra Issue Type: Bug Reporter: Sylvain Lebresne Assignee: Philip Thompson Priority: Minor On my box, it seems that the jemalloc loading from CASSANDRA-8714 made the process take ~10 seconds to even start (I have no explication for it). I don't know if it's specific to my machine or not, so that ticket is mainly so someone else can check if it sees the same, in particular for jenkins. If it does sees the same slowness, we might want to at least disable jemalloc for dtests. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (CASSANDRA-9197) Startup slowdown due to preloading jemalloc
[ https://issues.apache.org/jira/browse/CASSANDRA-9197?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14504676#comment-14504676 ] Sylvain Lebresne commented on CASSANDRA-9197: - Yes, the attached patch does seem to solve the problem. Haven't reviewed the patch more than that however. Startup slowdown due to preloading jemalloc --- Key: CASSANDRA-9197 URL: https://issues.apache.org/jira/browse/CASSANDRA-9197 Project: Cassandra Issue Type: Bug Reporter: Sylvain Lebresne Assignee: Philip Thompson Priority: Minor Attachments: 9197.txt On my box, it seems that the jemalloc loading from CASSANDRA-8714 made the process take ~10 seconds to even start (I have no explication for it). I don't know if it's specific to my machine or not, so that ticket is mainly so someone else can check if it sees the same, in particular for jenkins. If it does sees the same slowness, we might want to at least disable jemalloc for dtests. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (CASSANDRA-9197) Startup slowdown due to preloading jemalloc
[ https://issues.apache.org/jira/browse/CASSANDRA-9197?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14504642#comment-14504642 ] Robert Stupp commented on CASSANDRA-9197: - It seems that the {{find_library}} method causes the slowdown. I've got some patch ready but want to check it first. Startup slowdown due to preloading jemalloc --- Key: CASSANDRA-9197 URL: https://issues.apache.org/jira/browse/CASSANDRA-9197 Project: Cassandra Issue Type: Bug Reporter: Sylvain Lebresne Assignee: Philip Thompson Priority: Minor On my box, it seems that the jemalloc loading from CASSANDRA-8714 made the process take ~10 seconds to even start (I have no explication for it). I don't know if it's specific to my machine or not, so that ticket is mainly so someone else can check if it sees the same, in particular for jenkins. If it does sees the same slowness, we might want to at least disable jemalloc for dtests. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (CASSANDRA-9197) Startup slowdown due to preloading jemalloc
[ https://issues.apache.org/jira/browse/CASSANDRA-9197?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14503229#comment-14503229 ] Philip Thompson commented on CASSANDRA-9197: [~snazy], as discussed on IRC. I only notice this problem at the magnitude Brandon or Sylvain are mentioning on linux, not OSX. With Linux, installing jemalloc and then hardcoding the path as you stated does improve the startup time. Startup slowdown due to preloading jemalloc --- Key: CASSANDRA-9197 URL: https://issues.apache.org/jira/browse/CASSANDRA-9197 Project: Cassandra Issue Type: Bug Reporter: Sylvain Lebresne Assignee: Philip Thompson Priority: Minor On my box, it seems that the jemalloc loading from CASSANDRA-8714 made the process take ~10 seconds to even start (I have no explication for it). I don't know if it's specific to my machine or not, so that ticket is mainly so someone else can check if it sees the same, in particular for jenkins. If it does sees the same slowness, we might want to at least disable jemalloc for dtests. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (CASSANDRA-9197) Startup slowdown due to preloading jemalloc
[ https://issues.apache.org/jira/browse/CASSANDRA-9197?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14498521#comment-14498521 ] Brandon Williams commented on CASSANDRA-9197: - Also compounding this is after CASSANDRA-7254 we're launching the JVM twice. Startup slowdown due to preloading jemalloc --- Key: CASSANDRA-9197 URL: https://issues.apache.org/jira/browse/CASSANDRA-9197 Project: Cassandra Issue Type: Bug Reporter: Sylvain Lebresne Assignee: Philip Thompson Priority: Minor On my box, it seems that the jemalloc loading from CASSANDRA-8714 made the process take ~10 seconds to even start (I have no explication for it). I don't know if it's specific to my machine or not, so that ticket is mainly so someone else can check if it sees the same, in particular for jenkins. If it does sees the same slowness, we might want to at least disable jemalloc for dtests. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (CASSANDRA-9197) Startup slowdown due to preloading jemalloc
