[
https://issues.apache.org/jira/browse/TIKA-4626?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=18053094#comment-18053094
]
Tim Allison commented on TIKA-4626:
-----------------------------------
If we throw more hardware at it – 2 benchmark threads with 2 pipes clients, we
do better than single threaded legacy, not surprisingly. :D
{noformat}
==========================================================================================
SUMMARY
==========================================================================================
THROUGHPUT (req/s):
small-10 large-10000
short-10ms 86.10 57.73
long-500ms 3.91 3.86
AVG LATENCY (ms):
small-10 large-10000
short-10ms 22.53 34.04
long-500ms 510.29 517.04
P95 LATENCY (ms):
small-10 large-10000
short-10ms 25.00 42.00
long-500ms 514.00 522.00
┌─────────────┬────────────────┬───────────────┬─────────────┐
│ │ Legacy (1t/1c) │ Pipes (2t/2c) │ Improvement │
├─────────────┼────────────────┼───────────────┼─────────────┤
│ short/small │ 63.5 req/s │ 86.1 req/s │ +36% │
├─────────────┼────────────────┼───────────────┼─────────────┤
│ short/large │ 45.0 req/s │ 57.7 req/s │ +28% │
├─────────────┼────────────────┼───────────────┼─────────────┤
│ long/small │ 1.98 req/s │ 3.91 req/s │ +97% │
├─────────────┼────────────────┼───────────────┼─────────────┤
│ long/large │ 1.96 req/s │ 3.86 req/s │ +97% │
└─────────────┴────────────────┴───────────────┴─────────────┘
{noformat}
> Consider using tika-pipes in the backend for /rmeta and /tika endpoints i n4.x
> ------------------------------------------------------------------------------
>
> Key: TIKA-4626
> URL: https://issues.apache.org/jira/browse/TIKA-4626
> Project: Tika
> Issue Type: Task
> Components: tika-server
> Reporter: Tim Allison
> Priority: Major
> Attachments: tika-pipes-integration-plan.md
>
>
> In 4.x, we're consolidating the forking options to pipes parser. We've
> removed the "fork the entire server" option in main. We should consider
> swapping in tika pipes, writing to a tmp file, for /rmeta and /tika.
> This will prevent the entire server going down on oom, etc.
> If users want crashability, perhaps we add back in a /tika-legacy endpoint?
> I'm attaching the plan that I worked out with claude.
> We can do the same for /meta and /unpack on a separate ticket.
> Any concerns?
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
