| /linux-6.15/tools/perf/Documentation/ |
| D | callchain-overhead-calculation.txt | 1 Overhead calculation
3 The CPU overhead can be shown in two columns as 'Children' and 'Self'
5 wall-clock overhead). The 'self' overhead is simply calculated by
8 'self' overhead values should be 100%.
10 The 'children' overhead is calculated by adding all period values of
11 the child functions so that it can show the total overhead of the
16 It might be confusing that the sum of all the 'children' overhead
18 'self' overhead of its child functions. But with this enabled, users
19 can find which function has the most overhead even if samples are
46 in the usual (self-overhead-only) output of perf report:
[all …]
|
| D | cpu-and-latency-overheads.txt | 8 Perf can measure overhead for both of these times (shown in 'overhead' and
11 Optimizing CPU overhead is useful to improve 'throughput', while optimizing
12 latency overhead is useful to improve 'latency'. It's important to understand
20 128 seconds of CPU time). The CPU overhead is: 'foo' - 6.6%, 'bar' - 93.4%.
21 While the latency overhead is: 'foo' - 90%, 'bar' - 10%. If we try to optimize
22 running time of the program looking at the (wrong in this case) CPU overhead,
26 By default, perf shows only CPU overhead. To show latency overhead, use
30 Overhead Latency Command
38 To sort by latency overhead, use 'perf report --latency':
41 Latency Overhead Command
[all …]
|
| D | perf-config.txt | 182 'top' means a overhead percentage which is more than 5%.
187 'medium' means a overhead percentage which has more than 0.5%.
190 'normal' means the rest of overhead percentages
385 But if this option is 'false', percent values for overhead are printed i.e.
422 This option control the way to calculate overhead of filtered entries -
426 Overhead Symbols
432 This is an original overhead and we'll filter out the first 'foo'
433 entry. The value of 'relative' would increase the overhead of 'bar'
435 current overhead (33.33%).
439 This option controls display of column headers (like 'Overhead' and 'Symbol')
[all …]
|
| D | perf-report.txt | 47 the overhead and latency columns. See --percentage for more info.
57 the overhead and latency columns. See --percentage for more info.
62 the overhead and latency columns. See --percentage for more info.
78 the overhead and latency columns. See --percentage for more info.
116 - overhead: CPU overhead percentage of sample.
117 - latency: latency (wall-clock) overhead percentage of sample.
119 - overhead_sys: CPU overhead percentage of sample running in system mode
120 - overhead_us: CPU overhead percentage of sample running in user mode
121 - overhead_guest_sys: CPU overhead percentage of sample running in system mode
123 - overhead_guest_us: CPU overhead percentage of sample running in user mode on
[all …]
|
| D | perf-top.txt | 134 local_weight, abort, in_tx, transaction, overhead, sample, period.
140 overhead, overhead_sys, overhead_us, overhead_children, sample and period.
155 percentage of the overhead column. See --percentage for more info.
159 percentage of the overhead column. See --percentage for more info.
163 percentage of the overhead column. See --percentage for more info.
199 enabled. See the `overhead calculation' section for more details.
