diff for duplicates of <cover.1584728740.git.zhangweiping@didiglobal.com> diff --git a/a/content_digest b/N1/content_digest index 37605f6..8f66e0f 100644 --- a/a/content_digest +++ b/N1/content_digest @@ -1,10 +1,10 @@ "From\0Weiping Zhang <zhangweiping@didiglobal.com>\0" "Subject\0[RFC 0/3] blkcg: add blk-iotrack\0" "Date\0Sat, 21 Mar 2020 09:20:36 +0800\0" - "To\0axboe@kernel.dk" - " tj@kernel.org\0" - "Cc\0linux-block@vger.kernel.org" - " cgroups@vger.kernel.org\0" + "To\0<axboe@kernel.dk>" + " <tj@kernel.org>\0" + "Cc\0<linux-block@vger.kernel.org>" + " <cgroups@vger.kernel.org>\0" "\00:1\0" "b\0" "Hi all,\n" @@ -92,4 +92,4 @@ "-- \n" 2.18.1 -8f1c632c58298ca7462c6bb61dca13da6cebbe4bf4d900bdcc47caa96b2614c2 +e4e03e34cb84c13951a68bb0e37eecc45b8fbbfeb8ad435ba75547b54ac76300
diff --git a/a/1.txt b/N2/1.txt index 18cf7c2..1aafbc1 100644 --- a/a/1.txt +++ b/N2/1.txt @@ -32,36 +32,52 @@ policy. The user space tool, which called iotrack, used to collect these basic io statistics and then generate more valuable metrics at cgroup level. -From iotrack, you can get a cgroup's percentile for io, bytes, +From iotrack, you can get a cgroup's percentage for io(%io), bytes(%byte), total_time and disk_time of the whole disk. It can easily to evaluate the real weight of the weight based policy(bfq, blk-iocost). +Except the basic io/s, MB/s, iotrack also show: +%io There are lots of metrics for read and write generate by iotrack, for more details, please visit: https://github.com/dublio/iotrack. Test result for two fio with randread 4K, test1 cgroup bfq weight = 800 test2 cgroup bfq weight = 100 +numjobs=8, iodepth=32 -Device io/s MB/s %io %MB %tm %dtm %d2c %hit0 %hit1 %hit2 %hit3 %hit4 %hit5 %hit6 %hit7 cgroup -nvme1n1 44588.00 174.17 100.00 100.00 100.00 100.00 38.46 0.25 45.27 95.90 98.33 99.47 99.85 99.92 99.95 / -nvme1n1 30206.00 117.99 67.74 67.74 29.44 67.29 87.90 0.35 47.82 99.22 99.98 99.99 99.99 100.00 100.00 /test1 -nvme1n1 14370.00 56.13 32.23 32.23 70.55 32.69 17.82 0.03 39.89 88.92 94.88 98.37 99.53 99.77 99.85 /test2 +Device rrqm/s wrqm/s r/s w/s rMB/s wMB/s avgrqkb avgqu-sz await r_await w_await svctm %util conc +nvme1n1 0 0 217341 0 848.98 0.00 4.00 475.03 2.28 2.28 0.00 0.00 100.20 474.08 + +Device io/s MB/s %io %byte %tm %dtm %d2c ad2c aq2c %hit0 %hit1 %hit2 %hit3 %hit4 %hit5 %hit6 %hit7 cgroup +nvme1n1 217345 849.00 100.00 100.00 100.00 100.00 4.09 0.09 2.28 23.97 62.43 89.88 98.44 99.88 99.88 99.88 99.88 / +nvme1n1 193183 754.62 88.88 88.88 45.91 84.54 7.52 0.09 1.18 26.85 64.87 90.71 98.40 99.88 99.88 99.88 99.88 /test1 +nvme1n1 24235 94.67 11.15 11.15 54.09 15.48 1.17 0.13 11.06 0.98 43.00 83.31 98.77 99.87 99.87 99.87 99.87 /test2 * The root block cgroup "/" shows the io statistics for whole ssd disk. -* test1 use disk's %67 iops and bps. +* test1 use disk's 88% iops and bps. -* %dtm stands for the on disk time, test1 cgroup get 67% of whole disk, +* %dtm stands for the on disk time, test1 cgroup get 85% of whole disk, that means test1 gets more disk time than test2. -* For test's %d2c, there is only 17% latency cost at hardware disk, +* For test's %d2c, there is only 1.17% latency cost at hardware disk, that means the main latency cames from software, it was throttled by softwre. +* aq2c: average q2c, test2's aq2c(11ms) > test1's aq2c(1ms). + +* For latency distribution, hit1(<=100us), 64% io of test1 <=100us, and + 43% io of test2 <=100us, test1's latency is better than test2. + +For more detail test report, please visit: +https://github.com/dublio/iotrack/wiki/cgroup-io-weight-test The patch1 and patch2 are preapre patch. The last patch implement blk-iotrack. +Changes since v1: +* fix bio issue_size when split bio, v1 patch will clear issue_time. + Weiping Zhang (3): update the real issue size when bio_split bio: track timestamp of submitting bio the disk driver diff --git a/a/content_digest b/N2/content_digest index 37605f6..31d03e3 100644 --- a/a/content_digest +++ b/N2/content_digest @@ -1,10 +1,10 @@ "From\0Weiping Zhang <zhangweiping@didiglobal.com>\0" - "Subject\0[RFC 0/3] blkcg: add blk-iotrack\0" - "Date\0Sat, 21 Mar 2020 09:20:36 +0800\0" - "To\0axboe@kernel.dk" - " tj@kernel.org\0" - "Cc\0linux-block@vger.kernel.org" - " cgroups@vger.kernel.org\0" + "Subject\0[RFC PATCH v2 0/3] blkcg: add blk-iotrack\0" + "Date\0Fri, 27 Mar 2020 14:27:13 +0800\0" + "To\0<axboe@kernel.dk>" + " <tj@kernel.org>\0" + "Cc\0<linux-block@vger.kernel.org>" + " <cgroups@vger.kernel.org>\0" "\00:1\0" "b\0" "Hi all,\n" @@ -41,36 +41,52 @@ "\n" "The user space tool, which called iotrack, used to collect these basic\n" "io statistics and then generate more valuable metrics at cgroup level.\n" - "From iotrack, you can get a cgroup's percentile for io, bytes,\n" + "From iotrack, you can get a cgroup's percentage for io(%io), bytes(%byte),\n" "total_time and disk_time of the whole disk. It can easily to evaluate\n" "the real weight of the weight based policy(bfq, blk-iocost).\n" + "Except the basic io/s, MB/s, iotrack also show:\n" + "%io\n" "There are lots of metrics for read and write generate by iotrack,\n" "for more details, please visit: https://github.com/dublio/iotrack.\n" "\n" "Test result for two fio with randread 4K,\n" "test1 cgroup bfq weight = 800\n" "test2 cgroup bfq weight = 100\n" + "numjobs=8, iodepth=32\n" "\n" - "Device io/s MB/s %io %MB %tm %dtm %d2c %hit0 %hit1 %hit2 %hit3 %hit4 %hit5 %hit6 %hit7 cgroup\n" - "nvme1n1 44588.00 174.17 100.00 100.00 100.00 100.00 38.46 0.25 45.27 95.90 98.33 99.47 99.85 99.92 99.95 /\n" - "nvme1n1 30206.00 117.99 67.74 67.74 29.44 67.29 87.90 0.35 47.82 99.22 99.98 99.99 99.99 100.00 100.00 /test1\n" - "nvme1n1 14370.00 56.13 32.23 32.23 70.55 32.69 17.82 0.03 39.89 88.92 94.88 98.37 99.53 99.77 99.85 /test2\n" + "Device rrqm/s wrqm/s r/s w/s rMB/s wMB/s avgrqkb avgqu-sz await r_await w_await svctm %util conc\n" + "nvme1n1 0 0 217341 0 848.98 0.00 4.00 475.03 2.28 2.28 0.00 0.00 100.20 474.08\n" + "\n" + "Device io/s MB/s %io %byte %tm %dtm %d2c ad2c aq2c %hit0 %hit1 %hit2 %hit3 %hit4 %hit5 %hit6 %hit7 cgroup\n" + "nvme1n1 217345 849.00 100.00 100.00 100.00 100.00 4.09 0.09 2.28 23.97 62.43 89.88 98.44 99.88 99.88 99.88 99.88 /\n" + "nvme1n1 193183 754.62 88.88 88.88 45.91 84.54 7.52 0.09 1.18 26.85 64.87 90.71 98.40 99.88 99.88 99.88 99.88 /test1\n" + "nvme1n1 24235 94.67 11.15 11.15 54.09 15.48 1.17 0.13 11.06 0.98 43.00 83.31 98.77 99.87 99.87 99.87 99.87 /test2\n" "\n" "* The root block cgroup \"/\" shows the io statistics for whole ssd disk.\n" "\n" - "* test1 use disk's %67 iops and bps.\n" + "* test1 use disk's 88% iops and bps.\n" "\n" - "* %dtm stands for the on disk time, test1 cgroup get 67% of whole disk,\n" + "* %dtm stands for the on disk time, test1 cgroup get 85% of whole disk,\n" "\tthat means test1 gets more disk time than test2.\n" "\n" - "* For test's %d2c, there is only 17% latency cost at hardware disk,\n" + "* For test's %d2c, there is only 1.17% latency cost at hardware disk,\n" "\tthat means the main latency cames from software, it was\n" "\tthrottled by softwre.\n" "\n" + "* aq2c: average q2c, test2's aq2c(11ms) > test1's aq2c(1ms).\n" + "\n" + "* For latency distribution, hit1(<=100us), 64% io of test1 <=100us, and\n" + " 43% io of test2 <=100us, test1's latency is better than test2.\n" + "\n" + "For more detail test report, please visit:\n" + "https://github.com/dublio/iotrack/wiki/cgroup-io-weight-test\n" "\n" "The patch1 and patch2 are preapre patch.\n" "The last patch implement blk-iotrack.\n" "\n" + "Changes since v1:\n" + "* fix bio issue_size when split bio, v1 patch will clear issue_time.\n" + "\n" "Weiping Zhang (3):\n" " update the real issue size when bio_split\n" " bio: track timestamp of submitting bio the disk driver\n" @@ -92,4 +108,4 @@ "-- \n" 2.18.1 -8f1c632c58298ca7462c6bb61dca13da6cebbe4bf4d900bdcc47caa96b2614c2 +f04ed1746fc455d3ebfb63a3ac70fde94d28e6c8845548fc61a2426e634fcac5
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.