Swap pages per second in/out
I'm looking at the Munin report, under "Swap in/out - by day".
What is considered "good" when it comes to this section? I just migrated to a new server, and it's showing several times throughout the day that I'm either between 0 and -4.0, or between 0 and +3.0. I can't look at the stats on my old server (they have already aged out of Munin), but I don't remember it having ANY swap.
The CPU and RAM usage are well within normal limits. I have 4G of RAM, and "apps" usually stays between 1.6G and 3.0G. I also have two 2.4GHz CPUs, and the load usually stays between 0.4 and 0.5 (with a max today of 1.17 during peak hours).
With this hardware, should I be using swap at all? If not, what's causing it?
-
Do you have any type of RAID on the new server? Please provide the full output of: [QUOTE]free -mt
[QUOTE]cat /proc/cpuinfo
[QUOTE]lscpu
[QUOTE]sar -q
[QUOTE]sar -r
[QUOTE]iostat0 -
No, to my knowledge there's no RAID. Here is the output you requested. I'm doing this at 3:30am, when the traffic is typically the lowest; do you need it during peak hours, instead?: # free -mt total used free shared buffers cached Mem: 3881 3810 71 0 271 2206 -/+ buffers/cache: 1331 2549 Swap: 2047 121 1925 Total: 5928 3932 1996
# cat /proc/cpuinfo processor : 0 vendor_id : GenuineIntel cpu family : 6 model : 42 model name : Intel(R) Xeon(R) CPU E31270 @ 3.40GHz stepping : 7 cpu MHz : 3392.412 cache size : 8192 KB fpu : yes fpu_exception : yes cpuid level : 13 wp : yes flags : fpu de tsc msr pae cx8 sep cmov pat clflush mmx fxsr sse sse2 ss ht syscall nx lm rep_good aperfmperf unfair_spinlock pni pclmulqdq ssse3 cx16 pcid sse4_1 sse4_2 x2apic popcnt tsc_deadline_timer hypervisor lahf_lm arat epb pln pts dts bogomips : 6784.82 clflush size : 64 cache_alignment : 64 address sizes : 36 bits physical, 48 bits virtual power management: processor : 1 vendor_id : GenuineIntel cpu family : 6 model : 42 model name : Intel(R) Xeon(R) CPU E31270 @ 3.40GHz stepping : 7 cpu MHz : 3392.412 cache size : 8192 KB fpu : yes fpu_exception : yes cpuid level : 13 wp : yes flags : fpu de tsc msr pae cx8 sep cmov pat clflush mmx fxsr sse sse2 ss ht syscall nx lm rep_good aperfmperf unfair_spinlock pni pclmulqdq ssse3 cx16 pcid sse4_1 sse4_2 x2apic popcnt tsc_deadline_timer hypervisor lahf_lm arat epb pln pts dts bogomips : 6784.82 clflush size : 64 cache_alignment : 64 address sizes : 36 bits physical, 48 bits virtual power management:
# lscpu Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Byte Order: Little Endian CPU(s): 2 On-line CPU(s) list: 0,1 Thread(s) per core: 1 Core(s) per socket: 1 Socket(s): 2 NUMA node(s): 1 Vendor ID: GenuineIntel CPU family: 6 Model: 42 Stepping: 7 CPU MHz: 3392.412 BogoMIPS: 6784.82 Hypervisor vendor: Xen