216 Do not show entries which have an overhead under that percent.
220 Determine how to display the overhead percentage of filtered entries.
278 # Overhead Shared Object Symbol
290 # Overhead Shared Object / Symbol
[all …]
|
| /linux-6.15/tools/testing/selftests/powerpc/pmu/ebb/ |
| D | instruction_count_test.c | 26 uint64_t overhead, bool report) in do_count_loop() argument
46 expected = instructions + overhead; in do_count_loop()
51 printf("Looped for %lu instructions, overhead %lu\n", instructions, overhead); in do_count_loop()
72 uint64_t current, overhead; in determine_overhead() local
76 overhead = event->result.value; in determine_overhead()
81 if (current < overhead) { in determine_overhead()
82 printf("Replacing overhead %lu with %lu\n", overhead, current); in determine_overhead()
83 overhead = current; in determine_overhead()
87 return overhead; in determine_overhead()
112 uint64_t overhead; in instruction_count() local
[all …]
|
| /linux-6.15/tools/testing/selftests/powerpc/pmu/ |
| D | count_instructions.c | 30 u64 overhead, bool report) in do_count_loop() argument
45 expected = instructions + overhead; in do_count_loop()
53 printf("Looped for %llu instructions, overhead %llu\n", instructions, overhead); in do_count_loop()
76 u64 current, overhead; in determine_overhead() local
80 overhead = events[0].result.value; in determine_overhead()
85 if (current < overhead) { in determine_overhead()
86 printf("Replacing overhead %llu with %llu\n", overhead, current); in determine_overhead()
87 overhead = current; in determine_overhead()
91 return overhead; in determine_overhead()
97 u64 overhead; in test_body() local
[all …]
|
| D | count_stcx_fail.c | 30 u64 overhead, bool report) in do_count_loop() argument
47 expected = instructions + overhead + (events[2].result.value * 10); in do_count_loop()
57 printf("Looped for %llu instructions, overhead %llu\n", instructions, overhead); in do_count_loop()
81 u64 current, overhead; in determine_overhead() local
85 overhead = events[0].result.value; in determine_overhead()
90 if (current < overhead) { in determine_overhead()
91 printf("Replacing overhead %llu with %llu\n", overhead, current); in determine_overhead()
92 overhead = current; in determine_overhead()
96 return overhead; in determine_overhead()
105 u64 overhead; in test_body() local
[all …]
|
| /linux-6.15/tools/testing/selftests/tc-testing/tc-tests/qdiscs/ |
| D | cake.json | 17 …th unlimited diffserv3 triple-isolate nonat nowash no-ack-filter split-gso rtt 100ms raw overhead",
38 …dwidth 1Kbit diffserv3 triple-isolate nonat nowash no-ack-filter split-gso rtt 100ms raw overhead",
59 …rate-ingress diffserv3 triple-isolate nonat nowash no-ack-filter split-gso rtt 100ms raw overhead",
80 …th unlimited diffserv3 triple-isolate nonat nowash no-ack-filter split-gso rtt 200us raw overhead",
101 …h unlimited besteffort triple-isolate nonat nowash no-ack-filter split-gso rtt 100ms raw overhead",
122 …th unlimited diffserv8 triple-isolate nonat nowash no-ack-filter split-gso rtt 100ms raw overhead",
143 …th unlimited diffserv4 triple-isolate nonat nowash no-ack-filter split-gso rtt 100ms raw overhead",
164 …ndwidth unlimited diffserv3 flowblind nonat nowash no-ack-filter split-gso rtt 100ms raw overhead",
185 …+ bandwidth unlimited diffserv3 dsthost nat nowash no-ack-filter split-gso rtt 100ms raw overhead",
206 …9]+ bandwidth unlimited diffserv3 hosts nonat wash no-ack-filter split-gso rtt 100ms raw overhead",
[all …]
|
| /linux-6.15/drivers/net/fddi/skfp/ |
| D | ess.c | 100 static int process_bw_alloc(struct s_smc *smc, long int payload, long int overhead);
119 u_long payload, overhead ; in ess_raf_received_pack() local
257 overhead = ((struct smt_p_3210 *)p)->mib_overhead ; in ess_raf_received_pack()
259 DB_ESSN(2, "payload= %lx overhead= %lx", in ess_raf_received_pack()
260 payload, overhead); in ess_raf_received_pack()
265 (void)process_bw_alloc(smc,(long)payload,(long)overhead) ; in ess_raf_received_pack()
308 overhead = ((struct smt_p_3210 *)p)->mib_overhead ; in ess_raf_received_pack()
