Skip to contentSkip to conversation

How much shared memory is used by LTTng (UST) ?

DISCUSSION Michel Dagenais 2 participants 2 messages Jul 11, 2013 2 messages not in the archive

lore
Share & tools
lore
#1 lore raw
In reply to a message not in the archive
Quoted 6 lines
Quoted 4 lines

It still doesn't explain why I was able to add procname to the context but adding also vpid and vtid failed when the number of cores was 24 rather than 12.

No idea. These are unrelated.

Perhaps you were not tracing that much and not filling all buffers with the smaller events with less context? The kernel buffers are probably pre-allocated for real but other buffers in user-space may not.

#3 lore raw
In reply to a message not in the archive

Thanks for all the answers. I've now increased out SHM area size and the problem disappeared.

Amit Margalit
IBM XIV - Storage Reinvented
XIV-NAS Development Team
Tel. 03-689-7774
Fax. 03-689-7230

From:   Michel Dagenais <[email protected]>
To:     Mathieu Desnoyers <[email protected]>
Cc [email protected], Amit Margalit/Israel/IBM@IBMIL
Date:   07/11/2013 05:35 PM
Subject:        Re: [lttng-dev] How much shared memory is used by LTTng 

(UST) ?

Quoted 2 lines
Quoted 2 lines

It still doesn't explain why I was able to add procname to the context but adding also vpid and vtid failed when the number of cores

was 24

Quoted 3 lines
Quoted 1 line

rather than 12.

No idea. These are unrelated.

Perhaps you were not tracing that much and not filling all buffers with the smaller events with less context? The kernel buffers are probably pre-allocated for real but other buffers in user-space may not.

_______________________________________________
lttng-dev mailing list
[email protected]
http://lists.lttng.org/cgi-bin/mailman/listinfo/lttng-dev