Virtualization type: para L1d cache: 32K L1i cache: 32K L2 cache: 256K L3 cache: 8192K NUMA node0 CPU(s): 0,1
# sar -q Linux 2.6.32-431.5.1.el6.x86_64 (server1.example.com) 03/26/2014 _x86_64_(2 CPU) 12:00:01 AM runq-sz plist-sz ldavg-1 ldavg-5 ldavg-15 12:10:01 AM 2 204 0.02 0.11 0.09 12:20:01 AM 2 197 0.21 0.14 0.10 12:30:01 AM 5 205 0.33 0.21 0.12 12:40:01 AM 2 198 0.07 0.15 0.13 12:50:01 AM 2 197 0.04 0.10 0.12 01:00:01 AM 3 218 0.07 0.10 0.10 01:10:01 AM 4 195 0.22 0.14 0.10 01:20:01 AM 2 196 0.15 0.16 0.12 01:30:01 AM 3 200 0.07 0.18 0.17 01:40:01 AM 2 212 0.19 0.21 0.18 01:50:01 AM 2 206 0.04 0.14 0.16 02:00:01 AM 3 202 0.12 0.13 0.15 02:10:01 AM 3 195 0.16 0.13 0.14 02:20:01 AM 2 198 0.08 0.14 0.15 02:30:01 AM 4 196 0.03 0.09 0.13 02:40:01 AM 2 196 0.03 0.04 0.08 02:50:01 AM 2 208 0.25 0.16 0.10 03:00:01 AM 3 190 0.12 0.14 0.09 03:10:01 AM 2 197 0.09 0.09 0.09 03:20:01 AM 2 188 0.25 0.15 0.10 03:30:01 AM 3 192 0.05 0.08 0.08 Average: 3 200 0.12 0.13 0.12
# sar -r 12:00:01 AM kbmemfree kbmemused %memused kbbuffers kbcached kbcommit %commi t 12:10:01 AM 117856 3856504 97.03 178260 2292152 1864560 30.7 1 12:20:01 AM 128532 3845828 96.77 180780 2298528 1727312 28.4 5 12:30:01 AM 110456 3863904 97.22 182816 2308996 1772864 29.2 0 12:40:01 AM 62140 3912220 98.44 185252 2352588 1705716 28.1 0 12:50:01 AM 66372 3907988 98.33 186092 2356304 1680684 27.6 8 01:00:01 AM 34952 3939408 99.12 188968 2328928 2035512 33.5 3 01:10:01 AM 116472 3857888 97.07 182364 2312368 1638760 26.9 9 01:20:01 AM 52800 3921560 98.67 184788 2370712 1692752 27.8 8 01:30:01 AM 53616 3920744 98.65 186752 2364744 1708268 28.1 4 01:40:01 AM 97264 3877096 97.55 176848 2326128 1922004 31.6 6 01:50:01 AM 79656 3894704 98.00 179012 2331968 1794340 29.5 6 02:00:01 AM 108632 3865728 97.27 178092 2313560 1762932 29.0 4 02:10:01 AM 127436 3846924 96.79 180128 2318684 1682480 27.7 1 02:20:01 AM 93912 3880448 97.64 181788 2328084 1722140 28.3 7 02:30:01 AM 83464 3890896 97.90 183540 2336868 1688508 27.8 1 02:40:01 AM 93792 3880568 97.64 185412 2340540 1687460 27.8 0 02:50:01 AM 42456 3931904 98.93 184364 2334248 1932212 31.8 3 03:00:01 AM 95196 3879164 97.60 184612 2344428 1609236 26.5 1 03:10:01 AM 90688 3883672 97.72 186528 2354392 1692308 27.8 8 03:20:01 AM 57448 3916912 98.55 279416 2271124 1530716 25.2 1 03:30:01 AM 53464 3920896 98.65 278072 2260352 1618000 26.6 5 Average: 84124 3890236 97.88 192090 2325986 1736608 28.6 1
# iostat avg-cpu: %user %nice %system %iowait %steal %idle 6.75 0.63 4.41 1.42 0.08 86.71 Device: tps Blk_read/s Blk_wrtn/s Blk_read Blk_wrtn xvdb 0.41 1.05 2.63 145852 366576 xvda 53.89 183.23 631.54 25501168 878956980 -
Hello :) I do not see any performance issues based on the output from "iostat" that you provided. Thank you. 0 -
