diff for duplicates of <1483358298.3592.52.camel@sandisk.com> diff --git a/a/1.txt b/N1/1.txt index 0b6223a..6a34acf 100644 --- a/a/1.txt +++ b/N1/1.txt @@ -1,15 +1,20 @@ -T24gTW9uLCAyMDE3LTAxLTAyIGF0IDEyOjA2ICswMTAwLCBIYW5uZXMgUmVpbmVja2Ugd3JvdGU6 -DQo+IEhtbS4gQnV0IHRoYXQgd291bGQgYW1vdW50IHRvIGltcGxlbWVudCB5ZXQgYW5vdGhlciBx -dWV1aW5nIG1lY2hhbmlzbQ0KPiB3aXRoaW4gdGhlIGRyaXZlci9tbWMgc3Vic3lzdGVtLCB3b3Vs -ZG4ndCBpdD8NCj4gDQo+IFdoaWNoIGlzLCBpbmNpZGVudGFsbHksIHRoZSBzYW1lIG1ldGhvZCB0 -aGUgUy8zOTAgREFTRCBkcml2ZXIgdXNlcw0KPiBub3dhZGF5czsgcmVwb3J0IGFuIGFyYml0cmFy -eSBxdWV1ZSBkZXB0aCB0byB0aGUgYmxvY2sgbGF5ZXIgYW5kIHF1ZXVlDQo+IGFsbCByZXF1ZXN0 -cyBpbnRlcm5hbGx5IHRvIGJldHRlciBzYXR1cmF0ZSB0aGUgZGV2aWNlLg0KPiANCj4gSG93ZXZl -ciBJJ2QgcmVhbGx5IGxpa2UgdG8gZ2V0IHJpZCBvZiB0aGlzLCBhbmQgdHdlYWsgdGhlIGJsb2Nr -IGxheWVyIHRvDQo+IGhhbmRsZSB0aGVzZSBjYXNlcy4NCg0KSGVsbG8gSGFubmVzLA0KDQpTdWNo -IGZ1bmN0aW9uYWxpdHkgd2lsbCBiZSBhZGRlZCB0byB0aGUgYmxrLW1xIGNvcmUgYXMgcGFydCBv -ZiB0aGUNCmluaXRpYXRpdmUgdG8gYWRkIGJsay1tcSBJL08gc2NoZWR1bGluZyBzdXBwb3J0LiBP -bmUgaW1wbGVtZW50YXRpb24gaGFzIGJlZW4NCnByb3Bvc2VkIGJ5IEplbnMgKGh0dHA6Ly9naXQu -a2VybmVsLmRrL2NnaXQvbGludXgtYmxvY2svbG9nLz9oPWJsay1tcS1zY2hlZCkNCmFuZCBhbm90 -aGVyIGltcGxlbWVudGF0aW9uIGhhcyBiZWVuIHByb3Bvc2VkIGJ5IG15c2VsZiAoaHR0cHM6Ly9s -a21sLm9yZy9sa20NCmwvMjAxNi8xMi8yMi8zMjIpLg0KDQpCYXJ0Lg== +On Mon, 2017-01-02 at 12:06 +0100, Hannes Reinecke wrote: +> Hmm. But that would amount to implement yet another queuing mechanism +> within the driver/mmc subsystem, wouldn't it? +> +> Which is, incidentally, the same method the S/390 DASD driver uses +> nowadays; report an arbitrary queue depth to the block layer and queue +> all requests internally to better saturate the device. +> +> However I'd really like to get rid of this, and tweak the block layer to +> handle these cases. + +Hello Hannes, + +Such functionality will be added to the blk-mq core as part of the +initiative to add blk-mq I/O scheduling support. One implementation has been +proposed by Jens (http://git.kernel.dk/cgit/linux-block/log/?h=blk-mq-sched) +and another implementation has been proposed by myself (https://lkml.org/lkm +l/2016/12/22/322). + +Bart. diff --git a/a/content_digest b/N1/content_digest index e2f3764..c436b07 100644 --- a/a/content_digest +++ b/N1/content_digest @@ -20,20 +20,25 @@ " zhang.chunyan@linaro.org <zhang.chunyan@linaro.org>\0" "\00:1\0" "b\0" - "T24gTW9uLCAyMDE3LTAxLTAyIGF0IDEyOjA2ICswMTAwLCBIYW5uZXMgUmVpbmVja2Ugd3JvdGU6\n" - "DQo+IEhtbS4gQnV0IHRoYXQgd291bGQgYW1vdW50IHRvIGltcGxlbWVudCB5ZXQgYW5vdGhlciBx\n" - "dWV1aW5nIG1lY2hhbmlzbQ0KPiB3aXRoaW4gdGhlIGRyaXZlci9tbWMgc3Vic3lzdGVtLCB3b3Vs\n" - "ZG4ndCBpdD8NCj4gDQo+IFdoaWNoIGlzLCBpbmNpZGVudGFsbHksIHRoZSBzYW1lIG1ldGhvZCB0\n" - "aGUgUy8zOTAgREFTRCBkcml2ZXIgdXNlcw0KPiBub3dhZGF5czsgcmVwb3J0IGFuIGFyYml0cmFy\n" - "eSBxdWV1ZSBkZXB0aCB0byB0aGUgYmxvY2sgbGF5ZXIgYW5kIHF1ZXVlDQo+IGFsbCByZXF1ZXN0\n" - "cyBpbnRlcm5hbGx5IHRvIGJldHRlciBzYXR1cmF0ZSB0aGUgZGV2aWNlLg0KPiANCj4gSG93ZXZl\n" - "ciBJJ2QgcmVhbGx5IGxpa2UgdG8gZ2V0IHJpZCBvZiB0aGlzLCBhbmQgdHdlYWsgdGhlIGJsb2Nr\n" - "IGxheWVyIHRvDQo+IGhhbmRsZSB0aGVzZSBjYXNlcy4NCg0KSGVsbG8gSGFubmVzLA0KDQpTdWNo\n" - "IGZ1bmN0aW9uYWxpdHkgd2lsbCBiZSBhZGRlZCB0byB0aGUgYmxrLW1xIGNvcmUgYXMgcGFydCBv\n" - "ZiB0aGUNCmluaXRpYXRpdmUgdG8gYWRkIGJsay1tcSBJL08gc2NoZWR1bGluZyBzdXBwb3J0LiBP\n" - "bmUgaW1wbGVtZW50YXRpb24gaGFzIGJlZW4NCnByb3Bvc2VkIGJ5IEplbnMgKGh0dHA6Ly9naXQu\n" - "a2VybmVsLmRrL2NnaXQvbGludXgtYmxvY2svbG9nLz9oPWJsay1tcS1zY2hlZCkNCmFuZCBhbm90\n" - "aGVyIGltcGxlbWVudGF0aW9uIGhhcyBiZWVuIHByb3Bvc2VkIGJ5IG15c2VsZiAoaHR0cHM6Ly9s\n" - a21sLm9yZy9sa20NCmwvMjAxNi8xMi8yMi8zMjIpLg0KDQpCYXJ0Lg== + "On Mon, 2017-01-02 at 12:06 +0100, Hannes Reinecke wrote:\n" + "> Hmm. But that would amount to implement yet another queuing mechanism\n" + "> within the driver/mmc subsystem, wouldn't it?\n" + "> \n" + "> Which is, incidentally, the same method the S/390 DASD driver uses\n" + "> nowadays; report an arbitrary queue depth to the block layer and queue\n" + "> all requests internally to better saturate the device.\n" + "> \n" + "> However I'd really like to get rid of this, and tweak the block layer to\n" + "> handle these cases.\n" + "\n" + "Hello Hannes,\n" + "\n" + "Such functionality will be added to the blk-mq core as part of the\n" + "initiative to add blk-mq I/O scheduling support. One implementation has been\n" + "proposed by Jens (http://git.kernel.dk/cgit/linux-block/log/?h=blk-mq-sched)\n" + "and another implementation has been proposed by myself (https://lkml.org/lkm\n" + "l/2016/12/22/322).\n" + "\n" + Bart. -66f000f2c56fbae9bc941674da37463b36e02a9df3412b1b92b4fc91c8530346 +573e9cca17ed61005506a3a7974ded2052988d3186344211f6f84c404c3ffb11
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.