[ https://issues.apache.org/jira/browse/CASSANDRA-9197?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14498447#comment-14498447 ] Robert Stupp commented on CASSANDRA-9197: - jemalloc affects all allocations (including all off-heap allocations) It might be possible that the shell script code in {{conf/cassandra-env.sh}} gets slower since the {{find_library}} might be a bit inefficient. [~philipthompson] can you try to let {{conf/cassandra-env.sh}} skip the find the jemalloc lib code and hard-code {{CASSANDRA_LIBJEMALLOC}} and see if that mitigates the problem? Startup slowdown due to preloading jemalloc --- Key: CASSANDRA-9197 URL: https://issues.apache.org/jira/browse/CASSANDRA-9197 Project: Cassandra Issue Type: Bug Reporter: Sylvain Lebresne Assignee: Philip Thompson Priority: Minor On my box, it seems that the jemalloc loading from CASSANDRA-8714 made the process take ~10 seconds to even start (I have no explication for it). I don't know if it's specific to my machine or not, so that ticket is mainly so someone else can check if it sees the same, in particular for jenkins. If it does sees the same slowness, we might want to at least disable jemalloc for dtests. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (CASSANDRA-9197) Startup slowdown due to preloading jemalloc
[ https://issues.apache.org/jira/browse/CASSANDRA-9197?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14497079#comment-14497079 ] Sylvain Lebresne commented on CASSANDRA-9197: - So I guess we should definitively disable it for the tests. It's probably also a tad annoying when developing/testing too however, so I guess one question could be if we want to disable jemalloc by default and let people enable it if they actually use the row cache. I don't care too much either way though. Startup slowdown due to preloading jemalloc --- Key: CASSANDRA-9197 URL: https://issues.apache.org/jira/browse/CASSANDRA-9197 Project: Cassandra Issue Type: Bug Reporter: Sylvain Lebresne Assignee: Philip Thompson Priority: Minor On my box, it seems that the jemalloc loading from CASSANDRA-8714 made the process take ~10 seconds to even start (I have no explication for it). I don't know if it's specific to my machine or not, so that ticket is mainly so someone else can check if it sees the same, in particular for jenkins. If it does sees the same slowness, we might want to at least disable jemalloc for dtests. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (CASSANDRA-9197) Startup slowdown due to preloading jemalloc
[ https://issues.apache.org/jira/browse/CASSANDRA-9197?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14497093#comment-14497093 ] Jonathan Ellis commented on CASSANDRA-9197: --- Doesn't jemalloc affect all off-heap allocations, or is it really just row cache? Startup slowdown due to preloading jemalloc --- Key: CASSANDRA-9197 URL: https://issues.apache.org/jira/browse/CASSANDRA-9197 Project: Cassandra Issue Type: Bug Reporter: Sylvain Lebresne Assignee: Philip Thompson Priority: Minor On my box, it seems that the jemalloc loading from CASSANDRA-8714 made the process take ~10 seconds to even start (I have no explication for it). I don't know if it's specific to my machine or not, so that ticket is mainly so someone else can check if it sees the same, in particular for jenkins. If it does sees the same slowness, we might want to at least disable jemalloc for dtests. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (CASSANDRA-9197) Startup slowdown due to preloading jemalloc
[ https://issues.apache.org/jira/browse/CASSANDRA-9197?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14497050#comment-14497050 ] Philip Thompson commented on CASSANDRA-9197: It's less pronounced for me, but yes I also see it. Should I then change this to a test ticket about disabling jemalloc for dtests? Startup slowdown due to preloading jemalloc --- Key: CASSANDRA-9197 URL: https://issues.apache.org/jira/browse/CASSANDRA-9197 Project: Cassandra Issue Type: Bug Reporter: Sylvain Lebresne Assignee: Philip Thompson Priority: Minor On my box, it seems that the jemalloc loading from CASSANDRA-8714 made the process take ~10 seconds to even start (I have no explication for it). I don't know if it's specific to my machine or not, so that ticket is mainly so someone else can check if it sees the same, in particular for jenkins. If it does sees the same slowness, we might want to at least disable jemalloc for dtests. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (CASSANDRA-9197) Startup slowdown due to preloading jemalloc
[ https://issues.apache.org/jira/browse/CASSANDRA-9197?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14497032#comment-14497032 ] Brandon Williams commented on CASSANDRA-9197: - I too see this on my test cluster. Trunk takes about 4s on startup before any text is printed where 2.1 takes less than a second. Startup slowdown due to preloading jemalloc --- Key: CASSANDRA-9197 URL: https://issues.apache.org/jira/browse/CASSANDRA-9197 Project: Cassandra Issue Type: Bug Reporter: Sylvain Lebresne Assignee: Philip Thompson Priority: Minor On my box, it seems that the jemalloc loading from CASSANDRA-8714 made the process take ~10 seconds to even start (I have no explication for it). I don't know if it's specific to my machine or not, so that ticket is mainly so someone else can check if it sees the same, in particular for jenkins. If it does sees the same slowness, we might want to at least disable jemalloc for dtests. -- This message was sent by Atlassian JIRA (v6.3.4#6332)