For whatever reason, at around 8:50am EST today my disk latency, disk utilization, RAM, and CPU usage skyrocketed. I usually have a CPU load of around 0.5, and it's currently 77! I had made a few minor Exim changes through the WHM Basic Configuration editor, so I thought that might have been the culprit. I restored, and even turned off Exim entirely, with no change, so I guess that wasn't it. You can see exactly what I mean here: # sar -q Linux 2.6.32-431.5.1.el6.x86_64 (server1.example.com) 04/02/2014 _x86_64_(2 CPU) 12:00:01 AM runq-sz plist-sz ldavg-1 ldavg-5 ldavg-15 12:10:01 AM 1 200 0.06 0.17 0.17 12:20:01 AM 2 195 0.12 0.21 0.18 12:30:01 AM 4 195 0.06 0.17 0.17 12:40:01 AM 2 198 0.27 0.19 0.18 12:50:01 AM 2 206 0.21 0.19 0.18 01:00:01 AM 4 196 0.11 0.12 0.15 01:10:01 AM 2 194 0.01 0.13 0.16 01:20:01 AM 2 190 0.06 0.15 0.16 01:30:01 AM 3 189 0.06 0.14 0.16 01:40:01 AM 2 199 0.02 0.08 0.13 01:50:01 AM 2 197 0.25 0.13 0.10 02:00:01 AM 2 196 0.03 0.06 0.08 02:10:01 AM 3 202 0.15 0.12 0.09 02:20:01 AM 2 185 0.09 0.05 0.06 02:30:01 AM 4 191 0.18 0.08 0.04 02:40:01 AM 2 190 0.00 0.01 0.01 02:50:01 AM 2 191 0.03 0.03 0.00 03:00:01 AM 2 184 0.07 0.11 0.03 03:10:01 AM 2 187 0.19 0.16 0.10 03:20:01 AM 2 187 0.06 0.10 0.09 03:30:01 AM 3 183 0.02 0.08 0.08 03:40:02 AM 2 200 0.04 0.06 0.07 03:40:02 AM runq-sz plist-sz ldavg-1 ldavg-5 ldavg-15 03:50:01 AM 2 195 0.08 0.09 0.08 04:00:01 AM 3 193 0.07 0.20 0.17 04:10:01 AM 2 190 0.05 0.09 0.12 04:20:01 AM 2 200 0.42 0.32 0.20 04:30:01 AM 3 205 0.18 0.20 0.18 04:40:01 AM 2 192 0.16 0.21 0.18 04:50:01 AM 2 198 0.22 0.18 0.16 05:00:01 AM 2 192 0.16 0.16 0.15 05:10:01 AM 2 184 0.17 0.11 0.10 05:20:01 AM 2 186 0.18 0.11 0.09 05:30:01 AM 3 195 0.07 0.06 0.06 05:40:01 AM 2 194 0.12 0.14 0.11 05:50:01 AM 2 206 0.19 0.13 0.10 06:00:01 AM 3 201 0.04 0.12 0.10 06:10:01 AM 2 201 0.11 0.08 0.08 06:20:01 AM 4 213 0.06 0.12 0.10 06:30:01 AM 3 210 0.13 0.19 0.13 06:40:01 AM 2 206 0.24 0.22 0.17 06:50:01 AM 2 205 0.05 0.14 0.16 07:00:01 AM 2 210 0.17 0.19 0.18 07:10:01 AM 3 207 0.10 0.17 0.17 07:20:01 AM 2 228 0.41 0.27 0.20 07:20:01 AM runq-sz plist-sz ldavg-1 ldavg-5 ldavg-15 07:30:01 AM 2 212 0.23 0.18 0.17 07:40:01 AM 4 213 0.03 0.18 0.18 07:50:01 AM 2 231 0.18 0.24 0.20 08:00:01 AM 4 246 0.09 0.27 0.25 08:10:01 AM 2 231 0.48 0.28 0.22 08:20:01 AM 1 299 0.54 0.68 0.50 08:30:01 AM 5 241 0.80 1.16 0.90 08:40:01 AM 2 286 0.52 0.95 0.96 08:50:01 AM 2 255 10.68 7.60 3.85 09:00:01 AM 1 347 15.27 8.13 5.00 09:10:01 AM 2 224 5.09 5.79 5.44 09:20:01 AM 2 313 33.26 15.00 8.44 09:30:01 AM 2 289 13.55 25.06 19.79 09:40:01 AM 2 295 25.29 31.82 27.66 09:50:01 AM 1 312 37.19 28.17 26.51 10:00:01 AM 2 232 4.27 11.82 19.89 10:10:01 AM 2 267 11.29 8.02 13.50 10:20:01 AM 2 288 28.31 35.00 25.58 10:30:02 AM 3 222 2.95 