diff for duplicates of <1491590377.2559.22.camel@sandisk.com> diff --git a/a/1.txt b/N1/1.txt index fa98502..04d97d1 100644 --- a/a/1.txt +++ b/N1/1.txt @@ -2,40 +2,32 @@ On Fri, 2017-04-07 at 11:33 -0700, Bart Van Assche wrote: > On Fri, 2017-04-07 at 12:23 -0600, Jens Axboe wrote: > > On 04/07/2017 12:16 PM, Bart Van Assche wrote: > > > Hello Jens, -> > >=20 +> > > > > > The six patches in this patch series fix the queue lockup I reported -> > > recently on the linux-block mailing list. Please consider these patch= -es +> > > recently on the linux-block mailing list. Please consider these patches > > > for inclusion in the upstream kernel. -> >=20 -> > Some of this we need in 4.11, but not all of it. I can't be applying pa= -tches +> > +> > Some of this we need in 4.11, but not all of it. I can't be applying patches > > that "improve scalability" at this point. -> >=20 -> > 4-6 looks like what we want for 4.11, I'll see if those apply directly.= - Then +> > +> > 4-6 looks like what we want for 4.11, I'll see if those apply directly. Then > > we can put 1-3 on top in 4.12, with the others pulled in first. ->=20 +> > Hello Jens, ->=20 +> > Please note that patch 2/6 is a bug fix. The current implementation of -> blk_mq_sched_restart_queues() only considers hardware queues associated w= -ith +> blk_mq_sched_restart_queues() only considers hardware queues associated with > the same request queue as the hardware queue that has been passed as an -> argument. If a tag set is shared across request queues - as is the case f= -or -> SCSI - then all request queues that share a tag set with the hctx argumen= -t +> argument. If a tag set is shared across request queues - as is the case for +> SCSI - then all request queues that share a tag set with the hctx argument > must be considered. (replying to my own e-mail) Hello Jens, -If you want I can split that patch into two patches - one that runs all har= -dware -queues with which the tag set is shared and one that switches from rerunnin= -g +If you want I can split that patch into two patches - one that runs all hardware +queues with which the tag set is shared and one that switches from rerunning all hardware queues to one hardware queue. -Bart.= +Bart. diff --git a/a/content_digest b/N1/content_digest index f266878..39372d8 100644 --- a/a/content_digest +++ b/N1/content_digest @@ -13,42 +13,34 @@ "> On Fri, 2017-04-07 at 12:23 -0600, Jens Axboe wrote:\n" "> > On 04/07/2017 12:16 PM, Bart Van Assche wrote:\n" "> > > Hello Jens,\n" - "> > >=20\n" + "> > > \n" "> > > The six patches in this patch series fix the queue lockup I reported\n" - "> > > recently on the linux-block mailing list. Please consider these patch=\n" - "es\n" + "> > > recently on the linux-block mailing list. Please consider these patches\n" "> > > for inclusion in the upstream kernel.\n" - "> >=20\n" - "> > Some of this we need in 4.11, but not all of it. I can't be applying pa=\n" - "tches\n" + "> > \n" + "> > Some of this we need in 4.11, but not all of it. I can't be applying patches\n" "> > that \"improve scalability\" at this point.\n" - "> >=20\n" - "> > 4-6 looks like what we want for 4.11, I'll see if those apply directly.=\n" - " Then\n" + "> > \n" + "> > 4-6 looks like what we want for 4.11, I'll see if those apply directly. Then\n" "> > we can put 1-3 on top in 4.12, with the others pulled in first.\n" - ">=20\n" + "> \n" "> Hello Jens,\n" - ">=20\n" + "> \n" "> Please note that patch 2/6 is a bug fix. The current implementation of\n" - "> blk_mq_sched_restart_queues() only considers hardware queues associated w=\n" - "ith\n" + "> blk_mq_sched_restart_queues() only considers hardware queues associated with\n" "> the same request queue as the hardware queue that has been passed as an\n" - "> argument. If a tag set is shared across request queues - as is the case f=\n" - "or\n" - "> SCSI - then all request queues that share a tag set with the hctx argumen=\n" - "t\n" + "> argument. If a tag set is shared across request queues - as is the case for\n" + "> SCSI - then all request queues that share a tag set with the hctx argument\n" "> must be considered.\n" "\n" "(replying to my own e-mail)\n" "\n" "Hello Jens,\n" "\n" - "If you want I can split that patch into two patches - one that runs all har=\n" - "dware\n" - "queues with which the tag set is shared and one that switches from rerunnin=\n" - "g\n" + "If you want I can split that patch into two patches - one that runs all hardware\n" + "queues with which the tag set is shared and one that switches from rerunning\n" "all hardware queues to one hardware queue.\n" "\n" - Bart.= + Bart. -d5d921c0969ab9a286c1a58daf2ca8d3c0ffe7a8eeec560b62d74131eb031fdc +d7b336c87c26819607e0d0c0474fbf78e51978f80cf06e125a8fa50ea082d723
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.