aboutsummaryrefslogtreecommitdiff
path: root/note
diff options
context:
space:
mode:
Diffstat (limited to 'note')
-rw-r--r--note/memory_usage.txt57
-rw-r--r--note/security.txt2
-rw-r--r--note/weedfs.txt8
3 files changed, 33 insertions, 34 deletions
diff --git a/note/memory_usage.txt b/note/memory_usage.txt
index 821140ea2..0beb38558 100644
--- a/note/memory_usage.txt
+++ b/note/memory_usage.txt
@@ -3,44 +3,44 @@ Each volume has 25M index, so each cost 160MB memory
-Things happened when I use lots of threads ( almost 120 ) keeping read file from Weed-FS.
+Things happened when I use lots of threads ( almost 120 ) keeping read file from SeaweedFS.
But I'm not so familiar with linux so I can't tell you exactly what happened.
Next I'll show you things I know , if you need more info , contact me
-
-My weed-fs version is about 0.12
-
+
+My SeaweedFS version is about 0.12
+
1. top
-
+
top - 12:07:37 up 1 day, 3:17, 2 users, load average: 0.00, 0.00, 0.00
Tasks: 152 total, 1 running, 151 sleeping, 0 stopped, 0 zombie
Cpu(s): 0.0%us, 0.0%sy, 0.0%ni, 99.8%id, 0.1%wa, 0.0%hi, 0.0%si, 0.0%st
Mem: 16269880k total, 16192364k used, 77516k free, 58172k buffers
Swap: 2064376k total, 12324k used, 2052052k free, 2827520k cached
-
- PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
- 1499 root 20 0 11.6g 10g 1424 S 0.0 65.6 7:32.53 weedvolume
- 1498 root 20 0 3204m 2.1g 1428 S 0.0 13.5 4:36.59 weedvolume
- 1737 root 20 0 98868 4932 2920 S 0.0 0.0 0:00.56 sshd
- 1497 root 20 0 151m 4404 1152 S 0.0 0.0 1:21.40 weedmaster
- 1335 root 20 0 97816 3044 2896 S 0.0 0.0 0:00.76 sshd
-
-After system became steady , weedvolume used 65.6% memory .
-
+
+ PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
+ 1499 root 20 0 11.6g 10g 1424 S 0.0 65.6 7:32.53 weedvolume
+ 1498 root 20 0 3204m 2.1g 1428 S 0.0 13.5 4:36.59 weedvolume
+ 1737 root 20 0 98868 4932 2920 S 0.0 0.0 0:00.56 sshd
+ 1497 root 20 0 151m 4404 1152 S 0.0 0.0 1:21.40 weedmaster
+ 1335 root 20 0 97816 3044 2896 S 0.0 0.0 0:00.76 sshd
+
+After system became steady , weedvolume used 65.6% memory .
+
2. free -m
-
+
total used free shared buffers cached
Mem: 15888 15809 79 0 56 2758
-/+ buffers/cache: 12994 2894
Swap: 2015 12 2003
-
+
3. startup cmd
-
+
screen -d -m /opt/weed/weedmaster -mdir /data/weeddata/ > /data/logs/weed/master.log &
screen -d -m /opt/weed/weedvolume -volumes=0-64 -dir /data/weeddata/ -pulseSeconds=20 -publicUrl="x.y.z:9334" -port 9334 > /data/logs/weed/s01.log &
screen -d -m /opt/weed/weedvolume -volumes=65-107 -dir /data/weeddata/ -pulseSeconds=20 -publicUrl="x.y.z:9335" -port 9335 > /data/logs/weed/s02.log &
-
+
4. du -sh .
-
+
32G 0.dat
26M 0.idx
8.2G 100.dat
@@ -258,22 +258,21 @@ screen -d -m /opt/weed/weedvolume -volumes=65-107 -dir /data/weeddata/ -pulseSec
32G 9.dat
25M 9.idx
4.0K directory.seq
-
+
You can see the volume 1-64 is now full.
