[
https://issues.apache.org/jira/browse/HBASE-15218?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15134594#comment-15134594
]
stack commented on HBASE-15218:
-------------------------------
Ok. +1 on patch.
I ran a dumb perf compare of before and after and no substantial difference
(with patch seems better?)
Here is one of the runs without patch reading in a single 128MB WAL file...
probably not enough... we need a tool that just keeps reading WALs so we can
perf eval:
{code}
Performance counter stats for './hbase/bin/hbase --config
/home/stack/conf_hbase org.apache.hadoop.hbase.wal.WALPrettyPrinter
hdfs://ve0524.halxg.cloudera.com:8020/hbase/oldWALs/ve0530.halxg.cloudera.com%2C16020%2C1454394831931.default.1454461762891':
28336.328829 task-clock # 1.881 CPUs utilized
30,173 context-switches # 0.001 M/sec
2,985 cpu-migrations # 0.105 K/sec
101,633 page-faults # 0.004 M/sec
63,169,594,844 cycles # 2.229 GHz
<not supported> stalled-cycles-frontend
<not supported> stalled-cycles-backend
106,412,228,062 instructions # 1.68 insns per cycle
20,594,697,237 branches # 726.795 M/sec
186,547,023 branch-misses # 0.91% of all branches
15.063192434 seconds time elapsed
{code}
Here is one of the runs with patch applied:
{code}
Performance counter stats for './hbase/bin/hbase --config
/home/stack/conf_hbase org.apache.hadoop.hbase.wal.WALPrettyPrinter
hdfs://ve0524.halxg.cloudera.com:8020/hbase/oldWALs/ve0530.halxg.cloudera.com%2C16020%2C1454394831931.default.1454461762891':
26333.786232 task-clock # 1.872 CPUs utilized
29,186 context-switches # 0.001 M/sec
1,308 cpu-migrations # 0.050 K/sec
92,888 page-faults # 0.004 M/sec
62,869,624,114 cycles # 2.387 GHz
<not supported> stalled-cycles-frontend
<not supported> stalled-cycles-backend
106,242,745,200 instructions # 1.69 insns per cycle
20,637,432,716 branches # 783.686 M/sec
188,140,240 branch-misses # 0.91% of all branches
14.066822438 seconds time elapsed
{code}
> On RS crash and replay of WAL, loosing all Tags in Cells
> --------------------------------------------------------
>
> Key: HBASE-15218
> URL: https://issues.apache.org/jira/browse/HBASE-15218
> Project: HBase
> Issue Type: Bug
> Components: Recovery, regionserver, security
> Affects Versions: 2.0.0, 0.98.13, 1.0.2, 1.2.0, 1.1.1
> Reporter: Anoop Sam John
> Assignee: Anoop Sam John
> Priority: Blocker
> Fix For: 2.0.0, 1.2.0, 1.3.0, 1.1.4, 1.0.4, 0.98.18
>
> Attachments: HBASE-15218-branch-1.2.patch, HBASE-15218.patch
>
>
> The KeyValueCodec's Decoder makes NoTagsKeyValue. The WalCellCodec also makes
> this Decoder and so while reading Cells after RS crash, we will loose all
> tags in Cells.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