9.96 17.47 10:40:02 AM 3 235 4.73 4.73 11.03 10:50:01 AM 3 215 1.26 4.04 8.30 11:00:01 AM 0 220 5.29 7.98 8.47 11:00:01 AM runq-sz plist-sz ldavg-1 ldavg-5 ldavg-15 11:10:01 AM 2 231 4.63 4.48 6.49 11:20:01 AM 2 309 73.26 54.97 27.27 11:30:01 AM 2 271 1.68 11.20 17.52 11:40:01 AM 3 244 5.08 5.15 11.27 11:50:01 AM 2 313 53.20 29.30 18.71 12:00:01 PM 2 223 1.43 10.97 16.00 12:10:01 PM 3 254 3.21 3.42 9.33 12:20:01 PM 2 232 3.04 2.55 6.05 12:30:01 PM 4 214 4.32 3.39 4.64 12:40:13 PM 5 313 27.70 24.75 14.27 12:50:01 PM 2 288 10.56 15.85 16.26 01:00:01 PM 3 216 1.05 3.70 9.50 01:10:01 PM 1 241 1.92 5.92 8.35 01:20:01 PM 2 316 54.19 34.36 18.99 01:30:01 PM 2 213 3.33 10.49 14.00 01:40:01 PM 3 234 4.86 4.99 9.14 01:50:01 PM 2 243 9.73 11.92 11.20 02:00:01 PM 2 220 5.78 8.41 9.21 02:10:01 PM 2 231 3.87 4.82 6.95 02:20:01 PM 2 224 4.76 4.61 5.62 02:30:01 PM 3 228 1.41 3.70 5.37 02:40:01 PM 3 252 3.10 4.01 4.60 02:40:01 PM runq-sz plist-sz ldavg-1 ldavg-5 ldavg-15 02:50:01 PM 2 231 3.07 3.79 4.53 03:00:03 PM 2 319 27.38 14.55 8.95 03:10:01 PM 2 226 4.17 8.28 9.53 03:20:01 PM 2 358 16.61 16.15 12.25 03:30:01 PM 2 293 30.77 39.20 26.62 03:40:01 PM 2 238 3.64 16.06 21.69 03:50:01 PM 2 249 11.61 24.09 23.27 04:00:03 PM 1 349 40.80 33.00 25.51 04:10:01 PM 2 289 24.49 26.66 24.34 Average: 2 231 6.72 6.78 6.36
Iostat doesn't look much different than when I first posted, though:# iostat Linux 2.6.32-431.5.1.el6.x86_64 (server1.example.com) 04/02/2014 _x86_64_(2 CPU) avg-cpu: %user %nice %system %iowait %steal %idle 5.89 0.63 3.92 2.66 0.07 86.84 Device: tps Blk_read/s Blk_wrtn/s Blk_read Blk_wrtn xvdb 0.27 1.24 1.02 976420 805592 xvda 48.77 169.81 557.79 134086558 440438298
In Munin, all of the graphs are super high. VMStat shows "I/O Sleep" at 9.52, where it's usually at 0. CPU Usage - iowait is at 149.2, and it's usually at 0.5. IO Service Time also had a major shift on the chart, but I don't know how to read or explain it; in Munin, the red line is usually stable halfway between 1e03 and 1e04, but now it is erratic and halfway between 1e06 and 1e07. Disk Utilization in Munin is usually at around 500m, but it's currently at 95.54 (not 95m, but 95; so, 200 times higher than usual). Disk Latency is usually around 180m, but is currently at 2.49. If it matters, I'm using WHM 11.42.0 (build 23). Any suggestions? Any changes to cPanel at 8:50am that could cause this?0 -
We think that this problem was hardware failure, not software, so this is all probably irrelevant now :-( Man, this has been a bad day... 0 -
[quote="GoWilkes, post: 1611182">We think that this problem was hardware failure, not software, so this is all probably irrelevant now :-(
Thank you for updating us with the outcome.0
Please sign in to leave a comment.
Comments
6 comments