-
+
5. more log
-
+
see logs.zip
-
+
In messages you can see these lines: (Line 51095)
-
+
Sep 26 06:14:31 wedb-01 kernel: auditd: page allocation failure. order:0, mode:0x20
Sep 26 06:14:31 wedb-01 kernel: Pid: 1009, comm: auditd Not tainted 2.6.32-220.el6.x86_64 #1
Sep 26 06:14:31 wedb-01 kernel: Call Trace:
-
+
After those lines , the system deny any new network connect request
-
+
6. /dir/status
-
+
{"Machines":[{"Server":{"Url":"127.0.0.1:9335","PublicUrl":"x.y.z:9335"},"Volumes":[{"Id":106,"Size":8728909632},{"Id":66,"Size":8729852744},{"Id":90,"Size":8747834896},{"Id":103,"Size":8718106024},{"Id":87,"Size":8732133512},{"Id":96,"Size":8737251904},{"Id":80,"Size":8704130712},{"Id":77,"Size":8717989496},{"Id":70,"Size":8731474744},{"Id":94,"Size":8758656144},{"Id":107,"Size":8729599232},{"Id":67,"Size":8736848088},{"Id":91,"Size":8665847760},{"Id":100,"Size":8703272552},{"Id":84,"Size":8745121528},{"Id":97,"Size":8713031744},{"Id":81,"Size":8726088872},{"Id":74,"Size":8738588152},{"Id":71,"Size":8729349920},{"Id":95,"Size":8741526896},{"Id":104,"Size":8699374736},{"Id":88,"Size":8740362880},{"Id":101,"Size":8711832992},{"Id":85,"Size":8723479552},{"Id":78,"Size":8700345400},{"Id":75,"Size":8727796912},{"Id":68,"Size":8698607440},{"Id":92,"Size":8682683056},{"Id":105,"Size":8741226152},{"Id":65,"Size":8725365752},{"Id":89,"Size":8703062600},{"Id":98,"Size":8742331560},{"Id":82,"Size":8762554952},{"Id":79,"Size":8696300376},{"Id":72,"Size":8708217304},{"Id":69,"Size":8740268144},{"Id":93,"Size":8685060320},{"Id":102,"Size":8708695352},{"Id":86,"Size":8783247776},{"Id":99,"Size":8753463608},{"Id":83,"Size":8725963952},{"Id":76,"Size":8694693536},{"Id":73,"Size":8733560832}]},{"Server":{"Url":"127.0.0.1:9334","PublicUrl":"x.y.z:9334"},"Volumes":[{"Id":34,"Size":33415706800},{"Id":58,"Size":33569224784},{"Id":18,"Size":33474649968},{"Id":55,"Size":33542422680},{"Id":15,"Size":33517247576},{"Id":48,"Size":33574860328},{"Id":8,"Size":33511257144},{"Id":45,"Size":33463948408},{"Id":5,"Size":34317702920},{"Id":29,"Size":33465695776},{"Id":38,"Size":33553119624},{"Id":62,"Size":33448316736},{"Id":22,"Size":33566586296},{"Id":35,"Size":33493733728},{"Id":59,"Size":33498554904},{"Id":19,"Size":33493313784},{"Id":52,"Size":33552978448},{"Id":12,"Size":33505183752},{"Id":49,"Size":33603029896},{"Id":9,"Size":33515778064},{"Id":42,"Size":33500402248},{"Id":2,"Size":34223232992},{"Id":26,"Size":33526519600},{"Id":39,"Size":33580414336},{"Id":63,"Size":33476332456},{"Id":23,"Size":33543872592},{"Id":32,"Size":33515290168},{"Id":56,"Size":33499171184},{"Id":16,"Size":33556591168},{"Id":64,"Size":33495148616},{"Id":53,"Size":33467738560},{"Id":13,"Size":33596873960},{"Id":46,"Size":33508120448},{"Id":6,"Size":33417470256},{"Id":30,"Size":33532933992},{"Id":43,"Size":33591802008},{"Id":3,"Size":34270682080},{"Id":27,"Size":33525736944},{"Id":36,"Size":33443597824},{"Id":60,"Size":33427931336},{"Id":20,"Size":33499083096},{"Id":33,"Size":33531396280},{"Id":57,"Size":33578015104},{"Id":17,"Size":33510525480},{"Id":50,"Size":33503123704},{"Id":10,"Size":33502391608},{"Id":47,"Size":33521868568},{"Id":7,"Size":33497101664},{"Id":31,"Size":33426905232},{"Id":40,"Size":33472978696},{"Id":0,"Size":34337344304},{"Id":24,"Size":33550157192},{"Id":37,"Size":33477162720},{"Id":61,"Size":33537175080},{"Id":21,"Size":33517192456},{"Id":54,"Size":33480720288},{"Id":14,"Size":33513192896},{"Id":51,"Size":33531336080},{"Id":11,"Size":33562385088},{"Id":44,"Size":33554479104},{"Id":4,"Size":34333127520},{"Id":28,"Size":33510503000},{"Id":41,"Size":33574922928},{"Id":1,"Size":34307181368},{"Id":25,"Size":33542834568}]}],"Writers":[106,66,90,103,87,96,80,77,70,94,107,67,91,100,84,97,81,74,71,95,104,88,101,85,78,75,68,92,105,65,89,98,82,79,72,69,93,102,86,99,83,76,73,34,58,18,55,15,48,8,45,5,29,38,62,22,35,59,19,52,12,49,9,42,2,26,39,63,23,32,56,16,64,53,13,46,6,30,43,3,27,36,60,20,33,57,17,50,10,47,7,31,40,0,24,37,61,21,54,14,51,11,44,4,28,41,1,25],"FileIdSequence":110250000}
- \ No newline at end of file
diff --git a/note/security.txt b/note/security.txt
index c5482a569..59ac52bd2 100644
--- a/note/security.txt
+++ b/note/security.txt
@@ -1,4 +1,4 @@
-Design for Seaweed-FS security
+Design for SeaweedFS security
Design Objectives
Security can mean many different things. The original vision is that: if you have one machine lying around
diff --git a/note/weedfs.txt b/note/weedfs.txt
index d07ad9484..329bb5690 100644
--- a/note/weedfs.txt
+++ b/note/weedfs.txt
@@ -3,7 +3,7 @@ How to submit a content
1.c Create a hash value
1.d find a write logic volume id, and return [logic volume id, {physical volume ids}]
2. submit to physical volumes
-2.c
+2.c
generate the cookie
generate a unique id as key
choose the right altKey
@@ -26,7 +26,7 @@ How to retrieve a content
How to submit a content
-1. send bytes to weedfs, got <volume id, key uint64, cookie code>
+1. send bytes to SeaweedFS, got <volume id, key uint64, cookie code>
store <key uint64, volume id uint32, cookie code uint32, ext>, and other information
To read a content
@@ -40,7 +40,7 @@ The directory server
find a free logic volume id, start sending content to 3 machines
if all of them finishes, return <logic volume id, key, cookie code>
2.on read content
- based on logic volume id, pick a machine with less load,
+ based on logic volume id, pick a machine with less load,
return <machine id>
-
+