312 DB_ESSN(2, "payload= %lx overhead= %lx", in ess_raf_received_pack()
313 payload, overhead); in ess_raf_received_pack()
318 if(!process_bw_alloc(smc,(long)payload,(long)overhead)) in ess_raf_received_pack()
[all …]
|
| /linux-6.15/net/l2tp/ |
| D | l2tp_eth.c | 189 unsigned int overhead = 0; in l2tp_eth_adjust_mtu() local
195 overhead += sizeof(struct udphdr); in l2tp_eth_adjust_mtu()
204 /* L3 Overhead couldn't be identified, this could be in l2tp_eth_adjust_mtu()
211 /* Adjust MTU, factor overhead - underlay L3, overlay L2 hdr in l2tp_eth_adjust_mtu()
212 * UDP overhead, if any, was already factored in above. in l2tp_eth_adjust_mtu()
214 overhead += session->hdr_len + ETH_HLEN + l3_overhead; in l2tp_eth_adjust_mtu()
216 mtu = l2tp_tunnel_dst_mtu(tunnel) - overhead; in l2tp_eth_adjust_mtu()
218 dev->mtu = ETH_DATA_LEN - overhead; in l2tp_eth_adjust_mtu()
|
| /linux-6.15/net/sctp/ |
| D | output.c | 58 * current overhead after sending packets. in sctp_packet_reset()
60 packet->size = packet->overhead; in sctp_packet_reset()
88 /* set packet max_size with pathmtu, then calculate overhead */ in sctp_packet_config()
95 packet->overhead = sctp_mtu_payload(sp, 0, 0); in sctp_packet_config()
96 packet->size = packet->overhead; in sctp_packet_config()
154 /* The overhead will be calculated by sctp_packet_config() */ in sctp_packet_init()
155 packet->overhead = 0; in sctp_packet_init()
221 int overhead = 0; in sctp_packet_bundle_pad() local
227 overhead += sizeof(struct sctphdr) + sizeof(struct sctp_chunkhdr); in sctp_packet_bundle_pad()
228 overhead += sizeof(struct sctp_sender_hb_info) + sizeof(struct sctp_pad_chunk); in sctp_packet_bundle_pad()
[all …]
|
| /linux-6.15/drivers/net/wireless/ralink/rt2x00/ |
| D | rt2x00crypto.c | 68 unsigned int overhead = 0; in rt2x00crypto_tx_overhead() local
71 return overhead; in rt2x00crypto_tx_overhead()
78 overhead += key->icv_len; in rt2x00crypto_tx_overhead()
81 overhead += key->iv_len; in rt2x00crypto_tx_overhead()
85 overhead += 8; in rt2x00crypto_tx_overhead()
88 return overhead; in rt2x00crypto_tx_overhead()
|
| /linux-6.15/fs/freevxfs/ |
| D | vxfs_lookup.c | 84 int overhead = VXFS_DIRBLKOV(sbi, dbp); in vxfs_find_entry() local
86 pos += overhead; in vxfs_find_entry()
87 pg_ofs += overhead; in vxfs_find_entry()
234 int overhead = VXFS_DIRBLKOV(sbi, dbp); in vxfs_readdir() local
236 pos += overhead; in vxfs_readdir()
237 pg_ofs += overhead; in vxfs_readdir()
|
| /linux-6.15/kernel/trace/ |
| D | Kconfig | 150 Adds a very slight overhead to tracing when enabled.
226 (the bootup default), then the overhead of the instructions is very
360 then it will not have any overhead while the stack tracer
397 (Note that kernel size and overhead increase with this option
421 (Note that kernel size and overhead increase with this option
588 When this is enabled, this adds a little more overhead to the
593 and already adds the overhead (plus a lot more).
613 Either of the above profilers adds a bit of overhead to the system.
619 No branch profiling. Branch profiling adds a bit of overhead.
632 Note: this will add a significant overhead; only turn this
[all …]
|
| /linux-6.15/tools/testing/selftests/seccomp/ |
| D | seccomp_benchmark.c | 261 ESTIMATE("total seccomp overhead for 1 bitmapped filter", calc, in main()
263 ESTIMATE("total seccomp overhead for 2 bitmapped filters", calc, in main()
265 ESTIMATE("total seccomp overhead for 3 full filters", calc, in main()
267 ESTIMATE("total seccomp overhead for 4 full filters", calc, in main()
269 ESTIMATE("seccomp entry overhead", entry, in main()
271 ESTIMATE("seccomp per-filter overhead (last 2 diff)", per_filter1, in main()
273 ESTIMATE("seccomp per-filter overhead (filters / 4)", per_filter2, in main()
|
| /linux-6.15/kernel/rcu/ |
| D | Kconfig.debug | 66 These checks add overhead, and this Kconfig options is therefore
81 overhead, overhead that can make both failures and close calls
95 can be useful, but it does incur additional overhead, overhead
|
| /linux-6.15/Documentation/driver-api/mmc/ |
| D | mmc-async-req.rst | 8 How significant is the cache maintenance overhead?
