* [Lustre-devel] lustre-to-LNET API: big non-aligned bulk transfers @ 2009-10-14 15:22 Maxim V. Patlasov 2009-10-14 17:22 ` Eric Barton 0 siblings, 1 reply; 4+ messages in thread From: Maxim V. Patlasov @ 2009-10-14 15:22 UTC (permalink / raw) To: lustre-devel Hi lustre-devel, I'd like to gather some opinions about the following question: Is it allowed or possible for lustre to submit relatively big bulk transfer request (e.g. >512K) to LNET layer when offset in the very first page to fetch bulk data from (on sender side) is not equal to the offset in the very first page to store data (on receiver side)? In the other words - should LNET support such transfers? Thanks in advance, Maxim ^ permalink raw reply [flat|nested] 4+ messages in thread
* [Lustre-devel] lustre-to-LNET API: big non-aligned bulk transfers 2009-10-14 15:22 [Lustre-devel] lustre-to-LNET API: big non-aligned bulk transfers Maxim V. Patlasov @ 2009-10-14 17:22 ` Eric Barton 2009-10-16 16:49 ` Maxim V. Patlasov 0 siblings, 1 reply; 4+ messages in thread From: Eric Barton @ 2009-10-14 17:22 UTC (permalink / raw) To: lustre-devel Maxim, It should support such transfers, but you have to be careful about the number of fragments this can introduce. This issue has already been observed in routers, which buffer LNET message payloads at the same page offset, irrespective of the sender's page offset (of which it has no knowledge). For example, this can force the o2iblnd, if configured to pre-map all memory, to need double the number of RDMA fragments and therefore fail the transfer. Chat with Liang - he knows all about this... Cheers, Eric > -----Original Message----- > From: lustre-devel-bounces at lists.lustre.org [mailto:lustre-devel-bounces at lists.lustre.org] On Behalf Of Maxim V. > Patlasov > Sent: 14 October 2009 8:23 AM > To: lustre-devel at lists.lustre.org > Subject: [Lustre-devel] lustre-to-LNET API: big non-aligned bulk transfers > > Hi lustre-devel, > > I'd like to gather some opinions about the following question: > > Is it allowed or possible for lustre to submit relatively big bulk > transfer request (e.g. >512K) to LNET layer when offset in the very > first page to fetch bulk data from (on sender side) is not equal to the > offset in the very first page to store data (on receiver side)? In the > other words - should LNET support such transfers? > > Thanks in advance, > Maxim > _______________________________________________ > Lustre-devel mailing list > Lustre-devel at lists.lustre.org > http://lists.lustre.org/mailman/listinfo/lustre-devel ^ permalink raw reply [flat|nested] 4+ messages in thread
* [Lustre-devel] lustre-to-LNET API: big non-aligned bulk transfers 2009-10-14 17:22 ` Eric Barton @ 2009-10-16 16:49 ` Maxim V. Patlasov 2009-10-16 18:01 ` jan julian 0 siblings, 1 reply; 4+ messages in thread From: Maxim V. Patlasov @ 2009-10-16 16:49 UTC (permalink / raw) To: lustre-devel Eric, To make things 100% clear - did you answer positively ('It should...') because there are some lustre use-cases for such transfers or just because it would be natural for LNET to support both aligned and not-aligned big bulk transfers? Thanks in advance, Maxim On 10/14/2009 09:22 PM, Eric Barton wrote: > Maxim, > > It should support such transfers, but you have to be careful about > the number of fragments this can introduce. This issue has already > been observed in routers, which buffer LNET message payloads at > the same page offset, irrespective of the sender's page offset (of > which it has no knowledge). For example, this can force the o2iblnd, > if configured to pre-map all memory, to need double the number of RDMA > fragments and therefore fail the transfer. Chat with Liang - he knows > all about this... > > Cheers, > Eric > > >> -----Original Message----- >> From: lustre-devel-bounces at lists.lustre.org [mailto:lustre-devel-bounces at lists.lustre.org] On Behalf Of Maxim V. >> Patlasov >> Sent: 14 October 2009 8:23 AM >> To: lustre-devel at lists.lustre.org >> Subject: [Lustre-devel] lustre-to-LNET API: big non-aligned bulk transfers >> >> Hi lustre-devel, >> >> I'd like to gather some opinions about the following question: >> >> Is it allowed or possible for lustre to submit relatively big bulk >> transfer request (e.g.