* [lttng-dev] cds_lfht_resize() and QSBR @ 2015-07-27 16:03 Eugene Ivanov 2015-07-27 17:12 ` Mathieu Desnoyers 0 siblings, 1 reply; 3+ messages in thread From: Eugene Ivanov @ 2015-07-27 16:03 UTC (permalink / raw) Hi, According documentation "cds_lfht_resize should *not* be called from a RCU read-side critical section", can I use this function with QSBR, where almost everything is read-side CS? And cds_lfht_destroy()? -- Eugene Ivanov ________________________________ This e-mail is confidential and may contain legally privileged information. It is intended only for the addressees. If you have received this e-mail in error, kindly notify us immediately by telephone or e-mail and delete the message from your system. ^ permalink raw reply [flat|nested] 3+ messages in thread
* [lttng-dev] cds_lfht_resize() and QSBR 2015-07-27 16:03 [lttng-dev] cds_lfht_resize() and QSBR Eugene Ivanov @ 2015-07-27 17:12 ` Mathieu Desnoyers 2015-07-27 17:20 ` Eugene Ivanov 0 siblings, 1 reply; 3+ messages in thread From: Mathieu Desnoyers @ 2015-07-27 17:12 UTC (permalink / raw) Hi Eugene, It's fine to use both lfht resize and destroy from URCU QSBR, because we explicitly mark the threads "offline" (saving the old state), and restore the original state, at the beginning and end of those functions. However, calls to cds_lfht_resize() and cds_lfht_destroy are considered as an explicit quiescent state in URCU QSBR, therefore, don't expect your RCU read-side critical section to extend across those 2 calls. Thanks, Mathieu ----- On Jul 27, 2015, at 12:03 PM, Eugene Ivanov Eugene.Ivanov at orc-group.com wrote: > Hi, > > According documentation "cds_lfht_resize should *not* be called from a > RCU read-side critical section", can I use this function with QSBR, > where almost everything is read-side CS? And cds_lfht_destroy()? > > -- > Eugene Ivanov > > > ________________________________ > > This e-mail is confidential and may contain legally privileged information. It > is intended only for the addressees. If you have received this e-mail in error, > kindly notify us immediately by telephone or e-mail and delete the message from > your system. > > _______________________________________________ > lttng-dev mailing list > lttng-dev at lists.lttng.org > http://lists.lttng.org/cgi-bin/mailman/listinfo/lttng-dev -- Mathieu Desnoyers EfficiOS Inc. http://www.efficios.com ^ permalink raw reply [flat|nested] 3+ messages in thread
* [lttng-dev] cds_lfht_resize() and QSBR 2015-07-27 17:12 ` Mathieu Desnoyers @ 2015-07-27 17:20 ` Eugene Ivanov 0 siblings, 0 replies; 3+ messages in thread From: Eugene Ivanov @ 2015-07-27 17:20 UTC (permalink / raw) Thank you, Mathieu! On 07/27/2015 08:12 PM, Mathieu Desnoyers wrote: > Hi Eugene, > > It's fine to use both lfht resize and destroy from URCU QSBR, because > we explicitly mark the threads "offline" (saving the old state), > and restore the original state, at the beginning and end of those > functions. > > However, calls to cds_lfht_resize() and cds_lfht_destroy are considered > as an explicit quiescent state in URCU QSBR, therefore, don't expect > your RCU read-side critical section to extend across those 2 calls. > > Thanks, > > Mathieu > > ----- On Jul 27, 2015, at 12:03 PM, Eugene Ivanov Eugene.Ivanov at orc-group.com wrote: > >> Hi, >> >> According documentation "cds_lfht_resize should *not* be called from a >> RCU read-side critical section", can I use this function with QSBR, >> where almost everything is read-side CS? And cds_lfht_destroy()? >> >> -- >> Eugene Ivanov >> >> >> ________________________________ >> >> This e-mail is confidential and may contain legally privileged information. It >> is intended only for the addressees. If you have received this e-mail in error, >> kindly notify us immediately by telephone or e-mail and delete the message from >> your system. >> >> _______________________________________________ >> lttng-dev mailing list >> lttng-dev at lists.lttng.org >> http://lists.lttng.org/cgi-bin/mailman/listinfo/lttng-dev -- Eugene Ivanov ________________________________ This e-mail is confidential and may contain legally privileged information. It is intended only for the addressees. If you have received this e-mail in error, kindly notify us immediately by telephone or e-mail and delete the message from your system. ^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2015-07-27 17:20 UTC | newest] Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed) -- links below jump to the message on this page -- 2015-07-27 16:03 [lttng-dev] cds_lfht_resize() and QSBR Eugene Ivanov 2015-07-27 17:12 ` Mathieu Desnoyers 2015-07-27 17:20 ` Eugene Ivanov
This is a public inbox, see mirroring instructions for how to clone and mirror all data and code used for this inbox