11 pre-fetch makes the cache overhead relatively significant. If the DMA
13 transfer, the DMA preparation overhead would not affect the MMC performance.
75 Pseudocode to handle is_first_req scenario with minimal prepare overhead::
|
| /linux-6.15/drivers/net/ethernet/intel/libeth/ |
| D | rx.c | 57 * libeth_rx_page_pool_params - calculate params with the stack overhead
61 * Set the PP params to will all needed stack overhead (headroom, tailroom) and
99 * libeth_rx_page_pool_params_zc - calculate params without the stack overhead
103 * Set the PP params to exclude the stack overhead and both the buffer length
106 * overhead.
|
| /linux-6.15/drivers/net/fddi/skfp/h/ |
| D | smt.h | 485 * P18 : SBA Overhead Request
491 int sba_ov_req ; /* total sync bandwidth req for overhead*/
799 struct smt_p_3210 overhead ; /* current SBA overhead */ member
814 struct smt_p_0018 ov_req ; /* requested SBA overhead */
816 struct smt_p_3210 overhead ; /* current SBA overhead */ member
832 struct smt_p_3210 overhead ; /* current SBA overhead */ member
854 struct smt_p_3210 overhead ; /* current SBA overhead */ member
|
| /linux-6.15/fs/xfs/libxfs/ |
| D | xfs_trans_resv.c | 30 * A buffer has a format structure overhead in the log in addition
34 * reservation that has been used for this overhead.
252 * item logged to try to account for the overhead of the transaction mechanism.
496 unsigned int overhead = XFS_DQUOT_LOGRES; in xfs_calc_rename_reservation() local
527 * they become overhead added to each transaction in a in xfs_calc_rename_reservation()
535 overhead += max(rename_overhead, exchange_overhead); in xfs_calc_rename_reservation()
538 return overhead + max3(t1, t2, t3); in xfs_calc_rename_reservation()
607 unsigned int overhead = XFS_DQUOT_LOGRES; in xfs_calc_link_reservation() local
611 overhead += xfs_calc_iunlink_remove_reservation(mp); in xfs_calc_link_reservation()
620 overhead += xfs_calc_pptr_link_overhead(); in xfs_calc_link_reservation()
[all …]
|
| /linux-6.15/arch/riscv/ |
| D | Kconfig.errata | 11 Otherwise, please say "N" here to avoid unnecessary overhead.
32 Otherwise, please say "N" here to avoid unnecessary overhead.
83 Otherwise, please say "N" here to avoid unnecessary overhead.
|
| /linux-6.15/mm/ |
| D | Kconfig.debug | 35 By default this option will have a small overhead, e.g. by not
37 architectures. Even bigger overhead comes when the debugging is
174 kernel code. However the runtime performance overhead is virtually
255 feature will introduce an overhead to memory
309 overhead in the page fault path.
|
| /linux-6.15/drivers/media/platform/qcom/iris/ |
| D | iris_vpu3.c | 101 /* 21 / 20 is minimum overhead factor */ in iris_vpu3_calculate_frequency()
104 /* 1.059 is multi-pipe overhead */ in iris_vpu3_calculate_frequency()
110 /* VSP FW overhead 1.05 */ in iris_vpu3_calculate_frequency()
|
| /linux-6.15/include/net/sctp/ |
| D | sctp.h | 569 /* Calculate max payload size given a MTU, or the total overhead if
576 __u32 overhead = sizeof(struct sctphdr) + extra; in __sctp_mtu_payload() local
579 overhead += sp->pf->af->net_header_len; in __sctp_mtu_payload()
581 overhead += sizeof(struct udphdr); in __sctp_mtu_payload()
583 overhead += sizeof(struct ipv6hdr); in __sctp_mtu_payload()
586 if (WARN_ON_ONCE(mtu && mtu <= overhead)) in __sctp_mtu_payload()
587 mtu = overhead; in __sctp_mtu_payload()
589 return mtu ? mtu - overhead : overhead; in __sctp_mtu_payload()
|