>512K) to LNET layer when offset in the very >> first page to fetch bulk data from (on sender side) is not equal to the >> offset in the very first page to store data (on receiver side)? In the >> other words - should LNET support such transfers? >> >> Thanks in advance, >> Maxim >> _______________________________________________ >> Lustre-devel mailing list >> Lustre-devel at lists.lustre.org >> http://lists.lustre.org/mailman/listinfo/lustre-devel >> > > -------------- next part -------------- An HTML attachment was scrubbed... URL: <http://lists.lustre.org/pipermail/lustre-devel-lustre.org/attachments/20091016/8219f0ff/attachment.htm> ^ permalink raw reply [flat|nested] 4+ messages in thread
* [Lustre-devel] lustre-to-LNET API: big non-aligned bulk transfers 2009-10-16 16:49 ` Maxim V. Patlasov @ 2009-10-16 18:01 ` jan julian 0 siblings, 0 replies; 4+ messages in thread From: jan julian @ 2009-10-16 18:01 UTC (permalink / raw) To: lustre-devel Just so your aware, the21057 bugzilla's assignment yesterday was as follows. Who can I get to move this forward so that I can exchange messages with someone. People Reporter: pravin shelar <pravin.shelar@sun.com> Assigned To: pravin shelar <pravin.shelar@sun.com> Add CC: CC: Remove selected CCs On Oct 16, 2009, at 8:49 AM, Maxim V. Patlasov wrote: > Eric, > > To make things 100% clear - did you answer positively ('It > should...') because there are some lustre use-cases for such > transfers or just because it would be natural for LNET to support > both aligned and not-aligned big bulk transfers? > > Thanks in advance, > Maxim > > On 10/14/2009 09:22 PM, Eric Barton wrote: >> >> Maxim, >> >> It should support such transfers, but you have to be careful about >> the number of fragments this can introduce. This issue has already >> been observed in routers, which buffer LNET message payloads at >> the same page offset, irrespective of the sender's page offset (of >> which it has no knowledge). For example, this can force the o2iblnd, >> if configured to pre-map all memory, to need double the number of >> RDMA >> fragments and therefore fail the transfer. Chat with Liang - he >> knows >> all about this... >> >> Cheers, >> Eric >> >> >>> -----Original Message----- >>> From: lustre-devel-bounces at lists.lustre.org [mailto:lustre-devel-bounces at lists.lustre.org >>> ] On Behalf Of Maxim V. >>> Patlasov >>> Sent: 14 October 2009 8:23 AM >>> To: lustre-devel at lists.lustre.org >>> Subject: [Lustre-devel] lustre-to-LNET API: big non-aligned bulk >>> transfers >>> >>> Hi lustre-devel, >>> >>> I'd like to gather some opinions about the following question: >>> >>> Is it allowed or possible for lustre to submit relatively big bulk >>> transfer request (e.g. >512K) to LNET layer when offset in the very >>> first page to fetch bulk data from (on sender side) is not equal >>> to the >>> offset in the very first page to store data (on receiver side)? In >>> the >>> other words - should LNET support such transfers? >>> >>> Thanks in advance, >>> Maxim >>> _______________________________________________ >>> Lustre-devel mailing list >>> Lustre-devel at lists.lustre.org >>> http://lists.lustre.org/mailman/listinfo/lustre-devel >>> >> >> > > _______________________________________________ > Lustre-devel mailing list > Lustre-devel at lists.lustre.org > http://lists.lustre.org/mailman/listinfo/lustre-devel -------------- next part -------------- An HTML attachment was scrubbed... URL: <http://lists.lustre.org/pipermail/lustre-devel-lustre.org/attachments/20091016/2b6f7e97/attachment.htm> ^ permalink raw reply [flat|nested] 4+ messages in thread
end of thread, other threads:[~2009-10-16 18:01 UTC | newest] Thread overview: 4+ messages (download: mbox.gz follow: Atom feed -- links below jump to the message on this page -- 2009-10-14 15:22 [Lustre-devel] lustre-to-LNET API: big non-aligned bulk transfers Maxim V. Patlasov 2009-10-14 17:22 ` Eric Barton 2009-10-16 16:49 ` Maxim V. Patlasov 2009-10-16 18:01 ` jan julian
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.